Match!

Individualized performance prediction of sleep-deprived individuals with the two-process model

Published on Feb 1, 2008in Journal of Applied Physiology3.14
· DOI :10.1152/japplphysiol.00877.2007
Srinivasan Rajaraman8
Estimated H-index: 8
,
Andrei V. Gribok18
Estimated H-index: 18
+ 2 AuthorsJaques Reifman23
Estimated H-index: 23
Cite
Abstract
We present a new method for developing individualized biomathematical models that predict performance impairment for individuals restricted to total sleep loss. The underlying formulation is based on the two-process model of sleep regulation, which has been extensively used to develop group-average models. However, in the proposed method, the parameters of the two-process model are systematically adjusted to account for an individual's uncertain initial state and unknown trait characteristics, resulting in individual-specific performance prediction models. The method establishes the initial estimates of the model parameters using a set of past performance observations, after which the parameters are adjusted as each new observation becomes available. Moreover, by transforming the nonlinear optimization problem of finding the best estimates of the two-process model parameters into a set of linear optimization problems, the proposed method yields unique parameter estimates. Two distinct data sets are used to evaluate the proposed method. Results of simulated data (with superimposed noise) show that the model parameters asymptotically converge to their true values and the model prediction accuracy improves as the number of performance observations increases and the amount of noise in the data decreases. Results of a laboratory study (82 h of total sleep loss), for three sleep-loss phenotypes, suggest that individualized models are consistently more accurate than group-average models, yielding as much as a threefold reduction in prediction errors. In addition, we show that the two-process model of sleep regulation is capable of representing performance data only when the proposed individualized model is used.
  • References (43)
  • Citations (25)
Cite
References43
Newest
#1Antoine Viola (University of Surrey)H-Index: 18
#2Simon Archer (University of Surrey)H-Index: 44
Last.Derk-Jan Dijk (University of Surrey)H-Index: 90
view all 8 authors...
#1Nancy J. Wesensten (WRAIR: Walter Reed Army Institute of Research)H-Index: 27
#2William D. S. Killgore (WRAIR: Walter Reed Army Institute of Research)H-Index: 43
Last.Thomas J. Balkin (WRAIR: Walter Reed Army Institute of Research)H-Index: 41
view all 3 authors...
#1Thomas J. Balkin (WRAIR: Walter Reed Army Institute of Research)H-Index: 41
#2Paul D. Bliese (WRAIR: Walter Reed Army Institute of Research)H-Index: 48
Last.Nancy J. Wesensten (WRAIR: Walter Reed Army Institute of Research)H-Index: 27
view all 9 authors...
#1Hans P. A. Van Dongen (UPenn: University of Pennsylvania)H-Index: 39
#2Maurice D. Baynard (UPenn: University of Pennsylvania)H-Index: 3
Last.David F. Dinges (UPenn: University of Pennsylvania)H-Index: 81
view all 4 authors...
Cited By25
Newest
#1Eric Chern-Pin Chua (NUS: National University of Singapore)H-Index: 13
#2Jason P. Sullivan (Brigham and Women's Hospital)H-Index: 9
Last.Joshua J. Gooley (NUS: National University of Singapore)H-Index: 23
view all 8 authors...
#1Pooja Rajdev (United States Army Medical Research and Materiel Command)H-Index: 1
#2David Thorsley (United States Army Medical Research and Materiel Command)H-Index: 9
Last.Jaques Reifman (United States Army Medical Research and Materiel Command)H-Index: 6
view all 7 authors...
View next paperMicrocomputer analyses of performance on a portable, simple visual RT task during sustained operations