Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs

TL;DR

This paper presents an ensemble deep neural network with a squeeze and excite ResNet architecture for classifying 24 cardiac abnormalities from 12-lead ECGs, achieving competitive accuracy and highlighting label inconsistencies.

Contribution

The study introduces a novel adaptive weighted ResNet model that incorporates age and gender features for ECG classification, and analyzes label inconsistencies affecting model performance.

Findings

Achieved a weighted accuracy of 0.684 in cross-validation

Ranked 2nd out of 41 in the official challenge

Discovered high inconsistency in training labels among clinicians

Abstract

Background: Twelve lead ECGs are a core diagnostic tool for cardiovascular diseases. Here, we describe and analyse an ensemble deep neural network architecture to classify 24 cardiac abnormalities from 12-lead ECGs. Method: We proposed a squeeze and excite ResNet to automatically learn deep features from 12-lead ECGs, in order to identify 24 cardiac conditions. The deep features were augmented with age and gender features in the final fully connected layers. Output thresholds for each class were set using a constrained grid search. To determine why the model made incorrect predictions, two expert clinicians independently interpreted a random set of 100 misclassified ECGs concerning Left Axis Deviation. Results: Using the bespoke weighted accuracy metric, we achieved a 5-fold cross validation score of 0.684, and sensitivity and specificity of 0.758 and 0.969, respectively. We scored 0.520 on the full test data, and ranked 2nd out of 41 in the official challenge rankings. On a random set of misclassified ECGs, agreement between two clinicians and training labels was poor (clinician 1: kappa = -0.057, clinician 2: kappa = -0.159). In contrast, agreement between the clinicians was very high (kappa = 0.92). Discussion: The proposed prediction model performed well on the validation and hidden test data in comparison to models trained on the same data. We also discovered considerable inconsistency in training labels, which is likely to hinder development of more accurate models.