Work

Effectiveness of AI-enhanced virtual patients in clinical reasoning training of healthcare professionals and students: a systematic review

Year: 2026

Type: article

Abstract: Clinical reasoning is a core competency for healthcare students and professionals. However, current educational approaches may not adequately prepare learners for its complexity in practice. Virtual patients (VPs) provide a structured strategy for clinical reasoning education, and artificial intelligence (AI) may enhance their interactivity, adaptability, and feedback capacity. This study aimed to assess the effectiveness of AI-enhanced VPs in clinical reasoning training among healthcare professionals and students. We systematically searched PubMed/MEDLINE, Scopus, and ERIC. Records were screened at title/abstract and full-text stages by two independent reviewers. Data were extracted using a standardized form. Findings were synthesized descriptively, and methodological quality was assessed using the Mixed Methods Appraisal Tool (MMAT) 2018. The search retrieved 921 records, and 16 studies were included, with a total of 1,136 participants. Overall, 10 studies (63%) favored AI, 2 (13%) reported mixed findings, and 4 (25%) were not applicable. The most promising direction of effects was observed for clinical reasoning and history-taking performance, with 7 of 8 studies (88%) favoring AI. Favorable findings were also reported for learner perception or satisfaction (3/5, 60%), clinical competence/skills (3/5, 60%), diagnostic accuracy (1/3, 33%), and knowledge/retention (3/3, 100%). By AI role, tutor/mentor systems favored AI in 5 of 6 studies (83%), feedback generators in 8 of 10 (80%), simulation-only in 1 of 5 (20%), and adaptive narratives in 1 study. AI-enhanced VPs show promising potential for supporting clinical reasoning education, especially when used for history-taking, reasoning practice, feedback, or tutor/mentor support.

Source: BMC Medical Education

DOI: 10.1186/s12909-026-10242-6

Authors: Seyed Ali Mofidi, Zohreh Khoshgoftar

Institutions: Shahid Beheshti University, Shahid Beheshti University of Medical Sciences

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDGs: Good health and well-being, Quality education

Open Access status: gold

Estimated APC paid: $2,990