Early symptom change contributes to the outcome prediction of cognitive behavioral therapy for depression patients: A machine learning approach

Abstract

BackgroundLimited evidence exists regarding the association between early symptom change and later outcomes of cognitive behavioral therapy (CBT). This study aimed to apply machine learning algorithms to predict continuous treatment outcomes based on pre-treatment predictors and early symptom changes and to uncover whether additional variance could be explained compared to regression methods. Additionally, the study examined early subscale symptom changes to determine the most significant predictors of treatment outcome. MethodsWe investigated CBT outcomes in a large naturalistic dataset (N = 1975 depression patients). The sociodemographic profile, pre-treatment predictors, and early symptom change, including total and subscale scores were used to predict the Symptom Questionnaire (SQ)48 score at the 10th session as a continuous outcome. Different machine learners were compared to linear regression. ResultsEarly symptom change and baseline symptom score were the only significant predictors. Models with early symptom change explained 22.0 % to 23.3 % more variance than those without early symptom change. Specifically, the baseline total symptom score, and the early symptom score changes of the subscales pertaining to depression and anxiety were the top three predictors of treatment outcome. LimitationExcluded patients with missing treatment outcomes had slightly higher symptom scores at baseline, indicating possible selection bias. ConclusionEarly symptom change improved the prediction of treatment outcomes. The prediction performance achieved is far from clinical relevance: the best learner could only explain 51.2 % of the variance in outcomes. Compared to linear regression, more sophisticated preprocessing and learning methods did not substantially improve performance.