Cardiovascular Disease Diagnosis Based on Stacking Technology

摘要

Machine learning algorithms are widely used in the medical field. In the field of cardiovascular disease research, machine learning can be used for assisted diagnosis. In this paper, a model was built to use stacking technology to fuse logistic regression, support vector machine and BP neural network. Then cardiovascular disease dataset was used to solve the problem of how to improve the accuracy of cardiovascular disease diagnosis and shorten the diagnosis time. In the data collection, half of the patients were ill, and half were not. Most of them were male. Patients ‘ages, heights and weights were not the same. They were low in cholesterol and glucose, had no smoking or drinking habits, and most of them had physical labor. The model accuracy and F1 score trained with stacking technology are the highest, with a large increase. When training the model, we could get an auxiliary diagnostic accuracy higher than that of machine learning model using a certain algorithm alone without too many adjustments and feature selection. Its results are more accurate, greatly improving the accuracy of doctors in clinical diagnosis, and shortening the diagnostic time, so that patients can be treated in time.