Conversational AI for Depression

Overseen By Kevin Lybarger, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: George Mason University

Disqualifiers: Bipolar disorder

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 2

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests whether a conversational AI system for collecting medical history makes people feel more understood and connected with their healthcare providers compared to traditional multiple-choice surveys. Participants will either interact with the AI or complete a structured questionnaire, then share their thoughts on the experience. This trial is ideal for individuals diagnosed with major depression who feel comfortable using technology and have internet access. As an unphased trial, it offers a unique opportunity for participants to contribute to innovative research that could transform patient-provider communication.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on how medical history is collected rather than on medication use.

What prior data suggests that this conversational method is safe for collecting medical history?

Research has shown that people generally have a positive experience using conversational AI systems. One study found that these AI chatbots helped reduce symptoms of depression, indicating that users can engage with these systems without many negative experiences. Another study found that AI chatbots also helped lower both depression and anxiety over time. These findings suggest that people typically interact well with AI systems, with few negative effects reported. While research on conversational AI continues, current evidence suggests it is safe for use. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the Conversational AI system for depression because it offers a novel and interactive way to engage with patients. Unlike traditional treatment approaches that rely on structured surveys or clinician-led interviews, this AI system uses advanced Large Language Models to create a natural, empathetic conversation with patients, helping them feel more comfortable and understood. It also features a Dialogue Manager that keeps the conversation focused on relevant medical topics, enhancing the efficiency of data collection. Additionally, the system is monitored by human experts to ensure patient safety, especially when there are signs of self-harm, making it a potentially transformative tool in personalizing and streamlining the antidepressant recommendation process.

What evidence suggests that this conversational AI system is effective for improving patient perceptions and experiences?

This trial will compare the effectiveness of a Conversational AI system with a Structured Survey Questionnaire for managing depression. Research has shown that AI chatbots, like the Conversational AI system participants may use in this trial, can assist in managing mental health. A review found that these systems can improve conditions like depression by providing interactive and personalized support. Studies have demonstrated that AI chatbots can enhance patient well-being by fostering a sense of empathy and connection. Early findings suggest that these AI systems help strengthen the relationship between patients and their caregivers. The AI responds in a caring and natural way, making patients feel more understood and supported. ^{2 5 6 7 8}

Are You a Good Fit for This Trial?

This trial is for individuals with Major Depressive Disorder or depression. Participants should be comfortable using technology to interact either through a conversational AI system or by completing an online survey. Specific inclusion and exclusion criteria are not provided, but typically participants must meet diagnostic criteria for depression.

Inclusion Criteria

I have a primary care or mental health provider, or I agree to see one for the study.

Resides in a state where study clinicians are licensed

Has access to the Internet via phone or computer

Exclusion Criteria

Has clinically diagnosed bipolar disorder

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intake

Participants are randomly assigned to either conversational AI or structured survey intake methods to collect medical history

1 week

1 visit (virtual)

Evaluation

Participants rate their experience with the intake method, focusing on empathy and therapeutic bond

1 week

1 visit (virtual)

Follow-up

Participants are monitored for adherence to recommendations and perceptions of empathy

4 months

What Are the Treatments Tested in This Trial?

Interventions

• Conversational AI system

Trial Overview The study is testing if collecting medical history via a conversational AI affects patients' feelings of empathy and their bond with clinicians versus using traditional surveys. Participants will randomly receive one method: dialogue-based questions from the AI or multiple-choice questions in a survey.

How Is the Trial Designed?

Group I: Conversational AI system Experimental Treatment 1 Intervention

Participants engage in medical history intake through an interactive conversational AI system designed to create patient-centered interactions. The system utilizes advanced Large Language Models (LLMs) to understand patient inputs, interpret context, and generate coherent, natural language responses with an empathetic tone. Within the conversational AI, a Dialogue Manager guides the conversation by prioritizing medically relevant topics, ensuring efficient data collection and minimizing off-topic dialogue. To enhance patient safety, conversations are continuously monitored in real-time by trained human-in-the-loop monitors, who can promptly intervene if potential safety risks, such as indications of self-harm, are identified. The primary intent of the conversational AI system is to streamline the antidepressant recommendation process, provide personalized patient interactions, and foster patient comfort and therapeutic alliance through empathetically toned responses.

Group II: Structured Survey Questionnaire Active Control 1 Intervention

Participants complete a structured, multiple-choice questionnaire designed to efficiently collect medical history. This intake method uses decision trees to sequentially select questions based on prior responses, maximizing information gain and minimizing unnecessary queries. The questionnaire systematically gathers patient demographics, depression history, and previous antidepressant use through closed-ended, mutually exclusive, and exhaustive response options.

Who Is Running the Clinical Trial?

George Mason University

Lead Sponsor

Trials

60

Recruited

50,200+

Patient-Centered Outcomes Research Institute

Collaborator

Trials

592

Recruited

27,110,000+

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12416039/

Artificial Intelligence for Management of Major Depression ... (AI) system designed to manage major depressive disorder (MDD). The system is a web-based, patient-facing conversational AI that collects ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12120367/

Effectiveness of AI-Driven Conversational Agents in Improving ... This study aims to examine the effectiveness of AI-driven CAs for mental health among young people, and explore the potential moderators of efficacy.

3. sciencedirect.com sciencedirect.com/science/article/pii/S2949916X24000525

Enhancing mental health with Artificial Intelligence This review explores the integration of AI into mental healthcare, elucidating current trends, ethical considerations, and future directions in this dynamic ...

4. nature.com nature.com/articles/s41746-023-00979-5

Systematic review and meta-analysis of AI-based ... This systematic review and meta-analysis aims to fill this gap by synthesizing evidence on the effectiveness of AI-based CAs in improving mental health.

5. sciencedirect.com sciencedirect.com/science/article/pii/S2214782922000021

Using AI chatbots to provide self-help depression ... The main objective of this study is to add to the evidence of effectiveness for chatbot therapy as a convenient, affordable, interactive self-help intervention ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12162938/

Depression and the use of conversational AI for ... The present study aimed to examine the relationship between depression and the use of conversational AI for companionship (UCAI-C) among college students.

7. jmir.org jmir.org/2025/1/e69639/

Effectiveness of AI-Driven Conversational Agents in ... The results of this meta-analysis revealed that AI-driven CAs demonstrated a moderate-to-large intervention effect on depressive symptoms. This ...

8. clinicaltrials.gov clinicaltrials.gov/study/NCT06858371

Testing the Effectiveness of AI Chatbots to Improve Public ... Primary outcomes include changes in depression literacy, attitudes toward depression, help-seeking intentions, and confidence in helping others. The study aims ...