Xin Wang, Shaan Khurshid, Seung Hoan Choi, Samuel Friedman, Lu-Chen Weng, Christopher Reeder, James P Pirruccello, Pulkit Singh, Emily S Lau, Rachael Venn, Nate Diamant, Paolo Di Achille, Anthony Philippakis, Christopher D Anderson, Jennifer E Ho, Patrick T Ellinor, Puneet Batra, Steven A Lubitz
{"title":"Genetic Susceptibility to Atrial Fibrillation Identified via Deep Learning of 12-Lead Electrocardiograms.","authors":"Xin Wang, Shaan Khurshid, Seung Hoan Choi, Samuel Friedman, Lu-Chen Weng, Christopher Reeder, James P Pirruccello, Pulkit Singh, Emily S Lau, Rachael Venn, Nate Diamant, Paolo Di Achille, Anthony Philippakis, Christopher D Anderson, Jennifer E Ho, Patrick T Ellinor, Puneet Batra, Steven A Lubitz","doi":"10.1161/CIRCGEN.122.003808","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI) models applied to 12-lead ECG waveforms can predict atrial fibrillation (AF), a heritable and morbid arrhythmia. However, the factors forming the basis of risk predictions from AI models are usually not well understood. We hypothesized that there might be a genetic basis for an AI algorithm for predicting the 5-year risk of new-onset AF using 12-lead ECGs (ECG-AI)-based risk estimates.</p><p><strong>Methods: </strong>We applied a validated ECG-AI model for predicting incident AF to ECGs from 39 986 UK Biobank participants without AF. We then performed a genome-wide association study (GWAS) of the predicted AF risk and compared it with an AF GWAS and a GWAS of risk estimates from a clinical variable model.</p><p><strong>Results: </strong>In the ECG-AI GWAS, we identified 3 signals (<i>P</i><5×10<sup>-8</sup>) at established AF susceptibility loci marked by the sarcomeric gene <i>TTN</i> and sodium channel genes <i>SCN5A</i> and <i>SCN10A</i>. We also identified 2 novel loci near the genes <i>VGLL2</i> and <i>EXT1</i>. In contrast, the clinical variable model prediction GWAS indicated a different genetic profile. In genetic correlation analysis, the prediction from the ECG-AI model was estimated to have a higher correlation with AF than that from the clinical variable model.</p><p><strong>Conclusions: </strong>Predicted AF risk from an ECG-AI model is influenced by genetic variation implicating sarcomeric, ion channel and body height pathways. ECG-AI models may identify individuals at risk for disease via specific biological pathways.</p>","PeriodicalId":10326,"journal":{"name":"Circulation: Genomic and Precision Medicine","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10524395/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Circulation: Genomic and Precision Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1161/CIRCGEN.122.003808","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/6/6 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Artificial intelligence (AI) models applied to 12-lead ECG waveforms can predict atrial fibrillation (AF), a heritable and morbid arrhythmia. However, the factors forming the basis of risk predictions from AI models are usually not well understood. We hypothesized that there might be a genetic basis for an AI algorithm for predicting the 5-year risk of new-onset AF using 12-lead ECGs (ECG-AI)-based risk estimates.
Methods: We applied a validated ECG-AI model for predicting incident AF to ECGs from 39 986 UK Biobank participants without AF. We then performed a genome-wide association study (GWAS) of the predicted AF risk and compared it with an AF GWAS and a GWAS of risk estimates from a clinical variable model.
Results: In the ECG-AI GWAS, we identified 3 signals (P<5×10-8) at established AF susceptibility loci marked by the sarcomeric gene TTN and sodium channel genes SCN5A and SCN10A. We also identified 2 novel loci near the genes VGLL2 and EXT1. In contrast, the clinical variable model prediction GWAS indicated a different genetic profile. In genetic correlation analysis, the prediction from the ECG-AI model was estimated to have a higher correlation with AF than that from the clinical variable model.
Conclusions: Predicted AF risk from an ECG-AI model is influenced by genetic variation implicating sarcomeric, ion channel and body height pathways. ECG-AI models may identify individuals at risk for disease via specific biological pathways.
期刊介绍:
Circulation: Genomic and Precision Medicine is a distinguished journal dedicated to advancing the frontiers of cardiovascular genomics and precision medicine. It publishes a diverse array of original research articles that delve into the genetic and molecular underpinnings of cardiovascular diseases. The journal's scope is broad, encompassing studies from human subjects to laboratory models, and from in vitro experiments to computational simulations.
Circulation: Genomic and Precision Medicine is committed to publishing studies that have direct relevance to human cardiovascular biology and disease, with the ultimate goal of improving patient care and outcomes. The journal serves as a platform for researchers to share their groundbreaking work, fostering collaboration and innovation in the field of cardiovascular genomics and precision medicine.