TY - GEN
T1 - Deep Learning for Cardiologist-Level Myocardial Infarction Detection in Electrocardiograms
AU - Gupta, Arjun
AU - Huerta, Eliu
AU - Zhao, Zhizhen
AU - Moussa, Issam
N1 - Funding Information:
Acknowledgments. EAH and ZZ gratefully acknowledge National Science Foundation (NSF) awards OAC-1931561 and OAC-1934757. AG acknowledges support from the Fiddler Innovation Undergraduate Fellowship and the Students Pushing Innovation (SPIN) program at the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign.
Funding Information:
This work utilized resources supported by the NSF’s Major Research Instrumentation program, grant OAC-1725729, as well as the University of Illinois at Urbana-Champaign. We are grateful to NVIDIA for donating several Tesla P100 and V100 GPUs that we used for our analysis, and the NSF grants NSF-1550514, NSF-1659702 and TG-PHY160053. This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. We thank the NCSA Gravity Group for useful feedback.
Funding Information:
EAH and ZZ gratefully acknowledge National Science Foundation (NSF) awards OAC-1931561 and OAC-1934757. AG acknowledges support from the Fiddler Innovation Undergraduate Fellowship and the Students Pushing Innovation (SPIN) program at the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign. This work utilized resources supported by the NSF’s Major Research Instrumentation program, grant OAC-1725729, as well as the University of Illinois at Urbana-Champaign. We are grateful to NVIDIA for donating several Tesla P100 and V100 GPUs that we used for our analysis, and the NSF grants NSF-1550514, NSF-1659702 and TG-PHY160053. This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. We thank the NCSA Gravity Group for useful feedback.
Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - Myocardial infarction is the leading cause of death worldwide. In this paper, we design domain-inspired neural network models to detect myocardial infarction. First, we study the contribution of various leads. This systematic analysis, first of its kind in the literature, indicates that out of 15 ECG leads, data from the v6, vz, and ii leads are critical to correctly identify myocardial infarction. Second, we use this finding and adapt the ConvNetQuake neural network model—originally designed to identify earthquakes—to attain state-of-the-art classification results for myocardial infarction, achieving 99.43% classification accuracy on a record-wise split, and 97.83% classification accuracy on a patient-wise split. These two results represent cardiologist-level performance level for myocardial infarction detection after feeding only 10 s of raw ECG data into our model. Third, we show that our multi-ECG-channel neural network achieves cardiologist-level performance without the need of any kind of manual feature extraction or data pre-processing.
AB - Myocardial infarction is the leading cause of death worldwide. In this paper, we design domain-inspired neural network models to detect myocardial infarction. First, we study the contribution of various leads. This systematic analysis, first of its kind in the literature, indicates that out of 15 ECG leads, data from the v6, vz, and ii leads are critical to correctly identify myocardial infarction. Second, we use this finding and adapt the ConvNetQuake neural network model—originally designed to identify earthquakes—to attain state-of-the-art classification results for myocardial infarction, achieving 99.43% classification accuracy on a record-wise split, and 97.83% classification accuracy on a patient-wise split. These two results represent cardiologist-level performance level for myocardial infarction detection after feeding only 10 s of raw ECG data into our model. Third, we show that our multi-ECG-channel neural network achieves cardiologist-level performance without the need of any kind of manual feature extraction or data pre-processing.
KW - Biomedical engineering
KW - Machine learning
KW - Signal processing
UR - http://www.scopus.com/inward/record.url?scp=85097591377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097591377&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-64610-3_40
DO - 10.1007/978-3-030-64610-3_40
M3 - Conference contribution
AN - SCOPUS:85097591377
SN - 9783030646097
T3 - IFMBE Proceedings
SP - 341
EP - 355
BT - 8th European Medical and Biological Engineering Conference - Proceedings of the EMBEC 2020
A2 - Jarm, Tomaz
A2 - Cvetkoska, Aleksandra
A2 - Mahnič-Kalamiza, Samo
A2 - Miklavcic, Damijan
PB - Springer
T2 - 8th European Medical and Biological Engineering Conference, EMBEC 2020
Y2 - 29 November 2020 through 3 December 2020
ER -