Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation
Abstract Background Deep learning methods on standard, 12-lead electrocardiograms (ECG) have resulted in the ability to identify individuals at high-risk for the development of atrial fibrillation. However, the process remains a “black box” and does not help clinicians in understanding the electroca...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Communications Medicine |
| Online Access: | https://doi.org/10.1038/s43856-025-00749-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861681173823488 |
|---|---|
| author | Wei Yang Rajat Deo Wensheng Guo |
| author_facet | Wei Yang Rajat Deo Wensheng Guo |
| author_sort | Wei Yang |
| collection | DOAJ |
| description | Abstract Background Deep learning methods on standard, 12-lead electrocardiograms (ECG) have resulted in the ability to identify individuals at high-risk for the development of atrial fibrillation. However, the process remains a “black box” and does not help clinicians in understanding the electrocardiographic changes at an individual level. we propose a nonparametric feature extraction approach to identify features that are associated with the development of atrial fibrillation (AF). Methods We apply functional principal component analysis to the raw ECG tracings collected in the Chronic Renal Insufficiency Cohort (CRIC) study. We define and select the features using ECGs from participants enrolled in Phase I (2003–2008) of the study. Cox proportional hazards models are used to evaluate the association of selected ECG features and their changes with the incident risk of AF during study follow-up. The findings are then validated in ECGs from participants enrolled in Phase III (2013–2015). Results We identify four features that are related to the P-wave amplitude, QRS complex and ST segment. Both their initial measurement and 3-year changes are associated with the development of AF. In particular, one standard deviation in the 3-year decline of the P-wave amplitude is independently associated with a 29% increased risk of incident AF in the multivariable model (HR: 1.29, 95% CI: [1.16, 1.43]). Conclusions Compared with deep learning methods, our features are intuitive and can provide insights into the longitudinal ECG changes at an individual level that precede the development of AF. |
| format | Article |
| id | doaj-art-d786feb78da64804a057494b6ca4cf87 |
| institution | Kabale University |
| issn | 2730-664X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Medicine |
| spelling | doaj-art-d786feb78da64804a057494b6ca4cf872025-02-09T12:52:05ZengNature PortfolioCommunications Medicine2730-664X2025-02-01511810.1038/s43856-025-00749-2Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillationWei Yang0Rajat Deo1Wensheng Guo2Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine at the University of PennsylvaniaDivision of Cardiovascular Medicine, Electrophysiology Section, Perelman School of Medicine at the University of PennsylvaniaDepartment of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine at the University of PennsylvaniaAbstract Background Deep learning methods on standard, 12-lead electrocardiograms (ECG) have resulted in the ability to identify individuals at high-risk for the development of atrial fibrillation. However, the process remains a “black box” and does not help clinicians in understanding the electrocardiographic changes at an individual level. we propose a nonparametric feature extraction approach to identify features that are associated with the development of atrial fibrillation (AF). Methods We apply functional principal component analysis to the raw ECG tracings collected in the Chronic Renal Insufficiency Cohort (CRIC) study. We define and select the features using ECGs from participants enrolled in Phase I (2003–2008) of the study. Cox proportional hazards models are used to evaluate the association of selected ECG features and their changes with the incident risk of AF during study follow-up. The findings are then validated in ECGs from participants enrolled in Phase III (2013–2015). Results We identify four features that are related to the P-wave amplitude, QRS complex and ST segment. Both their initial measurement and 3-year changes are associated with the development of AF. In particular, one standard deviation in the 3-year decline of the P-wave amplitude is independently associated with a 29% increased risk of incident AF in the multivariable model (HR: 1.29, 95% CI: [1.16, 1.43]). Conclusions Compared with deep learning methods, our features are intuitive and can provide insights into the longitudinal ECG changes at an individual level that precede the development of AF.https://doi.org/10.1038/s43856-025-00749-2 |
| spellingShingle | Wei Yang Rajat Deo Wensheng Guo Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation Communications Medicine |
| title | Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation |
| title_full | Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation |
| title_fullStr | Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation |
| title_full_unstemmed | Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation |
| title_short | Functional feature extraction and validation from twelve-lead electrocardiograms to identify atrial fibrillation |
| title_sort | functional feature extraction and validation from twelve lead electrocardiograms to identify atrial fibrillation |
| url | https://doi.org/10.1038/s43856-025-00749-2 |
| work_keys_str_mv | AT weiyang functionalfeatureextractionandvalidationfromtwelveleadelectrocardiogramstoidentifyatrialfibrillation AT rajatdeo functionalfeatureextractionandvalidationfromtwelveleadelectrocardiogramstoidentifyatrialfibrillation AT wenshengguo functionalfeatureextractionandvalidationfromtwelveleadelectrocardiogramstoidentifyatrialfibrillation |