暂无摘要。

OBJECTIVE: This study proposed a moving average (MA) approach to dynamically process heart rate variability (HRV) and developed aberrant driving behavior (ADB) prediction models by using long short-term memory (LSTM) networks.
BACKGROUND: Fatigue-associated ADBs have traffic safety implications. Numerous models to predict such acts based on physiological responses have been developed but are still in embryonic stages.
METHODS: This study recorded the data of 20 commercial bus drivers during their routine tasks on four consecutive days and subsequently asked them to complete questionnaires, including subjective sleep quality, driver behavior questionnaire and the Karolinska Sleepiness Scale. Driving behaviors and corresponding HRV were determined using a navigational mobile application and a wristwatch. The dynamic-weighted MA (DWMA) and exponential-weighted MA were used to process HRV in 5-min intervals. The data were independently separated for training and testing. Models were trained with 10-fold cross-validation strategy, their accuracies were evaluated, and Shapley additive explanation (SHAP) values were used to determine feature importance.
RESULTS: Significant increases in the standard deviation of NN intervals (SDNN), root mean square of successive heartbeat interval differences (RMSSD), and normalized spectrum of high frequency (nHF) were observed in the pre-event stage. The DWMA-based model exhibited the highest accuracy for both driver types (urban: 84.41%; highway: 80.56%). The SDNN, RMSSD, and nHF demonstrated relatively high SHAP values.
CONCLUSIONS: HRV metrics can serve as indicators of mental fatigue. DWMA-based LSTM could predict the occurrence of the level of fatigue associated with ADBs.
CONCLUSIONS: The established models can be used in realistic driving scenarios.

OBJECTIVE: To assess the objectivity of measuring the level of sleepiness in the subjects using a monotonous psychomotor bimanual tapping test developed by us, performed on mobile devices running Android OS.
METHODS: Four hundred and ninety-four hour-long experiments with the performance of a psychomotor test were conducted on 102 students. Using the method of mixed linear models, correlations between the levels of sleepiness according to the Karolinska Sleepiness Scale (KSS) and the Epworth Sleepiness Scale (ESS) and the behavioral indicators of the test were evaluated.
RESULTS: Statistically significant correlations between the increase in KSS scores and such indicators as a decrease in the total number of button taps and an increase in the frequency of «microsleep» episodes are shown. Statistically significant correlations of ESS score characteristics with the behavioral indicators of the test were not found.
CONCLUSIONS: A large statistical material shows a reliable correlation of the parameters of the psychomotor test with the level of sleepiness on the Karolinska scale, which allows using the mobile application developed by us to determine the current level of sleepiness /alertness in the field.
UNASSIGNED: Оценка объективности измерения уровня сонливости у испытуемых при помощи разработанного монотонного психомоторного бимануального тэппинг-теста, выполняемого на мобильных устройствах под ОС Android.
UNASSIGNED: На 102 студентах проведено 494 часовых эксперимента с выполнением психомоторного теста. С помощью метода смешанных линейных моделей оценивали корреляции между уровнями сонливости по Каролинской шкале сонливости (KSS) и Эпвортской шкале сонливости (ESS) и поведенческими показателями теста.
UNASSIGNED: Показаны статистически значимые взаимосвязи между увеличением баллов по KSS и такими показателями, как снижение общего количества нажатий на кнопку и увеличение частоты эпизодов «микросна». Статистически значимых взаимосвязей балльных характеристик ESS с поведенческими показателями теста не выявлено.
UNASSIGNED: На большом статистическом материале показана достоверная корреляция параметров психомоторного теста с уровнем сонливости по KSS, что позволяет использовать разработанное мобильное приложение для определения текущего уровня сонливости/бдительности в полевых условиях.

Objectives. Current approaches via physiological features detecting aberrant driving behaviour (ADB), including speeding, abrupt steering, hard braking and aggressive acceleration, are developing. This study proposes using machine learning approaches incorporating heart rate variability (HRV) parameters to predict ADB occurrence. Methods. Naturalistic driving data of 10 highway bus drivers in Taiwan from their daily routes were collected for 4 consecutive days. Their driving behaviours and physiological data during a driving task were determined using a navigation mobile application and heart rate watch. Participants\' self-reported data on sleep, driving-related experience, open-source data on weather and the traffic congestion level were obtained. Five machine learning models - logistic regression, random forest, naive Bayes, support vector machine and gated recurrent unit (GRU) - were employed to predict ADBs. Results. Most drivers with ADB had low sleep efficiency (≤80%), with significantly higher scores in driver behaviour questionnaire subcategories of lapses and errors and in the Karolinska sleepiness scale than those without ADBs. Moreover, HRV parameters were significantly different between baseline and pre-ADB event measurements. GRU had the highest accuracy (81.16-84.22%). Conclusions. Sleep deficit may be related to the increased fatigue level and ADB occurrence predicted from HRV-based models among bus drivers.

There are substantial individual differences (resilience and vulnerability) in performance resulting from sleep loss and psychosocial stress, but predictive potential biomarkers remain elusive. Similarly, marked changes in the cardiovascular system from sleep loss and stress include an increased risk for cardiovascular disease. It remains unknown whether key hemodynamic markers, including left ventricular ejection time (LVET), stroke volume (SV), heart rate (HR), cardiac index (CI), blood pressure (BP), and systemic vascular resistance index (SVRI), differ in resilient vs. vulnerable individuals and predict differential performance resilience with sleep loss and stress. We investigated for the first time whether the combination of total sleep deprivation (TSD) and psychological stress affected a comprehensive set of hemodynamic measures in healthy adults, and whether these measures differentiated neurobehavioral performance in resilient and vulnerable individuals. Thirty-two healthy adults (ages 27-53; 14 females) participated in a 5-day experiment in the Human Exploration Research Analog (HERA), a high-fidelity National Aeronautics and Space Administration (NASA) space analog isolation facility, consisting of two baseline nights, 39 h TSD, and two recovery nights. A modified Trier Social Stress Test induced psychological stress during TSD. Cardiovascular measure collection [SV, HR, CI, LVET, BP, and SVRI] and neurobehavioral performance testing (including a behavioral attention task and a rating of subjective sleepiness) occurred at six and 11 timepoints, respectively. Individuals with longer pre-study LVET (determined by a median split on pre-study LVET) tended to have poorer performance during TSD and stress. Resilient and vulnerable groups (determined by a median split on average TSD performance) showed significantly different profiles of SV, HR, CI, and LVET. Importantly, LVET at pre-study, but not other hemodynamic measures, reliably differentiated neurobehavioral performance during TSD and stress, and therefore may be a biomarker. Future studies should investigate whether the non-invasive marker, LVET, determines risk for adverse health outcomes.

BACKGROUND: Mental fatigue is usually accompanied by a sense of weariness, reduced alertness, and reduced mental performance, which can lead to accidents, decrease of productivity in workplace and several other health hazards.
OBJECTIVE: The aim of this study was to assess mental fatigue of students while reading for a prolonged duration of time by application of electroencephalography (EEG).
METHODS: Ten healthy students (27.57±3.4 years; 5 females and 5 males), participated in the study. The experimental design consisted of 5 blocks of 15-min length, in total 75 min for each participant. The experiment was done without any reading activities at the first block. In the following, participants studied the texts and corrected the mistakes. In each block EEG (beta, alpha, and theta power), and the Karolinska Sleepiness Scale (KSS) were recorded.
RESULTS: The mean of the self-assessment of sleepiness by KSS from the first to final 15 minutes were 2.3, 3.4, 4.3, 5.2, and 6.1, respectively. The average power in the theta band decreased from 1.23μV2/Hz at the first 15-min period to 1.02μV2/Hz at the last 15-min period. Also, mean power in the alpha band decreased from 0.85μV2/Hz at the first 15-min period to 0.59μV2/Hz at the last 15-min period.
CONCLUSIONS: The study showed that the KSS and EEG activity indicate sleepiness which were highly correlated, with both changing along with performance.

Cortisol and C-reactive protein (CRP) typically change during total sleep deprivation (TSD) and psychological stress; however, it remains unknown whether these biological markers can differentiate robust individual differences in neurobehavioral performance and self-rated sleepiness resulting from these stressors. Additionally, little is known about cortisol and CRP recovery after TSD. In our study, 32 healthy adults (ages 27-53; mean ± SD, 35.1 ± 7.1 years; 14 females) participated in a highly controlled 5-day experiment in the Human Exploration Research Analog (HERA), a high-fidelity National Aeronautics and Space Administration (NASA) space analog isolation facility, consisting of two baseline nights, 39 h TSD, and two recovery nights. Psychological stress was induced by a modified Trier Social Stress Test (TSST) on the afternoon of TSD. Salivary cortisol and plasma CRP were obtained at six time points, before (pre-study), during [baseline, the morning of TSD (TSD AM), the afternoon of TSD (TSD PM), and recovery], and after (post-study) the experiment. A neurobehavioral test battery, including measures of behavioral attention and cognitive throughput, and a self-report measure of sleepiness, was administered 11 times. Resilient and vulnerable groups were defined by a median split on the average TSD performance or sleepiness score. Low and high pre-study cortisol and CRP were defined by a median split on respective values at pre-study. Cortisol and CRP both changed significantly across the study, with cortisol, but not CRP, increasing during TSD. During recovery, cortisol levels did not return to pre-TSD levels, whereas CRP levels did not differ from baseline. When sex was added as a between-subject factor, the time × sex interaction was significant for cortisol. Resilient and vulnerable groups did not differ in cortisol and CRP, and low and high pre-study cortisol/CRP groups did not differ on performance tasks or self-reported sleepiness. Thus, both cortisol and CRP reliably changed in a normal, healthy population as a result of sleep loss; however, cortisol and CRP were not markers of neurobehavioral resilience to TSD and stress in this study.

Sleepy drivers have problems with keeping the vehicle within the lines, and might often need to apply a sudden or hard corrective steering wheel movement. Such movements, if they occur while driving on a slippery road, might increase the risk of ending off road due to the unforgiving nature of slippery roads. We tested this hypothesis. Twelve young men participated in a driving simulator experiment with two counterbalanced conditions; dry versus slippery road × day (alert) versus night (sleepy) driving. The participants drove 52.5 km on a monotonous two-lane highway and rated their sleepiness seven times using the Karolinska Sleepiness Scale. Blink durations were extracted from an electrooculogram. The standard deviation of lateral position and the smoothness of steering events were measures of driving performance. Each outcome variable was analysed with mixed-effect models with road condition, time-of-day and time-on-task as predictors. The Karolinska Sleepiness Scale increased with time-on-task (p < 0.001) and was higher during night drives (p < 0.001), with a three-way interaction suggesting a small increased sleepiness with driving time at night with slippery road conditions (p = 0.012). Blink durations increased with time-on-task (p < 0.01) with an interaction between time-of-day and road condition (p = 0.040) such that physiological sleepiness was lower for sleep-deprived participants in demanding road conditions. The standard deviation of lateral position increased with time-on-task (p = 0.026); however, during night driving it was lower on a slippery road (p = 0.025). The results indicate that driving in demanding road condition (i.e. slippery road) might further exhaust already sleepy drivers, although this is not clearly reflected in driving performance.

OBJECTIVE: Although trait-like individual differences in subjective responses to sleep restriction (SR) and total sleep deprivation (TSD) exist, reliable characterizations remain elusive. We comprehensively compared multiple methods for defining resilience and vulnerability by subjective metrics.
METHODS: 41 adults participated in a 13-day experiment:2 baseline, 5 SR, 4 recovery, and one 36h TSD night. The Karolinska Sleepiness Scale (KSS) and the Profile of Mood States Fatigue (POMS-F) and Vigor (POMS-V) were administered every 2h. Three approaches (Raw Score [average SR score], Change from Baseline [average SR minus average baseline score], and Variance [intraindividual SR score variance]), and six thresholds (±1 standard deviation, and the highest/lowest scoring 12.5%, 20%, 25%, 33%, 50%) categorized Resilient/Vulnerable groups. Kendall\'s tau-b correlations compared the group categorization\'s concordance within and between KSS, POMS-F, and POMS-V scores. Bias-corrected and accelerated bootstrapped t-tests compared group scores.
RESULTS: There were significant correlations between all approaches at all thresholds for POMS-F, between Raw Score and Change from Baseline approaches for KSS, and between Raw Score and Variance approaches for POMS-V. All Resilient groups defined by the Raw Score approach had significantly better scores throughout the study, notably including during baseline and recovery, whereas the two other approaches differed by measure, threshold, or day. Between-measure correlations varied in strength by measure, approach, or threshold.
CONCLUSIONS: Only the Raw Score approach consistently distinguished Resilient/Vulnerable groups at baseline, during sleep loss, and during recovery‒‒we recommend this approach as an effective method for subjective resilience/vulnerability categorization. All approaches created comparable categorizations for fatigue, some were comparable for sleepiness, and none were comparable for vigor. Fatigue and vigor captured resilience/vulnerability similarly to sleepiness but not each other.

In shift work settings and on-call operations, workers may be at risk of sleep inertia when called to action immediately after awakening from sleep. However, individuals may differ substantially in their susceptibility to sleep inertia. We investigated this using data from a laboratory study in which 20 healthy young adults were each exposed to 36 h of total sleep deprivation, preceded by a baseline sleep period and followed by a recovery sleep period, on three separate occasions. In the week prior to each laboratory session and on the corresponding baseline night in the laboratory, participants either extended their sleep period to 12 h/day or restricted it to 6 h/day. During periods of wakefulness in the laboratory, starting right after scheduled awakening, participants completed neurobehavioral tests every 2 h. Testing included the Karolinska Sleepiness Scale to measure subjective sleepiness, for which the data were analyzed with nonlinear mixed-effects regression to quantify sleep inertia. This revealed considerable interindividual differences in the magnitude of sleep inertia, which were highly stable within individuals after both baseline and recovery sleep periods, regardless of study condition. Our results demonstrate that interindividual differences in subjective sleepiness due to sleep inertia are substantial and constitute a trait.