Multilabel 12-Lead Electrocardiogram Classification Using Gradient Boosting Tree Ensemble

TL;DR

This paper presents a gradient boosting tree ensemble approach for multilabel 12-lead ECG classification, utilizing morphology and signal features to detect cardiac abnormalities, achieving competitive results in a challenge setting.

Contribution

The study introduces a novel ensemble method combining morphology and signal features for ECG diagnosis, with a two-phase feature selection process for improved accuracy.

Findings

Achieved an official validation score of 0.476

Placed 36th out of 41 in the challenge rankings

Utilized a large dataset of 43,101 records for training and evaluation

Abstract

The 12-lead electrocardiogram (ECG) is a commonly used tool for detecting cardiac abnormalities such as atrial fibrillation, blocks, and irregular complexes. For the PhysioNet/CinC 2020 Challenge, we built an algorithm using gradient boosted tree ensembles fitted on morphology and signal processing features to classify ECG diagnosis. For each lead, we derive features from heart rate variability, PQRST template shape, and the full signal waveform. We join the features of all 12 leads to fit an ensemble of gradient boosting decision trees to predict probabilities of ECG instances belonging to each class. We train a phase one set of feature importance determining models to isolate the top 1,000 most important features to use in our phase two diagnosis prediction models. We use repeated random sub-sampling by splitting our dataset of 43,101 records into 100 independent runs of 85:15 training/validation splits for our internal evaluation results. Our methodology generates us an official phase validation set score of 0.476 and test set score of -0.080 under the team name, CVC, placing us 36 out of 41 in the rankings.