,
Department of Uzbek and Foreign Languages, Fergana Medical Institute of Public Health , Fergana , Uzbekistan
,
Associate Professor, Fergana State University , Fergana , Uzbekistan
,
Lecturer, Department of Pedagogy and Psychology, Termez University of Economics and Service , Termez , Uzbekistan
,
Lecturer, Jizzakh State Pedagogical University , Jizzakh , Uzbekistan
,
Associate Professor, Department of Languages, Tashkent Institute of Chemical Technology , Tashkent , Uzbekistan
,
Associate Professor, Tashkent State Medical University , Tashkent , Uzbekistan
Bukhara State Medical Institute named after Abu Ali ibn Sino , Bukhara , Uzbekistan
There is frequent conflict between diagnostic rigor and therapeutic empathy training in psychology undergraduates because students rarely encounter a variety of complex clinical presentations. This research investigates the usefulness of applying generative artificial intelligence (AI) clinical patient persona (GPT-4) by OpenAI to improve diagnostic accuracy and empathic interaction among psychology undergraduates. A quasi-experimental design was used, involving 124 third-year psychology students randomly assigned to either AI-persona training (n = 62) or traditional case-vignette training (n = 62) in a 6-week module. Structured simulated clinical interviews with dynamically responsive AI-generated personas simulating mood, anxiety, trauma-related, and personality disorders were provided to the intervention group. The measures were standardised using diagnostic accuracy rubrics and the Jefferson Scale of Empathy (JSE-S). Findings showed that students exposed to an AI persona had significantly better diagnostic accuracy (84.7% vs. 72.3%; p < .01) and better differentiation in diagnosis formulation (mean score change of 18.5; Cohen d = 0.74) than the controls. The JSE-S empathy scores increased by 21.2% in the intervention group compared with 8.9% in the control group (p < .01). Also, 89 % of the participants said they felt more confident in conducting clinical interviews, and 76 % said they felt more realistic than when using a static case study. The results indicate that clinical patient personas generated by generative AI can be a valuable addition to undergraduate psychology training, enhancing diagnostic competence and therapeutic empathy. A possible solution is to systematically incorporate simulated AI into training curricula, offering experience-based learning with scalable resource requirements at low cost, while maintaining ethical standards and pedagogical rigour.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
