Journal of Consulting and Clinical Psychology, Vol 93(7), Jul 2025, 471-483; doi:10.1037/ccp0000957
Objective: This study aims at improving dropout and treatment nonresponse prevention by optimizing the performance of models for their prediction through the integration of item-level data. Method: Routine data from 1,277 patients (Mage = 36.95, SDage = 13.64; 64.77% female) treated at Osnabrück University was used to train and evaluate 20 machine-learning algorithms and five ensemble models. Measures included sociodemographic information, Outcome Questionnaire-30, Questionnaire for the Evaluation of Psychotherapeutic Progress, Questionnaire on Emotional Well-Being, Symptom Checklist-90-R, and the Inventory of Interpersonal Problems-32. Prediction models were trained with nested cross-validation and validated in a holdout sample. SHapley Additive exPlanations values were extracted for the best resulting model. Results: Item-level models achieved the highest performance for both dropout (F1-Score = 0.87, Brier score = 0.0529, balanced accuracy = 0.88) and treatment nonresponse (F1-Score = 0.60, Brier score = 0.1646, balanced accuracy = 0.72) prediction. Items reflecting cognitive and bodily dimensions, respectively, emerged as key predictors. Conclusion: This study demonstrates the clinical value of using item-level data to enhance predictive modeling for dropout and treatment nonresponse and the potential to provide actionable insights for clinical practice. Integrating such models into clinical feedback systems could help identify at-risk patients and reduce dropout and nonresponse rates. (PsycInfo Database Record (c) 2025 APA, all rights reserved)