WCSE

An Ensemble Learning Model for Heart Disease Prediction

Abstract— Heart disease is a common disease that seriously threatens the health of mankind, especially the middle-aged population and the elderly. It is characterized by high prevalence, disability rate, and mortality rate. The patients are never completely cured even with the most advanced treatment. However, the prediction of the incidence in advance and the enabling of doctors on formulating scientific treatment plans would significantly improve the cure rate. In light of the current situation, this paper proposes a cardiovascular disease prediction model based on ensemble learning, which integrates several classical machine learning algorithms such as AdaBoost, Random Forest(RF), Support Vector Machine(SVM), Lightgbm, and Gradient Boosting Decision Tree(GBDT). The first four algorithms with low correlation are constructed as base learners and then ensemble into the meta learner Gradient Boosting Decision Tree to build an ensemble learning model. The excellence of the ensemble model is evaluated from the evaluation indexes such as accuracy, precision, and recall. The experimental results show that the accuracy rate of the ensemble model is 90%, the precision rate is 90.1%, and the recall rate is 90.66%. Compared with a single machine learning prediction model, the maximum improvement is 4%. The model will effectively assist doctors in making more accurate predictions of patients' physical conditions and carrying out scientific treatment.

Index Terms— heart disease, Adaboost, Random Forest, Support Vector Machine, Lightgbm, GBDT, Ensemble learning

Qingli Li
School of Computer Science and Technology, Xi'an University of Posts & Telecommunications, China
Yagang Wang
School of Computer Science and Technology, Xi'an University of Posts & Telecommunications, China
Shizhang Hu
School of Computer Science and Technology, Xi'an University of Posts & Telecommunications, China
Xiangchun Jin
School of Computer Science and Technology, Xi'an University of Posts & Telecommunications, China

[Download]

Cite: Qingli Li, Yagang Wang, Shizhang Hu, Xiangchun Jin, " An Ensemble Learning Model for Heart Disease Prediction, " WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications, pp. 1456-1463, Sanya, China, April 15-18, 2022.