KMAN Publication Inc. (KMANPUB) Journal of Adolescent and Youth Psychological Studies (JAYPS) 2981-2526 7 Serial Number 44 2026 04 01 Predicting Cognitive Distortions in Youth Using Advanced Machine Learning Algorithms Predicting Cognitive Distortions in Youth Using Advanced Machine Learning Algorithms 1 10 10.61838/kman.jayps.5046 EN Journal Article 2025 11 07 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> This study aimed to predict cognitive distortions among undergraduate students using advanced machine learning algorithms and to compare their predictive performance with traditional statistical approaches.</p> <p><strong>Methods and Materials: </strong>The study employed a quantitative, cross-sectional predictive design involving undergraduate students enrolled at universities in Yazd, Iran. Participants completed a battery of standardized self-report instruments assessing cognitive distortions and related psychological variables, including perceived stress, emotional distress, coping styles, and demographic characteristics. Data were preprocessed through screening for missing values, normalization, and partitioning into training, validation, and testing subsets. Multiple machine learning algorithms, including linear, nonlinear, and ensemble-based models, were implemented to predict overall cognitive distortion scores. Hyperparameter tuning and cross-validation procedures were applied to optimize model performance, and feature importance analyses were conducted to enhance interpretability. Model evaluation relied on multiple error-based and variance-explained indices to ensure robust and generalizable prediction.</p> <p><strong>Findings: </strong>Advanced machine learning models demonstrated substantially higher predictive accuracy than traditional linear regression, with ensemble-based algorithms achieving the strongest performance. The optimal model explained a large proportion of variance in cognitive distortion scores and maintained stable accuracy across training, validation, and testing datasets, indicating minimal overfitting. Perceived stress, emotional distress, and maladaptive coping emerged as the most influential predictors, while demographic variables contributed comparatively little to model performance. The results confirmed that nonlinear interactions among psychological variables play a critical role in predicting cognitive distortions in youth.</p> <p><strong>Conclusion: </strong>The findings indicate that cognitive distortions in university students can be accurately predicted using advanced machine learning approaches, highlighting the complex and multidimensional nature of distorted cognition.</p> </td> </tr> </tbody> </table> <p> </p> https://journals.kmanpub.com/index.php/jayps/article/download/5046/9502