Machine Learning–Based Prediction of Histopathological Classification in Colorectal Polyps
Turkish Journal of Gastroenterology · 2025
DOI: 10.5152/tjg.2025.25542 ↗Kurz gefasst
Fachartikel in der Zeitschrift Turkish Journal of Gastroenterology, 2025. Verfasst von Gökhan Koker und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, University of Health Sciences, Antalya Training and Research Hospital, Antalya, Türkiye. Hauptthemen laut MEDLINE: Machine Learning, Colonic Polyps, Colorectal Neoplasms, Adenomatous Polyps. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Background/Aims: Colorectal polyps are precursor lesions of colorectal cancer, and their histopathological types are critical for deter mining malignant potential. Predicting polyp histopathological types may support early and appropriate clinical management. Machine learning (ML) algorithms based on accessible demographic, clinical, and lifestyle data can contribute to individualized screening strategies. Materials and Methods: This retrospective cross-sectional study included 491 individuals who underwent colonoscopy for the first time between 2022 and 2025 at University of Health Sciences, Antalya Training and Research Hospital. Demographic and clinical data were recorded, and dietary habits were assessed using the Food Frequency Questionnaire. Patients were classified into 3 groups according to histopathology: adenomatous polyp, hyperplastic polyp, and no polyp. Four ML algorithms—decision tree, random forest, support vector machines (SVMs), and extreme gradient boosting—were applied. Model performance was evaluated using accuracy, sensitivity, specific ity, kappa statistic, and McNemar’s test. Variable contributions were further analyzed with SHapley Additive exPlanations.
Results
Accuracy ranged from 70.9% to 76.4%, with the highest performance from SVM (76.4%) and random forest (75.7%). Extreme gradient boosting showed lower overall accuracy (70.9%) but was the only model that identified hyperplastic polyps. The no polyp groupwas consistently predicted with high accuracy (sensitivity 85.6%-95.9%). Precision for adenomatous polyps was highest with SVM (71.4%). SHapley Additive exPlanations analysis highlighted frequent bulgur consumption (>2 times/week), red meat intake, age, and body mass index as major predictors.
Conclusion
Machine learning algorithms can predict colorectal polyp histopathological types using routine demographic, clinical, and dietary data, enabling more personalized and effective screening beyond age-based protocols. Cite this article as: Koker G, Gorgulugil GZ, Coskuner MA, Durmus ME. Machine learning–based prediction of histopathological classification in colorectal polyps. Turk J Gastroenterol. 2025;36(10):700-707
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Internal Medicine, University of Health Sciences, Antalya Training and Research Hospital, Antalya, Türkiye.
- Department of Internal Medicine, Antalya City Hospital, Antalya, Türkiye.
- Department of Gastroenterology, University of Health Sciences, Antalya Training and Research Hospital, Antalya, Türkiye.
ORCID-Profile: Gökhan Koker, Gizem Zorlu Gorgulugil, Muhammed Ali Coskuner, Merve Eren Durmus
Zitieren
APA
Koker, G., Gorgulugil, G. Z., Coskuner, M. A., & Durmus, M. E. (2025). Machine Learning–Based Prediction of Histopathological Classification in Colorectal Polyps. Turkish Journal of Gastroenterology. https://doi.org/10.5152/tjg.2025.25542
Vancouver
Koker G, Gorgulugil GZ, Coskuner MA, Durmus ME. Machine Learning–Based Prediction of Histopathological Classification in Colorectal Polyps. Turkish Journal of Gastroenterology. 2025. doi:10.5152/tjg.2025.25542
BibTeX
@article{Koker2025,
author = {Koker, Gökhan and Gorgulugil, Gizem Zorlu and Coskuner, Muhammed Ali and Durmus, Merve Eren},
title = {Machine Learning–Based Prediction of Histopathological Classification in Colorectal Polyps},
journal = {Turkish Journal of Gastroenterology},
year = {2025},
doi = {10.5152/tjg.2025.25542}
}
EUVIMED