Depressive Disorder
Conditions
Brief summary
The trial aimed to evaluate the accuracy of an artificial intelligence-based system for diagnosing depressive disorders. Specifically, it sought to determine whether the system's assessment validity is non-inferior to that of psychiatric specialists.
Detailed description
This study evaluates the performance of the AI-assisted diagnostic system for identifying depressive disorders and its applicability in clinical settings. Utilizing a paired design with psychiatrists' clinical diagnoses as the gold standard, the study compares the system's diagnostic results with those of physicians to determine sensitivity and specificity, thus validating its clinical effectiveness in real-world outpatient scenarios. Additionally, standardized scales are used to assess users' perceptions of the system's usability, trustworthiness, and satisfaction, offering evidence to support the clinical integration of AI technology in mental health screening.
Interventions
None listed
Sponsors
Shanghai Mental Health Center
Study design
Observational model
CASE_CONTROL
Time perspective
CROSS_SECTIONAL
Eligibility
Sex/Gender
ALL
Age
18 Years to 60 Years
Healthy volunteers
Yes
Inclusion criteria
1. Subjects with anxiety disorders （1）Inclusion Criteria: * In accordance with ICD-11 for Depressive Disorders; * Between the ages of 18-60; * Ability to use computers or smartphone; * Native Chinese speaker; * Signing informed consent. （2）
Exclusion criteria
* With severe psychiatric symptoms requiring hospitalization, or unable to complete the required assessment and treatment; * With a high risk of suicide or self-injury; * With severe physical diseases, central nervous system diseases, or substance abuse; * With intellectual, visual, or auditory impairments that affect their ability to interact with aided-diagnostic systems. 2. Health Control （1）Inclusion Criteria: * Not meet ICD-11 criteria for Mental Disorders; * Between the ages of 18-60; * Ability to use computers or smartphone; * Native Chinese speaker; * Signing informed consent. （2）
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic Accuracy (Sensitivity, Specificity, and Area Under the Curve) of the AI-Based Screening System for Depressive Disorders | through study completion, an average of 1 week | In this study, the evaluation results of the subjects were taken as the gold standard based on the diagnostic conclusions of psychiatrists. The screening results of the aided-diagnostic system were compared with the diagnostic conclusions of the psychiatrists to verify the screening effectiveness of this system. Sensitivity : Calculated as \[True Positives / (True Positives + False Negatives)\], evaluating the AI system's ability to correctly identify patients with depression. Specificity : Calculated as \[True Negatives / (True Negatives + False Positives)\], evaluating the AI system's ability to correctly exclude non-depressed individuals.Area Under the Receiver Operating Characteristic Curve (AUC), which comprehensively evaluates the diagnostic discriminative power of the system by plotting sensitivity versus 1-specificity across different decision thresholds and calculating the AUC value . |
Countries
China
Outcome results
None listed