You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018

TLDR

The PhysioNet/Computing in Cardiology Challenge 2018 focused on using physiological signals collected during polysomnographic sleep studies to detect non‑apnea arousal sources. Participants were asked to develop an algorithm that could label the presence of arousals within a hidden test set. The challenge provided 1,983 polysomnographic recordings, with 994 labeled for training and 989 withheld for testing, and evaluated submissions by area under the precision‑recall curve, attracting 22 teams that applied methods ranging from generalized linear models to deep neural networks.

Abstract

The PhysioNet/Computing in Cardiology Challenge 2018 focused on the use of various physiological signals (EEG, EOG, EMG, ECG, SaO2) collected during polysomnographic sleep studies to detect sources of arousal (non-apnea) during sleep. A total of 1,983 polysomnographic recordings were made available to the entrants. The arousal labels for 994 of the recordings were made available in a public training set while 989 labels were retained in a hidden test set. Challengers were asked to develop an algorithm that could label the presence of arousals within the hidden test set. The performance metric used to assess entrants was the area under the precision-recall curve. A total of twenty-two independent teams entered the Challenge, deploying a variety of methods from generalized linear models to deep neural networks.