Efficient Data Classification Model with Optimal Feature Selection for Predicting Chronic Kidney Disease

Medical professionals are embracing new medical information systems and electronic health records (EHRs) due to the rapid growth of technologies. Many forms of big data emerge in the field of healthcare, including but not limited to records from hospitals, medical records for patients, test findings, and IoT devices. There is a growing demand for more reliable methods of data capture, storage, and analysis as a result of the exponential growth in data generated by mining equipment. Health care organisations are rapidly realising the value of big data analytics for mining insights from massive amounts of medical data. New possibilities for contemporary healthcare may emerge from well-managed, analysed, and interpreted Big Data. These days, healthcare organisations produce vast amounts of data that is either not organised or only partially organised, necessitating real-time processing and analysis. In order to identify the most significant data for improved health care, modern medical practices need a smart and interactive platform that can handle massive biological datasets via human-computer interaction. However, the impact of big data and Machine Learning (ML) on healthcare is becoming more difficult to picture. With an accuracy of $99.35 \%$, the suggested approach, Particle Swarm Optimization for Feature Selection (PSO-FS), surpasses competing methods including Naive Bayes (NB), Ant Colony Optimization (ACO), OlexGA, and Random Tree (RT).