A knowledge-enhanced ECG foundation model trained on 160,000 patients achieved zero-shot diagnostic performance comparable to three experienced cardiologists for seven common clinical ECG types.
Does a knowledge-enhanced ECG diagnosis foundation model achieve comparable diagnostic performance to experienced cardiologists?
A novel knowledge-enhanced ECG foundation model demonstrates zero-shot diagnostic capabilities comparable to experienced cardiologists across diverse regions and unseen diseases.
We propose a knowledge-enhanced electrocardiogram (ECG) diagnosis foundation model (KED) that utilizes large language models to incorporate domain-specific knowledge of ECG signals. This model is trained on 800,000 ECGs from nearly 160,000 unique patients. Despite being trained on single-center data, KED demonstrates exceptional zero-shot diagnosis performance across various regions, including different locales in China, the United States, and other regions. This performance spans across all age groups for various conditions such as morphological abnormalities, rhythm abnormalities, conduction blocks, hypertrophy, myocardial ischemia, and infarction. Moreover, KED exhibits robust performance on diseases it has not encountered during its training. When compared to three experienced cardiologists on real clinical datasets, the model achieves comparable performance in zero-shot diagnosis of seven common clinical ECG types. We concentrate on the zero-shot diagnostic capability and the generalization performance of the proposed ECG foundation model, particularly in the context of external multi-center data and previously unseen disease.
Tian et al. (Sun,) conducted a other in ECG abnormalities (n=160,000). Knowledge-enhanced electrocardiogram (ECG) diagnosis foundation model (KED) vs. Three experienced cardiologists was evaluated on Zero-shot diagnosis performance of seven common clinical ECG types. A knowledge-enhanced ECG foundation model trained on 160,000 patients achieved zero-shot diagnostic performance comparable to three experienced cardiologists for seven common clinical ECG types.