Development of Interpretable Machine Learning Models to Detect Arrhythmia based on ECG Data

TL;DR

This paper develops and compares CNN and LSTM models for ECG arrhythmia detection, emphasizing interpretability techniques like Grad-CAM to understand model decision-making and improve clinical trust.

Contribution

It introduces a comprehensive interpretability analysis of deep learning models for ECG classification, highlighting Grad-CAM's effectiveness and the focus on QRS complex features.

Findings

Grad-CAM effectively explains model predictions.

High-performing models focus on QRS complex.

Interpretability varies between correct and incorrect classifications.

Abstract

The analysis of electrocardiogram (ECG) signals can be time consuming as it is performed manually by cardiologists. Therefore, automation through machine learning (ML) classification is being increasingly proposed which would allow ML models to learn the features of a heartbeat and detect abnormalities. The lack of interpretability hinders the application of Deep Learning in healthcare. Through interpretability of these models, we would understand how a machine learning algorithm makes its decisions and what patterns are being followed for classification. This thesis builds Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) classifiers based on state-of-the-art models and compares their performance and interpretability to shallow classifiers. Here, both global and local interpretability methods are exploited to understand the interaction between dependent and independent variables across the entire dataset and to examine model decisions in each sample, respectively. Partial Dependence Plots, Shapley Additive Explanations, Permutation Feature Importance, and Gradient Weighted Class Activation Maps (Grad-Cam) are the four interpretability techniques implemented on time-series ML models classifying ECG rhythms. In particular, we exploit Grad-Cam, which is a local interpretability technique and examine whether its interpretability varies between correctly and incorrectly classified ECG beats within each class. Furthermore, the classifiers are evaluated using K-Fold cross-validation and Leave Groups Out techniques, and we use non-parametric statistical testing to examine whether differences are significant. It was found that Grad-CAM was the most effective interpretability technique at explaining predictions of proposed CNN and LSTM models. We concluded that all high performing classifiers looked at the QRS complex of the ECG rhythm when making predictions.