Why the study?
Because many clinically important ECG classes occur at low frequencies, approaches are needed to improve classifier performance on rare classes.
Does a multi-headed convolutional neural network improve classification performance (F1 score) of rare diagnoses in 12-lead ECGs?
Does a multi-headed convolutional neural network improve classification performance (F1 score) of rare diagnoses in 12-lead ECGs?
Multi-task learning significantly improves the performance of convolutional neural networks in classifying rare abnormalities on 12-lead ECGs by leveraging shared representations from common classes.
May improve rare ECG abnormality detection; leaves open prospective clinical validation before adoption.
We develop a multi-task convolutional neural network (CNN) to classify multiple diagnoses from 12-lead electrocardiograms (ECGs) using a dataset comprised of over 40,000 ECGs, with labels derived from cardiologist clinical interpretations. Since many clinically important classes can occur in low frequencies, approaches are needed to improve performance on rare classes. We compare the performance of several single-class classifiers on rare classes to a multi-headed classifier across all available classes. We demonstrate that the addition of common classes can significantly improve CNN performance on rarer classes when compared to a model trained on the rarer class in isolation. Using this method, we develop a model with high performance as measured by F1 score on multiple clinically relevant classes compared against the gold-standard cardiologist interpretation.
No takes yet. Share an insight, caveat, or question.
Hughes et al. (2018) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: