Abstract
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.
Highlights
Thorough validation is necessary before applying deep learning-based algorithm to healthcare data
Most research does not consider the data dependency, which can be problem when the algorithms are used in real environment. To quantity this data dependency, we experimentally investigated the data dependency of deep learning model of atrial fibrillation (AF) classification build with those open databases
The Long-Term Atrial Fibrillation database (LTAFDB) consist of 84 subjects with paroxysmal or sustained atrial fibrillation, which is two-channel ECG signal digitized at 128 Hz with 12-bit resolution over 20 mV range for about 24–25 h20
Summary
Thorough validation is necessary before applying deep learning-based algorithm to healthcare data. The validation using external data collected from various devices or institutions is important to evaluate the generalization performance of deep learning-based algorithm. Deep learning-based algorithm is generally validated by the internal database used for the development. In the medical imaging application included radiology, ophthalmology, and pathology diagnostic analysis, most deep learning-based algorithms did not employ the validation using external d atabase[19]. Deep learning model build with AF data collected from the different setting, such as sampling frequency, resolution, and acquisition environment, may suffer from data dependency. To quantity this data dependency, we experimentally investigated the data dependency of deep learning model of AF classification build with those open databases
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have