Recurrence quantification analysis and support vector machines for golf handicap and low back pain EMG classification

Can Data-Driven Supervised Machine Learning Approaches Applied to Infrared Thermal Imaging Data Estimate Muscular Activity and Fatigue?

Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless EMG devices are still sensitive to motion artifacts and often not comfortable for long monitoring. In this study, a non-invasive contactless method to estimate parameters indicative of muscular activity and fatigue, as they are assessed by EMG, through infrared thermal imaging (IRI) and cross-validated machine learning (ML) approaches is described. Particularly, 10 healthy participants underwent five series of bodyweight squats until exhaustion interspersed by 1 min of rest. During exercising, the vastus medialis activity and its temperature were measured through sEMG and IRI, respectively. The EMG average rectified value (ARV) and the median frequency of the power spectral density (MDF) of each series were estimated through several ML approaches applied to IRI features, obtaining good estimation performances (r = 0.886, p < 0.001 for ARV, and r = 0.661, p < 0.001 for MDF). Although EMG and IRI measure physiological processes of a different nature and are not interchangeable, these results suggest a potential link between skin temperature and muscle activity and fatigue, fostering the employment of contactless methods to deliver metrics of muscular activity in a non-invasive and comfortable manner in sports and clinical applications.

Machine learning approaches applied in spinal pain research

The purpose of this narrative review is to provide a critical reflection of how analytical machine learning approaches could provide the platform to harness variability of patient presentation to enhance clinical prediction. The review includes a summary of current knowledge on the physiological adaptations present in people with spinal pain. We discuss how contemporary evidence highlights the importance of not relying on single features when characterizing patients given the variability of physiological adaptations present in people with spinal pain. The advantages and disadvantages of current analytical strategies in contemporary basic science and epidemiological research are reviewed and we consider how analytical machine learning approaches could provide the platform to harness the variability of patient presentations to enhance clinical prediction of pain persistence or recurrence. We propose that machine learning techniques can be leveraged to translate a potentially heterogeneous set of variables into clinically useful information with the potential to enhance patient management.

Multiplex Recurrence Network Analysis of Inter-Muscular Coordination During Sustained Grip and Pinch Contractions at Different Force Levels

Production of functional forces by human motor systems require coordination across multiple muscles. Grip and pinch are two prototypes for grasping force production. Each grasp plays a role in a range of hand functions and can provide an excellent paradigm for studying fine motor control. Despite previous investigations that have characterized muscle synergies during general force production, it is still unclear how intermuscular coordination differs between grip and pinch and across different force outputs. Traditional muscle synergy analyses, such as non-negative matrix factorization or principal component analysis, utilize dimensional reduction without consideration of nonlinear characteristics of muscle co-activations. In this study, we investigated the novel method of multiplex recurrence networks (MRN) to assess the inter-muscular coordination for both grip and pinch at different force levels. Unlike traditional methods, the MRN can leverage intrinsic similarities in muscle contraction dynamics and project its layers to the corresponding weighted network (WN) to better model muscle interactions. Twenty-four healthy volunteers were instructed to grip and pinch an apparatus with force production at 30%, 50%, and 70% of their respective maximal voluntary contraction (MVC). The surface electromyography (sEMG) signals were recorded from eight muscles, including intrinsic and extrinsic muscles spanning the hand and forearm. The sEMG signals were then analyzed using MRNs and WNs. Interlayer mutual information ( I ) and average edge overlap ( ω ) of MRNs and average shortest path length ( L ) of WNs were computed and compared across groups for grasp types (grip vs. pinch) and force levels (30%, 50% and 70% MVC). Results showed that the extrinsic, rather than the intrinsic muscles, had significant differences in network parameters between both grasp types ( ), and force levels ( ), and especially at higher force levels. Furthermore, I and ω were strengthened over time ( ) except with pinch at 30% MVC. Results suggest that the central nervous system (CNS) actively increases cortical oscillations over time in response to increasing force levels and changes in force production with different sustained grasping types. Muscle coupling in extrinsic muscles was higher than in intrinsic muscles for both grip and pinch. The MRNs may be a valuable tool to provide greater insights into inter-muscular coordination patterns of clinical populations, assess neuromuscular function, or stabilize force control in prosthetic hands.

Which subject-related variables contribute to movement variability during a simulated repetitive and standardised occupational task? Recurrence quantification analysis of surface electromyographic signals

Movement variability is a component of human movement. This study applied recurrence quantification analysis (RQA) on electromyographic signals to determine the effects of two types of variables on movement variability during a short, simulated repetitive and standardised occupational clip-fitting task. The electrical activity of six muscles in the dominant upper limb was recorded in 21 participants. Variables related to the task performance (insertion force and movements performed when fitting clips) affected RQA measures: recurrence rate (RR), percentage of determinism (DET) and diagonal line length entropy (ENT). Variables related to participant's characteristics (sex, age, and BMI) affected only DET and ENT. A constrasting variability was observed such as a high-DET value combined with a high-ENT value and inversely. Variables affected mainly the recurrences organisation of the more distal muscles. Even if movement variability is complex, it should be considered by ergonomists and work place designers to better understanding of operators' movements. Practitioner summary: It is essential to consider the complexity of operators' movement variability to understand their activities. Based on intrinsic movement variability knowledge, ergonomists and work place designers will be able to modulate the movement variability by acting on workstation designs and occupational organisation with the aim of preserving operators' health. Abbreviations: RR: recurrence rate; DET: percentage of determinism; ENT: diagonal line length entropy; BMI: body mass index; FDS: flexor digitorum superficialis; EXT: extensor digitorum communis; BIC: biceps brachii; TRI: triceps brachii; DEL: deltoideus anterior; TRA: trapezius pars descendens; F: female; M: male; S: supinated; P: pronated; CM: continuous movement; DM: discontinuous movement.

Deep Transfer Learning for Vulnerable Road Users Detection using Smartphone Sensors Data

As the Autonomous Vehicle (AV) industry is rapidly advancing, the classification of non-motorized (vulnerable) road users (VRUs) becomes essential to ensure their safety and to smooth operation of road applications. The typical practice of non-motorized road users’ classification usually takes significant training time and ignores the temporal evolution and behavior of the signal. In this research effort, we attempt to detect VRUs with high accuracy be proposing a novel framework that includes using Deep Transfer Learning, which saves training time and cost, to classify images constructed from Recurrence Quantification Analysis (RQA) that reflect the temporal dynamics and behavior of the signal. Recurrence Plots (RPs) were constructed from low-power smartphone sensors without using GPS data. The resulted RPs were used as inputs for different pre-trained Convolutional Neural Network (CNN) classifiers including constructing 227 × 227 images to be used for AlexNet and SqueezeNet; and constructing 224 × 224 images to be used for VGG16 and VGG19. Results show that the classification accuracy of Convolutional Neural Network Transfer Learning (CNN-TL) reaches 98.70%, 98.62%, 98.71%, and 98.71% for AlexNet, SqueezeNet, VGG16, and VGG19, respectively. Moreover, we trained resnet101 and shufflenet for a very short time using one epoch of data and then used them as weak learners, which yielded 98.49% classification accuracy. The results of the proposed framework outperform other results in the literature (to the best of our knowledge) and show that using CNN-TL is promising for VRUs classification. Because of its relative straightforwardness, ability to be generalized and transferred, and potential high accuracy, we anticipate that this framework might be able to solve various problems related to signal classification.

Artificial intelligence to improve back pain outcomes and lessons learnt from clinical classification approaches: three systematic reviews

Artificial intelligence and machine learning (AI/ML) could enhance the ability to detect patterns of clinical characteristics in low-back pain (LBP) and guide treatment. We conducted three systematic reviews to address the following aims: (a) review the status of AI/ML research in LBP, (b) compare its status to that of two established LBP classification systems (STarT Back, McKenzie). AI/ML in LBP is in its infancy: 45 of 48 studies assessed sample sizes <1000 people, 19 of 48 studies used ≤5 parameters in models, 13 of 48 studies applied multiple models and attained high accuracy, 25 of 48 studies assessed the binary classification of LBP versus no-LBP only. Beyond the 48 studies using AI/ML for LBP classification, no studies examined use of AI/ML in prognosis prediction of specific sub-groups, and AI/ML techniques are yet to be implemented in guiding LBP treatment. In contrast, the STarT Back tool has been assessed for internal consistency, test-retest reliability, validity, pain and disability prognosis, and influence on pain and disability treatment outcomes. McKenzie has been assessed for inter- and intra-tester reliability, prognosis, and impact on pain and disability outcomes relative to other treatments. For AI/ML methods to contribute to the refinement of LBP (sub-)classification and guide treatment allocation, large data sets containing known and exploratory clinical features should be examined. There is also a need to establish reliability, validity, and prognostic capacity of AI/ML techniques in LBP as well as its ability to inform treatment allocation for improved patient outcomes and/or reduced healthcare costs.

Sport Biomechanics Applications Using Inertial, Force, and EMG Sensors: A Literature Overview

In the last few decades, a number of technological developments have advanced the spread of wearable sensors for the assessment of human motion. These sensors have been also developed to assess athletes' performance, providing useful guidelines for coaching, as well as for injury prevention. The data from these sensors provides key performance outcomes as well as more detailed kinematic, kinetic, and electromyographic data that provides insight into how the performance was obtained. From this perspective, inertial sensors, force sensors, and electromyography appear to be the most appropriate wearable sensors to use. Several studies were conducted to verify the feasibility of using wearable sensors for sport applications by using both commercially available and customized sensors. The present study seeks to provide an overview of sport biomechanics applications found from recent literature using wearable sensors, highlighting some information related to the used sensors and analysis methods. From the literature review results, it appears that inertial sensors are the most widespread sensors for assessing athletes' performance; however, there still exist applications for force sensors and electromyography in this context. The main sport assessed in the studies was running, even though the range of sports examined was quite high. The provided overview can be useful for researchers, athletes, and coaches to understand the technologies currently available for sport performance assessment.

Interpretable machine learning models for classifying low back pain status using functional physiological variables

PURPOSE

To evaluate the predictive performance of statistical models which distinguishes different low back pain (LBP) sub-types and healthy controls, using as input predictors the time-varying signals of electromyographic and kinematic variables, collected during low-load lifting.

METHODS

Motion capture with electromyography (EMG) assessment was performed on 49 participants [healthy control (con) = 16, remission LBP (rmLBP) = 16, current LBP (LBP) = 17], whilst performing a low-load lifting task, to extract a total of 40 predictors (kinematic and electromyographic variables). Three statistical models were developed using functional data boosting (FDboost), for binary classification of LBP statuses (model 1: con vs. LBP; model 2: con vs. rmLBP; model 3: rmLBP vs. LBP). After removing collinear predictors (i.e. a correlation of > 0.7 with other predictors) and inclusion of the covariate sex, 31 predictors were included for fitting model 1, 31 predictors for model 2, and 32 predictors for model 3.

RESULTS

Seven EMG predictors were selected in model 1 (area under the receiver operator curve [AUC] of 90.4%), nine predictors in model 2 (AUC of 91.2%), and seven predictors in model 3 (AUC of 96.7%). The most influential predictor was the biceps femoris muscle (peak [Formula: see text]  = 0.047) in model 1, the deltoid muscle (peak [Formula: see text] =  0.052) in model 2, and the iliocostalis muscle (peak [Formula: see text] =  0.16) in model 3.

CONCLUSION

The ability to transform time-varying physiological differences into clinical differences could be used in future prospective prognostic research to identify the dominant movement impairments that drive the increased risk. These slides can be retrieved under Electronic Supplementary Material.

Methodology Proposal of EMG Hand Movement Classification Based on Cross Recurrence Plots

Dealing with electromyography (EMG) signals is often not simple. The nature of these signals is nonstationary, noisy, and high dimensional. These EMG characteristics make their predictability even more challenging. Cross recurrence plots (CRPs) have demonstrated in many works their capability of detecting very subtle patterns in signals often buried in a noisy environment. In this contribution, fifty subjects performed ten different hand movements with each hand with the aid of electrodes placed in each arm. Furthermore, the nonlinear features of each subject's signals using cross recurrence quantification analysis (CRQA) have been performed. Also, a novel methodology is proposed using CRQA as the mainstream technique to detect and classify each of the movements presented in this study. Additional tools were presented to determine to which extent this proposed methodology is able to avoid false classifications, thus demonstrating that this methodology is feasible to classify surface EMG (SEMG) signals with good accuracy, sensitivity, and specificity. Lastly, the results were compared with traditional machine learning methods, and the advantages of using the proposed methodology above such methods are highlighted.

Systematic review of musculoskeletal injuries in professional golfers

OBJECTIVE

The distribution of injuries affecting professional golfers is yet to be fully understood. We performed a systematic review of the clinical literature to establish the epidemiology of musculoskeletal injuries affecting professional golfers.

DESIGN

Systematic review.

DATA SOURCES

Searched databases in July 2018 were PubMed, SPORTDiscus and Embase.

ELIGIBILITY CRITERIA

Published observational research articles relating to the incidence or prevalence of musculoskeletal injuries in professional golfers, which were written in the English language and not restricted by age or gender.

RESULTS

Of the 1863 studies identified on the initial search, 5 studies were found to satisfy the inclusion criteria for analysis. The mean age of the golfers in these studies was 34.8 (±3.6) years. The gender of patients in included studies compromised 72% males and 28% females. Four studies reported that lumbar spine injuries were the most common (range 22%-34%). Excluding injuries to the spine (lumbar, thoracic and cervical), the hand/wrist was the next most common region of injury (range 6%-37%). The quality of the studies was relatively poor with no study satisfying >50% of the quality assessment tool questions and only one study giving a clear definition of how they defined injury.

CONCLUSION

There is a paucity of well-designed epidemiological studies evaluating musculoskeletal injuries affecting professional golfers. Injuries to the spine are the most frequently affected region, followed by the hand/wrist. This study has identified targeted areas of future research that aims to improve the management of injuries among professional golfers.

Risk Factors Associated With Low Back Pain in Golfers: A Systematic Review and Meta-analysis

Context:

Low back pain is common in golfers. The risk factors for golf-related low back pain are unclear but may include individual demographic, anthropometric, and practice factors as well as movement characteristics of the golf swing.

Objective:

The aims of this systematic review were to summarize and synthesize evidence for factors associated with low back pain in recreational and professional golfers.

Data Sources:

A systematic literature search was conducted using the PubMed, CINAHL, and SPORTDiscus electronic databases through September 2017.

Study Selection:

Studies were included if they quantified demographic, anthropometric, biomechanical, or practice variables in individuals with and without golf-related low back pain.

Study Design:

Systematic review and meta-analysis.

Level of Evidence:

Level 3.

Data Extraction:

Studies were independently reviewed for inclusion by 2 authors, and the following data were extracted: characterization of low back pain, participant demographics, anthropometrics, biomechanics, strength/flexibility, and practice characteristics. The methodological quality of studies was appraised by 3 authors using a previously published checklist. Where possible, individual and pooled effect sizes of select variables of interest were calculated for differences between golfers with and without pain.

Results:

The search retrieved 73 articles, 19 of which met the inclusion criteria (12 case-control studies, 5 cross-sectional studies, and 2 prospective longitudinal studies). Methodological quality scores ranged from 12.5% to 100.0%. Pooled analyses demonstrated a significant association between increased age and body mass and golf-related low back pain in cross-sectional/case-control studies. Prospective data indicated that previous history of back pain predicts future episodes of pain.

Conclusion:

Individual demographic and anthropometric characteristics may be associated with low back pain, but this does not support a relationship between swing characteristics and the development of golf-related pain. Additional high-quality prospective studies are needed to clarify risk factors for back pain in golfers.

The classification for "equilibrium triad" sensory loss based on sEMG signals of calf muscles

Surface Electromyography (sEMG) has been commonly applied for analysing the electrical activities of skeletal muscles. The sensory system of maintaining posture balance includes vision, proprioception and vestibular senses. In this work, an attempt is made to classify whether the body is missing one of the sense during balance control by using sEMG signals. A trial of combination with different features and muscles is also developed. The results demonstrate that the classification accuracy between vision loss and the normal condition is higher than the one between vestibular sense loss and normal condition. When using different features and muscles, the impact on classification results is also different. The outcomes of this study could aid the development of sEMG based classification for the function of sensory systems during human balance movement.

Electromyographic analyses of the erector spinae muscles during golf swings using four different clubs

The purpose of this study was to compare the electromyography (EMG) patterns of the thoracic and lumbar regions of the erector spinae (ES) muscle during the golf swing whilst using four different golf clubs. Fifteen right-handed male golfers performed a total of twenty swings in random order using the driver, 4-iron, 7-iron and pitching-wedge. Surface EMG was recorded from the lead and trail sides of the thoracic and lumbar regions of the ES muscle (T8, L1 and L5 lateral to the spinous-process). Three-dimensional high-speed video analysis was used to identify the backswing, forward swing, acceleration, early and late follow-through phases of the golf swing. No significant differences in muscle-activation levels from the lead and trail sides of the thoracic and lumbar regions of the ES muscle were displayed between the driver, 4-iron, 7-iron and pitching-wedge (P > 0.05). The highest mean thoracic and lumbar ES muscle-activation levels were displayed in the forward swing (67-99% MVC) and acceleration (83-106% MVC) phases of the swing for all clubs tested. The findings from this study show that there were no significant statistical differences between the driver, 4-iron, 7-iron and pitching-wedge when examining muscle activity from the thoracic and lumbar regions of the ES muscle.

Comparison of Thoracic and Lumbar Erector Spinae Muscle Activation Before and After a Golf Practice Session

Lower back pain is commonly associated with golfers. The study aimed: to determine whether thoracic- and lumbar-erector-spinae muscle display signs of muscular fatigue after completing a golf practice session, and to examine the effect of the completed practice session on club head speed, ball speed and absolute carry distance performance variables. Fourteen right-handed male golfers participated in the laboratory-based-study. Surface electromyography (EMG) data was collected from the lead and trail sides of the thoracic- and lumbar-erector-spinae muscle. Normalized root mean squared (RMS) EMG activation levels and performance variables for the golf swings were compared before and after the session. Fatigue was assessed using median frequency (MDF) and RMS during the maximum voluntary contraction (MVC) performed before and after the session. No significant differences were observed in RMS thoracic- and lumbar-erector-spinae muscle activation levels during the five phases of the golf swing and performance variables before and after the session (p > .05). Significant changes were displayed in MDF and RMS when comparing the MVC performed before and after the session (p < .05). Fatigue was evident in the trail side of the erector-spinae muscle after the session.