Abstract Data science has transformed fields such as computer vision and economics. The ability of modern data science methods to extract insights from large, complex, heterogeneous, and noisy ...datasets is beginning to provide a powerful complement to the traditional approaches of experimental motion capture and biomechanical modeling. The purpose of this article is to provide a perspective on how data science methods can be incorporated into our field to advance our understanding of gait biomechanics and improve treatment planning procedures. We provide examples of how data science approaches have been applied to biomechanical data. We then discuss the challenges that remain for effectively using data science approaches in clinical gait analysis and gait biomechanics research, including the need for new tools, better infrastructure and incentives for sharing data, and education across the disciplines of biomechanics and data science. By addressing these challenges, we can revolutionize treatment planning and biomechanics research by capitalizing on the wealth of knowledge gained by gait researchers over the past decades and the vast, but often siloed, data that are collected in clinical and research laboratories around the world.
Low back pain (LBP) is a major global disability contributor with profound health and socio-economic implications. The predominant form is non-specific LBP (NSLBP), lacking treatable pathology. ...Active physical interventions tailored to individual needs and capabilities are crucial for its management. However, the intricate nature of NSLBP and complexity of clinical classification systems necessitating extensive clinical training, hinder customised treatment access. Recent advancements in machine learning and computer vision demonstrate promise in characterising NSLBP altered movement patters through wearable sensors and optical motion capture. This study aimed to develop and evaluate a machine learning model (i.e., 'BACK-to-MOVE') for NSLBP classification trained with expert clinical classification, spinal motion data from a standard video alongside patient-reported outcome measures (PROMs).
Synchronised video and three-dimensional (3D) motion data was collected during forward spinal flexion from 83 NSLBP patients. Two physiotherapists independently classified them as motor control impairment (MCI) or movement impairment (MI), with conflicts resolved by a third expert. The Convolutional Neural Networks (CNNs) architecture, HigherHRNet, was chosen for effective pose estimation from video data. The model was validated against 3D motion data (subset of 62) and trained on the freely available MS-COCO dataset for feature extraction. The Back-to-Move classifier underwent fine-tuning through feed-forward neural networks using labelled examples from the training dataset. Evaluation utilised 5-fold cross-validation to assess accuracy, specificity, sensitivity, and F1 measure.
Pose estimation's Mean Square Error of 0.35 degrees against 3D motion data demonstrated strong criterion validity. Back-to-Move proficiently differentiated MI and MCI classes, yielding 93.98% accuracy, 96.49% sensitivity (MI detection), 88.46% specificity (MCI detection), and an F1 measure of .957. Incorporating PROMs curtailed classifier performance (accuracy: 68.67%, sensitivity: 91.23%, specificity: 18.52%, F1: .800).
This study is the first to demonstrate automated clinical classification of NSLBP using computer vision and machine learning with standard video data, achieving accuracy comparable to expert consensus. Automated classification of NSLBP based on altered movement patters video-recorded during routine clinical examination could expedite personalised NSLBP rehabilitation management, circumventing existing healthcare constraints. This advancement holds significant promise for patients and healthcare services alike.
Equinus deformity is one of the most common gait deformities in children with cerebral palsy. We examined whether estimates of gastrocnemius length in gait could identify limbs likely to have ...short-term and long-term improvements in ankle kinematics following gastrocnemius lengthening surgery to correct equinus. We retrospectively analyzed data of 891 limbs that underwent a single-event multi-level surgery (SEMLS), and categorized outcomes based on the normalcy of ankle kinematics. Limbs with short gastrocnemius lengths that received a gastrocnemius lengthening surgery as part of a SEMLS (case limbs) were 2.2 times more likely than overtreated limbs (i.e., limbs who did not have short lengths, but still received a lengthening surgery) to have a good surgical outcome at the follow-up gait visit (good outcome rate of 71% vs. 33%). Case limbs were 1.2 times more likely than control limbs (i.e., limbs that had short gastrocnemius lengths but no lengthening surgery) to have a good outcome (71% vs. 59%). Three-fourths of the case limbs with a good outcome at the follow-up gait visit maintained this outcome over time, compared to only one-half of the overtreated limbs. Our results caution against over-prescription of gastrocnemius lengthening surgery and suggest gastrocnemius lengths can be used to identify good surgical candidates.
It has been hypothesized that the central nervous system simplifies the production of movement by limiting motor commands to a small set of modules known as muscle synergies. Recently, investigators ...have questioned whether a low-dimensional controller can produce the rich and flexible behaviours seen in everyday movements. To study this issue, we implemented muscle synergies in a biomechanically realistic model of the human upper extremity and performed computational experiments to determine whether synergies introduced task performance deficits, facilitated the learning of movements, and generalized to different movements. We derived sets of synergies from the muscle excitations our dynamic optimizations computed for a nominal task (reaching in a plane). Then we compared the performance and learning rates of a controller that activated all muscles independently to controllers that activated the synergies derived from the nominal reaching task. We found that a controller based on synergies had errors within 1 cm of a full-dimensional controller and achieved faster learning rates (as estimated from computational time to converge). The synergy-based controllers could also accomplish new tasks-such as reaching to targets on a higher or lower plane, and starting from alternative initial poses-with average errors similar to a full-dimensional controller.
Abstract Pathological movement patterns like crouch gait are characterized by abnormal kinematics and muscle activations that alter how muscles support the body weight during walking. Individual ...muscles are often the target of interventions to improve crouch gait, yet the roles of individual muscles during crouch gait remain unknown. The goal of this study was to examine how muscles contribute to mass center accelerations and joint angular accelerations during single-limb stance in crouch gait, and compare these contributions to unimpaired gait. Subject-specific dynamic simulations were created for ten children who walked in a mild crouch gait and had no previous surgeries. The simulations were analyzed to determine the acceleration of the mass center and angular accelerations of the hip, knee, and ankle generated by individual muscles. The results of this analysis indicate that children walking in crouch gait have less passive skeletal support of body weight and utilize substantially higher muscle forces to walk than unimpaired individuals. Crouch gait relies on the same muscles as unimpaired gait to accelerate the mass center upward, including the soleus, vasti, gastrocnemius, gluteus medius, rectus femoris, and gluteus maximus. However, during crouch gait, these muscles are active throughout single-limb stance, in contrast to the modulation of muscle forces seen during single-limb stance in an unimpaired gait. Subjects walking in crouch gait rely more on proximal muscles, including the gluteus medius and hamstrings, to accelerate the mass center forward during single-limb stance than subjects with an unimpaired gait.
Creating large-scale public datasets of human motion biomechanics could unlock data-driven breakthroughs in our understanding of human motion, neuromuscular diseases, and assistive devices. However, ...the manual effort currently required to process motion capture data and quantify the kinematics and dynamics of movement is costly and limits the collection and sharing of large-scale biomechanical datasets. We present a method, called AddBiomechanics, to automate and standardize the quantification of human movement dynamics from motion capture data. We use linear methods followed by a non-convex bilevel optimization to scale the body segments of a musculoskeletal model, register the locations of optical markers placed on an experimental subject to the markers on a musculoskeletal model, and compute body segment kinematics given trajectories of experimental markers during a motion. We then apply a linear method followed by another non-convex optimization to find body segment masses and fine tune kinematics to minimize residual forces given corresponding trajectories of ground reaction forces. The optimization approach requires approximately 3-5 minutes to determine a subject's skeleton dimensions and motion kinematics, and less than 30 minutes of computation to also determine dynamically consistent skeleton inertia properties and fine-tuned kinematics and kinetics, compared with about one day of manual work for a human expert. We used AddBiomechanics to automatically reconstruct joint angle and torque trajectories from previously published multi-activity datasets, achieving close correspondence to expert-calculated values, marker root-mean-square errors less than 2 cm, and residual force magnitudes smaller than 2% of peak external force. Finally, we confirmed that AddBiomechanics accurately reproduced joint kinematics and kinetics from synthetic walking data with low marker error and residual loads. We have published the algorithm as an open source cloud service at AddBiomechanics.org, which is available at no cost and asks that users agree to share processed and de-identified data with the community. As of this writing, hundreds of researchers have used the prototype tool to process and share about ten thousand motion files from about one thousand experimental subjects. Reducing the barriers to processing and sharing high-quality human motion biomechanics data will enable more people to use state-of-the-art biomechanical analysis, do so at lower cost, and share larger and more accurate datasets.
Intratumoral collagen cross-links heighten stromal stiffness and stimulate tumor cell invasion, but it is unclear how collagen cross-linking is regulated in epithelial tumors. To address this ...question, we used Kras(LA1) mice, which develop lung adenocarcinomas from somatic activation of a Kras(G12D) allele. The lung tumors in Kras(LA1) mice were highly fibrotic and contained cancer-associated fibroblasts (CAF) that produced collagen and generated stiffness in collagen gels. In xenograft tumors generated by injection of wild-type mice with lung adenocarcinoma cells alone or in combination with CAFs, the total concentration of collagen cross-links was the same in tumors generated with or without CAFs, but coinjected tumors had higher hydroxylysine aldehyde-derived collagen cross-links (HLCC) and lower lysine-aldehyde-derived collagen cross-links (LCCs). Therefore, we postulated that an LCC-to-HLCC switch induced by CAFs promotes the migratory and invasive properties of lung adenocarcinoma cells. To test this hypothesis, we created coculture models in which CAFs are positioned interstitially or peripherally in tumor cell aggregates, mimicking distinct spatial orientations of CAFs in human lung cancer. In both contexts, CAFs enhanced the invasive properties of tumor cells in three-dimensional (3D) collagen gels. Tumor cell aggregates that attached to CAF networks on a Matrigel surface dissociated and migrated on the networks. Lysyl hydroxylase 2 (PLOD2/LH2), which drives HLCC formation, was expressed in CAFs, and LH2 depletion abrogated the ability of CAFs to promote tumor cell invasion and migration.
CAFs induce a collagen cross-link switch in tumor stroma to influence the invasive properties of tumor cells.
Nature underpins human well-being in critical ways, especially in health. Nature provides pollination of nutritious crops, purification of drinking water, protection from floods, and climate ...security, among other well-studied health benefits. A crucial, yet challenging, research frontier is clarifying how nature promotes physical activity for its many mental and physical health benefits, particularly in densely populated cities with scarce and dwindling access to nature. Here we frame this frontier by conceptually developing a spatial decision-support tool that shows where, how, and for whom urban nature promotes physical activity, to inform urban greening efforts and broader health assessments. We synthesize what is known, present a model framework, and detail the model steps and data needs that can yield generalizable spatial models and an effective tool for assessing the urban nature-physical activity relationship. Current knowledge supports an initial model that can distinguish broad trends and enrich urban planning, spatial policy, and public health decisions. New, iterative research and application will reveal the importance of different types of urban nature, the different subpopulations who will benefit from it, and nature's potential contribution to creating more equitable, green, livable cities with active inhabitants.
Experiments have shown that elastic ankle exoskeletons can be used to reduce ankle joint and plantar-flexor muscle loading when hopping in place and, in turn, reduce metabolic energy consumption. ...However, recent experimental work has shown that such exoskeletons cause less favourable soleus (SO) muscle-tendon mechanics than is observed during normal hopping, which might limit the capacity of the exoskeleton to reduce energy consumption. To directly link plantar-flexor mechanics and energy consumption when hopping in exoskeletons, we used a musculoskeletal model of the human leg and a model of muscle energetics in simulations of muscle-tendon dynamics during hopping with and without elastic ankle exoskeletons. Simulations were driven by experimental electromyograms, joint kinematics and exoskeleton torque taken from previously published data. The data were from seven males who hopped at 2.5 Hz with and without elastic ankle exoskeletons. The energetics model showed that the total rate of metabolic energy consumption by ankle muscles was not significantly reduced by an ankle exoskeleton. This was despite large reductions in plantar-flexor force production (40-50%). The lack of larger metabolic reductions with exoskeletons was attributed to increases in plantar-flexor muscle fibre velocities and a shift to less favourable muscle fibre lengths during active force production. This limited the capacity for plantar-flexors to reduce activation and energy consumption when hopping with exoskeleton assistance.
The NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Head and Neck Cancers provide treatment recommendations for cancers of the lip, oral cavity, pharynx, larynx, ethmoid and ...maxillary sinuses, and salivary glands. Recommendations are also provided for occult primary of the head and neck (H&N), and separate algorithms have been developed by the panel for very advanced H&N cancers. These NCCN Guidelines Insights summarize the panel's discussion and most recent recommendations regarding the increase in human papillomavirus-associated oropharyngeal cancer and the availability of immunotherapy agents for treatment of patients with recurrent or metastatic H&N cancer.