Machine Learning Model for Response to Internet-Delivered CBT vs Antidepressant Medication
This prognostic study in a naturalistic setting found that self-reported data predicted iCBT response better than cognitive data. Model predictions generalized to patients receiving antidepressants, some of whom also received psychotherapy. Training models on single-treatment cohorts may yield more treatment-specific predictions.
Authors
- Klaas Ε. Stephan (ORCID: https://orcid.org/0000-0002-8594-9092)
- Chi Tak Lee (ORCID: https://orcid.org/0000-0002-3404-5368)
- Veronica O’Keane (ORCID: https://orcid.org/0000-0002-1519-099X)
- Claire M. Gillan (ORCID: https://orcid.org/0000-0001-9065-403X)
- Anna K Hanlon (ORCID: https://orcid.org/0000-0001-7456-8641)
- Nathalie Claus (ORCID: https://orcid.org/0000-0002-4081-4952)
- Robert Whelan (ORCID: https://orcid.org/0000-0002-2790-7281)
- Derek Richards
- Siobhán Harty (ORCID: https://orcid.org/0000-0001-7560-9185)
- Jakob Heinzle (ORCID: https://orcid.org/0000-0001-5228-041X)
- Kevin Lynch (ORCID: https://orcid.org/0000-0002-8519-7863)
Institutions
- University of Bremen (DE)
- University of Zurich (CH)
- Trinity College Dublin (IE)
- Tallaght University Hospital (IE)
- ETH Zurich (CH)
- Institute for Biomedical Engineering (CH)
- Max Planck Institute for Metabolism Research (DE)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2025-11-06
- DOI
- https://doi.org/10.1001/jamanetworkopen.2025.41639
- Primary Topic
- Digital Mental Health Interventions
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission
- Science Foundation Ireland
- Irish Research Council
- René und Susanne Braginsky Stiftung
- Horizon 2020 Framework Programme
- Erasmus+