AI Models for Mental Health and Neurodevelopmental Disorder Detection

This study is looking at whether artificial intelligence (AI) models, called Solicue Machine Learning Models and Mercuria Machine Learning Models, can help doctors more accurately and efficiently diagnose various mental health conditions. These conditions include Autism Spectrum Disorder, depression (Major Depressive Disorder), anxiety (Generalized Anxiety Disorder), Bipolar Disorder, and Attention Deficit Hyperactivity Disorder (ADHD), among others. The study will analyze speech patterns to see if the AI can predict clinical diagnoses and assess risk for these conditions. You might be able to join if you are between 13 and 60 years old, are currently being assessed for a mental or behavioral health condition, and are fluent in English. The researchers will measure how well the AI models perform compared to clinical diagnoses over 0, 3, and 6 months. The current recruitment status is unclear.

Study design
This is an observational study with a planned enrollment of 500 participants. It is not specified if the study is randomized or blinded.
What's involved
You will participate in an initial assessment that includes a speech battery audio recording. Your clinical diagnosis and the performance of the AI models will be assessed at 0, 3, and 6 months.
Compensation
Not stated in the trial record.
Follow-up
Participants will be followed for 6 months after their initial assessment.

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

NCT06792175

Mental Health, Intellectual and Neurodevelopmental Disorder Detection With Artificial Intelligence Models

Enrolling by Invitation
Not specifiedAges 13–60Observational
Psyrin Inc.
~500 participants
Updated 2025-09-03 on ClinicalTrials.gov
What's tested:Solicue Machine Learning ModelsMercuria Machine Learning Models

At a glance

Recruiting sites
0 of 2 listed sites are recruiting right now
RecruitingSuspended, closed, or not yet open
What they're measuring
Speech Battery ("PSY-10") audio
Measured over At initial assessment
+2 more outcomes measured
Autism Spectrum Disorder
Depression - Major Depressive Disorder
Anxiety, Generalized
Bipolar Disorder (BD)
Attention Deficit Hyperactivity Disorder (ADHD)
Schizophrenia Spectrum &Amp; Other Psychotic Disorders
Post Traumatic Stress Disorder
Obsessive Compulsive Disorder (OCD)

NCT06792175

Where you'd take part

This study runs at 2 sites. They're the same protocol — you choose where, and that choice sets who your contact draft is addressed to.

  • Allwell Behavioral Health Services

    Zanesville, Ohiono site contact published

  • The Brookline Center

    Brookline, Massachusettsno site contact published

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

  • Julianna Olah, B.Sc., M.A., M.Sc., Ph.D. · PRINCIPAL_INVESTIGATOR · Psyrin Inc.
  • Atta-ul Raheem R Chaudhry, B.Sc. (Hons.), M.B.B.S. · PRINCIPAL_INVESTIGATOR · Psyrin Inc.

This trial hasn't published a contact. View it on ClinicalTrials.gov

  • Speech Battery ("PSY-10") audioAt initial assessment

    The speech battery consists of prompt-based tasks designed to elicit speech responses from participants in the form of monologues. This includes text reading, recall, and picture description tasks.

  • Clinical diagnosis0 months, 3 months, 6 months

    Clinician diagnosis will be recorded for each participant at first assessment, 3-month, and 6-month follow-up. Diagnoses will be made according to ICD-11 or DSM-5 criteria for the compatible disorders: ADHD, ASD, BPAD, GAD, MDD, OCD, PTSD, and SSD. Additional relevant labels such as other mental health disorders, clinical high risk (CHR) and substance use may be recorded.

  • Performance of AI models0 months, 3 months, 6 months

    The performance of the Mercuria and Solicue AI models will be evaluated using performance metrics of accuracy, balanced accuracy, sensitivity (recall), specificity, positive predictive value (precision), negative predictive value, F1 score, AUC-ROC. Predicted labels will be compared with the ground truth clinical diagnoses obtained from the participating mental health clinics. Confidence acceptance threshold will be set.