Resnet-based atrial fibrillation detection models achieved 98-99% accuracy on internal datasets but dropped to 53-92% on external datasets, demonstrating significant data dependency.
Does the use of residual neural networks for AF detection show data dependency when evaluated on external datasets?
Deep learning models for AF detection exhibit significant data dependency, performing worse on external datasets, though this effect is mitigated by larger training datasets.
Atrial fibrillation (AF) is an arrhythmia that can cause blood clot and may lead to stroke and heart failure. To detect AF, deep learning-based detection algorithms have recently been developed. However, deep learning models were often trained with limited datasets and were evaluated within the same datasets, which makes their performance generally drops on the external datasets, known as data dependency. For this study, three different databases from PhysioNet were used to investigate the data dependency of deep learning-based AF detection algorithm using the residual neural network (Resnet). Resnet 18, 34, 50 and 152 model were trained with raw electrocardiogram (ECG) signal extracted from independent database. The highest accuracy was about 98-99% which is evaluation results of test dataset from the own database. On the other hand, the lowest accuracy was about 53-92% which was evaluation results of the external dataset extracted from different source. There are data dependency according to the train dataset and the test dataset. However, the data dependency decreased as a large amount of train data.
Seo et al. (Tue,) conducted a other in Atrial fibrillation (n=155). Resnet deep learning models vs. External datasets was evaluated on Accuracy of AF detection. Resnet-based atrial fibrillation detection models achieved 98-99% accuracy on internal datasets but dropped to 53-92% on external datasets, demonstrating significant data dependency.