Predicting Therapy Outcomes for Stress-Related Disorders using Machine Learning: A Study Protocol (Preprint)

Abstract

Stress-related disorders, such as adjustment disorder and exhaustion disorder, are prevalent and associated with significant personal suffering and societal costs. While cognitive behavioral therapy has shown efficacy in treating these conditions, knowledge about factors contributing to treatment response is limited. Improved identification of such factors could enhance assessment procedures and treatment strategies.

This study aims to (1) evaluate putative predictors of treatment outcome in patients with stress-related disorders using traditional prediction methods and (2) model treatment outcomes utilizing a machine learning approach. The primary outcome of interest is responder status on the Perceived Stress Scale-10, evaluated based on the reliable change index post-treatment.

Data from a randomized controlled trial comparing two internet-delivered treatments for patients diagnosed with adjustment disorder or exhaustion disorder (N = 300) will be analyzed. Putative predictors include sociodemographic and clinical information, clinician-assessed data, self-rated symptoms, and cognitive test scores. For the traditional approach, univariate logistic regressions will be conducted for each predictor, followed by an ablation study for significant predictors. For the machine learning approach, four classifiers (logistic regression with Elastic Net, random forest, support vector machine, and AdaBoost) will be trained and evaluated. The dataset will be split into training (70%) and testing (30%) sets. Hyperparameter tuning will be conducted using 5-fold cross-validation with randomized search. Model performance will be assessed using balanced accuracy, precision, recall, and area under the curve.

All data to be used in the present study was collected between April 2021 and July 2022. We hypothesize that key predictors will include younger age, education level, baseline symptom severity, treatment credibility, and history of sickness absence. We anticipate that the machine learning models will outperform a dummy model predicting the majority class and achieve a balanced accuracy of 67% or higher, thus being considered clinically useful.

This study will contribute to the limited research on predictors of treatment outcome in stress-related disorders. By comparing traditional and machine learning approaches, it aims to enhance our understanding of factors influencing treatment response. The findings could support the development of more personalized and effective treatments for individuals diagnosed with adjustment disorder or exhaustion disorder, potentially improving clinical practice and patient outcomes. If successful, this approach may encourage future studies with larger datasets and the implementation of machine learning models in clinical settings, ultimately enhancing precision in mental health care.

ClinicalTrials ID: NCT04797273. Trial registration date 15 March 2021.