Muscular Strategies for Correcting the Pelvic Position to Improve Posture-An Exploratory Study.

The correction of postural weaknesses through the better positioning of the pelvis is an important approach in sports therapy and physiotherapy. The pelvic position in the sagittal plane is largely dependent on the muscular balance of the ventral and dorsal muscle groups. The aim of this exploratory study was to examine whether healthy persons use similar muscular activation patterns to correct their pelvic position or whether there are different motor strategies. The following muscles were recorded in 41 persons using surface electromyography (EMG): M. trapezius pars ascendens, M. erector spinae pars lumbalis, M. gluteus maximus, M. biceps femoris, M. rectus abdominis, and M. obliquus externus. The participants performed 10 voluntary pelvic movements (retroversion of the pelvis). The anterior pelvic tilt was measured videographically via marker points on the anterior and posterior superior iliac spine. The EMG data were further processed and normalized to the maximum voluntary contraction. A linear regression analysis was conducted to assess the relationship between changes in the pelvic tilt and muscle activities. Subsequently, a Ward clustering analysis was applied to detect potential muscle activation patterns. The differences between the clusters and the pelvic tilt were examined using ANOVA. Cluster analysis revealed the presence of four clusters with different muscle activation patterns in which the abdominal muscles and dorsal muscle groups were differently involved. However, the gluteus maximus muscle was involved in every activation pattern. It also had the strongest correlation with the changes in pelvic tilt. Different individual muscle patterns are used by different persons to correct pelvic posture, with the gluteus maximus muscle apparently playing the most important role. This can be important for therapy, as different muscle strategies should be trained depending on the individually preferred motor patterns.

Impact of Fatigue on Ergonomic Risk Scores and Foot Kinetics: A Field Study Employing Inertial and In-Shoe Plantar Pressure Measurement Devices.

(1) Background: Occupational fatigue is a primary factor leading to work-related musculoskeletal disorders (WRMSDs). Kinematic and kinetic experimental studies have been able to identify indicators of WRMSD, but research addressing real-world workplace scenarios is lacking. Hence, the authors of this study aimed to assess the influence of physical strain on the Borg CR-10 body map, ergonomic risk scores, and foot pressure in a real-world setting. (2) Methods: Twenty-four participants (seventeen men and seven women) were included in this field study. Inertial measurement units (IMUs) (n = 24) and in-shoe plantar pressure measurements (n = 18) captured the workload of production and office workers at the beginning of their work shift and three hours later, working without any break. In addition to the two 12 min motion capture processes, a Borg CR-10 body map and fatigue visual analog scale (VAS) were applied twice. Kinematic and kinetic data were processed using MATLAB and SPSS software, resulting in scores representing the relative distribution of the Rapid Upper Limb Assessment (RULA) and Computer-Assisted Recording and Long-Term Analysis of Musculoskeletal Load (CUELA), and in-shoe plantar pressure. (3) Results: Significant differences were observed between the two measurement times of physical exertion and fatigue, but not for ergonomic risk scores. Contrary to the hypothesis of the authors, there were no significant differences between the in-shoe plantar pressures. Significant differences were observed between the dominant and non-dominant sides for all kinetic variables. (4) Conclusions: The posture scores of RULA and CUELA and in-shoe plantar pressure side differences were a valuable basis for adapting one-sided requirements in the work process of the workers. Traditional observational methods must be adapted more sensitively to detect kinematic deviations at work. The results of this field study enhance our knowledge about the use and benefits of sensors for ergonomic risk assessments and interventions.

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence.

Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.

Machine Learning and Explainable Artificial Intelligence Using Counterfactual Explanations for Evaluating Posture Parameters.

Postural deficits such as hyperlordosis (hollow back) or hyperkyphosis (hunchback) are relevant health issues. Diagnoses depend on the experience of the examiner and are, therefore, often subjective and prone to errors. Machine learning (ML) methods in combination with explainable artificial intelligence (XAI) tools have proven useful for providing an objective, data-based orientation. However, only a few works have considered posture parameters, leaving the potential for more human-friendly XAI interpretations still untouched. Therefore, the present work proposes an objective, data-driven ML system for medical decision support that enables especially human-friendly interpretations using counterfactual explanations (CFs). The posture data for 1151 subjects were recorded by means of stereophotogrammetry. An expert-based classification of the subjects regarding the presence of hyperlordosis or hyperkyphosis was initially performed. Using a Gaussian progress classifier, the models were trained and interpreted using CFs. The label errors were flagged and re-evaluated using confident learning. Very good classification performances for both hyperlordosis and hyperkyphosis were found, whereby the re-evaluation and correction of the test labels led to a significant improvement (MPRAUC = 0.97). A statistical evaluation showed that the CFs seemed to be plausible, in general. In the context of personalized medicine, the present study's approach could be of importance for reducing diagnostic errors and thereby improving the individual adaptation of therapeutic measures. Likewise, it could be a basis for the development of apps for preventive posture assessment.

Assessing the Subjective Effectiveness of Sensorimotor Insoles (SMIs) in Reducing Pain: A Descriptive Multicenter Pilot Study.

This pilot study aimed to investigate the use of sensorimotor insoles in pain reduction, different orthopedic indications, and the wearing duration effects on the development of pain. Three hundred and forty patients were asked about their pain perception using a visual analog scale (VAS) in a pre-post analysis. Three main intervention durations were defined: VAS_post: up to 3 months, 3 to 6 months, and more than 6 months. The results show significant differences for the within-subject factor "time of measurement", as well as for the between-subject factor indication (p < 0.001) and worn duration (p < 0.001). No interaction was found between indication and time of measurements (model A) or between worn duration and time of measurements (model B). The results of this pilot study must be cautiously and critically interpreted, but may support the hypothesis that sensorimotor insoles could be a helpful tool for subjective pain reduction. The missing control group and the lack of confounding variables such as methodological weaknesses, natural healing processes, and complementary therapies must be taken into account. Based on these experiences and findings, a RCT and systematic review will follow.

Reference Values for Sagittal Clinical Posture Assessment in People Aged 10 to 69 Years.

Poor posture is a well-known problem in all age groups and can lead to back pain, which in turn can result in high socio-economic costs. Regular assessment of posture can therefore help to identify postural deficits at an early stage in order to take preventive measures and can therefore be an important tool for promoting public health. We measured the posture of 1127 symptom-free subjects aged 10 to 69 years using stereophotogrammetry and determined the sagittal posture parameters flèche cervicale (FC), flèche lombaire (FL), and kyphosis index (KI) as well as the values standardized to the trunk height (FC%, FL%, KI%). FC, FC%, KI, and KI% showed an increase with age in men but not in women, and a difference between the sexes. FL remained largely constant with age, although FL% had significantly greater values in women than men. Postural parameters correlated only moderately or weakly with body mass index. Reference values were determined for different age groups and for both sexes. Since the parameters analyzed can also be determined by simple and non-instrumental methods in medical office, they are suitable for performing preventive checks in daily medical or therapeutic practice.

In Vivo Monitoring of Acute and Intermittent Fatigue in Sport Climbing Using Near-Infrared Spectroscopy Wearable Biosensors.

The objectification of acute fatigue (during isometric muscle contraction) and cumulative fatigue (due to multiple intermittent isometric muscle contractions) plays an important role in sport climbing. The data of 42 participants were used in the study. Climbing performance was operationalized using maximal climbing-specific holding time (CSHT) by performing dead hangs. The test started with an initial measurement of handgrip strength (HGS) followed by three intermittent measurements of CSHT and HGS. During the test, finger flexor muscle oxygen saturation (SmO2) was measured using a near-infrared spectroscopy wearable biosensor. Significant reductions in CSHT and HGS could be found (p < 0.001), which indicates that the consecutive maximal isometric holding introduces cumulative fatigue. The reduction in CSHT did not correlate with a reduction in HGS over multiple consecutive maximal dead hangs (p > 0.35). Furthermore, there were no significant differences in initial SmO2 level, SmO2 level at termination, SmO2 recovery, and mean negative slope of the SmO2 saturation reduction between the different measurements (p > 0.24). Significant differences were found between pre-, termination-, and recovery- (10 s after termination) SmO2 levels (p < 0.001). Therefore, monitoring acute fatigue using athletes' termination SmO2 saturation seems promising. By contrast, the measurement of HGS and muscle oxygen metabolism seems inappropriate for monitoring cumulative fatigue during intermittent isometric climbing-specific muscle contractions.

Evaluation of Influencing Factors on the Maximum Climbing Specific Holding Time: An Inferential Statistics and Machine Learning Approach.

Handgrip strength (HGS) appears to be an indicator of climbing performance. The transferability of HGS measurements obtained using a hand dynamometer and factors that influence the maximal climbing-specific holding time (CSHT) are largely unclear. Forty-eight healthy subjects (27 female, 21 male; age: 22.46 ± 3.17 years; height: 172.76 ± 8.91 cm; weight: 69.07 ± 12.41 kg; body fat: 20.05% ± 7.95%) underwent a maximal pull-up test prior to the experiment and completed a self-assessment using a Likert scale questionnaire. HGS was measured using a hand dynamometer, whereas CSHT was measured using a fingerboard. Multiple linear regressions showed that weight, maximal number of pull-ups, HGS normalized by subject weight, and length of the middle finger had a significant effect on the maximal CSHT (non-dominant hand: R2corr = 0.63; dominant hand: R2corr = 0.55). Deeper exploration using a machine learning model including all available data showed a predictive performance with R2 = 0.51 and identified another relevant parameter for the regression model. These results call into question the use of hand dynamometers and highlight the performance-related importance of body weight in climbing practice. The results provide initial indications that finger length may be used as a sub-factor in talent scouting.

Effects of Feedback-Supported Online Training during the Coronavirus Lockdown on Posture in Children and Adolescents.

(1) Background. The coronavirus pandemic had a serious impact on the everyday life of children and young people with sometimes drastic effects on daily physical activity time that could have led to posture imbalances. The aim of the study was to examine whether a six-week, feedback-supported online training programme could improve posture parameters in young soccer players. (2) Methods. Data of 170 adolescent soccer players (age 15.6 ± 1.6 years) were analyzed. A total of 86 soccer players of a youth academy participated in an online training program that included eight exercises twice per week for 45 min (Zoom group). The participants' exercise execution could be monitored and corrected via smartphone or laptop camera. Before and after the training intervention, participants' posture was assessed using photographic analysis. The changes of relevant posture parameters (perpendicular positions of ear, shoulder and hips, pelvic tilt, trunk tilt and sacral angle) were statistically tested by robust mixed ANOVA using trimmed means. Postural parameters were also assessed post hoc at 8-week intervals in a control group of 84 participants of the same age. (3) Results. We found a statistically significant interaction (p < 0.05) between time and group for trunk tilt, head and shoulder protrusion and for hip anteversion in the Zoom group. No changes were found for these parameters in the control group. For pelvic tilt no significant changes were found. (4) Conclusions. Feedback-based online training with two 45 min sessions per week can improve postural parameters in adolescent soccer players over a period of six weeks.

Effects of Unilateral Muscle Fatigue on Thermographic Skin Surface Temperature of Back and Abdominal Muscles-A Pilot Study.

The present study aimed to assess the effects of asymmetric muscle fatigue on the skin surface temperature of abdominal and back muscles. The study was based on a pre-post/follow-up design with one group and included a total of 41 subjects (22 male, 19 female; age, 22.63 ± 3.91; weight, 71.89 ± 12.97 kg; height, 173.36 ± 9.95). All the participants were asked to perform side bends in sets of 20 repetitions on a Roman chair until complete exhaustion. The pre-, post- and follow-up test (24 h after) skin surface temperatures were recorded with infrared thermography. Subjective muscle soreness and muscle fatigue were analyzed using two questionnaires. The results of the post hoc tests showed that skin temperature was statistically significantly lower in the post-tests than in the pre- and follow-up tests, but no meaningful differences existed between the pre- and follow-up tests. Asymmetric side differences were found in the post-test for the upper and lower areas of the back. Differences were also noted for the front in both the upper and lower areas. No thermographic side asymmetries were found at the pre- or follow-up measurement for either the back or the front. Our results support the potential of using thermographic skin surface temperature to monitor exercise and recovery in athletes, as well as its use in rehabilitational exercise selection.

Machine learning techniques demonstrating individual movement patterns of the vertebral column: the fingerprint of spinal motion.

Surface topography systems enable the capture of spinal dynamic movement; however, it is unclear whether vertebral dynamics are unique enough to identify individuals. Therefore, in this study, we investigated whether the identification of individuals is possible based on dynamic spinal data. Three different data representations were compared (automated extracted features using contrastive loss and triplet loss functions, as well as simple descriptive statistics). High accuracies indicated the possible existence of a personal spinal 'fingerprint', therefore enabling subject recognition. The present work forms the basis for an objective comparison of subjects and the transfer of the method to clinical use cases.

Conceptual Structure and Current Trends in Artificial Intelligence, Machine Learning, and Deep Learning Research in Sports: A Bibliometric Review.

Artificial intelligence and its subcategories of machine learning and deep learning are gaining increasing importance and attention in the context of sports research. This has also meant that the number of corresponding publications has become complex and unmanageably large in human terms. In the current state of the research field, there is a lack of bibliometric analysis, which would prove useful for obtaining insights into the large amounts of available literature. Therefore, the present work aims to identify important research issues, elucidate the conceptual structure of the research field, and unpack the evolutionary trends and the direction of hot topics regarding key themes in the research field of artificial intelligence in sports. Using the Scopus database, 1215 documents (reviews and articles) were selected. Bibliometric analysis was performed using VOSviewer and bibliometrix R package. The main findings are as follows: (a) the literature and research interest concerning AI and its subcategories is growing exponentially; (b) the top 20 most cited works comprise 32.52% of the total citations; (c) the top 10 journals are responsible for 28.64% of all published documents; (d) strong collaborative relationships are present, along with small, isolated collaboration networks of individual institutions; (e) the three most productive countries are China, the USA, and Germany; (f) different research themes can be characterized using author keywords with current trend topics, e.g., in the fields of biomechanics, injury prevention or prediction, new algorithms, and learning approaches. AI research activities in the fields of sports pedagogy, sports sociology, and sports economics seem to have played a subordinate role thus far. Overall, the findings of this study expand knowledge on the research situation as well as the development of research topics regarding the use of artificial intelligence in sports, and may guide researchers to identify currently relevant topics and gaps in the research.

Automated detection and explainability of pathological gait patterns using a one-class support vector machine trained on inertial measurement unit based gait data.

BACKGROUND: Machine learning approaches for the classification of pathological gait based on kinematic data, e.g. derived from inertial sensors, are commonly used in terms of a multi-class classification problem. However, there is a lack of research regarding one-class classifiers that are independent of certain pathologies. Therefore, it was the aim of this work to design a one-class classifier based on healthy norm-data that provides not only a prediction probability but rather an explanation of the classification decision, increasing the acceptance of this machine learning approach. METHODS: The inertial sensor based gait kinematics of 25 healthy subjects was employed to train a one-class support vector machine. 25 healthy subjects, 20 patients after total hip arthroplasty and one transfemoral amputee served to validate the classifier. Prediction probabilities and feature importance scores were estimated for each subject. FINDINGS: The support vector machine predicted 100% of the patients as outliers from the healthy group. Three healthy subjects were predicted as outliers. The feature importance calculation revealed the hip in the sagittal plane as most relevant feature concerning the group after total hip arthroplasty. For the misclassified healthy subject with the lowest probability score the knee flexion and the pelvis obliquity were identified. INTERPRETATION: The support vector machine seems a useful tool to identify outliers from a healthy norm-group. The feature importance examination proved to provide valuable information on the musculoskeletal status of the subjects. In this combination, the present approach could be employed in various disciplines to identify abnormal gait and suggest subsequent training.

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.

General method for automated feature extraction and selection and its application for gender classification and biomechanical knowledge discovery of sex differences in spinal posture during stance and gait.

Modern technologies enable to capture multiple biomechanical parameters often resulting in relational data. The current work proposes a generally applicable method comprising automated feature extraction, ensemble feature selection and classification to best capture the potentials of the data also for generating new biomechanical knowledge. Its benefits are demonstrated in the concrete biomechanically and medically relevant use case of gender classification based on spinal data for stance and gait. Very good results for accuracy were obtained using gait data. Dynamic movements of the lumbar spine in sagittal and frontal plane and of the pelvis in frontal plane best map gender differences.

Interpretability of Input Representations for Gait Classification in Patients after Total Hip Arthroplasty.

Many machine learning models show black box characteristics and, therefore, a lack of transparency, interpretability, and trustworthiness. This strongly limits their practical application in clinical contexts. For overcoming these limitations, Explainable Artificial Intelligence (XAI) has shown promising results. The current study examined the influence of different input representations on a trained model's accuracy, interpretability, as well as clinical relevancy using XAI methods. The gait of 27 healthy subjects and 20 subjects after total hip arthroplasty (THA) was recorded with an inertial measurement unit (IMU)-based system. Three different input representations were used for classification. Local Interpretable Model-Agnostic Explanations (LIME) was used for model interpretation. The best accuracy was achieved with automatically extracted features (mean accuracy Macc = 100%), followed by features based on simple descriptive statistics (Macc = 97.38%) and waveform data (Macc = 95.88%). Globally seen, sagittal movement of the hip, knee, and pelvis as well as transversal movement of the ankle were especially important for this specific classification task. The current work shows that the type of input representation crucially determines interpretability as well as clinical relevance. A combined approach using different forms of representations seems advantageous. The results might assist physicians and therapists finding and addressing individual pathologic gait patterns.