Prediction of Atrial Fibrillation From the ECG in the Community Using Deep Learning: A Multinational Study.

IF 9.8 1区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS

Circulation. Arrhythmia and electrophysiology Pub Date : 2025-09-30 DOI:10.1161/CIRCEP.125.013734

Luisa C C Brant, Antônio H Ribeiro, Oseiwe B Eromosele, Marcelo M Pinto-Filho, Sandhi M Barreto, Bruce B Duncan, Martin G Larson, Emelia J Benjamin, Antonio L P Ribeiro, Honghuang Lin

{"title":"Prediction of Atrial Fibrillation From the ECG in the Community Using Deep Learning: A Multinational Study.","authors":"Luisa C C Brant, Antônio H Ribeiro, Oseiwe B Eromosele, Marcelo M Pinto-Filho, Sandhi M Barreto, Bruce B Duncan, Martin G Larson, Emelia J Benjamin, Antonio L P Ribeiro, Honghuang Lin","doi":"10.1161/CIRCEP.125.013734","DOIUrl":null,"url":null,"abstract":"Background: We aimed to refine and validate a deep neural network model from the ECG to predict atrial fibrillation (AF) risk, using samples from diverse backgrounds: the Framingham Heart Study (FHS), UK Biobank, and Estudo Longitudinal da Saúde do Adulto (ELSA-Brasil). We compared the model's performance to the clinical Cohorts for Heart and Aging Research in Genomic Epidemiology consortium (CHARGE-AF) risk score and evaluated the association with other cardiovascular outcomes.Methods: The ECG-derived deep-learning prediction of AF (ECG-AF) model was refined using 60% of FHS samples free of AF. Its performance was then tested in the remaining FHS samples, UK Biobank, and ELSA-Brasil, with discrimination assessed by the area under the receiver operating characteristic curve. The association of ECG-AF with cardiovascular outcomes was assessed using Cox proportional hazards models.Results: The study sample included 10 097 FHS participants (mean age 53±12 years; 54.9% women), 49 280 participants from the UK Biobank (mean age 64±8 years, 47.9% women), and 12 284 participants from ELSA-Brasil (mean age 53±8 years, 54.7% women). The ECG-AF model showed moderate discrimination for incident AF (area under the curve, 0.82 [95% CI, 0.80-0.84]) in the FHS, comparable to the CHARGE-AF score (area under the curve, 0.83 [95% CI, 0.81-0.85]), and incremental when combined (area under the curve, 0.85 [95% CI, 0.83-0.87]). In UK Biobank and ELSA-Brasil, combining ECG-AF and CHARGE also improved prediction. Higher ECG-AF scores were associated with increased risks of heart failure, myocardial infarction, stroke, and all-cause mortality in all 3 cohorts.Conclusions: In multinational cohort studies, the single-input ECG-AF deep neural network model demonstrated good performance in predicting AF and other cardiovascular outcomes, comparable to a multivariable clinical risk score, with improved performance when combined.","PeriodicalId":10319,"journal":{"name":"Circulation. Arrhythmia and electrophysiology","volume":" ","pages":"e013734"},"PeriodicalIF":9.8000,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Circulation. Arrhythmia and electrophysiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1161/CIRCEP.125.013734","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: We aimed to refine and validate a deep neural network model from the ECG to predict atrial fibrillation (AF) risk, using samples from diverse backgrounds: the Framingham Heart Study (FHS), UK Biobank, and Estudo Longitudinal da Saúde do Adulto (ELSA-Brasil). We compared the model's performance to the clinical Cohorts for Heart and Aging Research in Genomic Epidemiology consortium (CHARGE-AF) risk score and evaluated the association with other cardiovascular outcomes.

Methods: The ECG-derived deep-learning prediction of AF (ECG-AF) model was refined using 60% of FHS samples free of AF. Its performance was then tested in the remaining FHS samples, UK Biobank, and ELSA-Brasil, with discrimination assessed by the area under the receiver operating characteristic curve. The association of ECG-AF with cardiovascular outcomes was assessed using Cox proportional hazards models.

Results: The study sample included 10 097 FHS participants (mean age 53±12 years; 54.9% women), 49 280 participants from the UK Biobank (mean age 64±8 years, 47.9% women), and 12 284 participants from ELSA-Brasil (mean age 53±8 years, 54.7% women). The ECG-AF model showed moderate discrimination for incident AF (area under the curve, 0.82 [95% CI, 0.80-0.84]) in the FHS, comparable to the CHARGE-AF score (area under the curve, 0.83 [95% CI, 0.81-0.85]), and incremental when combined (area under the curve, 0.85 [95% CI, 0.83-0.87]). In UK Biobank and ELSA-Brasil, combining ECG-AF and CHARGE also improved prediction. Higher ECG-AF scores were associated with increased risks of heart failure, myocardial infarction, stroke, and all-cause mortality in all 3 cohorts.

Conclusions: In multinational cohort studies, the single-input ECG-AF deep neural network model demonstrated good performance in predicting AF and other cardiovascular outcomes, comparable to a multivariable clinical risk score, with improved performance when combined.

查看原文本刊更多论文

利用深度学习从社区心电图预测房颤：一项跨国研究。

背景：我们旨在完善和验证来自ECG的深度神经网络模型来预测房颤（AF）风险，使用来自不同背景的样本：弗雷明汉心脏研究（FHS），英国生物银行和Estudo Longitudinal da Saúde do Adulto （ELSA-Brasil）。我们将该模型的表现与基因组流行病学联盟（CHARGE-AF）心脏与衰老研究临床队列的风险评分进行了比较，并评估了与其他心血管结局的关联。方法：使用60%不含房颤的FHS样本对心电图衍生的房颤深度学习预测（ECG-AF）模型进行改进。然后在剩余的FHS样本、UK Biobank和ELSA-Brasil中测试其性能，并通过受试者工作特征曲线下面积评估其辨识度。使用Cox比例风险模型评估ECG-AF与心血管结局的关系。结果：研究样本包括10097名FHS参与者（平均年龄53±12岁，女性占54.9%），49280名来自英国生物银行的参与者（平均年龄64±8岁，女性占47.9%），以及12284名来自ELSA-Brasil的参与者（平均年龄53±8岁，女性占54.7%）。ECG-AF模型在FHS中对事件AF（曲线下面积，0.82 [95% CI, 0.80-0.84]）表现出中等程度的区分，与CHARGE-AF评分（曲线下面积，0.83 [95% CI, 0.81-0.85]）相当，在合并时表现出增加（曲线下面积，0.85 [95% CI, 0.83-0.87]）。在UK Biobank和ELSA-Brasil，结合ECG-AF和CHARGE也提高了预测。在所有3个队列中，较高的ECG-AF评分与心力衰竭、心肌梗死、中风和全因死亡率的风险增加相关。结论：在多国队列研究中，单输入ECG-AF深度神经网络模型在预测房颤和其他心血管结局方面表现良好，可与多变量临床风险评分相媲美，并在联合使用时表现更好。

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

Circulation. Arrhythmia and electrophysiology 医学-心血管系统

CiteScore

13.70

自引率

4.80%

发文量

187

审稿时长

4-8 weeks

期刊介绍： Circulation: Arrhythmia and Electrophysiology is a journal dedicated to the study and application of clinical cardiac electrophysiology. It covers a wide range of topics including the diagnosis and treatment of cardiac arrhythmias, as well as research in this field. The journal accepts various types of studies, including observational research, clinical trials, epidemiological studies, and advancements in translational research.