• JYOTI VERMA
• Dr. Yogesh Kumar Rathore

Chronic Kidney Disease (CKD) is a serious health condition that gradually reduces kidney function and often remains unnoticed in its early stages. Late diagnosis increases the risk of kidney failure, cardiovascular complications, and long-term medical treatment. This study presents a machine learning-based approach for predicting kidney disease severity using a large clinical dataset containing 20,539 patient records and 42 medical attributes. The dataset includes demographic information, laboratory test results, urine analysis, blood pressure, lifestyle factors, and medical history. A structured data preprocessing pipeline was applied to improve data quality, including handling missing values, encoding categorical variables, normalization, and feature selection. Five supervised learning algorithms—Decision Tree, Support Vector Machine, Random Forest, k-Nearest Neighbors, and Artificial Neural Network—were trained and evaluated using standard performance measures such as accuracy, precision, recall, F1-score, confusion matrix, and ROC-AUC. Among all models, the Random Forest classifier achieved the best performance with an accuracy of 99.21% and an AUC of 0.994. The model also showed a very low rate of false-negative predictions, which is important in medical diagnosis. The results indicate that ensemble learning methods can effectively analyze multidimensional clinical data and support early identification of kidney disease severity levels. The proposed framework can assist healthcare professionals in screening high-risk patients and improving early intervention, especially in healthcare settings with limited specialist resources.

Chronic Kidney Disease, Machine Learning, Random Forest, Kidney Disease Prediction, Clinical Data, Healthcare Analytics, Early Detection, Multiclass Classification.

"Machine Learning-Based Kidney Disease Prediction Using Multidimensional Clinical Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.c650-c657, September-2026, Available :http://www.jetir.org/papers/JETIR2609271.pdf

"Machine Learning-Based Kidney Disease Prediction Using Multidimensional Clinical Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppc650-c657, September-2026, Available at : http://www.jetir.org/papers/JETIR2609271.pdf