Enhancing Depression Diagnosis with Chain-of-Thought Prompting

TL;DR

This paper demonstrates that using chain-of-thought prompting with AI models improves the accuracy of depression severity assessments based on PHQ-8 scores, advancing AI's role in mental health diagnostics.

Contribution

It introduces the application of chain-of-thought prompting to enhance AI accuracy in depression diagnosis through PHQ-8 score evaluation.

Findings

CoT prompting yields PHQ-8 score estimates closer to true scores

AI models with CoT reasoning better understand patient conversations

Improved diagnostic accuracy with CoT in mental health assessment

Abstract

When using AI to detect signs of depressive disorder, AI models habitually draw preemptive conclusions. We theorize that using chain-of-thought (CoT) prompting to evaluate Patient Health Questionnaire-8 (PHQ-8) scores will improve the accuracy of the scores determined by AI models. In our findings, when the models reasoned with CoT, the estimated PHQ-8 scores were consistently closer on average to the accepted true scores reported by each participant compared to when not using CoT. Our goal is to expand upon AI models' understanding of the intricacies of human conversation, allowing them to more effectively assess a patient's feelings and tone, therefore being able to more accurately discern mental disorder symptoms; ultimately, we hope to augment AI models' abilities, so that they can be widely accessible and used in the medical field.