Prediction of heart attack based on ensemble learning

Heart disease has always been a high proportion of diseases worldwide, and it is also one of the leading causes of death worldwide. The prevention and detection of heart disease is still a key issue. To enhance patient outcomes in the real world and add to the expanding body of knowledge in heart disease research, this work aims to develop an integrated learning model to predict heart disease using machine learning techniques. The main research object of this paper is the heart disease data set. This paper's primary approach is to use 10 distinct machine-learning algorithms to construct a model for predicting heart attacks. And then, score and compare the performance of the models with some fundamental metrics. According to the result of the performance, the best three are selected, and a better-ensembled model is built through the ensemble learning of the voting method with Multilayer Perceptron Classifier (MLPC), the Support Vector Machine (SVM), and the Naive Bayes. This may be likely to help with real-life diagnoses in the future.