AI Technology for Detecting Depression and Anxiety in the Emergency Department

This study is exploring whether Artificial Intelligence (AI) technology can help emergency department (ED) doctors and nurses better identify depression and anxiety. These mental health conditions are common but often missed in the ED, and can affect or worsen other medical problems. Researchers are testing an AI device that analyzes facial expressions and voice patterns when you read a story. The goal is to see if this AI can accurately detect different levels of depression, as measured by a standard questionnaire (PHQ-9). You might be able to join if you are an adult (18+) who speaks English, is not critically ill, and is in the ED for a non-urgent concern. The study is currently unclear on its recruitment status and plans to enroll 30 participants.

Study design
This interventional study plans to enroll 30 participants. It is not specified if it is randomized or blinded.
What's involved
You would be asked to read a story while your facial expressions and audio cues are recorded. This recording will then be analyzed by a computer.
Compensation
Not stated in the trial record.
Follow-up
The primary outcomes (PHQ-9 scores) are measured at baseline, so there is no specified follow-up period after the initial recording.

AI-generated from the public study record. Only the study team can confirm whether you're eligible — confirm details with them before making decisions.

NCT06473558

Identification of Depressive and Anxiety Symptoms Among a Sample of Emergency Department Patients Using Artificial Intelligence (AI) Technology

Not Yet Recruiting
NAAges 18+InterventionalScreening
University Hospitals Cleveland Medical Center
~30 participants
Updated 2026-09-15 on ClinicalTrials.gov
What's tested:Biometrics (or AI Biomaker)

At a glance

Recruiting sites
0 of 1 listed site is recruiting right now
RecruitingSuspended, closed, or not yet open
What they're measuring
Percentage of participants who score 5-9 on the PHQ-9
Measured over Baseline
+13 more outcomes measured
Artificial Intelligence (AI)

NCT06473558

Where you'd take part

This study runs at 1 site. They're the same protocol — you choose where, and that choice sets who your contact draft is addressed to.

  • University Hospitals ED

    Cleveland, Ohiostudy coordinator listed

Sites open and close at different times, so the status above is per site — it can differ from the study's overall status.

  • Kiran Faryar, MD, MPH · PRINCIPAL_INVESTIGATOR · University Hospitals

Opens a ready-to-send draft in your own email app — review before sending.

Want this trial checked against your situation?

Add a private profile and we'll compare every criterion below against your situation — and tell you which ones are met, uncertain, or excluding.

Check eligibility for this trial ~2 min · HIPAA-protected · delete anytime
Eligibility criteria

Inclusion

Adult patients (age 18 and over) who presents to the UHCMC ED voluntarily with no obvious psychological disturbance by self-report or nurse/provider initial assessment
English-speaking
Patients with non-emergent concerns of Emergency Severity Index (ESI) level 3, 4, or 5

Exclusion

Prisoners
Patients who are deemed to be critically ill (including life or limb threatening illness) or unable to consent
Non-English Speaking
  • Percentage of participants who score 5-9 on the PHQ-9Baseline

    Patient Health Questionnaire (PHQ-9) is a multipurpose instrument for screening, diagnosing, monitoring, and measuring severity of depression. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score 10-14 on the PHQ-9Baseline

    Patient Health Questionnaire (PHQ-9) is a multipurpose instrument for screening, diagnosing, monitoring, and measuring severity of depression. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score 15-19 on the PHQ-9Baseline

    Patient Health Questionnaire (PHQ-9) is a multipurpose instrument for screening, diagnosing, monitoring, and measuring severity of depression. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score 20-27 on the PHQ-9Baseline

    Patient Health Questionnaire (PHQ-9) is a multipurpose instrument for screening, diagnosing, monitoring, and measuring severity of depression. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score 5-9 on the GAD-7Baseline

    Generalized Anxiety Disorder (GAD-7) is a easy to preform initial screening tool for generalized anxiety disorder. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score 10-14 on the GAD-7Baseline

    Generalized Anxiety Disorder (GAD-7) is a easy to preform initial screening tool for generalized anxiety disorder. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Percentage of participants who score above 15 on the GAD-7Baseline

    Generalized Anxiety Disorder (GAD-7) is a easy to preform initial screening tool for generalized anxiety disorder. Questions are scored on a Likert scale of 0-3 with 0 being not at all and 3 being nearly every day.

  • Number of participants that AI screened positive for mild depression symptoms.Baseline
  • Number of participants that AI screened positive for moderate depression symptoms.Baseline
  • Number of participants that AI screened positive for moderately severe depression symptoms.Baseline
  • Number of participants that AI screened positive for severe depression screeningBaseline
  • Number of participants that AI screened positive for mild anxiety symptoms.Baseline
  • Number of participants that AI screened positive for moderate anxiety symptoms.Baseline
  • Number of participants that AI screened positive for severe anxiety symptoms.Baseline