An accurate and efficient method to train classifiers for atrial fibrillation detection in ECGs

An accurate and efficient method to train classifiers for atrial fibrillation detection in ECGs: Learning by asking better questions

Wesselius, F.J. (Erasmus MC)
van Schie, M.S. (Erasmus MC)
de Groot, N.M.S. (TU Delft Signal Processing Systems; Erasmus MC)
Hendriks, R.C. (TU Delft Signal Processing Systems)

2022

Background: An increasing number of wearables are capable of measuring electrocardiograms (ECGs), which may help in early detection of atrial fibrillation (AF). Therefore, many studies focus on automated detection of AF in ECGs. A major obstacle is the required amount of manually labelled data. This study aimed to provide an efficient and reliable method to train a classifier for AF detection using large datasets of real-life ECGs. Method: Human-controlled semi-supervised learning was applied, consisting of two phases: the pre-training phase and the semi-automated training phase. During pre-training, an initial classifier was trained, which was used to predict the classes of new ECG segments in the semi-automated training phase. Based on the degree of certainty, segments were added to the training dataset automatically or after human validation. Thereafter, the classifier was retrained and this procedure was repeated. To test the model performance, a real-life telemetry dataset containing 3,846,564 30-s ECG segments of hospitalized patients (n = 476) and the CinC Challenge 2017 database were used. Results: After pre-training, the average F1-score on a hidden testing dataset was 89.0%. Furthermore, after the pre-training phase 68.0% of all segments in the hidden test set could be classified with an estimated probability of successful classification of 99%, providing an F1-score of 97.9% for these segments. During the semi-automated training phase, this F1-score showed little variation (97.3%–97.9% in the hidden test set), whilst the number of segments which could be automatically classified increased from 68.0% to 75.8% due to the enhanced training dataset. At the same time, the overall F1-score increased from 89.0% to 91.4%. Conclusions: Human-validated semi-supervised learning makes training a classifier more time efficient without compromising on accuracy, hence this method might be valuable in the automated detection of AF in real-life ECGs.

Algorithms
Atrial fibrillation
Classification
ECG signal Processing
Machine learning
Telemetry

http://resolver.tudelft.nl/uuid:660dd698-298d-435c-a8c0-7891d1d789b5

https://doi.org/10.1016/j.compbiomed.2022.105331

0010-4825

Computers in Biology and Medicine, 143

Institutional Repository

journal article

© 2022 F.J. Wesselius, M.S. van Schie, N.M.S. de Groot, R.C. Hendriks