On Leveraging Machine Learning in Sport Science in the Hypothetico-deductive Framework.

Supervised machine learning (ML) offers an exciting suite of algorithms that could benefit research in sport science. In principle, supervised ML approaches were designed for pure prediction, as opposed to explanation, leading to a rise in powerful, but opaque, algorithms. Recently, two subdomains of ML-explainable ML, which allows us to "peek into the black box," and interpretable ML, which encourages using algorithms that are inherently interpretable-have grown in popularity.

Transference of outdoor gait-training to treadmill running biomechanics and strength measures: A randomized controlled trial.

Outdoor gait-training has been successful in improving pain and reducing contact time during outdoor running for runners with exercise-related lower leg pain (ERLLP). However, it is unclear if these adaptations translate to gold standard treadmill running and clinical strength assessments. The study purpose was to assess the influence of a 4-week outdoor gait-training intervention with home exercises (FBHE) on treadmill running biomechanics and lower extremity strength compared to home exercises alone (HE) among runners with ERLLP.

Comparison of Limb Loading Characteristics and Subjective Functional Outcomes Between Sexes After Anterior Cruciate Ligament Reconstruction.

Context: Anterior cruciate ligament reconstruction (ACLR) patients commonly adopt poor movement patterns that potentially place them at an increased risk for reinjury if untreated. Limb loading characteristics during functional tasks can highlight movement compensations.

Objective: To examine loading symmetry during a bilateral bodyweight squatting task between sexes, compare loading metrics between limbs and sexes, and describe the relationship between loading metrics and patient-reported outcomes (PROs) after ACLR.

Sensor-based gait training to reduce contact time for runners with exercise-related lower leg pain: a randomised controlled trial.

Objectives: To assess the effects of a 4-week randomised controlled trial comparing an outdoor gait-training programme to reduce contact time in conjunction with home exercises (contact time gait-training feedback with home exercises (FBHE)) to home exercises (HEs) alone for runners with exercise-related lower leg pain on sensor-derived biomechanics and patient-reported outcomes.

Design: Randomised controlled trial.

Setting: Laboratory and field-based study.

An analysis of the Clinical and Translational Science Award pilot project portfolio using data from Research Performance Progress Reports.

Introduction: Pilot projects ("pilots") are important for testing hypotheses in advance of investing more funds for full research studies. For some programs, such as Clinical and Translational Science Awards (CTSAs) supported by the National Center for Translational Sciences, pilots also make up a significant proportion of the research projects conducted with direct CTSA support. Unfortunately, administrative data on pilots are not typically captured in accessible databases.

Prospective running assessments among division I cross-country athletes.

Objectives: To prospectively monitor biomechanics, session-rating of perceived exertion (sRPE), and wellness in a cohort of collegiate Division-1 cross-country athletes over the course of a single competitive season.

Design: Prospective cohort study.

Methods: Healthy Division-1 cross-country athletes (9 males, 13 females) were prospectively followed over a single competitive cross-country season.

Use of wearable sensors to identify biomechanical alterations in runners with Exercise-Related lower leg pain.

Exercise-related lower leg pain (ERLLP) is one of the most prevalent running-related injuries, however little is known about injured runners' mechanics during outdoor running. Establishing biomechanical alterations among ERLLP runners would help guide clinical interventions. Therefore, we sought to a) identify defining biomechanical features among ERLLP runners compared to healthy runners during outdoor running, and b) identify biomechanical thresholds to generate objective gait-training recommendations.

Detecting multivariate cross-correlation between brain regions.

The problem of identifying functional connectivity from multiple time series data recorded in each of two or more brain areas arises in many neuroscientific investigations. For a single stationary time series in each of two brain areas statistical tools such as cross-correlation and Granger causality may be applied. On the other hand, to examine multivariate interactions at a single time point, canonical correlation, which finds the linear combinations of signals that maximize the correlation, may be used.

Population Vectors Can Provide Near Optimal Integration of Information.

Much attention has been paid to the question of how Bayesian integration of information could be implemented by a simple neural mechanism. We show that population vectors based on point-process inputs combine evidence in a form that closely resembles Bayesian inference, with each input spike carrying information about the tuning of the input neuron. We also show that population vectors can combine information relatively accurately in the presence of noisy synaptic encoding of tuning curves.