0241 2B-ALERT APP AND WEB: TOOLS FOR MEASURING, PREDICTING, AND OPTIMIZING NEUROBEHAVIORAL PERFORMANCE AT INDIVIDUAL AND GROUP-AVERAGE LEVELS
Abstract Introduction: To date, no validated, computer-based tools exist to measure, predict, and optimize neurobehavioral performance due to sleep loss at both individual and group-average levels, while also accounting for the effects of caffeine. We addressed this gap by developing and validating...
Gespeichert in:
Veröffentlicht in: | Sleep (New York, N.Y.) N.Y.), 2017-04, Vol.40 (suppl_1), p.A89-A89 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Abstract
Introduction:
To date, no validated, computer-based tools exist to measure, predict, and optimize neurobehavioral performance due to sleep loss at both individual and group-average levels, while also accounting for the effects of caffeine. We addressed this gap by developing and validating a predictive mathematical model of performance [the unified model of performance (UMP)], and instantiating it into two tools: 1) 2B-Alert App, a smartphone application for real-time, individualized performance prediction and 2) 2B-Alert Web, a Web-based software for designing sleep/wake and caffeine schedules to optimize group-average performance.
Methods:
We developed and validated the UMP on psychomotor vigilance task (PVT) performance data from 14 different studies (in laboratory and field conditions), encompassing >500 subjects and including a wide range of sleep/wake schedules and caffeine doses. We then developed and validated an automated method to customize the UMP to an individual’s sleep-loss phenotype based on the individual’s PVT measurements. Finally, we embedded these capabilities into a smartphone app (Android and iPhone) and a Web tool, which allow users to enter sleep/wake schedules and caffeine consumption (doses and times), and obtain individual-specific or group-average performance predictions.
Results:
The UMP predicted group-average PVT performance across 26 different sleep/wake schedules (from partial to total sleep loss) and 6 different caffeine doses (ranging from repeated 200 mg doses to single 600 mg dose) with errors ranging from 6% to 36%. Accounting for the effects of caffeine in the model improved prediction accuracy by up to 70%. Individualized UMP models improved prediction accuracy by up to 50% compared to a group-average model. The Web tool is freely available at: , and the 2B-Alert App is expected to be available by summer of 2017.
Conclusion:
The 2B-Alert App and Web provide practical means for personal fatigue management and for optimizing work/rest schedules.
Support (If Any):
Disclaimer: The opinions and assertions contained herein are the private views of the authors and are not to be construed as official or as reflecting the views of the U.S. Army or of the U.S. Department of Defense. This abstract has been approved for public release with unlimited distribution. |
---|---|
ISSN: | 0161-8105 1550-9109 |
DOI: | 10.1093/sleepj/zsx050.240 |