Article of the day: research on AI in education

Assessment validity under generative AI, AI-resilient assessment, drift and compromise in educational measurement — only papers we read in full, with verified quotes.

Article for 2026-11-15

7.0
quasi_experiment

Assessment of Clinical Competence Using AI-Standardized Clinical Examination

Antonio Lopez, Ludovic Gabellier, Clement Peytavi, Zeno Loi, Emma Lavigne, Catherine Plotton, Vincent Dupont, Léon Jahdauti, P. De Vries, Philippe Thuillier, Maxence Compagnat, Pascale Vergne‐Salle, Mathieu Kuchenbuch, Eva Feigerlová, P. Berthelot, Nathalie Bednarek, Béatrice Cochener, Pierre-Yves Robert, Marc Braun, Denis Morin, Philippe Deruelle, Isabelle Laffont, Yves‐Marie Pers, Kévin Yauy · medRxiv (2026) · doi:10.64898/2026.10.01.26364500 · gemini-3.1-flash-lite

TL;DR

Researchers tested a new AI-based clinical exam where students interacted with AI patients and AI raters scored their performance. They found that students' scores on this AI exam correlated reasonably well with their actual scores on a high-stakes national exam. This suggests that AI could eventually help scale standardized assessments, though human review is still needed.

Method and sample: Prospective multicenter cohort study with 948 enrolled sixth-year medical students from six French universities. 588 students had paired ASCE and national OSCE scores. GPT-4o was used to simulate standardized patients, and GPT-4.1 to score transcripts against faculty-defined rubrics.

#AI-Standardized Clinical Examination#OSCE#Automated Scoring#Validity#Clinical Competence#Psychometrics

Read full analysis →