Anomaly Detection in Time Series with Triadic Motif Fields and Application in Atrial Fibrillation ECG Classification

TL;DR

This paper introduces Triadic Motif Fields (TMF), a novel time-series image encoding method for ECG signals, combined with transfer learning and simple classifiers, achieving high accuracy in atrial fibrillation detection with clinical interpretability.

Contribution

The paper proposes TMF as an effective encoding for ECG analysis, integrating transfer learning and simple classifiers for accurate AF detection, with improved interpretability and patient-wise clustering.

Findings

Achieved 95.50% ROC-AUC in AF classification.

TMF features enable clear patient-wise clustering.

Model provides clinically interpretable results.

Abstract

In the time-series analysis, the time series motifs and the order patterns in time series can reveal general temporal patterns and dynamic features. Triadic Motif Field (TMF) is a simple and effective time-series image encoding method based on triadic time series motifs. Electrocardiography (ECG) signals are time-series data widely used to diagnose various cardiac anomalies. The TMF images contain the features characterizing the normal and Atrial Fibrillation (AF) ECG signals. Considering the quasi-periodic characteristics of ECG signals, the dynamic features can be extracted from the TMF images with the transfer learning pre-trained convolutional neural network (CNN) models. With the extracted features, the simple classifiers, such as the Multi-Layer Perceptron (MLP), the logistic regression, and the random forest, can be applied for accurate anomaly detection. With the test dataset of the PhysioNet Challenge 2017 database, the TMF classification model with the VGG16 transfer learning model and MLP classifier demonstrates the best performance with the 95.50% ROC-AUC and 88.43% F1 score in the AF classification. Besides, the TMF classification model can identify AF patients in the test dataset with high precision. The feature vectors extracted from the TMF images show clear patient-wise clustering with the t-distributed Stochastic Neighbor Embedding technique. Above all, the TMF classification model has very good clinical interpretability. The patterns revealed by symmetrized Gradient-weighted Class Activation Mapping have a clear clinical interpretation at the beat and rhythm levels.