NCT06801925: GPT4-RAG-PHQ

Evaluating the Effectiveness and Acceptability of a GPT-4o and RAG-Based Voice Chatbot for Depression Screening Using PHQ-9

ENROLLING BY INVITATION Last updated 30 January 2025

What this trial tests

trial testing GPT-4o and RAG Voice Chatbot for PHQ-9 Screening in Depression - Major Depressive Disorder in 100 participants. Enrolling by invitation.

Timeline

1 February 2025

Primary endpoint
31 March 2025

31 May 2025

Quick facts

Lead sponsor	University College, London
Status	ENROLLING BY INVITATION
Study type	OBSERVATIONAL
Enrollment	100
Start date	1 February 2025
Primary completion	31 March 2025
Estimated completion	31 May 2025
Sites	1 location across United Kingdom

Drugs / interventions tested

• GPT-4o and RAG Voice Chatbot for PHQ-9 Screening

Conditions studied

• Depression - Major Depressive Disorder — all drugs for Depression - Major Depressive Disorder →
• Depression Anxiety Disorder — all drugs for Depression Anxiety Disorder →

Sponsor

University College, London

Who can join

Adults 18 to 65, any sex, with Depression - Major Depressive Disorder or Depression Anxiety Disorder. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

This study aims to assess the feasibility and acceptability of a voice-based chatbot, powered by GPT-4o and Retrieval-Augmented Generation (RAG), for conducting depression screening using the Patient Health Questionnaire-9 (PHQ-9). The PHQ-9 is a validated self-report instrument widely used to screen, diagnose, and monitor the severity of depression. It consists of nine questions that correspond to the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) criteria for major depressive disorder. Respondents rate the frequency of symptoms experienced over the past two weeks on a scale from 0 ("not at all") to 3 ("nearly every day"). The total score (ranging from 0 to 27) indicates the severity of depressive symptoms, categorized into minimal, mild, moderate, moderately severe, or severe depression. The PHQ-9 is also used to assess functional impairment and guide treatment decisions in clinical and research settings.

The voice-based chatbot integrates GPT-4o, with RAG to enhance its ability to provide informed and contextualized responses during interactions. GPT-4o serves as the conversational engine, capable of generating human-like, empathetic, and contextually appropriate dialogue. RAG, on the other hand, enables the chatbot to retrieve and incorporate external, up-to-date knowledge from a curated database or knowledge repository, ensuring the accuracy and reliability of its responses.

Publications & conference data

No peer-reviewed publications indexed yet for this trial.