2B‐Alert App: A mobile application for real‐time individualized prediction of alertness

Abstract

Knowing how an individual responds to sleep deprivation is a requirement for developing personalized fatigue management strategies. Here we describe and validate the 2B-Alert App, the first mobile application that progressively learns an individual's trait-like response to sleep deprivation in real time, to generate increasingly more accurate individualized predictions of alertness. We incorporated a Bayesian learning algorithm within the validated Unified Model of Performance to automatically and gradually adapt the model parameters to an individual after each psychomotor vigilance test. We implemented the resulting model and the psychomotor vigilance test as a smartphone application (2B-Alert App), and prospectively validated its performance in a 62-hr total sleep deprivation study in which 21 participants used the app to perform psychomotor vigilance tests every 3 hr and obtain real-time individualized predictions after each test. The temporal profiles of reaction times on the appconducted psychomotor vigilance tests were well correlated with and as sensitive as those obtained with a previously characterized psychomotor vigilance test device.The app progressively learned each individual's trait-like response to sleep deprivation throughout the study, yielding increasingly more accurate predictions of alertness for the last 24 hr of total sleep deprivation as the number of psychomotor vigilance tests increased. After only 12 psychomotor vigilance tests, the accuracy of the model predictions was comparable to the peak accuracy obtained using all psychomotor vigilance tests. With the ability to make real-time individualized predictions of the effects of sleep deprivation on future alertness, the 2B-Alert App can be used to tailor personalized fatigue management strategies, facilitating self-management of alertness and safety in operational and non-operational settings. K E Y W O R D Salertness, caffeine, individualized predictions, psychomotor vigilance test, sleep, smartphoneThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

Poor Subjective Sleep Quality Is Associated with Poor Occupational Outcomes in Elite Soldiers

“…Overall, the sample of 35 soldiers had poor sleep on the PSQI (6.3 ± 3.1)-above the commonly-used cut-off score of 5 [54,55], consistent with prior military samples [56][57][58][59][60][61]. The participants reported obtaining 5.6 ± 1.2 h of sleep per night prior to the exercise, indicating the soldiers had a modest amount of sleep debt before beginning the exercise.…”

“…Therefore, military researchers (particularly in our lab) have started focusing on increasing resiliency to sleep loss rather than eliminating sleep loss. This is done either by enhancing or extending sleep prior to sleep loss (i.e., sleep banking [49][50][51][52][53]) or by creating fatigue management strategies during and after sleep loss (e.g., using smart apps to enhance caffeine timing [54]). The current study focuses on the former concept-how does sleep quality prior to mandated sleep loss longitudinally predict the selected outcomes after sleep loss occurs?…”

“…Subjective sleep quality: The Pittsburgh Sleep Quality Index (PSQI) [54,55] is a multi-component measure of sleep quality that queries participants on sleep duration, sleep onset latency, causes of awakenings, and functional outcomes related to sleep loss. The seven components created from these data are summed to create a PSQI Global Score (described in statistical analyses section).…”

How sleep can help maximize human potential: The role of leaders

“…The mobile device application "PeakAlert" and the FAST, or Fatigue Avoidance Scheduling Tool, use algorithms developed by WRAIR, the Biotechnology High Performance Computing Software Application Institute of the U.S. Army Medical Research and Materiel Command for the US Department of Defense that integrates performance and device data to predict cognitive alertness levels and performance. 82 When soldiers learn how physical activity, caffeine intake and other variables objectively affect their cognitive performance by using these tools, they are better able to apply strategies wisely in the future. 78 For those with persistent sleeping problems or established diagnosed insomnia, there are free resources for assistance that may be combined with guidance from their military medical provider.…”

Tracing Pilots’ Situation Assessment by Neuroadaptive Cognitive Modeling

“…Tracing individual behavior (model-tracing; Fu et al, 2006) can suffer from epistemic uncertainty (Kiureghian and Ditlevsen, 2009), for example, when it is unknown why a pilot did not react to an alert. This uncertainty can be reduced by using physiological data alongside system inputs to build richer models of individual performance (Olofsen et al, 2010;Putze et al, 2015;Reifman et al, 2018). However, sensor data inaccuracies can introduce a different, aleatory kind of uncertainty that is hard to assign to individual observations and needs to be considered in design of adaptive models (Kiureghian and Ditlevsen, 2009).…”