Draft:SAFTE-FAST
Submission declined on 12 September 2026 by Theroadislong (talk).
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
SAFTE-FAST is a software-based Fatigue Risk Management System developed by the Institutes for Behavior Resources, Inc. It consists of the Sleep Activity Fatigue Task Effectiveness (SAFTE) mathematical performance prediction model and a user interface called the Fatigue Avoidance Scheduling Tool (FAST). Inputs to the SAFTE model include sleep duration, work schedules and time-of-day – the combined effects of which are used to predict performance. SAFTE-FAST is used by a variety of industries, including aviation and rail, to predict performance deficits (fatigue levels) based on sleep opportunities and work schedule.
History
[edit]Model Development by US Military
Biomathematical models of fatigue incorporate the principles of the two-process model of sleep regulation, with fatigue levels represented as the interaction between the homeostatic pressure for sleep that increases during wakefulness and decreases during sleep, and the circadian rhythm for wakefulness that peaks during the day and reaches a nadir in the early morning hours. In the 1990s, the Walter Reed Army Institute of Research (WRAIR)[1] incorporated these principles into the Sleep and Performance Model (SPM) to predict the relationships between sleep, time-of-day, and cognitive performance – a tool that was the centerpiece of a comprehensive fatigue management system developed for the US Department of Defense (DoD).
Over the years, the mathematical model has undergone a number of upgrades that improve both its accuracy and its utility. For example, as evidence accrued in the 1990s that biomathematical models (including SPM) tend to overestimate the rate of recovery following sleep restriction (multiple nights of inadequate sleep, SR) – i.e., that performance deficits resulting from SR persist much longer than those resulting from a comparable level of acute sleep deprivation (SD) – the model was updated using relevant data from SR studies conducted at WRAIR for the express purpose of providing relevant data for model development. Since then, the model has continued to evolve to better account for various aspects of input variables – e.g., taking into account not only the duration of work periods but also the workload during those work periods. The SAFTE model (a next-generation version of the SPM), was patented by Dr. Steven Hursh in 2003.
Software Development for Commercial Applications
Historically, sleep data (specifically bedtimes and wake times) have been used as the primary input to biomathematical models of fatigue. However, as models were adopted by industry and employee sleep data were generally unavailable, it was necessary to adopt a two-step approach: (1) predict sleep duration from the work schedule, and (2) predict performance from the predicted sleep duration.
For SAFTE-FAST, the sleep prediction algorithm (Auto-Sleep) was developed using sleep and work diary data collected from railroad engineers[2] to predict the average sleep pattern associated with a work schedule. The average sleep pattern was then used to predict performance. Auto-Sleep has been validated against wrist activity data (actigraphy) and sleep logs in aviation and rail workers.[3][4] The algorithm is trained to predict sleep duration in working populations with specific sleep schedules based previously-collected actigraphy data, using a process called harmonization. The harmonized Auto-Sleep data are then used for prospective modeling of proposed new schedules. SAFTE-FAST with AutoSleep has been adopted as a tool for fatigue assessments associated with work schedules, including those of aviators and firefighters.[5][6]
Validation
Previous studies have been performed to determine the extent to which SAFTE-FAST performance predictions are predictive of railroad accidents. Thirty-day work histories from 2,800 employees involved in 1,400 freight railroad accidents over 2 ½ years were processed using a SAFTE-FAST special batch processor version developed by Dr. Timothy Elsmore. Of the 1,400 accidents, 400 were attributed to human error. For those accidents, the model predicted a significant relationship between sleep duration and performance degradations and, importantly, the ‘inflection point’ (the amount of sleep loss) at which the risk of accident accelerates.[7]
References
[edit]- ↑ Hursh SR, Redmond DP, Johnson ML, et al. Fatigue models for applied research in warfighting. Aviation, space, and environmental medicine. 2004;75(3):A44-A53.
- ↑ Gertler J, Hursh S, Fanzone J, Raslear T, America QN. Validation of FAST model sleep estimates with actigraph measured sleep in locomotive engineers. 2012. https://rosap.ntl.bts.gov/view/dot/24796
- ↑ Roma PG, Hursh SR, Mead AM, Nesthus TE. Flight attendant work/rest patterns, alertness, and performance assessment: Field validation of biomathematical fatigue modeling. 2012. https://rosap.ntl.bts.gov/view/dot/57158
- ↑ Hursh SR, Raslear, T.G., Kaye, A.S., and Fanzone, J.F. Validation and calibration of a fatigue assessment tool for railroad work schedules, summary report. (Report No. DOT/ FRA/ORD–06/21). 2006. https://railroads.dot.gov/elibrary/validation-and-calibration-fatigue-assessment-tool-railroad-work-schedules-summary-report
- ↑ Devine JK, Nichols MG, Schwartz LP, Choynowski J, Hursh SR. Biomathematical modeling for the prediction of sleep behavior and comparison against cognitive performance in firefighters. Safety Science. 2023;163:106128
- ↑ Paul MA, Hursh SR, Love RJ. The Importance of Validating Sleep Behavior Models for Fatigue Management Software in Military Aviation. Mil Med. Dec 30 2020;185(11-12):e1986-e1991.
- ↑ Hursh SR, Fanzone, J.F., and Raslear, T.G. Analysis of the Relationship between Operator Effectiveness Measures and Economic Impacts of Rail Accidents (Technial Report DOT/FRA/ORD-11/13). 2011. https://rosap.ntl.bts.gov/view/dot/40523
- provide significant coverage: discuss the subject in detail, not just brief mentions or routine announcements;
- are reliable: from reputable outlets with editorial oversight;
- are independent: not connected to the subject, such as interviews, press releases, the subject's own website, or sponsored content.
Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia.