Myocardial scar and left ventricular ejection fraction classification for electrocardiography image using multi-task deep learning
3
item.page.dc.date.issued
2024-12-01
item.page.dc.type
item.page.dc.identifier.eissn
20452322
item.page.dc.identifier.doi
item.page.dc.identifier.scopus
2-s2.0-85189033624
item.page.oaire.citation.title
Scientific Reports
item.page.oaire.citation.volume
14
item.page.oaire.citation.issue
1
item.page.dc.rights.holder
SCOPUS
item.page.dc.identifier.citation
Scientific Reports Vol.14 No.1 (2024)
punsarn.item.page.citation
Boribalburephan A., Treewaree S., Tantisiriwat N., Yindeengam A., Achakulvisut T., Krittayaphong R. Myocardial scar and left ventricular ejection fraction classification for electrocardiography image using multi-task deep learning. Scientific Reports Vol.14 No.1 (2024). doi:10.1038/s41598-024-58131-6 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/97888
item.page.dc.title
Myocardial scar and left ventricular ejection fraction classification for electrocardiography image using multi-task deep learning
item.page.dc.contributor.author
item.page.oairecerif.author.affiliation
item.page.dc.contributor.correspondence
item.page.dc.contributor.other
item.page.dc.description.abstract
Myocardial scar (MS) and left ventricular ejection fraction (LVEF) are vital cardiovascular parameters, conventionally determined using cardiac magnetic resonance (CMR). However, given the high cost and limited availability of CMR in resource-constrained settings, electrocardiograms (ECGs) are a cost-effective alternative. We developed computer vision-based multi-task deep learning models to analyze 12-lead ECG 2D images, predicting MS and LVEF < 50%. Our dataset comprises 14,052 ECGs with clinical features, utilizing ground truth labels from CMR. Our top-performing model achieved AUC values of 0.838 (95% CI 0.812–0.862) for MS and 0.939 (95% CI 0.921–0.954) for LVEF < 50% classification, outperforming cardiologists. Moreover, MS predictions in a prevalence-specific test dataset recorded an AUC of 0.812 (95% CI 0.810–0.814). Extracted 1D signals from ECG images yielded inferior performance, compared to the 2D approach. In conclusion, our results demonstrate the potential of computer-based MS and LVEF < 50% classification from ECG scan images in clinical screening offering a cost-effective alternative to CMR.
