KMAN Publication Inc. (KMANPUB) Journal of Assessment and Research in Applied Counseling (JARAC) 8 Serial Number 29 2026 04 01 Identifying Predictors of Therapy Responsiveness from Meta-Emotion Beliefs and Cognitive Flexibility Using ML Identifying Predictors of Therapy Responsiveness from Meta-Emotion Beliefs and Cognitive Flexibility Using ML 1 11 10.61838/kman.jarac.5191 EN Journal Article 2025 12 18 <p><strong>Objective: </strong>This study aimed to identify transdiagnostic cognitive and affective predictors of therapy responsiveness by applying machine learning algorithms to evaluate meta-emotion beliefs and cognitive flexibility in an outpatient clinical sample.</p> <p><strong>Methods and Materials: </strong>A prospective, longitudinal predictive design was employed with a sample of N=514 adult participants from Malaysia. Baseline data were collected utilizing the Meta-Emotion Scale and the Cognitive Flexibility Inventory, while treatment outcomes were measured using the Outcome Questionnaire-45.2. Data analysis was conducted in Python using Scikit-Learn, which involved handling missing values, Z-score standardization, and an 80/20train-test split. Machine learning models underwent hyperparameter optimization via 10-fold cross-validation and were thoroughly evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics, with SHAP (Shapley Additive Explanations) values utilized to determine explicit feature interpretability.</p> <p><strong>Findings:</strong> Results indicated that 62.4%of the participants (N=514) demonstrated clinically significant improvement following therapeutic intervention. Therapy responsiveness exhibited significant positive correlations with meta-emotion facets (acceptability: r=〖0.41〗^(**); controllability: r=〖0.53〗^(**)) and cognitive flexibility domains (alternatives: r=〖0.61〗^(**); control: r=〖0.48〗^(**)). Among the evaluated machine learning classifiers, the XGBoost model achieved the highest predictive performance on the test set (n=103), yielding an overall accuracy of 85.4%and an ROC-AUC of 0.91. Furthermore, SHAP value analysis explicitly identified the Alternatives facet of Cognitive Flexibility (Mean Abs SHAP: 1.24) and the Controllability facet of Meta-Emotion (Mean Abs SHAP: 0.98) as the most highly significant positive predictors of successful therapeutic outcomes.</p> <p><strong>Conclusion:</strong> Assessing cognitive flexibility and meta-emotion utilizing advanced algorithmic modeling provides a highly accurate framework for predicting therapy responsiveness, thereby directly facilitating the crucial transition toward proactive, personalized mental health care.</p> https://journals.kmanpub.com/index.php/jarac/article/download/5191/9518