Machine learning-based computerized adaptive testing of PHQ-8 and GAD-7 in psychiatric outpatients
Journal of Affective Disorders · 2027-01 · 417 · 122660
DOI: 10.1016/j.jad.2026.122660 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Affective Disorders, 2027-01. Verfasst von Edimansyah Abdin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Division, Institute of Mental Health, Singapore, Singapore; Saw Swee Hock School of Public Health, National University of Singapore, Singapo…. Hauptthemen laut MEDLINE: Machine Learning, Anxiety Disorders, Diagnosis, Computer-Assisted. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Medical Research Council.
Abstract (Originalsprache)
BACKGROUND: Scalable, accurate and efficient monitoring tools are urgently needed to support psychiatric assessment in routine care. This study aimed to evaluate a machine learning-based computerized adaptive testing (ML-CAT) model for the PHQ-8 and GAD-7 in psychiatric outpatient settings. METHODS: Data were obtained from a longitudinal cohort study of patients with depression or anxiety diagnoses. ML-CAT models were developed using the M5P algorithm. Model performance was evaluated via 10-fold cross-validation. Concurrent validity was assessed with Pearson's r, R2, and mean absolute error (MAE). Longitudinal change detection was assessed using paired t-tests and Cohen's d. Diagnostic classification agreement (based on the ≥10 cutoff between assessments) was examined using percentage agreement and Cohen's κ. RESULTS: The ML-CAT administered a median of 2 items per instrument (66-71% item reduction) while achieving near-perfect concurrent validity with full-scale scores (r = 0.996-0.997; R2 = 0.986-0.991; MAE < 0.62). Both ML-CAT versions reliably detected symptom reductions at 6 months and 1 year. Classification agreement between ML-CAT and full-scale versions was high at 6 months and 1 year for PHQ-8 (κ = 0.85-0.93) and GAD-7 (κ = 0.91-0.96). CONCLUSIONS: The ML-CAT model reproduced PHQ-8 and GAD-7 scores with high accuracy and detected meaningful clinical change across two follow-up waves. The resulting adaptive questionnaire can be presented as a flowchart and administered both online and offline, providing real-world clinical evidence for scalable ML-CAT-based psychiatric assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Division, Institute of Mental Health, Singapore, Singapore; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore. Electronic address: Edimansyah.abdin@nhghealth.com.sg.
- Research Division, Institute of Mental Health, Singapore, Singapore.
- Department of Mood and Anxiety, Institute of Mental Health, Singapore, Singapore.
- Department of Psychosis, Institute of Mental Health, Singapore, Singapore.
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore.
- Research Division, Institute of Mental Health, Singapore, Singapore; Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore.
Förderung
- National Medical Research Council
Zitieren
APA
Abdin, E., Jeyagurunathan, A., Tan, S. C., Mok, Y. M., Verma, S., Feng, M., & Subramaniam, M. (2027). Machine learning-based computerized adaptive testing of PHQ-8 and GAD-7 in psychiatric outpatients. Journal of Affective Disorders, 417, 122660. https://doi.org/10.1016/j.jad.2026.122660
Vancouver
Abdin E, Jeyagurunathan A, Tan SC, Mok YM, Verma S, Feng M, et al. Machine learning-based computerized adaptive testing of PHQ-8 and GAD-7 in psychiatric outpatients. Journal of Affective Disorders. 2027;417:122660. doi:10.1016/j.jad.2026.122660
BibTeX
@article{Abdin2027,
author = {Abdin, Edimansyah and Jeyagurunathan, Anitha and Tan, Sing Chik and Mok, Yee Ming and Verma, Swapna and Feng, Mengling and Subramaniam, Mythily},
title = {Machine learning-based computerized adaptive testing of PHQ-8 and GAD-7 in psychiatric outpatients},
journal = {Journal of Affective Disorders},
year = {2027},
volume = {417},
pages = {122660},
doi = {10.1016/j.jad.2026.122660}
}
EUVIMED