{"type":"ScholarlyArticle","title":"MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals","authors":[{"name":"Shenda Hong","slug":"shenda-hong","given":"Shenda","family":"Hong","affiliation":"School of Electronics Engineering and Computer Science , Peking University , China; Key Laboratory of Machine Perception (Ministry of Education) , Peking University , China; Department of Computational Science and Engineering , Georgia Institute of Technology , USA"},{"name":"Cao Xiao","slug":"cao-xiao","given":"Cao","family":"Xiao","affiliation":"Analytics Center of Excellence , IQVIA , USA"},{"name":"Tengfei Ma","slug":"tengfei-ma","given":"Tengfei","family":"Ma","affiliation":"IBM Research , USA"},{"name":"Hongyan Li","slug":"hongyan-li","given":"Hongyan","family":"Li","affiliation":"School of Electronics Engineering and Computer Science , Peking University , China; Key Laboratory of Machine Perception (Ministry of Education) , Peking University , China"},{"name":"Jimeng Sun","slug":"jimeng-sun","given":"Jimeng","family":"Sun","affiliation":"Department of Computational Science and Engineering , Georgia Institute of Technology , USA"}],"abstract":"Electrocardiography (ECG) signals are commonly used to diagnose various cardiac abnormalities. Recently, deep learning models showed initial success on modeling ECG data, however they are mostly black-box, thus lack interpretability needed for clinical usage. In this work, we propose MultIlevel kNowledge-guided Attention networks (MINA) that predict heart diseases from ECG signals with intuitive explanation aligned with medical knowledge. By extracting multilevel (beat-, rhythm- and frequency-level) domain knowledge features separately, MINA combines the medical knowledge and ECG data via a multilevel attention model, making the learned models highly interpretable. Our experiments showed MINA achieved PR-AUC 0.9436 (outperforming the best baseline by 5.51%) in real world ECG dataset. Finally, MINA also demonstrated robust performance and strong interpretability against signal distortion and noise contamination.","doi":"10.24963/ijcai.2019/816","url":"https://ijcai.org/proceedings/2019/816","pdf":"https://ijcai.org/proceedings/2019/0816.pdf","markdown":"https://ijcai.org/proceedings/2019/816.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/816","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"AI for Improving Human Well-being","track":"AI for Improving Human Well-being","number":816,"pages":{"first":5888,"last":5894},"keywords":["Special Track on AI for Improving Human-Well Being: Health applications (Special Track on AI and Human Wellbeing)"],"videos":[],"references":[{"position":1,"raw":"[Benjamin et al., 2018] Emelia J Benjamin, Salim S Virani, Clifton W Callaway, Alanna M Chamberlain, Alexander R Chang, Susan Cheng, Stephanie E Chiuve, Mary Cushman, Francesca N Delling, Rajat Deo, et al. Heart Disease and Stroke Statistics 2018 Update: A Report from the American Heart Association. Circulation, 137(12):e67-e492, 2018.","title":"Heart Disease and Stroke Statistics 2018 Update: A Report from the American Heart Association","authors":"Emelia J Benjamin, Salim S Virani, Clifton W Callaway, Alanna M Chamberlain, Alexander R Chang, Susan Cheng, Stephanie E Chiuve, Mary Cushman, Francesca N Delling, Rajat Deo","year":"2018","venue":"Circulation","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Clifford et al., 2017] Gari D Clifford, Chengyu Liu, Ben- jamin Moody, Li-wei H Lehman, Ikaro Silva, Qiao Li, AE Johnson, and Roger G Mark. AF Classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge 2017. Computing in Cardiology, 44:1, 2017.","title":"AF Classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge","authors":"Chengyu Gari D Clifford, Benjamin Liu, Moody, Ikaro Li-Wei H Lehman, Qiao Silva, Li, Roger G Johnson, Mark","year":"2017","venue":"Computing in Cardiology","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Davis and Goadrich, 2006] Jesse Davis and Mark Goadrich. The Relationship Between Precision-Recall and ROC Curves. In ICML 2006, pages 233-240. ACM, 2006.","title":"The Relationship Between Precision-Recall and ROC Curves","authors":"Jesse Davis, Mark Goadrich","year":"2006","venue":"ICML 2006","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[EC57, 2012] Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms. Standard ANSI/AAMI EC57:2012, Association for the Ad- vancement of Medical Instrumentation, 2012.","title":"Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms","authors":null,"year":"2012","venue":"Standard ANSI/AAMI EC","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[García et al., 2016] Manuel García, Juan Ródenas, Raúl Al- caraz, and José J Rieta. Application of the Relative Wavelet Energy to Heart Rate Independent Detection of Atrial Fibril- lation. COMPUT METH PROG BIO, 131:157-168, 2016.","title":"Application of the Relative Wavelet Energy to Heart Rate Independent Detection of Atrial Fibrillation","authors":"Manuel García, Juan Ródenas, Raúl Alcaraz, José J Rieta","year":"2016","venue":"COMPUT METH PROG BIO","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hannun et al., 2019] Awni Y Hannun, Pranav Rajpurkar, Masoumeh Haghpanahi, Geoffrey H Tison, Codie Bourn, Mintu P Turakhia, and Andrew Y Ng. Cardiologist-level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms using a Deep Neural Network. Nature medicine, 25(1):65, 2019.","title":"Cardiologist-level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms using a Deep Neural Network","authors":"Pranav Awni Y Hannun, Masoumeh Rajpurkar, Geoffrey H Haghpanahi, Codie Tison, Bourn, P Mintu, Andrew Y Turakhia, Ng","year":"2019","venue":"Nature medicine","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hong et al., 2017] Shenda Hong, Meng Wu, Yuxi Zhou, Qingyun Wang, Junyuan Shang, Hongyan Li, and Junqing Xie. ENCASE: an ENsemble ClASsifiEr for ECG Classifi- cation Using Expert Features and Deep Neural Networks. Computing in Cardiology, 44:1, 2017.","title":"ENCASE: an ENsemble ClASsifiEr for ECG Classification Using Expert Features and Deep Neural Networks","authors":"Shenda Hong, Meng Wu, Yuxi Zhou, Qingyun Wang, Junyuan Shang, Hongyan Li, Junqing Xie","year":"2017","venue":"Computing in Cardiology","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hong et al., 2019] Shenda Hong, Yuxi Zhou, Meng Wu, Jun- yuan Shang, Qingyun Wang, Hongyan Li, and Junqing Xie. Combining deep neural networks and engineered fea- tures for cardiac arrhythmia detection from ECG recordings. Physiological Measurement, 40(5):054009, jun 2019.","title":"Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings","authors":"Shenda Hong, Yuxi Zhou, Meng Wu, Junyuan Shang, Qingyun Wang, Hongyan Li, Junqing Xie","year":"2019","venue":"Physiological Measurement","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2011] Chao Huang, Shuming Ye, Hang Chen, Dingli Li, Fangtian He, and Yuewen Tu. A Novel Method for Detection of the Transition Between Atrial Fibrillation and Sinus Rhythm. IEEE T BIO-MED ENG, 2011.","title":"A Novel Method for Detection of the Transition Between Atrial Fibrillation and Sinus Rhythm","authors":"Chao Huang, Shuming Ye, Hang Chen, Dingli Li, Fangtian He, Yuewen Tu","year":"2011","venue":"IEEE T BIO-MED ENG","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kashani and Barold, 2005] Amir Kashani and S Serge Barold. Significance of QRS Complex Duration in Patients with Heart Failure. J AM COLL CARDIOL, 2005.","title":"Significance of QRS Complex Duration in Patients with Heart Failure","authors":"Barold Kashani, Amir Kashani, Serge Barold","year":"2005","venue":"J AM COLL CARDIOL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2014] Diederik Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. arXiv:1412.6980, 2014.","title":"Adam: A Method for Stochastic Optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kiranyaz et al., 2016] Serkan Kiranyaz, Turker Ince, and Moncef Gabbouj. Real-Time Patient-Specific ECG Classi- fication by 1-D Convolutional Neural Networks. IEEE T BIO-MED ENG, 2016.","title":"Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks","authors":"Serkan Kiranyaz, Turker Ince, Moncef Gabbouj","year":"2016","venue":"IEEE T BIO-MED ENG","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ladavich and Ghoraani, 2015] Steven Ladavich and Behnaz Ghoraani. Rate-independent Detection of Atrial Fibrillation by Statistical Modeling of Atrial Activity. Biomedical Signal Processing and Control, 2015.","title":"Rate-independent Detection of Atrial Fibrillation by Statistical Modeling of Atrial Activity","authors":"Steven Ladavich, Behnaz Ghoraani","year":"2015","venue":"Biomedical Signal Processing and Control","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lake and Moorman, 2010] Douglas E Lake and J Randall Moorman. Accurate Estimation of Entropy in Very Short Physiological Time Series: the Problem of Atrial Fibril- lation Detection in Implanted Ventricular Devices. AM J PHYSIOL-HEART C, 300(1):H319-H325, 2010.","title":"Accurate Estimation of Entropy in Very Short Physiological Time Series: the Problem of Atrial Fibrillation Detection in Implanted Ventricular Devices","authors":"E Douglas, J Lake, Randall Moorman","year":"2010","venue":"AM J PHYSIOL-HEART C","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Linker, 2016] David T Linker. Accurate, Automated De- tection of Atrial Fibrillation in Ambulatory Recordings. CARDIOVASC ENG TECHN, 7(2):182-189, 2016. Oppenheim et al., 1996]","title":"Accurate, Automated Detection of Atrial Fibrillation in Ambulatory Recordings","authors":"T David, Linker","year":"1996","venue":"CARDIOVASC ENG TECHN","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"Alan V. Oppenheim, Alan S. Will- sky, and S. Hamid Nawab. Signals &Amp; Systems (2Nd Ed.). Prentice-Hall, Inc., 1996.","title":"Signals &Amp; Systems","authors":"Alan V Oppenheim, Alan S Willsky, S Hamid Nawab","year":"1996","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Oster and Clifford, 2015] Julien Oster and Gari D Clifford. Impact of the Presence of Noise on RR Interval-based Atrial Fibrillation Detection. J ELECTROCARDIOL, 2015.","title":"Impact of the Presence of Noise on RR Interval-based Atrial Fibrillation Detection","authors":"Julien Oster, D Gari, Clifford","year":"2015","venue":"J ELECTROCARDIOL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pan and Tompkins, 1985] Jiapu Pan and Willis J Tompkins. A Real-time QRS Detection Algorithm. IEEE T BIO-MED ENG, (3):230-236, 1985.","title":"Jiapu Pan and Willis J Tompkins. A Real-time QRS Detection Algorithm","authors":"Tompkins Pan","year":"1985","venue":"IEEE T BIO-MED ENG","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Park et al., 2009] Jinho Park, Sangwook Lee, and Moongu Jeon. Atrial Fibrillation Detection by Heart Rate Variability in Poincare Plot. Biomedical engineering, 8(1):38, 2009.","title":"Atrial Fibrillation Detection by Heart Rate Variability in Poincare Plot","authors":"Jinho Park, Sangwook Lee, Moongu Jeon","year":"2009","venue":"Biomedical engineering","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pürerfellner et al., 2014] Helmut Pürerfellner, Evgeny Pokushalov, Shantanu Sarkar, Jodi Koehler, Ren Zhou, Lubos Urban, and Gerhard Hindricks. P-wave Evidence as a Method for Improving Algorithm to Detect Atrial Fibrillation in Insertable Cardiac Monitors. Heart Rhythm, 2014.","title":"P-wave Evidence as a Method for Improving Algorithm to Detect Atrial Fibrillation in Insertable Cardiac Monitors","authors":"Helmut Pürerfellner, Evgeny Pokushalov, Shantanu Sarkar, Jodi Koehler, Ren Zhou, Lubos Urban, Gerhard Hindricks","year":"2014","venue":"Heart Rhythm","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rajpurkar et al., 2017] Pranav Rajpurkar, Awni Y. Hannun, Masoumeh Haghpanahi, Codie Bourn, and Andrew Y. Ng. Cardiologist-Level Arrhythmia Detection with Convolu- tional Neural Networks. ArXiv e-prints, July 2017.","title":"Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks","authors":"Pranav Rajpurkar, Y Awni, Masoumeh Hannun, Codie Haghpanahi, Andrew Y Bourn, Ng","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rodríguez et al., 2015] R. Rodríguez, A. Mexicano, J. Bila, S. Cervantes, and R. Ponce. Feature Extraction of Elec- trocardiogram Signals by Applying Adaptive Threshold and Principal Component Analysis. J Appl Res Technol, 13(2):261 -269, 2015.","title":"Feature Extraction of Electrocardiogram Signals by Applying Adaptive Threshold and Principal Component Analysis","authors":"R Rodríguez, A Mexicano, J Bila, S Cervantes, R Ponce","year":"2015","venue":"J Appl Res Technol","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Roopa and Harish, 2017] CK Roopa and BS Harish. A Sur- vey on Various Machine Learning Approaches for ECG Analysis. Int J of Computer Applications, 163(9), 2017.","title":"A Survey on Various Machine Learning Approaches for ECG Analysis","authors":"Harish ; Ck Roopa, Roopa, Harish","year":"2017","venue":"Int J of Computer Applications","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Schuster and Paliwal, 1997] Mike Schuster and Kuldip K Paliwal. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11):2673-2681, 1997.","title":"Bidirectional recurrent neural networks","authors":"Mike Schuster, Kuldip K Paliwal","year":"1997","venue":"IEEE Transactions on Signal Processing","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Schwab et al., 2017] Patrick Schwab, Gaetano Scebba, Jia Zhang, Marco Delai, and Walter Karlen. Beat by Beat: Classifying Cardiac Arrhythmias with Recurrent Neural Networks. Computing in Cardiology, 2017.","title":"Beat by Beat: Classifying Cardiac Arrhythmias with Recurrent Neural Networks","authors":"Patrick Schwab, Gaetano Scebba, Jia Zhang, Marco Delai, Walter Karlen","year":"2017","venue":"Computing in Cardiology","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tateno and Glass, 2001] K Tateno and L Glass. Automatic Detection of Atrial Fibrillation using the Coefficient of Variation and Density Histograms of RR and ∆RR Intervals. Med Biol Eng Comput, 39(6):664-671, 2001.","title":"Automatic Detection of Atrial Fibrillation using the Coefficient of Variation and Density Histograms of RR and ∆RR Intervals","authors":"K Tateno, L Glass","year":"2001","venue":"Med Biol Eng Comput","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tsai et al., 2003] Theodore L Tsai, Douglas B Fridsma, and Guido Gatti. Computer Decision Support as a Source of In- terpretation Error: the Case of Electrocardiograms. JAMIA, 10(5):478-483, 2003.","title":"Computer Decision Support as a Source of Interpretation Error: the Case of Electrocardiograms","authors":"Douglas B Theodore L Tsai, Guido Fridsma, Gatti","year":"2003","venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Turakhia, 2018] Mintu P. Turakhia. Moving From Big Data to Deep Learning-The Case of Atrial Fibrillation. JAMA Cardiology, 3(5):371-372, 2018.","title":"Moving From Big Data to Deep Learning-The Case of Atrial Fibrillation","authors":"P Mintu, Turakhia","year":"2018","venue":"JAMA Cardiology","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yanowitz, 2012] Frank G Yanowitz. Introduction to ECG Interpretation. LDS Hosp & Inter Med Center, 2012.","title":"Introduction to ECG Interpretation","authors":"G Frank, Yanowitz","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zihlmann et al., 2017] Martin Zihlmann, Dmytro Perekrestenko, and Michael Tschannen. Convolu- tional Recurrent Neural Networks for Electrocardiogram Classification. Computing in Cardiology, 2017.","title":"Convolutional Recurrent Neural Networks for Electrocardiogram Classification","authors":"Martin Zihlmann, Dmytro Perekrestenko, Michael Tschannen","year":"2017","venue":"Computing in Cardiology","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}