Browse > Article
http://dx.doi.org/10.9718/JBER.2019.40.2.62

Performance Evaluation of Deep Neural Network (DNN) Based on HRV Parameters for Judgment of Risk Factors for Coronary Artery Disease  

Park, Sung Jun (Department of Biomedical Engineering, Graduate School, Konyang University)
Choi, Seung Yeon (Department of Biomedical Engineering, Graduate School, Konyang University)
Kim, Young Mo (Department of Biomedical Engineering, Graduate School, Konyang University)
Publication Information
Journal of Biomedical Engineering Research / v.40, no.2, 2019 , pp. 62-67 More about this Journal
Abstract
The purpose of this study was to evaluate the performance of deep neural network model in order to determine whether there is a risk factor for coronary artery disease based on the cardiac variation parameter. The study used unidentifiable 297 data to evaluate the performance of the model. Input data consists of heart rate parameters, which are SDNN (standard deviation of the N-N intervals), PSI (physical stress index), TP (total power), VLF (very low frequency), LF (low frequency), HF (high frequency), RMSSD (root mean square of successive difference) APEN (approximate entropy) and SRD (successive R-R interval difference), the age group and sex. Output data are divided into normal and patient groups, and the patient group consists of those diagnosed with diabetes, high blood pressure, and hyperlipidemia among the various risk factors that can cause coronary artery disease. Based on this, a binary classification model was applied using Deep Neural Network of deep learning techniques to classify normal and patient groups efficiently. To evaluate the effectiveness of the model used in this study, Kernel SVM (support vector machine), one of the classification models in machine learning, was compared and evaluated using same data. The results showed that the accuracy of the proposed deep neural network was train set 91.79% and test set 85.56% and the specificity was 87.04% and the sensitivity was 83.33% from the point of diagnosis. These results suggest that deep learning is more efficient when classifying these medical data because the train set accuracy in the deep neural network was 7.73% higher than the comparative model Kernel SVM.
Keywords
Autonomic nervous system (ANS); Cardiovascular risk factors; Heart rate variability (HRV); Deep learning; Deep neural network (DNN);
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 B. M. Curtis and J. H. Jr. O'Keefe, "Autonomic tone as a cardiovascular risk factor: the dangers of chronic fight or flight," Mayo Clin Proc, vol. 77, no. 1, pp. 45-54, 2002.   DOI
2 N. Lakusic, D. Mahovic and T. Babic, "Gradual recovery of impaired cardiac autonomic balance within first six months after ischemic cerebral stroke," Acta Neurol Belg., vol. 105, no. 1, pp. 39-42, 2005.
3 http://www.mohw.go.kr/react/jb/sjb030301vw.jsp?PAR_MENU_ID=03&MENU_ID=032901&CONT_SEQ=336672&page=1, accessed on 28 Jan. 2010.
4 E.J. Um, W.R. Park, J.S. Kim, B.J. Lee and B.J. Na, "Comparison of Cerebral Blood Flow between Patients with Metabolic Syndrome and Normal Group to Evaluate Diagnostic Value of Transcranial Doppler Ultrasound," Journal Of The Korea Institute Of Oriental Medical Diagnostics, vol.14, no. 2, pp. 85-100, 2010.
5 M. Esler, "The autonomic nervous system and cardiac arrhythmias," Cl in Auton Res., vol. 2, no. 2 pp. 133-135, 1992.   DOI
6 R. P. Sloan, J. B. Korten and M. M. Myers, "Components of heart rate reactivity during mental arithmetic with and without speaking," Physiol Behav., vol. 50, no. 5, pp. 1039-1045, 1991.   DOI
7 Nationwide College of Oriental Medicine, "Oriental Medicine.Neurology," Seoul, Korea: Koonja Publishing Inc., 2010, pp. 171-178.
8 A. R. Richard, P. B. Jean and S. C. Alain, "Heart rate variability modulation after manipulation in pain-free patients vs patient in pain," Journal of Manipulation and Physiology Therapeutics, vol. 32, no. 4, pp. 277-286, 2009.   DOI
9 K.Y. Kim, H.K. Rhee, S.K. Jung and H.J. Jung, "Evaluation of Autonomic Function in Patients with Hyperhidrosis by Power Spectral Analysis of Heart Rate Variability," Journal of Oriental Medicine, vol. 29, no. 1, pp. 1-11, 2008.
10 J.H. Kang and Y.N. Kim, "The influence of Transcutaneous Electrical Stimulation on Autonomic Function," Journal of the Korean Society of Physical Medicine, vol. 4, no. 4, pp. 241-247, 2009.
11 H. Mussalo, E. Vanninen, R. Ikaheimo, T. Laitinen, M. Laakso, E. Lansimies and J. Hartikainen, "Heart rate variability and its determinants in patients with severe or mild essential hypertension," Clinical Physiology, vol. 21, no. 5, pp. 594-604, 2001.   DOI
12 B. Ballinger, J. Hsieh, A. Singh, N. Sohoni, J. Wang, G. H. Tison, G. M. Marcus, J. M. Sanchez, C. Maguire, J. E. Olgin and M. J. Pletcher, "DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction," The Association for the Advancement of Artificial Intelligence AAAI Conference( AAAI), USA, New Orleans, Feb. 2018.
13 I. H. Cho, C. Y. Kwon, J.S. Kim, C.H. Lee and D.H. Yoon, "A Study on Noise Cancellation of ECG Signal Using Neural Network," Journal of Korean Institute of Information Technology, vol. 6, no. 4, pp. 151-157, 2008.
14 A. Aliper, S. Plis, A. Artemov, A. Ulloa, P. Mamoshina, and A. Zhavoronkov, "Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data," Molecular Pharmaceutics, vol. 13, no. 7, pp. 2524-2530, 2016.   DOI
15 T. Madl, "Deep Neural Heart Rate Variability Analysis," arXiv preprint arXiv:1612.09205, Sep. 2016.
16 Y. LeCun, Y. Bengio and G. Hinton, "Deep Learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.   DOI
17 S. S. Xu, M. W. Mak and C. C. Cheung "Deep Neural Network Versus Support Vector Machines for ECG Arrhythmia Classification," International Conference on Multimedia and Expo Workshops(ICMEW), America, San Diego, Jul. 2017, pp. 127-132.
18 D. P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," International Conference Learning Representations( ICLR), America, San Diego, Dec. 2014.