Individualized Management of Fatigue and Cognitive Performance Impairment through Biomathematical Modeling.

摘要

In this work, we present a method for developing individualized biomathematical models for predicting cognitive performance impairment of individuals subjected to total sleep loss. The proposed method uses the two- process model of sleep regulation as the underlying parametric model, whose parameters are systematically customized for an individual by optimally combining the performance information obtained from the individual's performance measurements with a priori performance information using a Bayesian framework. As a result, the models incrementally account for an individual's uncertain initial state and unknown trait characteristics as each new performance measurement from the individual becomes available, yielding improved performance predictions. Additionally, the proposed method enables the analytical computation of statistically based measures of reliability of the model predictions in the form of prediction intervals. Results using data from subjects who participated in an 82-h total sleep loss laboratory study showed that the proposed method yielded individualized predictions that were up to 43% more accurate than group-average model predictions and better captured the circadian and homeostatic variations in the performance data.