Wireless ear EEG to monitor drowsiness

• Published in: Nature communications Vol. 15; no. 1; pp. 6520 - 13
• Main Authors: Kaveh, Ryan, Schwendeman, Carolyn, Pu, Leslie, Arias, Ana C., Muller, Rikky
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.08.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/985; 639/166/987; 692/53/2423; 9/10; 9/26; Adult; Algorithms; Classification; Drowsiness; Ear; Ear - physiology; Electrodes; Electroencephalography - instrumentation; Electroencephalography - methods; Electronics; Environmental monitoring; Female; Humanities and Social Sciences; Humans; Machine learning; Male; Monitoring, Physiologic - instrumentation; Monitoring, Physiologic - methods; multidisciplinary; Remote monitoring; Science; Science (multidisciplinary); Sleep Stages - physiology; Sleepiness; Support Vector Machine; Wearable Electronic Devices; Wireless Technology - instrumentation; Young Adult
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-48682-7

Neural wearables can enable life-saving drowsiness and health monitoring for pilots and drivers. While existing in-cabin sensors may provide alerts, wearables can enable monitoring across more environments. Current neural wearables are promising but most require wet-electrodes and bulky electronics. This work showcases in-ear, dry-electrode earpieces used to monitor drowsiness with compact hardware. The employed system integrates additive-manufacturing for dry, user-generic earpieces, existing wireless electronics, and offline classification algorithms. Thirty-five hours of electrophysiological data were recorded across nine subjects performing drowsiness-inducing tasks. Three classifier models were trained with user-specific, leave-one-trial-out, and leave-one-user-out splits. The support-vector-machine classifier achieved an accuracy of 93.2% while evaluating users it has seen before and 93.3% when evaluating a never-before-seen user. These results demonstrate wireless, dry, user-generic earpieces used to classify drowsiness with comparable accuracies to existing state-of-the-art, wet electrode in-ear and scalp systems. Further, this work illustrates the feasibility of population-trained classification in future electrophysiological applications. Neural wearables can enable life-saving drowsiness monitoring. This work showcases an in-ear, dry-electrode earpiece used to monitor drowsiness for 35 hours across 9 subjects. This data was used to train offline machine learning classifiers and achieve an average accuracy of >90% across all models.