Measuring Biomechanical Risk in Lifting Load Tasks Through Wearable System and Machine-Learning Approach

Exposures to select risk factors can be estimated from a continuous stream of inertial sensor measurements during a variety of lifting-lowering tasks

Wearable inertial measurement units (IMUs) are used increasingly to estimate biomechanical exposures in lifting-lowering tasks. The objective of the study was to develop and evaluate predictive models for estimating relative hand loads and two other critical biomechanical exposures to gain a comprehensive understanding of work-related musculoskeletal disorders in lifting. We collected 12,480 lifting-lowering phases from 26 subjects (15 men and 11 women) performing manual lifting-lowering tasks with hand loads (0-22.7 kg) at varied workstation heights and handling modes. We implemented a Hierarchical model, that sequentially classified risk factors, including workstation height, handling mode, and relative hand load. Our algorithm detected lifting-lowering phases (>97.8%) with mean onset errors of 0.12 and 0.2 seconds for lifting and lowering phases. It estimated workstation height (>98.5%), handling mode (>87.1%), and relative hand load (mean absolute errors of 5.6-5.8%) across conditions, highlighting the benefits of data-driven models in deriving lifting-lowering occurrences, timing, and critical risk factors from continuous IMU-based kinematics.

Estimation of lower back muscle force in a lifting task using wearable IMUs

Low back pain is commonly reported in occupational settings due to factors such as heavy lifting and poor ergonomic practices, often resulting in significant healthcare expenses and lowered productivity. Assessment tools for human motion and ergonomic risk at the workplace are still limited. Therefore, this study aimed to assess lower back muscle and joint reaction forces in laboratory conditions using wearable inertial measurement units (IMUs) during weight lifting, a frequently high-risk workplace task. Ten able-bodied participants were instructed to lift a 28 lbs. box while surface electromyography sensors, IMUs, and a camera-based motion capture system recorded their muscle activity and body motion. The data recorded by IMUs and motion capture system were used to estimate lower back muscle and joint reaction forces via musculoskeletal modeling. Lower back muscle patterns matched well with electromyography recordings. The normalized mean absolute differences between muscle forces estimated based on measurements of IMUs and cameras were less than 25 %, and the statistical parametric mapping results indicated no significant difference between the forces estimated by both systems. However, abrupt changes in motion, such as lifting initiation, led to significant differences (p < 0.05) between the muscle forces. Furthermore, the maximum L5-S1 joint reaction force estimated using IMU data was significantly lower (p < 0.05) than those estimated by cameras during weight lifting and lowering. The study showed how kinematic errors from IMUs propagated through the musculoskeletal model and affected the estimations of muscle forces and joint reaction forces. Our findings showed the potential of IMUs for in-field ergonomic risk evaluations.

Wearables for Monitoring and Postural Feedback in the Work Context: A Scoping Review

Wearables offer a promising solution for simultaneous posture monitoring and/or corrective feedback. The main objective was to identify, synthesise, and characterise the wearables used in the workplace to monitor and postural feedback to workers. The PRISMA-ScR guidelines were followed. Studies were included between 1 January 2000 and 22 March 2023 in Spanish, French, English, and Portuguese without geographical restriction. The databases selected for the research were PubMed®, Web of Science®, Scopus®, and Google Scholar®. Qualitative studies, theses, reviews, and meta-analyses were excluded. Twelve studies were included, involving a total of 304 workers, mostly health professionals (n = 8). The remaining studies covered workers in the industry (n = 2), in the construction (n = 1), and welders (n = 1). For assessment purposes, most studies used one (n = 5) or two sensors (n = 5) characterised as accelerometers (n = 7), sixaxial (n = 2) or nonaxialinertial measurement units (n = 3). The most common source of feedback was the sensor itself (n = 6) or smartphones (n = 4). Haptic feedback was the most prevalent (n = 6), followed by auditory (n = 5) and visual (n = 3). Most studies employed prototype wearables emphasising kinematic variables of human movement. Healthcare professionals were the primary focus of the study along with haptic feedback that proved to be the most common and effective method for correcting posture during work activities.

The highs and lows of lifting loads: SPM analysis of multi-segmental spine angles in healthy adults during manual handling with increased load

Introduction: Manual handling personnel and those performing manual handling tasks in non-traditional manual handling industries continue to suffer debilitating and costly workplace injuries. Smart assistive devices are one solution to reducing musculoskeletal back injuries. Devices that provide targeted assistance need to be able to predict when and where to provide augmentation via predictive algorithms trained on functional datasets. The aim of this study was to describe how an increase in load impacts spine kinematics during a ground-to-platform manual handling task. Methods: Twenty-nine participants performed ground-to-platform lifts for six standardised loading conditions (50%, 60%, 70%, 80%, 90%, and 100% of maximum lift capacity). Six thoracic and lumbar spine segments were measured using inertial measurement units that were processed using an attitude-heading-reference filter and normalised to the duration of the lift. The lift was divided into four phases weight-acceptance, standing, lift-to-height and place-on-platform. Statistical significance of sagittal angles from the six spine segments were identified through statistical parametric mapping one-way analysis of variance with repeated measures and post hoc paired t-tests. Results: Two regions of interest were identified during a period of peak flexion and a period of peak extension. There was a significant increase in spine range of motion and peak extension angle for all spine segments when the load conditions were increased (p < 0.001). There was a decrease in spine angles (more flexion) during the weight acceptance to standing phase at the upper thoracic to upper lumbar spine segments for some condition comparisons. A significant increase in spine angles (more extension) during the place-on-platform phase was seen in all spine segments when comparing heavy loads (>80% maximum lift capacity, inclusive) to light loads (<80% maximum lift capacity) (p < 0.001). Discussion: The 50%-70% maximum lift capacity conditions being significantly different from heavier load conditions is representative that the kinematics of a lift do change consistently when a participant's load is increased. The understanding of how changes in loading are reflected in spine angles could inform the design of targeted assistance devices that can predict where and when in a task assistance may be needed, possibly reducing instances of back injuries in manual handling personnel.

Physical Exertion Recognition Using Surface Electromyography and Inertial Measurements for Occupational Ergonomics

By observing the actions taken by operators, it is possible to determine the risk level of a work task. One method for achieving this is the recognition of human activity using biosignals and inertial measurements provided to a machine learning algorithm performing such recognition. The aim of this research is to propose a method to automatically recognize physical exertion and reduce noise as much as possible towards the automation of the Job Strain Index (JSI) assessment by using a motion capture wearable device (MindRove armband) and training a quadratic support vector machine (QSVM) model, which is responsible for predicting the exertion depending on the patterns identified. The highest accuracy of the QSVM model was 95.7%, which was achieved by filtering the data, removing outliers and offsets, and performing zero calibration; in addition, EMG signals were normalized. It was determined that, given the job strain index's purpose, physical exertion detection is crucial to computing its intensity in future work.

The Three-Dimensional Body Center of Mass at the Workplace under Hypogravity

The center of mass dynamics of the seated posture of humans in a work environment under hypogravity (0 < g < 1) have rarely been investigated, and such research is yet to be carried out. The present study determined the difference in the body system of 32 participants working under simulated 1/6 g (Moon) and 1 g (Earth) for comparison using static and dynamic task measurements. This was based on a markerless motion capture method that analyzed participants' center of mass at the start, middle and end of the task when they began to get fatigued. According to this analysis, there is a positive relationship (p < 0.01) with a positive coefficient of correlation between the downward center of mass body shift along the proximodistal axis and gravity level for males and females. At the same time, the same positive relationship (p < 0.01) between the tilt of the body backward along the anterior-posterior axis and the level of gravity was found only in females. This offers fresh perspectives for comprehending hypogravity in a broader framework regarding its impact on musculoskeletal disorders. It can also improve workplace ergonomics, body stability, equipment design, and biomechanics.

sEMG Spectral Analysis and Machine Learning Algorithms Are Able to Discriminate Biomechanical Risk Classes Associated with Manual Material Liftings

Manual material handling and load lifting are activities that can cause work-related musculoskeletal disorders. For this reason, the National Institute for Occupational Safety and Health proposed an equation depending on the following parameters: intensity, duration, frequency, and geometric characteristics associated with the load lifting. In this paper, we explore the feasibility of several Machine Learning (ML) algorithms, fed with frequency-domain features extracted from electromyographic (EMG) signals of back muscles, to discriminate biomechanical risk classes defined by the Revised NIOSH Lifting Equation. The EMG signals of the multifidus and erector spinae muscles were acquired by means of a wearable device for surface EMG and then segmented to extract several frequency-domain features relating to the Total Power Spectrum of the EMG signal. These features were fed to several ML algorithms to assess their prediction power. The ML algorithms produced interesting results in the classification task, with the Support Vector Machine algorithm outperforming the others with accuracy and Area under the Receiver Operating Characteristic Curve values of up to 0.985. Moreover, a correlation between muscular fatigue and risky lifting activities was found. These results showed the feasibility of the proposed methodology-based on wearable sensors and artificial intelligence-to predict the biomechanical risk associated with load lifting. A future investigation on an enriched study population and additional lifting scenarios could confirm the potential of the proposed methodology and its applicability in the field of occupational ergonomics.

Detecting subject-specific fatigue-related changes in lifting kinematics using a machine learning approach

Individual responses to fatigue have been observed in lifting kinematics, suggesting a subject-specific approach is necessary for fatigue identification. One-class support vector machines (OCSVM) may provide an objective method to classify fatigue-related kinematic changes during repetitive lifting. Participants completed a repetitive lifting protocol while motion capture recorded lifting motions. Subject-specific kinematics from participants' first 35% of lifts trained OCSVM decision boundaries. The remaining lifts were separated into test sets and classified against the decision boundary to identify the percentage of outlier lifts within each test set. Spearman's correlation assessed if the test sets' percentage of outlier lifts increased concurrently with participants' rating of perceived exertion (RPE). Significant positive associations were found for participants who demonstrated evidence of fatigue, while no significant associations were found for participants who did not demonstrate evidence of fatigue. These results demonstrate the prospective efficacy of an outlier detection tool for fatigue detection during repetitive lifting.Practitioner Summary: An objective subject-specific fatigue detection method is desired for workplace tasks, such as lifting. An outlier detection machine learning approach was identified when lifting movement patterns changed from baseline throughout a repetitive lifting protocol. Participants who demonstrated an increase in outlier movement patterns had a concurrent increase in self-reported fatigue.

Wearable Sensors and Artificial Intelligence for Physical Ergonomics: A Systematic Review of Literature

Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, for example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown potential for improvement in experimental methods of ergonomic analysis, through the combined use of artificial intelligence, and wearable sensors. In this regard, this review intends to provide a first account of the investigations carried out using these combined methods, considering the period up to 2021. The method that combines the information obtained on the worker through physical sensors (IMU, accelerometer, gyroscope, etc.) or biopotential sensors (EMG, EEG, EKG/ECG), with the analysis through artificial intelligence systems (machine learning or deep learning), offers interesting perspectives from both diagnostic, prognostic, and preventive points of view. In particular, the signals, obtained from wearable sensors for the recognition and categorization of the postural and biomechanical load of the worker, can be processed to formulate interesting algorithms for applications in the preventive field (especially with respect to musculoskeletal disorders), and with high statistical power. For Ergonomics, but also for Occupational Medicine, these applications improve the knowledge of the limits of the human organism, helping in the definition of sustainability thresholds, and in the ergonomic design of environments, tools, and work organization. The growth prospects for this research area are the refinement of the procedures for the detection and processing of signals; the expansion of the study to assisted working methods (assistive robots, exoskeletons), and to categories of workers suffering from pathologies or disabilities; as well as the development of risk assessment systems that exceed those currently used in ergonomics in precision and agility.

A Logistic Regression Model for Biomechanical Risk Classification in Lifting Tasks

Lifting is one of the most potentially harmful activities for work-related musculoskeletal disorders (WMSDs), due to exposure to biomechanical risk. Risk assessment for work activities that involve lifting loads can be performed through the NIOSH (National Institute of Occupational Safety and Health) method, and specifically the Revised NIOSH Lifting Equation (RNLE). Aim of this work is to explore the feasibility of a logistic regression model fed with time and frequency domains features extracted from signals acquired through one inertial measurement unit (IMU) to classify risk classes associated with lifting activities according to the RNLE. Furthermore, an attempt was made to evaluate which are the most discriminating features relating to the risk classes, and to understand which inertial signals and which axis were the most representative. In a simplified scenario, where only two RNLE variables were altered during lifting tasks performed by 14 healthy adults, inertial signals (linear acceleration and angular velocity) acquired using one IMU placed on the subject’s sternum during repeated rhythmic lifting tasks were automatically segmented to extract several features in the time and frequency domains. The logistic regression model fed with significant features showed good results to discriminate “risk” and “no risk” NIOSH classes with an accuracy, sensitivity and specificity equal to 82.8%, 84.8% and 80.9%, respectively. This preliminary work indicated that a logistic regression model—fed with specific inertial features extracted by signals acquired using a single IMU sensor placed on the sternum—is able to discriminate risk classes according to the RNLE in a simplified context, and therefore could be a valid tool to assess the biomechanical risk in an automatic way also in more complex conditions (e.g., real working scenarios).

Learning from Acceleration Data to Differentiate the Posture, Dynamic and Static Work of the Back: An Experimental Setup

Information on body posture, postural change, and dynamic and static work is essential in understanding biomechanical exposure and has many applications in ergonomics and healthcare. This study aimed at evaluating the possibility of using triaxial acceleration data to classify postures and to differentiate between dynamic and static work of the back in an experimental setup, based on a machine learning (ML) approach. A movement protocol was designed to cover the essential degrees of freedom of the back, and a subject wearing a triaxial accelerometer implemented this protocol. Impulses and oscillations from the signals were removed by median filtering, then the filtered dataset was fed into two ML algorithms, namely a multilayer perceptron with back propagation (MLPBNN) and a random forest (RF), with the aim of inferring the most suitable algorithm and architecture for detecting dynamic and static work, as well as for correctly classifying the postures of the back. Then, training and testing subsets were delimitated and used to evaluate the learning and generalization ability of the ML algorithms for the same classification problems. The results indicate that ML has a lot of potential in differentiating between dynamic and static work, depending on the type of algorithm and its architecture, and the data quantity and quality. In particular, MLPBNN can be used to better differentiate between dynamic and static work when tuned properly. In addition, static work and the associated postures were better learned and generalized by the MLPBNN, a fact that could provide the basis for cheap real-world offline applications with the aim of getting time-scaled postural profiling data by accounting for the static postures. Although it wasn’t the case in this study, on bigger datasets, the use of MLPBPNN may come at the expense of high computational costs in the training phase. The study also discusses the factors that may improve the classification performance in the testing phase and sets new directions of research.

Classifying hazardous movements and loads during manual materials handling using accelerometers and instrumented insoles

Improper manual material handling (MMH) techniques are shown to lead to low back pain, the most common work-related musculoskeletal disorder. Due to the complex nature and variability of MMH and obtrusiveness and subjectiveness of existing hazard analysis methods, providing systematic, continuous, and automated risk assessment is challenging. We present a machine learning algorithm to detect and classify MMH tasks using minimally-intrusive instrumented insoles and chest-mounted accelerometers. Six participants performed standing, walking, lifting/lowering, carrying, side-to-side load transferring (i.e., 5.7 kg and 12.5 kg), and pushing/pulling. Lifting and carrying loads as well as hazardous behaviors (i.e., stooping, overextending and jerky lifting) were detected with 85.3%/81.5% average accuracies with/without chest accelerometer. The proposed system allows for continuous exposure assessment during MMH and provides objective data for use with analytical risk assessment models that can be used to increase workplace safety through exposure estimation.

A machine learning approach to identify risk factors for running-related injuries: study protocol for a prospective longitudinal cohort trial

BACKGROUND

Running is a very popular sport among both recreational and competitive athletes. However, participating in running is associated with a comparably high risk of sustaining an exercise-related injury. Due to the often multifactorial and individual reasons for running injuries, a shift in thinking is required to account for the dynamic process of the various risk factors. Therefore, a machine learning approach will be used to comprehensively analyze biomechanical, biological, and loading parameters in order to identify risk factors and to detect risk patterns in runners.

METHODS

The prospective longitudinal cohort study will include competitive adult athletes, running at least 20 km per week and being free of injuries three months before the start of the study. At baseline and the end of the study period, subjective questionnaires (demographics, injury history, sports participation, menstruation, medication, psychology), biomechanical measures (e.g., stride length, cadence, kinematics, kinetics, tibial shock, and tibial acceleration) and a medical examination (BMI, laboratory: blood count, creatinine, calcium, phosphate, parathyroid hormone, vitamin D, osteocalcin, bone-specific alkaline phosphatase, DPD cross-links) will be performed. During the study period (one season), continuous data collection will be performed for biomechanical parameters, injuries, internal and external load. Statistical analysis of the data is performed using machine learning (ML) methods. For this purpose, the correlation of the collected data to possible injuries is automatically learned by an ML model and from this, a ranking of the risk factors can be determined with the help of sensitivity analysis methods.

DISCUSSION

To achieve a comprehensive risk reduction of injuries in runners, a multifactorial and individual approach and analysis is necessary. Recently, the use of ML processes for the analysis of risk factors in sports was discussed and positive results have been published. This study will be the first prospective longitudinal cohort study in runners to investigate the association of biomechanical, bone health, and loading parameters as well as injuries via ML models. The results may help to predict the risk of sustaining an injury and give way for new analysis methods that may also be transferred to other sports.

TRIAL REGISTRATION

DRKS00026904 (German Clinical Trial Register DKRS), date of registration 18.10.2021.

Review of the Application of Wearable Devices in Construction Safety: A Bibliometric Analysis from 2005 to 2021

Wearable devices as an emerging technology to collect safety data on construction site is gaining increasing attention from researchers and practitioners. Given the rapid development of wearable devices research and the high application prospects of wearable devices in construction safety, a state-of-the-art review of research and implementations in this field is needed. The aim of this study is to provide an objective and extensive bibliometric analysis of the published articles on wearable applications in construction safety for the period of 2005–2021. CiteSpace software was used to conduct co-citation analysis, co-occurrence analysis, and cluster identification on 169 identified articles. The results show that 10 research clusters (e.g., attentional failure, brain-computer interface) were extremely important in the development of wearable devices for construction safety. The results highlight the evolution of wearable devices in construction-safety-related research, revealing the underlying structure of this cross-cutting research area. The analysis also summarizes the status quo of wearable devices in the construction safety field and provides a dynamic platform for integrating future applications.

A 3D-Printed Knee Wearable Goniometer with a Mobile-App Interface for Measuring Range of Motion and Monitoring Activities

Wearable technology has been developed in recent years to monitor biomechanical variables in less restricted environments and in a more affordable way than optical motion capture systems. This paper proposes the development of a 3D printed knee wearable goniometer that uses a Hall-effect sensor to measure the knee flexion angle, which works with a mobile app that shows the angle in real-time as well as the activity the user is performing (standing, sitting, or walking). Detection of the activity is done through an algorithm that uses the knee angle and angular speeds as inputs. The measurements of the wearable are compared with a commercial goniometer, and, with the Aktos-t system, a commercial motion capture system based on inertial sensors, at three speeds of gait (4.0 km/h, 4.5 km/h, and 5.0 km/h) in nine participants. Specifically, the four differences between maximum and minimum peaks in the gait cycle, starting with heel-strike, were compared by using the mean absolute error, which was between 2.46 and 12.49 on average. In addition, the algorithm was able to predict the three activities during online testing in one participant and detected on average 94.66% of the gait cycles performed by the participants during offline testing.

The role of machine learning in the primary prevention of work-related musculoskeletal disorders: A scoping review

To determine the applications of machine learning (ML) techniques used for the primary prevention of work-related musculoskeletal disorders (WMSDs), a scoping review was conducted using seven literature databases. Of the 4,639 initial results, 130 primary research studies were deemed relevant for inclusion. Studies were reviewed and classified as a contribution to one of six steps within the primary WMSD prevention research framework by van der Beek et al. (2017). ML techniques provided the greatest contributions to the development of interventions (48 studies), followed by risk factor identification (33 studies), underlying mechanisms (29 studies), incidence of WMSDs (14 studies), evaluation of interventions (6 studies), and implementation of effective interventions (0 studies). Nearly a quarter (23.8%) of all included studies were published in 2020. These findings provide insight into the breadth of ML techniques used for primary WMSD prevention and can help identify areas for future research and development.

Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System

Accurately measuring the lower extremities and L5/S1 moments is important since L5/S1 moments are the principal parameters that measure the risk of musculoskeletal diseases during lifting. In this study, protocol that predicts lower extremities and L5/S1 moments with an insole sensor was proposed to replace the prior methods that have spatial constraints. The protocol is hierarchically composed of a classification model and a regression model to predict joint moments. Additionally, a single LSTM model was developed to compare with proposed protocol. To optimize hyperparameters of the machine learning model and input feature, Bayesian optimization method was adopted. As a result, the proposed protocol showed a relative root mean square error (rRMSE) of 8.06~13.88% while the single LSTM showed 9.30~18.66% rRMSE. This protocol in this research is expected to be a starting point for developing a system for estimating the lower extremity and L5/S1 moment during lifting that can replace the complex prior method and adopted to workplace environments. This novel study has the potential to precisely design a feedback iterative control system of an exoskeleton for the appropriate generation of an actuator torque.

Classification and Automated Interpretation of Spinal Posture Data Using a Pathology-Independent Classifier and Explainable Artificial Intelligence (XAI)

Clinical classification models are mostly pathology-dependent and, thus, are only able to detect pathologies they have been trained for. Research is needed regarding pathology-independent classifiers and their interpretation. Hence, our aim is to develop a pathology-independent classifier that provides prediction probabilities and explanations of the classification decisions. Spinal posture data of healthy subjects and various pathologies (back pain, spinal fusion, osteoarthritis), as well as synthetic data, were used for modeling. A one-class support vector machine was used as a pathology-independent classifier. The outputs were transformed into a probability distribution according to Platt's method. Interpretation was performed using the explainable artificial intelligence tool Local Interpretable Model-Agnostic Explanations. The results were compared with those obtained by commonly used binary classification approaches. The best classification results were obtained for subjects with a spinal fusion. Subjects with back pain were especially challenging to distinguish from the healthy reference group. The proposed method proved useful for the interpretation of the predictions. No clear inferiority of the proposed approach compared to commonly used binary classifiers was demonstrated. The application of dynamic spinal data seems important for future works. The proposed approach could be useful to provide an objective orientation and to individually adapt and monitor therapy measures pre- and post-operatively.

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: "artificial intelligence" OR "machine learning" AND "neurosurgery" AND "spine." Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

A Computational Framework Towards the Tele-Rehabilitation of Balance Control Skills

Mobility has been one of the most impacted aspects of human life due to the spread of the COVID-19 pandemic. Home confinement, the lack of access to physical rehabilitation, and prolonged immobilization of COVID-19-positive patients within hospitals are three major factors that affected the mobility of the general population world-wide. Balance is one key indicator to monitor the possible movement disorders that may arise both during the COVID-19 pandemic and in the coming future post-COVID-19. A systematic quantification of the balance performance in the general population is essential for preventing the appearance and progression of certain diseases (e.g., cardiovascular, neurodegenerative, and musculoskeletal), as well as for assessing the therapeutic outcomes of prescribed physical exercises for elderly and pathological patients. Current research on clinical exercises and associated outcome measures of balance is still far from reaching a consensus on a "golden standard" practice. Moreover, patients are often reluctant or unable to follow prescribed exercises, because of overcrowded facilities, lack of reliable and safe transportation, or stay-at-home orders due to the current pandemic. A novel balance assessment methodology, in combination with a home-care technology, can overcome these limitations. This paper presents a computational framework for the in-home quantitative assessment of balance control skills. Novel outcome measures of balance performance are implemented in the design of rehabilitation exercises with customized and quantifiable training goals. Using this framework in conjunction with a portable technology, physicians can treat and diagnose patients remotely, with reduced time and costs and a highly customized approach. The methodology proposed in this research can support the development of innovative technologies for smart and connected home-care solutions for physical therapy rehabilitation.

Work-Related Risk Assessment According to the Revised NIOSH Lifting Equation: A Preliminary Study Using a Wearable Inertial Sensor and Machine Learning

Many activities may elicit a biomechanical overload. Among these, lifting loads can cause work-related musculoskeletal disorders. Aspiring to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established a methodology for assessing lifting actions by means of a quantitative method based on intensity, duration, frequency and other geometrical characteristics of lifting. In this paper, we explored the machine learning (ML) feasibility to classify biomechanical risk according to the revised NIOSH lifting equation. Acceleration and angular velocity signals were collected using a wearable sensor during lifting tasks performed by seven subjects and further segmented to extract time-domain features: root mean square, minimum, maximum and standard deviation. The features were fed to several ML algorithms. Interesting results were obtained in terms of evaluation metrics for a binary risk/no-risk classification; specifically, the tree-based algorithms reached accuracies greater than 90% and Area under the Receiver operating curve characteristics curves greater than 0.9. In conclusion, this study indicates the proposed combination of features and algorithms represents a valuable approach to automatically classify work activities in two NIOSH risk groups. These data confirm the potential of this methodology to assess the biomechanical risk to which subjects are exposed during their work activity.

Dynamic Joint Motions in Occupational Environments as Indicators of Potential Musculoskeletal Injury Risk

The objective of this study was to test the feasibility of using a pair of wearable inertial measurement unit (IMU) sensors to accurately capture dynamic joint motion data during simulated occupational conditions. Eleven subjects (5 males and 6 females) performed repetitive neck, low-back, and shoulder motions simulating low- and high-difficulty occupational tasks in a laboratory setting. Kinematics for each of the 3 joints were measured via IMU sensors in addition to a "gold standard" passive marker optical motion capture system. The IMU accuracy was benchmarked relative to the optical motion capture system, and IMU sensitivity to low- and high-difficulty tasks was evaluated. The accuracy of the IMU sensors was found to be very good on average, but significant positional drift was observed in some trials. In addition, IMU measurements were shown to be sensitive to differences in task difficulty in all 3 joints (P < .05). These results demonstrate the feasibility for using wearable IMU sensors to capture kinematic exposures as potential indicators of occupational injury risk. Velocities and accelerations demonstrate the most potential for developing risk metrics since they are sensitive to task difficulty and less sensitive to drift than rotational position measurements.

Wearable Devices for Ergonomics: A Systematic Literature Review

Wearable devices are pervasive solutions for increasing work efficiency, improving workers' well-being, and creating interactions between users and the environment anytime and anywhere. Although several studies on their use in various fields have been performed, there are no systematic reviews on their utilisation in ergonomics. Therefore, we conducted a systematic review to identify wearable devices proposed in the scientific literature for ergonomic purposes and analyse how they can support the improvement of ergonomic conditions. Twenty-eight papers were retrieved and analysed thanks to eleven comparison dimensions related to ergonomic factors, purposes, and criteria, populations, application and validation. The majority of the available devices are sensor systems composed of different types and numbers of sensors located in diverse body parts. These solutions also represent the technology most frequently employed for monitoring and reducing the risk of awkward postures. In addition, smartwatches, body-mounted smartphones, insole pressure systems, and vibrotactile feedback interfaces have been developed for evaluating and/or controlling physical loads or postures. The main results and the defined framework of analysis provide an overview of the state of the art of smart wearables in ergonomics, support the selection of the most suitable ones in industrial and non-industrial settings, and suggest future research directions.

Estimation of Human Center of Mass Position through the Inertial Sensors-Based Methods in Postural Tasks: An Accuracy Evaluation

The estimation of the body’s center of mass (CoM) trajectory is typically obtained using force platforms, or optoelectronic systems (OS), bounding the assessment inside a laboratory setting. The use of magneto-inertial measurement units (MIMUs) allows for more ecological evaluations, and previous studies proposed methods based on either a single sensor or a sensors’ network. In this study, we compared the accuracy of two methods based on MIMUs. Body CoM was estimated during six postural tasks performed by 15 healthy subjects, using data collected by a single sensor on the pelvis (Strapdown Integration Method, SDI), and seven sensors on the pelvis and lower limbs (Biomechanical Model, BM). The accuracy of the two methods was compared in terms of RMSE and estimation of posturographic parameters, using an OS as reference. The RMSE of the SDI was lower in tasks with little or no oscillations, while the BM outperformed in tasks with greater CoM displacement. Moreover, higher correlation coefficients were obtained between the posturographic parameters obtained with the BM and the OS. Our findings showed that the estimation of CoM displacement based on MIMU was reasonably accurate, and the use of the inertial sensors network methods should be preferred to estimate the kinematic parameters.

Prototype System for Measuring and Analyzing Movements of the Upper Limb for the Detection of Occupational Hazards

In the work environment, there are usually different pathologies that are related to Repetitive Efforts and Movements (REM) that tend to predominantly affect the upper limbs. To determine whether a worker is at risk of suffering some type of pathology, observation techniques are usually used by qualified technical personnel. In order to define from quantitative data if there is a risk of suffering a pathology due to movements and repetitive efforts in the upper limb, a prototype of a movement measurement system has been designed and manufactured. This system interferes minimally with the activity studied, maintaining a reduced cost of manufacture and use. The system allows the study of the movements made by the subject in the work environment by determining the origin of the Musculoskeletal Disorder (MSD) from the movements of the elbow and wrist, collecting data on the position and accelerations of the arm, forearm and hand, and taking into account the risk factors established for suffering from an MSD: high repetition of movements, the use of a high force in a repetitive manner, or the adoption of forced positions. The data obtained with this system can be analyzed by qualified personnel from tables, graphs, and 3D animations at the time of execution, or stored for later analysis.

Using a Motion Sensor to Categorize Nonspecific Low Back Pain Patients: A Machine Learning Approach

Nonspecific low back pain (NSLBP) constitutes a critical health challenge that impacts millions of people worldwide with devastating health and socioeconomic consequences. In today’s clinical settings, practitioners continue to follow conventional guidelines to categorize NSLBP patients based on subjective approaches, such as the STarT Back Screening Tool (SBST). This study aimed to develop a sensor-based machine learning model to classify NSLBP patients into different subgroups according to quantitative kinematic data, i.e., trunk motion and balance-related measures, in conjunction with STarT output. Specifically, inertial measurement units (IMU) were attached to the trunks of ninety-four patients while they performed repetitive trunk flexion/extension movements on a balance board at self-selected pace. Machine learning algorithms (support vector machine (SVM) and multi-layer perceptron (MLP)) were implemented for model development, and SBST results were used as ground truth. The results demonstrated that kinematic data could successfully be used to categorize patients into two main groups: high vs. low-medium risk. Accuracy levels of ~75% and 60% were achieved for SVM and MLP, respectively. Additionally, among a range of variables detailed herein, time-scaled IMU signals yielded the highest accuracy levels (i.e., ~75%). Our findings support the improvement and use of wearable systems in developing diagnostic and prognostic tools for various healthcare applications. This can facilitate development of an improved, cost-effective quantitative NSLBP assessment tool in clinical and home settings towards effective personalized rehabilitation.

Using Artificial Intelligence for Pattern Recognition in a Sports Context

Optimizing athlete’s performance is one of the most important and challenging aspects of coaching. Physiological and positional data, often acquired using wearable devices, have been useful to identify patterns, thus leading to a better understanding of the game and, consequently, providing the opportunity to improve the athletic performance. Even though there is a panoply of research in pattern recognition, there is a gap when it comes to non-controlled environments, as during sports training and competition. This research paper combines the use of physiological and positional data as sequential features of different artificial intelligence approaches for action recognition in a real match context, adopting futsal as its case study. The traditional artificial neural networks (ANN) is compared with a deep learning method, Long Short-Term Memory Network, and also with the Dynamic Bayesian Mixture Model, which is an ensemble classification method. The methods were used to process all data sequences, which allowed to determine, based on the balance between precision and recall, that Dynamic Bayesian Mixture Model presents a superior performance, with an F1 score of 80.54% against the 33.31% achieved by the Long Short-Term Memory Network and 14.74% achieved by ANN.