Medicine and Surgery

PROGRAMME Diagnostic Study Design.Structure of a diagnostic accuracy study. The gold standard and the problem of verification bias. Accuracy Measures: Sensitivity and Specificity, Positive Predictive Values (PPV) and Negative Predictive Values (NPV).Likelihood Ratios (LRs): Positive LR (LR+) and Negative LR (LR-). Confidence intervals for accuracy measures. ROC Curves (Receiver Operating Characteristic). Application: Integrating diagnostic results into clinical practice. Practical Exercise: Critical appraisal of a diagnostic study article. Identifying the strengths and limitations in a real-world study. RCT Design and Structure. The role of RCTs in the hierarchy of evidence. Randomization (types, methods). Blinding (single, double, triple) and the problem of attrition bias. Selection and classification of endpoints (primary, secondary, composite). RCT Data Analysis. Intention-to-Treat (ITT) analysis vs. Per-Protocol analysis. Efficacy measures: Absolute Risk Reduction (ARR), Relative Risk Reduction (RRR), and Number Needed to Treat (NNT), and their confidence intervals. Practical Exercise: Critical appraisal of an RCT article. Evaluating its transferability to clinical practice (external validity). Systematic Reviews and Meta-Analysis. Ethical implications: informed consent and the role of the ethics committee. Introduction to AI in Medicine. Definitions: AI, Machine Learning (ML), Deep Learning. The role of Big Data and the necessity of high-quality data. Algorithm Development and Training Study designs for AI: training, validation, and test data sets. Specific performance measures for AI (e.g., Area Under the Curve - AUC). AI in Decision-Making and Ethics in Healthcare.