Deep Learning for Cardiologist-Level Myocardial Infarction Detection in Electrocardiograms

Arjun Gupta, Eliu Huerta, Zhizhen Zhao, Issam Moussa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publication8th European Medical and Biological Engineering Conference - Proceedings of the EMBEC 2020
EditorsTomaz Jarm, Aleksandra Cvetkoska, Samo Mahnič-Kalamiza, Damijan Miklavcic
PublisherSpringer Science and Business Media Deutschland GmbH
Pages341-355
Number of pages15
ISBN (Print)9783030646097
DOIs
StatePublished - 2021
Event8th European Medical and Biological Engineering Conference, EMBEC 2020 - Portorož, Slovenia
Duration: Nov 29 2020Dec 3 2020

Publication series

NameIFMBE Proceedings
Volume80
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference8th European Medical and Biological Engineering Conference, EMBEC 2020
CountrySlovenia
CityPortorož
Period11/29/2012/3/20

Keywords

  • Biomedical engineering
  • Machine learning
  • Signal processing

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Deep Learning for Cardiologist-Level Myocardial Infarction Detection in Electrocardiograms'. Together they form a unique fingerprint.

Cite this