nursing case study for hypertension

Hypertension

Learn about the nursing care management of patients with hypertension .

Table of Contents

• What is Hypertension? 

Classification

Pathophysiology, epidemiology, clinical manifestations, complications, diagnostic tests, pharmacologic therapy.

• Nursing Assessment 
• Diagnosis 
• Nursing Care Plan and Goals

Nursing Priorities

Nursing interventions, discharge and home care guidelines, documentation guidelines, what is hypertension.

Hypertension is one of the most common lifestyle diseases to date. It affects people from all walks of life. Let us get to know hypertension more by its definitions.

• Hypertension is defined as a systolic blood pressure greater than 140 mmHg and a diastolic pressure of more than 90 mmHg .
• This is based on the average of two or more accurate blood pressure measurements during two or more consultations with the healthcare provider.
• The definition is taken from the Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure .

In 2017, the American College of Cardiology and the American Heart Association revised their hypertension guidelines . The previous guidelines set the threshold at 140/90 mm Hg for younger people and 150/80 mm Hg for those ages 65 and older.

• Normal . The normal range for blood pressure is between, less than 120 mmHg and less than 80 mmHg.
• Elevated . Elevated stage starts from 120 mmHg to 129 mmHg for systolic blood pressure and less than 80 mmHg for diastolic pressure.
• Stage 1 hypertension . Stage 1 starts when the patient has a systolic pressure of 130 to 139 mmHg and a diastolic pressure of 80 to 89 mmHg.
• Stage 2 hypertension . Stage 2 starts when the systolic pressure is already more than or equal than 140 mmHg and the diastolic is more than or equal than 90 mmHg.

In a normal circulation, pressure is transferred from the heart muscle to the blood each time the heart contracts and then pressure is exerted by the blood as it flows through the blood vessels.

The pathophysiology of hypertension follows.

• Hypertension is a multifactorial
• When there is excess sodium intake , renal sodium retention occurs, which increases fluid volume resulting in increased preload and increase in contractility.
• Obesity is also a factor in hypertension because hyperinsulinemia develops and structural hypertrophy results leading to increased peripheral vascular resistance.
• Genetic alteration also plays a role in the development of hypertension because when there is cell membrane alteration, functional constriction may follow and also results in increased peripheral vascular resistance.

Hypertension is slowly rising to the top as one of the primary causes of morbidity in the world . Here are the current statistics of the status of hypertension in some of the leading countries.

• About 31% of the adults in the United States have hypertension.
• African-Americans have the highest prevalence rate of 37%.
• In the total US population of persons with hypertension, 90% to 95% have primary hypertension or high blood pressure from an unidentified cause.
• The remaining 5% to 10% of this group have secondary hypertension or high blood pressure related to identified causes.
• Hypertension is also termed as the “silent killer” because 24% of people who had pressures exceeding 140/90 mmHg were unaware that their blood pressures were elevated.

Hypertension has a lot of causes just like how  fever has many causes. The factors that are implicated as causes of hypertension are:

• Increased sympathetic nervous system activity . Sympathetic nervous system activity increases because there is dysfunction in the autonomic nervous system .
• Increase renal reabsorption . There is an increase reabsorption of sodium, chloride, and water which is related to a genetic variation in the pathways by which the kidneys handle sodium.
• Increased RAAS activity . The renin-angiotensin-aldosterone system increases its activity leading to the expansion of extracellular fluid volume and increased systemic vascular resistance.
• Decreased vasodilation of the arterioles . The vascular endothelium is damaged because of the decrease in the vasodilation of the arterioles.

Many people who have hypertension are asymptomatic at first. Physical examination may reveal no abnormalities except for an elevated blood pressure, so one must be prepared to recognize hypertension at its earliest.

• Headache . The red blood cells carrying oxygen is having a hard time reaching the brain because of constricted vessels , causing headache.
• Dizziness occurs due to the low concentration of oxygen that reaches the brain.
• Chest pain . Chest pain occurs also due to decreased oxygen levels .
• Blurred vision. Blurred vision may occur later on because of too much constriction in the blood vessels of the eye that red blood cells carrying oxygen cannot pass through.

Prevention of hypertension mainly relies on a healthy lifestyle and self-discipline.

• Weight reduction . Maintenance of normal body weight can help prevent hypertension.
• Adopt DASH . DASH or the Dietary Approaches to Stop Hypertension includes consummation of a diet rich in fruits, vegetable, and low-fat dairy .
• Dietary sodium retention . Sodium contributes to an elevated blood pressure, so reducing the dietary intake to no more than 2.4 g sodium per day can be really helpful.
• Physical activity . Engage in regular aerobic physical activity for 30 minutes thrice every week.
• Moderation of alcohol consumption . Limit alcohol consumption to no more than 2 drinks per day in men and one drink for women and people who are lighter in weight.

If hypertension is left untreated, it could progress to complications of the different body organs.

• Heart failure . With increased blood pressure, the heart pumps blood faster than normal until the heart muscle goes weak from too much exertion.
• Myocardial infarction . Decreased oxygen due to constriction of blood vessels may lead to MI.
• Impaired vision. Ineffective peripheral perfusion affects the eye, causing problems in vision because of decreased oxygen.
• Renal failure. Blood carrying oxygen and nutrients could not reach the renal system because of the constricted blood vessels .

Assessment and Diagnostic Findings

Assessment of the patient with hypertension must be detailed and thorough. There are also diagnostic tests that can be performed to establish the diagnosis of hypertension.

• Assess the patient’s health history
• Perform physical examination as appropriate.
• The retinas are examined to assess possible organ damage .
• Laboratory tests are also taken to check target organ damage .
• Urinalysis is performed to check the concentration of sodium in the urine though the specific gravity.
• Blood chemistry (e.g. analysis of sodium, potassium , creatinine , fasting glucose , and total and high density lipoprotein cholesterol levels). These tests are done to determine the level of sodium and fat in the body.
• 12-lead ECG . ECG needs to be performed to rule presence of cardiovascular damage .
• Echocardiography . Echocardiography assesses the presence of left ventricular hypertrophy .
• Creatinine clearance . Creatinine clearance is performed to check for the level of BUN and creatinine that can determine if there is renal damage or not.
• Renin level . Renin level should be assessed to determine how RAAS is coping.
• Hemoglobin/hematocrit:  Not diagnostic but assesses relationship of cells to fluid volume (viscosity) and may indicate risk factors such as hypercoagulability, anemia .
• Blood urea nitrogen (BUN)/creatinine:  Provides information about renal perfusion/function.
• Glucose:  Hyperglycemia ( diabetes mellitus is a precipitator of hypertension) may result from elevated catecholamine levels (increases hypertension).
• Serum potassium :   Hypokalemia may indicate the presence of primary aldosteronism (cause) or be a side effect of diuretic ­therapy.
• Serum calcium :  Imbalance may contribute to hypertension.
• Lipid panel (total lipids, high-density lipoprotein [HDL], low-density lipoprotein [LDL], cholesterol, triglycerides, phospholipids):  Elevated level may indicate predisposition for/presence of atheromatous plaques.
• Thyroid studies:  Hyperthyroidism may lead or contribute to vasoconstriction and hypertension.
• Serum/urine aldosterone level:  May be done to assess for primary aldosteronism (cause).
• Urinalysis:  May show blood, protein, or white blood cells; or glucose suggests renal dysfunction and/or presence of diabetes .
• Creatinine clearance:  May be reduced, reflecting renal damage.
• Urine vanillylmandelic acid (VMA) (catecholamine metabolite):  Elevation may indicate presence of pheochromocytoma (cause); 24-hour urine VMA may be done for assessment of pheochromocytoma if hypertension is intermittent.
• Uric acid:  Hyperuricemia has been implicated as a risk factor for the development of hypertension.
• Renin:  Elevated in renovascular and malignant hypertension, salt-wasting disorders.
• Urine steroids:  Elevation may indicate hyperadrenalism, pheochromocytoma, pituitary dysfunction, Cushing’s syndrome.
• Intravenous pyelogram (IVP):  May identify cause of secondary hypertension, e.g., renal parenchymal disease, renal/ureteral ­calculi.
• Kidney and renography nuclear scan:  Evaluates renal status (TOD).
• Excretory urography:  May reveal renal atrophy, indicating chronic renal disease.
• Chest x-ray :  May demonstrate obstructing calcification in valve areas; deposits in and/or notching of aorta ; cardiac enlargement.
• Computed tomography (CT) scan:  Assesses for cerebral tumor , CVA, or encephalopathy or to rule out pheochromocytoma.
• Electrocardiogram (ECG):  May demonstrate enlarged heart, strain patterns, conduction disturbances. Note: Broad, notched P wave is one of the earliest signs of hypertensive heart disease.

Medical Management

Main Topic: Antihypertensive Drugs

The goal of hypertension treatment is to prevent complications and death by achieving and maintaining arterial blood pressure at or below 130/80 mmHg.

• The medications used for treating hypertension decrease peripheral resistance , blood volume , or the strength and rate of myocardial contraction .
• For uncomplicated hypertension, the initial medications recommended are diuretics and beta blockers.
• Only low doses are given, but if blood pressure still exceeds 140/90 mmHg, the dose is increased gradually.
• Thiazide diuretics decrease blood volume , renal blood flow, and cardiac output.
• ARBs are competitive inhibitors of aldosterone binding .
• Beta blockers block the sympathetic nervous system to produce a slower heart rate and a lower blood pressure.
• ACE inhibitors inhibit the conversion of angiotensin I to angiotensin II and lowers peripheral resistance.

Stage 1 Hypertension

• Thiazide diuretic is recommended for most and angiotensin-converting enzyme-1, aldosterone receptor blocker , beta blocker , or calcium channel blocker is considered.

Stage 2 Hypertension

• Two-drug combination is followed, usually including thiazide diuretic and angiotensin-converting enzyme-1, or beta-blocker , or calcium channel blocker.

Nursing Management

The goal of nursing management is to help achieve a normal blood pressure through independent and dependent interventions.

Nursing Assessment

Nursing assessment must involve careful monitoring of the blood pressure at frequent and routinely scheduled intervals.

• If patient is on antihypertensive medications, blood pressure is assessed to determine the effectiveness and detect changes in the blood pressure.
• Complete history should be obtained to assess for signs and symptoms that indicate target organ damage.
• Pay attention to the rate, rhythm, and character of the apical and peripheral pulses.

Based on the assessment data, nursing diagnoses may include the following:

• Deficient knowledge regarding the relation between the treatment regimen and control of the disease process.
• Noncompliance with the therapeutic regimen related to side effects of the prescribed therapy.
• Risk for activity intolerance related to imbalance between oxygen supply and demand.
• Risk- prone health behavior related to condition requiring change in lifestyle.

Nursing Care Plan and Goals

Main article: Hypertension Nursing Care Plans

The major goals for a patient with hypertension are as follows:

• Understanding of the disease process and its treatment.
• Participation in a self-care program.
• Absence of complications.
• BP within acceptable limits for individual.
• Cardiovascular and systemic complications prevented/minimized.
• Disease process/prognosis and therapeutic regimen understood.
• Necessary lifestyle/behavioral changes initiated.
• Plan in place to meet needs after discharge.
• Maintain/enhance cardiovascular functioning.
• Prevent complications.
• Provide information about disease process/prognosis and treatment regimen.
• Support active patient control of condition.

The objective of nursing care focuses on lowering and controlling the blood pressure without adverse effects and without undue cost.

• Encourage the patient to consult a dietitian to help develop a plan for improving nutrient intake or for weight loss .
• Encourage restriction of sodium and fat
• Emphasize increase intake of fruits and vegetables .
• Implement regular physical activity .
• Advise patient to limit alcohol consumption and avoidance of tobacco.
• Assist the patient to develop and adhere to an appropriate exercise regimen.  

At the end of the treatment regimen, the following are expected to be achieved:

• Maintain blood pressure at less than 140/90 mmHg with lifestyle modifications, medications, or both.
• Demonstrate no symptoms of angina , palpitations, or visual changes.
• Has stable BUN and serum creatinine levels.
• Has palpable peripheral pulses.
• Adheres to the dietary regimen as prescribed.
• Exercises regularly.
• Takes medications as prescribed and reports side effects.
• Measures blood pressure routinely.
• Abstains from tobacco and alcohol intake.
• Exhibits no complications.

Following discharge, the nurse should promote self-care and independence of the patient.

• The nurse can help the patient achieve blood pressure control through education about managing blood pressure.
• Assist the patient in setting goal blood pressures .
• Provide assistance with social support.
• Encourage the involvement of family members in the education program to support the patient’s efforts to control hypertension.
• Provide written information about expected effects and side effects.
• Encourage and teach patients to measure their blood pressures at home.
• Emphasize strict compliance of follow-up check up .

These are the following data that should be documented for the patient’s record:

• Effects of behavior on health status/condition.
• Plan for adjustments and interventions for achieving the plan and the people involved.
• Client responses to the interventions, teaching, and action plan performed.
• Attainment or progress towards desired outcome.
• Modifications to plan care.
• Individual findings including deviation from prescribed treatment plan.
• Consequences of actions to date.

Posts related to Hypertension:

• Pregnancy Induced Hypertension
• 6 Hypertension Nursing Care Plans
• Antihypertensive Drugs
• Cardiovascular Care Nursing Mnemonics and Tips

6 thoughts on “Hypertension”

I want some NMC questions to solve

Question regarding Stage 1 HTN is incorrect. Stage 1 HTN is BP reading 140-159/90-99.

In new version of Brunner & Suddath’s medical surgical nursing textbook (2022), stage 1 HTN is BP reading 130-139/80-89. (pp: 866, vol 1)

I don’t understand the explanation for the classification of hypertension, the explanation is not matching with the table, why?

“Medical Management Main Topic: Antihypertensive Drugs

The goal of hypertensive treatment I to prevent complications and death by achieving and maintaining the arterial blood pressure at 40/90 mmHg or lower.”

I think need to correct the above sentence as follows;

The goal of hypertensive treatment is to prevent complications and death by achieving and maintaining the arterial blood pressure at 140/90 mmHg or lower.”

please there is a place you wrote BP 40/90,is that correct. Meanwhile, the article is educative.

Leave a Comment Cancel reply

This website is intended for healthcare professionals

• { $refs.search.focus(); })" aria-controls="searchpanel" :aria-expanded="open" class="hidden lg:inline-flex justify-end text-gray-800 hover:text-primary py-2 px-4 lg:px-0 items-center text-base font-medium"> Search

Search menu

Abegaz TM, Shehab A, Gebreyohannes EA, Bhagavathula AS, Elnour AA. Nonadherence to antihypertensive drugs. Medicine (Baltimore). 2017; 96:(4) https://doi.org/10.1097/MD.0000000000005641

Armitage LC, Davidson S, Mahdi A Diagnosing hypertension in primary care: a retrospective cohort study to investigate the importance of night-time blood pressure assessment. Br J Gen Pract. 2023; 73:(726)e16-e23 https://doi.org/10.3399/BJGP.2022.0160

Barratt J. Developing clinical reasoning and effective communication skills in advanced practice. Nurs Stand. 2018; 34:(2)48-53 https://doi.org/10.7748/ns.2018.e11109

Bostock-Cox B. Nurse prescribing for the management of hypertension. British Journal of Cardiac Nursing. 2013; 8:(11)531-536

Bostock-Cox B. Hypertension – the present and the future for diagnosis. Independent Nurse. 2019; 2019:(1)20-24 https://doi.org/10.12968/indn.2019.1.20

Chakrabarti S. What's in a name? Compliance, adherence and concordance in chronic psychiatric disorders. World J Psychiatry. 2014; 4:(2)30-36 https://doi.org/10.5498/wjp.v4.i2.30

De Mauri A, Carrera D, Vidali M Compliance, adherence and concordance differently predict the improvement of uremic and microbial toxins in chronic kidney disease on low protein diet. Nutrients. 2022; 14:(3) https://doi.org/10.3390/nu14030487

Demosthenous N. Consultation skills: a personal reflection on history-taking and assessment in aesthetics. Journal of Aesthetic Nursing. 2017; 6:(9)460-464 https://doi.org/10.12968/joan.2017.6.9.460

Diamond-Fox S. Undertaking consultations and clinical assessments at advanced level. Br J Nurs. 2021; 30:(4)238-243 https://doi.org/10.12968/bjon.2021.30.4.238

Diamond-Fox S, Bone H. Advanced practice: critical thinking and clinical reasoning. Br J Nurs. 2021; 30:(9)526-532 https://doi.org/10.12968/bjon.2021.30.9.526

Donnelly M, Martin D. History taking and physical assessment in holistic palliative care. Br J Nurs. 2016; 25:(22)1250-1255 https://doi.org/10.12968/bjon.2016.25.22.1250

Fawcett J. Thoughts about meanings of compliance, adherence, and concordance. Nurs Sci Q. 2020; 33:(4)358-360 https://doi.org/10.1177/0894318420943136

Fisher NDL, Curfman G. Hypertension—a public health challenge of global proportions. JAMA. 2018; 320:(17)1757-1759 https://doi.org/10.1001/jama.2018.16760

Green S. Assessment and management of acute sore throat. Pract Nurs. 2015; 26:(10)480-486 https://doi.org/10.12968/pnur.2015.26.10.480

Harper C, Ajao A. Pendleton's consultation model: assessing a patient. Br J Community Nurs. 2010; 15:(1)38-43 https://doi.org/10.12968/bjcn.2010.15.1.45784

Hitchings A, Lonsdale D, Burrage D, Baker E. The Top 100 Drugs; Clinical Pharmacology and Practical Prescribing, 2nd edn. Scotland: Elsevier; 2019

Hobden A. Strategies to promote concordance within consultations. Br J Community Nurs. 2006; 11:(7)286-289 https://doi.org/10.12968/bjcn.2006.11.7.21443

Ingram S. Taking a comprehensive health history: learning through practice and reflection. Br J Nurs. 2017; 26:(18)1033-1037 https://doi.org/10.12968/bjon.2017.26.18.1033

James A, Holloway S. Application of concepts of concordance and health beliefs to individuals with pressure ulcers. British Journal of Healthcare Management. 2020; 26:(11)281-288 https://doi.org/10.12968/bjhc.2019.0104

Jamison J. Differential diagnosis for primary care. A handbook for health care practitioners, 2nd edn. China: Churchill Livingstone Elsevier; 2006

History and Physical Examination. 2021. https://patient.info/doctor/history-and-physical-examination (accessed 26 January 2023)

Kumar P, Clark M. Clinical Medicine, 9th edn. The Netherlands: Elsevier; 2017

Matthys J, Elwyn G, Van Nuland M Patients' ideas, concerns, and expectations (ICE) in general practice: impact on prescribing. Br J Gen Pract. 2009; 59:(558)29-36 https://doi.org/10.3399/bjgp09X394833

McKinnon J. The case for concordance: value and application in nursing practice. Br J Nurs. 2013; 22:(13)766-771 https://doi.org/10.12968/bjon.2013.22.13.766

McPhillips H, Wood AF, Harper-McDonald B. Conducting a consultation and clinical assessment of the skin for advanced clinical practitioners. Br J Nurs. 2021; 30:(21)1232-1236 https://doi.org/10.12968/bjon.2021.30.21.1232

Moulton L. The naked consultation; a practical guide to primary care consultation skills.Abingdon: Radcliffe Publishing; 2007

Medicine adherence; involving patients in decisions about prescribed medications and supporting adherence.England: NICE; 2009

National Institute for Health and Care Excellence. How do I control my blood pressure? Lifestyle options and choice of medicines patient decision aid. 2019. https://www.nice.org.uk/guidance/ng136/resources/patient-decision-aid-pdf-6899918221 (accessed 25 January 2023)

National Institute for Health and Care Excellence. Hypertension in adults: diagnosis and management. NICE guideline NG136. 2022. https://www.nice.org.uk/guidance/ng136 (accessed 15 June 2023)

Nazarko L. Healthwise, Part 4. Hypertension: how to treat it and how to reduce its risks. Br J Healthc Assist. 2021; 15:(10)484-490 https://doi.org/10.12968/bjha.2021.15.10.484

Neighbour R. The inner consultation.London: Radcliffe Publishing Ltd; 1987

The Code. professional standards of practice and behaviour for nurses, midwives and nursing associates.London: NMC; 2018

Nuttall D, Rutt-Howard J. The textbook of non-medical prescribing, 2nd edn. Chichester: Wiley-Blackwell; 2016

O'Donovan K. The role of ACE inhibitors in cardiovascular disease. British Journal of Cardiac Nursing. 2018; 13:(12)600-608 https://doi.org/10.12968/bjca.2018.13.12.600

O'Donovan K. Angiotensin receptor blockers as an alternative to angiotensin converting enzyme inhibitors. British Journal of Cardiac Nursing. 2019; 14:(6)1-12 https://doi.org/10.12968/bjca.2019.0009

Porth CM. Essentials of Pathophysiology, 4th edn. Philadelphia: Wolters Kluwer; 2015

Rae B. Obedience to collaboration: compliance, adherence and concordance. Journal of Prescribing Practice. 2021; 3:(6)235-240 https://doi.org/10.12968/jprp.2021.3.6.235

Rostoft S, van den Bos F, Pedersen R, Hamaker ME. Shared decision-making in older patients with cancer - What does the patient want?. J Geriatr Oncol. 2021; 12:(3)339-342 https://doi.org/10.1016/j.jgo.2020.08.001

Schroeder K. The 10-minute clinical assessment, 2nd edn. Oxford: Wiley Blackwell; 2017

Thomas J, Monaghan T. The Oxford handbook of clinical examination and practical skills, 2nd edn. Oxford: Oxford University Press; 2014

Vincer K, Kaufman G. Balancing shared decision-making with ethical principles in optimising medicines. Nurse Prescribing. 2017; 15:(12)594-599 https://doi.org/10.12968/npre.2017.15.12.594

Waterfield J. ACE inhibitors: use, actions and prescribing rationale. Nurse Prescribing. 2008; 6:(3)110-114 https://doi.org/10.12968/npre.2008.6.3.28858

Weiss M. Concordance, 6th edn. In: Watson J, Cogan LS Poland: Elsevier; 2019

Williams H. An update on hypertension for nurse prescribers. Nurse Prescribing. 2013; 11:(2)70-75 https://doi.org/10.12968/npre.2013.11.2.70

Adherence to long-term therapies, evidence for action.Geneva: WHO; 2003

Young K, Franklin P, Franklin P. Effective consulting and historytaking skills for prescribing practice. Br J Nurs. 2009; 18:(17)1056-1061 https://doi.org/10.12968/bjon.2009.18.17.44160

Newly diagnosed hypertension: case study

Angela Brown

Trainee Advanced Nurse Practitioner, East Belfast GP Federation, Northern Ireland

View articles · Email Angela

The role of an advanced nurse practitioner encompasses the assessment, diagnosis and treatment of a range of conditions. This case study presents a patient with newly diagnosed hypertension. It demonstrates effective history taking, physical examination, differential diagnoses and the shared decision making which occurred between the patient and the professional. It is widely acknowledged that adherence to medications is poor in long-term conditions, such as hypertension, but using a concordant approach in practice can optimise patient outcomes. This case study outlines a concordant approach to consultations in clinical practice which can enhance adherence in long-term conditions.

Hypertension is a worldwide problem with substantial consequences ( Fisher and Curfman, 2018 ). It is a progressive condition ( Jamison, 2006 ) requiring lifelong management with pharmacological treatments and lifestyle adjustments. However, adopting these lifestyle changes can be notoriously difficult to implement and sustain ( Fisher and Curfman, 2018 ) and non-adherence to chronic medication regimens is extremely common ( Abegaz et al, 2017 ). This is also recognised by the National Institute for Health and Care Excellence (NICE) (2009) which estimates that between 33.3% and 50% of medications are not taken as recommended. Abegaz et al (2017) furthered this by claiming 83.7% of people with uncontrolled hypertension do not take medications as prescribed. However, leaving hypertension untreated or uncontrolled is the single largest cause of cardiovascular disease ( Fisher and Curfman, 2018 ). Therefore, better adherence to medications is associated with better outcomes ( World Health Organization, 2003 ) in terms of reducing the financial burden associated with the disease process on the health service, improving outcomes for patients ( Chakrabarti, 2014 ) and increasing job satisfaction for professionals ( McKinnon, 2013 ). Therefore, at a time when growing numbers of patients are presenting with hypertension, health professionals must adopt a concordant approach from the initial consultation to optimise adherence.

Great emphasis is placed on optimising adherence to medications ( NICE, 2009 ), but the meaning of the term ‘adherence’ is not clear and it is sometimes used interchangeably with compliance and concordance ( De Mauri et al, 2022 ), although they are not synonyms. Compliance is an outdated term alluding to paternalism, obedience and passivity from the patient ( Rae, 2021 ), whereby the patient's behaviour must conform to the health professional's recommendations. Adherence is defined as ‘the extent to which a person's behaviour, taking medication, following a diet and/or executing lifestyle changes, corresponds with agreed recommendations from a health care provider’ ( Chakrabarti, 2014 ). This term is preferred over compliance as it is less paternalistic ( Rae, 2021 ), as the patient is included in the decision-making process and has agreed to the treatment plan. While it is not yet widely embraced or used in practice ( Fawcett, 2020 ), concordance is recognised, not as a behaviour ( Rae, 2021 ) but more an approach or method which focuses on the equal partnership between patient and professional ( McKinnon, 2013 ) and enables effective and agreed treatment plans.

NICE last reviewed its guidance on medication adherence in 2019 and did not replace adherence with concordance within this. This supports the theory that adherence is an outcome of good concordance and the two are not synonyms. NICE (2009) guidelines, which are still valid, show evidence of concordant principles to maximise adherence. Integrating the theoretical principles of concordance into this case study demonstrates how the trainee advanced nurse practitioner aimed to individualise patient-centred care and improve health outcomes through optimising adherence.

Patient introduction and assessment

Jane (a pseudonym has been used to protect the patient's anonymity; Nursing and Midwifery Council (NMC) 2018 ), is a 45-year-old woman who had been referred to the surgery following an attendance at an emergency department. Jane had been role-playing as a patient as part of a teaching session for health professionals when it was noted that her blood pressure was significantly elevated at 170/88 mmHg. She had no other symptoms. Following an initial assessment at the emergency department, Jane was advised to contact her GP surgery for review and follow up. Nazarko (2021) recognised that it is common for individuals with high blood pressure to be asymptomatic, contributing to this being referred to as the ‘silent killer’. Hypertension is generally only detected through opportunistic checking of blood pressure, as seen in Jane's case, which is why adults over the age of 40 years are offered a blood pressure check every 5 years ( Bostock-Cox, 2013 ).

Consultation

Jane presented for a consultation at the surgery. Green (2015) advocates using a model to provide a structured approach to consultations which ensures quality and safety, and improves time management. Young et al (2009) claimed that no single consultation model is perfect, and Diamond-Fox (2021) suggested that, with experience, professionals can combine models to optimise consultation outcomes. Therefore, to effectively consult with Jane and to adapt to her individual personality, different models were intertwined to provide better person-centred care.

The Calgary–Cambridge model is the only consultation model that places emphasis on initiating the session, despite it being recognised that if a consultation gets off to a bad start this can interfere throughout ( Young et al, 2009 ). Being prepared for the consultation is key. Before Jane's consultation, the environment was checked to minimise interruptions, ensuring privacy and dignity ( Green, 2015 ; NMC, 2018 ), the seating arrangements optimised to aid good body language and communication ( Diamond-Fox, 2021 ) and her records were viewed to give some background information to help set the scene and develop a rapport ( Young et al, 2009 ). Being adequately prepared builds the patient's trust and confidence in the professional ( Donnelly and Martin, 2016 ) but equally viewing patient information can lead to the professional forming preconceived ideas ( Donnelly and Martin, 2016 ). Therefore, care was taken by the trainee advanced nurse practitioner to remain open-minded.

During Jane's consultation, a thorough clinical history was taken ( Table 1 ). History taking is common to all consultation models and involves gathering important information ( Diamond-Fox, 2021 ). History-taking needs to be an effective ( Bostock-Cox, 2019 ), holistic process ( Harper and Ajao, 2010 ) in order to be thorough, safe ( Diamond-Fox, 2021 ) and aid in an accurate diagnosis. The key skill for taking history is listening and observing the patient ( Harper and Ajao, 2010 ). Sir William Osler said:‘listen to the patient as they are telling you the diagnosis’, but Knott and Tidy (2021) suggested that patients are barely given 20 seconds before being interrupted, after which they withdraw and do not offer any new information ( Demosthenous, 2017 ). Using this guidance, Jane was given the ‘golden minute’ allowing her to tell her ‘story’ without being interrupted ( Green, 2015 ). This not only showed respect ( Ingram, 2017 ) but interest in the patient and their concerns.

Once Jane shared her story, it was important for the trainee advanced nurse practitioner to guide the questioning ( Green 2015 ). This was achieved using a structured approach to take Jane's history, which optimised efficiency and effectiveness, and ensured that pertinent information was not omitted ( Young et al, 2009 ). Thomas and Monaghan (2014) set out clear headings for this purpose. These included:

• The presenting complaint
• Past medical history
• Drug history
• Social history
• Family history.

McPhillips et al (2021) also emphasised a need for a systemic enquiry of the other body systems to ensure nothing is missed. From taking this history it was discovered that Jane had been feeling well with no associated symptoms or red flags. A blood pressure reading showed that her blood pressure was elevated. Jane had no past medical history or allergies. She was not taking any medications, including prescribed, over the counter, herbal or recreational. Jane confirmed that she did not drink alcohol or smoke. There was no family history to note, which is important to clarify as a genetic link to hypertension could account for 30–50% of cases ( Nazarko, 2021 ). The information gathered was summarised back to Jane, showing good practice ( McPhillips et al, 2021 ), and Jane was able to clarify salient or missing points. Green (2015) suggested that optimising the patient's involvement in this way in the consultation makes her feel listened to which enhances patient satisfaction, develops a therapeutic relationship and demonstrates concordance.

During history taking it is important to explore the patient's ideas, concerns and expectations. Moulton (2007) refers to these as the ‘holy trinity’ and central to upholding person-centredness ( Matthys et al, 2009 ). Giving Jane time to discuss her ideas, concerns and expectations allowed the trainee advanced nurse practitioner to understand that she was concerned about her risk of a stroke and heart attack, and worried about the implications of hypertension on her already stressful job. Using ideas, concerns and expectations helped to understand Jane's experience, attitudes and perceptions, which ultimately will impact on her health behaviours and whether engagement in treatment options is likely ( James and Holloway, 2020 ). Establishing Jane's views demonstrated that she was eager to engage and manage her blood pressure more effectively.

Vincer and Kaufman (2017) demonstrated, through their case study, that a failure to ask their patient's viewpoint at the initial consultation meant a delay in engagement with treatment. They recognised that this delay could have been avoided with the use of additional strategies had ideas, concerns and expectations been implemented. Failure to implement ideas, concerns and expectations is also associated with reattendance or the patient seeking second opinions ( Green, 2015 ) but more positively, when ideas, concerns and expectations is implemented, it can reduce the number of prescriptions while sustaining patient satisfaction ( Matthys et al, 2009 ).

Physical examination

Once a comprehensive history was taken, a physical examination was undertaken to supplement this information ( Nuttall and Rutt-Howard, 2016 ). A physical examination of all the body systems is not required ( Diamond-Fox, 2021 ) as this would be extremely time consuming, but the trainee advanced nurse practitioner needed to carefully select which systems to examine and use good examination technique to yield a correct diagnosis ( Knott and Tidy, 2021 ). With informed consent, clinical observations were recorded along with a full cardiovascular examination. The only abnormality discovered was Jane's blood pressure which was 164/90 mmHg, which could suggest stage 2 hypertension ( NICE, 2019 ; 2022 ). However, it is the trainee advanced nurse practitioner's role to use a hypothetico-deductive approach to arrive at a diagnosis. This requires synthesising all the information from the history taking and physical examination to formulate differential diagnoses ( Green, 2015 ) from which to confirm or refute before arriving at a final diagnosis ( Barratt, 2018 ).

Differential diagnosis

Hypertension can be triggered by secondary causes such as certain drugs (non-steroidal anti-inflammatory drugs, steroids, decongestants, sodium-containing medications or combined oral contraception), foods (liquorice, alcohol or caffeine; Jamison, 2006 ), physiological response (pain, anxiety or stress) or pre-eclampsia ( Jamison, 2006 ; Schroeder, 2017 ). However, Jane had clarified that these were not contributing factors. Other potential differentials which could not be ruled out were the white-coat syndrome, renal disease or hyperthyroidism ( Schroeder, 2017 ). Further tests were required, which included bloods, urine albumin creatinine ratio, electrocardiogram and home blood pressure monitoring, to ensure a correct diagnosis and identify any target organ damage.

Joint decision making

At this point, the trainee advanced nurse practitioner needed to share their knowledge in a meaningful way to enable the patient to participate with and be involved in making decisions about their care ( Rostoft et al, 2021 ). Not all patients wish to be involved in decision making ( Hobden, 2006 ) and this must be respected ( NMC, 2018 ). However, engaging patients in partnership working improves health outcomes ( McKinnon, 2013 ). Explaining the options available requires skill so as not to make the professional seem incompetent and to ensure the patient continues to feel safe ( Rostoft et al, 2021 ).

Information supported by the NICE guidelines was shared with Jane. These guidelines advocated that in order to confirm a diagnosis of hypertension, a clinic blood pressure reading of 140/90 mmHg or higher was required, with either an ambulatory or home blood pressure monitoring result of 135/85 mmHg or higher ( NICE, 2019 ; 2022 ). However, the results from a new retrospective study suggested that the use of home blood pressure monitoring is failing to detect ‘non-dippers’ or ‘reverse dippers’ ( Armitage et al, 2023 ). These are patients whose blood pressure fails to fall during their nighttime sleep. This places them at greater risk of cardiovascular disease and misdiagnosis if home blood pressure monitors are used, but ambulatory blood pressure monitors are less frequently used in primary care and therefore home blood pressure monitors appear to be the new norm ( Armitage et al, 2023 ).

Having discussed this with Jane she was keen to engage with home blood pressure monitoring in order to confirm the potential diagnosis, as starting a medication without a true diagnosis of hypertension could potentially cause harm ( Jamison, 2006 ). An accurate blood pressure measurement is needed to prevent misdiagnosis and unnecessary therapy ( Jamison, 2006 ) and this is dependent on reliable and calibrated equipment and competency in performing the task ( Bostock-Cox, 2013 ). Therefore, Jane was given education and training to ensure the validity and reliability of her blood pressure readings.

For Jane, this consultation was the ideal time to offer health promotion advice ( Green, 2015 ) as she was particularly worried about her elevated blood pressure. Offering health promotion advice is a way of caring, showing support and empowerment ( Ingram, 2017 ). Therefore, Jane was provided with information on a healthy diet, the reduction of salt intake, weight loss, exercise and continuing to abstain from smoking and alcohol ( Williams, 2013 ). These were all modifiable factors which Jane could implement straight away to reduce her blood pressure.

Safety netting

The final stage and bringing this consultation to a close was based on the fourth stage of Neighbour's (1987) model, which is safety netting. Safety netting identifies appropriate follow up and gives details to the patient on what to do if their condition changes ( Weiss, 2019 ). It is important that the patient knows who to contact and when ( Young et al, 2009 ). Therefore, Jane was advised that, should she develop chest pains, shortness of breath, peripheral oedema, reduced urinary output, headaches, visual disturbances or retinal haemorrhages ( Schroeder, 2017 ), she should present immediately to the emergency department, otherwise she would be reviewed in the surgery in 1 week.

Jane was followed up in a second consultation 1 week later with her home blood pressure readings. The average reading from the previous 6 days was calculated ( Bostock-Cox, 2013 ) and Jane's home blood pressure reading was 158/82 mmHg. This reading ruled out white-coat syndrome as Jane's blood pressure remained elevated outside clinic conditions (white-coat syndrome is defined as a difference of more than 20/10 mmHg between clinic blood pressure readings and the average home blood pressure reading; NICE, 2019 ; 2022 ). Subsequently, Jane was diagnosed with stage 2 essential (or primary) hypertension. Stage 2 is defined as a clinic blood pressure of 160/100 mmHg or higher or a home blood pressure of 150/95 mmHg or higher ( NICE, 2019 ; 2022 ).

A diagnosis of hypertension can be difficult for patients as they obtain a ‘sick label’ despite feeling well ( Jamison, 2006 ). This is recognised as a deterrent for their motivation to initiate drug treatment and lifestyle changes ( Williams, 2013 ), presenting a greater challenge to health professionals, which can be addressed through concordance strategies. However, having taken Jane's bloods, electrocardiogram and urine albumin:creatinine ratio in the first consultation, it was evident that there was no target organ damage and her Qrisk3 score was calculated as 3.4%. These results provided reassurance for Jane, but she was keen to engage and prevent any potential complications.

Agreeing treatment

Concordance is only truly practised when the patient's perspectives are valued, shared and used to inform planning ( McKinnon, 2013 ). The trainee advanced nurse practitioner now needed to use the information gained from the consultations to formulate a co-produced and meaningful treatment plan based on the best available evidence ( Diamond-Fox and Bone, 2021 ). Jane understood the risk associated with high blood pressure and was keen to begin medication as soon as possible. NICE guidelines ( 2019 ; 2022 ) advocate the use of an angiotensin-converting enzyme (ACE) inhibitor or angiotensin-receptor blockers in patients under 55 years of age and not of Black African or African-Caribbean origin. However, ACE inhibitors seem to be used as the first-line treatment for hypertensive patients under the age of 55 years ( O'Donovan, 2019 ).

ACE inhibitors directly affect the renin–angiotensin-aldosterone system which plays a central role in regulation of blood pressure ( Porth, 2015 ). Renin is secreted by the juxtaglomerular cells, in the kidneys' nephrons, when there is a decrease in renal perfusion and stimulation of the sympathetic nervous system ( O'Donovan, 2018 ). Renin then combines with angiotensinogen, a circulating plasma globulin from the liver, to form angiotensin I ( Kumar and Clark, 2017 ). Angiotensin I is inactive but, through ACE, an enzyme present in the endothelium of the lungs, it is transformed into angiotensin II ( Kumar and Clark, 2017 ). Angiotensin II is a vasoconstrictor which increases vascular resistance and in turn blood pressure ( Porth, 2015 ) while also stimulating the adrenal gland to produce aldosterone. Aldosterone reduces sodium excretion in the kidneys, thus increasing water reabsorption and therefore blood volume ( Porth, 2015 ). Using an ACE inhibitor prevents angiotensin II formation, which prevents vasoconstriction and stops reabsorption of sodium and water, thus reducing blood pressure.

When any new medication is being considered, providing education is key. This must include what the medication is for, the importance of taking it, any contraindications or interactions with the current medications being taken by the patient and the potential risk of adverse effects ( O'Donovan, 2018 ). Sharing this information with Jane allowed her to weigh up the pros and cons and make an informed choice leading to the creation of an individualised treatment plan.

Jamison (2006) placed great emphasis on sharing information about adverse effects, because patients with hypertension feel well before commencing medications, but taking medication has the potential to cause side effects which can affect adherence. Therefore, the range of side effects were discussed with Jane. These include a persistent, dry non-productive cough, hypotension, hypersensitivity, angioedema and renal impairment with hyperkalaemia ( Hitchings et al, 2019 ). ACE inhibitors have a range of adverse effects and most resolve when treatment is stopped ( Waterfield, 2008 ).

Following discussion with Jane, she proceeded with taking an ACE inhibitor and was encouraged to report any side effects in order to find another more suitable medication and to prevent her hypertension from going untreated. This information was provided verbally and written which is seen as good practice ( Green, 2015 ). Jane was followed up with fortnightly blood pressure recordings and urea and electrolyte checks and her dose of ramipril was increased fortnightly until her blood pressure was under 140/90 mmHg ( NICE, 2019 ; 2022 ).

Conclusions

Adherence to medications can be difficult to establish and maintain, especially for patients with long-term conditions. This can be particularly challenging for patients with hypertension because they are generally asymptomatic, yet acquire a sick label and start lifelong medication and lifestyle adjustments to prevent complications. Through adopting a concordant approach in practice, the outcome of adherence can be increased. This case study demonstrates how concordant strategies were implemented throughout the consultation to create a therapeutic patient–professional relationship. This optimised the creation of an individualised treatment plan which the patient engaged with and adhered to.

• Hypertension is a growing worldwide problem
• Appropriate clinical assessment, diagnosis and management is key to prevent misdiagnosis
• Long-term conditions are associated with high levels of non-adherence to treatments
• Adopting a concordance approach to practice optimises adherence and promotes positive patient outcomes

CPD reflective questions

• How has this article developed your assessment, diagnosis or management of patients presenting with a high blood pressure?
• What measures can you implement in your practice to enhance a concordant approach?

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
• Front Cardiovasc Med
• PMC10241069

Editorial: Case reports in hypertension: 2022

Editorial on the Research Topic Case reports in hypertension: 2022

1. Introduction

Clinical guidelines for the management of hypertension are regularly updated, and the whole community of hypertension specialists is longing for the promised new guidelines of the ESH/ESC expected to be released in June 2023. Despite the availability of such important reference points, in daily practice, the management of hypertension often requires refined clinical skills. This is particularly true when facing peculiar hypertensive cases such as resistant hypertension or hypertension of the young, particularly in non-obese patients. In these cases, the possibility to diagnose a secondary form of hypertension is particularly high but requires that all the possible causes are explored, even those that are less frequent. This is when the investigative capabilities of the clinician come to play only if supported by a profound knowledge of the physiopathology of the disease.

In this series of clinical cases in hypertension, five papers were published from January 2022 to January 2023. Again, the relevance of a similar Research Topic is confirmed by its impact around the world ( Figure 1 ). The treated cases focus on specific cases, which are sometimes neglected by the guidelines for the lack of specific clinical trials. Two cases approach the adrenal gland as causative of hypertension, one discusses the renal artery, and two more identify an oncological cause of the disease with very well-hidden tumors. Altogether, these cases point to emerging clinical conditions in hypertension and the possibility of novel technology for their management.

Impact of the research topic: the number of downloads of papers on this research topic from around the world since 2022.

2. A modern approach to classifying renal artery fibrodysplasia

Fibromuscular dysplasia (FMD) is the second most common etiology of renal artery stenosis (RAS) and renovascular hypertension, especially in young patients ( 1 ). FMD is a systemic arterial disease presenting as arterial stenosis, aneurysm, and dissection in virtually any arterial bed. When affecting the renal artery, FMD causes significant cardiovascular manifestations including renovascular hypertension. Although several studies have demonstrated the benefits of renal artery revascularization, it is difficult to predict the real benefit of this procedure, and there is evidence that appropriate patient selection is, therefore, the key to avoiding therapeutic failure ( 2 ). In this report, Yuxi Li et al. borrow a hemodynamic assessment technology from coronary intervention using the combination of pressure guidewire [to calculate Flow Fractional Reserve (FFR)] and coherence tomography (OCT)-guided angioplasty treatment in a young hypertensive patient with renal FMD Li et al . The authors walk us through the interpretation of the data received from the combination of both technologies. In particular, OCT helps in confirming the diagnosis of the angiographically ambiguous lesion, properly classifying FMD, and guiding and optimizing the intervention. The FFR before and after the procedure demonstrated the efficient therapy of the stenosis with a significant reduction and normalization of the pressure gradient. The combined use of OCT and rFFR may improve the diagnosis and stratification of patients, and it will help identify patients who may respond to revascularization and guide the procedure.

3. Superselective adrenal arterial embolization in primary aldosteronism

Approximately 4%–5% of patients undergoing abdominal imaging report adrenal incidentaloma, with an increase in the number of patients in the age group. A similar percentage (6%) is reported in a series of 87,065 autopsies ( 3 ). Interventional radiology of the adrenal glands represents an important interventional radiologic procedure indicated during primary aldosteronism (PA). Hokotate et al. ( 4 ) reported that 33 cases of aldosteronism were treated with embolization. The results were encouraging. The plasma levels of aldosterone returned to normal in 82% of patients. In this issue, the case report of a successful selective embolization of the adrenal adenoma in a 39-year-old man with a 5-year history of hypertension was discussed Zhou et al.

4. Primary Aldosteronism and Subclinical Cushing Syndrome

Over the years, the approach to identifying, diagnosing, and treating primary aldosteronism has remained unchanged and often focuses on detecting and treating the more severe symptoms of the condition. However, recent evidence shows that the prevalence of primary aldosteronism is higher than previously thought and that the small and abnormal production of aldosterone without renin alteration may cause an increase in cardiovascular risk ( 5 ). The CoSh syndrome (synchronous adrenal aldosterone and excess cortisol) is a distinct entity in PA, as described by Arlt et al. in 2017 ( 6 ). The disease has been studied for more than 40 years. Recently, this has become one of the most dynamic topics in hormonally active adrenal lesions due to significant progress in steroid metabolomics, molecular genetics of the immune CYP11B1/B2 gene constellation, and newly developed pathological types in the 2022 WHO classification ( 6 ). Lihua Hu et al. described the management of a 49-year-old woman with coexisting primary aldosteronism (PA) and subclinical Cushing's syndrome due to a right adrenal adenoma. Hu et al.

5. Pheochromocytoma of the urinary bladder

According to existing literature, pheochromocytomas account for 0.05%–0.1% of patients with hypertension ( 7 ). Although paroxysmal or resistant hypertension is still a major cause for the diagnostic workup of pheochromocytoma, there is a steadily increasing proportion of cases found as part of investigations for adrenal incidentalomas or accidentally found extra-adrenal paragangliomas showing few, if any, symptoms ( 7 ). Eighty to eighty-five percent are phaeochromocytomas arising from the adrenal medulla. Fifteen to twenty percent are sympathetic paragangliomas arising from the sympathetic ganglia in the thorax, abdomen, and pelvis ( 8 ). Liang-Liang Hu et al. describe the unusual localization of a paraganglioma/pheochromocytoma to the bladder of a 52-year-old woman with paroxysmal palpitations Hu et al .

6. Malignant hypertension

Malignant hypertension is defined as uncontrolled severe hypertension in the presence of acute organ damage including the brain, heart, and kidney. This condition is often associated with thrombotic microangiopathy, which is an expression of endothelial acute damage ( 9 ). For this reason, it has to be differentiated from thrombotic thrombocytopenic purpura, which addresses the management of the case toward plasma exchange. Bosisio et al. describe the case of a patient affected by malignant hypertension. Prior history of hypertension, high mean arterial pressure, significant renal impairment but relatively modest thrombocytopenia, and a lack of severe ADAMTS-13 deficiency (activity <10%) at diagnosis are clues to diagnose malignant hypertension-induced thrombotic microangiopathy Bosisio et al . This very well-described case allows the reader to focus on three major issues: (1) Malignant hypertension needs to be included in the flowchart for the diagnosis in the presence of acute syndrome in order to save time and prevent further damage; (2) fast reduction of blood pressure levels might as well favor the progression of the organ damage, given the reduced perfusion of target organs such as the heart or the kidney; (3) recidivism occurs, in particular, to those patients who do not adhere to treatment; therefore, strategies for improving adherence (including closer follow-ups) need to be put in place.

Author contributions

GI has conceived and written this Editorial.

Conflict of interest

The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher's note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Nursing case management for people with hypertension in primary health care: A randomized controlled trial

Affiliations.

• 1 Department of Nursing, Postgraduate Nursing Program, Federal University of Parana, Curitiba, Parana, Brazil.
• 2 Department of Nursing, Northern State University of Parana, Bandeirantes, Parana, Brazil.
• 3 Academic Department of Mathematics, Federal University of Technology, Cornelio Procopio, Parana, Brazil.
• PMID: 31710134
• DOI: 10.1002/nur.21994

Introduction: Hypertension is a chronic disease that requires continuous and long-term care to prevent or delay the development of associated complications. Although various interventions for hypertension exist, case management in Brazil's primary healthcare is understudied. We examined nursing case management effectiveness for controlling blood pressure among Brazilian adults with hypertension in the public healthcare system.

Method: A randomized controlled trial with a 12-month follow-up was conducted at a primary healthcare clinic in southern Brazil. Adult patients with hypertension were randomly allocated to intervention (n = 47) and usual care groups (n = 47). The nursing case management model includes nursing consultations, telephone contact, home visits, health education, and appropriate referrals. Patient outcomes (blood pressure, body mass index, waist circumference, quality of life, treatment adherence) were assessed at baseline and 6- and 12-month follow-up for the intervention group and at baseline and 12-month follow-up for the usual care group. Data were collected from only the intervention group at T6 to avoid contact between the researcher and the usual care group, and to check the care plan and modify it if necessary.

Results: After the intervention, the intervention group's blood pressure decreased significantly compared to the usual care group. The differences in systolic and diastolic blood pressure between the groups was -8.3 (intervention)/1.1 (usual care) mmHg (p = .004) and -7.4/-0.6 mmHg (p = .007), respectively. The intervention group had significantly greater improvement in waist circumference (-2.0/1.2 cm), body mass index (- 0.4/0.3), and treatment adherence (4.8/-1.1) than the usual care group (all p < .05).

Conclusion: Nursing case management in primary healthcare may be effective for improving outcomes among patients with hypertension.

Keywords: adult; blood pressure; body mass index; health education; quality of life; treatment adherence and compliance; waist circumference.

© 2019 Wiley Periodicals, Inc.

Publication types

• Randomized Controlled Trial
• Research Support, Non-U.S. Gov't
• Case Management / standards*
• Chronic Disease / therapy*
• Hypertension / nursing*
• Middle Aged
• Nursing Care / standards*
• Practice Guidelines as Topic*
• Primary Health Care / standards*

• 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

2 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]