TY - GEN
T1 - Mina
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
AU - Hong, Shenda
AU - Xiao, Cao
AU - Ma, Tengfei
AU - Li, Hongyan
AU - Sun, Jimeng
N1 - Publisher Copyright:
© 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85074940435&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074940435&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/816
DO - 10.24963/ijcai.2019/816
M3 - Conference contribution
AN - SCOPUS:85074940435
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 5888
EP - 5894
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
Y2 - 10 August 2019 through 16 August 2019
ER -