Predictive analysis of multiple diseases using ensemble learning

With the big data revolution, medical organizations are turning to machine learning and predictive analytics to make data-driven decisions and improve patient outcomes. Early predictions can help prevent the progression of diseases. It allows healthcare businesses to take quick actions in time and avoid the long-term effects of epidemics. A tool can be set up to predict and create a risk score based on different datasets. In the proposed model how various ensembling techniques affects the results over machine learning algorithms is observed. The suggested model uses various models like Support vector classifier, Hyper parameter tuned Support vector classifier, Naive Bayes and Decision tree are used to perform the predictive analysis. Later these models are compared with models using the ensemble techniques. By doing so the process of decision making got much easier. This helped the overall process of predictive analysis by giving better predictions of diseases by outperforming the accuracy of single classifier models which gave the maximum accuracy of 95%. The proposed models using ensemble learning gave accuracy of 99%.