Data-driven personalized medicine approaches to cognitive-behavioral therapy allocation in a large sample: A reanalysis of the ENRICHED study

Background: Although effective treatments for common mental health problems are available, individual responses to these treatments are heterogeneous and difficult to predict. Treatment efficacy can be optimized by targeting interventions using individual predictions of differential treatment outcomes. The aim of this study was to develop and test a multivariable prediction algorithm with machine learning techniques using data from one of the largest randomized clinical trials on psychological interventions for common mental health problems.Methods: This is a secondary analysis of the Enhancing Recovery in Coronary Heart Disease study, which investigated the effectiveness of six months of cognitive behavioral therapy (CBT) and care as usual (CAU) for depression and low perceived social support following an acute myocardial infarction. 2481 participants were randomly assigned to CBT and CAU. Baseline sociodemographics, depression characteristics, comorbid symptoms, and stress and adversity measures were used to build an algorithm to predict post-treatment depression severity. Performance and generalizability of the prediction algorithm were tested in a held-out sample. This study is registered http://clinicaltrial.gov/ct2/show/NCT00000557, The clinical Trials.gov Identifier: NCT00000557.Results: Treatment matching based on predictions in the testing sample resulted in small effects, that were more pronounced for individuals matched to CBT. We identified a subgroup of individuals for which CBT did not appear more efficacious than CAU. Conclusions: These small matching effects are likely a realistic representation of the performance and generalizability of multivariable prediction algorithms based on clinical measures. These results indicate that future work and new approaches are needed.