"Crash Test Dummies" for AI-Enabled Clinical Assessment: Validating Virtual Patient Scenarios with Virtual Learners
Abstract
Background: In medical and health professions education (HPE), AI is increasingly used to assess clinical competencies, including via virtual standardized patients. However, most evaluations rely on AI-human interrater reliability and lack a measurement framework for how cases, learners, and raters jointly shape scores. This leaves robustness uncertain and can expose learners to misguidance from unvalidated systems. We address this by using AI "simulated learners" to stress-test and psychometrically characterize assessment pipelines before human use. Objective: Develop an open-source AI virtual patient platform and measurement model for robust competency evaluation across cases and rating conditions. Methods: We built a platform with virtual patients, virtual learners with tunable ACGME-aligned competency profiles, and multiple independent AI raters scoring encounters with structured Key-Features items. Transcripts were analyzed with a Bayesian HRM-SDT model that treats ratings as decisions under uncertainty and separates learner ability, case performance, and rater behavior; parameters were estimated with MCMC. Results: The model recovered simulated learners' competencies, with significant correlations to the generating competencies across all ACGME domains despite a non-deterministic pipeline. It estimated case difficulty by competency and showed stable rater detection (sensitivity) and criteria (severity/leniency thresholds) across AI raters using identical models/prompts but different seeds. We also propose a staged "safety blueprint" for deploying AI tools with learners, tied to entrustment-based validation milestones. Conclusions: Combining a purpose-built virtual patient platform with a principled psychometric model enables robust, interpretable, generalizable competency estimates and supports validation of AI-assisted assessment prior to use with human learners.
Keywords
Cite
@article{arxiv.2601.18085,
title = {"Crash Test Dummies" for AI-Enabled Clinical Assessment: Validating Virtual Patient Scenarios with Virtual Learners},
author = {Brian Gin and Ahreum Lim and Flávia Silva e Oliveira and Kuan Xing and Xiaomei Song and Gayana Amiyangoda and Thilanka Seneviratne and Alison F. Doubleday and Ananya Gangopadhyaya and Bob Kiser and Lukas Shum-Tim and Dhruva Patel and Kosala Marambe and Lauren Maggio and Ara Tekian and Yoon Soo Park},
journal= {arXiv preprint arXiv:2601.18085},
year = {2026}
}