resistant hypertension case study

Log in using your username and password

• Search More Search for this keyword Advanced search
• Latest content
• Current issue
• Browse by collection
• BMJ Journals More You are viewing from: Google Indexer

You are here

• Online First
• Diagnosis and management of resistant hypertension
• Article Text
• Article info
• Citation Tools
• Rapid Responses
• Article metrics

• http://orcid.org/0000-0002-8669-6410 Miguel Camafort 1 , 2 ,
• Reinhold Kreutz 3 , 4 ,
• Myeong-Chan Cho 5
• 1 Hypertensión Unit. Internal Medicine Department , Hospital Clinic de Barcelona , Barcelona , Spain
• 2 CIBEROBN , Instituto de Salud Carlos III , Madrid , Spain
• 3 Charite Medical Faculty Berlin , Berlin , Germany
• 4 Institut für Klinische Pharmakologie und Toxikologie , Berlin Institute of Health at Charite , Berlin , Germany
• 5 Cardiology , Chungbuk National University Hospital , Cheongju , Korea
• Correspondence to Dr Miguel Camafort, Internal Medicine, Hospital Clinic de Barcelona, Barcelona, Catalunya 08036, Spain; camafort{at}clinic.cat

Resistant hypertension is a condition where blood pressure levels remain elevated above target despite changes in lifestyle and concurrent use of at least three antihypertensive agents, including a long-acting calcium channel blocker (CCB), a blocker of the renin-angiotensin system (ACE inhibitor or angiotensin receptor blocker) and a diuretic. To be diagnosed as resistant hypertension, maintaining adherence to therapy is required along with confirmation of blood pressure levels above target by out-of-office blood pressure measurements and exclusion of secondary causes of hypertension. The key management points of this condition include lifestyle changes such as reduced sodium and alcohol intake, regular physical activity, weight loss and discontinuation of substances that can interfere with blood pressure control. It is also recommended that current treatment be rationalised, including single pill combination treatment where antihypertensive drugs should be provided at the maximum tolerated dose. It is further recommended that current drugs be replaced with a more appropriate and less difficult treatment regimen based on the patient’s age, ethnicity, comorbidities and risk of drug–drug interactions. The fourth line of treatment for patients with resistant hypertension should include mineralocorticoid receptor antagonists such as spironolactone, as demonstrated in the PATHWAY-2 trial and meta-analyses. Alternatives to spironolactone include amiloride, doxazosin, eplerenone, clonidine and beta-blockers, as well as any other antihypertensive drugs not already in use. New approaches under research are selective non-steroidal mineralocorticoid receptor antagonists such as finerenone, esaxerenone and ocedurenone, selective aldosterone synthase inhibitors such as baxdrostat, and dual endothelin antagonist aprocitentan.

• hypertension
• pharmacology

https://doi.org/10.1136/heartjnl-2022-321730

Statistics from Altmetric.com

Request permissions.

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Learning objectives

To fully understand resistant hypertension's definition, prevalence, and prognosis.

To discuss the procedures for conducting an effective resistant hypertension diagnostic.

To examine the available alternatives for treating resistant hypertension, including pharmaceutical treatment, surgical intervention, and lifestyle advice.

Introduction

Cardiovascular diseases (CVD) represent a global burden due to the high number of deaths and disabilities they cause. One of the major risk factors for CVD is hypertension. Hypertension is associated with a higher probability of sudden death, cardiovascular (CV) and all-cause mortality, ischaemic heart disease, heart failure (HF), atrial fibrillation, stroke, chronic kidney disease (CKD), cognitive dysfunction, dementia and peripheral artery disease. 1

In the 2017 American College of Cardiology (ACC)/American Heart Association (AHA) guideline for the prevention, detection, evaluation and management of high blood pressure in adults, stage 1 hypertension was defined as systolic blood pressure (SBP) values above 130 mm Hg and below 139 mm Hg, or diastolic blood pressure (DBP) values above 80 mm Hg and below 89 mm Hg, as these values are related to a higher probability of mortality and disability due to CVD and also to an increased risk of cognitive impairment and dementia. 2 Antihypertensive drug therapy has been shown to prevent its development by lowering blood pressure (BP) in patients with hypertension. Lifestyle modifications are also crucial to lowering BP and preventing the onset of newly diagnosed hypertension. Therefore, international guidelines have established BP goals to determine when BP is under control in order to efficiently reduce CVD risk. 3–5 Nevertheless, despite initiation of lifestyle modifications and treatment, some patients have BP values that remain above the recommended goals. This condition could raise the suspicion for resistant hypertension (RHT), related by itself to a higher risk of developing CVD than the usual hypertension. 6 It is essential to remember the precise definition of this condition to ensure rapid identification, proper diagnosis and management.

In this review, we will cover the definition, prevalence, aetiology, damage to target organs, CV consequences, patient evaluation and therapy for RHT. However, it is crucial to bear in mind that a substantial portion of research on RHT was based on observational studies, and that except for a few recent randomised controlled trials (RCTs) there are actually little reliable data. This paper will focus on recent developments while still upholding the value of commonly recognised information.

Definition of RHT

As one of the main criteria for RHT is having BP levels above target, we might observe slight differences in the available definitions for RHT in the latest published guidelines. In the 2017 AHA/ACC, 2018 European Society of Hypertension (ESH/European Society of Cardiology) and 2020 International Society of Hypertension hypertension guidelines, the goals to consider BP as controlled are SBP levels below 140 mm Hg in European and international guidelines and below 130 mm Hg in North American guidelines. The goals for DBP are below 90 mm Hg in European and international guidelines and below 80 mm Hg in North American guidelines. 3–5

The 2018 AHA scientific statement on detection, evaluation and management of resistant hypertension defines RHT as the condition where the BP values of a patient with hypertension remain elevated above target despite concurrent use of three antihypertensive agents of different classes, commonly including a long-acting CCB, a renin-angiotensin system (RAS) blocker (an ACE inhibitor or angiotensin receptor blocker) and a diuretic. All agents should be administered at maximum or maximally tolerated doses and at the appropriate dosing frequency. Patients with the white coat effect should not be included in the definition of RHT, and the diagnosis of RHT requires the exclusion of non-adherence to antihypertensive medications. Finally, this position paper also includes patients with RHT whose BP shows values below target but are on four or more antihypertensive medications, a condition that has been referred to in the literature as controlled RHT. 7

In the 2023 ESH guidelines, RHT is defined as hypertension in patients who fail to lower office BP to ESH treatment goals (BP levels below <140/90 mm Hg) once appropriate lifestyle measures and treatment with optimal or best tolerated doses of three or more drugs (specifying a thiazide/thiazide-like diuretic, an RAS blocker and a CCB) have been initiated. The ESH guidelines also specify that inadequate BP control should be confirmed by out-of-office BP measurements showing uncontrolled 24-hour BP (130 mm Hg SBP or 80 mm Hg DBP) values. Evidence of adherence to therapy and exclusion of secondary causes of hypertension are required to define RHT, otherwise RHT is only apparent and called pseudo-RHT. 8

The guidelines therefore recommend thoroughly confirming uncontrolled office BP values through measurement of BP values outside of the office as ambulatory BP measurement (ABPM) or home BP measurement (HBPM), confirming adherence to therapy and properly ruling out secondary causes of hypertension when RHT is suspected in order to have a case of true RHT . Pseudo-RHT is the condition where office BP shows lack of BP control, while ABPM or HBPM shows well-controlled BP. Nevertheless, if obtaining ABPM or HBPM is not feasible, epidemiological studies refer to this condition as apparent RHT . On the other hand, in some patients, office BP values are below target, showing good control, but ABPM or HBPM values are clearly showing lack of BP control. This condition is called masked RHT . 9 Finally, refractory HT is a type of RHT where BP remains uncontrolled despite being on five or more antihypertensive drug classes, including a diuretic.

Epidemiology of RHT

It is difficult to learn the actual prevalence of RHT due to several reasons. First, the prevalence of RHT depends on the BP levels used to define BP control in the various guidelines. 3–5 Moreover, although the guidelines clearly establish how to rule out pseudo-resistance, population studies do not always exclude it. 3–5 For example, Noubiap et al 10 conducted a meta-analysis of 91 studies reporting data of a pooled sample of 3 207 911 patients with hypertension on antihypertensive drugs globally to estimate the global prevalence of RHT. Nevertheless, the first limitation was that 64% of the studies only used office BP measurement. They found a prevalence of apparent treatment resistance of 14.7%, but only 10.3% for true RHT. True RHT was found in 22.9% of patients with CKD, 56.0% of renal transplant recipients and 12.3% of geriatric individuals. Another recent study found that in Canada 5.3% of subjects with hypertension had apparent RHT. The majority were female and aged 70 or older (45.3%). 11

As for the evolution of prevalence over time, according to a longitudinal study from the UK (1996–2004), the incidence of RHT among patients with hypertension increased from 0.93 per 100 patient-years to 2.07 per 100 patient-years. 12 Finally, selection bias is usually present in registries and clinical trials and therefore could explain the higher prevalence of apparent RHT.

Outcomes of RHT

According to observational studies, people with RHT are more likely to have adverse CV outcomes than those without RHT. In a retrospective analysis of 6357 adult participants with hypertension in the National Health and Nutrition Examination Survey, those with RHT had a 47% higher risk of mortality, myocardial infarction, HF, stroke or CKD after a median follow-up of 3.8 years. 13 Another study using data from subjects with hypertension from Kaiser Permanente Southern California Health Care compared the risk of renal, CV and mortality outcomes among individuals identified with controlled RHT, uncontrolled RHT and non-RHT. They found that those with RHT had a 32% higher possibility of acquiring end-stage renal disease, a 24% higher risk of an ischaemic cardiac event, a 46% higher risk of HF and a 24% higher risk of an ischaemic stroke. 14

Diagnosis of RHT

For an accurate and proper diagnosis of true RHT following major guideline recommendations, it is recommended to take the steps that are summarised in figure 1 .

• Download figure
• Open in new tab
• Download powerpoint

Diagnostic algorithm proposal for resistant hypertension. BP, blood pressure; CKD, chronic kidney disease.

As a first step, the causes of pseudo-RHT must be ruled out, which are summarised in table 1 . Pseudo-RHT may be due to errors in BP measurement. For instance, the patient’s preparation, the office’s milieu, wrong cuff size and improper BP measurement methodology can significantly affect measurements. 15

• View inline

Causes of pseudo-resistant hypertension

Beside accurate office BP measurement, home, work or ambulatory BP readings should always be obtained to exclude the white coat effect, 4 which could occur in 30% of patients with elevated BP and with treatment of up to three drugs. 16 Particularly for office BP measurements and due to intrinsic BP fluctuations, diagnostic BP records should comprise an average of at least two measurements taken on at least two different dates. As for out-of-office BP measurement, either an HBPM or a 24-hour ABPM is recommended. 17

Before diagnosing RHT, non-adherence to prescribed antihypertensive drugs also has to be ruled out. Patients with pseudo-RH have a high prevalence of non-adherence as some patients are reluctant or unable to adhere to their antihypertensive medications. 18 While the WHO estimates the prevalence of non-adherence to antihypertensive medication at between 30% and 50%, 19 the estimated prevalence of non-adherence to antihypertensive medication in Asia is 48%. 20 Significant pill burden, complicated dosing, high cost, high frequency of adverse reactions with multidrug antihypertensive regimens and poor patient–clinician relationships are all factors that contribute to non-adherence, causing pseudo-RHT. Direct observed therapy clinic can be an effective method for identifying the patient with truly resistant hypertension. 18 Medication non-adherence is a significant problem in a patient with apparent RHT. Identifying the most accurate and clinically feasible adherence assessment methods is necessary to reduce BP and CV morbidity, facilitate early behavioural intervention, prevent unnecessary diagnostic testing, and limit the sometimes unnecessary and expensive BP-lowering procedures. 21

Finally, it is mandatory to discontinue or minimise interfering substances such as steroidal and non-steroidal anti-inflammatory drugs, and sympathomimetic drugs such as amphetamines, decongestants, stimulants, oral contraceptives, licorice and Ephedra , which can increase BP. 4

Once pseudo-RHT has been ruled out, it is mandatory to also rule out secondary hypertension, as these patients usually show an RHT clinical picture. As can be seen in table 2 , the frequent causes of secondary hypertension are primary hyperaldosteronism, pheochromocytoma, obstructive sleep apnoea (OSA), renal artery stenosis and renal parenchymal disease, while the less frequent causes are Cushing’s syndrome, thyroid and parathyroid diseases, and fibromuscular dysplasia. Although secondary hypertension might present frequently as RHT, its diagnosis, treatment and outcomes are completely different and therefore it needs to be ruled out before establishing a diagnosis of RHT. 16 The most relevant and frequent secondary hypertension causes that have to be considered are primary aldosteronism in patients with an elevated aldosterone to renin ratio; CKD when the estimated glomerular filtration ratio (eGFR) is <60 mL/min/1.73 m 2 ; renal artery stenosis in young female patients, or known atherosclerotic disease with worsening kidney function; and OSA in patients with snoring, witnessed apnoea and excessive daytime sleepiness. As for the less frequent causes, fibrodysplasia can be considered in young female patients with hypertension, and pheochromocytoma in patients with episodic hypertension, palpitations, diaphoresis and headache. 4

Causes of secondary hypertension

RHT treatment should involve lifestyle changes, including reduced sodium and alcohol intake, regular physical activity, weight loss as shown by the TRIUMPH RCT (Lifestyle Interventions in Treatment-Resistant Hypertension) and discontinuation of interfering substances 4 22 ; however, current treatment should also be rationalised, accompanied by sequential addition of antihypertensive drugs to triple therapy. 4 8 23

In addition to lifestyle recommendations, a specific pharmacological treatment strategy is suggested ( figure 2 ).

Treatment algorithm proposal for resistant hypertension.

The algorithm in the 2023 ESH guidelines recommends the use of single pill combination (SPC) treatment as the basis. Replacing current drugs with a more appropriate and less difficult treatment regimen based on the patient’s age, ethnicity, compelling grounds for certain medication classes, comorbidities and risk of drug–drug interactions is recommended. Drugs should be provided at the maximum tolerated dose and in SPCs to improve adherence to therapy. It is also recommended to increase the thiazide diuretic dose or switch to a longer-acting thiazide-like diuretic. If the eGFR is less than 30 mL/min, administer loop diuretics instead of thiazide/thiazide-like diuretics. Nevertheless, the CLICK (Chlorthalidone in Chronic Kidney Disease) trial found chlortalidone reduced the 24-hour SBP in patients with stage 4 CKD with poorly controlled hypertension. 24 Furosemide and bumetanide should be given two times per day due to their short duration, while longer-lasting drugs such as torsemide can be given once daily. Severe CKD and albuminuria may require increased loop diuretic doses. Monitoring kidney function, electrolyte levels and fluid status is crucial to detect dehydration, hypokalaemia, hyponatraemia, hypovolaemia or worsening renal function. 8

The fourth line of treatment for patients with RHT should include the mineralocorticoid receptor antagonist (MRA) spironolactone, as demonstrated in the PATHWAY-2 (spironolactone versus placebo, bisoprolol, and doxazosin to determine the optimal treatment for drug-resistant hypertension) trial and meta-analyses, including those with heart failure with reduced ejection faction (HFrEF). A secondary analysis of the TOPCAT (Aldosterone Antagonist Therapy for Adults With Heart Failure and Preserved Systolic Function) trial showed beneficial effects in patients with heart failure with preserved ejection faction (HFpEF), a condition with difficult-to-control hypertension. The efficacy and safety of spironolactone in patients with advanced CKD or higher potassium levels at baseline have not been established. The risk of hyperkalaemia is greater in patients with CKD, especially if the drug is added to a treatment regimen that usually includes an RAS blocker. It is necessary to closely monitor plasma potassium and eGFR after treatment initiation and at least annually or at 3-month to 6-month intervals thereafter. Newer potassium binders such as patiromer and sodium zirconium cyclosilicate can reduce the risk of hyperkalaemia without increasing sodium overload or decreasing antihypertensive drug absorption. 25

Spironolactone is not suitable for all patients due to its antiandrogenic side effects, such as breast tenderness, gynecomastia, sexual impotence and menstrual irregularities. Eplerenone, a less potent alternative, can lower BP but is only approved for patients with hypertension in some European countries. Amiloride can be used at high doses. New, selective non-steroidal MRAs such as finerenone, esaxerenone and ocedurenone may provide future alternatives to spironolactone for patients with RHT. Selective aldosterone synthase inhibitors such as baxdrostat have been shown to effectively lower BP in patients with RHT, potentially becoming an additional treatment. 26 Spironolactone and other MRAs should be used cautiously in patients with reduced eGFR and baseline potassium levels above 4.5 mmol/L. Alternatives include bisoprolol, doxazosin extended release or alpha-adrenergic receptor agonists such as clonidine. However, bisoprolol and doxazosin reduced BP less effectively than spironolactone in the PATHWAY-2 trial, while clonidine showed similar BP-lowering effects in a head-to-head comparison open-label RCT. 27 The dual endothelin antagonist aprocitentan may also be used as it has a sustained BP-lowering effect in patients with RHT. 23

Recent RCTs have demonstrated that endovascular renal denervation (RDN) can significantly reduce BP in patients with uncontrolled hypertension. In a large registry of patients with RDN, BP reduction was long-lasting and without significant safety problems. RDN can be proposed as an adjunctive therapy for patients with RHT, provided the eGFR is >40 mL/min/1.73 m 2 , where BP control cannot be achieved or serious side effects cannot be avoided with antihypertensive medications. However, dedicated trials such as PATHWAY-2 and ReHOT (Resistant Hypertension Optimal Treatment) showed short-term efficacy, with a large fraction of patients still not controlled after treatment with spironolactone. Therefore, as for device therapy, more specific studies are needed before any device-based antihypertensive treatment can be generalised into routine clinical practice. Until then, the use of these devices should be limited to specialised centres. A more detailed view of these trials is shown in table 3 .

Summary of the newest trials in RHT

Treatment for RHT considers patients’ frequent comorbidities, and additional treatment options are also offered. Continuous positive airway pressure (CPAP) may be beneficial in patients with OSA, while glucagon-like peptide-1 (GLP1) receptor agonists can reduce body weight and improve CV prognosis in obese patients. Bariatric surgery can lower BP, CV risk factors and CV events in severely obese patients. Sodium-glucose transport protein 2 (SGLT2) inhibitors may add a moderate BP-lowering effect to background antihypertensive therapy. The sacubitril–valsartan combination did not lower hospitalisation for HF and death in patients with HFpEF but significantly reduced the New York Heart Association (NYHA) class. It also reduced BP in patients with RHT despite treatment with four antihypertensive drugs, confirming the BP-lowering effect of the compound in a phase II trial. 28 The use of SPC treatment is the basis for replacing current drugs with a more appropriate and less difficult treatment regimen based on the patient’s age, ethnicity, compelling grounds for certain medication classes, comorbidities and risk of drug–drug interactions.

According to the AHA/ACC recommendations, diuretic medications should be intensified in RHT and an MRA should also be added. Additionally, other available drugs with a different mechanism of action should be considered. Finally, the guidelines urge patients with CKD and/or those treated with powerful vasodilators to use loop diuretics to reduce BP. 4

The AHA scientific statement on RHT also points to some specific issues that are associated with treatment resistance and recommends some management considerations. If patients present issues related to volume control and need resolution of oedema, a switch in diuretics from a thiazide to a chlorthalidone or even to a loop diuretic would be advisable. If heart rate control is inadequate, beta-blocker, alpha beta-blocker, verapamil or diltiazem could be used. In patients with low renin and aldosterone levels, a low-salt diet, avoiding night-time shift work and amiloride could be recommended. However, in case of low renin levels but normal to high aldosterone levels, it would be reasonable to use MRAs. It is recommended to evaluate BP patterns according to home and ambulatory BP monitoring to decide if split dosing of medications would improve control. If medication adherence is questionable, the statement recommends initiating indirect or direct methods to identify non-adherence, and if partial or complete non-adherence is documented it is recommended that the issue be discussed frankly and non-judgementally with the patient and the family. In case of sleep disordered breathing and significant anxiety associated with highly variable hypertension, initiating non-drug strategies concurrently with or separately from antihypertensive drug therapy is recommended. 15 In one study, a multifaceted pharmacist intervention through medication possession ratio in a hospital setting led to a sustained improvement in medication adherence in patients with hypertension. 29

The ISH recommendations advise using maximum tolerated dosages of diuretics, specifically thiazide-like rather than thiazide diuretics, and loop diuretics in patients with eGFR <30 mL/min/1.73 m 2 or clinical volume overload to optimise therapy. As with previous recommendations, adding a low dose of spironolactone as a fourth-line medication is advised if serum potassium is below 4.5 mmol/L and eGFR is higher than 45 mL/min/1.73 m 2 . Amiloride, doxazosin, eplerenone, clonidine and beta-blockers are suggested as spironolactone alternatives, along with any other antihypertensive drugs not already in use. 5

The different recommendations for RHT following different guidelines are summarised in table 4 .

Summary of the recommendations of the different guidelines

Conclusions

While the exact prevalence of RHT remains uncertain, existing research suggests that it may impact approximately 10% of individuals within the hypertensive community. RHT constitutes a significant risk factor for CVD and CKD. Consequently, it is imperative to promptly acknowledge this condition and ensure its management by a trained healthcare team capable of ruling out underlying causes of secondary hypertension and pseudo-RHT. Lifestyle adjustments are the fundamental basis of treatment and warrant consistent reinforcement. The intensification of antihypertensive treatment may involve the addition of supplementary antihypertensive medications, such as spironolactone and vasodilating beta-blockers, or RDN. The patient’s preference should be considered in the decision-making process.

CME credits for Education in Heart

Education in Heart articles are accredited for CME by various providers. To answer the accompanying multiple choice questions (MCQs) and obtain your credits, click on the ‘Take the Test’ link on the online version of the article. The MCQs are hosted on BMJ Learning. All users must complete a one-time registration on BMJ Learning and subsequently log in on every visit using their username and password to access modules and their CME record. Accreditation is only valid for 2 years from the date of publication. Printable CME certificates are available to users that achieve the minimum pass mark.

Ethics statements

Patient consent for publication.

Not required.

• Wei L , et al
• Whelton PK ,
• Aronow WS , et al
• Williams B ,
• Spiering W , et al
• Charchar F , et al
• Calhoun DA ,
• Bakris GL , et al
• Brunström M , et al
• Brant LCC ,
• Passaglia LG ,
• Pinto-Filho MM , et al
• Noubiap JJ ,
• Nansseu JR ,
• Nyaga UF , et al
• Williams JVA ,
• Tran KC , et al
• Sinnott S-J ,
• Williamson E , et al
• Kaczmarski KR ,
• Chen J , et al
• Bhandari SK ,
• Shi J , et al
• Parreira RC ,
• Lacerda LHG ,
• Vasconcellos R , et al
• Muxfeldt ES ,
• Barros GS ,
• Viegas BB , et al
• Hameed MA ,
• Jacques N , et al
• van der Laan DM ,
• Elders PJM ,
• Boons C , et al
• Mahmood S ,
• Hadi MA , et al
• Morrissey EC , et al
• Blumenthal JA ,
• Hinderliter AL ,
• Smith PJ , et al
• Schlaich MP ,
• Weber MA , et al
• Agarwal R ,
• Cramer AE , et al
• Rossignol P ,
• Budden J , et al
• Freeman MW ,
• Halvorsen Y-D ,
• Krieger EM ,
• Drager LF ,
• Giorgi DMA , et al
• Jackson AM ,
• Anand IS , et al
• Hedegaard U ,
• Kjeldsen LJ ,
• Pottegård A , et al
• Chernova I ,

Twitter @MiguelCamafort

Contributors MC, RK and M-CC contributed equally to the conception or design of the work, data collection, data analysis and interpretation, drafting the article, critical revision of the article, and final approval of the version to be published.

Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

Competing interests None declared.

Provenance and peer review Commissioned; externally peer reviewed.

Author note References which include a * are considered to be key references.

Read the full text or download the PDF:

Resistant hypertension: A stepwise approach

Affiliations.

• 1 Department of Internal Medicine, Cleveland Clinic, Cleveland, OH.
• 2 Director, Center for Blood Pressure Disorders, Department of Kidney Medicine, Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH; Associate Professor, Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH; Co-principal Investigator for SPRINT and SYMPLICITY HTN-3.
• 3 Department of Kidney Medicine, Glickman Urological and Kidney Institute Cleveland Clinic, Cleveland, OH; Clinical Assistant Professor, Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH.
• 4 Program Director, Nephrology and Hypertension Fellowship, Department of Kidney Medicine, Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH; Associate Professor, Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH; Co-principal Investigator for SYMPLICITY HTN-3 [email protected].
• PMID: 36724917
• DOI: 10.3949/ccjm.90a.22046

Resistant hypertension can be challenging to manage, but a stepwise approach to diagnosis, evaluation, and treatment can lead to better blood pressure control. In this article, we review the definition and prevalence of resistant hypertension and its diagnostic workup and management, including lifestyle modifications, drugs, and experimental interventional therapies.

Copyright © 2023 The Cleveland Clinic Foundation. All Rights Reserved.

Publication types

• Antihypertensive Agents* / therapeutic use
• Blood Pressure
• Blood Pressure Determination
• Hypertension* / diagnosis
• Hypertension* / drug therapy
• Hypertension* / epidemiology
• Antihypertensive Agents

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Review Article
• Published: 27 September 2022

Novel antihypertensive agents for resistant hypertension: what does the future hold?

• Vincent D. Salvador 1 &
• George L. Bakris 1  

Hypertension Research volume  45 ,  pages 1918–1928 ( 2022 ) Cite this article

1138 Accesses

7 Citations

7 Altmetric

Metrics details

Finding complementary compelling novel therapeutic agents for better control of blood pressure in people with resistant hypertension is moving into unchartered territory. The latest therapeutic developments explore approaches in the clinical arena that were either not examined or could only be examined in animal models two decades ago. Four main mechanisms have now been explored and operationalized in drug development: (a) mineralocorticoid receptor blockade using a nonsteroidal structure with many fewer side effects, (b) an aminopeptidase A inhibitor that has central effects on vasopressin, (c) a combined endothelin A and B receptor blocker and (d) an aldosterone synthase inhibitor devoid of glucocorticoid activity. All these agents are either completing Phase II development and starting Phase III or are involved in the ongoing recruitment of Phase III trials. Additionally, novel agents use antisense inhibition to block angiotensinogen development in the liver. These agents are discussed only for completeness, as they are still in Phase II trial development. Last, another agent that was initially being developed as an antihypertensive and once the data were reviewed by the company clearly showed efficacy as a heart failure agent was sacubitril/valsartan, which was ultimately approved. However, there are some discussions about reinvigorating the quest for an indication for hypertension, although no such steps have been formally initiated.

This is a preview of subscription content, access via your institution

Access options

Subscribe to this journal

Receive 12 print issues and online access

251,40 € per year

only 20,95 € per issue

Buy this article

• Purchase on Springer Link
• Instant access to full article PDF

Prices may be subject to local taxes which are calculated during checkout

Similar content being viewed by others

Novel therapeutics for the treatment of hypertension and its associated complications: peptide- and nonpeptide-based strategies

Angiotensin receptor-neprilysin inhibitors: Comprehensive review and implications in hypertension treatment

Angiotensin receptor–neprilysin inhibitors for hypertension—hemodynamic effects and relevance to hypertensive heart disease

Harrison DG, Coffman TM, Wilcox CS. Pathophysiology of hypertension: The Mosaic Theory and Beyond. Circ Res. 2021;128:847–63.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Carey RM, Calhoun DA, Bakris GL, Brook RD, Daugherty SL, Dennison-Himmelfarb CR, et al. Resistant hypertension: detection, evaluation, and management: a scientific statement from the American Heart Association. Hypertension. 2018;72:e53–90.

Article   CAS   PubMed   Google Scholar  

Weber MA, Schiffrin EL, White WB, Mann S, Lindholm LH, Kenerson JG, et al. Clinical practice guidelines for the management of hypertension in the community: a statement by the American Society of Hypertension and the International Society of Hypertension. J Clin Hypertens (Greenwich). 2014;16:14–26.

Article   Google Scholar  

Williams B, Mancia G, Spiering W, Agabiti Rosei E, Azizi M, Burnier M, et al. 2018 ESC/ESH Guidelines for the management of arterial hypertension. Eur Heart J. 2018;39:3021–104.

Article   PubMed   Google Scholar  

Oparil S, Acelajado MC, Bakris GL, Berlowitz DR, Cífková R, Dominiczak AF, et al. Hypertension. Nat Rev Dis Prim. 2018;4:18014.

Law MR, Wald NJ, Morris JK, Jordan RE. Value of low dose combination treatment with blood pressure lowering drugs: analysis of 354 randomised trials. Bmj. 2003;326:1427.

Gradman AH, Basile JN, Carter BL, Bakris GL. Combination therapy in hypertension. J Clin Hypertens (Greenwich). 2011;13:146–54.

Jamerson K, Weber MA, Bakris GL, Dahlöf B, Pitt B, Shi V, et al. Benazepril plus amlodipine or hydrochlorothiazide for hypertension in high-risk patients. N. Engl J Med. 2008;359:2417–28.

Bakris GL, Sarafidis PA, Weir MR, Dahlöf B, Pitt B, Jamerson K, et al. Renal outcomes with different fixed-dose combination therapies in patients with hypertension at high risk for cardiovascular events (ACCOMPLISH): a prespecified secondary analysis of a randomised controlled trial. Lancet. 2010;375:1173–81.

Rahman M, Pressel S, Davis BR, Nwachuku C, Wright JT Jr., Whelton PK, et al. Renal outcomes in high-risk hypertensive patients treated with an angiotensin-converting enzyme inhibitor or a calcium channel blocker vs a diuretic: a report from the Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial (ALLHAT). Arch Intern Med. 2005;165:936–46.

Wright JT Jr., Bakris G, Greene T, Agodoa LY, Appel LJ, Charleston J, et al. Effect of blood pressure lowering and antihypertensive drug class on progression of hypertensive kidney disease: results from the AASK trial. Jama. 2002;288:2421–31.

Randomised placebo-controlled trial of effect of ramipril on decline in glomerular filtration rate and risk of terminal renal failure in proteinuric, non-diabetic nephropathy. The GISEN Group (Gruppo Italiano di Studi Epidemiologici in Nefrologia). Lancet. 1997;349:1857–63.

Lewis EJ, Hunsicker LG, Clarke WR, Berl T, Pohl MA, Lewis JB, et al. Renoprotective effect of the angiotensin-receptor antagonist irbesartan in patients with nephropathy due to type 2 diabetes. N. Engl J Med. 2001;345:851–60.

Brenner BM, Cooper ME, de Zeeuw D, Keane WF, Mitch WE, Parving HH, et al. Effects of losartan on renal and cardiovascular outcomes in patients with type 2 diabetes and nephropathy. N. Engl J Med. 2001;345:861–9.

Kintscher U, Bakris GL, Kolkhof P. Novel non-steroidal mineralocorticoid receptor antagonists in cardiorenal disease. Br J Pharmacol. 2021. https://doi.org/10.1111/bph.15747 .

Barrera-Chimal J, Jaisser F, Anders HJ. The mineralocorticoid receptor in chronic kidney disease. Br J Pharmacol. 2021. https://doi.org/10.1111/bph.15734 .

Barrera-Chimal J, Kolkhof P, Lima-Posada I, Joachim A, Rossignol P, Jaisser F. Differentiation between emerging non-steroidal and established steroidal mineralocorticoid receptor antagonists: head-to-head comparisons of pharmacological and clinical characteristics. Expert Opin Investig Drugs. 2021;30:1141–57.

Chow CPLJ, Tan XJ, Huang ZH. Pharmacological Profile of Kbp-5074, a novel nonsteroidal mineralocorticoid receptor antagonist for the treatment of cardiorenal diseases. J Drug Res Dev. 2017;3:67–75.

Google Scholar  

Pitt B, Jaisser F, Bakris G. An evaluation of KBP-5074 in advanced chronic kidney disease with uncontrolled hypertension. Expert Opin Investig Drugs. 2021;30:1017–23.

Jaisser F, Tan X, Chi S, Liu J, Wang P, Bush M, et al. The non-steroidal mineralocorticoid receptor antagonist KBP-5074 limits Albuminuria and has improved therapeutic index compared with Eplerenone in a Rat Model With mineralocorticoid-induced renal injury. Front Pharm. 2021;12:604928.

Article   CAS   Google Scholar  

Zhang B, Tan X, Ni S. Pharmacokinetics and safety of KBP-5074 in phase 1 single and multiple ascending dose studies. Paper presented at: Poster presented at American Society of Nephrology Kidney Week meeting 2016.

Zhang BCP, Smith WB, Lasseter K, Yang F, Tan X, Pelka P. Safety, tolerability and pharmacokinetics of KBP-5074 in patients with mild-to-moderate chronic kidney disease [Abstract PUB116]. J Am Soc Nephrol. 2016;27:931A.

Bakris G, Yang YF, Pitt B. Mineralocorticoid receptor antagonists for Hypertension management in advanced Chronic Kidney Disease: BLOCK-CKD Trial. Hypertension. 2020;76:144–9.

Bakris G, Pergola PE, Delgado B, Genov D, Doliashvili T, Vo N, et al. Effect of KBP-5074 on Blood Pressure in Advanced Chronic Kidney Disease: Results of the BLOCK-CKD Study. Hypertension. 2021;78:74–81.

Lazich I, Bakris GL. Prediction and management of hyperkalemia across the spectrum of chronic kidney disease. Semin Nephrol. 2014;34:333–9.

Trensz F, Bortolamiol C, Kramberg M, Wanner D, Hadana H, Rey M, et al. Pharmacological characterization of Aprocitentan, a dual Endothelin receptor antagonist, alone and in combination with blockers of the Renin Angiotensin System, in two models of experimental Hypertension. J Pharm Exp Ther. 2019;368:462–73.

Yanagisawa M, Kurihara H, Kimura S, Tomobe Y, Kobayashi M, Mitsui Y, et al. A novel potent vasoconstrictor peptide produced by vascular endothelial cells. Nature. 1988;332:411–5.

Schiffrin EL, Deng LY, Sventek P, Day R. Enhanced expression of endothelin-1 gene in resistance arteries in severe human essential hypertension. J Hypertens. 1997;15:57–63.

Gueneau de Mussy P, Sidharta PN, Wuerzner G, Maillard MP, Guérard N, Iglarz M, et al. Effects of the dual Endothelin receptor antagonist aprocitentan on body weight and fluid homeostasis in healthy subjects on a high Sodium diet. Clin Pharm Ther. 2021;109:746–53.

Iglarz M, Clozel M. At the heart of tissue: endothelin system and end-organ damage. Clin Sci (Lond). 2010;119:453–63.

Amiri F, Virdis A, Neves MF, Iglarz M, Seidah NG, Touyz RM, et al. Endothelium-restricted overexpression of human endothelin-1 causes vascular remodeling and endothelial dysfunction. Circulation. 2004;110:2233–40.

Sen S, Chen S, Feng B, Iglarz M, Chakrabarti S. Renal, retinal and cardiac changes in type 2 diabetes are attenuated by macitentan, a dual endothelin receptor antagonist. Life Sci. 2012;91:658–68.

McCoy EK, Lisenby KM. Aprocitentan (a Dual Endothelin-Receptor Antagonist) for Treatment-Resistant Hypertension. J Cardiovasc Pharm. 2021;77:699–706.

Dhaun N, Goddard J, Kohan DE, Pollock DM, Schiffrin EL, Webb DJ. Role of endothelin-1 in clinical hypertension: 20 years on. Hypertension. 2008;52:452–9.

Angeli F, Verdecchia P, Reboldi G. Aprocitentan, A Dual Endothelin Receptor Antagonist Under Development for the Treatment of Resistant Hypertension. Cardiol Ther. 2021;10:397–406.

Article   PubMed   PubMed Central   Google Scholar  

Angeli F, Reboldi G, Verdecchia P. Interpretation of ambulatory blood pressure profile: a prognostic approach for clinical practice. J Hypertens. 2015;33:454–7.

Sidharta PN, Ulč I, Dingemanse J. Single-Dose Pharmacokinetics and Tolerability of Aprocitentan, a Dual Endothelin Receptor Antagonist, in Subjects with Severe Renal Function Impairment. Clin Drug Investig. 2019;39:1117–23.

Verweij P, Danaietash P, Flamion B, Ménard J, Bellet M. Randomized Dose-Response Study of the New Dual Endothelin Receptor Antagonist Aprocitentan in Hypertension. Hypertension. 2020;75:956–65.

Kohan DE, Pollock DM. Endothelin antagonists for diabetic and non-diabetic chronic kidney disease. Br J Clin Pharm. 2013;76:573–9.

CAS   Google Scholar  

Mann JF, Green D, Jamerson K, Ruilope LM, Kuranoff SJ, Littke T, et al. Avosentan for overt diabetic nephropathy. J Am Soc Nephrol. 2010;21:527–35.

Black HR, Bakris GL, Weber MA, Weiss R, Shahawy ME, Marple R, et al. Efficacy and safety of darusentan in patients with resistant hypertension: results from a randomized, double-blind, placebo-controlled dose-ranging study. J Clin Hypertens (Greenwich). 2007;9:760–9.

Burnier M. Update on Endothelin Receptor Antagonists in Hypertension. Curr Hypertens Rep. 2018;20:51.

Georgianos PI, Agarwal R. Endothelin A receptor antagonists in diabetic kidney disease. Curr Opin Nephrol Hypertens. 2017;26:338–44.

Smeijer JD, Kohan DE, Webb DJ, Dhaun N, Heerspink HJL. Endothelin receptor antagonists for the treatment of diabetic and nondiabetic chronic kidney disease. Curr Opin Nephrol Hypertens. 2021;30:456–65.

Heerspink HJL, Parving HH, Andress DL, Bakris G, Correa-Rotter R, Hou FF, et al. Atrasentan and renal events in patients with type 2 diabetes and chronic kidney disease (SONAR): a double-blind, randomised, placebo-controlled trial. Lancet. 2019;393:1937–47.

Reaux A, Fournie-Zaluski MC, David C, Zini S, Roques BP, Corvol P, et al. Aminopeptidase A inhibitors as potential central antihypertensive agents. Proc Natl Acad Sci USA. 1999;96:13415–20.

Bodineau L, Frugiere A, Marc Y, Inguimbert N, Fassot C, Balavoine F, et al. Orally active aminopeptidase A inhibitors reduce blood pressure: a new strategy for treating hypertension. Hypertension. 2008;51:1318–25.

Basting T, Lazartigues E. DOCA-Salt Hypertension: an Update. Curr Hypertens Rep. 2017;19:32.

Balavoine F, Azizi M, Bergerot D, De Mota N, Patouret R, Roques BP, et al. Randomised, double-blind, placebo-controlled, dose-escalating phase I study of QGC001, a centrally acting aminopeptidase a inhibitor prodrug. Clin Pharmacokinet. 2014;53:385–95.

Azizi M, Courand PY, Denolle T, Delsart P, Zhygalina V, Amar L, et al. A pilot double-blind randomized placebo-controlled crossover pharmacodynamic study of the centrally active aminopeptidase A inhibitor, firibastat, in hypertension. J Hypertens. 2019;37:1722–8.

Ferdinand KC, Balavoine F, Besse B, Black HR, Desbrandes S, Dittrich HC, et al. Efficacy and Safety of Firibastat, A First-in-Class Brain Aminopeptidase A Inhibitor, in Hypertensive Overweight Patients of Multiple Ethnic Origins. Circulation. 2019;140:138–46.

Lenzini L, Zanotti G, Bonchio M, Rossi GP. Aldosterone synthase inhibitors for cardiovascular diseases: A comprehensive review of preclinical, clinical and in silico data. Pharm Res. 2021;163:105332.

Ren L, Colafella KMM, Bovée DM, Uijl E, Danser AHJ. Targeting angiotensinogen with RNA-based therapeutics. Curr Opin Nephrol Hypertens. 2020;29:180–9.

Setten RL, Rossi JJ, Han SP. The current state and future directions of RNAi-based therapeutics. Nat Rev Drug Disco. 2019;18:421–46.

Liang XH, Sun H, Nichols JG, Crooke ST. RNase H1-Dependent Antisense Oligonucleotides Are Robustly Active in Directing RNA Cleavage in Both the Cytoplasm and the Nucleus. Mol Ther. 2017;25:2075–92.

Bertrand JR, Pottier M, Vekris A, Opolon P, Maksimenko A, Malvy C. Comparison of antisense oligonucleotides and siRNAs in cell culture and in vivo. Biochem Biophys Res Commun. 2002;296:1000–4.

Levin AA. Treating Disease at the RNA Level with Oligonucleotides. N. Engl J Med. 2019;380:57–70.

Springer AD, Dowdy SF. GalNAc-siRNA Conjugates: Leading the Way for Delivery of RNAi Therapeutics. Nucleic Acid Ther. 2018;28:109–18.

Prakash TP, Graham MJ, Yu J, Carty R, Low A, Chappell A, et al. Targeted delivery of antisense oligonucleotides to hepatocytes using triantennary N-acetyl galactosamine improves potency 10-fold in mice. Nucleic Acids Res. 2014;42:8796–807.

Morgan ES, Tami Y, Hu K, Brambatti M, Mullick AE, Geary RS, et al. Antisense Inhibition of Angiotensinogen With IONIS-AGT-L(Rx): Results of Phase 1 and Phase 2 Studies. JACC Basic Transl Sci. 2021;6:485–96.

Huang STJ, Casey S, Leung PM, Webb DJ, Desai AS, Cheng Y, et al. Durable Reductions in Circulating Angiotensinogen and Blood Pressure Six Months After Single Doses of ALN-AGT, an RNA Interference Therapeutic Targeting Hepatic Angiotensinogen Synthesis, in Hypertensive Patients. Circulation. 2021;144:A10974 https://doi.org/10.1161/circ.144.suppl_1.10974.

McMurray JJ, Packer M, Desai AS, Gong J, Lefkowitz MP, Rizkala AR, et al. Angiotensin-neprilysin inhibition versus enalapril in heart failure. N. Engl J Med. 2014;371:993–1004.

De Vecchis R, Soreca S, Ariano C. Anti-Hypertensive Effect of Sacubitril/Valsartan: A Meta-Analysis of Randomized Controlled Trials. Cardiol Res. 2019;10:24–33.

Zhao Y, Yu H, Zhao X, Ma R, Li N, Yu J. The Effects of LCZ696 in Patients With Hypertension Compared With Angiotensin Receptor Blockers: A Meta-Analysis of Randomized Controlled Trials. J Cardiovasc Pharm Ther. 2017;22:447–57.

Wang JG, Yukisada K, Sibulo A Jr., Hafeez K, Jia Y, Zhang J. Efficacy and safety of sacubitril/valsartan (LCZ696) add-on to amlodipine in Asian patients with systolic hypertension uncontrolled with amlodipine monotherapy. J Hypertens. 2017;35:877–85.

Kostis JB, Packer M, Black HR, Schmieder R, Henry D, Levy E. Omapatrilat and enalapril in patients with hypertension: the Omapatrilat Cardiovascular Treatment vs. Enalapril (OCTAVE) trial. Am J Hypertens. 2004;17:103–11.

Bavishi C, Messerli FH, Kadosh B, Ruilope LM, Kario K. Role of neprilysin inhibitor combinations in hypertension: insights from hypertension and heart failure trials. Eur Heart J. 2015;36:1967–73.

Gu J, Noe A, Chandra P, Al-Fayoumi S, Ligueros-Saylan M, Sarangapani R, et al. Pharmacokinetics and pharmacodynamics of LCZ696, a novel dual-acting angiotensin receptor-neprilysin inhibitor (ARNi). J Clin Pharm. 2010;50:401–14.

Segura J, Ruilope LM. Dual-acting angiotensin receptor-neprilysin inhibition. Curr Hypertens Rep. 2011;13:74–8.

Chrysant SG. Benefits and pitfalls of sacubitril/valsartan treatment in patients with hypertension. J Clin Hypertens (Greenwich). 2018;20:351–5.

Ruilope LM, Dukat A, Böhm M, Lacourcière Y, Gong J, Lefkowitz MP. Blood-pressure reduction with LCZ696, a novel dual-acting inhibitor of the angiotensin II receptor and neprilysin: a randomised, double-blind, placebo-controlled, active comparator study. Lancet. 2010;375:1255–66.

Perkovic V, Huxley R, Wu Y, Prabhakaran D, MacMahon S. The burden of blood pressure-related disease: a neglected priority for global health. Hypertension. 2007;50:991–7.

Kario K, Sun N, Chiang FT, Supasyndh O, Baek SH, Inubushi-Molessa A, et al. Efficacy and safety of LCZ696, a first-in-class angiotensin receptor neprilysin inhibitor, in Asian patients with hypertension: a randomized, double-blind, placebo-controlled study. Hypertension. 2014;63:698–705.

Kario K, Tamaki Y, Okino N, Gotou H, Zhu M, Zhang J. LCZ696, a First-in-Class Angiotensin Receptor-Neprilysin Inhibitor: The First Clinical Experience in Patients With Severe Hypertension. J Clin Hypertens (Greenwich). 2016;18:308–14.

Stamler J. The INTERSALT Study: background, methods, findings, and implications. Am J Clin Nutr. 1997;65:626s–42s.

Katsuya T, Ishikawa K, Sugimoto K, Rakugi H, Ogihara T. Salt sensitivity of Japanese from the viewpoint of gene polymorphism. Hypertens Res. 2003;26:521–5.

Wang TD, Tan RS, Lee HY, Ihm SH, Rhee MY, Tomlinson B, et al. Effects of Sacubitril/Valsartan (LCZ696) on Natriuresis, Diuresis, Blood Pressures, and NT-proBNP in Salt-Sensitive Hypertension. Hypertension. 2017;69:32–41.

Volpe M, Gallo G. Sacubitril/valsartan for heart failure with preserved ejection fraction and resistant hypertension: one shot for a double strike? Eur Heart J. 2021;42:3753–5.

Solomon SD, Zile M, Pieske B, Voors A, Shah A, Kraigher-Krainer E, et al. The angiotensin receptor neprilysin inhibitor LCZ696 in heart failure with preserved ejection fraction: a phase 2 double-blind randomised controlled trial. Lancet. 2012;380:1387–95.

Jackson AM, Jhund PS, Anand IS, Düngen HD, Lam CSP, Lefkowitz MP, et al. Sacubitril-valsartan as a treatment for apparent resistant hypertension in patients with heart failure and preserved ejection fraction. Eur Heart J. 2021;42:3741–52.

Anderson AH, Yang W, Townsend RR, Pan Q, Chertow GM, Kusek JW, et al. Time-updated systolic blood pressure and the progression of chronic kidney disease: a cohort study. Ann Intern Med. 2015;162:258–65.

Williams B, Cockcroft JR, Kario K, Zappe DH, Brunel PC, Wang Q, et al. Effects of Sacubitril/Valsartan Versus Olmesartan on Central Hemodynamics in the Elderly With Systolic Hypertension: The PARAMETER Study. Hypertension. 2017;69:411–20.

Williams B. Hypertension and the “J-curve”. J Am Coll Cardiol. 2009;54:1835–6.

Ruiz-Hurtado G, Ruilope LM. Advantages of sacubitril/valsartan beyond blood pressure control in arterial hypertension. Eur Heart J. 2017;38:3318–20.

Iwata N, Tsubuki S, Takaki Y, Shirotani K, Lu B, Gerard NP, et al. Metabolic regulation of brain Abeta by neprilysin. Science. 2001;292:1550–2.

Hüttenrauch M, Baches S, Gerth J, Bayer TA, Weggen S, Wirths O. Neprilysin deficiency alters the neuropathological and behavioral phenotype in the 5XFAD mouse model of Alzheimer’s disease. J Alzheimers Dis. 2015;44:1291–302.

Download references

Author information

Authors and affiliations.

Department of Medicine, Am Heart Assoc. Comprehensive Hypertension Center, University of Chicago Medicine, Chicago, IL, USA

Vincent D. Salvador & George L. Bakris

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to George L. Bakris .

Ethics declarations

Conflict of interest.

VDS—None; GLB is supported by T32 NIH grant DK07011 and is a consultant to Bayer, KBP Biosciences, Ionis, Alnylam, Astra Zeneca, Quantum Genomics, Horizon, Novo Nordisk, Dia Medica Therapeutics, and InRegen.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article.

Salvador, V.D., Bakris, G.L. Novel antihypertensive agents for resistant hypertension: what does the future hold?. Hypertens Res 45 , 1918–1928 (2022). https://doi.org/10.1038/s41440-022-01025-9

Download citation

Received : 14 July 2022

Revised : 16 August 2022

Accepted : 25 August 2022

Published : 27 September 2022

Issue Date : December 2022

DOI : https://doi.org/10.1038/s41440-022-01025-9

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Hypertension
• Resistant hypertension
• Nephropathy

This article is cited by

Resistant hypertension: consensus document from the korean society of hypertension.

• Sungha Park
• Jong-Moo Park

Clinical Hypertension (2023)

Topics 2023 in Hypertension Research leading to guidelines in Asia

• Kazuomi Kario
• Satoshi Hoshide
• Masaki Mogi

Hypertension Research (2023)

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

• Open access
• Published: 22 April 2024

Mutations in the NUP93 , NUP107 and NUP160 genes cause steroid-resistant nephrotic syndrome in Chinese children

• Yanxinli Han 1 ,
• Hongyu Sha 2 ,
• Yuan Yang 1 ,
• Zhuowei Yu 1 ,
• Lanqi Zhou 1 ,
• Yi Wang 1 ,
• Fengjie Yang 1 ,
• Liru Qiu 1 ,
• Yu Zhang 1 &
• Jianhua Zhou 1  

Italian Journal of Pediatrics volume  50 , Article number:  81 ( 2024 ) Cite this article

18 Accesses

Metrics details

The variants of nucleoporins are extremely rare in hereditary steroid-resistant nephrotic syndrome (SRNS). Most of the patients carrying such variants progress to end stage kidney disease (ESKD) in their childhood. More clinical and genetic data from these patients are needed to characterize their genotype–phenotype relationships and elucidate the role of nucleoporins in SRNS.

Four patients of SRNS carrying biallelic variants in the NUP93 , NUP107 and NUP160 genes were presented. The clinical and molecular genetic characteristics of these patients were summarized, and relevant literature was reviewed.

All four patients in this study were female and initially presented with SRNS. The median age at the onset of the disease was 5.08 years, ranging from 1 to 10.5 years. Among the four patients, three progressed to ESKD at a median age of 7 years, ranging from 1.5 to 10.5 years, while one patient reached stage 3 chronic kidney disease (CKD3). Kidney biopsies revealed focal segmental glomerulosclerosis in three patients. Biallelic variants were detected in NUP93 in one patient, NUP107 in two patients, as well as NUP160 in one patient respectively. Among these variants, five yielded single amino acid substitutions, one led to nonsense mutation causing premature termination of NUP107 translation, one caused a single nucleotide deletion resulting in frameshift and truncation of NUP107. Furthermore, one splicing donor mutation was observed in NUP160 . None of these variants had been reported previously.

This report indicates that biallelic variants in NUP93 , NUP107 and NUP160 can cause severe early-onset SRNS, which rapidly progresses to ESKD. Moreover, these findings expand the spectrum of phenotypes and genotypes and highlight the importance of next-generation sequencing in elucidating the molecular basis of SRNS and allowing rational treatment for affected individuals.

Introduction

Nephrotic syndrome (NS) is common in children. Most of them respond well to glucocorticoid, while a minority are steroid-resistant [ 1 , 2 , 3 ]. Steroid-resistant nephrotic syndrome (SRNS) primarily presents as focal segmental glomerulosclerosis (FSGS), which is associated with an unfavorable renal prognosis [ 4 , 5 ]. Despite extensive research efforts, the etiology and pathogenesis of SRNS remain incompletely understood. Recent studies have identified an increasing number of genes associated with the development of SRNS, totally accounting for 29.5% of SRNS as reported by Hildebrandt [ 6 ]. About 66% of SRNS occurring within the first year of their life are caused by monogenic variants [ 7 ]. Thus far, more than 50 genes have been identified for SRNS worldwide [ 8 ]. Most of these gene products are located in slit diaphragm, cytoskeleton, mitochondria, lysosome and endocytic compartment of podocytes [ 8 , 9 ].

Currently, variants in several nucleoporins (NUPs) have been identified as the underlying causes of SRNS. The nuclear pore complex includes a variety of NUPs that are distributed across the nuclear envelope and play a critical role in macro-molecular transportation between nucleus and cytoplasm [ 10 , 11 ]. However, the reported cases of such variants are limited. Therefore, additional clinical and genetic data are required to characterize genotype–phenotype relationships and elucidate the role of NUPs in SRNS. This study aims to summarize the clinical and molecular genetic characteristics of four cases of SRNS caused by variants in NUP93 , NUP107 and NUP160 genes with the intention of providing new insights into this rare disease.

Patients and methods

Case presentation.

Case 1 was a 1-year-old female patient who initially presented with edema on the lower limbs and eyelids. She developed normally and was well-nourished. Upon physical examination, the patient presented with hypertension with a blood pressure of 115/68mmHg (≥95th percentile + 12 mmHg), while no other evident abnormalities were observed. The urine test showed proteinuria 3+ and hematuria 2+. The serum creatinine was 0.58mg/dl (eGFR 57ml/min/1.73m 2 ). Subsequent renal biopsy revealed FSGS. Despite receiving treatment with a combination of prednisone and cyclosporin A, the patient remained nephrotic after approximately six months of treatment and eventually progressed to end-stage kidney disease (ESKD). Whole-exome sequencing (WES) identified biallelic variants in the NUP93 gene.

Case 2 was a 5.3-year-old female patient who was hospitalized due to edema on lower limbs, with blood pressure of 141/108mmHg (≥95th percentile + 12 mmHg). Physical examination revealed no other significant abnormalities. Her growth and development were normal without any malformations. Urine examination showed hematuria 2+ and proteinuria 3+, while the serum creatinine level was 0.4mg/dl (eGFR 110ml/min/1.73m 2 ). Despite four weeks of treatment with prednisone, the patient showed no response. So renal biopsy and whole-exome sequencing (WES) were recommended. The renal biopsy revealed global sclerosis in 11 glomeruli and segmental glomerulosclerosis in 4 among total 30 glomeruli. WES identified biallelic variants in the NUP107 gene.

Case 3 involved a female child aged 10.5 years who presented with chest tightness and nausea. Physical examination showed hypertension with blood pressure ranging from 151/108 mmHg to 200/149 mmHg (≥95th percentile + 12 mmHg). There were no edema or growth and developmental delays. The plasma renin level was within the normal range, and the whole aortic computer tomography angiography (CTA) showed no remarkable findings. Echocardiography showed left ventricular hypertrophy with left ventricular ejection fractions (LVEF) at 38.7%. Ultrasound examination revealed no abnormalities in the kidneys, uterus, or ovaries. Urine analysis revealed a significant proteinuria level of 4+ without hematuria. The level of serum creatinine was 6.26 mg/dl (eGFR 9.6ml/min/1.73m 2 ). Subsequently, the patient underwent peritoneal dialysis, and whole-exome sequencing (WES) identified biallelic variants in the NUP107 gene.

Case 4 was a 3.5-year-old girl presenting with eyelid edema and hypertension. Urinalysis revealed proteinuria 4+ and hematuria 2+. The patient showed mild intellectual disability, as evidenced by a full-scale score of 48 on the Wechsler Preschool and Primary Scale of Intelligence (WPPSI), indicating an intellectual delay. A comprehensive neuropsychiatric assessment indicated delays in both gross and fine motor skills, adaptive abilities, language development and social behavior. Cognitive assessment demonstrated abnormal cognitive play and social communication behaviors. The Autism Behavior Checklist (ABC) confirmed the presence of autistic behaviors, with the Childhood Autism Rating Scale (CARS) indicating mild to moderate autism spectrum disorder. The ultrasound examination revealed the presence of a cord-like uterine, structure measuring 13 mm in length and 3 mm in anteroposterior diameter. The baseline level of serum creatinine was 0.34mg/dl (eGFR 114ml/min/1.73m 2 ). However, there was an increase level in serum creatinine to 0.98mg/dl (eGFR 42ml/min/1.73m 2 ) during the follow-up, suggesting the development of stage 3 chronic kidney disease (CKD3). Renal biopsy revealed FSGS. The patient was initially treated with prednisone and tacrolimus, which were discontinued due to no response. Thereafter WES identified biallelic variants in the NUP160 gene.

All of these cases had no family history of the disease. The specific family diagram is illustrated in Fig.  1 .

Family diagram of four patients. Black arrow indicates proband; WT: wild type

Detection and analysis of nucleoporin gene variants

After obtaining the informed consent of the patients’ parents, blood samples were collected from both the patients and their parents. DNA was extracted from peripheral white blood cells by using the MagPure Buffy Coat DNA Midi KF Kit according to manufacturer’s standard protocol. Genomic DNA was broken into 100–500 bp fragments by BGI’s enzyme kit (Segmentase, BGI), and 280–320 bp fragments were collected by magnetic bead. PCR amplification was performed using universal primers complementary to the adapter sequence to form a sequencing library. All amplified libraries were hybridized with exome capture probes (Agilent, USA) and sequenced. The clean reads derived from targeted sequencing and filtering were then aligned to the human genome reference (hg19) by using the BWA. Single-nucleotide variants (SNVs) and INDELs were detected with Sentieon (the same algorithm with GATK) analysis. The pathogenic variants were screened by ClinVar, OMIM, and HGMD databases. Functional prediction of missense mutations was conducted using PolyPhen-2, SIFT, and MutationTaster. All variants and potential pathogenic variants were validated via conventional Sanger sequencing methods.

Clinical and renal pathological features and long-term outcome

The clinical and laboratory data of four patients are shown in Table 1 . All patients initially presented with massive proteinuria with or without hematuria. Patient 2 and 4 had normal serum creatinine levels and eGFR at the onset, while patient 1 and 3 had elevated levels of serum creatinine and impaired renal function at beginning. Moreover, patient 3 presented with heart failure as an extra-renal manifestation, and patient 4 showed mild intellectual disability and uterine dysplasia. Renal biopsy revealed focal and segmental glomerular sclerosis (Fig.  2 ).

kidney biopsies reveal FSGS in the patients. A shows segmental sclerosis in a glomerulus and a global sclerosis in another glomerulus (HE, 100). B indicates global glomerulosclerosis (PASM, 100)

Patient 1 rapidly progressed to ESKD within six months of onset and regrettably passed away at 1.5 years of age. Patient 2 developed renal failure at 9 years old and subsequently underwent renal transplantation. Patient 3 was diagnosed with ESKD at the initial presentation and was on maintenance peritoneal dialysis. And patient 4 was diagnosed with CKD3 at 5 years old during the follow-up period (Table 1 ).

Identification of pathological variants in the NUP genes

Biallelic variants in the NUP genes were detected by WES in all patients. Specifically, patient 1 had biallelic missense mutations c.1235A>C (p.Tyr412Ser) and c.1286A>G (p.Tyr429Cys) in the NUP93 gene. Patient 2 showed biallelic variants c.1199G>A (p.Gly400Glu) and c.580C>T (p.Arg194*) in the NUP107 gene, and patient 3 also had biallelic variants c.2564delC (p.Pro855fsTer*23) and c.2753C>T (p.Pro918Leu) in NUP107 , resulting in amino acid substitutions and proteins truncation. Patient 4 was identified with a missense mutation c.3656T>G (p.Leu1219Trp) and a splicing donor mutation c.2241+1G>T in the NUP160 gene. Ployphen2, MutationTaster analysis indicated that all the missense mutations were harmful (Table 2 ).

Clinical and molecular genetic characterization of reported patients carrying biallelic variants of NUP genes

To date, a total of 60 cases of NUP -associated SRNS have been reported worldwide (Table 3 ). Among these reported cases, variants of NUP93 gene were observed in 24 individuals (40%), while NUP107 variants in 20 individuals (33.3%). Additionally, there were also eight cases (13.3%) with NUP133 mutations, four cases (6.7%) with NUP85 mutations, one case (1.7%) with NUP205 mutation and three cases (5%) with NUP160 mutations. The majority of these reported cases initially presented with SRNS and eventually progressed to ESKD. The detailed information of these variants were presented in Table 3 and Fig.  3 , involving 22 variants in NUP93 , 11 in NUP107 , 6 in NUP133 , 4 in NUP85 , 1 in NUP205 , and 3 in NUP160 . Missense mutations were the majority of all NUP  mutations.

Schematic illustration of mutation sites in genes of NUP85 ( A ), NUP93 ( B ), NUP107 ( C ) , NUP133 ( D ) and NUP160 ( E ). Hot spot mutations are indicated in red

NUPs are situated in the nuclear membrane, and approximately 30 kinds of NUPs assemble to form the nuclear pore complex (NPC), serving as a special and unique transport channel across the nuclear membrane [ 29 ]. The NPC comprises a core scaffold, a nuclear basket, transmembrane nucleoporins and a central selective channel [ 11 ]. NUP93 is located in the inner ring of the core scaffold, while NUP107 and NUP160 are located in the outer ring also known as the “Y” complex [ 30 ]. NUP93, NUP107 and NUP160 interact with other NUPs and participate in the assembly of NPCs, which are crucial for trans-nuclear membrane transportation. Any alterations in the NUPs or defects in transport channels can hinder transmembrane transport, resulting in the abnormal accumulation of materials in nucleus or cytoplasm. Consequently, variants in NUPs are associated with a variety of diseases [ 31 ]. Previous studies have linked NUP93 , NUP107 and NUP160 to cancer, congenital heart disease, neurological diseases and gonadal dysgenesis [ 32 , 33 , 34 , 35 , 36 ]. Recently several SRNS cases caused by variants in NUPs have been reported and attracted the attention of pediatric nephrologists.

Previous studies had indicated that variants in NUP93 and NUP107 were the most frequent mutated NUP genes in individuals with SRNS. Patients with variants in these genes rapidly progressed to ESKD at a young age. Conversely, cases of SRNS with NUP160 variants presented relatively later and progressed to ESKD at an older age than those with NUP93 and NUP107 variants. Furthermore, patients with variants in NUP93 , NUP107 , and NUP133 were more likely to present with extra-renal manifestations.

Previously reported NUP variants included missense, nonsense, frameshift, small deletion and splicing mutations, among which missense mutations were found to be the most prevalent. Notably, variant hotspots were found in NUP93 and NUP107 genes. Specifically, the c.1772G>T (p.G591V) variant in NUP93 was identified as a pathogenic European founder variant and the c.1537+ 1G>A (deletion of exon 13) was found to be another pathogenic variant in Germans [ 13 ]. The c.2492A > C (D831A) variant in the NUP107 gene was considered to be unique to East Asians [ 23 ]. Furthermore, the variant c.2407G>A (p.Glu803Lys) in the NUP160 may be a hotspot variant in Asian according to previous reports.

The specific mechanisms underlying steroid-resistant nephrotic syndrome (SRNS) caused by NUPs remain unclear. A previous study demonstrated the presence of glomerular dysplasia and abnormal podocyte processes in zebrafish models with NUP107 knockdown [ 22 ]. Knockdown of NUP160 gene resulted in podocyte proliferation incapability, increased apoptosis, autophagy and cell migration, and altered expression and localization of nephrin, podocin, CD2AP and α-actinin-4 [ 37 ]. Furthermore, Braun [ 25 ] discovered upregulation of cdc42 in podocytes with knockout of NUP85 , NUP107 , and NUP133 genes. In addition, knockdown of NUP93 gene in podocytes disrupted BMP7-dependent SMAD signaling, potentially implicating it in the pathogenesis of SRNS [ 16 ].

Next-generation sequencing (NGS) is a powerful and high-throughput genetic test helping to identify the causative variants of genetic diseases. This technique offers valuable insights and evidence for the purposes of diagnosis, treatment, and genetic counseling [ 38 , 39 , 40 ]. Targeted panel sequencing is faster and cheaper than WES, making it a preferred choice for patients whose clinical data are highly consistent with a specific genetic defect or a known group of genes [ 41 ]. However, the limitation of targeted panel is that only genes within the panel are sequenced, which may result in missing genes located beyond the panel. As the cost of sequencing becomes cheaper and cheaper, WES has been widely accepted especially for patients with ambiguous phenotypes that make it difficult to apply targeted panel sequencing [ 42 ].

Cystic kidney diseases and renal tubulopathies subjected to WES result in relatively high rates of positive findings [ 43 ]. Generally speaking, an earlier onset of a disease is associated with a higher possibility of genetic etiology. Identifying the causes of sporadic non-syndromic SRNS is challenging. Overall, WES should be considered for SRNS patients with multisystem involvement as well as with unexplained clinical manifestations. In this study, all four patients lacked specific manifestation and two of them showed multisystemic involvement. Therefore, gene variant screening was the only way to identify genetic causes. Fortunately WES uncovered definitive pathogenic biallelic variants of NUP genes, thereby the ineffective treatment of prednisone and immunosuppressants was immediately discontinued. Our report demonstrates the necessity and diagnostic utility of genetic analysis in sporadic cases of SRNS and highlights the role of NGS in understanding the molecular mechanisms of SRNS and facilitating rational and individualized treatment for patients.

This paper is believed to be the first to report on a series of Chinese cases of SRNS associated with variants of NUP genes. Furthermore, all these variants in NUP93 , NUP107 and NUP160 have not been previously reported. Since this study is solely a case report, the limited number of cases prevented us from drawing conclusive phenotypic and genotypic correlations. In addition, how NUP variants cause SRNS remains unclear and requires further comprehensive molecular research.

In summary, this study reports four cases of sporadic SRNS caused by novel variants in the NUP93 , NUP107 , and NUP160 genes in Chinese children. The findings extend the spectrum of phenotypes and genotypes, and also highlight the importance of NGS in elucidating the molecular mechanisms of SRNS and allowing personalized treatment for affected individuals.

Availability of data and materials

The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.

Abbreviations

• Steroid-resistant nephrotic syndrome

End stage kidney disease

Chronic kidney disease

Stage 3 chronic kidney disease

Nucleoporin

Whole-exome sequencing

Nuclear pore complex

Next-generation sequencing

Trautmann A, Vivarelli M, Samuel S, et al. IPNA clinical practice recommendations for the diagnosis and management of children with steroid-resistant nephrotic syndrome. Pediatr Nephrol. 2020;35(8):1529–61.

Article   PubMed   PubMed Central   Google Scholar  

Downie M L, Gallibois C, Parekh R S, et al. Nephrotic syndrome in infants and children: pathophysiology and management[Z]. England: Taylor & Francis, 2017: 37, 248-258.

Tullus K, Webb H, Bagga A. Management of steroid-resistant nephrotic syndrome in children and adolescents. Lancet Child Adolesc Health. 2018;2(12):880–90.

Article   PubMed   Google Scholar  

Lee JM, Kronbichler A, Shin JI, et al. Current understandings in treating children with steroid-resistant nephrotic syndrome. Pediatr Nephrol (Berlin, West). 2021;36(4):747–61.

Article   Google Scholar  

Shin JI, Kronbichler A, Oh J, et al. Nephrotic syndrome: genetics, mechanism, and therapies. Biomed Res Int. 2018;2018:6215942–6.

Sadowski CE, Lovric S, Ashraf S, et al. A single-gene cause in 29.5% of cases of steroid-resistant nephrotic syndrome. J Am Soc Nephrol. 2015;26(6):1279–89.

Article   CAS   PubMed   Google Scholar  

Hinkes BG, Mucha B, Vlangos CN, et al. Nephrotic syndrome in the first year of life: two thirds of cases are caused by mutations in 4 genes (NPHS1, NPHS2, WT1, and LAMB2). Pediatrics. 2007;119(4):e907–19.

Preston R, Stuart HM, Lennon R. Genetic testing in steroid-resistant nephrotic syndrome: why, who, when and how? Pediatr Nephrol (Berlin, West). 2019;34(2):195–210.

Trautmann A, Lipska-Ziętkiewicz BS, Schaefer F. Exploring the clinical and genetic spectrum of steroid resistant nephrotic syndrome: the podonet registry. Front Pediatr. 2018;6:200.

Lin DH, Hoelz A. The structure of the nuclear pore complex (an update). Ann Rev Biochem. 2019;88(1):725–83.

Hampoelz B, Andres-Pons A, Kastritis P, et al. Structure and assembly of the nuclear pore complex. Ann Rev Biophys. 2019;48(1):515–36.

Article   CAS   Google Scholar  

Bierzynska A, Bull K, Miellet S, et al. Exploring the relevance of NUP93 variants in steroid-resistant nephrotic syndrome using next generation sequencing and a fly kidney model. Pediatr Nephrol (Berlin, West). 2022;37(11):2643–56.

Bezdíčka M, Štolbová Š, Seeman T, et al. Genetic diagnosis of steroid-resistant nephrotic syndrome in a longitudinal collection of Czech and Slovak patients: a high proportion of causative variants in NUP93. Pediatr Nephrol (Berlin, West). 2018;33(8):1347–63.

Rossanti R, Shono A, Miura K, et al. Molecular assay for an intronic variant in NUP93 that causes steroid resistant nephrotic syndrome. J Hum Genet. 2019;64(7):673–9.

Sandokji I, Marquez J, Ji W, et al. Identification of novel mutations and phenotype in the steroid resistant nephrotic syndrome gene NUP93: a case report. BMC Nephrol. 2019;20(1):271.

Braun DA, Sadowski CE, Kohl S, et al. Mutations in nuclear pore genes NUP93, NUP205 and XPO5 cause steroid-resistant nephrotic syndrome. Nat Genet. 2016;48(4):457–65.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Zhao B, Chen J, Liao Y, et al. Steroid-resistant nephrotic syndrome in infants caused by a novel compound heterozygous mutation of the NUP93: A CARE case report. Medicine (Baltimore). 2021;100(6):e24627.

Cason RK, Williams A, Chryst-Stangl M, et al. Collapsing focal segmental glomerulosclerosis in siblings with compound heterozygous variants in NUP93 expand the spectrum of kidney phenotypes associated with nucleoporin gene mutations. Front Pediatr. 2022;10:915174.

Acharya R, Upadhyay K. End-stage renal disease in a child with focal segmental glomerulosclerosis associated with a homozygous NUP93 variant. Clin Case Rep. 2021;9(11):e05111.

Hashimoto T, Harita Y, Takizawa K, et al. In Vivo expression of NUP93 and its alteration by NUP93 mutations causing focal segmental glomerulosclerosis. Kidney Int Rep. 2019;4(9):1312–22.

Al Riyami M S, Al Alawi I, Al Gaithi B, et al. Genetic analysis and outcomes of Omani children with steroid-resistant nephrotic syndrome. Mol Genet Genomic Med. 2023;11(9):e2201.

Miyake N, Tsukaguchi H, Koshimizu E, et al. Biallelic mutations in nuclear pore complex subunit NUP107 cause early-childhood-onset steroid-resistant nephrotic syndrome. Am J Hum Genet. 2015;97(4):555–66.

Park E, Ahn YH, Kang HG, et al. NUP107 mutations in children with steroid-resistant nephrotic syndrome. Nephrol Dial Transplan. 2017;32(6):1013–7.

CAS   Google Scholar  

Rosti RO, Sotak BN, Bielas SL, et al. Homozygous mutation in NUP107 leads to microcephaly with steroid-resistant nephrotic condition similar to Galloway-Mowat syndrome. J Med Genet. 2017;54(6):399–403.

Braun DA, Lovric S, Schapiro D, et al. Mutations in multiple components of the nuclear pore complex cause nephrotic syndrome. J Clin Investig. 2018;128(10):4313–28.

Zhao F, Zhu JY, Richman A, et al. Mutations in NUP160 are implicated in steroid-resistant nephrotic syndrome. J Am Soc Nephrol. 2019;30(5):840–53.

Fujita A, Tsukaguchi H, Koshimizu E, et al. Homozygous splicing mutation in NUP133 causes Galloway-Mowat syndrome. Ann Neurol. 2018;84(6):814–28.

Wang Q, Gu R, Li FW, et al. Steroid-resistant nephrotic syndrome caused by nuclear pore gene NUP133 variation. Clin Genet. 2023;104(2):272–4.

Schuller AP, Wojtynek M, Mankus D, et al. The cellular environment shapes the nuclear pore complex architecture. Nature. 2021;598(7882):667–71.

Beck M, Hurt E. The nuclear pore complex: understanding its function through structural insight. Nat Rev Mol Cell Biol. 2017;18(2):73–89.

Jamali T, Jamali Y, Mehrbod M, et al. Chapter six - Nuclear Pore Complex: Biochemistry and Biophysics of Nucleocytoplasmic Transport in Health and Disease[M]// Jeon K W . International Review of Cell and Molecular Biology. Academic Press, 2011:233-286.

Ouyang X, Hao X, Liu S, et al. Expression of Nup93 is associated with the proliferation, migration and invasion capacity of cervical cancer cells. Acta Biochimica Et Biophysica Sinica. 2019;51(12):1276–85.

Pan L, Song XW, Song JC, et al. Downregulation of NUP93 aggravates hypoxia-induced death of cardiomyocytes in vitro through abnormal regulation of gene transcription. Acta Pharmacol Sin. 2023;44(5):969–83.

Nong JS, Zhou X, Liu JQ, et al. Nucleoporin 107 is a prognostic biomarker in hepatocellular carcinoma associated with immune infiltration. Cancer Med. 2023;12(9):10990–1009.

Ren Y, Diao F, Katari S, et al. Functional study of a novel missense single-nucleotide variant of NUP107 in two daughters of Mexican origin with premature ovarian insufficiency. Mol Genet Genom Med. 2018;6(2):276–81.

Tarazon E, Rivera M, Rosello-Lleti E, et al. Heart failure induces significant changes in nuclear pore complex of human cardiomyocytes. Plos One. 2012;7(11):e48957.

Wang P, Zhao F, Nie X, et al. Knockdown of NUP160 inhibits cell proliferation, induces apoptosis, autophagy and cell migration, and alters the expression and localization of podocyte associated molecules in mouse podocytes. Gene. 2018;664:12–21.

Serra G, Antona V, D’Alessandro MM, Maggio MC, Verde V, Corsello G. Novel SCNN1A gene splicing-site mutation causing autosomal recessive pseudohypoaldosteronism type 1 (PHA1) in two Italian patients belonging to the same small town. Ital J Pediatr. 2021;47(1):138.

Piro E, Schierz IAM, Antona V, et al. Neonatal hyperinsulinemic hypoglycemia: case report of kabuki syndrome due to a novel KMT2D splicing-site mutation. Ital J Pediatr. 2020;46(1):136.

Serra G, Corsello G, Antona V, et al. Autosomal recessive polycystic kidney disease: case report of a newborn with rare PKHD1 mutation, rapid renal enlargement and early fatal outcome. Ital J Pediatr. 2020;46(1):154.

Platt CD, Zaman F, Bainter W, et al. Efficacy and economics of targeted panel versus whole-exome sequencing in 878 patients with suspected primary immunodeficiency. J Allergy Clin Immunol. 2021;147(2):723–6.

Lee JY, Oh SH, Keum C, Lee BL, Chung WY. Clinical application of prospective whole-exome sequencing in the diagnosis of genetic disease: Experience of a regional disease center in South Korea. Ann Hum Genet. Published online October 5, 2023.

Vilboux T, Doherty DA, Glass IA, et al. Molecular genetic findings and clinical correlations in 100 patients with Joubert syndrome and related disorders prospectively evaluated at a single center. Genet Med. 2017;19(8):875–82.

Download references

Acknowledgments

The authors thank all patients and their families for participation in this study.

The work for this study was supported by the National Key Scientific Research and Development Program of China (No.2022YFC2705193) and the Key Scientific Research and Development Program of Hubei Province (No.2022BCA047).

Author information

Authors and affiliations.

Department of Pediatrics, Tongji Hospital, Tongji Medical College, Huazhong University of Science & Technology, Wuhan, Hubei province, 430030, China

Yanxinli Han, Yuan Yang, Zhuowei Yu, Lanqi Zhou, Yi Wang, Fengjie Yang, Liru Qiu, Yu Zhang & Jianhua Zhou

Department of Pharmacy, Yantai Yuhuangding Hospital, Yantai, Shandong Province, 264000, China

You can also search for this author in PubMed   Google Scholar

Contributions

HYXL and ZJH conceived the study. HYXL collected and analyzed the data and drafted the initial manuscript. SHY, YY, ZLQ, YZW, WY and YFJ helped to collect and supplement the data and participated in the care of these patients. QLR and ZY interpreted the results of WES and kidney biopsies. ZJH was the research grant recipient, revised the manuscript and supervised all the process. All authors had read and approved the manuscript.

Corresponding author

Correspondence to Jianhua Zhou .

Ethics declarations

Ethics approval and consent to participate.

Informed consent documents for this study were obtained from patients’ parents. The study was approved by the the Medical Ethics Committee of Tongji Medical College and was conducted in accordance with HIPAA regulations and with the tenets of the Declaration of Helsinki.

Consent for publication

Consent for publication were obtained from the institution and patients’ parents.

Competing interests

The authors declare no competing interests in this paper.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Han, Y., Sha, H., Yang, Y. et al. Mutations in the NUP93 , NUP107 and NUP160 genes cause steroid-resistant nephrotic syndrome in Chinese children. Ital J Pediatr 50 , 81 (2024). https://doi.org/10.1186/s13052-024-01656-3

Download citation

Received : 12 November 2023

Accepted : 07 April 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s13052-024-01656-3

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• End-stage kidney disease
• Gene variants

Italian Journal of Pediatrics

ISSN: 1824-7288

• Submission enquiries: Access here and click Contact Us
• General enquiries: [email protected]

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

281 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• BMJ Case Rep

Case report

Translating research evidence into clinical practice: a reminder of important clinical lessons in management of resistant hypertension through a case study in general practice, timothy yap.

1 Curtin Medical School, Curtin University, Perth, Western Australia, Australia

Jacquita S Affandi

2 School of Public Health, Curtin University, Perth, Western Australia, Australia

Christopher M Reid

3 Department of General Practice, Curtin University Bentley Campus, Perth, Western Australia, Australia

4 Department of Medical Education, Sun Yan-sen University of Medical Sciences, Guangzhou, China

A case of a 59-year-old man with resistant hypertension, despite 8 months of non-pharmacological and pharmacological management up to maximal doses of triple antihypertensive therapy. Review of the literature found a study that reported improved blood pressure control with bedtime dosing of antihypertensive treatment. Changing to bedtime dosage of antihypertensives resulted in significant improvement in blood pressure control to below target levels. This highlights the importance of the clinicians’ awareness and implementation of research findings and hence delivery of best evidence-based care.

Hypertension (or high blood pressure (BP)) is the most common condition managed by general practice in Australia, accounting for 5.8% of the total burden of disease. 1 2 This mini-review will be discussing research translation into clinical practice by examining a clinical case with treatment-resistant hypertension. Resistant hypertension is defined as systolic BP/diastolic BP (SBP/DBP) above the set goal of 140/90 mm Hg, despite concurrent use of three antihypertensive agents of different classes, one of which should be a diuretic agent. 3 4

Case presentation

A 59-year-old engineer presented to his general practitioner (GP) at the beginning of 2019 with the following problems:

• Hypertension 168/98 mm Hg from average of three unattended automated office BP measurements.
• Obesity body mass index (BMI) 33 kg/m 2 since mid 40s with weight loss failure (exercise limitation due to osteoarthritis).
• Heavy snoring indicating obstructive sleep apnoea. Patient requested for a sleep study.
• Family history of dyslipidemia with both parents on lipid lowering medications.
• No smoking, no excessive alcohol intake and no history of regular non-steroidal anti-inflammatory drugs use.

Investigations

The next step for management of hypertension in general practice encompasses the three ‘C’ approaches 5 :

• Confirm the condition with 24-hour ambulatory BP monitor: the patient’s average day BP 162/96 mm Hg and night BP 152/92 mm Hg.
• Causes: investigations—blood tests, ECG and renal arterial Doppler ultrasound (part of GORDS approach—see below).
• Complications monitoring target-organ damage (heart, brain, renal and retina) (part of GORDS approach—see below).

The management discussion began with the confirmation of hypertension and target setting for 120/70 mm Hg due to his associated risks/problems. Target BP levels were discussed with him and were set according to the Australian Blood Pressure treatment guidelines. 6 After the discussion regarding the ‘GORDS’ for management of hypertension, he fully agreed with the approaches and his investigation results as below:

• ‘G’: glucose-associated hypertension 7 —confirmed pre-diabetes with impaired fasting glucose/glucose tolerance.
• ‘O’: obesity/overweight-associated hypertension 8 —weight loss diet and confirm no obstructive sleep apnoea during sleep study.
• ‘R: renal-disease-associated hypertension 9 —renal function, serum metanephrine, aldosterone/renin ration and renal arterial Doppler ultrasound were all within normal range.
• ‘D’: dyslipidaemia/drug-associated hypertension 5 —mildly raised triglyceride levels, managed with controlled diet; however, other lipid profile markers were unremarkable.
• ‘S’: salt/social-factors-dependent hypertension 5 —implement low salt, low fat and low glycaemic-index diet, non-smoker and no excessive alcohol intake.

The patient commenced treatment on Exforge (Novartis), including valsartan 160 mg and amlodipine 5 mg in the morning. In the first 2 weeks, he experienced mild generalised headache without any adverse neurological symptoms and signs; subsequently, his headache resolved without intervention and his self-monitor BP was 155/92 mm Hg. He was told by his GP that his mild headache was most likely due to the side effects of amlodipine. After 3 months, he reduced his BMI to 31 kg/m 2 . His average BP during three unattended automated office BP measurements decreased to 150/90 mm Hg.

Guideline recommendations in the presence of sustained elevated BP were to consider adding hydrochlorothiazide (HCT) 12.5 mg to become Exforge HCT (amlodipine 5 mg/valsartan 160 mg/HCT 12.5 mg), 5 taking into account of his initial headache side effect of amlodipine at 5 mg. At 6 weeks’ review, he tolerated the adding of HCT 12.5 mg without any side effects, and his average BP during three unattended automated office BP measurements decreased to 146/90 mm Hg, and we increased his Exforge HCT prescription to the maximal dose of amlodipine 10 mg/valsartan 160 mg/HCT 25 mg. Twelve weeks later, his BP subsequently reduced further to 143/90 mm Hg and he managed to reduce his BMI to 29 kg/m 2 .

We discussed the next step of treatment with a plan to add the fourth antihypertensive to manage his resistant hypertension. As per our usual practice, we performed a comprehensive clinical assessment again to ensure both the adherence to his medications and the absence of other treatment-compromising risk factors. Our consensus view in the next step treatment was to review the current literature for the most optimal fourth agent for his resistant hypertension.

A newly published multicentre trial reported that antihypertensive medication taken at bedtime is associated with improved BP control and a halving of cardiovascular deaths and events in comparison with morning dosing. 10 The study included nearly 20 000 hypertensive patients in general practice with the final ambulatory BP monitoring evaluation demonstrating considerably lower mean SBP/DBP when asleep in people who took ≥1 antihypertensives at bedtime. This study provides strong evidence that it may be better to take BP medications at bedtime, not in the morning. Additionally, the safety of evening dosage is also consistent with a previous review, which found no increase in incidence of adverse effects. 11

We communicated the study results to him and advised him to try ingesting his BP medication before bedtime and warn him about the side effects of increased urinary frequency during sleep. At his 1 week visit after taking Exforge HCT at bedtime, his BP was reduced to 127/78 mm Hg without any urinary frequency side effects. After 3 months of bedtime dosing of Exforge HCT, his BP was further reduced to 125/75 mm Hg, despite his BMI remained at the overweight range of 28 kg/m 2 . The patient contemplated whether he should reduce the dose of Exforge HCT or change to Exforge only.

After 4 months of bedtime dosing, his BP was further reduced to 115/65 mm Hg, and did not report any adverse events. We discussed the dose reduction of Exforge HCT from amlodipine 10 mg/valsartan 160 mg/HCT 25 mg to amlodipine 5 mg/valsartan 160 mg/HCT 25 mg, decreasing amlodipine from 10 mg to 5 mg. We will follow-up his BP in 6 weeks’ time to titrate his antihypertensives aiming at the ideal BP of 120–130/70–80 mm Hg. We plan to change Exforge HCT back to Exforge in our next visit if his BP continues to show the trend of ideal-control values.

Time-unspecified BP measurements have traditionally been used to diagnose and evaluate patients with hypertension. However, it has been shown that BP exhibits a predictable 24-hour day–night patterning. 12 In normotensive and uncomplicated hypertensive patients, the typical pattern of BP is a 10%–20% decline in sleep, mean SBP compared with mean awake SBP followed by an abrupt rise into 2-day time peaks, the first 2–3 hours after the termination of sleep and the other in the early evening with a small mid-afternoon nadir. 13 This ‘dipping’ pattern is suggested to result from the interrelationship of the many 24-hour circadian physiological, neuroendocrine and environmental factors 12–14 :

• Rest and activity associated factors—intensity of activity, fluid, stimulants (caffeine), nutrition, mental stress and posture.
• External day to night changes—ambient light intensity and spectrum, temperature, humidity and noise.
• Endogenous circadian cyclical variation—neuroendocrine, endothelial, vasoactive peptide, opioid and haemodynamic parameters (plasma norepinephrine and epinephrine (autonomic nervous system), atrial natriuretic and calcitonin gene-related peptides and renin–angiotensin–aldosterone system).

However, this pattern is often disrupted in both secondary and resistant hypertension with up to 69% prevalence of a ‘non-dipping’ BP pattern in patients with resistant hypertension. 15 16 In these patients, sleep SBP commonly fail to decline by more than 10% of mean diurnal BP. It is suggested that an imbalance of sympathetic and parasympathetic activity is a major determinant of this change, while in resistant hypertension, the excessive morning ingestion of shorter-acting antihypertensives which lack 24-hour coverage may play a role. 17 The extent of nocturnal BP decline is clinically significant as it appears to be associated with and hence predictor of cardiovascular disease (CVD) risk and end-organ injury. 14 Thus, the use of ambulatory blood pressure monitoring (ABPM) and targeting this pattern are necessary to not only to improve BP control, but also most importantly to reduce CVD risk.

By targeting this increased nocturnal BP with chronotherapy of evening dosage of antihypertensive, many trials conducted have shown an improvement in BP control as well as reduction in cardiovascular and stroke risk. 10 18 19 The exact mechanism underlying this improvement is yet unclear, but administration-time differences in the effects of antihypertensives are thought to arise from circadian rhythm differences in pharmacokinetics (PK) and pharmacodynamics (PD) as well as on the mechanisms of BP regulation. 12 20 We know that PK of antihypertensives are affected due to circadian changes in gastric function and motility, biliary function and circulation, liver enzyme activity, blood flow to the gastrointestinal tract and glomerular filtration rate. 21 PD is also influenced by changes in circulating drug-free fraction, rate-limiting steps of key biochemical and metabolic processes, receptor number and signalling pathways. 22 Therefore, ultimately slowing down clearance and prolonging the therapeutic effect of antihypertensives. 17 Night-time dosage of antihypertensive is further justified by the fact that sodium excretion is usually lowest at night due to lower BP. When sodium intake is excessive or its daytime excretion reduced, compensation is achieved nocturnally by adjusting BP to a higher level through the pressure-natriuresis mechanism, resulting in a ‘non-dipping’ BP pattern. 23 Therefore, the ingestion of bedtime antihypertensives would enhance nocturnal natriuresis and reset BP back into a normal ‘dipper’ pattern, with its functional effect like that of sodium restriction. 24 Despite the many mechanisms of BP regulation, pressure natriuresis ultimately dominates due to its infinite gain. 25

The goal of health research is to bring about positive health outcomes for patients and to provide an evidence base for clinical decision-making. Thus, in order to achieve this goal, research findings need to be disseminated and taken up by clinicians to be delivered to patients. In the USA, only 54.9% of patients received recommended evidence-based care. 26 Similar rates of guideline-based care were also found globally in all areas and disciplines of health. 27 Additionally, a study on a US national cohort of treatment-resistant hypertension patients found that only 25% patients were on the recommended combination therapy of angiotensin converting enzyme inhibitor (ACEI)/angiotensin II receptor blocker (ARB) + calcium channel blocker (CCB) +thiazide. 28 It has been shown that deficits in primary and secondary preventive care are also associated with an increase in preventable deaths. 26 Clearly more must be done to deliver quality care to patients.

Currently, it takes an average of 17 years before research evidence is translated to clinical practice. 29–31 However, Morris et al describes the complexity of quantifying the lag and attempts to simplify the model of translational research into two major steps, ‘bench to bedside’ and ‘research into practice’. 32 Similarly, the US National Institutes of Health (NIH) ‘T1–T4 Research Translation Framework’ provides a framework to understand the complex steps taken from health and medical research to improve health outcomes. 33

Individually, clinicians can have the most significant impact on the overall process of research translation at step T3, ‘Dissemination and Implementation‘. Balas and Boren estimate that an average of 9.3 years is taken in this step. 29 Additionally, de-adoption of harmful and ineffective clinical practices may take even longer. 34 Often innovative research into evidence-based guidelines will be significantly reduced in intensity after guidelines are published and more needs to be done by both researchers and clinicians to translate this research knowledge into best evidence and best practice healthcare. 33 However, Glasgow et al provide many examples of successful and efficient implementations of new research. 35 Strategies have been proposed to systemically narrow this research to practice gap by encouraging healthcare leaders to work together with researchers and clinicians for the ultimate benefit of patients. 33 36 Investments into new research is much greater than that of investment towards redesigning systems to better deliver care, while dissemination and implementation may have a greater impact and better decrease morbidity and mortality than a new research or discovery. 37 Despite all the research into translation and their recommendations, this large gap still exists due to obstacles at every level of the healthcare system. 38 This includes barriers and challenges such as lack of access, lack of awareness, lack of confidence, lack of trust, decreased motivation and a perceived lack of usefulness. 39 40

In our patient’s case, there was almost no gap in research evidence translation into clinical practice with a favourable outcome. However, we had initial hesitation in terms of applying the research evidence because of potential side effects of diuretics if dosing is before bedtime, as well as the bedtime dosing study 10 included a majority of patients without a diagnosis of resistant hypertension and being treated with an average number of less then two antihypertensive medications. The individual management experiences of our patient reminds practising clinicians that research evidence translation will always need to be patient specific.

Finally, our take-home message for the clinician is that research evidence should be readily translated into practice promptly and specifically to determine whether the findings translate into clinical benefit for individual patients. As a competent clinician, we should advocate evidence-based practice to reduce the gap time between the arrival of the research evidence and the implementation of the research evidence into the management guideline in our clinical practice. Hermida et al propose that further studies and clinical trials would be required to confirm the definite benefits and mechanism of taking antihypertensive at bedtime in an even larger population, including different cultural groups. 10

Patient’s perspective

Having been diagnosed with hypertension just over 1 year ago, I initially thought my blood pressure (BP) should be easily controlled with changing lifestyle and taking the combined antihypertensives. When I realised that my BP was still poorly controlled with two antihypertensives, my doctor used the most updated research to add on the third antihypertensive. Both my doctor and myself were quite confident that triple-combined antihypertensives would get my BP to target. We were both a little disappointed that my doctor had to start to search for the fourth antihypertensive. We were discussing that I could be recruited into a new clinical trial, which is a phase three trial examining a new endothelial receptor antagonist. I was worrying about the potential side effects of four antihypertensives and hesitating to participate in the trial. My good news came when my doctor called in for a home visit to tell me a new study stating that taking antihypertensive at bedtime can significantly improve BP control and reduce all the BP-related cardiovascular complications. I was so grateful to my doctor who successfully used the innovative treatment regimen and brought my BP to the ideal target level when this novel research evidence was just released 2 days before his home visit. Having been working in the science field, I immediately asked my doctor whether he will apply this innovative treatment regimen to other hypertensive patients and introduce the innovation into the hypertensive treatment guideline. My doctor told me that he would individually apply this new approach to all his hypertensive patients but it will take some time to cement the innovative research into the guideline. I was quite relieved to hear that he will use my case to review the evidence of research translation into clinical practice and hopefully identify the ways to shorten the time gap between research evidence translation into clinical practice. Overall, my experience has been a double blessing for both my optimal clinical care by prompt use of new research evidence and stimulation of further research to facilitate rapid research translation into practice.

Learning points

• Diagnose and evaluate hypertension with ambulatory blood pressure monitoring.
• Consider bedtime dosage of antihypertensive treatment for clinically appropriate patients.
• Clinicians should seek out latest evidence to guide management in clinical practice.
• Systemic effort is required to reduce translational time lags from research to improved patient outcomes.

Contributors: TY designed a part of the initial draft and edited and reviewed the final manuscript. JA and CR reviewed and edited the initial and final manuscript. DX designed the initial draft and reviewed and edited the initial and final manuscript.

Funding: The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

Competing interests: None declared.

Patient consent for publication: Obtained.

Provenance and peer review: Not commissioned; externally peer reviewed.