Maqola

UTILIZING GENERATIVE AI CLINICAL PATIENT PERSONAS FOR ENHANCING DIAGNOSTIC ACCURACY AND THERAPEUTIC EMPATHY IN UNDERGRADUATE PSYCHOLOGY TRAINING

Komilova Mokhitabon Ramish QiziDepartment of Uzbek and Foreign Languages, Fergana Medical Institute of Public Health,Fergana,UzbekistanGo‘yoxon YakubovaAssociate Professor, Fergana State University,Fergana,UzbekistanShoxista XolmurotovaLecturer, Department of Pedagogy and Psychology, Termez University of Economics and Service,Termez,UzbekistanAzizbek MukhamedovLecturer, Jizzakh State Pedagogical University,Jizzakh,UzbekistanUmida DjalilovaAssociate Professor, Department of Languages, Tashkent Institute of Chemical Technology,Tashkent,UzbekistanAliya KadirbaevaAssociate Professor, Tashkent State Medical University,Tashkent,UzbekistanЖўраев, Бобур РахмоновичBukhara State Medical Institute named after Abu Ali ibn Sino,Bukhara,Uzbekistan

2026

Ochiq kirishOlmos

Litsenziya: cc-by-nc

ABI

Annotatsiya

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.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.70102/afts.2026.1835.691

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba