Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram
Abstract Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhan...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01407-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544273986584576 |
|---|---|
| author | Albert J. Rogers Neal K. Bhatia Sabyasachi Bandyopadhyay James Tooley Rayan Ansari Vyom Thakkar Justin Xu Jessica Torres Soto Jagteshwar S. Tung Mahmood I. Alhusseini Paul Clopton Reza Sameni Gari D. Clifford J. Weston Hughes Euan A. Ashley Marco V. Perez Matei Zaharia Sanjiv M. Narayan |
| author_facet | Albert J. Rogers Neal K. Bhatia Sabyasachi Bandyopadhyay James Tooley Rayan Ansari Vyom Thakkar Justin Xu Jessica Torres Soto Jagteshwar S. Tung Mahmood I. Alhusseini Paul Clopton Reza Sameni Gari D. Clifford J. Weston Hughes Euan A. Ashley Marco V. Perez Matei Zaharia Sanjiv M. Narayan |
| author_sort | Albert J. Rogers |
| collection | DOAJ |
| description | Abstract Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhance WMA detection, referencing echocardiography as the gold standard. We collected ECG and echocardiogram data from 35,210 patients in California and labeled WMA using unstructured language parsing of echocardiographic reports. A deep neural network (ECG-WMA-Net) was trained and outperformed both expert ECG interpretation and Q-wave indices, achieving an AUROC of 0.781 (CI: 0.762–0.799). The model was externally validated in a diverse cohort from Georgia (n = 2338), with an AUC of 0.723 (CI: 0.685–0.757). Explainability analysis revealed significant contributions from QRS and T-wave regions. This deep learning approach improves WMA screening accuracy, potentially addressing physiological differences not captured by standard ECG-based methods. |
| format | Article |
| id | doaj-art-436621723e19411aa682cfe576df7333 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-436621723e19411aa682cfe576df73332025-01-12T12:41:00ZengNature Portfolionpj Digital Medicine2398-63522025-01-018111010.1038/s41746-024-01407-yIdentification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogramAlbert J. Rogers0Neal K. Bhatia1Sabyasachi Bandyopadhyay2James Tooley3Rayan Ansari4Vyom Thakkar5Justin Xu6Jessica Torres Soto7Jagteshwar S. Tung8Mahmood I. Alhusseini9Paul Clopton10Reza Sameni11Gari D. Clifford12J. Weston Hughes13Euan A. Ashley14Marco V. Perez15Matei Zaharia16Sanjiv M. Narayan17Department of Medicine, Stanford University School of MedicineDepartment of Medicine, Emory UniversityDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Computer Science, Stanford UniversityDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Biomedical Informatics, Emory UniversityDepartment of Biomedical Informatics, Emory UniversityDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Medicine, Stanford University School of MedicineDepartment of Computer Science, UC BerkeleyDepartment of Medicine, Stanford University School of MedicineAbstract Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhance WMA detection, referencing echocardiography as the gold standard. We collected ECG and echocardiogram data from 35,210 patients in California and labeled WMA using unstructured language parsing of echocardiographic reports. A deep neural network (ECG-WMA-Net) was trained and outperformed both expert ECG interpretation and Q-wave indices, achieving an AUROC of 0.781 (CI: 0.762–0.799). The model was externally validated in a diverse cohort from Georgia (n = 2338), with an AUC of 0.723 (CI: 0.685–0.757). Explainability analysis revealed significant contributions from QRS and T-wave regions. This deep learning approach improves WMA screening accuracy, potentially addressing physiological differences not captured by standard ECG-based methods.https://doi.org/10.1038/s41746-024-01407-y |
| spellingShingle | Albert J. Rogers Neal K. Bhatia Sabyasachi Bandyopadhyay James Tooley Rayan Ansari Vyom Thakkar Justin Xu Jessica Torres Soto Jagteshwar S. Tung Mahmood I. Alhusseini Paul Clopton Reza Sameni Gari D. Clifford J. Weston Hughes Euan A. Ashley Marco V. Perez Matei Zaharia Sanjiv M. Narayan Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram npj Digital Medicine |
| title | Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| title_full | Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| title_fullStr | Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| title_full_unstemmed | Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| title_short | Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| title_sort | identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram |
| url | https://doi.org/10.1038/s41746-024-01407-y |
| work_keys_str_mv | AT albertjrogers identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT nealkbhatia identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT sabyasachibandyopadhyay identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT jamestooley identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT rayanansari identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT vyomthakkar identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT justinxu identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT jessicatorressoto identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT jagteshwarstung identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT mahmoodialhusseini identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT paulclopton identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT rezasameni identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT garidclifford identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT jwestonhughes identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT euanaashley identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT marcovperez identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT mateizaharia identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram AT sanjivmnarayan identificationofcardiacwallmotionabnormalitiesindiversepopulationsbydeeplearningoftheelectrocardiogram |