Advancing Mental Health Diagnosis Using AI

ABSTRACT Introduction Mental health disorders are often misinterpreted or misdiagnosed, resulting in insufficient support. Artificial intelligence (AI) has emerged as a promising tool to improve the accuracy of early detection of mental disorders and facilitate early intervention. This study evaluates the effectiveness of AI-driven tools, including large language model (LLM) chatbots, speech analysis, and behavior tracking in identifying mental health disorders. This proof-of-concept study aimed to determine whether AI LLM models can improve diagnostic precision and enable earlier identification of at-risk individuals. Methods This proof-of-concept study used the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition Text Revision ( DSM-5-TR ) as the primary reference for diagnostic criteria. Owing to restricted access to public clinical records, 200 patient profiles were randomly generated by AI to simulate real-world psychiatric case data using information about mental health disorders as outlined in the DSM-5-TR . These profiles incorporated key information such as name, age, sex, health condition, lifestyle, and symptoms. Four AI LLM models, including ChatGPT, DeepSeek, Gemini, and Claude, were used to evaluate diagnostic performance. Each model’s ability to identify mental health disorders based on behavioral patterns and emotional distress was assessed using the DSM-5-TR criteria. Results The four AI models were evaluated using the following five-tier rating system: success (4/4), substantial success (3/4), moderate success (2/4), partial success (1/4), or failure (0/4). A rating of “substantial success” or “success” was classified as a correct diagnosis. Based on this criterion, the models achieved a combined success rate of 89.5% across the 200 simulated profiles, with ChatGPT outperforming the others in terms of accuracy, organization, and speed. AI models often accurately identified the specific DSM-5-TR disorder, but when the precise diagnosis was missed, it still recognized the broader symptom category. Conclusion Among the four AI models tested, ChatGPT delivered the best results due to its accuracy, speed, and well-organized responses. AI-based tools demonstrate significant potential in improving the accuracy and timeliness of mental health disorder diagnoses. Integrating these technologies into clinical practice could help healthcare providers enhance early intervention strategies and improve patient outcomes. Future research should focus on enhancing AI models for clinical integration, particularly by improving accuracy by considering additional factors.