Machine Learning for Comparative Antidepressant Selection in Major Depressive Disorder: Systematic Review
Machine Learning zur vergleichenden Auswahl von Antidepressiva bei Major Depression: systematische Übersicht
JMIR Mental Health · 13.05.2026 · 13 · e89352-e89352
DOI: 10.2196/89352 ↗Auf einen Blick
Die Übersicht von 19 Studien zeigt: ML-Modelle zur vergleichenden Antidepressiva-Auswahl bei MDD erreichen sehr unterschiedliche Vorhersagegüten. Nur 1 Studie nutzte ein einheitliches Framework für patientenbezogene Rangfolgen.
Fragestellung
Welche ML-Ansätze untersuchen bei Erwachsenen mit MDD 2 oder mehr pharmakologische Behandlungen zur Vorhersage von Behandlungsergebnissen und zur vergleichenden Medikamentenauswahl?
Methode
Systematische Übersicht nach PRISMA; Suche in PubMed, Scopus und Web of Science für Studien von 2015 bis 2025; Risikobewertung mit PROBAST-AI; narrative Synthese.
Ergebnisse
19 Studien mit Datensätzen von 49 bis 77.226 Teilnehmenden. AUC 0,59 bis 0,95; Klassifikationsgenauigkeit 62 % bis 95,4 %. Nur 7 Studien berichteten externe Validierung.
Einschränkungen
Die meisten Studien unterschieden nicht formal zwischen prognostischen und prädiktiven Merkmalen; keine nutzte formale Explainability-Techniken.
Schlussfolgerung der Autor:innen
ML zur vergleichenden Antidepressiva-Auswahl befindet sich noch in einem frühen Entwicklungsstadium. Genannt werden fehlende Kalibrierung, begrenzte externe Validierung und fehlende Explainability als Hürden.
Kernaussagen
- 19 Studien, breite Spannweite der Vorhersagegüte
- Nur 1 Studie mit einheitlichem Framework für patientenbezogenes Ranking
- Externe Validierung nur in 7 Studien, meist konservativere Schätzungen
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift JMIR Mental Health, online erschienen am 13.05.2026. Verfasst von Fiona He und 5 weiteren Autor:innen. Beteiligte Einrichtung: Digital Transformation and Innovation, Faculty of Engineering, University of Ottawa, Ottawa, ON, Canada. Hauptthemen laut MEDLINE: Major Depressive Disorder, Antidepressive Agents, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Major depressive disorder (MDD) affects approximately 1 in 6 adults during their lifetime, yet antidepressant selection relies predominantly on trial-and-error, with response rates of only 42% to 53%. While machine learning (ML) models have shown promise in predicting treatment outcomes, most focus on single treatments rather than comparative selection across therapeutic alternatives, limiting their clinical utility for the medication choice decisions that clinicians face in practice.
Objective
This systematic review evaluates ML approaches that examine 2 or more pharmacological interventions for predicting treatment outcomes in MDD, with a focus on their capacity to facilitate comparative treatment selection between medications or medication classes for individual patients.
Methods
Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we searched PubMed, Scopus, and Web of Science for studies published from 2015 to 2025. We included studies involving adults with MDD that used ML models to predict treatment outcomes across 2 or more pharmacological treatments and reported medication-specific prediction outcomes. Risk of bias was assessed using PROBAST-AI (Prediction Model Risk of Bias Assessment Tool for Artificial Intelligence). We conducted a narrative synthesis organized by modeling strategies, data integration approaches, validation methodologies, and performance patterns.
Results
From 5370 initial records, 19 studies met the inclusion criteria, with dataset sample sizes ranging from 49 to 77,226 participants. Studies employed 3 distinct modeling strategies: drug-specific supervised models trained independently for each medication, subtype- or trajectory-based approaches using clustering methods to identify differential response patterns, and a unified differential prediction framework generating calibrated cross-treatment predictions. Performance varied substantially, with area under the curve values ranging from 0.59 to 0.95 and classification accuracies between 62% and 95.4%, though high performance was concentrated in studies with small samples, high-dimensional neurobiological features, and internal-only validation. Only 7 studies conducted external validation, which generally yielded more conservative performance estimates. Feature informativeness was more consistently associated with performance variation than algorithm complexity. Most studies did not formally distinguish between prognostic features predicting general outcomes and predictive features identifying differential medication responses, and none applied formal explainability techniques.
Conclusions
ML for comparative antidepressant selection remains in an early stage of development. Only 1 study implemented a unified framework directly supporting patient-level treatment ranking. Key barriers to clinical translation include insufficient distinction between prognostic and predictive markers, limited cross-trial validation, near-absent calibration reporting, and absent explainability. Future research should prioritize unified comparative frameworks with calibrated predictions, rigorous external validation on diverse cohorts, explicit modeling of heterogeneous treatment effects, and integration of explainability into model development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Digital Transformation and Innovation, Faculty of Engineering, University of Ottawa, Ottawa, ON, Canada.
- Faculty of Science, University of British Columbia, Vancouver, BC, Canada.
- Ottawa Heart Institute, Ottawa, ON, Canada.
- Department of Physiology and Pharmacology, Western University, London, ON, Canada.
- University of Ottawa Institute of Mental Health Research at The Royal, Ottawa, ON, Canada.
- Telfer School of Management, University of Ottawa, 55 Laurier Ave E, Ottawa, ON, K1N 9B9, Canada, 1 (613) 562-5800 ext 4570.
Zitieren
APA
He, F., Huang, S., Wang, R., Chang, A., Phillips, J. L., & Sun, C. (2026). Machine Learning for Comparative Antidepressant Selection in Major Depressive Disorder: Systematic Review. JMIR Mental Health, 13, e89352-e89352. https://doi.org/10.2196/89352
Vancouver
He F, Huang S, Wang R, Chang A, Phillips JL, Sun C. Machine Learning for Comparative Antidepressant Selection in Major Depressive Disorder: Systematic Review. JMIR Mental Health. 2026;13:e89352-e89352. doi:10.2196/89352
BibTeX
@article{He2026,
author = {He, Fiona and Huang, Steven and Wang, Richard and Chang, Aland and Phillips, Jennifer L and Sun, Christopher},
title = {Machine Learning for Comparative Antidepressant Selection in Major Depressive Disorder: Systematic Review},
journal = {JMIR Mental Health},
year = {2026},
volume = {13},
pages = {e89352--e89352},
doi = {10.2196/89352}
}
EUVIMED