Use of machine learning for early pre-clinical diagnostics of heart diseases

Authors

  • Z. M. Abdiakhmetova Faculty of Information Technology, al-Farabi Kazakh National University, Almaty, Kazakhstan
  • B. K. Alimbayeva Faculty of Information Technology, al-Farabi Kazakh National University, Almaty, Kazakhstan
  • P. T. Omarova Faculty of Information Technology, al-Farabi Kazakh National University, Almaty, Kazakhstan

DOI:

https://doi.org/10.26577/ijmph.2017.v8.i2.03

Abstract

 The main cause of death in different countries are heart diseases. Therefore, the problem of early preclinical diagnosis of these diseases at the origin is acute. ECG analysis is widely used to diagnose many cardiac diseases. Since the majority of clinically useful information in the ECG is found in the intervals and amplitudes determined by its significant points (characteristic peaks and wave boundaries), the development of accurate and reliable methods for automatic ECG delineation is a matter of great importance, especially for the analysis of long records. This article presents an intelligent system for the interpretation of electrocardiographic signals of cardiac valves based on the wavelet transform method. The model of the neural network of wavelet packets developed by us is used. The productivity of the developed system was estimated in 2000 samples. The test results showed that this system was effective when using wavelet transform methods. The correct rate of classification was about 91 percent for abnormal and normal subjects. The aim of the study is to develop a neural network based on the wavelet transform method for early preclinical diagnosis of diseases, and paroxysmal atrial fibrillation of the heart. At present, the problem of processing fuzzy data, short high-frequency low-amplitude signals is difficult to solve. Since, for example, if the ECG is visually monitored, the probability of obtaining a human error is high, every 10-result is interpreted with an error. In this connection, it became necessary to search for new methods for predicting signal propagation in various directions of science. The problems of extracting information from the electrophysiological signal that can not be obtained by visual analysis of the record, as well as the problems of automation of traditional algorithms of medical analysis are relevant in connection with the lack of research in this field [1].

      G M T   Английский Испанский Итальянский Казахский Китайский Трад Китайский Упр Корейский Русский Турецкий Французский   Английский Испанский Итальянский Казахский Китайский Трад Китайский Упр Корейский Русский Турецкий Французский                 Звуковая функция ограничена 200 символами     Настройки : История : Обратная связь : Donate Закрыть

Downloads

Published

2017-12-25

How to Cite

Abdiakhmetova, Z. M., Alimbayeva, B. K., & Omarova, P. T. (2017). Use of machine learning for early pre-clinical diagnostics of heart diseases. International Journal of Mathematics and Physics, 8(2), 19–22. https://doi.org/10.26577/ijmph.2017.v8.i2.03