EUVIMEDEUVIMED entdecken
Crossref

CatBoost Prediction of Obsessive-Compulsive Symptoms Using Thought Suppression, Cognitive Fusion, Perfectionism, and Anxiety Sensitivity

Rosa Alcázar Campos, Margarita Izquierdo Morán, Ferran Fernández-Llario, Luís F. Seoane

Journal of Assessment and Research in Applied Counseling · 2026 · 8 (3) · 1-14

DOI: 10.61838/kman.jarac.5796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Assessment and Research in Applied Counseling, 2026. Verfasst von Rosa Alcázar Campos und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study aimed to develop and interpret a CatBoost machine learning model for predicting obsessive-compulsive symptom severity based on thought suppression, cognitive fusion, perfectionism, and anxiety sensitivity among adults in Spain. Methods and Materials: This cross-sectional predictive study was conducted on 1,214 adults from Spain. Participants completed standardized self-report measures assessing obsessive-compulsive symptoms, thought suppression, cognitive fusion, perfectionism, and anxiety sensitivity. After data screening, the final dataset was analyzed using descriptive and inferential statistics, Pearson correlation analysis, multicollinearity assessment, and CatBoost regression modeling. The dataset was divided into training and testing subsets, and hyperparameter tuning was performed using five-fold cross-validation. Model performance was evaluated using R², adjusted R², root mean squared error, mean absolute error, mean absolute percentage error, and explained variance. SHAP and permutation importance analyses were used to interpret the relative contribution of each predictor.

Findings

Obsessive-compulsive symptoms were significantly and positively correlated with thought suppression (r = .71, p < .001), cognitive fusion (r = .67, p < .001), anxiety sensitivity (r = .64, p < .001), and perfectionism (r = .58, p < .001). The optimized CatBoost model demonstrated strong predictive performance, explaining 89.2% of variance in the training dataset and 85.4% of variance in the testing dataset. The testing model showed low prediction error, with RMSE = 4.28, MAE = 3.24, MAPE = 13.18%, and explained variance = .855. Five-fold cross-validation confirmed stable model performance, with a mean R² of .849. SHAP and permutation importance analyses identified thought suppression as the strongest predictor, followed by cognitive fusion, anxiety sensitivity, and perfectionism.

Conclusion

The findings indicate that obsessive-compulsive symptoms can be predicted with high accuracy using a CatBoost model based on key cognitive-affective vulnerability factors. Thought suppression and cognitive fusion showed the strongest predictive influence, suggesting that maladaptive responses to intrusive thoughts are central to obsessive-compulsive symptom severity. The model provides an interpretable framework for identifying psychological mechanisms relevant to assessment, prevention, and intervention.

Zitieren

APA

Campos, R. A., Morán, M. I., Fernández-Llario, F., & Seoane, L. F. (2026). CatBoost Prediction of Obsessive-Compulsive Symptoms Using Thought Suppression, Cognitive Fusion, Perfectionism, and Anxiety Sensitivity. Journal of Assessment and Research in Applied Counseling, 8(3), 1-14. https://doi.org/10.61838/kman.jarac.5796

Vancouver

Campos RA, Morán MI, Fernández-Llario F, Seoane LF. CatBoost Prediction of Obsessive-Compulsive Symptoms Using Thought Suppression, Cognitive Fusion, Perfectionism, and Anxiety Sensitivity. Journal of Assessment and Research in Applied Counseling. 2026;8(3):1-14. doi:10.61838/kman.jarac.5796

BibTeX
@article{Campos2026,
  author = {Campos, Rosa Alcázar and Morán, Margarita Izquierdo and Fernández-Llario, Ferran and Seoane, Luís F.},
  title = {CatBoost Prediction of Obsessive-Compulsive Symptoms Using Thought Suppression, Cognitive Fusion, Perfectionism, and Anxiety Sensitivity},
  journal = {Journal of Assessment and Research in Applied Counseling},
  year = {2026},
  volume = {8},
  number = {3},
  pages = {1--14},
  doi = {10.61838/kman.jarac.5796}
}
Kostenlos starten →