Abstract: Systems and methods to estimate a subject's sleep status over time by applying data-fusion algorithms to sleep data sets collected from multiple sleep data sources are disclosed. Embodiments employ Bayes' Theorem to combine sleep data from actigraphy, sleep diary, direct observation, sleep schedules, work schedules, performance tests, neurobehavioral tests and/or the like. Particular embodiments assign data error characteristics to each source, determine likelihoods of correct reporting of sleep status from each source, and apply Bayesian analysis to each source-specific likelihood to determine an overall sleep status estimate. Data error characteristics may account, without limitation, for data insertion errors, data deletion errors, and sleep timing errors. Heuristics may be also used to correct common errors found within collected sleep data and/or to infer sleep status from atypical sources of sleep data.

Abstract: A normalized contextual performance metric quantifies the susceptibility of fatigue-related risk in a fatigue environment with activities conducted within a fatigue level range of interest. Fatigue incidents are quantified by one of a plurality of values associated with fatigue-incident measurement. Activities are quantified by one of a plurality of values associated with activity measurement. A normalized contextual performance metric is determined by identifying a fatigue level range of interest, summing all values of incidents occurring at the fatigue level range of interest, summing all values for relevant activities occurring at the fatigue level range of interest, and then dividing the first sum by the second. The normalized contextual performance metric thereby allows operational managers to assess risk of fatigue incidents by monitoring activities and fatigue levels within the fatigue environment.

Abstract: Human neurobehavioral performance prediction systems and methods are disclosed in which disrupted sleep patterns, such as (without limitation) sleep fracturing due to apnea, are accounted for. Biomathematical models are used to predict neurobehavioral performance based on disrupted sleep using a sleep function modified in accordance with apnea-severity data to account for loss in sleep efficiency. Risk of diminished neurobehavioral performance can then be monitored in affected individuals. Compliance with treatment regimens, adjustments to apnea severity assessment, corrections to predicted future sleep schedules, and/or individualization of neurobehavioral performance model parameters can also be achieved based upon a comparison of actual and model-predicted performance levels.