KMAN Publication Inc. (KMANPUB) تست 3060-6713 In Press 2025 12 01 Predicting Adaptive School Functioning in Students with ADHD Through Explainable Boosting Machines: The Roles of Cognitive Flexibility, Self-Regulation, and Teacher–Student Relationship Quality Predicting Adaptive School Functioning in Students with ADHD Through Explainable Boosting Machines: The Roles of Cognitive Flexibility, Self-Regulation, and Teacher–Student Relationship Quality 1 13 EN Journal Article 2026 04 15 <p>The present study aimed to predict adaptive school functioning among students with Attention-Deficit/Hyperactivity Disorder (ADHD) using an Explainable Boosting Machine (EBM) model and to determine the relative contributions of cognitive flexibility, self-regulation, and teacher–student relationship quality to educational adaptation. This cross-sectional predictive study was conducted among 428 students diagnosed with ADHD who were enrolled in public primary and lower secondary schools in Greece during the 2024–2025 academic year. Participants completed standardized measures of cognitive flexibility, self-regulation, and adaptive school functioning, while teachers evaluated teacher–student relationship quality. Following data screening, descriptive and correlational analyses were conducted. The primary analytical approach involved Explainable Boosting Machines, an interpretable machine learning technique capable of modeling nonlinear relationships and interaction effects. The dataset was divided into training and testing subsets, and five-fold cross-validation was employed to optimize model performance. Model accuracy was assessed using the coefficient of determination (R²), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and feature importance analyses. Significant positive correlations were observed among all study variables. Adaptive school functioning demonstrated strong associations with self-regulation (r = .73, p &lt; .001), teacher–student relationship quality (r = .69, p &lt; .001), and cognitive flexibility (r = .61, p &lt; .001). The Explainable Boosting Machine model demonstrated excellent predictive performance, explaining 78.4% of the variance in the training dataset and 74.8% of the variance in the testing dataset. Feature importance analyses revealed that self-regulation was the strongest predictor (41.2%), followed by teacher–student relationship quality (33.7%) and cognitive flexibility (25.1%). Nonlinear effect analyses indicated threshold effects for self-regulation and teacher–student relationship quality, while interaction analyses showed that the positive effects of cognitive flexibility were amplified when combined with high levels of self-regulation. The highest predicted levels of adaptive school functioning were observed among students demonstrating strong self-regulation together with highly positive teacher–student relationships. The findings indicate that adaptive school functioning among students with ADHD is best understood as the product of interacting cognitive, behavioral, and relational processes. Self-regulation emerged as the most influential predictor, while teacher–student relationship quality and cognitive flexibility provided substantial additional explanatory value. Explainable machine learning approaches such as EBM offer powerful and interpretable tools for identifying factors associated with educational adaptation and may inform targeted interventions aimed at improving school functioning among students with ADHD.</p> https://www.journals.kmanpub.com/index.php/prien/article/download/5434/12139