Heart disease detection using machine learning

Mohammad Al-Habahbeh, Moath Alomari, Hebatullah Khattab, Raed Alazaidah, Nawaf Alshdaifat, Suhaila Abuowaida, Saleh Alqatan, Mohammad Arabiat

Abstract


Heart disease continues to be a major worldwide health issue, requiring accurate prediction models to improve early identification and treatment. This research aims to address two main objectives in light of the increasing prevalence of heart-related disorders. Firstly, it aims to determine the most efficient classifier for identifying heart disease among twenty-nine different classifiers that represent six distinct learning strategies. Furthermore, the research seeks to identify the most effective method for selecting features in heart disease datasets. The results show how well different classifiers and feature selection methods work by using two datasets with different features and judging performance using four important criteria. The evaluation results demonstrate that the RandomCommittee classifier outperforms in diagnosing heart illness, displaying strong skills across various learning strategies. This classifier exhibits favorable results in terms of accuracy, precision, recall, and F1-score metrics, hence confirming its appropriateness for predictive modeling in heart-related datasets. Moreover, the paper examines feature selection methods, specifically aiming to determine the most effective method for enhancing the predicted accuracy of heart disease models. The prediction models' overall performance is enhanced by their capacity to accurately identify and prioritize pertinent variables, thereby facilitating the early detection and management of heart-related problems.

Keywords


Fifth heart disease; First classification; Fourth machine learning; Second feature selection; Third learning strategies

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v14i2.8324

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191, e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).