Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
This work addresses the need for fast and accessible diagnosis of pulmonary embolism, a leading cause of out-of-hospital cardiac arrest, but it is incremental as it applies existing methods to optimize learning on small datasets.
The study tackled the problem of diagnosing pulmonary embolism using electrocardiograms by investigating neural networks and transfer learning from larger ECG datasets to a smaller PE dataset, resulting in improved learning efficiency and predictive performance on limited data.
Pulmonary embolism is a leading cause of out of hospital cardiac arrest that requires fast diagnosis. While computed tomography pulmonary angiography is the standard diagnostic tool, it is not always accessible. Electrocardiography is an essential tool for diagnosing multiple cardiac anomalies, as it is affordable, fast and available in many settings. However, the availability of public ECG datasets, specially for PE, is limited and, in practice, these datasets tend to be small, making it essential to optimize learning strategies. In this study, we investigate the performance of multiple neural networks in order to assess the impact of various approaches. Moreover, we check whether these practices enhance model generalization when transfer learning is used to translate information learned in larger ECG datasets, such as PTB-XL, CPSC18 and MedalCare-XL, to a smaller, more challenging dataset for PE. By leveraging transfer learning, we analyze the extent to which we can improve learning efficiency and predictive performance on limited data. Code available at https://github.com/joaodsmarques/Are-ECGs-enough-Deep-Learning-Classifiers .