A Machine Learning Approach to Prognostication in Oral Cancer: Analysis of the Surveillance, Epidemiology, and End Results Database
Cancer Informatics · 2026-05 · 25
DOI: 10.1177/11769351261442875 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancer Informatics, online erschienen am 25.05.2026. Verfasst von Philips Okeagu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Objective
To develop and validate machine learning models to predict 5-year survival in oral cancer using a large population-based registry and to rank prognostic factors.
Methods
We analyzed Surveillance, Epidemiology, and End Results (SEER) data from 1992 to 2020. After applying inclusion criteria, 39 904 patients with complete data on 21 variables were included from 53 611 cases (25.6% exclusion). Selection bias was assessed by comparing included and excluded patients. The outcome was binary 5-year survival. Four models were trained and evaluated using nested fivefold cross-validation: XGBoost, LASSO, Random Forest, and logistic regression. Performance was assessed using the Brier score, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Calibration was evaluated using slope and intercept with 95% confidence intervals. Model explainability used permutation feature importance and SHAP values.
Results
Random Forest showed the best discrimination (AUC 77.6%, accuracy 71.4%, Brier 0.186) and was selected for risk stratification. However, it overestimated risk in lower deciles. Logistic regression and LASSO showed better calibration, with slopes near 1.0, but slightly lower discrimination (AUCs 75.5% and 76.9%). SHAP analysis identified localized stage as the strongest protective factor (importance 100.0), followed by age (91.1) and chemotherapy (29.3). Excluded patients had more unstaged tumors (3.9% vs 1.7%, P < .001).
Conclusion
Random Forest provides strong risk stratification, but miscalibration limits its use for absolute risk prediction. Logistic regression and LASSO may be preferable when accurate probabilities are needed. External validation is required before clinical use.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
- Department of Oral Health Policy and Epidemiology, Harvard School of Dental Medicine, Boston, MA, USA.
- Department of Oral Health Sciences, Temple University Kornberg School of Dentistry, Philadelphia, PA, USA.
- Department of Comprehensive Care, Fairfield Clinic, Tufts University School of Dental Medicine, Boston, MA, USA.
ORCID-Profile: Philips Okeagu
Zitieren
APA
Okeagu, P., Murukutla, S., Iwuchukwu, A., & Ogwo, C. (2026). A Machine Learning Approach to Prognostication in Oral Cancer: Analysis of the Surveillance, Epidemiology, and End Results Database. Cancer Informatics, 25. https://doi.org/10.1177/11769351261442875
Vancouver
Okeagu P, Murukutla S, Iwuchukwu A, Ogwo C. A Machine Learning Approach to Prognostication in Oral Cancer: Analysis of the Surveillance, Epidemiology, and End Results Database. Cancer Informatics. 2026;25. doi:10.1177/11769351261442875
BibTeX
@article{Okeagu2026,
author = {Okeagu, Philips and Murukutla, Saranya and Iwuchukwu, Afamdi and Ogwo, Chukwuebuka},
title = {A Machine Learning Approach to Prognostication in Oral Cancer: Analysis of the Surveillance, Epidemiology, and End Results Database},
journal = {Cancer Informatics},
year = {2026},
volume = {25},
doi = {10.1177/11769351261442875}
}
EUVIMED