Fully Automated Diagnosis of Acute Myocardial Infarction Using Electrocardiograms and Multimodal Deep Learning
JACC: Advances · 2025-08 · 4 (8) · 102011
DOI: 10.1016/j.jacadv.2025.102011 ↗Kurz gefasst
Fachartikel in der Zeitschrift JACC: Advances, 2025-08. Verfasst von Lukas Hilgendorf und 13 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medicine, Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Wallenberg C…. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Svenska Lakaresallskapet, Göteborgs Universitet Wallenbergcentrum för molekylär och translationell medicin, Västra Götalandsregionen.
Abstract (Originalsprache)
BACKGROUND: Rapid detection of acute myocardial infarction (AMI) reduces morbidity and mortality. Deep learning may enhance automated electrocardiogram (ECG) interpretation. OBJECTIVES: The purpose of the study was to develop and validate a deep learning model for AMI detection using ECG data, demographics, and symptoms. METHODS: This retrospective cohort study used ECG data from 2 centers in Västra Götaland County, Sweden (January 2015-June 2023), for model training and validation, with a third center for external testing. Patients with chest pain or dyspnea who received a prehospital or in-hospital ECG were included. A residual convolutional neural network was trained on ECG features, age, sex, and symptoms to predict AMI, defined by International Classification of Diseases codes at discharge. Performance was assessed using area under the receiver operating characteristic, sensitivity, and specificity. RESULTS: The study included 104,507 individuals (208,366 ECGs), with 8.17% in the training set and 8.59% in the external set diagnosed with AMI. The model achieved AUROCs of 0.8221 ± 0.0101 (internal validation ± 95% CI) and 0.8314 ± 0.0085 (external validation). Performance was consistent across sex but slightly lower for ambulance-arriving patients (area under the receiver operating characteristic: 0.8081 ± 0.0095). Saliency maps highlighted focus on ST segments and T waves. CONCLUSIONS: The deep learning model demonstrated strong AMI detection across diverse patient groups. A randomized trial is needed to compare its performance with emergency physicians.
Autor:innen und Institutionen
- Institute of Medicine, Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Wallenberg Centre for Molecular and Translational Research (WCMTM), Sahlgrenska Ac…
- Institute of Medicine, Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden.
- Institute of Medicine, Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
- Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
- Department of Emergency Medicine, Stanford University, Stanford, California, USA.
- Institute of Medicine, Department of Molecular and Clinical Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Department of Cardiology, Sahlgrenska University Hospital, Gothenburg, Sweden; Cen…
Förderung
- Svenska Lakaresallskapet
- Göteborgs Universitet Wallenbergcentrum för molekylär och translationell medicin
- Västra Götalandsregionen
Zitieren
APA
Hilgendorf, L., Petursson, P., Andersson, E., Rawshani, A., Bhatt, D. L., Råmunddal, T., Gupta, V., Skoglund, K., Omerovic, E., Sjöland, H., Taha, A., Kim, D., Lundgren, P., & Rawshani, A. (2025). Fully Automated Diagnosis of Acute Myocardial Infarction Using Electrocardiograms and Multimodal Deep Learning. JACC: Advances, 4(8), 102011. https://doi.org/10.1016/j.jacadv.2025.102011
Vancouver
Hilgendorf L, Petursson P, Andersson E, Rawshani A, Bhatt DL, Råmunddal T, et al. Fully Automated Diagnosis of Acute Myocardial Infarction Using Electrocardiograms and Multimodal Deep Learning. JACC: Advances. 2025;4(8):102011. doi:10.1016/j.jacadv.2025.102011
BibTeX
@article{Hilgendorf2025,
author = {Hilgendorf, Lukas and Petursson, Petur and Andersson, Erik and Rawshani, Aidin and Bhatt, Deepak L and Råmunddal, Truls and Gupta, Vibha and Skoglund, Kristofer and Omerovic, Elmir and Sjöland, Helen and Taha, Amar and Kim, David and Lundgren, Peter and Rawshani, Araz},
title = {Fully Automated Diagnosis of Acute Myocardial Infarction Using Electrocardiograms and Multimodal Deep Learning},
journal = {JACC: Advances},
year = {2025},
volume = {4},
number = {8},
pages = {102011},
doi = {10.1016/j.jacadv.2025.102011}
}
EUVIMED