Artificial intelligence to detect abnormal heart rhythm from scanned electrocardiogram tracings. Issue 3 (29th March 2022)

• Record Type: Journal Article
• Authors: Bridge, Joshua; Fu, Lu; Lin, Weidong; Xue, Yumei; Lip, Gregory Y. H.; Zheng, Yalin
• Is Part Of: Journal of arrhythmia. Volume 38:Issue 3(2022)
• Page Start: 425
• Page End: 431
• Publication Date: 2022-03-29
• Subjects: deep learning -- ECG -- screening; Arrhythmia -- Periodicals; Cardiac pacing -- Periodicals; Arrhythmias, Cardiac; Arrhythmia; Cardiac pacing; Periodicals; Electronic journals; Periodicals; 616.128
• DOI: 10.1002/joa3.12707
• Languages: English
• ISSNs: 1880-4276

Abstract

Abstract: Background: Electrocardiogram (ECG) interpretation is an integral part of the clinical ECG workflow; however, this process is often time‐consuming and labor‐intensive. We aim to develop a rapid, inexpensive means to detect abnormal ECGs using artificial intelligence (AI) from scanned ECG printouts. Methods: The study included 1172 12‐lead ECG scans performed in 1172 individuals from a community in Guangzhou, China; 878 (74.9%) were diagnosed with sinus rhythm, and the remaining 294 (25.1%) with abnormal rhythms. A deep learning model consisting of a convolutional neural network based on InceptionV3 and a fully connected layer followed by a GEV activation was trained to classify scanned tracings as either normal or abnormal. Results: In a hold‐out testing set, the model achieved a area under curve (AUC), sensitivity, specificity, PPV, and NPV of 0.932 (95% confidence interval [CI]: 0.890, 0.976), 0.816 (95% CI: 0.657, 0.923), 0.993 (95% CI: 0.959, 1.0), 0.969 (95% CI: 0.838, 0.999), and 0.950 (95% CI: 0.90, 0.980) respectively, when using a probability threshold of 0.5. When compared with a physiological expert, these results show comparable performance with a statistically significant increase in specificity and a non‐significant decrease in sensitivity at the 95% level. Conclusions: We have developed a rapid, inexpensive, accurate means to detect abnormal ECGs using AI. Easy and accurate identification of such "abnormal" ECGs could allow the mass automated review of ECGs in community settings where abnormal ones could be flagged using AI for detailed clinical review by healthcare professionals. Abstract : We developed a deep learning algorithm that uses scanned ECG printouts to predict normal or abnormal rhythm. In addition, the method can produce saliency maps, showing which areas are relevant in the diagnosis to aid interpretability. The method has applications in low resource settings such as screening, where electrophysiological experts may not be available.