Utilization of Five-Distinct Dataset to Diagnose and Predict Heart Disease: A Machine Learning Approach

The heart is a finely-tuned instrument that serves the whole body. Heart disease is the most common serious illness affecting human nature. Early diagnosis of heart disease is the most important for reducing mortality and minimizing heart disease-related complications. Manual identification of heart disease is a very monotonous task or perhaps impossible at times. Machine learning algorithms can be used to detect risk characteristics, which might lead to more accurate heart disease prediction. In this article, we present a model that is based on machine learning with the goal of improving the accuracy of the prediction of heart diseases. To make our applied model successful, efficient data collection, data preprocessing techniques have been performed efficiently. The dataset consists of various medical issues relating to a heart disease. To handle missing data, the transformation method has been applied. For the classification purposes, six machine learning (ML) classifiers have applied. We have also calculated seven different performance evaluation metrics to evaluate each classifier’s performance. Our presented model has obtained higher accuracy for the Random Forest classifier which is 95.61%.