Cardiovascular Disease Prediction from Electrocardiogram by Using Machine Learning

Authors

  • Nayan Nazrul Anuar Universiti Kebangsaan Malaysia https://orcid.org/0000-0001-6657-2982
  • Ab Hamid Hafifah Universiti Kebangsaan Malaysia
  • Suboh Mohd Zubir Universiti Kebangsaan Malaysia
  • Abdullah Noraidatulakma UKM Medical Molecular Biology Institute
  • Jaafar Rosmina Universiti Kebangsaan Malaysia
  • Mhd Yusof Nurul Ain UKM Medical Molecular Biology Institute
  • Hamid Mariatul Akma UKM Medical Molecular Biology Institute
  • Zubiri Nur Farawahida UKM Medical Molecular Biology Institute
  • Kamalul Arifin Azwa Shawani UKM Medical Molecular Biology Institute
  • Mohd Abd Daud Syakila UKM Medical Molecular Biology Institute
  • Kamaruddin Mohd Arman UKM Medical Molecular Biology Institute
  • A. Jamal Rahman UKM Medical Molecular Biology Institute

DOI:

https://doi.org/10.3991/ijoe.v16i07.13569

Keywords:

CVD, ECG, machine learning, The Malaysian Cohort, RMSSD

Abstract


Cardiovascular disease (CVD) is the leading cause of deaths worldwide. In 2017, CVD contributed to 13,503 deaths in Malaysia. The current approaches for CVD prediction are usually invasive and costly. Machine learning (ML) techniques allow an accurate prediction by utilizing the complex interactions among relevant risk factors. This study presents a case–control study involving 60 participants from The Malaysian Cohort, which is a prospective population-based project. Five parameters, namely, the R–R interval and root mean square of successive differences extracted from electrocardiogram (ECG), systolic and diastolic blood pressures, and total cholesterol level, were statistically significant in predicting CVD. Six ML algorithms, namely, linear discriminant analysis, linear and quadratic support vector machines, decision tree, k-nearest neighbor, and artificial neural network (ANN), were evaluated to determine the most accurate classifier in predicting CVD risk. ANN, which achieved 90% specificity, 90% sensitivity, and 90% accuracy, demonstrated the highest prediction performance among the six algorithms. In summary, by utilizing ML techniques, ECG data can serve as a good parameter for CVD prediction among the Malaysian multiethnic population.

Downloads

Published

2020-06-19

How to Cite

Nazrul Anuar, N., Hafifah, A. H., Mohd Zubir, S., Noraidatulakma, A., Rosmina, J., Nurul Ain, M. Y., … Rahman, A. J. (2020). Cardiovascular Disease Prediction from Electrocardiogram by Using Machine Learning. International Journal of Online and Biomedical Engineering (iJOE), 16(07), pp. 34–48. https://doi.org/10.3991/ijoe.v16i07.13569

Issue

Section

Papers