BMC Psychiatry, Год журнала: 2025, Номер 25(1)

Опубликована: Апрель 10, 2025

The Chat Generative Pre-trained Transformer (ChatGPT), an artificial intelligence-based web application, has demonstrated substantial potential across various knowledge domains, particularly in medicine. This cross-sectional study assessed the validity and possible usefulness of ChatGPT-4 assessing anxiety depression by comparing two questionnaires. tasked with generating a structured interview questionnaire based on validated Patient Health Questionnaire-9 (PHQ-9) Generalized Anxiety Disorder Scale-7 (GAD-7). These new measures were referred to as GPT-PHQ-9 GPT-GAD-7. utilized Spearman correlation analysis, Intra-class coefficients (ICC), Youden's index, receiver operating characteristic (ROC) Bland-Altman plots evaluate consistency between scores from adapted those questionnaire. A total 200 college students participated. Cronbach's α indicated acceptable reliability for both (α = 0.75) GPT-GAD-7 0.76). ICC values 0.80 PHQ-9 0.70 GAD-7. Spearman's showed moderate associations (p 0.63) GAD-7 0.68). ROC curve analysis revealed optimal cutoffs 9.5 depressive symptoms 6.5 symptoms, high sensitivity specificity. good Future studies should investigate ChatGPT designed different populations.

Язык: Английский