Fatigue Monitoring Through Wearables: A State-of-the-Art Review

Wrist-Worn and Arm-Worn Wearables for Monitoring Heart Rate During Sedentary and Light-to-Vigorous Physical Activities: Device Validation Study

Background

Heart rate (HR) is a vital physiological parameter, serving as an indicator of homeostasis and a key metric for monitoring cardiovascular health and physiological responses. Wearable devices using photoplethysmography (PPG) technology provide noninvasive HR monitoring in real-life settings, but their performance may vary due to factors such as wearing position, blood flow, motion, and device updates. Therefore, ongoing validation of their accuracy and reliability across different activities is essential.

objectives

This study aimed to assess the accuracy and reliability of the HR measurement from the PPG-based Polar Verity Sense and the Polar Vantage V2 devices across a range of physical activities and intensities as well as wearing positions (ie, upper arm, forearm, and both wrists).

Methods

Sixteen healthy participants were recruited to participate in this study protocol, which involved 9 activities of varying intensities, ranging from lying down to high-intensity interval training, each repeated twice. The HR measurements from the Verity Sense and Vantage V2 were compared with the criterion measure Polar H10 electrocardiogram (ECG) chest strap. The data were processed to eliminate artifacts and outliers. Accuracy and reliability were assessed using multiple statistical methods, including systematic bias (mean of differences), mean absolute error (MAE) and mean absolute percentage error (MAPE), Pearson product moment correlation coefficient (r), Lin concordance correlation coefficient (CCC), and within-subject coefficient of variation (WSCV).

Results

All 16 participants (female=7; male=9; mean 27.4, SD 5.8 years) completed the study. The Verity Sense, worn on the upper arm, demonstrated excellent accuracy across most activities, with a systematic bias of -0.05 bpm, MAE of 1.43 bpm, MAPE of 1.35%, r=1.00, and CCC=1.00. It also demonstrated high reliability across all activities with a WSCV of 2.57% and no significant differences between the 2 sessions. The wrist-worn Vantage V2 demonstrated moderate accuracy with a slight overestimation compared with the ECG and considerable variation in accuracy depending on the activity. For the nondominant wrist, it demonstrated a systematic bias of 2.56 bpm, MAE of 6.41 bpm, MAPE 6.82%, r=0.93, and CCC=0.92. Reliability varied considerably, ranging from a WSCV of 3.64% during postexercise sitting to 23.03% during lying down.

Conclusions

The Verity Sense was found to be highly accurate and reliable, outperforming many other wearable HR devices and establishing itself as a strong alternative to ECG-based chest straps, especially when worn on the upper arm. The Vantage V2 was found to have moderate accuracy, with performance highly dependent on activity type and intensity. While it exhibited greater variability and limitations at lower HR, it performed better at higher intensities and outperformed several wrist-worn devices from previous research, particularly during vigorous activities. These findings highlight the importance of device selection and wearing position to ensure the highest possible accuracy in the intended context.

Biosensors in wearable medical devices: Regulatory framework and compliance across US, EU, and Indian markets

Biosensors play a crucial role in the diagnosis and monitoring of diseases as therapeutic applications that come with ease through incorporation and collaboration with wearable medical devices. Various regulatory markets are implementing development and management strategies for this emerging medical device field. This paper provides regulatory navigation of biosensors in wearable diagnostic devices across the US, EU, and Indian markets. The regulatory structure of all three countries differs from their origination and management which is discussed in this article along with the regulatory requirements applicable to such devices. The study also focuses on areas such as Good Manufacturing Practices (GMP), risk-based device classification, validation, and post-market surveillance. Key highlights include understanding regulatory authorities, guidelines, rules, regulations, and standards; comparison of regulatory perspectives between the three markets; application of biosensors in medical devices; prospects and market size. The study identifies approval pathways, regulatory challenges, and harmonization efforts across the globe. The paper explores recent advancements in biosensors for health interventions, such as personalized medicine, collaboration with the IoT, biomedical applications, and their accessibility.

Technology for measuring freezing of gait: Current state of the art and recommendations

This report summarizes the existing literature on the use of technology for the assessment of freezing of gait (FOG) as well as the use of technology to provide insights into the mechanisms of FOG in people with Parkinson's disease. Specifically, this work was carried out for the 3rd International Workshop on Freezing of Gait in Jerusalem in 2023. This review focuses on the most used technologies to quantitatively assess FOG in a laboratory environment and describes the technologies that hold promise for assessing FOG in daily life. Examples of implementation of machine learning algorithms are provided as well as algorithmic biases. Lastly, a standardized assessment using inertial measurement units during a clinical protocol is proposed and a 5-year outlook is discussed. We anticipate this review will help move the field forward in the coming years.

Explicit metrics for implicit emotions: investigating physiological and gaze indices of learner emotions

Learning experiences are intertwined with emotions, which in turn have a significant effect on learning outcomes. Therefore, digital learning environments can benefit from taking the emotional state of the learner into account. To do so, the first step is real-time emotion detection which is made possible by sensors that can continuously collect physiological and eye-tracking data. In this paper, we aimed to find features derived from skin conductance, skin temperature, and eye movements that could be used as indicators of learner emotions. Forty-four university students completed different math related tasks during which sensor data and self-reported data on the learner's emotional state were collected. Results indicate that skin conductance response peak count, tonic skin conductance, fixation count, duration and dispersion, saccade count, duration and amplitude, and blink count and duration may be used to distinguish between different emotions. These features may be used to make learning environments more emotionally aware.

Latent Space Representation of Human Movement: Assessing the Effects of Fatigue

Fatigue plays a critical role in sports science, significantly affecting recovery, training effectiveness, and overall athletic performance. Understanding and predicting fatigue is essential to optimize training, prevent overtraining, and minimize the risk of injuries. The aim of this study is to leverage Human Activity Recognition (HAR) through deep learning methods for dimensionality reduction. The use of Adversarial AutoEncoders (AAEs) is explored to assess and visualize fatigue in a two-dimensional latent space, focusing on both semi-supervised and conditional approaches. By transforming complex time-series data into this latent space, the objective is to evaluate motor changes associated with fatigue within the participants' motor control by analyzing shifts in the distribution of data points and providing a visual representation of these effects. It is hypothesized that increased fatigue will cause significant changes in point distribution, which will be analyzed using clustering techniques to identify fatigue-related patterns. The data were collected using a Wii Balance Board and three Inertial Measurement Units, which were placed on the hip and both forearms (distal part, close to the wrist) to capture dynamic and kinematic information. The participants followed a fatigue-inducing protocol that involved repeating sets of 10 repetitions of four different exercises (Squat, Right Lunge, Left Lunge, and Plank Jump) until exhaustion. Our findings indicate that the AAE models are effective in reducing data dimensionality, allowing for the visualization of fatigue's impact within a 2D latent space. The latent space representation provides insights into motor control variations, revealing patterns that can be used to monitor fatigue levels and optimize training or rehabilitation programs.

Data-driven natural computational psychophysiology in class

Objective. The assessment of mental fatigue (MF) and attention span in educational and healthcare settings frequently relies on subjective scales or methods such as induced-task interruption tools. However, these approaches are deficient in real-time evaluation and dynamic definitions. To address this gap, this paper proposes a Continuous Quantitative Scale (CQS) that allows for the natural and real-time measurement of MF based on group-synchronized electroencephalogram (EEG) data. Approach. In this study, computational psychophysiology was used to measure MF scores during a realistic class. Our methodology continuously monitored participants' psychological states without interrupting their regular routines, providing an objective evaluation. By analyzing multi-subject brain-computer interface (mBCI) data with a collaborative computing approach, the group-synchronized data were obtained from 10 healthy participants to assess MF levels. Each participant wore an EEG headset for only 10 min of preparation before performing a sustained task for 80 min. Main results. Our findings indicate that a lecture duration of 18.9 min is most effective, while a duration of 43.1 min leads to heightened MF levels. By focusing on the group-level simultaneous data analysis, the effects of individual variability were mitigated and the efficiency of cognitive computing was improved. From the perspective of a neurocomputational measure, these results confirm previous research. Significance. The proposed CQS provides a reliable, objective, memory- and emotion-free approach to the assessment of MF and attention span. These findings have significant implications not only for education, but also for the study of group cognitive mechanisms and for improving the quality of mental healthcare.

Artificial Intelligence-Driven Approaches to Managing Surgeon Fatigue and Improving Performance

Surgeon fatigue significantly affects cognitive and motor functions, increasing the risk of errors and adverse patient outcomes. Traditional fatigue management methods, such as structured breaks and duty-hour limits, are insufficient for real-time fatigue detection in high-stakes surgeries. With advancements in artificial intelligence (AI), there is growing potential for AI-driven technologies to address this issue through continuous monitoring and adaptive interventions. This paper explores how AI, via machine learning algorithms, wearable devices, and real-time feedback systems, enables comprehensive fatigue detection by analysing physiological, behavioural, and environmental data. Techniques such as heart rate variability analysis, electroencephalogram monitoring, and computer vision-based behavioural analysis are examined, as well as predictive models that provide proactive solutions. These AI-driven systems could suggest personalized break schedules, task redistribution, and interface adaptations in response to real-time fatigue indicators, potentially enhancing surgical safety and precision. However, ethical challenges, including data privacy and surgeon autonomy, must be carefully navigated to foster acceptance and integration within clinical settings. This review highlights AI's transformative potential in optimizing fatigue management and improving overall outcomes in the operating room​​​​​.

Classification of Breathing Phase and Path with In-Ear Microphones

In recent years, the use of smart in-ear devices (hearables) for health monitoring has gained popularity. Previous research on in-ear breath monitoring with hearables uses signal processing techniques based on peak detection. Such techniques are greatly affected by movement artifacts and other challenging real-world conditions. In this study, we use an existing database of various breathing types captured using an in-ear microphone to classify breathing path and phase. Having a small dataset, we use XGBoost, a simple and fast classifier, to address three different classification challenges. We achieve an accuracy of 86.8% for a binary path classifier, 74.1% for a binary phase classifier, and 67.2% for a four-class path and phase classifier. Our path classifier outperforms existing algorithms in recall and F1, highlighting the reliability of our approach. This work demonstrates the feasibility of the use of hearables in continuous breath monitoring tasks with machine learning.

Raw Photoplethysmography as an Enhancement for Research-Grade Wearable Activity Monitors

Wearable monitors continue to play a critical role in scientific assessments of physical activity. Recently, research-grade monitors have begun providing raw data from photoplethysmography (PPG) alongside standard raw data from inertial sensors (accelerometers and gyroscopes). Raw PPG enables granular and transparent estimation of cardiovascular parameters such as heart rate, thus presenting a valuable alternative to standard PPG methodologies (most of which rely on consumer-grade monitors that provide only coarse output from proprietary algorithms). The implications for physical activity assessment are tremendous, since it is now feasible to monitor granular and concurrent trends in both movement and cardiovascular physiology using a single noninvasive device. However, new users must also be aware of challenges and limitations that accompany the use of raw PPG data. This viewpoint paper therefore orients new users to the opportunities and challenges of raw PPG data by presenting its mechanics, pitfalls, and availability, as well as its parallels and synergies with inertial sensors. This includes discussion of specific applications to the prediction of energy expenditure, activity type, and 24-hour movement behaviors, with an emphasis on areas in which raw PPG data may help resolve known issues with inertial sensing (eg, measurement during cycling activities). We also discuss how the impact of raw PPG data can be maximized through the use of open-source tools when developing and disseminating new methods, similar to current standards for raw accelerometer and gyroscope data. Collectively, our comments show the strong potential of raw PPG data to enhance the use of research-grade wearable activity monitors in science over the coming years.

Evaluation of sweat-based biomarkers using wearable biosensors for monitoring stress and fatigue: a systematic review

Objectives. This systematic review aims to report the evaluation of wearable biosensors for the real-time measurement of stress and fatigue using sweat biomarkers. Methods. A thorough search of the literature was carried out in databases such as PubMed, Web of Science and IEEE. A three-step approach for selecting research articles was developed and implemented. Results. Based on a systematic search, a total of 17 articles were included in this review. Lactate, cortisol, glucose and electrolytes were identified as sweat biomarkers. Sweat-based biomarkers are frequently monitored in real time using potentiometric and amperometric biosensors. Wearable biosensors such as an epidermal patch or a sweatband have been widely validated in scientific literature. Conclusions. Sweat is an important biofluid for monitoring general health, including stress and fatigue. It is becoming increasingly common to use biosensors that can measure a wide range of sweat biomarkers to detect fatigue during high-intensity work. Even though wearable biosensors have been validated for monitoring various sweat biomarkers, such biomarkers can only be used to assess stress and fatigue indirectly. In general, this study may serve as a driving force for academics and practitioners to broaden the use of wearable biosensors for the real-time assessment of stress and fatigue.

Wireless ear EEG to monitor drowsiness

Neural wearables can enable life-saving drowsiness and health monitoring for pilots and drivers. While existing in-cabin sensors may provide alerts, wearables can enable monitoring across more environments. Current neural wearables are promising but most require wet-electrodes and bulky electronics. This work showcases in-ear, dry-electrode earpieces used to monitor drowsiness with compact hardware. The employed system integrates additive-manufacturing for dry, user-generic earpieces, existing wireless electronics, and offline classification algorithms. Thirty-five hours of electrophysiological data were recorded across nine subjects performing drowsiness-inducing tasks. Three classifier models were trained with user-specific, leave-one-trial-out, and leave-one-user-out splits. The support-vector-machine classifier achieved an accuracy of 93.2% while evaluating users it has seen before and 93.3% when evaluating a never-before-seen user. These results demonstrate wireless, dry, user-generic earpieces used to classify drowsiness with comparable accuracies to existing state-of-the-art, wet electrode in-ear and scalp systems. Further, this work illustrates the feasibility of population-trained classification in future electrophysiological applications.

The human-factors' challenges of (tele)drivers of Autonomous Vehicles

Autonomous capabilities, including Autonomous Vehicle (AV) technology, aim to reduce human effort, extend capabilities, and enhance safety. While AVs offer societal benefits, human intervention remains necessary, especially in complex situations. As communication technology advances, human intervention is possible from remote sites. In such remote locations, highly skilled tele-drivers (TEDs) are ready to face situations too complicated for the AV. However, current work still needs a comprehensive mapping of the challenges that TEDs would face. Some of these challenges are shared with IVDs but may have stronger or weaker effects on the remote driver's ability to maintain safety. Other challenges, such as limited situational awareness of the road scene, the indirect experience of vehicle motion, and communication latency, are unique to TEDs. We assess the challenges, comparing their impact on TEDs versus IVDs, and explore technological countermeasures aimed at mitigating specific challenges encountered by TEDs. Lastly, we identified knowledge gaps and areas lacking understanding in the literature, highlighting avenues for future research and practical implications for practitioners.

Detection of driver drowsiness level using a hybrid learning model based on ECG signals

OBJECTIVES

Fatigue has a considerable impact on the driver's vehicle and even the driver's own operating ability.

METHODS

An intelligent algorithm is proposed for the problem that it is difficult to classify the degree of drowsiness generated by the driver during the driving process. By studying the driver's electrocardiogram (ECG) during driving, two models were established to jointly classify the ECG signals as awake, stress, and fatigue or drowsiness states for drowsiness levels. Firstly, the deep learning method was used to establish the model_1 to predict the drowsiness of the original ECG, and model_2 was developed using the combination of principal component analysis (PCA) and weighted K-nearest neighbor (WKNN) algorithm to classify the heart rate variability characteristics. Then, the drowsiness prediction results of the two models were weighted according to certain rules, and the hybrid learning model combining dilated convolution and bidirectional long short-term memory network with PCA and WKNN algorithm was established, and the mixed model was denoted as DiCNN-BiLSTM and PCA-WKNN (DBPW). Finally, the validity of the DBPW model was verified by simulation of the public database.

RESULTS

The experimental results show that the average accuracy, sensitivity and F1 score of the test model in the dataset containing multiple drivers are 98.79, 98.81, and 98.79 % respectively, and the recognition accuracy for drowsiness or drowsiness state is 99.33 %.

CONCLUSIONS

Using the proposed algorithm, it is possible to identify driver anomalies and provide new ideas for the development of intelligent vehicles.

Modeling multiple sclerosis using mobile and wearable sensor data

Multiple sclerosis (MS) is a neurological disease of the central nervous system that is the leading cause of non-traumatic disability in young adults. Clinical laboratory tests and neuroimaging studies are the standard methods to diagnose and monitor MS. However, due to infrequent clinic visits, it is fundamental to identify remote and frequent approaches for monitoring MS, which enable timely diagnosis, early access to treatment, and slowing down disease progression. In this work, we investigate the most reliable, clinically useful, and available features derived from mobile and wearable devices as well as their ability to distinguish people with MS (PwMS) from healthy controls, recognize MS disability and fatigue levels. To this end, we formalize clinical knowledge and derive behavioral markers to characterize MS. We evaluate our approach on a dataset we collected from 55 PwMS and 24 healthy controls for a total of 489 days conducted in free-living conditions. The dataset contains wearable sensor data - e.g., heart rate - collected using an arm-worn device, smartphone data - e.g., phone locks - collected through a mobile application, patient health records - e.g., MS type - obtained from the hospital, and self-reports - e.g., fatigue level - collected using validated questionnaires administered via the mobile application. Our results demonstrate the feasibility of using features derived from mobile and wearable sensors to monitor MS. Our findings open up opportunities for continuous monitoring of MS in free-living conditions and can be used to evaluate and guide the effectiveness of treatments, manage the disease, and identify participants for clinical trials.

E-Textiles for Sports and Fitness Sensing: Current State, Challenges, and Future Opportunities

E-textiles have emerged as a fast-growing area in wearable technology for sports and fitness due to the soft and comfortable nature of textile materials and the capability for smart functionality to be integrated into familiar sports clothing. This review paper presents the roles of wearable technologies in sport and fitness in monitoring movement and biosignals used to assess performance, reduce injury risk, and motivate training/exercise. The drivers of research in e-textiles are discussed after reviewing existing non-textile and textile-based commercial wearable products. Different sensing components/materials (e.g., inertial measurement units, electrodes for biosignals, piezoresistive sensors), manufacturing processes, and their applications in sports and fitness published in the literature were reviewed and discussed. Finally, the paper presents the current challenges of e-textiles to achieve practical applications at scale and future perspectives in e-textiles research and development.

Identification of runner fatigue stages based on inertial sensors and deep learning

Introduction: Running is one of the most popular sports in the world, but it also increases the risk of injury. The purpose of this study was to establish a modeling approach for IMU-based subdivided action pattern evaluation and to investigate the classification performance of different deep models for predicting running fatigue. Methods: Nineteen healthy male runners were recruited for this study, and the raw time series data were recorded during the pre-fatigue, mid-fatigue, and post-fatigue states during running to construct a running fatigue dataset based on multiple IMUs. In addition to the IMU time series data, each participant's training level was monitored as an indicator of their level of physical fatigue. Results: The dataset was examined using single-layer LSTM (S_LSTM), CNN, dual-layer LSTM (D_LSTM), single-layer LSTM plus attention model (LSTM + Attention), CNN, and LSTM hybrid model (LSTM + CNN) to classify running fatigue and fatigue levels. Discussion: Based on this dataset, this study proposes a deep learning model with constant length interception of the raw IMU data as input. The use of deep learning models can achieve good classification results for runner fatigue recognition. Both CNN and LSTM can effectively complete the classification of fatigue IMU data, the attention mechanism can effectively improve the processing efficiency of LSTM on the raw IMU data, and the hybrid model of CNN and LSTM is superior to the independent model, which can better extract the features of raw IMU data for fatigue classification. This study will provide some reference for many future action pattern studies based on deep learning.

Metaverse Wearables for Immersive Digital Healthcare: A Review

The recent exponential growth of metaverse technology has been instrumental in reshaping a myriad of sectors, not least digital healthcare. This comprehensive review critically examines the landscape and future applications of metaverse wearables toward immersive digital healthcare. The key technologies and advancements that have spearheaded the metamorphosis of metaverse wearables are categorized, encapsulating all-encompassed extended reality, such as virtual reality, augmented reality, mixed reality, and other haptic feedback systems. Moreover, the fundamentals of their deployment in assistive healthcare (especially for rehabilitation), medical and nursing education, and remote patient management and treatment are investigated. The potential benefits of integrating metaverse wearables into healthcare paradigms are multifold, encompassing improved patient prognosis, enhanced accessibility to high-quality care, and high standards of practitioner instruction. Nevertheless, these technologies are not without their inherent challenges and untapped opportunities, which span privacy protection, data safeguarding, and innovation in artificial intelligence. In summary, future research trajectories and potential advancements to circumvent these hurdles are also discussed, further augmenting the incorporation of metaverse wearables within healthcare infrastructures in the post-pandemic era.

Management of multiple sclerosis fatigue in the digital age: from assessment to treatment

Fatigue is one of the most disabling symptoms of Multiple Sclerosis (MS), affecting more than 80% of patients over the disease course. Nevertheless, it has a multi-faceted and complex nature, making its diagnosis, evaluation, and treatment extremely challenging in clinical practice. In the last years, digital supporting tools have emerged to support the care of people with MS. These include not only smartphone or table-based apps, but also wearable devices or novel techniques such as virtual reality. Furthermore, an additional effective and cost-efficient tool for the therapeutic management of people with fatigue is becoming increasingly available. Virtual reality and e-Health are viable and modern tools to both assess and treat fatigue, with a variety of applications and adaptability to patient needs and disability levels. Most importantly, they can be employed in the patient's home setting and can not only bridge clinic visits but also be complementary to the monitoring and treatment means for those MS patients who live far away from healthcare structures. In this narrative review, we discuss the current knowledge and future perspectives in the digital management of fatigue in MS. These may also serve as sources for research of novel digital biomarkers in the identification of disease activity and progression.

Well-being as a performance pillar: a holistic approach for monitoring tennis players

This perspective article aims to discuss the usefulness of tools that can assist tennis professionals effectively manage the well-being of their players. This includes identifying and monitoring meaningful metrics (i.e., training load, training intensity, heart rate variability), as well as careful planning of training and competition schedules with appropriate recovery periods. The use of innovative training methods (i.e., repeated-sprint training in hypoxia and heat training), and proper dietary practices, along with biometric assessment for young players, represents should be considered. Adopting a holistic approach to decision-making about training and competition, balancing both health and performance considerations, is crucial for tennis players and their support teams. More research is needed to refine best practices for enhancing tennis performance while prioritizing the well-being of players.

Sociotechnical Work System Approach to Occupational Fatigue

INTRODUCTION TO THE PROBLEM

Occupational fatigue is a characteristic of excessive workload and depicts the limited capacity to complete demands. The impact of occupational fatigue has been studied outside of health care in fields such as transportation and heavy industry. Research in health care professionals such as physicians, medical residents, and nurses has demonstrated the potential for occupational fatigue to affect patient, employee, and organizational outcomes. A conceptual framework of occupational fatigue that is informed by a sociotechnical systems approach is needed to (1) describe the multidimensional facets of occupational fatigue, (2) explore individual and work system factors that may affect occupational fatigue, and (3) anticipate downstream implications of occupational fatigue on employee well-being, patient safety, and organizational outcomes.

CONCEPTUAL FRAMEWORK OF OCCUPATIONAL FATIGUE

The health care professional occupational fatigue conceptual framework is outlined following the Systems Engineering Initiative for Patient Safety (SEIPS) model and adapted from the Conceptual Model of Occupational Fatigue in Nursing. Future research may apply this conceptual framework to health care professionals as a tool to describe occupational fatigue, identify the causes, and generate solutions. Interventions to mitigate and resolve occupational fatigue must address the entire sociotechnical system, not just individual or employee changes.

Applying a Smartwatch to Predict Work-related Fatigue for Emergency Healthcare Professionals: Machine Learning Method

INTRODUCTION

Healthcare professionals frequently experience work-related fatigue, which may jeopardize their health and put patient safety at risk. In this study, we applied a machine learning (ML) approach based on data collected from a smartwatch to construct prediction models of work-related fatigue for emergency clinicians.

METHODS

We conducted this prospective study at the emergency department (ED) of a tertiary teaching hospital from March 10-June 20, 2021, where we recruited physicians, nurses, and nurse practitioners. All participants wore a commercially available smartwatch capable of measuring various physiological data during the experiment. Participants completed the Multidimensional Fatigue Inventory (MFI) web form before and after each of their work shifts. We calculated and labeled the before-and-after-shift score differences between each pair of scores. Using several tree-based algorithms, we constructed the prediction models based on features collected from the smartwatch. Records were split into training/validation and testing sets at a 70:30 ratio, and we evaluated the performances using the area under the curve (AUC) measure of receiver operating characteristic on the test set.

RESULTS

In total, 110 participants were included in this study, contributing to a set of 1,542 effective records. Of these records, 85 (5.5%) were labeled as having work-related fatigue when setting the MFI difference between two standard deviations as the threshold. The mean age of the participants was 29.6. Most of the records were collected from nurses (87.7%) and females (77.5%). We selected a union of 31 features to construct the models. For total participants, CatBoost classifier achieved the best performances of AUC (0.838, 95% confidence interval [CI] 0.742-0.918) to identify work-related fatigue. By focusing on a subgroup of nurses <35 years in age, XGBoost classifier obtained excellent performance of AUC (0.928, 95% CI 0.839-0.991) on the test set.

CONCLUSION

By using features derived from a smartwatch, we successfully built ML models capable of classifying the risk of work-related fatigue in the ED. By collecting more data to optimize the models, it should be possible to use smartwatch-based ML models in the future to predict work-related fatigue and adopt preventive measures for emergency clinicians.

Validation of Endurance Model for Manual Tasks. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023;2023:1-5. [PMID: 38083441 DOI: 10.1109/embc40787.2023.10341139] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Physical fatigue in the workplace can lead to work-related musculoskeletal disorders (WMSDs), especially in occupations that require repetitive, mid-air movements, such as manufacturing and assembly tasks in industry settings. The current paper endeavors to validate an existing torque-based fatigue prediction model for lifting tasks. The model uses anthropometrics and the maximum torque of the individual to predict the time to fatigue. Twelve participants took part in the study which measured body composition parameters and the maximum force produced by the shoulder joint in flexion, followed by three lifting tasks for the shoulder in flexion, including isometric and dynamic tasks with one and two hands. Inertial measurements units (IMUs) were worn by participants to determine the torque at each instant to calculate the endurance time and CE, while a self-subjective questionnaire was utilized to assess physical exertion, the Borg Rate of Perceived Exertion (RPE) scale. The model was effective for static and two-handed tasks and produced errors in the range of [28.62 49.21] for the last task completed, indicating the previous workloads affect the endurance time, even though the individual perceives they are fully rested. The model was not effective for the one-handed dynamic task and differences were observed between males and females, which will be the focus of future work.An individualized, torque-based fatigue prediction model, such as the model presented, can be used to design worker-specific target levels and workloads, take inter and intra individual differences into account, and put fatigue mitigating interventions into place before fatigue occurs; resulting in potentially preventing WMSDs, aiding in worker wellbeing and benefitting the quality and efficiency of the work output.Clinical Relevance- This research provides the basis for an individualized, torque-based approach to the prediction of fatigue at the shoulder joint which can be used to assign worker tasks and rest breaks, design worker specific targets and reduce the prevalence of work-related musculoskeletal disorders in occupational settings.

Exploring the Applicability of Physiological Monitoring to Manage Physical Fatigue in Firefighters

Physical fatigue reduces productivity and quality of work while increasing the risk of injuries and accidents among safety-sensitive professionals. To prevent its adverse effects, researchers are developing automated assessment methods that, despite being highly accurate, require a comprehensive understanding of underlying mechanisms and variables' contributions to determine their real-life applicability. This work aims to evaluate the performance variations of a previously developed four-level physical fatigue model when alternating its inputs to have a comprehensive view of the impact of each physiological variable on the model's functioning. Data from heart rate, breathing rate, core temperature and personal characteristics from 24 firefighters during an incremental running protocol were used to develop the physical fatigue model based on an XGBoosted tree classifier. The model was trained 11 times with different input combinations resulting from alternating four groups of features. Performance measures from each case showed that heart rate is the most relevant signal for estimating physical fatigue. Breathing rate and core temperature enhanced the model when combined with heart rate but showed poor performance individually. Overall, this study highlights the advantage of using more than one physiological measure for improving physical fatigue modelling. The findings can contribute to variables and sensor selection in occupational applications and as the foundation for further field research.

Driving drowsiness detection using spectral signatures of EEG-based neurophysiology

Introduction: Drowsy driving is a significant factor causing dire road crashes and casualties around the world. Detecting it earlier and more effectively can significantly reduce the lethal aftereffects and increase road safety. As physiological conditions originate from the human brain, so neurophysiological signatures in drowsy and alert states may be investigated for this purpose. In this preface, A passive brain-computer interface (pBCI) scheme using multichannel electroencephalography (EEG) brain signals is developed for spatially localized and accurate detection of human drowsiness during driving tasks.

Methods: This pBCI modality acquired electrophysiological patterns of 12 healthy subjects from the prefrontal (PFC), frontal (FC), and occipital cortices (OC) of the brain. Neurological states are recorded using six EEG channels spread over the right and left hemispheres in the PFC, FC, and OC of the sleep-deprived subjects during simulated driving tasks. In post-hoc analysis, spectral signatures of the δ, θ, α, and β rhythms are extracted in terms of spectral band powers and their ratios with a temporal correlation over the complete span of the experiment. Minimum redundancy maximum relevance, Chi-square, and ReliefF feature selection methods are used and aggregated with a Z-score based approach for global feature ranking. The extracted drowsiness attributes are classified using decision trees, discriminant analysis, logistic regression, naïve Bayes, support vector machines, k-nearest neighbors, and ensemble classifiers. The binary classification results are reported with confusion matrix-based performance assessment metrics.

Results: In inter-classifier comparison, the optimized ensemble model achieved the best results of drowsiness classification with 85.6% accuracy and precision, 89.7% recall, 87.6% F1-score, 80% specificity, 70.3% Matthews correlation coefficient, 70.2% Cohen’s kappa score, and 91% area under the receiver operating characteristic curve with 76-ms execution time. In inter-channel comparison, the best results were obtained at the F8 electrode position in the right FC of the brain. The significance of all the results was validated with a p-value of less than 0.05 using statistical hypothesis testing methods.

Conclusions: The proposed scheme has achieved better results for driving drowsiness detection with the accomplishment of multiple objectives. The predictor importance approach has reduced the feature extraction cost and computational complexity is minimized with the use of conventional machine learning classifiers resulting in low-cost hardware and software requirements. The channel selection approach has spatially localized the most promising brain region for drowsiness detection with only a single EEG channel (F8) which reduces the physical intrusiveness in normal driving operation. This pBCI scheme has a good potential for practical applications requiring earlier, more accurate, and less disruptive drowsiness detection using the spectral information of EEG biosignals.

Machine Learning Approach to Model Physical Fatigue during Incremental Exercise among Firefighters

Physical fatigue is a serious threat to the health and safety of firefighters. Its effects include decreased cognitive abilities and a heightened risk of accidents. Subjective scales and, recently, on-body sensors have been used to monitor physical fatigue among firefighters and safety-sensitive professionals. Considering the capabilities (e.g., noninvasiveness and continuous monitoring) and limitations (e.g., assessed fatiguing tasks and models validation procedures) of current approaches, this study aimed to develop a physical fatigue prediction model combining cardiorespiratory and thermoregulatory measures and machine learning algorithms within a firefighters' sample. Sensory data from heart rate, breathing rate and core temperature were recorded from 24 participants during an incremental running protocol. Various supervised machine learning algorithms were examined using 21 features extracted from the physiological variables and participants' characteristics to estimate four physical fatigue conditions: low, moderate, heavy and severe. Results showed that the XGBoosted Trees algorithm achieved the best outcomes with an average accuracy of 82% and accuracies of 93% and 86% for recognising the low and severe levels. Furthermore, this study evaluated different methods to assess the models' performance, concluding that the group cross-validation method presents the most practical results. Overall, this study highlights the advantages of using multiple physiological measures for enhancing physical fatigue modelling. It proposes a promising health and safety management tool and lays the foundation for future studies in field conditions.

EMG Signal Processing for the Study of Localized Muscle Fatigue-Pilot Study to Explore the Applicability of a Novel Method

This pilot study aimed to explore a method for characterization of the electromyogram frequency spectrum during a sustained exertion task, performed by the upper limb. Methods: Nine participants underwent an isometric localized muscle fatigue protocol on an isokinetic dynamometer until exhaustion, while monitored with surface electromyography (sEMG) of the shoulder's external rotators. Firstly, three methods of signal energy analysis based on primer frequency contributors were compared to the energy of the entire spectrum. Secondly, the chosen method of analysis was used to characterize the signal energy at beginning (T1), in the middle (T2) and at the end (T3) of the fatigue protocol and compared to the torque output and the shift in the median frequencies during the trial. Results: There were statistically significant differences between T1 and T3 for signal energy (p < 0.007) and for central frequency of the interval (p = 0.003). Moreover, the isometric peak torque was also different between T1 and T3 (p < 0.001). Overall, there were no differences between the signal energy enclosed in the 40 primer frequency contributors and the analysis of the full spectrum energy; consequently, it was the method of choice. The reported fatigue and the decrease in the produced muscle torque was consistent with fatigue-induced alterations in the electromyogram frequency spectrum. In conclusion, the developed protocol has potential to be considered as an easy-to-use method for EMG-based analysis of isometric muscle exertion until fatigue. Thus, the novelty of the proposed method is to explore, in muscle fatigue, the use of only the main contributors in the frequency domain of the EMG spectrum, avoiding surplus information, that may not represent muscle functioning. However, further studies are needed to investigate the stability of the present findings in a more comprehensive sample.

A rapid, non-invasive method for fatigue detection based on voice information

Fatigue results from a series of physiological and psychological changes due to continuous energy consumption. It can affect the physiological states of operators, thereby reducing their labor capacity. Fatigue can also reduce efficiency and, in serious cases, cause severe accidents. In addition, it can trigger pathological-related changes. By establishing appropriate methods to closely monitor the fatigue status of personnel and relieve the fatigue on time, operation-related injuries can be reduced. Existing fatigue detection methods mostly include subjective methods, such as fatigue scales, or those involving the use of professional instruments, which are more demanding for operators and cannot detect fatigue levels in real time. Speech contains information that can be used as acoustic biomarkers to monitor physiological and psychological statuses. In this study, we constructed a fatigue model based on the method of sleep deprivation by collecting various physiological indexes, such as P300 and glucocorticoid level in saliva, as well as fatigue questionnaires filled by 15 participants under different fatigue procedures and graded the fatigue levels accordingly. We then extracted the speech features at different instances and constructed a model to match the speech features and the degree of fatigue using a machine learning algorithm. Thus, we established a method to rapidly judge the degree of fatigue based on speech. The accuracy of the judgment based on unitary voice could reach 94%, whereas that based on long speech could reach 81%. Our fatigue detection method based on acoustic information can easily and rapidly determine the fatigue levels of the participants. This method can operate in real time and is non-invasive and efficient. Moreover, it can be combined with the advantages of information technology and big data to expand its applicability.

A Deep Learning Approach to Classify Sitting and Sleep History from Raw Accelerometry Data during Simulated Driving

Prolonged sitting and inadequate sleep can impact driving performance. Therefore, objective knowledge of a driver's recent sitting and sleep history could help reduce safety risks. This study aimed to apply deep learning to raw accelerometry data collected during a simulated driving task to classify recent sitting and sleep history. Participants (n = 84, Mean ± SD age = 23.5 ± 4.8, 49% Female) completed a seven-day laboratory study. Raw accelerometry data were collected from a thigh-worn accelerometer during a 20-min simulated drive (8:10 h and 17:30 h each day). Two convolutional neural networks (CNNs; ResNet-18 and DixonNet) were trained to classify accelerometry data into four classes (sitting or breaking up sitting and 9-h or 5-h sleep). Accuracy was determined using five-fold cross-validation. ResNet-18 produced higher accuracy scores: 88.6 ± 1.3% for activity (compared to 77.2 ± 2.6% from DixonNet) and 88.6 ± 1.1% for sleep history (compared to 75.2 ± 2.6% from DixonNet). Class activation mapping revealed distinct patterns of movement and postural changes between classes. Findings demonstrate the suitability of CNNs in classifying sitting and sleep history using thigh-worn accelerometer data collected during a simulated drive. This approach has implications for the identification of drivers at risk of fatigue-related impairment.

Fatigue Driving Detection Method Based on Combination of BP Neural Network and Time Cumulative Effect

Fatigue driving has always received a lot of attention, but few studies have focused on the fact that human fatigue is a cumulative process over time, and there are no models available to reflect this phenomenon. Furthermore, the problem of incorrect detection due to facial expression is still not well addressed. In this article, a model based on BP neural network and time cumulative effect was proposed to solve these problems. Experimental data were used to carry out this work and validate the proposed method. Firstly, the Adaboost algorithm was applied to detect faces, and the Kalman filter algorithm was used to trace the face movement. Then, a cascade regression tree-based method was used to detect the 68 facial landmarks and an improved method combining key points and image processing was adopted to calculate the eye aspect ratio (EAR). After that, a BP neural network model was developed and trained by selecting three characteristics: the longest period of continuous eye closure, number of yawns, and percentage of eye closure time (PERCLOS), and then the detection results without and with facial expressions were discussed and analyzed. Finally, by introducing the Sigmoid function, a fatigue detection model considering the time accumulation effect was established, and the drivers’ fatigue state was identified segment by segment through the recorded video. Compared with the traditional BP neural network model, the detection accuracies of the proposed model without and with facial expressions increased by 3.3% and 8.4%, respectively. The number of incorrect detections in the awake state also decreased obviously. The experimental results show that the proposed model can effectively filter out incorrect detections caused by facial expressions and truly reflect that driver fatigue is a time accumulating process.

Using Machine Learning to Identify Feelings of Energy and Fatigue in Single-Task Walking Gait: An Exploratory Study

The objective of this study was to use machine learning to identify feelings of energy and fatigue using single-task walking gait. Participants (n = 126) were recruited from a university community and completed a single protocol where current feelings of energy and fatigue were measured using the Profile of Moods Survey–Short Form approximately 2 min prior to participants completing a two-minute walk around a 6 m track wearing APDM mobility monitors. Gait parameters for upper and lower extremity, neck, lumbar and trunk movement were collected. Gradient boosting classifiers were the most accurate classifiers for both feelings of energy (74.3%) and fatigue (74.2%) and Random Forest Regressors were the most accurate regressors for both energy (0.005) and fatigue (0.007). ANCOVA analyses of gait parameters comparing individuals who were high or low energy or fatigue suggest that individuals who are low energy have significantly greater errors in walking gait compared to those who are high energy. Individuals who are high fatigue have more symmetrical gait patterns and have trouble turning when compared to their low fatigue counterparts. Furthermore, these findings support the need to assess energy and fatigue as two distinct unipolar moods as the signals used by the algorithms were unique to each mood.