Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies

•What is the primary question addressed by this study?Can machine learning models of depression treatment response be trained to generate treatment-relevant subgroups from a pool of patients with major depression?•What is the main finding of this study?Using the Differential Prototypes Neural Network to analyze six studies of antidepressant medication treatment (n = 5,438), we trained a model with the potential to improve population remission rates by 6.5% (15.6% relative improvement). The model generated three novel patient subgroups. These subgroups differed from each other in terms of symptoms (such as psychomotor agitation) and demographic characteristics.•What is the meaning of the finding?Machine learning models can be trained to generate treatment-relevant patient subgroups, thereby potentially improving the ability to personalize treatment for depression. Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological and behavioral substrates are associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning (ML) shows promise in predicting treatment response in MDD, but its application is limited by challenges to the clinical interpretability of ML models, and clinicians often lack confidence in model results. In order to improve the interpretability of ML models in clinical practice, our goal was to demonstrate the derivation of treatment-relevant patient profiles comprised of clinical and demographic information using a novel ML approach. We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a ML model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Prototypes were evaluated for interpretability by assessing differences in feature distributions (e.g. age, sex, symptom severity) and treatment-specific outcomes. A 3-prototype model achieved an area under the receiver operating curve of 0.66 and an expected absolute improvement in remission rate for those receiving the best predicted treatment of 6.5% (rel