This research introduces AutoPsyC, a system that leverages large language models to automatically identify psychodynamic conflicts from clinical interviews, a task previously requiring extensive manual expert analysis.

• Achieves comparable performance to human experts in recognizing psychological conflicts from semi-structured interviews
• Demonstrates that fine-tuned LLMs can effectively interpret complex psychological data without requiring extensive clinical training
• Provides a scalable approach to mental health diagnostics that could significantly reduce clinician workload

This innovation matters for healthcare by potentially making sophisticated psychological assessments more accessible and efficient, allowing clinicians to focus on treatment rather than time-consuming diagnoses.

AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models