A Reproducible Multi-Disease Prediction Framework Using Ensemble and Gradient Boosting Models with SHAP Explainability
International Journal of Advanced Research in Science Communication and Technology · 12.05.2026 · 187
DOI: 10.48175/ijarsct-35220 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 12.05.2026. Verfasst von Tanmay Yadav und 2 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben.
Abstract (Originalsprache)
This paper presents a reproducible multi-disease prediction framework targeting diabetes, heart disease, liver disease, and chronic kidney disease. The framework systematically compares Logistic Regression, Random Forest, and XGBoost classifiers using leakage-safe preprocessing pipelines, SMOTE-based class balancing, 5-fold stratified cross-validation, GridSearchCV hyperparameter tuning, and SHAP-based explainability analysis. Experimental results demonstrate that XGBoost and Random Forest consistently outperform Logistic Regression across most disease datasets, with Random Forest and XGBoost achieving perfect classification metrics on the chronic kidney disease dataset. The system is designed as an educational research implementation and does not constitute a clinical diagnostic tool
Zitieren
APA
Yadav, T., Kumar, H., & Singh, R. (2026). A Reproducible Multi-Disease Prediction Framework Using Ensemble and Gradient Boosting Models with SHAP Explainability. International Journal of Advanced Research in Science Communication and Technology, 187. https://doi.org/10.48175/ijarsct-35220
Vancouver
Yadav T, Kumar H, Singh R. A Reproducible Multi-Disease Prediction Framework Using Ensemble and Gradient Boosting Models with SHAP Explainability. International Journal of Advanced Research in Science Communication and Technology. 2026:187. doi:10.48175/ijarsct-35220
BibTeX
@article{Yadav2026,
author = {Yadav, Tanmay and Kumar, Hemant and Singh, Rajendra},
title = {A Reproducible Multi-Disease Prediction Framework Using Ensemble and Gradient Boosting Models with SHAP Explainability},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {187},
doi = {10.48175/ijarsct-35220}
}
EUVIMED