Key result
The AA-ECG model achieved better overall diagnostic performance than seven state-of-the-art classifiers in identifying 27 categories of cardiac abnormalities across 66,314 ECG images.
Why the study?
Current artificial intelligence-based electrocardiogram diagnostic algorithms suffer from a low rate of abnormality detection, especially in real-world clinical scenarios.
Does the AA-ECG model improve diagnostic accuracy for identifying cardiac abnormalities on raw ECG images compared to state-of-the-art classifiers?
Observational (n=55,787)
Yes
Does the AA-ECG model improve diagnostic accuracy for identifying cardiac abnormalities on raw ECG images compared to state-of-the-art classifiers?
The AA-ECG model demonstrates high diagnostic accuracy for detecting cardiac abnormalities directly from raw ECG images, offering a potentially efficient and interpretable AI tool for clinical diagnostic assistance.
BACKGROUND: The low rate of detection of abnormalities has been a major problem with current artificial intelligence-based electrocardiogram diagnostic algorithms, particularly when applied under real-world clinical scenarios. METHODS: We proposed an aggregation attention multilabel electrocardiogram classification model (AA-ECG) that can be applied directly to raw images to identify cardiac abnormalities using image-level annotation only. To develop and validate the model, we conducted a prospective two-site study to build two large-scale real-world datasets of 12-lead electrocardiogram images, annotated by clinical experts in a multilabeled manner. We compared the proposed model with seven state-of-the-art classifiers on both datasets in 27 main categories. RESULTS: In total, 47,733 electrocardiogram images from 37,442 consecutive patients were included in the development set, while 18,581 from 18,345 in the external set. The proposed model achieved better overall performance than the other seven models.The visualization of the attention maps provided an approach to build medical interpretability for machine intelligence. CONCLUSIONS: The proposed model had high diagnostic accuracy in identifying cardiac abnormalities on two real-world datasets. It has the potential to help clinicians provide more efficient cardiac care with fewer medical resources.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2023) conducted an observational in Arrhythmias and cardiac abnormalities (n=55,787). Aggregation attention multilabel electrocardiogram classification model (AA-ECG) vs. Seven state-of-the-art classifiers was evaluated on Overall performance in identifying cardiac abnormalities in 27 main categories. The AA-ECG model achieved better overall diagnostic performance than seven state-of-the-art classifiers in identifying 27 categories of cardiac abnormalities across 66,314 ECG images.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: