Abstract / Summary
Abstract Generative artificial intelligence (AI) offers new opportunities to improve the efficiency and scalability of Script Concordance Test (SCT) development in medical education. However, its use raises important concerns regarding validity, fairness, clinical accuracy and alignment with curricular outcomes. This monograph provides a practical guide for educators on using AI to design SCTs, including blueprinting, prompt construction, expert panel development, scoring, psychometric evaluation, bias auditing and sustainable item banking. AI should function as an adjunct to expert judgement, ensuring defensible, valid and educationally meaningful assessment while preserving authentic clinical reasoning.
Topics
Primary Source