AI Technology for Depression and Anxiety Detection

Overseen By Andie M Moore, MS

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Kiran Faryar, MD

Disqualifiers: Prisoners, Critically ill, Non-English speakers

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

Compensation: Varies

Number of Visits: 1

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to enhance how emergency departments identify depression and anxiety using AI technology. By analyzing facial expressions and voice tones, researchers aim to develop a tool that better detects these mental health issues. Participants will be recorded while reading a story, allowing the AI to analyze their speech and expressions. This trial may suit adults visiting the emergency department for non-urgent issues who speak English. As an unphased trial, it offers participants the chance to contribute to groundbreaking research that could improve mental health diagnostics.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this AI technology is safe for detecting depression and anxiety?

Research has shown that using biometric technology, such as AI to detect depression and anxiety, is generally safe. Studies have not reported any specific safety concerns with this type of AI technology, indicating no major issues with similar systems.

This study is in a phase that does not involve new drugs or invasive procedures, which often carry more risks. Instead, it uses recordings of facial expressions and voice tones to assess mood, presenting little to no physical risk for participants. The main safety concern is privacy, as biometric data (like facial and voice data) is sensitive. However, the study ensures that only computers analyze the data, helping doctors understand mental health signs without anyone directly viewing or listening to the recordings.

Overall, while biometric technology employs new methods, current information suggests it is well-tolerated, with minimal physical risk. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about using AI technology for detecting depression and anxiety because it offers a unique, non-invasive approach. Unlike traditional methods, which often rely on self-reported questionnaires and clinical interviews, this technology uses biometrics to analyze facial expressions and audio cues. This innovative method can potentially provide real-time, objective insights, making it faster and possibly more accurate in identifying mental health issues. By leveraging AI, this approach could revolutionize how we screen and diagnose depression and anxiety, offering a novel tool that complements existing methods.

What evidence suggests that this AI technology is effective for detecting depression and anxiety?

This trial will explore AI technology for detecting depression and anxiety by analyzing facial expressions and voice patterns. Research has shown that AI can help detect these conditions, with studies finding that machine learning can predict generalized anxiety disorder and major depressive disorder using electronic health records. One study discovered that combining audio and text data can help identify depression. Additionally, wearable AI devices have successfully predicted depression levels by tracking movement. These findings suggest that AI could improve the diagnosis and care of mental health issues. Participants in this trial will visit University Hospitals Cleveland Medical Center Emergency Department, where they will complete assessments and be recorded reading a story to capture facial expressions and audio cues. ^{2 3 6 7 8}

Who Is on the Research Team?

Kiran Faryar, MD, MPH

Principal Investigator

University Hospitals

Are You a Good Fit for This Trial?

This trial is for emergency department patients who may have depression or anxiety. It aims to test if AI can identify these conditions by analyzing facial expressions and tone of voice from recordings during their visit.

Inclusion Criteria

English-speaking

I am over 18 and went to the emergency department on my own without any clear mental health issues.

Patients with non-emergent concerns of Emergency Severity Index (ESI) level 3, 4, or 5

Exclusion Criteria

Prisoners

Patients who are deemed to be critically ill (including life or limb-threatening illness) or unable to consent

Non-English Speaking

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Assessment

Participants complete assessments and questionnaires, and are recorded reading a story to capture facial expressions and audio cues

1 day

1 visit (in-person)

Follow-up

Participants are monitored for safety and effectiveness after assessment

2-4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• Biometrics

Trial Overview The study tests an AI software's ability to detect signs of depression and anxiety through biometrics, using participants' audio and video responses to simple questions recorded in the emergency department.

How Is the Trial Designed?

Group I: Participants seen at University Hospitals Cleveland Medical Center Emergency Department Experimental Treatment 1 Intervention

Eligible patients must present with non-emergent concerns of Emergency Severity Index (ESI) level 3, 4, or 5. Patients will complete assessments and questionnaires and end with being recorded reading a story to capture facial expressions and audio cues.

Who Is Running the Clinical Trial?

Kiran Faryar, MD

Lead Sponsor

Trials

1

Recruited

30+

University Hospitals Cleveland Medical Center

Lead Sponsor

Trials

348

Recruited

394,000+

Published Research Related to This Trial

The 16-week Feel Program, a digital mental health support initiative, showed a 65% retention rate among 48 adult participants, with high user satisfaction (65% reported very high satisfaction) and significant engagement in activities designed to manage depressive and anxiety symptoms.

Results indicated that 93.5% of participants experienced a decrease in depressive or anxiety symptoms, with 51.6% showing clinically significant improvement, suggesting that higher engagement in the program correlates with better mental health outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Feasibility, engagement, and preliminary clinical outcomes of a digital biodata-driven intervention for anxiety and depression. Tsirmpas, C., Andrikopoulos, D., Fatouros, P., et al.[2022]

The study developed machine learning models using Danish registry data from 1995 to 2018 to predict non-fatal suicide attempts and suicides after psychiatric discharge, achieving a high predictive accuracy for attempts (ROC-AUC of 0.85) and moderate accuracy for suicides (ROC-AUC of 0.71).

The results highlight the importance of treating suicide and non-fatal suicide attempts as separate outcomes, as the predictors for each differed, and the ensemble models showed fair performance across different sexes and ages, suggesting they could be more reliable for clinical use than simpler models.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prediction models of suicide and non-fatal suicide attempt after discharge from a psychiatric inpatient stay: A machine learning approach on nationwide Danish registers. Nielsen, SD., Christensen, RHB., Madsen, T., et al.[2023]

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC7820000/

Predictive modeling of depression and anxiety using ... Our results indicate moderate predictive performance for the application of machine learning methods in detection of GAD and MDD based on EHR data. By ...

2. sciencedirect.com sciencedirect.com/science/article/pii/S0010482524017037

A lightweight approach based on cross-modality for ... This paper proposes a multimodal depression detection model that fuses audio and textual data. We evaluate the performance of each model using depression ...

3. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC8537335/

Machine Learning-Based Behavioral Diagnostic Tools for ... The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders.

4. link.springer.com link.springer.com/article/10.1007/s41347-024-00475-x

Using Biometric Technology to Explore the Physiological ... This is the first study to use biometric technology across 72 h to identify physiological indicators of stress, recovery, and sleep in frontline child welfare ...

5. withpower.com withpower.com/trial/phase-artificial-intelligence-ai-10-2024-65698

AI Technology for Depression and Anxiety Detection Research shows that wearable AI technology using motor activity data can effectively predict depression levels, suggesting that similar biometric data could ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11651562/

An improved biometric stress monitoring solution for working ... In this paper, we propose a new approach based on the CapsNets model for continuously monitoring psychophysiological stress.

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC10918303/

Exploring the Impact of Security Technologies on Mental Health Facial recognition software is an advanced form of surveillance that uses biometric data to identify individuals based on their facial features.

8. medrxiv.org medrxiv.org/content/10.1101/2025.08.28.25334668v1.full-text

Real-Time Biometric Monitoring for Cognitive Workload ... Many users are unaware of the privacy risks associated with wearable biometric devices and how their data are protected [9,22]. Biometric ...