โมเดลทำนายการรอดชีวิตของผู้ป่วยโรคหัวใจล้มเหลวโดยใช้วิธีแบบผสม

Abstract

The purposes of this research were to develop a predictive model for survival of patients with heart failure using ensemble methods. This study the variables used in the model to describe the factors affecting the survival of heart failure patients from the RapidMiner program using Synthetic Minority Oversampling Technique (SMOTE) method to correct data imbalances class. This model use a combination of techniques such as Artificial Neural Network, Random Forest, Decision Tree, K-Nearest Neighbors, and Support Vector Machine to create prediction models. As a result, a developed model with 0.9268 accuracy was created to predict the survival of heart failure patients. The results of the study can be applied to the creation of a treatment decision support system for physicians and clinical professionals in healthcare to make sensible decisions.