Compressor-Based Classification for Atrial Fibrillation Detection
This addresses the need for efficient AF detection in biomedical engineering, but it is incremental as it adapts an existing text method to a new domain.
The paper tackled the problem of automatic atrial fibrillation detection from ECG signals by applying a compressor-based classification method using gzip, achieving average sensitivity of 97.1% and specificity of 91.7%, close to specialized algorithms.
Atrial fibrillation (AF) is one of the most common arrhythmias with challenging public health implications. Therefore, automatic detection of AF episodes on ECG is one of the essential tasks in biomedical engineering. In this paper, we applied the recently introduced method of compressor-based text classification with gzip algorithm for AF detection (binary classification between heart rhythms). We investigated the normalized compression distance applied to RR-interval and $Δ$RR-interval sequences ($Δ$RR-interval is the difference between subsequent RR-intervals). Here, the configuration of the k-nearest neighbour classifier, an optimal window length, and the choice of data types for compression were analyzed. We achieved good classification results while learning on the full MIT-BIH Atrial Fibrillation database, close to the best specialized AF detection algorithms (avg. sensitivity = 97.1\%, avg. specificity = 91.7\%, best sensitivity of 99.8\%, best specificity of 97.6\% with fivefold cross-validation). In addition, we evaluated the classification performance under the few-shot learning setting. Our results suggest that gzip compression-based classification, originally proposed for texts, is suitable for biomedical data and quantized continuous stochastic sequences in general.