Abstract
OBJECTIVES: This study presents a systematic review aimed at evaluating the effectiveness of virtual patients in enhancing clinical reasoning skills in medical education. A hybrid methodology was used, combining human reviewers and ChatGPT to assess the impact of conversational virtual patients on student learning outcomes and satisfaction. METHODS: Various studies involving conversational virtual patients were analyzed to determine the effect of these digital tools on clinical competencies. The hybrid review process incorporated both human assessments and AI-driven reviews, allowing a comparison of accuracy between the two approaches. RESULTS: Consistent with previous systematic reviews, our findings suggest that conversational virtual patients can improve clinical competencies, particularly in history-taking and clinical reasoning. Regarding student feedback, satisfaction tends to be higher when virtual patients' interactions are more realistic, often due to the use of artificial intelligence (AI) and natural language processing (NLP) in the simulators. Furthermore, the study compares the accuracy of AI-driven reviews with human assessments, revealing comparable results. CONCLUSIONS: This research highlights AI's potential to complement human expertise in academic evaluations, contributing to more efficient and consistent systematic reviews in rapidly evolving educational fields.