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

Rob Brisk, RR Bond, D Finlay, James McLaughlin, Alicja Jasinska-Piadlo, David McEneaney

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
105 Downloads (Pure)

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 wave segmentation would be a useful form of electrocardiogram (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 wave segmentation masks. U-Net models were trained to segment waves 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 wave 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. Conclusion: WaSP using synthetic data and labels 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.
Original languageEnglish
Article number760000
Pages (from-to)1-17
Number of pages17
JournalFrontiers in Physiology
Volume13
Early online date17 Mar 2022
DOIs
Publication statusPublished online - 17 Mar 2022

Bibliographical note

Funding information:
RBr holds a Ph.D. scholarship from the Eastern Corridor Medical Engineering Centre that is supported by the European Union’s INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB). This research was also supported by the Craigavon Cardiac Care Association, whom we wish to thank for their active support of cardiovascular research in Northern Ireland over the last 50 years.

Funding Information:
RBr holds a Ph.D. scholarship from the Eastern Corridor Medical Engineering Centre that is supported by the European Union’s INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB). This research was also supported by the Craigavon Cardiac Care Association, whom we wish to thank for their active support of cardiovascular research in Northern Ireland over the last 50 years.

Publisher Copyright:
Copyright © 2022 Brisk, Bond, Finlay, McLaughlin, Piadlo and McEneaney.

Keywords

  • Artificial intelligence
  • ECG
  • Machine learning
  • Explainable AI
  • Representation learning
  • electrocardiogram (ECG)
  • representation learning
  • explainable AI
  • machine learning
  • artificial intelligence

Fingerprint

Dive into the research topics of 'WaSP-ECG: A Wave Segmentation Pretraining Toolkit for Electrocardiogram Analysis'. Together they form a unique fingerprint.

Cite this