Similar articles

Abstract: Deep learning provides an effective way for automatic classification of cardiac arrhythmias, but in clinical decision-making, pure data-driven methods working as black-boxes may lead to unsatisfactory results. A promising solution is combining domain knowledge with deep learning. This paper develops a flexible and extensible framework for integrating domain knowledge with a deep neural network. The model consists of a deep neural network to capture the statistical pattern between input data and the ground-truth label, and a knowledge module to guarantee consistency with the domain knowledge. These two components are trained interactively to bring the best of both worlds. The experiments show that the domain knowledge is valuable in refining the neural network prediction and thus improves accuracy.

融入领域知识的深度学习在心律失常分类中的应用

[1]Abadi M, Barham P, Chen JM, et al., 2016. TensorFlow: a system for large-scale machine learning. 12^th SENIX Conf on Operating Systems Design and Implementation, p.265-283.

[2]Acharya UR, Fujita H, Oh SL, et al., 2019. Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals. Appl Intell, 49(1):16-27.

[3]Baloglu UB, Talo M, Yildirim Ö, et al., 2019. Classification of myocardial infarction with multi-lead ECG signals and deep CNN. Patt Recogn Lett, 122:23-30.

[4]Chen B, Guo W, Li B, et al., 2018. A study of deep feature fusion based methods for classifying multi-lead ECG. https://arxiv.org/abs/1808.01721

[5]Chen TM, Huang CH, Shih ESC, et al., 2020. Detection and classification of cardiac arrhythmias by a challenge-best deep learning neural network model. iScience, 23(3):100886.

[6]Crawford MH, Bernstein SJ, Deedwania PĆ, et al., 1999. ACC/AHA guidelines for ambulatory electrocardiography: a report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines (Committee to revise the guidelines for ambulatory electrocardiography)developed in collaboration with the North American Society for Pacing and Electrophysiology. J Am Coll Cardiol, 34(3):912-948.

[7]Dai WZ, Xu QL, Yu Y, et al., 2019. Bridging machine learning and logical reasoning by abductive learning. 33^rd Conf on Neural Information Processing Systems, p.2811-2822.

[8]Diligenti M, Gori M, Sacca C, 2017. Semantic-based regularization for learning and inference. Artif Intell, 244:143-165.

[9]Fawaz HI, Lucas B, Forestier G, et al., 2020. InceptionTime: finding AlexNet for time series classification. Data Min Knowl Disc, 34(6):1936-1962.

[10]Giannini F, Diligenti M, Gori M, et al., 2019. On a convex logic fragment for learning and reasoning. IEEE Trans Fuzzy Syst, 27(7):1407-1416.

[11]Goldberger AL, Goldberger ZD, Shvilkin A, 2017. Goldberger’s Clinical Electrocardiography (9^th Ed.). Elsevier, Armstrong, the Netherlands.

[12]Gorgels APM, Engelen DJM, Wellens HJJ, 2001. Lead aVR, a mostly ignored but very valuable lead in clinical electrocardiography. J Am Coll Cardiol, 38(5):1355-1356.

[13]Gupta A, Huerta EA, Zhao ZZ, et al., 2020. Deep learning for cardiologist-level myocardial infarction detection in electrocardiograms. Proc 8^th European Medical and Biological Engineering Conf, p.341-355.

[14]Hamad T, 2018. ABC of Clinical Electrocardiography (2^nd Ed.). BMJ Books, Massachusetts, USA.

[15]Hanna EB, Glancy DL, 2015. ST-segment elevation: differential diagnosis, caveats. Cleveland Clin J Med, 82(6):373-384.

[16]Hannun AY, Rajpurkar P, Haghpanahi M, et al., 2019. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 25(1):65-69.

[17]He KM, Zhang XY, Ren SQ, et al., 2016. Deep residual learning for image recognition. IEEE Conf on Computer Vision and Pattern Recognition, p.770-778.

[18]Hu ZT, Ma XZ, Liu ZZ, et al., 2016. Harnessing deep neural networks with logic rules. Proc 54^th Annual Meeting of the Association for Computational Linguistics, p.2410-2420.

[19]Ioffe S, Szegedy C, 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. Proc 32^nd Int Conf on Machine Learning, p.448-456.

[20]Jin LP, Dong J, 2017. Classification of normal and abnormal ECG records using lead convolutional neural network and rule inference. Sci China Inform Sci, 60(7):078103.

[21]Kimmig A, Bach SH, Broecheler M, et al., 2012. A short introduction to probabilistic soft logic. Proc 11th NIPS Workshop on Probabilistic Programming: Foundations and Applications, p.1-4.

[22]Kingma DP, Ba LJ, 2015. Adam: a method for stochastic optimization. Proc 3rd Int Conf on Learning Representations.

[23]Klir GJ, Yuan B, 1995. Fuzzy sets and fuzzy logic: theory and applications. Prentice Hall, New Jersey, USA.

[24]Liu FF, Liu CY, Zhao LN, et al., 2018. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J Med Imag Health Inform, 8(7):1368-1373.

[25]Liu WH, Zhang MX, Zhang YD, et al., 2018. Real-time multilead convolutional neural network for myocardial infarction detection. IEEE J Biomed Health Inform, 22(5):1434-1444.

[26]Luo CS, Jiang HX, Li QC, et al., 2019. Multi-label classification of abnormalities in 12-lead ECG using 1D CNN and LSTM. Proc 8^th Int Workshop on Machine Learning and Medical Engineering for Cardiovascular Healthcare, p.55-63.

[27]Mostayed A, Luo JY, Shu XL, et al., 2018. Classification of 12-lead ECG signals with bi-directional LSTM network. https://arxiv.org/abs/1811.02090

[28]National Center for Cardiovascular Diseases, 2019. Report on Cardiovascular Diseases in China 2018. Encyclopedia of China Publishing House, Beijing, China(in Chinese).

[29]O’Gara PT, Kushner FG, Ascheim DD, et al., 2013. ACCF/AHA guideline for the management of ST-elevation myocardial infarction: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. Circulation, 127(4):e362-e425.

[30]Pan JP, Tompkins WJ, 1985. A real-time QRS detection algorithm. IEEE Trans Biomed Eng, BME-32(3):230-236.

[31]Parvaneh S, Rubin J, Rahman A, et al., 2018. Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation. Physiol Meas, 39(8):084003.

[32]Sankaran PG, Sunoj SM, Nair NU, 2016. Kullback–Leibler divergence: a quantile approach. Stat Probab Lett, 111:72-79.

[33]Simonyan K, Zisserman A, 2015. Very deep convolutional networks for large-scale image recognition. Proc 3rd Int Conf on Learning Representations.

[34]Singh BN, Tiwari AK, 2006. Optimal selection of wavelet basis function applied to ECG signal denoising. Dig Signal Process, 16(3):275-287.

[35]Singstad BJ, Tronstad C, 2020. Convolutional neural network and rule-based algorithms for classifying 12-lead ECGs. Computing in Cardiology, p.1-4.

[36]Surawicz B, Knilans TK, 2008. Chou’s Electrocardiography in Clinical Practice: Adult and Pediatric (6^th Ed.). Saunders Elsevier, Philadelphia, USA.

[37]Wagner P, Strodthoff N, Bousseljot RD, et al., 2020. PTB-XL, a large publicly available electrocardiography dataset. Sci Data, 7(1):154.

[38]Yao QH, Wang RX, Fan XM, et al., 2020. Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network. Inform Fus, 53:174-182.

[39]Zhou FY, Jin LP, Dong J, 2017. Premature ventricular contraction detection combining deep neural networks and rules inference. Artif Intell Med, 79:42-51.