{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["6(4)"],"submitter":["Hughes JW"],"funding":["Apple Inc","NHLBI","Bristol Myers Squibb","Johnson &amp; Johnson","QALY","Boston Scientific","Biotronik Inc","NIH"],"pubmed_abstract":["<h4>Aims</h4>Deep learning methods have shown impressive performance in detecting a range of diseases from electrocardiogram (ECG) waveforms, but the breadth of diseases that can be detected with high accuracy remains unknown, and in many cases the changes to the ECG allowing these classifications are also opaque. In this study, we aim to determine the full set of cardiac and non-cardiac conditions detectable from the ECG and to understand which ECG features contribute to the disease classification.<h4>Methods and results</h4>Using large datasets of ECGs and connected electronic health records from two separate medical centres, we independently trained PheWASNet, a multi-task deep learning model, to detect 1243 different disease phenotypes from the raw ECG waveform. We confirmed that the E"],"journal":["European heart journal. Digital health"],"pagination":["595-607"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12282379"],"repository":["biostudies-literature"],"pubmed_title":["A deep learning phenome wide association study of the electrocardiogram."],"pmcid":["PMC12282379"],"pubmed_authors":["Somani S","Ghazizadeh Z","Theurer J","Gomes B","Rogers AJ","Jain SS","Zou JY","Salerno M","Ouyang D","Kang G","Perez MV","Hughes JW","Ashley E","O'Sullivan JW","Vukadinovic M"],"additional_accession":[]},"is_claimable":false,"name":"A deep learning phenome wide association study of the electrocardiogram.","description":"<h4>Aims</h4>Deep learning methods have shown impressive performance in detecting a range of diseases from electrocardiogram (ECG) waveforms, but the breadth of diseases that can be detected with high accuracy remains unknown, and in many cases the changes to the ECG allowing these classifications are also opaque. In this study, we aim to determine the full set of cardiac and non-cardiac conditions detectable from the ECG and to understand which ECG features contribute to the disease classification.<h4>Methods and results</h4>Using large datasets of ECGs and connected electronic health records from two separate medical centres, we independently trained PheWASNet, a multi-task deep learning model, to detect 1243 different disease phenotypes from the raw ECG waveform. We confirmed that the E","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Jul","modification":"2025-08-23T03:08:58.912Z","creation":"2025-08-23T03:08:58.912Z"},"accession":"S-EPMC12282379","cross_references":{"pubmed":["40703109"],"doi":["10.1093/ehjdh/ztaf047"]}}