A Comprehensive Review on Disease Predictions Using Machine Learning Approaches

There are various machine learning models for medical treatment that are now in use, however they all primarily target identifying a single condition. Consequently, this study has created a mechanism to just one graphical interface can predict multiple illness. This framework is capable of predicting numerous illnesses, including coronary artery disease, arrhythmias, Parkinson, Alzheimer, chronic kidney disease, and polycystic kidney disease. If neglected even when handled such illness are dangerous for people. Due to this, early recognition and treatment of may save countless lives in these conditions. This study makes a proposed approach, and use single model and mixed dataset of heart, brain, and kidney. There are several techniques for classification k-nearest neighbor, logistic regression, decision trees, Random Forest, naive Bayes to do illness prediction. Every algorithm correctness is verified and in contrast to each other to identify the most precise forecasts. Also, numerous datasets (one for each condition) are employed to ensure that predictions are accurate. The primary objective is to develop a proposed model that can forecast various disease using machine learning including coronary artery disease, arrhythmias, Parkinson, Alzheimer, chronic kidney disease, and polycystic kidney.