Optimized SVM With BWA for CKD Prediction

Abstract Chronic Kidney Disease (CKD) is a significant health concern affecting millions worldwide. It is a prevalent health condition which results in gradual loss of Kidney function. About 10% of global population is affected by it which accounts to more than 800 million people. There is a need for early diagnosis and intervention to mitigate its risk. By Utilizing the AI/ML algorithms prediction of CKD can be done accurately. In this paper the efficiency of Black widow optimization algorithm with SVM is proposed in identifying whether it is prone to CKD or not. CKD dataset from standard UCI machine learning repository which consists of wide range of clinical features and biomarkers which aids in CKD Classification has been used. The accuracy and execution time of BWO-SVM achieved is 98.75% and 0.0023s in classifying CKD. It is observed that the BWO SVM algorithm outperforms other algorithms in terms of both accuracy and execution time metrics. The intention of this project is to contribute in CKD diagnosis and help to provide early detection and timely intervention.