NEURAL NETWORK MODEL FOR DIAGNOSING MYOCARDIAL INFARCTION
Abstract
Body surface potential mapping (BSPM) is a non-invasive and effective method for diagnosing coronary heart disease (CHD) and acute myocardial infarction (AMI). However, most existing systems of BSPM are unable to create standard diagnostic criteria. Aim. To develop the neural network model (NNM) for diagnosing Q-wave AMI and to assess the model effectiveness. Material and methods. The BSPM method in 90 leads was used in 96 controls, 35 patients with anterior Q-wave AMI, 43 with posterior Q-wave AMI, 14 with inferior Q-wave AMI, and 21 with lateral Q-wave AMI. The input NNM layer was decomposed into five subsets corresponding to horizontal levels of registered signals, using amplitudes of Q, R, S, and T waves and the ST segment. The output layer produced the probability of the norm (controls) and different AMI locations. Results. Exploring the NNM performance in controls and AMI patients, sensitivity of 100% and specificity of 97,4% was observed. Sensitivity reached 100% for anterior Q-wave AMI, 94,4% for posterior Q-wave AMI, 85,7% for inferior Q-wave AMI, and 83,3% for lateral Q-wave AMI. Conclusion. Our data have demonstrated the effectiveness of NNM in AMI diagnostics.
About the Authors
B. I. Zagidullin
Tatar Republic Hospital of Emergency Medical Care, Naberezhnye Chelny
Russian Federation
Russian Federation
I. A. Nagaev
Bashkir Republic Cardiology Dispanser, Ufa
Russian Federation
Russian Federation
N. Sh. Zagidullin
Bashkir State Medical University, Ufa
Russian Federation
Russian Federation
Sh. Z. Zagidullin
Bashkir State Medical University, Ufa
Russian Federation
Russian Federation
References
1. Finlay D., Nugent C., Donnelly M. et al. Selection of optimal recording sites for limited lead body surface potential mapping: A sequential selection based approach. BMC Medical Informatics and Decision Making. 2006, 6:9.
2. Ramanthan C., Ghanem R., Jia P. et al. Noninvasive electrocardiohraphic imaging for cardiac electrophysiology and arrythmia. Nature medicine. 2004; 10:4:422–8.
3. Medvegy M., MD, Preda I., Savard P. New Body Surface Isopotential Map Evaluation Method to Detect Minor Potential Losses in Non–Q-Wave Myocardial Infarction. Electrocardiographic body surface mapping: potential tool for the detection of transient myocardial ischemia in the 21st century? Ann Noninvasive Electrocardiol. 2009; 14 (2):201–10.
4. Kittnar O, Mlcek M. Analysis of the electrical heart field. Physiol Res. 2010; 59 Suppl 1: S19–24.
5. Golovenkin S. E., Shulman V. A., Gorban A. N. et al. The use of neuronet expert system for complications of myocardial infarction. IZvestiya VUZov. Priborostroenie. 2005; 5:19–22. Russian. (Головенкин С. Е., Шульман В. А., Горбань А. Н. и др. Применение нейросетевой экспертной системы для прогнозирования осложнений инфаркта миокарда. Известия ВУЗов. Приборостроение. 2005; 5:19–22).
6. Vartanov A. V. Mechanisms of semantics: human – neuron – model. Neurokompjuteri. 2011; 11:54–65. Russian (Вартанов А. В. Механизмы синематики: человек – нейрон – модель. Нейрокомпьютеры. 2011; 12:54–65).
7. Ijasov B. G., Munasypov R. A., Bulaev V. I. Neuronet structure minimization for data compression. Neurecomputors: Development, use. 2007; 10:75–81. Russian (Ильясов Б. Г., Мунасыпов Р. А., Булаев В. И. Минимизация структуры нейронной сети для решения задачи сжатия данных. Нейрокомпьютеры: Разработка, при-менение. 2001; 10:31–5).
8. Ijasov B. G. Zagidullin N. Sh., Munasypov P. A. et al. Computer program of myocardial infarction diagnostics “Neurokard”. Patent 2005610728 RF/Applic.
9. 04.2005. Russian (Ильясов Б. Г., Загидуллин Н. Ш., Мунасыпов Р. А. и др. Компьютерная программа нейросетевой диагностики инфаркта миокарда «Нейрокард». А. С. № 2005610728 РФ. Заявл. 11.04.2005).
10. Finlay D., Nugent C., McCullaghP. Mining for diagnostic information in body surface potential maps: A comparison of feature selection techniques. BioMedical Engineering OnLine. 2005, 4:51.
11. McClelland AJJ, Owens CG, Menown IBA et al. Comparison of the 80-lead body surface map to physician and to 12-lead electrocardiogram in detection of acute myocardial infarction. Am J Cardiol. 2003; 92 (3):252–7.
Review
For citations:
Zagidullin B.I., Nagaev I.A., Zagidullin N.Sh., Zagidullin Sh.Z. NEURAL NETWORK MODEL FOR DIAGNOSING MYOCARDIAL INFARCTION. Russian Journal of Cardiology. 2012;(6):51-54. (In Russ.)
Views:
436
Email this article 