2019/12/31 by Arjun Gupta, E. A. Huerta, Eliu Huerta +2
Computer Science · Engineering · Mathematics · Medicine · Physics and Astronomy · #Artificial neural network #Cardiac electrophysiology and arrhythmias #Deep learning #ECG Monitoring and Analysis #Feature (linguistics) #Feature extraction #Myocardial infarction #Non-Invasive Vital Sign Monitoring #Pattern recognition (psychology) #acm:68Txx #acm:92C50 #acm:97R40 #cs.LG #eess.SP #msc:68Txx #msc:92C50 #msc:97R40 #physics.med-ph #stat.ML
paper · pdf · doi:10.1007/978-3-030-64610-3_40
Accepted to the European Medical and Biological Engineering Conference (EMBEC) 2020
openalex created_date 2019/09/26 · arxiv created 2020/09/21 · openalex publication_date 2020/11/29 · arxiv updated 2021/01/27 · openalex updated_date 2026/08/05
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 seconds 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.