Published on: April 2026
DETECTION AND STAGE PREDICTION OF KIDNEY DISEASE USING MACHINE LEARNING
K. Shiva Durga Devi CH. Sri Pooja K.Bhargavi N.Ajith K.Upendhar E. Kiran Kumar
Article Status
Available Documents
Abstract
Chronic Kidney Disease (CKD) affects over 500 million people globally, with India bearing a 15–20% prevalence rate largely driven by diabetes and hypertension. Approximately 90% of CKD cases remain undetected until the irreversible Stage 4–5, requiring dialysis or transplant. This paper presents a production-ready, Flask-based web application that integrates Random Forest and XGBoost ensemble models trained on the UCI CKD dataset to perform real-time CKD detection and KDIGO-based stage classification (Stages 0–5) from clinical lab inputs and uploaded PDF lab reports. The system achieves 95.5% accuracy with 89% PDF extraction success using multi-pattern regex parsing, SMOTE-balanced training, and interpretable feature importance visualizations. Deployed as a Progressive Web App (PWA), the system supports offline rural screening and longitudinal patient monitoring, addressing critical healthcare gaps in Telangana and across India
How to Cite this Paper
Devi, K. S. D., Pooja, C. S., K.Bhargavi, , N.Ajith, , K.Upendhar, & Kumar, E. K. (2026). Detection and Stage Prediction of Kidney Disease using Machine Learning. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.028
Devi, K., et al.. "Detection and Stage Prediction of Kidney Disease using Machine Learning." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.028.
Devi, K.,CH. Pooja, K.Bhargavi, N.Ajith, K.Upendhar, and E. Kumar. "Detection and Stage Prediction of Kidney Disease using Machine Learning." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.028.
Search & Index
References
- UCI Machine Learning Repository. Chronic Kidney Disease Dataset. Available: https://archive.ics.uci.edu/ml/datasets/chronic_kidney_disease
- KDIGO Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease. Kidney International Supplements, 2013; 3(1): 1–150.
- Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. KDD 2016.
- Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.
- Chawla, N. V. et al. (2002). SMOTE: Synthetic Minority Over-sampling Technique. JAIR, 16, 321–357.
- Lundberg, S. M., & Lee, S. I. (2017). A Unified Approach to Interpreting Model Predictions (SHAP). NeurIPS 2017.
- Grinsztajn, L. et al. (2022). Why tree-based models still outperform deep learning on tabular data. NeurIPS 2022.
- Ministry of Health and Family Welfare, India. Ayushman Bharat – ABDM. Available: https://abdm.gov.in
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Apr 03 2026
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.