Machine Learning Methods for Predicting the Prognosis of Chronic Kidney Disease
Procedia Computer Science · 2025 · 258 · 1372-1382
DOI: 10.1016/j.procs.2025.04.370 ↗Kurz gefasst
Fachartikel in der Zeitschrift Procedia Computer Science, 2025. Verfasst von Srinivasa Rao Kalupukuru und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Chronic Kidney Disease (CKD) is a growing global health concern, often diagnosed in its advanced stages, leading to high treatment costs and poor patient outcomes. Early detection is crucial for better disease management. This study proposes a machine learning-based approach for predicting CKD using six models: Cat Boost, AdaBoost, Extra Trees, Naive Bayes, Logistic Regression, and K-Nearest Neighbors. The models were trained on a dataset of 400 patient records with 26 clinical features. Data preprocessing involved handling missing values and selecting important features through XGBoost. Cat Boost demonstrated the highest performance with 97.5% accuracy, 100% recall, and an F1-score of 98%, making it the most reliable model for CKD prediction. These results highlight the potential of ensemble learning models in early diagnosis, offering valuable insights for healthcare practitioners to improve treatment planning and patient outcomes.
Zitieren
APA
Kalupukuru, S. R., & Natarajan, K. (2025). Machine Learning Methods for Predicting the Prognosis of Chronic Kidney Disease. Procedia Computer Science, 258, 1372-1382. https://doi.org/10.1016/j.procs.2025.04.370
Vancouver
Kalupukuru SR, Natarajan K. Machine Learning Methods for Predicting the Prognosis of Chronic Kidney Disease. Procedia Computer Science. 2025;258:1372-1382. doi:10.1016/j.procs.2025.04.370
BibTeX
@article{Kalupukuru2025,
author = {Kalupukuru, Srinivasa Rao and Natarajan, Karthika},
title = {Machine Learning Methods for Predicting the Prognosis of Chronic Kidney Disease},
journal = {Procedia Computer Science},
year = {2025},
volume = {258},
pages = {1372--1382},
doi = {10.1016/j.procs.2025.04.370}
}
EUVIMED