Abstract
INTRODUCTION: Mental health issues bring a heavy burden to individuals and societies around the world. Recently, the large language model ChatGPT has demonstrated potential in depression intervention. The primary objective of this study was to ascertain the viability of ChatGPT as a tool for aiding counselors in their interactions with patients while concurrently evaluating its comparability to human-generated content (HGC). METHODS: We propose a novel framework that integrates state-of-the-art AI technologies, including ChatGPT, BERT, and SHAP, to enhance the accuracy and effectiveness of mental health interventions. ChatGPT generates responses to user inquiries, which are then classified using BERT to ensure the reliability of the content. SHAP is subsequently employed to provide insights into the underlying semantic constructs of the AI-generated recommendations, enhancing the interpretability of the intervention. RESULTS: Remarkably, our proposed methodology consistently achieved an impressive accuracy rate of 93.76%. We discerned that ChatGPT always employs a polite and considerate tone in its responses. It refrains from using intricate or unconventional vocabulary and maintains an impersonal demeanor. These findings underscore the potential significance of AIGC as an invaluable complementary component in enhancing conventional intervention strategies. DISCUSSION: This study illuminates the considerable promise offered by the utilization of large language models in the realm of healthcare. It represents a pivotal step toward advancing the development of sophisticated healthcare systems capable of augmenting patient care and counseling practices.