Using machine learning techniques to differentiate acute coronary syndrome

authors:

avatar Sougand Setareh 1 , avatar Ali Asghar Safaei 1 , * , avatar Farid Najafi 2

Dept. of Medical Informatics, Faculty of Medical Science, Tarbiat Modares University, Tehran, Iran
Dept. of Biostatistics and Epidemiology, School of Health, Kermanshah University of Medical Sciences, Kermanshah, Iran
Journal of Kermanshah University of Medical Sciences: Vol.18, issue 11; e73997
published online: February 27, 2015
article type: Article Commentary
received: September 02, 2014
accepted: January 20, 2015
DOI: https://doi.org/10.22110/jkums.v18i11.2023

how to cite: Setareh S, Safaei A A, Najafi F. Using machine learning techniques to differentiate acute coronary syndrome. J Kermanshah Univ Med Sci. 2015;18(11):e73997. https://doi.org/10.22110/jkums.v18i11.2023.

Abstract

Backgroud: Acute coronary syndrome (ACS) is an unstable and dynamic process that includes unstable angina, ST elevation myocardial infarction, and non-ST elevation myocardial infarction. Despite recent technological advances in early diognosis of ACS,  differentiating between different types of coronary diseases in the early hours of admission is controversial. The present study was aimed to accurately differentiate between various coronary events, using machine learning techniques. Such methods, as a subset of artificial intelligence, include algorithms that allow computers to learn and play a major role in treatment decisions.
Methods: 1902 patients diagnosed with ACS  and admitted to hospital were selected according to Euro Heart Survey on ACS. Patients were classified based on decision tree J48. Bagging aggregation algorithms was implemented to increase the efficiency of algorithm.
Results: The performance of classifiers was estimated and compared based on their accuracy computed from confusion matrix. The accuracy rates of decision tree and bagging algorithm were calculated to be 91.74% and 92.53%, respectively.
Conclusion: The proposed methods used in this study proved to have the ability to identify various ACS. In addition, using matrix of confusion, an acceptable number of subjects with acute coronary syndrome were identified in each class. 

Fulltext

References

  • 1.

    The references of this article is available on PDF.