Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204608,
        author = {Isha Gaikwad and Purva Jadhav and Pratiksha Jagdale and Shahrukh Shekh},
        title = {NephroXplain: AI-Powered Chronic Kidney Disease Detection with Interpretability},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4177-4182},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204608},
        abstract = {The Chronic Kidney Disease (CKD) is a continuously progressing condition usually left unnoticed until later stages, causing grave complications and expensive treatments. The classical AI models hold promise to predict CKD but are restricted to clinical practice by lack of explainability as black-box models. The base work cited employed Decision Trees with LIME for explainability but was bound by limited dataset size, stability, and performance. In this paper, we propose NephroXplain, an AI system comprised of XGBoost for high-predictive power and SHAP (SHapley Additive Explanations) for feature-level interpretability. Clinical indicators such as serum creatinine, hemoglobin, and blood pressure are investigated to achieve accurate and interpretable predictions. The system is executed through a web user interface with MERN stack and ML Python integration to permit runtimes in realistic healthcare environments. Experimental investigation exhibits superior performance to Decision Tree models while offering better prediction rationale insight. This paper bridges the gap towards accuracy and interpretability and advances ethical and trustworthy AI for CKD detection.},
        keywords = {Chronic Kidney Disease, XGBoost, Explainable AI, SHAP, Medical Diagnosis},
        month = {June},
        }