Heart disease prediction method based on dual feature selection and XGBoost algorithm

Abstract

The invention discloses a heart disease prediction method based on dual feature selection and an XGBoost algorithm. The method comprises the following steps that original data is processed, the processed data is subjected to a random forest algorithm and feature correlation analysis, feature indexes are calculated according to importance ranking of features, correlation among features and correlation between the features and sample tags, the features are selected for model training, and thus, the defects that existing heart disease prediction needs too many features and is poor in accuracy areovercome.

Description

technical field [0001] The invention belongs to the technical field of medical data analysis, in particular to a heart disease prediction method based on dual feature selection and XGBoost algorithm. Background technique [0002] Heart disease is a common and serious cardiovascular disease in life. Cardiovascular disease is one of the biggest threats to people's health in my country and even in the world. This disease has brought a serious burden to the medical system in our country. The "Global Burden of Disease Report 2013" published by the famous journal "The Lancet" evaluated the death of patients in 190 countries between 1990 and 2013. It pointed out that coronary heart disease, chronic lung disease, and sudden brain death are the three most common diseases in Chinese people. The mortality rate was as high as 46% in that year, and this number is still increasing. Based on existing medical data, we can train heart disease prediction models to provide health guidance fo...

AI Technical Summary

Problems solved by technology

However, the GBDT algorithm only samples the classification and regression tree (CART) as the base classifier. Compared with the XGBoost algorithm, the base classifier is single, and it cannot handle missing values, which is easy to overfit.

Images