{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Brant LCC"],"funding":["NIA NIH HHS","NHLBI NIH HHS","NIH HHS"],"pagination":["e013734"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12569998"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["18(10)"],"pubmed_abstract":["<h4>Background</h4>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.<h4>Methods</h4>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. "],"journal":["Circulation. Arrhythmia and electrophysiology"],"pubmed_title":["Prediction of Atrial Fibrillation From the ECG in the Community Using Deep Learning: A Multinational Study."],"pmcid":["PMC12569998"],"funding_grant_id":["R01 AG028321","R01 AG083735","HHSN268201500001C","75N92023D00012","R01 HL092577","R21 HL175584","75N98025D00012","N01 HC025195","U01 AG068221","R01 AG066010","75N92019D00031","HHSN268201500001I","U54 HL120163"],"pubmed_authors":["Duncan BB","Larson MG","Barreto SM","Pinto-Filho MM","Eromosele OB","Lin H","Brant LCC","Ribeiro AH","Ribeiro ALP","Benjamin EJ"],"additional_accession":[]},"is_claimable":false,"name":"Prediction of Atrial Fibrillation From the ECG in the Community Using Deep Learning: A Multinational Study.","description":"<h4>Background</h4>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.<h4>Methods</h4>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. ","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Oct","modification":"2026-06-10T05:19:06.396Z","creation":"2026-06-10T03:07:44.846Z"},"accession":"S-EPMC12569998","cross_references":{"pubmed":["41025252"],"doi":["10.1161/CIRCEP.125.013734","10.1161/circep.125.013734"]}}