biostudies-literatureKwon OSNIEHS NIH HHSNational Research Foundation of Koreathe Ministry of Health &amp; Welfare, Republic of Koreae001898https://www.ebi.ac.uk/biostudies/studies/S-EPMC8796259biostudies-literatureUnknown9(1)<h4>Objective</h4>We previously reported early-onset atrial fibrillation (AF) associated genetic loci among a Korean population. We explored whether the AF-associated single-nucleotide polymorphisms (SNPs) selected from the Genome-Wide Association Study (GWAS) of an external large cohort has a prediction power for AF in Korean population through a convolutional neural network (CNN).<h4>Methods</h4>This study included 6358 subjects (872 cases, 5486 controls) from the Korean population GWAS data. We extracted the lists of SNPs at each p value threshold of the association statistics from three different previously reported ethnical-specific GWASs. The Korean GWAS data were divided into training (64%), validation (16%) and test (20%) sets, and a stratified K-fold cross-validation was performedOpen heartGenome-wide association study-based prediction of atrial fibrillation using artificial intelligence.PMC8796259HI21C0011NRF-2020R1A2B0100169527398C001127305C001127307C0011NRF-2019R1I1A1A01041440HI19C0114Hong MLee MHChoi EKLim HEPak HNOh SKwon OSYu HTShim JHwang IKim THJoung BKim YHUhm JSfalseGenome-wide association study-based prediction of atrial fibrillation using artificial intelligence.<h4>Objective</h4>We previously reported early-onset atrial fibrillation (AF) associated genetic loci among a Korean population. We explored whether the AF-associated single-nucleotide polymorphisms (SNPs) selected from the Genome-Wide Association Study (GWAS) of an external large cohort has a prediction power for AF in Korean population through a convolutional neural network (CNN).<h4>Methods</h4>This study included 6358 subjects (872 cases, 5486 controls) from the Korean population GWAS data. We extracted the lists of SNPs at each p value threshold of the association statistics from three different previously reported ethnical-specific GWASs. The Korean GWAS data were divided into training (64%), validation (16%) and test (20%) sets, and a stratified K-fold cross-validation was performed2022-01-01T00:00:00Z2022 Jan2026-06-07T07:30:13.121Z2025-04-04T07:52:06.318ZS-EPMC87962593508691810.1136/openhrt-2021-001898