Even though different psychotherapeutic interventions for depression have shown to be effective, patients suffering from depression vary substantially in their treatment response. The goal of this study was to answer the following research questions: (1) What are the most important predictors determining optimal treatment allocation to cognitive behavioral therapy (CBT) or CBT with integrated exposure and emotion-focused elements (CBT-EE)?, and (2) Would model-determined treatment allocation using this predictive information result in better treatment outcomes? Bayesian Model Averaging (BMA) was applied to the data of a randomized controlled trial comparing the efficacy of CBT and CBT-EE in depressive outpatients. Predictions were made for every patient for both treatment conditions and an optimal versus a suboptimal treatment was identified in each case. An index comparing the two estimates, the Personalized Advantage Index (PAI), was calculated. Different predictors were found for both conditions. A PAI of 1.35 BDI-II points for the two conditions was found and 46% of the sample was predicted to have a clinically meaningful advantage in one of the therapies. Although the utility of the PAI approach must be further confirmed in prospective research, the present study study promotes the identification of specific interventions favorable for specific patients.
Keywords: CBT; Personalized Advantage Index; depression; precision medicine; psychotherapy; treatment selection.