Intelligent detection of chronic kidney disease using machine learning: A comparative evaluation with nested cross-validation
Technology and Health Care · 18.11.2026
DOI: 10.1177/09287329261507156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 18.11.2026. Verfasst von Huda Dham Bader und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physiology, College of Medicine, University of Mosul, Mosul, Iraq. Die Arbeit nennt 47 Literaturangaben.
Abstract (Originalsprache)
Background
Chronic kidney disease (CKD) is progressive, and early diagnosis improves outcomes.
Objective
We assessed how reliably routine clinical and laboratory variables identify CKD, and whether differences between common classifiers exceed the sampling error of a 400-patient dataset.
Methods
We analysed the UCI CKD dataset (250 CKD and 150 non-CKD patients, 24 predictors) with ten classifiers: logistic regression (LR), K-nearest neighbours (KNN), decision tree (DT), random forest (RF), AdaBoost, support vector machine (SVM), gradient boosting (GB), extra trees (ETs), XGBoost and LightGBM. A majority-class baseline served as reference. Imputation (KNN, k = 5), scaling and hyperparameter search were fitted inside the training folds of a nested, repeated stratified 5-fold cross-validation (CV) (three repeats). We report mean ± SD with Nadeau–Bengio 95% confidence intervals and compared models with corrected paired t -tests and Holm adjustment.
Results
Nine classifiers reached a cross-validated accuracy of 98.25–99.50% (AUC ≥ 0.990); KNN reached 93.33% and the baseline 62.50%. LightGBM (99.50 ± 0.63%), RF (99.42 ± 0.80%) and XGBoost (99.25 ± 0.79%) had the highest mean accuracy, but no pair among the nine non-KNN classifiers differed significantly. Permutation importance and SHAP highlighted specific gravity, haemoglobin, serum creatinine, albumin and packed cell volume.
Conclusion
No classifier could be ranked above another. The data come from one public dataset with almost completely separable classes, so external validation is needed.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Physiology, College of Medicine, University of Mosul, Mosul, Iraq.
- Ninevah University, Office of the Scientific Assistant, Registration and Student Affairs Department, Mosul, Iraq.
ORCID-Profile: Huda Dham Bader, Noora Mazin Sheet, Alyaa Farouk Al-Omari
Zitieren
APA
Bader, H. D., Sheet, N. M., & Al-Omari, A. F. (2026). Intelligent detection of chronic kidney disease using machine learning: A comparative evaluation with nested cross-validation. Technology and Health Care. https://doi.org/10.1177/09287329261507156
Vancouver
Bader HD, Sheet NM, Al-Omari AF. Intelligent detection of chronic kidney disease using machine learning: A comparative evaluation with nested cross-validation. Technology and Health Care. 2026. doi:10.1177/09287329261507156
BibTeX
@article{Bader2026,
author = {Bader, Huda Dham and Sheet, Noora Mazin and Al-Omari, Alyaa Farouk},
title = {Intelligent detection of chronic kidney disease using machine learning: A comparative evaluation with nested cross-validation},
journal = {Technology and Health Care},
year = {2026},
doi = {10.1177/09287329261507156}
}
EUVIMED