Prediction Of The Sickle Cell Anaemia Disease Using Machine Learning Techniques

Abstract

This research examines the utilization of machine learning to classify medical datasets, especially to guide sickle cell illness therapy. Numerous studies had shown that machine learning algorithms enhance pre-processing of medical time-series data signals and help classify medical data accurately. This study presents data for different kinds of medical learning algorithms. The first case is to identify drug dosages for individuals with Sickle Cell Disorder. The present study explores the performance and accuracy of Fuzzy C- means architectures. The major goal of using categorization is to help healthcare institutions give proper medicine dosage. Accuracy curves for the training and testing datasets are represented by the matching curves for each of the bars on the graphs During trials, the Fuzzy C-means delivered the best overall results with an accuracy of 99.90%.