Study guide
12.3 Biostatistics, Evidence-Based Medicine & Ethics
MRCPI in General Medicine Part I Written
Track your progress as you read
Finished sections get a check mark.
1 Chapter 1: Exam Structure, Strategy & Foundation
1.1 MRCPI Part I Format, Scoring & Standard-Setting 1.2 RCPI BST Curriculum & Single-Best-Answer Exam Strategy
2 Chapter 2: Cardiology & Vascular Medicine
2.1 Acute Coronary Syndromes & Stable Angina 2.2 Tachyarrhythmias, Bradyarrhythmias & Channelopathies 2.3 Heart Failure & Valvular Heart Disease 2.4 Hypertension, Vascular & Pericardial Diseases
3 Chapter 3: Respiratory Medicine
3.1 Asthma, COPD & Airway Diseases 3.2 Pneumonia, Tuberculosis & Respiratory Infections 3.3 Interstitial Lung Disease & Pleural Disorders 3.4 Pulmonary Embolism, Pulmonary Hypertension & Sleep Apnoea
4 Chapter 4: Gastroenterology & Hepatology
4.1 Upper & Lower GI Disorders & Inflammatory Bowel Disease 4.2 Acute & Chronic Liver Disease 4.3 Pancreatitis, Biliary Tract & GI Bleeding 4.4 Malabsorption, GI Motility & Clinical Nutrition
5 Chapter 5: Nephrology & Acid-Base Disorders
5.1 Acute Kidney Injury & Glomerular Diseases 5.2 Chronic Kidney Disease & Renal Replacement Therapy 5.3 Electrolyte Imbalances & Acid-Base Disorders
6 Chapter 6: Endocrinology & Diabetes
6.1 Diabetes Mellitus & Metabolic Complications 6.2 Thyroid & Calcium Disorders 6.3 Adrenal, Pituitary & Endocrine Syndromes
7 Chapter 7: Rheumatology & Clinical Immunology
7.1 Inflammatory Arthritides 7.2 Systemic Autoimmune & Vasculitic Diseases 7.3 Metabolic Bone Disease & Clinical Immunology
8 Chapter 8: Haematology & Medical Oncology
8.1 Anaemias, Haemostasis & Thrombosis 8.2 Leukaemias, Lymphomas & Plasma Cell Disorders 8.3 Medical Oncology & Oncological Emergencies
9 Chapter 9: Neurology & Dermatology
9.1 Stroke & Cerebrovascular Diseases 9.2 Epilepsy, Headache & Movement Disorders 9.3 Neuromuscular & Peripheral Nerve Disorders 9.4 Cutaneous Manifestations of Systemic Disease
10 Chapter 10: Acute Medicine, Critical Care & Geriatrics
10.1 Acute Poisoning & Toxidromes 10.2 Sepsis, Shock & Resuscitation 10.3 Geriatric Syndromes, Frailty & Comprehensive Care
11 Chapter 11: Clinical Pharmacology & Therapeutics
11.1 Pharmacokinetics & Pharmacodynamics 11.2 High-Risk Drug Classes & Prescribing Safety 11.3 Adverse Drug Reactions & Drug Safety
12 Chapter 12: Basic Sciences, Biostatistics & Clinical Ethics
12.1 Applied Cardiovascular & Respiratory Physiology 12.2 Clinical Biochemistry, Molecular Genetics & Microbiology 12.3 Biostatistics, Evidence-Based Medicine & Ethics
12.3 Biostatistics, Evidence-Based Medicine & Ethics
Key Takeaways Explain This Topic AI
Positive Predictive Value (PPV) and Negative Predictive Value (NPV) are directly dependent on disease prevalence, whereas Sensitivity and Specificity are intrinsic properties of the test.
Number Needed to Treat (NNT) is calculated as the inverse of Absolute Risk Reduction (NNT = 1 / ARR); values must always be rounded UP to the nearest whole integer.
Case-control studies select participants based on disease status, report Odds Ratios (OR), and are prone to recall bias; cohort studies select by exposure status, report Relative Risk (RR), and allow direct incidence rate calculations.
Intention-to-treat (ITT) analysis evaluates all randomized participants according to their original group assignment regardless of adherence, maintaining baseline balance and preventing attrition bias.
Autonomy respects a competent patient's right to refuse life-sustaining treatment, taking priority over beneficence provided the patient possesses decision-making capacity.
Last updated: July 2026
- 12.3 Biostatistics, Evidence-Based Medicine & Ethics
- Diagnostic Test Performance & 2x2 Contingency Tables
Evaluating diagnostic tests requires mastering 2x2 contingency tables and understanding how prevalence influences predictive values.
The 2x2 Diagnostic Matrix
- Test Result Disease Present Disease Absent Total
- Test Positive True Positive ( T P TP TP ) False Positive ( F P FP FP ) T P + F P TP + FP TP + FP
- Test Negative False Negative ( F N FN FN ) True Negative ( T N TN TN ) F N + T N FN + TN FN + TN
- Total T P + F N TP + FN TP + FN F P + T N FP + TN FP + TN N N N
- Core Diagnostic Equations
Sensitivity (True Positive Rate) : The proportion of individuals with the disease who test positive. Sensitivity = T P T P + F N \text{Sensitivity} = \frac{TP}{TP + FN} Sensitivity = TP + FN TP
Clinical Utility : High sensitivity tests have very few false negatives ( SnNout : a S ensitive test when N egative rules OUT the disease). Used for initial screening.
Specificity (True Negative Rate) : The proportion of individuals without the disease who test negative. Specificity = T N T N + F P \text{Specificity} = \frac{TN}{TN + FP} Specificity = TN + FP TN
Clinical Utility : High specificity tests have very few false positives ( SpPinn : a Sp ecific test when P ositive rules IN the disease). Used for diagnostic confirmation.
Positive Predictive Value (PPV) : The probability that a patient with a positive test actually has the disease. PPV = T P T P + F P \text{PPV} = \frac{TP}{TP + FP} PPV = TP + FP TP
Negative Predictive Value (NPV) : The probability that a patient with a negative test is truly free of the disease. NPV = T N T N + F N \text{NPV} = \frac{TN}{TN + FN} NPV = TN + FN TN
Critical Exam Concept: Impact of Disease Prevalence
Sensitivity and Specificity are intrinsic characteristics of a diagnostic test and do not change with disease prevalence.
PPV increases as disease prevalence increases in the screened population.
NPV decreases as disease prevalence increases in the screened population.
Likelihood Ratios (LR) : Combine sensitivity and specificity into a single metric independent of prevalence.
Positive Likelihood Ratio ( L R + LR+ L R + ) : Sensitivity 1 − Specificity = True Positive Rate False Positive Rate \frac{\text{Sensitivity}}{1 - \text{Specificity}} = \frac{\text{True Positive Rate}}{\text{False Positive Rate}} 1 − Specificity Sensitivity = False Positive Rate True Positive Rate . An L R + > 10 LR+ > 10 L R + > 10 strongly confirms the presence of disease.
Negative Likelihood Ratio ( L R − LR- L R − ) : 1 − Sensitivity Specificity = False Negative Rate True Negative Rate \frac{1 - \text{Sensitivity}}{\text{Specificity}} = \frac{\text{False Negative Rate}}{\text{True Negative Rate}} Specificity 1 − Sensitivity = True Negative Rate False Negative Rate . An L R − < 0.1 LR- < 0.1 L R − < 0.1 strongly rules out disease.
Clinical Study Designs, Measures of Association & Trial Analytics
Epidemiology categorizes study designs by intervention status, temporal sequence, and sampling method.
Observational & Interventional Study Designs
Cross-Sectional Study : Measures exposure and disease status simultaneously at a single point in time.
Primary Measure : Prevalence . Cannot determine temporal sequence or causality.
Case-Control Study : Retrospective study comparing individuals with the disease ("cases") to individuals without the disease ("controls") to assess prior exposure history.
Primary Measure : Odds Ratio (OR) ( O R = a × d b × c OR = \frac{a \times d}{b \times c} OR = b × c a × d ).
Biases : Highly susceptible to Recall Bias (cases remember past exposures differently than controls) and Selection Bias .
Cohort Study : Prospective or retrospective study tracking exposed and unexposed groups over time to observe disease incidence.
Primary Measure : Relative Risk (RR) ( R R = Incidence in Exposed Incidence in Unexposed = a / [ a + b ] c / [ c + d ] RR = \frac{\text{Incidence in Exposed}}{\text{Incidence in Unexposed}} = \frac{a / [a+b]}{c / [c+d]} RR = Incidence in Unexposed Incidence in Exposed = c / [ c + d ] a / [ a + b ] ) and Attributable Risk (AR) .
Advantage : Establishes temporal sequence; directly measures disease incidence.
Randomized Controlled Trial (RCT) : Gold standard for evaluating therapeutic efficacy. Participants are randomly allocated to treatment vs control groups.
Therapeutic Trial Metrics & Calculations
Consider a clinical trial comparing a novel oral anticoagulant against standard treatment for stroke prevention in atrial fibrillation:
Control Event Rate (CER) : Events in Control Group Total Control Patients \frac{\text{Events in Control Group}}{\text{Total Control Patients}} Total Control Patients Events in Control Group
Experimental Event Rate (EER) : Events in Treatment Group Total Treatment Patients \frac{\text{Events in Treatment Group}}{\text{Total Treatment Patients}} Total Treatment Patients Events in Treatment Group
Absolute Risk Reduction (ARR) : A R R = C E R − E E R ARR = CER - EER A RR = CER − EER
Relative Risk Reduction (RRR) : R R R = C E R − E E R C E R = A R R C E R = 1 − R R RRR = \frac{CER - EER}{CER} = \frac{ARR}{CER} = 1 - RR RRR = CER CER − EER = CER A RR = 1 − RR
Number Needed to Treat (NNT) : The number of patients who must receive the intervention to prevent one additional adverse outcome. N N T = 1 A R R = 1 C E R − E E R NNT = \frac{1}{ARR} = \frac{1}{CER - EER} NNT = A RR 1 = CER − EER 1 (Always round NNT UP to the next whole integer to avoid overestimating clinical benefit).
Number Needed to Harm (NNH) : N N H = 1 Absolute Risk Increase (ARI) = 1 E E R h a r m − C E R h a r m NNH = \frac{1}{\text{Absolute Risk Increase (ARI)}} = \frac{1}{EER_{harm} - CER_{harm}} NN H = Absolute Risk Increase (ARI) 1 = EE R ha r m − CE R ha r m 1
Analytical Strategies: ITT vs Per-Protocol
Intention-to-Treat (ITT) Analysis : Analyzes every patient in the group to which they were originally randomized, regardless of non-compliance, protocol deviations, or withdrawal.
Purpose : Preserves baseline randomization balance, reflects real-world clinical effectiveness, and prevents Attrition Bias .
Per-Protocol Analysis : Analyzes only patients who fully completed the trial protocol as assigned. Evaluates maximal potential efficacy but risks selection bias.
Biomedical Ethics, Informed Consent & Medical Law
Clinical ethics questions on the MRCPI assess decision-making frameworks under UK/Irish law and international ethical guidelines.
The Four Core Principles of Biomedical Ethics (Beauchamp & Childress)
Ethical Principle Core Definition Clinical Application / Scenario
Autonomy The obligation to respect a competent patient's self-determination and independent choices. A competent adult patient has the absolute legal and ethical right to refuse any medical treatment, including life-sustaining blood transfusions or mechanical ventilation.
Beneficence The duty to act in the best interests of the patient, promoting well-being and health. Providing evidence-based treatments, optimizing pain management, and advocating for preventive care.
Non-Maleficence The obligation to "do no harm" ( primum non nocere ). Avoiding futile interventions, minimizing drug toxicity, and weighing risk-benefit ratios before invasive procedures.
Justice The fair and equitable distribution of healthcare resources and non-discriminatory treatment. Triaging acute patients in emergency departments based on clinical urgency rather than socioeconomic status.
Decision-Making Capacity & Informed Consent
Decision-Making Capacity is time-specific and decision-specific. A patient is presumed competent unless proven otherwise. To possess capacity for a specific medical decision, a patient must be able to:
Understand the information relevant to the decision (nature, purpose, risks, benefits, alternatives).
Retain that information long enough to make the choice.
Weigh or use the information as part of the decision-making process.
Communicate their decision (by speech, sign language, or clear gestures).
If an adult patient lacks capacity:
Inspect for valid Advance Healthcare Directives (Living Wills) or designated Durable Power of Attorney / Healthcare Proxy .
If no advance directive exists, treatment decisions must be made in the patient's Best Interests , involving family/carers, multi-disciplinary teams, and independent advocates.
Confidentiality & Legal Exceptions to Disclosure
Confidentiality is a fundamental duty, but disclosure without patient consent is legally and ethically justified under specific conditions:
Express Consent : Patient explicitly consents to sharing information.
Statutory Requirement : Mandated by law (e.g., reporting specified communicable infectious diseases like tuberculosis or measles to public health authorities).
Public Interest / Harm Prevention : To prevent serious, imminent harm to third parties or the public (e.g., reporting a patient with uncontrolled epilepsy who continues driving against medical advice, or warning identifiable targets under duty to protect frameworks).