A SHAP and LIME based Explainable AI Solution for Predicting Chronic Kidney Diseases
Journal Title: International Journal of Advanced Research in Science and Technology (IJARST) - Year 2024, Vol 13, Issue 6
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
- EP ID EP739770
- DOI 10.62226/ijarst20241396
- Views 38
- Downloads 0
Transforming Education Through Technology: Empowering Students in The Digital Age, A Mini Review
In the actively growing educational platform, the implementation of information and communication technology (ICT) has become pivotal for educators to facilitate students with the skills required to flourish in a dynamic...
Epileptic Seizure Detection by Cascading Isolation Forest-Based Anomaly Screening and Easy Ensemble
Electroencephalogram (EEG) signal-based emotion recognition has attracted wide interests in recent years and has been broadly adopted in medical, affective computing, and other relevant fields. Depression has become a le...
Enhancing Malware Detection through Machine Learning: A Comparative Analysis of Random Forest and Naive Bayes Classification Systems
Malware, a type of malicious software encompassing viruses, worms, Trojans, backdoors, and spyware, poses a grave threat to the confidentiality, integrity, and functionality of computer systems, given their integral role...
Anticancer Properties and Cytotoxic Effects of Agasthiyar Hills Medicinal Herb Vernonia cinerea
Vernonia cinerea, an indigenous medicinal plant in Agasthiyar Hills, exhibits potent anticancer properties and cytotoxic effects. Research has revealed its ability to prevent the proliferation of cancer cells through sev...
A Review on Mineralization on Sustainable Dryland Agriculture
Sustainable dryland agricultural production relies on efficient and integrated systems for resource management, including irrigation and dryland farming, with water and soil conservation and efficient utilization of nutr...