통계적 학습 모형에 기반한 불규칙 맥파 검출 알고리즘 개발
Development of The Irregular Radial Pulse Detection Algorithm Based on Statistical Learning Model
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Arrhythmia is basically diagnosed with the electrocardiogram (ECG) signal, however, ECG is difficult to measure and it requires expert help in analyzing the signal. On the other hand, the radial pulse can be measured with easy and uncomplicated way in daily life, and could be suitable bio-signal for the recent untact paradigm and extensible signal for diagnosis of Korean medicine based on pulse pattern. In this study, we developed an irregular radial pulse detection algorithm based on a learning model and considered its applicability as arrhythmia screening. A total of 1432 pulse waves including irregular pulse data were used in the experiment. Three data sets were prepared with minimal preprocessing to avoid the heuristic feature extraction. As classification algorithms, elastic net logistic regression, random forest, and extreme gradient boosting were applied to each data set and the irregular pulse detection performances were estimated using area under the receiver operating characteristic curve based on a 10-fold cross-validation. The extreme gradient boosting method showed the superior performance than others and found that the classification accuracy reached 99.7%. The results confirmed that the proposed algorithm could be used for arrhythmia screening. To make a fusion technology integrating western and Korean medicine, arrhythmia subtype classification from the perspective of Korean medicine will be needed for future research.
Abstract
Arrhythmia is basically diagnosed with the electrocardiogram (ECG) signal, however, ECG is difficult to measure and it requires expert help in analyzing the signal. On the other hand, the radial pulse can be measured with easy and uncomplicated way in daily life, and could be suitable bio-signal for the recent untact paradigm and extensible signal for diagnosis of Korean medicine based on pulse pattern. In this study, we developed an irregular radial pulse detection algorithm based on a learning model and considered its applicability as arrhythmia screening. A total of 1432 pulse waves including irregular pulse data were used in the experiment. Three data sets were prepared with minimal preprocessing to avoid the heuristic feature extraction. As classification algorithms, elastic net logistic regression, random forest, and extreme gradient boosting were applied to each data set and the irregular pulse detection performances were estimated using area under the receiver operating characteristic curve based on a 10-fold cross-validation. The extreme gradient boosting method showed the superior performance than others and found that the classification accuracy reached 99.7%. The results confirmed that the proposed algorithm could be used for arrhythmia screening. To make a fusion technology integrating western and Korean medicine, arrhythmia subtype classification from the perspective of Korean medicine will be needed for future research.
참고문헌 (35)
- Garcia TB, "Arrhythmia recognition: The art of interpretation" (2019), Jones & Bartlett Publishers
- 송미혜, "SVM 분류기를 통한 심실세동 검출", 전자공학회논문지 - SC, 42(5), pp.261~268 (2005), 대한전자공학회
- 이승민, "심전도 신호에서 R파 왜곡에 따른 적응적 특이심박 검출", 전자공학회논문지, 51(9), pp.200~207 (2014), 대한전자공학회
- 조익성, "Auto Regressive모델링 기반의 특징점 추출과 Support Vector Machine을 통한 조기수축 부정맥 분류", 한국정보통신학회논문지, 23(2), pp.117~126 (2019), 한국정보통신학회[DOI]
- 이전, "홀터 심전계를 위한 심방세동 신호 추출 알고리즘", 전자공학회논문지 - SC, 49(3), pp.38~46 (2012), 대한전자공학회[DOI]
- Bashar SK, "Atrial Fibrillation Detection from Wrist Photoplethysmography Signals Using Smartwatches", Sci Rep, 9 (2019)
- Tison GH, "Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch", JAMA Cardiol, 3(5), pp.409~416 (2018)
- Sohn K, "Utility of a smartphone based system (cvrPhone) to predict short-term arrhythmia susceptibility", 9(1), pp.1~11 (2019)
- 조정희, "사용 편의성과 소형화 기반의 맥파 측정장치 개발", 의공학회지, 38(4), pp.168~174 (2017), 대한의용생체공학회
- Xu L, "Arrhythmic pulses detection using Lempel-Ziv complexity analysis", EURASIP Journal on Applied Signal Processing (2006)
- Wang H-Y, "A model for automatic identification of human pulse signals", Journal of Zhejiang University-Science A, 9(10), pp.1382~1389 (2008)
- Joo S, "Well-being Korean Medicine-Arrhythmia", Journal of the KSME, 46(2), pp.104~105 (2006)
- Min C-H, "Detection of ECG Signal Waveform for Arrhythmia Classification", Proceedings of the IEEK Conference, pp.453~456 (2005)
- Yildirim O, "Arrhythmia detection using deep convolutional neural network with long duration ECG signals", Comput Biol Med, 102, pp.411~420 (2018)
- Ullah A, "Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation", Remote Sensing, 12(10) (2020)
- Singh S, "Classification of ECG arrhythmia using recurrent neural networks", J Procedia computer science, 132, pp.1290~1297 (2018)
- Bae J-H, "Harmonic analysis of pulse morphology variability for pulse smoothness assessment", Biomedical Signal Processing and Control, 44, pp.1~11 (2018)
- Bae J-H, "New assessment model of pulse depth based on sensor displacement in pulse diagnostic devices", Evid Based Complement Alternat Med (2013)
- Smith J, "A flexible sampling-rate conversion method", IEEE International Conference on Acoustics, Speech, and Signal Processing, 9, pp.112~115 (1984)
- Wei L, "A new scientific method of pulse diagnosis", J American Journal of Acupuncture, 12(3), pp.205~218 (1984)
- Simon N, "Regularization paths for Cox’s proportional hazards model via coordinate descent", 39(5), pp.1~ (2011)
- Liaw A, "Classification and regression by random", Forest, 2(3), pp.18~22 (2002)
- Chen T, "Xgboost:extreme gradient boosting", 1~4 (2015)
- A Lasso and Elastic-Net Regularized Generalized Linear Model for Predicting Blast-Induced Air Over-pressure in Open-Pit Mines, "Bui XN", 21~ (2019)
- Breiman LJ, "Random forests", 45(1), pp.5~32 (2001)
- Wright MN, "ranger: A fast implementation of random forests for high dimensional data in C++ and R" (2015)
- Freund Y, "A decision-theoretic generalization of on-line learning and an application to boosting", 55(1), pp.119~139 (1997)
- Friedman JH, "Stochastic gradient boosting", 38(4), pp.367~378 (2002)
- Chen C, "Using random forest to learn imbalanced data", 110(12), pp.24~ (2004)
- Fluss R, "Estimation of the Youden Index and its associated cutoff point", 47(4), pp.458~472 (2005)
- Prasad B V P, "Detection and classification of cardiovascular abnormalities using FFT based multi-objective genetic algorithm", Biotechnology & Biotechnological Equipment, 32(1), pp.183~193 (2017)
- Huang CM, "Radial pressure pulse and heart rate variability in heat- and cold-stressed humans", Evid Based Complement Alternat Med (2011)
- Huang CM, "Developing the effective method of spectral harmonic energy ratio to analyze the arterial pulse spectrum", Evid Based Complement Alternat Med (2011)
- Sheridan RP, "Extreme gradient boosting as a method for quantitative structure–activity relationships", 56(12), pp.2353~2360 (2016)
- Ribeiro M T, "Why should I trust you? Explaining the predictions of any classifier", Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp.1135~1144 (2016)