Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지

Prediction of Transient Ischemia Using ECG Signals

심전도 신호를 이용한 일시적 허혈 예측

  • Han-Go Choi (School of Electronics Engineering, Kumoh National Institute of Technology) ;
  • Roger G. Mark (Health Science and Technology, Massachusetts Institute of Technology, Cambridge, U.S.A.)
  • Published : 2004.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents automated prediction of transient ischemic episodes using neural networks(NN) based pattern matching method. The learning algorithm used to train the multilayer networks is a modified backpropagation algorithm. The algorithm updates parameters of nonlinear function in a neuron as well as connecting weights between neurons to improve learning speed. The performance of the method was evaluated using ECG signals of the MIT/BIH long-term database. Experimental results for 15 records(237 ischemic episodes) show that the average sensitivity and specificity of ischemic episode prediction are 85.71% and 71.11%, respectively. It is also found that the proposed method predicts an average of 45.53［sec］ ahead real ischemia. These results indicate that the NN approach as the pattern matching classifier can be a useful tool for the prediction of transient ischemic episodes.

본 연구는 신경망에 근거한 패턴매칭 방법을 사용하여 일시적 허혈 에피소드의 자동예측을 다루고 있다. 다층 신경망을 학습하기 위한 알고리즘은 수정된 역전파 알고리즘으로서 이 알고리즘은 학습속도를 향상시키기 위해 뉴런간의 연결계수 뿐만 아니라 뉴런내 비선형 함수의 변수들도 갱신한다. 제안된 방법의 성능은 MIT/BIH long-term 데이터베이스의 심전도(ECG) 신호를 사용하여 평가하였다. 총 15 레코드(237 허혈 에피소드)에 대한 실험결과에 의하면 허혈 에피소드 예측의 평균 sensitivity와 specificity 각각 85.71%와 71.11%이다. 또한 제안된 방법은 실제 허혈 에피소드로부터 평균 45.53초 이전에 예측하였다. 이러한 결과는 패턴매칭 분류기로서의 신경망 접근방법이 일시적 허혈 에피소드예측에 유용한 도구로 사용될 수 있음을 의미한다.

Keywords

References

  1. Ann. N Acad. Sci. v.601 Electrocardiography: Past and Future P. Counmel;O. Garfein
  2. The Heart and Cardiovascular System v.2 Effects of acute ischemia on cardiac electrophysiology L.S. Geddes;W.E. Cascio;H.A. Fozzard(et al.)(Eds.)
  3. IEE Trans. on Biomed. Eng. v.47 no.9 Automatic detection of ST-T complex changes on the ECG using filtered RMS difference series: Application to ambulatory ischemia monitoring J. Garcia;L.Sornmo;S. Olmos;P. Laguna
  4. IEEE Trans. on biomedical engineering v.46 no.11 ECG analysis using nonlinear PCA neural networks for ischemia detection T. Stamkopoulos;K. Diamentaras;N. Maglaveras;M. Strinzis
  5. IEEE Trans. on biomedical engineering v.45 no.7 An adaptive backpropagatrion neural network for real-time ischemia episodes detection: Development and performance analysis using the european ST-T database N. Maglaveras;T. Stamkopoulos;C. Pappas;M.G. Strintzis
  6. IEEE Trans. Biomed. Eng. v.42 Detection of ECG characteristic points using wavelet transforms C. Li;C. Zheng;C. Tai
  7. IEEE Trans. Biomed. Eng. v.BME-33 Recognition of the shape of the ST segment in ECG waveforms E. Skordalakis
  8. Journal of the American College of Cardiology v.38 no.3 Changes in heart rate and heart rate variability before ambulatory ischemic events W.J. Kop;R.J. Verdino;J.S. Gottdiener;S.T. O'leary;C.N.Merz;D.S. Krantz
  9. Computer in Cardiology v.24 Sympatho-Vagal correlates of transient ischemia in ambulatory patients J. Jager;G.B. Moody;G. Antolic;D. Masic;R.G. Mark
  10. Ann. Ncninvasive Electrocardioligy v.2 no.3 The initial ECG pattern in acute myocardial infarction: Correlation with underlying coronary anatomy and prognosis Y. Birnbaum;S. Sclarovsky
  11. Med. Biol. ENg. Comput. v.37 Analysis of the ST-T complex of the electrocardiogram using the Karhunen-Loeve transform: Adaptive monitoring and alternans detection P. Laguna;G.B. Moody;G. Garcia;A.L. Goldberger;T.G. Mark
  12. Compt. Biomed. Res. v.32 no.5 Identification of the occluded artery in patients with myocardial ischemia induced by prolonged PTCA using traditional vs. transformed ECG-based indexes J. Garcia;G. Wagner;L. Sornmo;P. Lander;P. Laguna
  13. Computer in Cardiology v.27 The long-term ST database: a research resource for algorithm development and physiologic studies of transient myocardial ischemia F. Jager;A. Taddei;M. Emdin;G. Antolic;R. Dorn;G.B. Moody;B. Glavic;A. Smrdel;M. Varanini;M. Zabukovec;S. Bordigiagp;C. Marchesi;R.G. Mark
  14. IEEE Int. Conf. ASSP. v.3 A probabilistic approach to the understanding and training of neural network classifiers H. Gish
  15. IEEE Int. Joint Conf. on Neural Networks v.3 A new error criterion for posterior probability estimation with neural nets A. El-Jaroudi;J. Makhoul