An Efficient Machine Learning Framework for Chronic Kidney Disease Prediction Using Feature Selection and Hyperparameter Optimization
International Journal of Sciences and Innovation Engineering · 27.04.2026 · 3 (4) · 2443-2448
DOI: 10.70849/ijsci03042668072 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Sciences and Innovation Engineering, online erschienen am 27.04.2026. Verfasst von N. REHNA.
Abstract (Originalsprache)
Chronic Kidney Disease (CKD) is a progressive medical condition that leads to the gradual loss of kidney function and poses a serious global health burden. Early detection is essential to prevent severe complications such as kidney failure and cardiovascular diseases. This study proposes a machine learning-based framework for predicting CKD using clinical and laboratory parameters including specific gravity, hypertension, hemoglobin, diabetes mellitus, albumin, appetite, red blood cell count, and pus cell indicators. The dataset used in this research is obtained from the Kaggle dataset platform and consists of 25 attributes comprising both numerical and categorical variables. Data preprocessing techniques such as handling missing values, correcting inconsistent categorical entries, and encoding categorical features were applied. Various machine learning algorithms including Random Forest, AdaBoost, Gradient Boosting, Logistic Regression, Naïve Bayes, K-Nearest Neighbors, Support Vector Machine, and Decision Tree were implemented and evaluated. Among these, the Random Forest classifier achieved the highest performance with an accuracy of 97.5% after hyperparameter tuning. The results demonstrate that machine learning techniques can significantly improve early detection of CKD and assist healthcare professionals in making accurate and timely decisions.
Zitieren
APA
REHNA, N. (2026). An Efficient Machine Learning Framework for Chronic Kidney Disease Prediction Using Feature Selection and Hyperparameter Optimization. International Journal of Sciences and Innovation Engineering, 3(4), 2443-2448. https://doi.org/10.70849/ijsci03042668072
Vancouver
REHNA N. An Efficient Machine Learning Framework for Chronic Kidney Disease Prediction Using Feature Selection and Hyperparameter Optimization. International Journal of Sciences and Innovation Engineering. 2026;3(4):2443-2448. doi:10.70849/ijsci03042668072
BibTeX
@article{REHNA2026,
author = {REHNA, N.},
title = {An Efficient Machine Learning Framework for Chronic Kidney Disease Prediction Using Feature Selection and Hyperparameter Optimization},
journal = {International Journal of Sciences and Innovation Engineering},
year = {2026},
volume = {3},
number = {4},
pages = {2443--2448},
doi = {10.70849/ijsci03042668072}
}
EUVIMED