Machine learning approach for predicting heart and diabetes diseases using data-driven analysis

Abstract

<p>Environmental changes and food habits affect people's health with numerous<br />diseases in today's life. Machine learning is a technique that plays a vital role<br />in predicting diseases from collected data. The health sector has plenty of<br />electronic medical data, which helps this technique to diagnose various<br />diseases quickly and accurately. There has been an improvement in accuracy<br />in medical data analysis as data continues to grow in the medical field. Doctors<br />may have a hard time predicting symptoms accurately. This proposed work<br />utilized Kaggle data to predict and diagnose heart and diabetic diseases. The<br />diseases heart and diabetes are the foremost cause of higher death rates for<br />people. The dataset contains target features for the diagnosis of heart disease.<br />This work finds the target variable for diabetic disease by comparing the<br />patient's blood sugars to normal levels. Blood pressure, body mass index<br />(BMI), and other factors diagnose these diseases and disorders. This work<br />justifies the filter method and principal component analysis for selecting and<br />extracting the feature. The main aim of this work is to highlight the<br />implementation of three ensemble techniques-Adaptive boost, Extreme<br />Gradient boosting, and Gradient boosting-as well as the emphasis placed on<br />the accuracy of the results.</p>