Evidence of transfer from AI-VP training to real clinical practice is scarce, and one cohort study found lower field assessment scores after AI-VP training¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Shorey et al. (2023) found students exposed to AI-VP simulations obtained lower clinical assessment scores in the field than a historical cohort without simulation. → Gilbert Valentin 2026

Evidence¶

Gilbert Valentin 2026¶

Gilbert Valentin, Philip Pierre, Llorca Pierre-Michel, Samalin Ludovic. (2026). Use of artificial intelligence–enhanced virtual patients in educational approaches to medical interview training: a systematic review. BMC Medical Education. https://doi.org/10.1186/s12909-026-08804-9

q2 · i? · causal · r1

Non-randomized comparative trial (Shorey et al. 2023, MMAT 2/5, single university, 24% attrition) comparing an AI-VP-trained cohort with a historical cohort. The review reports "lower scores in their clinical assessment in the field"; no effect size is printed.

"Shorey et al., 2023, showed that students exposed to simulations with AI-VPs obtain lower scores in their clinical assessment in the field, compared to a historical cohort without simulation."

Discussion¶

Related Claims¶

• Evidence on long-term retention and transfer of clinical communication skills to clinical practice remained inconsistent or lacking across included reviews — a broader claim this one bears on
• Controlled GenAI virtual-patient and communication studies reported short-term skill gains, but positive findings were not universal — related
• Learner self-reported improvement after AI-generated virtual patient training is sometimes discordant with observed or cohort-comparison performance — a broader claim this one bears on