2018/06/18 by Nils Strodthoff, Claas Strodthoff · 1 voice
Computer Science · Mathematics · Medicine · #Artificial neural network #Cardiac electrophysiology and arrhythmias #Clinical decision making #Convolutional neural network #Deep learning #ECG Monitoring and Analysis #Myocardial infarction #Pattern recognition (psychology) #cs.CY #cs.LG #stat.ML
paper · pdf · doi:10.1088/1361-6579/aaf34d
published as Physiological Measurement, vol. 40, no. 1, p. 015001, 2019 · 11 pages, 4 figures
arxiv published 2018/06/18 · openalex publication_date 2018/11/23 · openalex created_date 2018/11/29 · arxiv created 2019/02/05 · arxiv updated 2019/02/06 · openalex updated_date 2026/08/05
OBJECTIVE: We aim to provide an algorithm for the detection of myocardial infarction that operates directly on ECG data without any preprocessing and to investigate its decision criteria. APPROACH: We train an ensemble of fully convolutional neural networks on the PTB ECG dataset and apply state-of-the-art attribution methods. MAIN RESULTS: Our classifier reaches 93.3% sensitivity and 89.7% specificity evaluated using 10-fold cross-validation with sampling based on patients. The presented method outperforms state-of-the-art approaches and reaches the performance level of human cardiologists for detection of myocardial infarction. We are able to discriminate channel-specific regions that contribute most significantly to the neural network's decision. Interestingly, the network's decision is influenced by signs also recognized by human cardiologists as indicative of myocardial infarction. SIGNIFICANCE: Our results demonstrate the high prospects of algorithmic ECG analysis for future clinical applications considering both its quantitative performance as well as the possibility of assessing decision criteria on a per-example basis, which enhances the comprehensibility of the approach.