Machine Learning Model for Response to Internet-Delivered CBT vs Antidepressant Medication

Can a machine learning model predict response to internet-based cognitive behavioral therapy (iCBT) but not antidepressant medication?In this prognostic study of 883 patients receiving iCBT or antidepressant medications, an elastic net regression with 27 mostly self-reported predictors explained 19% of the variance in depression improvement in unseen data. The model generalized well to patients receiving antidepressants when the sample contained individuals also receiving psychotherapy, but retraining the model on patients receiving only iCBT delivered a treatment-specific model.These findings suggest that clinical and cognitive data are predictive of iCBT response in a naturalistic clinical setting, with evidence of treatment specificity.

Corresponding Author: Chi Tak Lee, PhD (clee@tcd.ie), and Claire M. Gillan, PhD (gillancl@tcd.ie), Lloyd Institute, Trinity College Institute of Neuroscience, School of Psychology, Dublin D02 R123, Ireland.

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.