Ensemble Learning for Heart Disease Prediction: a Review

EasyChair Preprint 15173

Abstract

Humanity has been affected by various diseases throughout history, which have killed many lives. One of the deadliest diseases that humanity has seen in the modern age and is still acknowledged today is heart disease. Heart disease is on the rise as a result of the spread of unhealthy behaviors including smoking, overeating, and inactivity. This paper examined the machine learning (ML), deep learning (DL), and ensemble learning methods (ELMs) utilized in heart disease prediction research, as well as how they are being implemented. Searches were carried out on the Google Scholar online datasets. Sixty-five studies were included, with ML methods making up most of the studies with 28 (43%), and ELMs were the next single largest group with 24 (37%). DL methods were the smallest single group with 13 (20%). The Cleveland dataset was used in most studies. The result shows that over the last 5 years, there has been a growing desire of leveraging ML, and DL techniques to help further the understanding of heart disease prediction, whether it be by expanding the knowledge of the physiological changes or by improving the accuracies of models to help improve the treatments and disease management.

Keyphrases: Heart Disease Prediction, deep learning, ensemble learning, machine learning

@booklet{EasyChair:15173,
  author    = {Rasha Alquhali},
  title     = {Ensemble Learning for Heart Disease Prediction: a Review},
  howpublished = {EasyChair Preprint 15173},
  year      = {EasyChair, 2024}}