Artificial Intelligence–Derived Electrocardiographic Age Predicts Mortality in Adults With Congenital Heart Disease

JACC advances Pub Date : 2025-05-14 DOI:10.1016/j.jacadv.2025.101777

Scott Anjewierden MD , Donnchadh O'Sullivan MB, BCh, BAO , Kathryn E. Mangold PhD , Itzhak Zachi Attia PhD , Francisco Lopez-Jimenez MD , Paul A. Friedman MD , Alexander C. Egbe MBBS, MPH , Heidi M. Connolly MD , William R. Miranda MD , Samuel J. Asirvatham MD , Jennifer Dugan , Katia Bravo-Jaimes MD , Talha Niaz MBBS , Malini Madhavan MBBS , Luke J. Burchill MBBS, PhD

{"title":"Artificial Intelligence–Derived Electrocardiographic Age Predicts Mortality in Adults With Congenital Heart Disease","authors":"Scott Anjewierden MD , Donnchadh O'Sullivan MB, BCh, BAO , Kathryn E. Mangold PhD , Itzhak Zachi Attia PhD , Francisco Lopez-Jimenez MD , Paul A. Friedman MD , Alexander C. Egbe MBBS, MPH , Heidi M. Connolly MD , William R. Miranda MD , Samuel J. Asirvatham MD , Jennifer Dugan , Katia Bravo-Jaimes MD , Talha Niaz MBBS , Malini Madhavan MBBS , Luke J. Burchill MBBS, PhD","doi":"10.1016/j.jacadv.2025.101777","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Artificial intelligence (AI) can be used to estimate age from the electrocardiogram (AI-ECG age). The difference between AI-ECG age and chronological age (delta-age) is an independent predictor of mortality in the general population.</div></div><div><h3>Objectives</h3><div>The purpose of this study was to assess the relationship between delta-age and mortality among adults with congenital heart disease (ACHD).</div></div><div><h3>Methods</h3><div>A previously validated neural network was used to analyze standard digital 12-lead ECGs in a cohort of ACHD (age >18 years) between 1992 and 2023. A single ECG from each patient, collected during the first visit to the ACHD clinic, was analyzed to compute the delta-age. The relationship between the delta-age and mortality was evaluated using Cox proportional hazard models adjusting for influential clinical factors.</div></div><div><h3>Results</h3><div>Of 5,780 subjects tested (50% females), the mean chronological age was 39.1 ± 15.0 years. AI-ECG age was 52.3 ± 16.6 years. CHD complexity was classified as mild, moderate, and severe in 7.4%, 73.9%, and 18.7% of patients, respectively. Patients with severe CHD had the highest median delta-age of 15.8 (IQR: 3.5-31.2) years followed by moderate 11.5 (IQR: 3.5-21.3) years and simple 6.7 (IQR: 0.3-14.2) years. During a median follow-up of 6.4 years (IQR: 1.58-13.7 years), 839 (14.5%) patients died. After adjusting for chronologic age, CHD complexity, and other clinical variables, delta-age was associated with increased mortality risk (HR: 1.06 [1.03-1.09] per 5-year increment in delta-age, <em>P</em> < 0.05).</div></div><div><h3>Conclusions</h3><div>Delta-age, the difference between AI-ECG and chronological age, is an independent predictor of all-cause mortality in ACHD.</div></div>","PeriodicalId":73527,"journal":{"name":"JACC advances","volume":"4 6","pages":"Article 101777"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JACC advances","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772963X25001954","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Artificial intelligence (AI) can be used to estimate age from the electrocardiogram (AI-ECG age). The difference between AI-ECG age and chronological age (delta-age) is an independent predictor of mortality in the general population.

Objectives

The purpose of this study was to assess the relationship between delta-age and mortality among adults with congenital heart disease (ACHD).

Methods

A previously validated neural network was used to analyze standard digital 12-lead ECGs in a cohort of ACHD (age >18 years) between 1992 and 2023. A single ECG from each patient, collected during the first visit to the ACHD clinic, was analyzed to compute the delta-age. The relationship between the delta-age and mortality was evaluated using Cox proportional hazard models adjusting for influential clinical factors.

Results

Of 5,780 subjects tested (50% females), the mean chronological age was 39.1 ± 15.0 years. AI-ECG age was 52.3 ± 16.6 years. CHD complexity was classified as mild, moderate, and severe in 7.4%, 73.9%, and 18.7% of patients, respectively. Patients with severe CHD had the highest median delta-age of 15.8 (IQR: 3.5-31.2) years followed by moderate 11.5 (IQR: 3.5-21.3) years and simple 6.7 (IQR: 0.3-14.2) years. During a median follow-up of 6.4 years (IQR: 1.58-13.7 years), 839 (14.5%) patients died. After adjusting for chronologic age, CHD complexity, and other clinical variables, delta-age was associated with increased mortality risk (HR: 1.06 [1.03-1.09] per 5-year increment in delta-age, P < 0.05).

Conclusions

Delta-age, the difference between AI-ECG and chronological age, is an independent predictor of all-cause mortality in ACHD.

查看原文本刊更多论文

人工智能心电图年龄预测先天性心脏病成人死亡率

人工智能（AI）可用于从心电图（AI- ecg age）中估计年龄。AI-ECG年龄与实足年龄（delta-age）之间的差异是普通人群死亡率的独立预测因子。目的本研究的目的是评估成人先天性心脏病（ACHD）患者的delta年龄与死亡率之间的关系。方法采用先前验证的神经网络对1992 ~ 2023年一组18岁ACHD患者的标准数字12导联心电图进行分析。分析每位患者首次到ACHD诊所时收集的单次心电图，以计算delta-age。使用Cox比例风险模型对影响临床因素进行校正，评估delta年龄与死亡率之间的关系。结果5780名受试者（50%为女性）的平均实足年龄为39.1±15.0岁。AI-ECG年龄52.3±16.6岁。冠心病并发症分为轻度、中度和重度的患者分别为7.4%、73.9%和18.7%。重度冠心病患者的中位δ年龄最高，为15.8 （IQR: 3.5-31.2）岁，其次是中度11.5 （IQR: 3.5-21.3）岁和单纯6.7 （IQR: 0.3-14.2）岁。在中位随访6.4年（IQR: 1.58-13.7年）期间，839例（14.5%）患者死亡。在调整了实际年龄、冠心病复杂性和其他临床变量后，δ年龄与死亡风险增加相关（HR: 1.06 [1.03-1.09] / δ年龄每增加5年），P <；0.05)。结论delta -age （AI-ECG与实足年龄之间的差异）是ACHD全因死亡率的独立预测因子。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

JACC advances Cardiology and Cardiovascular Medicine

CiteScore

1.90

自引率

0.00%

发文量