Prediction with ML paradigm in Healthcare System

Precise and synchronized research of any health-related issues is important for the eradication and curing of the illness. But the accurate prediction on the basis of symptoms becomes too difficult for doctors. A stronger proposal to medical-care is to eradicate a disease with initial interference instead of taking treatment after it is recognized. Medical-care produces an enormous quantity of data, with the assistance of disease data, ML finds invisible samples of details in this enormous dataset. The aim of this research is to enhance the precision of the prognosis. Enlarging a health treatment system centered on several ML algorithms for the prognosis of any disease can assist in an extra correct diagnosis. Our dataset consists of 4920 patient data identified with 41 diseases. An experimental target consists of 41 diseases. 95 of 132 manipulated features closely coupled to diseases were picked and improved. The result of this research relies on how correct the data set is. For prognosis prediction, this research work has integrated the Naive-Bayes, Decision Trees, Random Forest, KNN, SVM, Logistic Regression, and SGD. The accuracy of general disease prediction by using KNN is 97.32%, which is more than any other algorithms. Our diagnosis model can act as a doctor for the early diagnosis of a disease to ensure the treatment can take place on time and lives can be saved.