A SHAP and LIME based Explainable AI Solution for Predicting Chronic Kidney Diseases

Abstract

Chronic Kidney Disease (CKD) presents a major global health issue, contributing to renal failure, cardiovascular problems, and elevated mortality rates. This research focuses on creating an effective machine learning (ML) model for CKD prediction, utilizing 25 features that represent different health indicators. We implemented three main algorithms: Logistic Regression (LR), K-Nearest Neighbors (KNN), and Decision Tree, along with extensive preprocessing, feature selection, and hyperparameter optimization. Based on accuracy, the models were evaluated, along with the confusion matrix, and ROC curves. Furthermore, we employed SHAP (SHapley Additive exPlanations) for model interpretability, offering insights via summary plots, waterfall plots, force plots, and dependence plots. Our results indicate high prediction accuracy, with a 10% increase in performance with the Decision Tree model achieving near-perfect performance, highlighting its potential for early CKD detection and contributing to timely medical interventions.

Authors and Affiliations

Mamatha B*1, Sujatha P Terdal*2

Keywords

Related Articles

Preparation and Study of Stability Pharmaceutical Composition [PSMA-11] and Radiopharmaceutical [99mtc]-PSMA-11 Labeled With 99mtc Radionuclide

This work is devoted to the study of the synthesis of a pharmaceutical composition (PhC) [PSMA-11] in the form of a lyophilisate with optimization of the amount of ingredients and sodium pertechnetate (Na99mTcO4) from th...

Time Management and Academic Achievement of Under Graduate Students

Time management is an important thing in human life because it is only a things in human life which cannot change by the human. Good time management leads to improved efficiency and productivity, less stress, and more su...

Petrology and Geochemical Study of Calc-Alkaline Lamprophyres from South of Garla Area Bank of Munneru River, Eastern Dharwar Craton, Telangana South India

The Eastern Dharwar Craton (EDC) in southern India frequently features lamprophyre dykes, with the present study identifying two new dykes near South of Garla village. Petrographic and geochemical analyses were conducted...

A Review of Oil Spills on Marine Life and Associated Wildlife

Oil is an ancient fossil fuel used to power sectors like heat and electricity production. A wide range of fuels in automobiles and lubricants for mechanical machines have a significant role in our economy. Oil spills occ...

Influence of Identity Crisis on Fear of Missing Out Among College Students

The current research endeavored to experimentally explore the correlation between identity achievement, identity moratorium, identity foreclosure, identity diffusion, and Fear of Missing Out (FOMO).The participants of th...

Download PDF file
  • EP ID EP739770
  • DOI 10.62226/ijarst20241396
  • Views 4
  • Downloads 0

How To Cite

Mamatha B*1, Sujatha P Terdal*2 (2024). A SHAP and LIME based Explainable AI Solution for Predicting Chronic Kidney Diseases. International Journal of Advanced Research in Science and Technology (IJARST), 13(6), -. https://europub.co.uk/articles/-A-739770