Abstract
The electrocardiogram (ECG) is an important diagnostic tool for identifying cardiac problems. Nowadays, new ways to record ECG signals outside of the hospital are being investigated. A promising technique is capacitively coupled ECG (ccECG), which allows ECG signals to be recorded through insulating materials. However, as the ECG is no longer recorded in a controlled environment, this inevitably implies the presence of more artefacts. Artefact detection algorithms are used to detect and remove these. Typically, the training of a new algorithm requires a lot of ground truth data, which is costly to obtain. As many labelled contact ECG datasets exist, we could avoid the use of labelling new ccECG signals by making use of previous knowledge. Transfer learning can be used for this purpose. Here, we applied transfer learning to optimise the performance of an artefact detection model, trained on contact ECG, towards ccECG. We used ECG recordings from three different datasets, recorded with three recording devices. We showed that the accuracy of a contact-ECG classifier improved between 5 and 8% by means of transfer learning when tested on a ccECG dataset. Furthermore, we showed that only 20 segments of the ccECG dataset are sufficient to significantly increase the accuracy.
Highlights
We propose to use transfer learning to extend a model from contact ECG to other sensor modalities, like capacitively coupled ECG (ccECG), without the need of relabelling an entire new dataset
The primary goal of this study was to optimise the performance of a simple artefact detection model, that is trained on contact ECG, towards ccECG
The resulting Acc values seem to confirm this hypothesis, as they are remarkably lower, compared to the values of the original classifier. This is due to a substantial decrease in Sp, sa the Se values increased. These findings indicate that the clean ccECG segments are accurately detected, but that the noisy segments are not
Summary
A typical cardiac examination is taken in a hospital environment and lasts only 10 s. This is often sufficient to detect major pathology’s, yet this “snapshot” can be deceptive when used to evaluate one’s general condition [1]. During a cardiac examination in the hospital, the patient is asked to lay still in a supine position, and as a result, the recorded signals are generally of very high quality. This is no longer the case for ambulatory recordings. The diagnostic capabilities of the signals can be reduced by the
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
