JMIR Publications

ABSTRACT

Background:

Depression is a major global healthcare challenge, causing significant individual distress but also contributing to a substantial global burden. Timely and accurate diagnosis is crucial. To help future clinicians develop these essential skills, we trained a GPT-powered chatbot to simulate patients with varying degrees of depression and suicidality.

Objective:

The Objective of this study is to evaluate the applicability and transferability of our GPT-4-powered chatbot for psychosomatic cases. Specifically, we aim to investigate how accurately the chatbot can simulate patients exhibiting various stages of depression and phases of suicidal ideation, while adhering to a predefined role script and maintaining a sufficient level of authenticity. Additionally, we want to analyze to what level the chatbot is suitable for practicing correctly diagnosing depressive disorders in patients as well as assessing suicidality stages.

Methods:

Medical students interacted with these virtual patients via chat. We assessed the perceived authenticity and role script adherence and analyzed chat transcripts to gain further insight into the chatbot's behavior and the students' diagnostic accuracy.

Results:

In over 90% of cases, the chatbot maintained its assigned role. On average, students correctly identified the severity of depression in 60% and the phase of suicidality in 67% of the cases. Notably, the majority either failed to address or insufficiently explored the topic of suicidality despite explicit instructions beforehand.

Conclusions:

This study demonstrates that a GPT-powered chatbot can reliably simulate depressive patients. However, we identified potential challenges in designing such bots. Students reported enjoying the training and perceived the conversations as rather authentic. However, their diagnostic accuracy varied depending on the severity of the case, highlighting the need for targeted training. AI-supported virtual patients provide a highly flexible, standardized, and readily available training tool, independent of real-life constraints.