Automatic Detection of Arousals during Sleep using Multiple Physiological Signals

TL;DR

This paper introduces an automatic algorithm for detecting sleep arousals using multiple physiological signals, leveraging patient-specific models and ensemble classification to improve sleep analysis accuracy.

Contribution

The study presents a novel ensemble-based approach utilizing multiple physiological signals for automatic sleep arousal detection with subject-specific modeling.

Findings

Achieved AUPRC of 0.25 on in-house test set

Achieved AUPRC of 0.21 on blind test set

Demonstrated feasibility of multi-signal, patient-specific arousal detection

Abstract

The visual scoring of arousals during sleep routinely conducted by sleep experts is a challenging task warranting an automatic approach. This paper presents an algorithm for automatic detection of arousals during sleep. Using the Physionet/CinC Challenge dataset, an 80-20% subject-level split was performed to create in-house training and test sets, respectively. The data for each subject in the training set was split to 30-second epochs with no overlap. A total of 428 features from EEG, EMG, EOG, airflow, and SaO2 in each epoch were extracted and used for creating subject-specific models based on an ensemble of bagged classification trees, resulting in 943 models. For marking arousal and non-arousal regions in the test set, the data in the test set was split to 30-second epochs with 50% overlaps. The average of arousal probabilities from different patient-specific models was assigned to each 30-second epoch and then a sample-wise probability vector with the same length as test data was created for model evaluation. Using the PhysioNet/CinC Challenge 2018 scoring criteria, AUPRCs of 0.25 and 0.21 were achieved for the in-house test and blind test sets, respectively.