Michael A. Riley

Machine learning has the potential to reveal latent biomechanical profiles that link athlete physiology, injury predisposition, and responses to interventions to reducing injury risk. This study developed a manifold-learning-based clustering approach to stratify athletes into biomechanically distinct subgroups. We evaluated combinations of four dimensionality-reduction techniques (t-SNE, KPCA, Diffusion Maps, Autoencoders) with three clustering algorithms (GMM, Agglomerative, DBSCAN) on biomechanical data from 312 female athletes (soccer, volleyball, or basketball) during a drop vertical jump (DVJ), selecting the optimal pipeline. All participants received a neuromuscular training (NMT) intervention aimed at reducing anterior cruciate ligament injury risk and were additionally randomized to receive either augmented NMT (aNMT) or sham NMT (sNMT), respectively involving accurate or uninformative visual feedback about training exercise performance. The optimal pipeline (t-SNE with GMM) identified three biomechanically distinct clusters that aligned with sport type, injury incidence, and intervention allocation. Profiles included a moderate-risk group, an injury-resilient group, and a high-risk, injury-prone group with elevated sprains, concussions, and non-preventable injuries, demonstrating that athletes can be grouped based on latent biomechanical structure using this approach. Cluster validity was confirmed by silhouette scores (0.49) and statistical testing at 95% confidence for separation of sport (0.00002), injury (0.036), and intervention (0.017). These results demonstrate that learned manifolds capture physiologically meaningful structure, offering a generalizable framework for stratifying athletes into biomechanically distinct subgroups associated with injury patterns, sport participation, and the distribution of interventions.

Background: Neuromuscular training (NMT) improves biomechanical risk factors associated with anterior cruciate ligament (ACL) injury yet has failed to abate increasing ACL injury rates at scale. This study assessed sport-specific sensorimotor adaptations resulting from a NMT protocol with additive real-time sensorimotor augmented biofeedback (augmented NMT [aNMT] or sham aNMT) in a standardized drop vertical jump (DVJ) task and in ecologically valid sport-specific tasks performed in a simulated virtual reality (VR) environment. Hypothesis: Both training groups will display beneficial biomechanical changes in the standard DVJ, but aNMT will have greater transfer to the VR sport-specific scenario. Biomechanical improvements in DVJ will vary by sport, while improvements in VR sport-specific scenarios will not vary by sport. Study Design: Prospective longitudinal randomized placebo-controlled trial. Level of Evidence: Level 1. Methods: A total of 271 adolescent female soccer, basketball, and volleyball athletes performed 6 weeks of preseason NMT with additive aNMT or sham aNMT. Three-dimensional biomechanics were assessed at pre-/post-training that included DVJs and sport-specific VR tasks. Pre-/post-training standardized delta scores for both tasks were computed for hip and knee angles and external joint moments. Hierarchical clustering and chi-square analyses (omnibus and within each sport) assessed sport by intervention interactions for biomechanical transfer to both tasks. Results: Hierarchical clustering identified 3 DVJ clusters, 2 of which (N = 243) demonstrated beneficial pre-/post-training changes. A small proportion (10%) of athletes classified in a maladaptive cluster that consisted predominantly of aNMT participants, while sham aNMT made up a greater proportion of a beneficial adaptive cluster ( χ ² = 6.06; P = 0.05). For the sport-specific VR task, 2 statistical clusters were identified, both characterized primarily by improved hip flexion angles regardless of sport. Conclusion: Beneficial effects of aNMT and sham aNMT on the DVJ were observed in most participants, with aNMT accounting for a greater proportion of players exhibiting maladaptive DVJ changes. VR scenarios revealed consistently beneficial changes in landing biomechanics in all participants. Clinical Relevance: Sport-specific VR tasks may assess more nuanced levels of movement complexity than traditional laboratory-based tasks and provide a complementary approach to evaluate biomechanical adaptations resulting from NMT.

Background: Moderate- to high-intensity walking training (M-HIT) is an established intervention for improving walking capacity in chronic stroke. Musculoskeletal (MSK) adverse events commonly occur during M-HIT, yet tools to identify individuals at higher risk are limited. Baseline clinical characteristics may provide insight into susceptibility to training-related MSK adverse events during M-HIT. Thus, this study aimed to develop and internally validate a model for predicting MSK adverse events during a 12-week M-HIT program in chronic stroke using baseline clinical characteristics. Methods: Participants (n=100) from HIT-Stroke Trials 1 and 2 were included. Baseline clinical characteristics included measures of orthopedic history, pre-existing pain, motor function, recent exercise history, demographics and health characteristics, stroke chronicity, and psychological health. Logistic regression models evaluated all possible combinations of baseline characteristics with up to three predictors. Leave-one-out cross-validation was used for internal validation to mitigate overfitting. Predictive performance was quantified using the C-statistic, and the candidate model with the highest cross-validated C-statistic was selected as the final model. Results: MSK adverse events occurred in 32.0% of participants. The optimal three-variable model included prior orthopedic condition (Odds ratio [OR] 3.02 [95% CI 1.14-8.64]), Fugl-Meyer lower extremity motor score (OR 1.14 [95% CI 1.02-1.28]), and self-reported participation in regular walking exercise (OR 0.17 [95% CI 0.05-0.49]) at baseline. This model demonstrated moderate discrimination (cross-validated C-statistic = 0.74; apparent C-statistic = 0.78). Conclusions: Participants reporting at least one pre-existing lower extremity or lumbar spine orthopedic condition and those with better lower-extremity motor function exhibited greater odds of experiencing MSK adverse events during M-HIT, while participants reporting participation in regular walking exercise had lower odds. These findings suggest that baseline clinical characteristics may help identify individuals at elevated risk for MSK adverse events during M-HIT who may warrant closer monitoring or risk-reduction strategies. Future studies are needed for external validation. Clinical Trial Registration: https://ClinicalTrials.gov ; Unique identifiers: NCT03760016 , NCT06268041

People with stroke (PwS) often exhibit altered postural control, and concomitant stroke-related communication disorders (e.g., aphasia, dysarthria) may be an underrecognized risk factor for post-stroke falls. This heightened fall risk may be related to alterations in postural control that emerge during different speaking and listening conditions. This study evaluated how variations in the relative articulatory demands during speech production-termed "oral-motor complexity"-affect postural center of pressure (COP) patterns among PwS, both with communication disorders (PwS-CDis) and without (PwS). Three groups of adults (PwS, PwS-CDis, and a nondisabled Control group) stood on a force platform while completing four 30-second quiet stance trials, followed by twelve 30-second trials randomized across three experimental conditions of varying oral-motor complexities ("ba", "puh tuh kuh", "rah shah lah nah"). COP variability (SD) was significantly higher during experimental conditions compared to quiet stance, regardless of group and movement plane. Differences in nonlinear time-dependent metrics were found across oral-motor task conditions, particularly among PwS-CDis, suggesting oral-motor complexity may influence underlying postural-motor organization. Distinct temporal-dynamical patterns observed in PwS-CDis indicate a possible link between pathology, postural control, and speech motor tasks, which is relevant when evaluating postural control in individuals with stroke-related communication disorders.

Individuals post-stroke commonly demonstrate alterations in motor behavior with regard to both task performance and the motor strategies used in pursuit of task goals. We evaluated whether constraining postural sway (motor strategy) during practice would affect upper-limb precision aiming performance (task performance) and postural control adaptations. Adults with stroke stood on a force plate while immersed in a virtual scene displaying an anterior target. Participants aimed to position a virtual laser pointer (via handheld device) in the target. Participants then completed practice trials involving aiming at a lateral target. For this practice session, participants were randomized to either (a) a "constraint" group wherein they received physical constraint to limit postural sway, or (b) a "no-constraint" group. Task performance and postural control were assessed before and after practice, and transfer to another upper-limb task was evaluated. After practice, both groups improved paretic upper-limb performance. For the target task, the no-constraint group showed task-sensitive changes in postural control. The constraint group showed no changes in postural control. At transfer, the constraint group increased postural sway. Constraining postural sway after stroke should be carefully considered with the recognition that postural sway arises from exploratory movements involved in the discovery of adaptable motor solutions.

People with stroke (PwS) often exhibit altered postural control, and concomitant stroke-related communication disorders (e.g., aphasia, dysarthria) may be an underrecognized risk factor for post-stroke falls. This heightened fall risk may be related to alterations in postural control that emerge during different speaking and listening conditions. This study evaluated how variations in the relative articulatory demands during speech production—termed “oral-motor complexity”—affect postural center of pressure (COP) patterns among PwS, both with communication disorders (PwS-CDis) and without (PwS). Three groups of adults (PwS, PwS-CDis, and a nondisabled Control group) stood on a force platform while completing four 30-second quiet stance trials, followed by twelve 30-second trials randomized across three experimental conditions of varying oral-motor complexities (“ba”, “puh tuh kuh”, “rah shah lah nah”). COP variability (SD) was significantly higher during experimental conditions compared to quiet stance, regardless of group and movement plane. Differences in nonlinear time-dependent metrics were found across oral-motor task conditions, particularly among PwS-CDis, suggesting oral-motor complexity may influence underlying postural-motor organization. Distinct temporal-dynamical patterns observed in PwS-CDis indicate a possible link between pathology, postural control, and speech motor tasks, which is relevant when evaluating postural control in individuals with stroke-related communication disorders.

Michael T. Turvey passed away on August 12, 2023 at the age of 81. This obituary aims to honor his life and career by highlighting some key events in his personal and professional life, noting some of his many remarkable accomplishments, and emphasizing his exceptional mentorship, friendship, and generosity.

Purpose: Ultrasound biofeedback therapy (UBT) is a relatively new type of technology-assisted speech-language therapy and has shown promise in remediating speech sound disorders. However, there is a current lack of understanding of the barriers and benefits that may influence the usage behavior and clinical decision making for the implementation of UBT from a clinician perspective. In this qualitative study, we explore the perspectives of speech-language pathologists (SLPs) who have used ultrasound biofeedback in programs of speech sound therapy using the unified theory of acceptance and use of technology (UTAUT) model. Method: Seven SLPs who had clinical experience treating speech sound disorders with UBT participated. Semistructured in-depth interviews were conducted and video-recorded. Two coders coded and categorized the transcribed data, with consensus established with a third coder. Using thematic analysis, the data were exploratorily grouped into themes along components of the UTAUT model. Results: The highest number of codes was sorted into the “effort expectancy” theme, followed by “performance expectancy,” “social influence,” and “facilitating conditions” themes of the UTAUT model. Clinicians identified multiple perceived barriers and benefits to the use of ultrasound technology. The top identified barrier was limited accessibility, and the top benefit was the ability to visualize a client's articulatory response to cues on a display. Conclusions: Clinicians prioritized “effort expectancy” and “performance expectancy” when reflecting on the use of ultrasound biofeedback for speech sound disorders. Clinicians spoke favorably about using UBT for speech sound disorder treatment but acknowledged institutional barriers and limitations at organizational and social levels.

Ultrasound biofeedback therapy (UBT), which incorporates real-time imaging of tongue articulation, has demonstrated generally positive speech remediation outcomes for individuals with residual speech sound disorder (RSSD). However, UBT requires high attentional demands and may therefore benefit from a simplified display of articulation targets that are easily interpretable and can be compared to real-time articulation. Identifying such targets requires automatic quantification and analysis of movement features relevant to accurate speech production. Our image-analysis program TonguePART automatically quantifies tongue movement as tongue part displacement trajectories from midsagittal ultrasound videos of the tongue, with real-time capability. The present study uses such displacement trajectories to compare accurate and misarticulated American-English rhotic /ɑr/ productions from 40 children, with degree of accuracy determined by auditory perceptual ratings. To identify relevant features of accurate articulation, support vector machine (SVM) classifiers were trained and evaluated on several candidate data representations. Classification accuracy was up to 85%, indicating that quantification of tongue part displacement trajectories captured tongue articulation characteristics that distinguish accurate from misarticulated production of /ɑr/. Regression models for perceptual ratings were also compared. The simplest data representation that retained high predictive ability, demonstrated by high classification accuracy and strong correlation between observed and predicted ratings, was displacements at the midpoint of /r/ relative to /ɑ/ for the tongue dorsum and blade. This indicates that movements of the dorsum and blade are especially relevant to accurate production of /r/, suggesting that a predictive parameter and biofeedback target based on this data representation may be usable for simplified UBT.

: Mobility and speech-language impairments and limitations in adults with neurological conditions manifest not in isolated anatomical components but instead in the individual-environment system and are task-dependent. Optimization of function thus requires interprofessional care to promote participation in meaningful life areas within appropriate task and environmental contexts. Cotreatment guidelines (ie, the concurrent intervention of disciplines) were established by the physical therapy, occupational therapy, and speech-language and hearing professional organizations nearly 2 decades ago to facilitate seamless interprofessional care. Despite this, cotreatment between physical therapy and speech therapy remains limited. The purpose of this Perspective article is to encourage physical therapists and speech-language pathologists to increase interprofessional collaboration through cotreatment in the management of adults with neurological conditions. Evidence from pediatrics and basic motor control literature points toward reciprocal interactions between speech-language and mobility. We provide recommendations for clinical practice with an emphasis on the gains each discipline can provide the other. This Perspective is rooted in the International Classification of Functioning, Disability and Health model and ecological theory. Impact: The goals of speech therapy and physical therapy are complementary and mutually supportive. Enhanced cotreatment, and collaboration more generally, between physical therapists and speech-language pathologists in the management of adults with neurological conditions can augment task-relevant conditions to improve function.