A deep learning ECG model for identification and localization of occlusion myocardial infarction.

Stefan Gustafsson¹, Antônio H Ribeiro^2,3, Daniel Gedon^4,5, Petrus E O G B Abreu⁶, Nicolas Pielawski², Gabriela M M Paixão⁷, Marco Antonio Gutierrez⁸, José Eduardo Krieger⁸, Felipe Meneguitti Dias⁸, Antonio Luiz P Ribeiro⁷, Daniel Lindholm^1,9, Thomas B Schön², Johan Sundström^10,11

¹Department of Medical Sciences, Clinical Epidemiology Unit, Uppsala University, Uppsala, Sweden.

²Department of Information Technology, Division of Systems and Control, Uppsala University, Uppsala, Sweden.

³Science for life laboratory (SciLifeLab), Uppsala, Sweden.

⁴Machine Learning in Science, University of Tübingen, Tübingen, Germany.

⁵Tübingen AI Center, Tübingen, Germany.

⁶Postgraduate Program in Health Sciences: Infectious Diseases and Tropical Medicine, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

⁷Department of Internal Medicine, Faculdade de Medicina, and Telehealth Center and Cardiology Service, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.

⁸Heart Institute, University of São Paulo Medical School, São Paulo, Brazil.

⁹Department of Medicine, Norrtälje hospital (Tiohundra AB), Norrtälje, Sweden.

¹⁰Department of Medical Sciences, Clinical Epidemiology Unit, Uppsala University, Uppsala, Sweden. johan.sundstrom@uu.se.

¹¹The George Institute for Global Health, University of New South Wales, Sydney, NSW, Australia. johan.sundstrom@uu.se.

PubMed PMC DOI PDF

Abstract

Rapid identification and localization of an acute coronary occlusion are vital to prevent myocardial damage, yet reliance on ST-segment ECG criteria misses many acute occlusion myocardial infarctions (OMI) and triggers unnecessary acute angiographies. Here, we present a trained and validated deep learning model using 540,372 emergency ECGs paired with definitive catheterization outcomes. The model…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.