Manuscript received December 14, 2022; revised March 3, 2023; accepted July 3, 2023.
Abstract—Heart failure disease, a wide-ranging clinical disorder, is affecting more and more individuals worldwide. The Healthcare Sector (HCS) places a high focus on the early detection of cardiac disease. The creation of a machine learning-based cardiovascular disease prediction system is the main objective of this project. This study’s presentation of several machine learning techniques is based on a brief examination of heart disease diagnosis. First, a lasso features selection approach is used to forecast heart disease. The second ensemble strategy is utilized to look into several areas of cardiac disease. We provided two ensemble stages of classifiers such Max Voting and Stacking for XG Boost, Random Forest, and Multilayer Perception in order to enhance results. A variety of factors were used to evaluate the performance of the recommended cardiovascular disease in order to select the best machine learning model. The major objective of this study is to give physicians a tool to help in the early diagnosis of heart problems. As a result, treating patients effectively and preventing negative effects will be easy. This study lasso uses selection-based techniques with machine learning classifiers to investigate several classification algorithms in terms of Mean Average Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Scattered Index in an effort to increase the accuracy of heart disease identification.
Index Terms—XG boost, random forest, and multilayer perception, Mean Average Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), scattered index and heart disease dataset
The authors are with Department Computer Science & Engineering, Unsietvbs Purvanchal University, Jaunpur, India.
*Correspondence: gyanpal@gmail.com (G.K.P.)
[PDF]
Cite:Gyanendra Kumar Pal and Sanjeev Gangwar, "Analysis of Hidden Pattern of Heart Disease Dataset Using Multiple Machine Learning Ensemble Methods," International Journal of Computer Theory and Engineering vol. 15, no. 4, pp. 178-185, 2023.
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
