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

30 Participants Needed

Trial Summary

What is the purpose of this trial?

Behavioral health problems, such as depression and anxiety, are common yet often are not identified by emergency department doctors and nurses. These mental health conditions can be due to medical issues or can worsen medical problems. One way investigators hope to do a better job of learning about mental health is by training Artificial Intelligence (AI) software to detect anxiety and depression by analyzing facial expression and tone of voice. Participants are invited to participate in a study which may help improve emergency department care. An audio and video recording of the participant's responses to some simple, non-psychological questions will be analyzed by a computer to determine whether investigators can assess mood and anxiety by analyzing speech and visual patterns. The audio and video will not be listened to nor watched by study personnel, only analyzed by a computer. The investigator's hope is that it will help others in the future by aiding in the assessment of psychological state. This study is being conducted at CMC ED only.

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 data supports the effectiveness of the treatment Biometrics 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 help in identifying and managing depression and anxiety. Additionally, a digital biodata-driven program has shown promise in engaging users and managing symptoms of depression and anxiety. ^{1 2 3 4 5}

Is AI technology for detecting depression and anxiety safe for humans?

The research does not provide specific safety data for AI technology used in detecting depression and anxiety, but it suggests that wearable AI is still in its early stages and should be used alongside other methods until further studies improve its performance. ^{1 6 7 8 9}

How does AI technology for depression and anxiety detection differ from other treatments?

This AI technology is unique because it uses wearable devices and machine learning models to predict and identify depression and anxiety by analyzing physiological data like motor activity and cardiovascular signals, offering a non-invasive and potentially more accessible alternative to traditional psychiatric interviews. ^{1 4 10 11 12}

Research Team

Kiran Faryar, MD, MPH

Principal Investigator

University Hospitals

Eligibility Criteria

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

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

English-speaking

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

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

Treatment Details

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.

Participant Groups

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+

Findings from Research

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]

References

1. Netherlands pubmed.ncbi.nlm.nih.gov

Performance of Artificial Intelligence in Predicting Future Depression Levels. [2023]

2. Switzerland pubmed.ncbi.nlm.nih.gov

Feasibility, engagement, and preliminary clinical outcomes of a digital biodata-driven intervention for anxiety and depression. [2022]

3. Netherlands pubmed.ncbi.nlm.nih.gov

Proactive screening for depression through metaphorical and automatic text analysis. [2012]

4. Switzerland pubmed.ncbi.nlm.nih.gov

Diagnosis of Depressive Disorder Model on Facial Expression Based on Fast R-CNN. [2022]

5. Netherlands pubmed.ncbi.nlm.nih.gov

The project for objective measures using computational psychiatry technology (PROMPT): Rationale, design, and methodology. [2022]

6. England pubmed.ncbi.nlm.nih.gov

Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence. [2021]

7. England pubmed.ncbi.nlm.nih.gov

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression. [2023]

8. Switzerland pubmed.ncbi.nlm.nih.gov

Classification of Suicide Attempts through a Machine Learning Algorithm Based on Multiple Systemic Psychiatric Scales. [2020]

9. United States 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. [2023]

10. Switzerland pubmed.ncbi.nlm.nih.gov

Automated recognition of major depressive disorder from cardiovascular and respiratory physiological signals. [2023]

11. England pubmed.ncbi.nlm.nih.gov

Computer assisted identification of stress, anxiety, depression (SAD) in students: A state-of-the-art review. [2023]

12. Switzerland pubmed.ncbi.nlm.nih.gov

Deep Neural Networks for Depression Recognition Based on 2D and 3D Facial Expressions Under Emotional Stimulus Tasks. [2021]