Mental Load and Fatigue Assessment Instruments: A Systematic Review

A Deep Learning Approach for Mental Fatigue State Assessment

This study investigates mental fatigue in sports activities by leveraging deep learning techniques, deviating from the conventional use of heart rate variability (HRV) feature analysis found in previous research. The study utilizes a hybrid deep neural network model, which integrates Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (Bi-LSTM) for feature extraction, and a transformer for feature fusion. The model achieves an impressive accuracy of 95.29% in identifying fatigue from original ECG data, 2D spectral characteristics and physiological information of subjects. In comparison to traditional methods, such as Support Vector Machines (SVMs) and Random Forests (RFs), as well as other deep learning methods, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), the proposed approach demonstrates significantly improved experimental outcomes. Overall, this study offers a promising solution for accurately recognizing fatigue through the analysis of physiological signals, with potential applications in sports and physical fitness training contexts.

The Effects of Mental Fatigue Induced by the Stroop Test on Muscular Endurance Performance and Neuromuscular Activation in Division III Female Athletes

The purpose of this study was to investigate the effect that mental fatigue, as induced by a Stroop test, has on resistance training performance outcomes such as muscular endurance, power output, and neuromuscular activation. Seven female college-aged NCAA Division III student-athletes with at least one year of resistance training experience and were within the 50th percentile for maximal aerobic capacity provided informed consent for participation. During two separate visits, using a within-subject crossover experimental design, subjects completed either the experimental or control condition. Subjects then completed a to-failure leg press test at 50% of their 1-repetition maximum (1RM) followed by an isometric midthigh pull (IMTP) attempt with electromyography (EMG) analysis. The experimental condition consisted of a 30-minute Stroop test, while the control condition consisted of watching 30 minutes of a sitcom. Both activities were completed while cycling at 40% of their aerobic capacity. A NASA Task Load Index (TLX) inventory was administered following the completion of each cycling session to determine the perceived workload and mental fatigue of each activity. While the mentally fatiguing condition was significantly more mentally fatiguing (p = 0.02) than the control condition, mental fatigue did not statistically affect any of the evaluated performance outcomes (p>0.05). These findings suggest that mental fatigue, a common symptom of psychological stress, does not affect resistance-training-related performance outcomes among female athletic populations.

Effects of isolated and combined mental and physical fatigue on motor skill and endurance exercise performance

BACKGROUND

Mental fatigue, elicited by cognitive demands, can impair sport and exercise performance. The effects of isolated mental fatigue on performance are well documented but few studies have explored the effects of combined mental and physical fatigue on skilled motor and endurance exercise performance.

OBJECTIVE

This study explored the effects of isolated mental, isolated physical, and combined (mental plus physical) fatigue on skill and exercise task performance.

METHOD

164 athletes were randomly assigned to 1 of 4 groups: mental fatigue, physical fatigue, combined fatigue, control (no fatigue). Mental fatigue was induced by a 15-min time-load dual-back cognitive task. Physical fatigue was induced by a 90-s burpee exercise task. Next, all participants completed a throwing skill task and performed burpee exercises to failure. Objective (brief Psychomotor Vigilance Task, PVT-B) and subjective (self-report) measures of mental fatigue and Ratings of Perceived Exertion were obtained throughout.

RESULTS

The mental fatigue and combined fatigue groups performed the worst on both the throwing and burpee tasks compared with the physical fatigue and control groups. The former reported higher mental fatigue throughout and had worse response accuracy and variation on the end-of-session PVT-B task. The combined fatigue group performed better than the mental fatigue group on the throwing and burpee tasks.

CONCLUSION

A demanding cognitive task induced a state of mental fatigue and impaired skill and endurance performance. Mental fatigue alone was more detrimental than combined fatigue to skill and endurance performance, suggesting that the physical activity manipulation reduced the negative effects of mental fatigue on performance.

Classification of recovery states in U15, U17, and U19 sub-elite football players: a machine learning approach

Introduction

A promising approach to optimizing recovery in youth football has been the use of machine learning (ML) models to predict recovery states and prevent mental fatigue. This research investigates the application of ML models in classifying male young football players aged under (U)15, U17, and U19 according to their recovery state. Weekly training load data were systematically monitored across three age groups throughout the initial month of the 2019-2020 competitive season, covering 18 training sessions and 120 observation instances. Outfield players were tracked using portable 18-Hz global positioning system (GPS) devices, while heart rate (HR) was measured using 1 Hz telemetry HR bands. The rating of perceived exertion (RPE 6-20) and total quality recovery (TQR 6-20) scores were employed to evaluate perceived exertion, internal training load, and recovery state, respectively. Data preprocessing involved handling missing values, normalization, and feature selection using correlation coefficients and a random forest (RF) classifier. Five ML algorithms [K-nearest neighbors (KNN), extreme gradient boosting (XGBoost), support vector machine (SVM), RF, and decision tree (DT)] were assessed for classification performance. The K-fold method was employed to cross-validate the ML outputs.

Results

A high accuracy for this ML classification model (73-100%) was verified. The feature selection highlighted critical variables, and we implemented the ML algorithms considering a panel of 9 variables (U15, U19, body mass, accelerations, decelerations, training weeks, sprint distance, and RPE). These features were included according to their percentage of importance (3-18%). The results were cross-validated with good accuracy across 5-fold (79%).

Conclusion

The five ML models, in combination with weekly data, demonstrated the efficacy of wearable device-collected features as an efficient combination in predicting football players' recovery states.

Data Mining Paths for Standard Weekly Training Load in Sub-Elite Young Football Players: A Machine Learning Approach

The aim of this study was to test a machine learning (ML) model to predict high-intensity actions and body impacts during youth football training. Sixty under-15, -17, and -19 sub-elite Portuguese football players were monitored over a 6-week period. External training load data were collected from the target variables of accelerations (ACCs), decelerations (DECs), and dynamic stress load (DSL) using an 18 Hz global positioning system (GPS). Additionally, we monitored the perceived exertion and biological characteristics using total quality recovery (TQR), rating of perceived exertion (RPE), session RPE (sRPE), chronological age, maturation offset (MO), and age at peak height velocity (APHV). The ML model was computed by a feature selection process with a linear regression forecast and bootstrap method. The predictive analysis revealed that the players' MO demonstrated varying degrees of effectiveness in predicting their DEC and ACC across different ranges of IQR. After predictive analysis, the following performance values were observed: DEC (x¯predicted = 41, β = 3.24, intercept = 37.0), lower IQR (IQRpredicted = 36.6, β = 3.24, intercept = 37.0), and upper IQR (IQRpredicted = 46 decelerations, β = 3.24, intercept = 37.0). The player's MO also demonstrated the ability to predict their upper IQR (IQRpredicted = 51, β = 3.8, intercept = 40.62), lower IQR (IQRpredicted = 40, β = 3.8, intercept = 40.62), and ACC (x¯predicted = 46 accelerations, β = 3.8, intercept = 40.62). The ML model showed poor performance in predicting the players' ACC and DEC using MO (MSE = 2.47-4.76; RMSE = 1.57-2.18: R2 = -0.78-0.02). Maturational concerns are prevalent in football performance and should be regularly checked, as the current ML model treated MO as the sole variable for ACC, DEC, and DSL. Applying ML models to assess automated tracking data can be an effective strategy, particularly in the context of forecasting peak ACC, DEC, and bodily effects in sub-elite youth football training.

Association of brain-autonomic activities and task accuracy under cognitive load: a pilot study using electroencephalogram, autonomic activity measurements, and arousal level estimated by machine learning

The total amount of mental activity applied to working memory at a given point in time is called cognitive load, which is an important factor in various activities in daily life. We have proposed new feature quantities that reflect the time-series changes in the power of typical frequency bands in electroencephalogram (EEG) for use in examining the relationship between brain activity and behavior under cognitive load. We also measured heart rate variability (HRV) and spontaneous skin conductance responses (SCR) to examine functional associations among brain activity, autonomic activity, and behavior under cognitive load. Additionally, we applied our machine learning model previously developed using EEG to the estimation of arousal level to interpret the brain-autonomic-behavior functional association under cognitive load. Experimental data from 12 healthy undergraduate students showed that participants with higher levels of infra-slow fluctuations of alpha power have more cognitive resources and thus can process information under cognitive load more efficiently. In addition, HRV reflecting parasympathetic activity correlated with task accuracy. The arousal level estimated using our machine learning model showed its robust relationship with EEG. Despite the limitation of the sample size, the results of this pilot study suggest that the information processing efficiency of the brain under cognitive load is reflected by time-series fluctuations in EEG, which are associated with an individual's task performance. These findings can contribute to the evaluation of the internal state of humans associated with cognitive load and the prediction of human behaviors in various situations under cognitive load.

Action-rule-based cognitive control enables efficient execution of stimulus-response conflict tasks: a model validation of Simon task performance

Introduction

The human brain can flexibly modify behavioral rules to optimize task performance (speed and accuracy) by minimizing cognitive load. To show this flexibility, we propose an action-rule-based cognitive control (ARC) model. The ARC model was based on a stochastic framework consistent with an active inference of the free energy principle, combined with schematic brain network systems regulated by the dorsal anterior cingulate cortex (dACC), to develop several hypotheses for demonstrating the validity of the ARC model.

Methods

A step-motion Simon task was developed involving congruence or incongruence between important symbolic information (illustration of a foot labeled "L" or "R," where "L" requests left and "R" requests right foot movement) and irrelevant spatial information (whether the illustration is actually of a left or right foot). We made predictions for behavioral and brain responses to testify to the theoretical predictions.

Results

Task responses combined with event-related deep-brain activity (ER-DBA) measures demonstrated a key contribution of the dACC in this process and provided evidence for the main prediction that the dACC could reduce the Shannon surprise term in the free energy formula by internally reversing the irrelevant rapid anticipatory postural adaptation. We also found sequential effects with modulated dip depths of ER-DBA waveforms that support the prediction that repeated stimuli with the same congruency can promote remodeling of the internal model through the information gain term while counterbalancing the surprise term.

Discussion

Overall, our results were consistent with experimental predictions, which may support the validity of the ARC model. The sequential effect accompanied by dip modulation of ER-DBA waveforms suggests that cognitive cost is saved while maintaining cognitive performance in accordance with the framework of the ARC based on 1-bit congruency-dependent selective control.

Measurement properties of instruments to measure the fatigue domain of vitality capacity in community-dwelling older people: an umbrella review of systematic reviews and meta-analysis

BACKGROUND

Vitality capacity (VC) is a key domain of intrinsic capacity (IC) and is the underlying biophysiological aspect of IC. Energy and metabolism (E&M) is one of the domains of VC. Fatigue is one of the main characteristics of E&M.

OBJECTIVE

The aims of this umbrella review are (i) to identify the available instruments suitable for measuring fatigue in community-dwelling older adults and (ii) to critically review the measurement properties of the identified instruments.

DESIGN

Umbrella review.

SETTING

Healthcare.

SUBJECTS

Community-dwelling older adults.

METHODS

PubMed and Web of Knowledge were systematically screened for systematic reviews and meta-analysis reporting on fatigue instruments resulting in 2,263 articles (last search 5 December 2022). The COSMIN checklist was used to appraise psychometric properties and the AMSTAR for assessing methodological quality. Data on fatigue instruments, construct, reference period, assessment method, validated population, reliability, validity, responsiveness and predictive validity on negative health outcomes were extracted.

RESULTS

10 systematic reviews and 1 meta-analysis were included in this study. 70 fatigue instruments were identified in the literature and 21 were originally designed for fatigue. The Fatigue Severity Scale (FSS), Pittsburgh Fatigability Scale (PFS) and Visual Analogue scale (VAS-F), Fatigue Impact Scale (FIS) and the Functional Assessment of Chronic Illness Therapy Fatigue (FACIT-F) presented good psychometric properties.

CONCLUSIONS

The FSS, FIS, FACIT-F, PFS and the VAS-F presented good psychometric properties in various conditions. Therefore, these instruments could be used to quantify trajectories in the domain E&M in the context of VC in community-dwelling older adults.

Self-regulation learning as active inference: dynamic causal modeling of an fMRI neurofeedback task

Introduction

Learning to self-regulate brain activity by neurofeedback has been shown to lead to changes in the brain and behavior, with beneficial clinical and non-clinical outcomes. Neurofeedback uses a brain-computer interface to guide participants to change some feature of their brain activity. However, the neural mechanism of self-regulation learning remains unclear, with only 50% of the participants succeeding in achieving it. To bridge this knowledge gap, our study delves into the neural mechanisms of self-regulation learning via neurofeedback and investigates the brain processes associated with successful brain self-regulation.

Methods

We study the neural underpinnings of self-regulation learning by employing dynamical causal modeling (DCM) in conjunction with real-time functional MRI data. The study involved a cohort of 18 participants undergoing neurofeedback training targeting the supplementary motor area. A critical focus was the comparison between top-down hierarchical connectivity models proposed by Active Inference and alternative bottom-up connectivity models like reinforcement learning.

Results

Our analysis revealed a crucial distinction in brain connectivity patterns between successful and non-successful learners. Particularly, successful learners evinced a significantly stronger top-down effective connectivity towards the target area implicated in self-regulation. This heightened top-down network engagement closely resembles the patterns observed in goal-oriented and cognitive control studies, shedding light on the intricate cognitive processes intertwined with self-regulation learning.

Discussion

The findings from our investigation underscore the significance of cognitive mechanisms in the process of self-regulation learning through neurofeedback. The observed stronger top-down effective connectivity in successful learners indicates the involvement of hierarchical cognitive control, which aligns with the tenets of Active Inference. This study contributes to a deeper understanding of the neural dynamics behind successful self-regulation learning and provides insights into the potential cognitive architecture underpinning this process.

Mental Fatigue Is Associated with Subjective Cognitive Decline among Older Adults

Both Subjective Cognitive Decline (SCD) and mental fatigue are becoming increasingly prevalent as global demographics shifts indicate our aging populations. SCD is a reversible precursor for Alzheimer's disease, and early identification is important for effective intervention strategies. We aim to investigate the association between mental fatigue-as well as other factors-and SCD. A total of 707 old adults (aged from 60 to 99) from Shanghai, China, participated in this study and completed self-reported instruments covering their cognitive and mental status as well as demographic information. Mental fatigue status was assessed by using four items derived from the functional impairment syndrome of the Old Adult Self Report (OASR). SCD was assessed by using the Memory/Cognition syndrome of OASR. A total of 681 old adults were included in the current study. The means of SCD significantly differed between each group of factors (age, gender, and mental fatigue). The general linear regression models showed that SCD increased with age, females scored higher than males, and SCD was positively associated with mental fatigue factors including difficulty getting things done, poor task performance, sleeping more, and a lack of energy among old adults. The study also found that SCD is negatively associated with the high-income group among young-old (aged from 60 to 75) males and associated with good marital/living status with the companion of spouses/partners among young-old females. These results suggest that gender, income level, marital/living status, and mental fatigue are crucial factors in preventing SCD among old adults and are pivotal in developing early intervention strategies to preserve the mental health of an increasingly aging population.

Influence of Scoring Systems on Mental Fatigue, Physical Demands, and Tactical Behavior during Soccer Large-Sided Games

Constraints are common in soccer training to develop physical, technical-tactical, and mental training concurrently. This study examined how different scoring systems influence physical, tactical, and mental demands during large-sided games in soccer. Eighteen youth-elite male (17.39 ± 1.04 y) soccer players completed three 8 vs. 8 large-sided games where the different score systems were i) official score system (OSS; i.e., 1 goal = 1 goal), ii) double the value of the goal-4 min (DVx4; i.e., 1 goal = 1 goal from 0.00 to 7.59 min, and 1 goal = 2 goals from 8.00 to 12.00 min), and iii) double the value of the goal-8 min (DVx8; i.e., 1 goal = 1 goal from 0.00 to 3.59 min, and 1 goal = 2 goals from 4.00 to 12.00 min). Physical demands and tactical behaviors were recorded during tasks using a global positioning system and video camera. Mental fatigue was recorded pre- and post-task using a visual analogue scale. Also, the ratio of perceived exertion and mental load were recorded after tasks were finished. Results reported the highest values of mental and physical demands in DVx4. Mental fatigue increased during all three large-sided games, although this increase was significantly higher in DVx4 compared with OSS (p = 0.006) and DVx8 (p = 0.027). Tactical behavior showed a trend towards more direct play during DVx4, which was less observed during DVx8, and not at all during OSS. In conclusion, changing the scoring system affects physical, tactical, and mental demands.

[Asthenia, mental fatigue and cognitive dysfunction]

Conditions associated with asthenia are usually characterized by increased fatigue, impaired activities of daily living and decreased productivity. In clinical practice it is important to distinguish between idiopathic chronic fatigue (primary or functional asthenia) and chronic fatigue syndrome (CFS). Fatigue can also be classified by neuromuscular and/or cognitive and mental fatigue. The article discusses the neuroanatomical basis and focuses on the neurocognitive theory of pathological fatigue. In addition the relationship between mental stress, fatigue and cognitive impairments such as subjective cognitive impairment (SCI) and mild cognitive impairment (MCI) are also discussed. We discuss the rationale that for treatment of asthenic conditions accompanied by cognitive dysfunction it is justified to use combination therapy - fonturacetam and a preparation containing nicotinoyl-GABA and Ginkgo Biloba.

Gender differences in professional drivers’ fatigue level measured with BAlert mobile app: A psychophysiological, time efficient, accessible, and innovative approach to fatigue management

Addressing fatigue is useful in a variety of scenarios and activities. Fatigue has recently been studied from a psychophysiological standpoint. As a result, the expression and impact of peripheral and central fatigue has been evaluated. Driving is one occupation where tiredness has disastrous consequences. BAlert is a smartphone app that approaches exhaustion with psychophysiological measures. More specifically, it evaluates the level of fatigue via heart rate variability (HRV) data and the cognitive compromise via Stroop effect. The goal of this study is to determine if there are gender differences in fatigue levels among professional drivers using the BAlert app. Statistically significant differences were found in the number of hours awake, in different parameters of HRV (AVNN, PNN50, RMSSD, and SDNN), in the level of stress, as well as in the cognitive response evaluated through the app. The results are discussed and their implications for the management of work fatigue are presented.

Automatic Cognitive Fatigue Detection Using Wearable fNIRS and Machine Learning

Wearable sensors have increasingly been applied in healthcare to generate data and monitor patients unobtrusively. Their application for Brain-Computer Interfaces (BCI) allows for unobtrusively monitoring one's cognitive state over time. A particular state relevant in multiple domains is cognitive fatigue, which may impact performance and attention, among other capabilities. The monitoring of this state will be applied in real learning settings to detect and advise on effective break periods. In this study, two functional near-infrared spectroscopy (fNIRS) wearable devices were employed to build a BCI to automatically detect the state of cognitive fatigue using machine learning algorithms. An experimental procedure was developed to effectively induce cognitive fatigue that included a close-to-real digital lesson and two standard cognitive tasks: Corsi-Block task and a concentration task. Machine learning models were user-tuned to account for the individual dynamics of each participant, reaching classification accuracy scores of around 70.91 ± 13.67 %. We concluded that, although effective for some subjects, the methodology needs to be individually validated before being applied. Moreover, time on task was not a particularly determining factor for classification, i.e., to induce cognitive fatigue. Further research will include other physiological signals and human-computer interaction variables.