AUTHOR=Brisk Rob , Bond Raymond R. , Finlay Dewar , McLaughlin James A. D. , Piadlo Alicja J. , McEneaney David J. 

TITLE=WaSP-ECG: A Wave Segmentation Pretraining Toolkit for Electrocardiogram Analysis

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.760000

DOI=10.3389/fphys.2022.760000

ISSN=1664-042X

ABSTRACT=Introduction : Representation learning allows artificial intelligence (AI) models to learn useful features from large, unlabelled datasets. This can reduce the need for labelled data across a range of downstream tasks. It was hypothesised that wavelet segmentation would be a useful form of ECG representation learning. In addition to reducing labelled data requirements, segmentation masks may provide a mechanism for explainable AI. This study details the development and evaluation of a wave segmentation pretraining (WaSP) application.

Materials and methods : Pretraining: A non-AI-based ECG signal and image simulator was developed to generate ECGs and wavelet segmentation masks. U-Net models were trained to segment wavelets from synthetic ECGs. Dataset: The raw sample files from the PTB-XL dataset were downloaded. Each ECG was also plotted into an image. Fine-tuning and evaluation: A hold-out approach was used with a 60:20:20 training / validation / test set split. The encoder portions of the U-Net models were fine-tuned to classify PTB-XL ECGs for two tasks: sinus rhythm (SR) vs atrial fibrillation (AF), and myocardial infarction (MI) vs normal ECGs. The fine-tuning was repeated without pretraining. Results were compared. Explainable AI: an example pipeline combining AI-derived segmentation masks and a rule-based AF detector was developed and evaluated.

Results : WaSP consistently improved model performance on downstream tasks for both ECG signals and images. The difference between non-pretrained models and models pretrained for wavelet segmentation was particularly marked for ECG image analysis. A selection of segmentation masks are shown. An AF detection algorithm comprising both AI and rule-based components performed less well than end-to-end AI models but its outputs are proposed to be highly explainable. An example output is shown.

Conclusions : WaSP using synthetic data and lables allows AI models to learn useful features for downstream ECG analysis with real-world data. Segmentation masks provide an intermediate output that may facilitate confidence calibration in the context of end-to-end AI. It is possible to combine AI-derived segmentation masks and rule-based diagnostic classifiers for explainable ECG analysis.