Multi-Disease Risk Prediction: Leveraging Machine Learning for Heart Disease and Diabetes Prediction

Abstract

Heart disease is one of the leading causes of death worldwide, affecting primarily middle aged and older adults, and men are more likely to be affected than women. The International Diabetes Federation also states that there are 382 million people with diabetes worldwide. That number is also expected to rise to 592 million by the year of 2035. In this research study we will present a machine learning model that predicts heart disease and diabetes using data from Kaggle, Data World and the UCI repository. We were operating under the empirical goal of developing a model that could help us when attempting to predict heart disease and diabetes, so that fewer human beings die from each respectively. Our aim contrived the development of a model that is expected to gain a higher percentage of accuracy by combining the results of several machine learning techniques. The machine learning techniques used were KNN, logistic regression, random forest, SVM and finally gradient- boosting. The ultimate conception of our research study was to determine the best model to use when predicting heart disease and diabetes.

Ähnliche Arbeiten