Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes
BackgroundThere is a paucity of data on artificial intelligence-estimated biological electrocardiography (ECG) heart age (AI ECG-heart age) for predicting cardiovascular outcomes, distinct from the chronological age (CA). We developed a deep learning-based algorithm to estimate the AI ECG-heart age...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1137892/full |
| _version_ | 1811153987276111872 |
|---|---|
| author | Yong-Soo Baek Yong-Soo Baek Yong-Soo Baek Dong-Ho Lee Yoonsu Jo Sang-Chul Lee Sang-Chul Lee Wonik Choi Wonik Choi Dae-Hyeok Kim Dae-Hyeok Kim |
| author_facet | Yong-Soo Baek Yong-Soo Baek Yong-Soo Baek Dong-Ho Lee Yoonsu Jo Sang-Chul Lee Sang-Chul Lee Wonik Choi Wonik Choi Dae-Hyeok Kim Dae-Hyeok Kim |
| author_sort | Yong-Soo Baek |
| collection | DOAJ |
| description | BackgroundThere is a paucity of data on artificial intelligence-estimated biological electrocardiography (ECG) heart age (AI ECG-heart age) for predicting cardiovascular outcomes, distinct from the chronological age (CA). We developed a deep learning-based algorithm to estimate the AI ECG-heart age using standard 12-lead ECGs and evaluated whether it predicted mortality and cardiovascular outcomes.MethodsWe trained and validated a deep neural network using the raw ECG digital data from 425,051 12-lead ECGs acquired between January 2006 and December 2021. The network performed a holdout test using a separate set of 97,058 ECGs. The deep neural network was trained to estimate the AI ECG-heart age [mean absolute error, 5.8 ± 3.9 years; R-squared, 0.7 (r = 0.84, p < 0.05)].FindingsIn the Cox proportional hazards models, after adjusting for relevant comorbidity factors, the patients with an AI ECG-heart age of 6 years older than the CA had higher all-cause mortality (hazard ratio (HR) 1.60 [1.42–1.79]) and more major adverse cardiovascular events (MACEs) [HR: 1.91 (1.66–2.21)], whereas those under 6 years had an inverse relationship (HR: 0.82 [0.75–0.91] for all-cause mortality; HR: 0.78 [0.68–0.89] for MACEs). Additionally, the analysis of ECG features showed notable alterations in the PR interval, QRS duration, QT interval and corrected QT Interval (QTc) as the AI ECG-heart age increased.ConclusionBiological heart age estimated by AI had a significant impact on mortality and MACEs, suggesting that the AI ECG-heart age facilitates primary prevention and health care for cardiovascular outcomes. |
| first_indexed | 2024-04-09T18:15:05Z |
| format | Article |
| id | doaj.art-ec40860bdb6648feba47918c2aba9b83 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-04-09T18:15:05Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-ec40860bdb6648feba47918c2aba9b832023-04-13T05:32:42ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-04-011010.3389/fcvm.2023.11378921137892Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomesYong-Soo Baek0Yong-Soo Baek1Yong-Soo Baek2Dong-Ho Lee3Yoonsu Jo4Sang-Chul Lee5Sang-Chul Lee6Wonik Choi7Wonik Choi8Dae-Hyeok Kim9Dae-Hyeok Kim10Division of Cardiology, Department of Internal Medicine, Inha University College of Medicine and Inha University Hospital, Incheon, South KoreaDeepCardio Inc., Incheon, South KoreaSchool of Computer Science, University of Birmingham, Birmingham, United KingdomDeepCardio Inc., Incheon, South KoreaDeepCardio Inc., Incheon, South KoreaDeepCardio Inc., Incheon, South KoreaDepartment of Computer Engineering, Inha University, Incheon, South KoreaDeepCardio Inc., Incheon, South KoreaDepartment of Information and Communication Engineering, Inha University, Incheon, South KoreaDivision of Cardiology, Department of Internal Medicine, Inha University College of Medicine and Inha University Hospital, Incheon, South KoreaDeepCardio Inc., Incheon, South KoreaBackgroundThere is a paucity of data on artificial intelligence-estimated biological electrocardiography (ECG) heart age (AI ECG-heart age) for predicting cardiovascular outcomes, distinct from the chronological age (CA). We developed a deep learning-based algorithm to estimate the AI ECG-heart age using standard 12-lead ECGs and evaluated whether it predicted mortality and cardiovascular outcomes.MethodsWe trained and validated a deep neural network using the raw ECG digital data from 425,051 12-lead ECGs acquired between January 2006 and December 2021. The network performed a holdout test using a separate set of 97,058 ECGs. The deep neural network was trained to estimate the AI ECG-heart age [mean absolute error, 5.8 ± 3.9 years; R-squared, 0.7 (r = 0.84, p < 0.05)].FindingsIn the Cox proportional hazards models, after adjusting for relevant comorbidity factors, the patients with an AI ECG-heart age of 6 years older than the CA had higher all-cause mortality (hazard ratio (HR) 1.60 [1.42–1.79]) and more major adverse cardiovascular events (MACEs) [HR: 1.91 (1.66–2.21)], whereas those under 6 years had an inverse relationship (HR: 0.82 [0.75–0.91] for all-cause mortality; HR: 0.78 [0.68–0.89] for MACEs). Additionally, the analysis of ECG features showed notable alterations in the PR interval, QRS duration, QT interval and corrected QT Interval (QTc) as the AI ECG-heart age increased.ConclusionBiological heart age estimated by AI had a significant impact on mortality and MACEs, suggesting that the AI ECG-heart age facilitates primary prevention and health care for cardiovascular outcomes.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1137892/fullECG ageheart agebiological ageingartificial intelligencemortalityhospitalization |
| spellingShingle | Yong-Soo Baek Yong-Soo Baek Yong-Soo Baek Dong-Ho Lee Yoonsu Jo Sang-Chul Lee Sang-Chul Lee Wonik Choi Wonik Choi Dae-Hyeok Kim Dae-Hyeok Kim Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes Frontiers in Cardiovascular Medicine ECG age heart age biological ageing artificial intelligence mortality hospitalization |
| title | Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes |
| title_full | Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes |
| title_fullStr | Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes |
| title_full_unstemmed | Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes |
| title_short | Artificial intelligence-estimated biological heart age using a 12-lead electrocardiogram predicts mortality and cardiovascular outcomes |
| title_sort | artificial intelligence estimated biological heart age using a 12 lead electrocardiogram predicts mortality and cardiovascular outcomes |
| topic | ECG age heart age biological ageing artificial intelligence mortality hospitalization |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1137892/full |
| work_keys_str_mv | AT yongsoobaek artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT yongsoobaek artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT yongsoobaek artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT dongholee artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT yoonsujo artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT sangchullee artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT sangchullee artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT wonikchoi artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT wonikchoi artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT daehyeokkim artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes AT daehyeokkim artificialintelligenceestimatedbiologicalheartageusinga12leadelectrocardiogrampredictsmortalityandcardiovascularoutcomes |