Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
The application of artificial intelligence (AI) for automated diagnosis of electrocardiograms (ECGs) can improve care in remote settings but is limited by the reliance on infrequently available signal-based data. We report the development of a multilabel automated diagnosis model for electrocardiographic images, more suitable for broader use. A total of 2,228,236 12-lead ECGs signals from 811 municipalities in Brazil are transformed to ECG images in varying lead conformations to train a convolutional neural network (CNN) identifying 6 physician-defined clinical labels spanning rhythm and conduction disorders, and a hidden label for gender. The image-based model performs well on a distinct test set validated by at least two cardiologists (average AUROC 0.99, AUPRC 0.86), an external validation set of 21,785 ECGs from Germany (average AUROC 0.97, AUPRC 0.73), and printed ECGs, with performance superior to signal-based models, and learning clinically relevant cues based on Grad-CAM. The model allows the application of AI to ECGs across broad settings.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8948243 | PMC |
| http://dx.doi.org/10.1038/s41467-022-29153-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Artificial Intelligence in Adult Congenital Heart Disease: Diagnostic and Therapeutic Applications and Future Directions.
Rev Cardiovasc Med
August 2025
Department of Cardiology, University Hospitals of Leicester NHS Trust, Glenfield Hospital, LE3 9QP Leicester, UK.
Adult congenital heart disease (ACHD) constitutes a heterogeneous and expanding patient cohort with distinctive diagnostic and management challenges. Conventional detection methods are ineffective at reflecting lesion heterogeneity and the variability in risk profiles. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL) models, has revolutionized the potential for improving diagnosis, risk stratification, and personalized care across the ACHD spectrum.
View Article and Find Full Text PDFEarly repolarization pattern with oral liquid nicotine.
BMC Cardiovasc Disord
September 2025
Department of Cardiology II (Electrophysiology), University Hospital Münster, Albert-Schweitzer-Campus 1, Münster, 48149, Germany.
While most sudden cardiac deaths are due to structural heart disease or cardiac ischemia, intoxications are rather rare and often unrecognized. Here we present a case of a 35-year-old patient who trickled cumulative 60 mg of the pure nicotine liquid. This led to cardiac arrest and ventricular fibrillation.
View Article and Find Full Text PDFRight Ventricle-Dominant Cardiac Sarcoidosis Diagnosed Using a Multimodal Approach.
JACC Case Rep
September 2025
Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan.
Background: Cardiac sarcoidosis (CS) usually affects the left ventricle and presents with nonspecific features like conduction abnormalities and ventricular arrhythmias. However, right ventricle (RV)-dominant involvement has been increasingly reported, making diagnosis difficult.
Case Summary: A 55-year-old man presented with palpitations.
Myocardial infarction with nonobstructive coronary arteries associated with blood transfusion in a young woman: A case report.
Medicine (Baltimore)
September 2025
Department of Cardiology, Jining Key Laboratory of Metabolic Cardiovascular Diseases, Institute of Cardiovascular Diseases of Jining Medical Research Academy, Jining No. 1 People's Hospital, Jining, Shandong, China.
Rationale: Myocardial infarction with nonobstructive coronary arteries (MINOCA) has diverse ischemic etiologies and has been defined by the absence of angiographically significant obstructive coronary artery disease. Blood transfusion has seldom been reported as a precipitating factor for MINOCA. Here, we present a rare case of transfusion-associated MINOCA in a young woman without underlying chronic conditions, aiming to raise clinical awareness of this uncommon yet important phenomenon and to explore its potential pathophysiological mechanisms.
View Article and Find Full Text PDFHigh-sensitivity troponin T as a rule-out marker for myocardial inflammation detectable by CMR imaging.
Open Heart
September 2025
Department of Cardiology, Angiology and Internal Intensive Care Medicine, RWTH Aachen University, Aachen, Germany.
Background: Acute myocarditis is a potentially life-threatening cardiac condition and immediate assessment of this disease is imminent. While laboratory tests, electrocardiography or transthoracic echocardiography can provide indirect signs for the presence of acute myocarditis, cardiac magnetic resonance (CMR) imaging enables direct visualisation of myocardial inflammation and confirms the diagnosis.Since there is limited accessibility to CMR, the goal of this study was to evaluate the sensitivity and specificity of an elevation of established biomarkers for the diagnosis of myocarditis and to define a specific rule-out threshold for deferring CMR.
View Article and Find Full Text PDF