0313 2B-Alert App: A Tool to Predict Individual Trait-like Responses to Sleep Loss in Real Time. (27th April 2018)

• Record Type: Journal Article
• Authors: Ramakrishnan, S; Doty, T J; Balkin, T J; Reifman, J
• Is Part Of: Sleep. Volume 41(2018)Supplement 1
• Page Start: A120
• Page End: A120
• Publication Date: 2018-04-27
• Subjects: Sleep -- Physiological aspects -- Periodicals; Sleep disorders -- Periodicals; Sommeil -- Aspect physiologique -- Périodiques; Sommeil, Troubles du -- Périodiques; Sleep disorders; Sleep -- Physiological aspects; Sleep -- physiological aspects; Sleep Wake Disorders; Psychophysiology; Electronic journals; Periodicals; 616.8498
• DOI: 10.1093/sleep/zsy061.312
• Languages: English
• ISSNs: 0161-8105

Abstract

Abstract: Introduction: Individuals differ in their trait-like neurobehavioral response to sleep loss, and in their risks for fatigue-related accidents. However, no validated, computer-based tools exist to measure and predict the neurobehavioral performance of an individual, in real time, while accounting for the individual's unique sleep-loss phenotype. Methods: We developed a smartphone application, 2B-Alert App, for Android and iPhone, in which we incorporated four key components: 1) the psychomotor vigilance task (PVT), 2) a user interface to enter sleep/wake history, 3) the validated unified model of performance (UMP), which accurately predicts an individual's PVT performance across a wide range of sleep/wake and caffeine schedules, and 4) a validated algorithm that, in real time, uses the individual's PVT measurements to customize the UMP to his/her sleep-loss phenotype. We experimentally validated the 2B-Alert App PVT measurements and 48-h-ahead predictions in 13 healthy adults who performed 20 PVTs on the app and on the gold-standard PC-PVT during 62 h of total sleep deprivation (TSD). Results: All 2B-Alert PVT statistics [e.g., mean response time (RT), lapses, false starts] correlated well with PC-PVT statistics (Pearson's r and Spearman's ρ > 0.5 and 0.8, respectively), accurately capturing within- and between-subject variations in performance across the 62 h of TSD. Sleep loss had a large effect (Cohen's d > 1.0) on all 2B-Alert PVT statistics. A comparison of the 48-h-ahead real-time predictions against the measured mean RT data revealed that the app's prediction accuracy increased with the number of PVT measurements available for tool customization. The app learned each individual's sleep-loss phenotype within 12 PVT measurements over the first 36 h of TSD, yielding an average error of less than 10 ms when compared to the UMP customized using all 20 PVT measurements. Conclusion: The 2B-Alert App offers a practical means for personal fatigue management by allowing for real-time individualized performance assessment and prediction in a smartphone. Support (If Any): This work was sponsored by the Military Operational Medicine Research Area Directorate of the U.S. Army Medical Research and Materiel Command, Ft. Detrick, MD.