Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms
Background: There is increasing evidence that 12-lead electrocardiograms (ECG) can be used to predict biological age, which is associated with cardiovascular events. However, the utility of artificial intelligence (AI)-predicted age using ECGs remains unclear. Methods: Using a single-center database...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-02-01
|
| Series: | International Journal of Cardiology: Heart & Vasculature |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352906723000039 |
| _version_ | 1811172176677568512 |
|---|---|
| author | Naomi Hirota Shinya Suzuki Jun Motogi Hiroshi Nakai Wataru Matsuzawa Tsuneo Takayanagi Takuya Umemoto Akira Hyodo Keiichi Satoh Takuto Arita Naoharu Yagi Takayuki Otsuka Takeshi Yamashita |
| author_facet | Naomi Hirota Shinya Suzuki Jun Motogi Hiroshi Nakai Wataru Matsuzawa Tsuneo Takayanagi Takuya Umemoto Akira Hyodo Keiichi Satoh Takuto Arita Naoharu Yagi Takayuki Otsuka Takeshi Yamashita |
| author_sort | Naomi Hirota |
| collection | DOAJ |
| description | Background: There is increasing evidence that 12-lead electrocardiograms (ECG) can be used to predict biological age, which is associated with cardiovascular events. However, the utility of artificial intelligence (AI)-predicted age using ECGs remains unclear. Methods: Using a single-center database, we developed an AI-enabled ECG using 17 042 sinus rhythm ECGs (SR-ECG) to predict chronological age (CA) with a convolutional neural network that yields AI-predicted age. Using the 5-fold cross validation method, AI-predicted age deriving from the test dataset was yielded for all ECGs. The incidence by AgeDiff and the areas under the curve by receiver operating characteristic curve with AI-predicted age for cardiovascular events were analyzed. Results: During the mean follow-up period of 460.1 days, there were 543 cardiovascular events. The annualized incidence of cardiovascular events was 2.24 %, 2.44 %, and 3.01 %/year for patients with AgeDiff < −6, −6 to ≤6, and >6 years, respectively. The areas under the curve for cardiovascular events with CA and AI-predicted age, respectively, were 0.673 and 0.679 (Delong’s test, P = 0.388) for all patients; 0.642 and 0.700 (P = 0.003) for younger patients (CA < 60 years); and 0.584 and 0.570 (P = 0.268) for older patients (CA ≥ 60 years). Conclusions: AI-predicted age using 12-lead ECGs showed superiority in predicting cardiovascular events compared with CA in younger patients, but not in older patients. |
| first_indexed | 2024-04-10T17:25:32Z |
| format | Article |
| id | doaj.art-0b1ecc56b707419d9dba5a6e9025ea7e |
| institution | Directory Open Access Journal |
| issn | 2352-9067 |
| language | English |
| last_indexed | 2024-04-10T17:25:32Z |
| publishDate | 2023-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Cardiology: Heart & Vasculature |
| spelling | doaj.art-0b1ecc56b707419d9dba5a6e9025ea7e2023-02-04T04:18:05ZengElsevierInternational Journal of Cardiology: Heart & Vasculature2352-90672023-02-0144101172Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiogramsNaomi Hirota0Shinya Suzuki1Jun Motogi2Hiroshi Nakai3Wataru Matsuzawa4Tsuneo Takayanagi5Takuya Umemoto6Akira Hyodo7Keiichi Satoh8Takuto Arita9Naoharu Yagi10Takayuki Otsuka11Takeshi Yamashita12Department of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, Japan; Corresponding author at: The Cardiovascular Department of Cardiovascular MedicineInstitute, 3-2-19 Nishiazabu, Minato-Ku, Tokyo 106-0031, Japan.Department of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanInformation System Division, The Cardiovascular Institute, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanNihon Kohden Corporation, Tokyo, JapanDepartment of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, JapanDepartment of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, JapanDepartment of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, JapanDepartment of Cardiovascular Medicine, The Cardiovascular Institute, Tokyo, JapanBackground: There is increasing evidence that 12-lead electrocardiograms (ECG) can be used to predict biological age, which is associated with cardiovascular events. However, the utility of artificial intelligence (AI)-predicted age using ECGs remains unclear. Methods: Using a single-center database, we developed an AI-enabled ECG using 17 042 sinus rhythm ECGs (SR-ECG) to predict chronological age (CA) with a convolutional neural network that yields AI-predicted age. Using the 5-fold cross validation method, AI-predicted age deriving from the test dataset was yielded for all ECGs. The incidence by AgeDiff and the areas under the curve by receiver operating characteristic curve with AI-predicted age for cardiovascular events were analyzed. Results: During the mean follow-up period of 460.1 days, there were 543 cardiovascular events. The annualized incidence of cardiovascular events was 2.24 %, 2.44 %, and 3.01 %/year for patients with AgeDiff < −6, −6 to ≤6, and >6 years, respectively. The areas under the curve for cardiovascular events with CA and AI-predicted age, respectively, were 0.673 and 0.679 (Delong’s test, P = 0.388) for all patients; 0.642 and 0.700 (P = 0.003) for younger patients (CA < 60 years); and 0.584 and 0.570 (P = 0.268) for older patients (CA ≥ 60 years). Conclusions: AI-predicted age using 12-lead ECGs showed superiority in predicting cardiovascular events compared with CA in younger patients, but not in older patients.http://www.sciencedirect.com/science/article/pii/S2352906723000039ElectrocardiogramBiological ageCardiovascular eventArtificial intelligence |
| spellingShingle | Naomi Hirota Shinya Suzuki Jun Motogi Hiroshi Nakai Wataru Matsuzawa Tsuneo Takayanagi Takuya Umemoto Akira Hyodo Keiichi Satoh Takuto Arita Naoharu Yagi Takayuki Otsuka Takeshi Yamashita Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms International Journal of Cardiology: Heart & Vasculature Electrocardiogram Biological age Cardiovascular event Artificial intelligence |
| title | Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms |
| title_full | Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms |
| title_fullStr | Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms |
| title_full_unstemmed | Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms |
| title_short | Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms |
| title_sort | cardiovascular events and artificial intelligence predicted age using 12 lead electrocardiograms |
| topic | Electrocardiogram Biological age Cardiovascular event Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2352906723000039 |
| work_keys_str_mv | AT naomihirota cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT shinyasuzuki cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT junmotogi cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT hiroshinakai cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT watarumatsuzawa cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT tsuneotakayanagi cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT takuyaumemoto cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT akirahyodo cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT keiichisatoh cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT takutoarita cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT naoharuyagi cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT takayukiotsuka cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms AT takeshiyamashita cardiovasculareventsandartificialintelligencepredictedageusing12leadelectrocardiograms |