Improved sparse autoencoder based artificial neural network approach for prediction of heart disease

Ibomoiye Domor Mienye, Yanxia Sun, Zenghui Wang

Research output: Contribution to journalArticlepeer-review

81 Citations (Scopus)

Abstract

In this paper a two stage method is proposed to effectively predict heart disease. The first stage involves training an improved sparse autoencoder (SAE), an unsupervised neural network, to learn the best representation of the training data. The second stage involves using an artificial neural network (ANN) to predict the health status based on the learned records. The SAE was optimized so as to train an efficient model. The experimental result shows that the proposed method improves the performance of the ANN classifier, and is more robust as compared to other methods and similar scholarly works.

Original languageEnglish
Article number100307
JournalInformatics in Medicine Unlocked
Volume18
DOIs
Publication statusPublished - 2020

Keywords

  • ANN
  • Deep learning
  • Heart disease
  • Sparse autoencoder
  • Unsupervised learning

ASJC Scopus subject areas

  • Health Informatics

Fingerprint

Dive into the research topics of 'Improved sparse autoencoder based artificial neural network approach for prediction of heart disease'. Together they form a unique fingerprint.

Cite this