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

NCT06801925 | Enrolling By Invitation

• 1 other identifier: 26133.001
• Study Type: observational
• Target: 100
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Depression - Major Depressive Disorder; Depression Anxiety Disorder

Keywords

mental health; depression; chatbot; GPT; PHQ-9; RAG

Outcome Measures

Primary Outcomes (1)

• Feasibility and Acceptability of the GPT-4o and RAG Voice Chatbot

  Participants' perceptions of the chatbot's feasibility, acceptability, and effectiveness are assessed through semi-structured interviews conducted after the interaction session. These interviews explore themes such as the chatbot's empathy, usability, and the overall user experience.

  Interviews are conducted immediately following the chatbot interaction.

Secondary Outcomes (1)

• Accuracy of PHQ-9 Scoring by the Chatbot

  Measured immediately after the interaction session, once the chatbot has generated PHQ-9 scores

Interventions

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

This study involves the use of a voice-based chatbot powered by GPT-4o and Retrieval-Augmented Generation (RAG) to conduct depression screening using the Patient Health Questionnaire-9 (PHQ-9). The chatbot aims to evaluate the feasibility and acceptability of using AI-powered conversational tools for mental health screening. Participants interact with the chatbot in a single session, answering PHQ-9 questions and receiving responses generated using GPT-4o and RAG technologies.

Eligibility Criteria

• Age: 18 Years - 65 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of healthy individuals aged 18 to 65 years who do not have severe mental illnesses. We welcome participants who have an interest in artificial intelligence technologies. Recruitment will be conducted both online and offline. Participants will engage with a sophisticated AI chatbot designed to simulate a consultation with a mental health professional. This interaction enables them to complete a psychometric evaluation, such as the PHQ-9 test, in a structured yet conversational manner. Unlike conventional online versions of the PHQ-9 test, the chatbot offers enhanced interactivity. For individuals who may experience difficulties in articulating or summarizing their responses, the chatbot provides clarifications and assistance using a comprehensive language model. After the assessment, participants will receive an interpretation of their test results along with tailored advice, delivered in accordance with established mental health guidelines.

You may qualify if:

• Adults aged 18-65 years.
• Fluent in English.
• Access to a device capable of voice interaction and stable internet connection.
• Willing to participate in chatbot interaction and a follow-up interview.

You may not qualify if:

• Current severe psychiatric diagnoses (e.g., psychosis, bipolar disorder).
• Participants undergoing active treatment for depression with a psychiatrist.
• Discomfort with voice-based technology or inability to provide informed consent.

Sponsors & Collaborators

• University College, London: lead

Study Sites (1)

UCL Institute of Health Informatics

London, NW1 2DA, United Kingdom

Location

MeSH Terms

Conditions

Psychological Well-Being; Depression

Condition Hierarchy (Ancestors)

Personal Satisfaction; Behavior; Behavioral Symptoms

Study Officials

• Kezhi Li

  University College, London

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: January 24, 2025
• First Posted: January 30, 2025
• Study Start: February 1, 2025
• Primary Completion: March 31, 2025
• Study Completion: May 31, 2025
• Last Updated: January 30, 2025

Record last verified: 2025-01

Data Sharing

• IPD Sharing: Will not share

Locations

GB (1)