Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study
Abstract Aging affects the 12-lead electrocardiogram (ECG) and correlates with cardiovascular disease (CVD). AI-ECG models estimate aging effects as a novel biomarker but have only been evaluated on single ECGs—without utilizing longitudinal data. We validated an AI-ECG model, originally trained on...
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/s41746-024-01428-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594410585456640 |
|---|---|
| author | Philip Hempel Antônio H. Ribeiro Marcus Vollmer Theresa Bender Marcus Dörr Dagmar Krefting Nicolai Spicher |
| author_facet | Philip Hempel Antônio H. Ribeiro Marcus Vollmer Theresa Bender Marcus Dörr Dagmar Krefting Nicolai Spicher |
| author_sort | Philip Hempel |
| collection | DOAJ |
| description | Abstract Aging affects the 12-lead electrocardiogram (ECG) and correlates with cardiovascular disease (CVD). AI-ECG models estimate aging effects as a novel biomarker but have only been evaluated on single ECGs—without utilizing longitudinal data. We validated an AI-ECG model, originally trained on Brazilian data, using a German cohort with over 20 years of follow-up, demonstrating similar performance (r 2 = 0.70) to the original study (0.71). Incorporating longitudinal ECGs revealed a stronger association with cardiovascular risk, increasing the hazard ratio for mortality from 1.43 to 1.65. Moreover, aging effects were associated with higher odds ratios for atrial fibrillation, heart failure, and mortality. Using explainable AI methods revealed that the model aligns with clinical knowledge by focusing on ECG features known to reflect aging. Our study suggests that aging effects in longitudinal ECGs can be applied on population level as a novel biomarker to identify patients at risk early. |
| format | Article |
| id | doaj-art-65c852330ad246c891457801a4e26f4b |
| 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-65c852330ad246c891457801a4e26f4b2025-01-19T12:39:45ZengNature Portfolionpj Digital Medicine2398-63522025-01-018111110.1038/s41746-024-01428-7Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population studyPhilip Hempel0Antônio H. Ribeiro1Marcus Vollmer2Theresa Bender3Marcus Dörr4Dagmar Krefting5Nicolai Spicher6Department of Medical Informatics, University Medical Center GöttingenDepartment of Information Technology, Uppsala UniversityInstitute of Bioinformatics, University Medicine GreifswaldDepartment of Medical Informatics, University Medical Center GöttingenGerman Centre for Cardiovascular Research (DZHK), Partner Site GreifswaldDepartment of Medical Informatics, University Medical Center GöttingenDepartment of Medical Informatics, University Medical Center GöttingenAbstract Aging affects the 12-lead electrocardiogram (ECG) and correlates with cardiovascular disease (CVD). AI-ECG models estimate aging effects as a novel biomarker but have only been evaluated on single ECGs—without utilizing longitudinal data. We validated an AI-ECG model, originally trained on Brazilian data, using a German cohort with over 20 years of follow-up, demonstrating similar performance (r 2 = 0.70) to the original study (0.71). Incorporating longitudinal ECGs revealed a stronger association with cardiovascular risk, increasing the hazard ratio for mortality from 1.43 to 1.65. Moreover, aging effects were associated with higher odds ratios for atrial fibrillation, heart failure, and mortality. Using explainable AI methods revealed that the model aligns with clinical knowledge by focusing on ECG features known to reflect aging. Our study suggests that aging effects in longitudinal ECGs can be applied on population level as a novel biomarker to identify patients at risk early.https://doi.org/10.1038/s41746-024-01428-7 |
| spellingShingle | Philip Hempel Antônio H. Ribeiro Marcus Vollmer Theresa Bender Marcus Dörr Dagmar Krefting Nicolai Spicher Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study npj Digital Medicine |
| title | Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study |
| title_full | Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study |
| title_fullStr | Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study |
| title_full_unstemmed | Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study |
| title_short | Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study |
| title_sort | explainable ai associates ecg aging effects with increased cardiovascular risk in a longitudinal population study |
| url | https://doi.org/10.1038/s41746-024-01428-7 |
| work_keys_str_mv | AT philiphempel explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT antoniohribeiro explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT marcusvollmer explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT theresabender explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT marcusdorr explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT dagmarkrefting explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy AT nicolaispicher explainableaiassociatesecgagingeffectswithincreasedcardiovascularriskinalongitudinalpopulationstudy |