New PVT Metrics with an Improved Sensitivity to Sleep Deprivation. Analysis from Short to Long Time Intervals. LATOUR Philippe and VAN DROOGENBROECK Marc University of Liège – Belgium 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 1
General context Interested in analyzing, studying, designing and/or assessing performances … of automatic « instantaneous » alertness monitoring and drowsiness detection problems/systems … by using (especially) PVTs (Psychomotor Vigilance Test) 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 2
Our PVT Protocol (22 Subjects & 3 PVTs) 22 Subjects (11 males, 11 females, mean 22.2y., range 19-34 years): Arrival at the laboratory at 8h30, day 1. Non-SDP PVT 1 : at 9h30, day 1; this is the reference “Non Sleep Deprived” PVT. Go home or at work, with an actigraph and back to the laboratory at 20h30, day1. SDP PVT 2 : at 02h30, during the night; this is the first Sleep Deprived PVT. SDP PVT 3 : at 10h30, day 2; this is the second Sleep Deprived PVT. 12h 23h 7h 9h 11h 20h30 23h 2h 4h 7h 10h PVT Tests 1 2 3 Night 1 Day 1 Night 2 Day 2 At home In lab At home + actigraphy In lab Sleep No sleep No stimulant Figure adapted, with permission, from C. François & al., “Tests of a new drowsiness characterization and monitoring system based on ocular parameters”, in Int. J. Environ. Res. Public Health , Vol. 13, n°2, 2016, pp. 174-183 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 3
Alertness Monitoring & Drowsiness Detection Temporal sub-interval PVT RT … … RT RT RT RT RT k n 1 k 1 k k 1 k ' k n Physiological Signals 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 4
Alertness Monitoring & Drowsiness Detection Temporal sub-interval PVT RT … … RT RT RT RT RT k n 1 k 1 k k 1 k ' k n Metrics computation Alertness Monitoring & Drowsiness Detection Physiological Signals 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 5
Alertness Monitoring & Drowsiness Detection Temporal sub-interval PVT RT … … RT RT RT RT RT k n 1 k 1 k k 1 k ' k n 1 k n 1 Metrics RT RT k ' n k ' k computation k n 1 1 1 RS n R T k ' k k ' LN 5 0 0 # k RT ' 500 ms k , k ' k n k ' Alertness Monitoring & Alertness level Drowsiness Detection Physiological Signals 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 6
Alertness Monitoring & Drowsiness Detection Temporal sub-interval PVT RT … … RT RT RT RT RT k n 1 k 1 k k 1 k ' k n 1 k n 1 Metrics RT RT k ' n k ' k computation k n 1 1 1 RS n R T k ' k k ' Compare LN 5 0 0 # k RT ' 500 ms k , k ' k n k ' Correlate Alertness Monitoring & Alertness level Drowsiness Detection Physiological Signals 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 7
Alertness Monitoring & Drowsiness Detection Difficulties … PVT metrics sensitivity to sleep deprivation has been demonstrated mainly when computed on the full length PVT, not on (much) shorter temporal sub-interval. RT distribution (and then also any metrics distribution) are strongly dependent on the subject. How is the alertness level retated to sleep deprivation? 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 8
Alertness Monitoring & Drowsiness Detection Difficulties … PVT metrics sensitivity to sleep deprivation has been demonstrated mainly when computed on the full length PVT, not on (much) shorter temporal sub-interval. • Will be discussed later … stay tuned! RT distribution (and then also any metrics distribution) are strongly dependent on the subject. • It’s Now How is the alertness level retated to sleep deprivation? • Not Today! 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 9
How to normalize metrics? Lapse Number Use a threshold adapted to the subject; instead of 500ms for everyone. meanRT / meanRS Not obvious at first sight Could consider to apply a kind of normalizing function to RT/RS before summing or averaging 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 10
How to normalize metrics? Lapse Number Use a threshold adapted to the subject; instead of 500ms for everyone. meanRT / meanRS Not obvious at first sight Could consider to apply a kind of normalizing function to RT/RS before summing or averaging 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 11
25% Quantile in the RS distrib. of PVT1 The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 12
25% Quantile in the RS distrib. of PVT1 The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 13
25% Quantile in the RS distrib. of PVT1 The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 14
25% Quantile in the RS distrib. of PVT1 The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 15
25% Quantile in the RS distrib. of PVT1 The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 25( 3) Q Sbj 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 16
LNQ25 : Normalized Lapse Number The entire Non-SDP PVT1 (10min) of Subject 3 … … Sub-interval in a PVT of Subject 3 RT … RT RT … RT N 1 2 k … … RT RT … RT RT RT … k n 1 k n k 1 k k ' Metrics computation 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 17
LNQ25 : Normalized Lapse Number The entire Non-SDP PVT1 (10min) of Subject 3 … … Sub-interval in a PVT of Subject 3 RT … RT RT … RT N 1 2 k … … RT RT … RT RT RT … k n 1 k n k 1 k k ' 25( 3) Q Sbj Metrics computation 1 LNQ 25 # k ' Q 25 ( Sbj 3 ) , k k ' k n RT k ' 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 18
How to normalize metrics? Lapse Number Use the 25% quantile of the RS distribution in the Non-SDP PVT for each subject as a lapse threshold. meanRT / meanRS Could consider to apply a kind of normalizing function to RT/RS before summing or averaging 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 19
How to normalize metrics? Lapse Number Use the 25% quantile of the RS distribution in the Non-SDP PVT for each subject as a lapse threshold. meanRT / meanRS Could consider to apply a kind of normalizing function to RT/RS before summing or averaging 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 20
Lapse Probability The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 21
Lapse Probability The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 22
Lapse Probability The entire Non-SDP PVT1 (10min) of Subject 3 … … RT … RT RT … RT N 1 2 k RS LpPr 1 RS 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 23
ELN: Expected Lapse Number The entire Non-SDP PVT1 (10min) of Subject 3 … … Sub-interval in a PVT of Subject 3 RT … RT RT … RT N … … 1 2 k RT RT … RT RT RT … k n 1 k n k 1 k ' k Metrics computation 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 24
ELN: Expected Lapse Number The entire Non-SDP PVT1 (10min) of Subject 3 … … Sub-interval in a PVT of Subject 3 RT … RT RT … RT N … … 1 2 k RT RT … RT RT RT … k n 1 k n k 1 k ' k Metrics RS LpPr 1 RS computation k n 1 1 ELN L pPr RT k ' k k ' 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 25
How to normalize metrics? Lapse Number Use the 25% quantile of the RS distribution in the Non-SDP PVT for each subject as a lapse threshold. meanRT / meanRS Use an estimation of the Lapse Probability as a normalizing function for RS. 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 26
Alertness Monitoring & Drowsiness Detection Temporal sub-interval PVT RT … … RT RT RT RT RT k n 1 k 1 k k 1 k ' k n LN 500 RT RS Metrics computation ELN LNQ 25 Measure the Sensitivity to Sleep Deprivation ? 20 March 2017 10th Int. Conf. on Managing Fatigue (San Diego, USA) 27
Recommend
More recommend
