Prospective evaluation of 24-hour movement behaviors among adolescents recovering from a sport-related concussion.

This study aimed to describe the 24-hour composition of movement behaviors, including sleep, sedentary behavior, and physical activity (PA), among pediatric sports-related concussion (SRC) patients over their recovery period, assess the association between movement compositions and recovery time, and understand feasibility of 24-hour accelerometry in the study population. A cohort of 50 pediatric SRC patients were asked to wear a wrist-worn accelerometer continuously for the duration of their recovery. Among all enrolled participants, the sample was primarily 14 or 15 years of age (65%), female (55%), and recovered in under 28 days (88%). Accelerometer compliance was moderate; 35 participants (70%) were compliant with the protocol. Compositional analysis was used to address time-use objectives in 33 participants who provided adequate data for inclusion. Overall, participants spent an average of 50% of their 24-hour day sedentary, 33% sleeping, 11% in light intensity PA, and 6% in moderate or vigorous intensity PA. The 24-hour composition of movement behaviors was not associated with recovery time (p = .09-.99). However, the limited sample size may have contributed to null findings. Given recent evidence supporting the effects of sedentary behavior and PA on concussion recovery, future studies should aim to further validate these findings in a larger sample.

Weight status and meeting the physical activity, sleep, and screen-time guidelines among Texas children: results from a population based, cross-sectional analysis.

BACKGROUND: Evidence suggests that the interactive effects of physical activity, screen-time and sleep are stronger than independent effects of these behaviors on pediatric obesity. However, this hypothesis has not been fully examined among samples of young school-aged children. The aim of this study is to determine the association of weight status with meeting the physical activity, screen-time, and sleep guidelines, independently and concurrently, among 2nd grade children. METHODS: The Texas School Physical Activity and Nutrition Project collected parent-reported physical activity, screen-time, and sleep, and measured body height and weight on a statewide representative weighted sample (n = 320,005) of children. Weighted multivariable logistic regressions were used to assess associations of weight status (classified using age- and sex-specific body weight [kg]/height [m]2, based on International Obesity Task Force cutoffs) with meeting the physical activity, screen-time, and sleep guidelines, while controlling for relevant covariates (age, sex, race/ethnicity, comorbidities etc.). RESULTS: A greater proportion of healthy weight children (9.9%) met the physical activity, screen-time, and sleep guidelines concurrently compared to children who are thin (3.3%), or children with overweight (5.7%), obese (3.5%), and morbid obesity (1.0%). Children who were thin (adjusted odds ratio [aOR]:0.40, 95% confidence interval [CI]: 0.10, 1.50), overweight (aOR = 0.75, CI: 0.33, 1.70), obese (aOR = 0.53, CI: 0.15, 1.81), and morbidly obese (aOR = 0.10, CI: 0.02, 0.28) had lower odds of concurrently meeting the guidelines compared to children with healthy weight. CONCLUSIONS: Among this representative sample of Texas children, weight status was associated with meeting physical activity, screen-time, and sleep guidelines. Future studies should aim to evaluate causal relations between these behaviors and weight status.

Machine learning to predict sports-related concussion recovery using clinical data.

OBJECTIVES: Sport-related concussions (SRCs) are a concern for high school athletes. Understanding factors contributing to SRC recovery time may improve clinical management. However, the complexity of the many clinical measures of concussion data precludes many traditional methods. This study aimed to answer the question, what is the utility of modeling clinical concussion data using machine-learning algorithms for predicting SRC recovery time and protracted recovery? METHODS: This was a retrospective case series of participants aged 8 to 18 years with a diagnosis of SRC. A 6-part measure was administered to assess pre-injury risk factors, initial injury severity, and post-concussion symptoms, including the Vestibular Ocular Motor Screening (VOMS) measure, King-Devick Test and C3 Logix Trails Test data. These measures were used to predict recovery time (days from injury to full medical clearance) and binary protracted recovery (recovery time > 21 days) according to several sex-stratified machine-learning models. The ability of the models to discriminate protracted recovery was compared to a human-driven model according to the area under the receiver operating characteristic curve (AUC). RESULTS: For 293 males (mean age 14.0 years) and 362 females (mean age 13.7 years), the median (interquartile range) time to recover from an SRC was 26 (18-39) and 21 (14-31) days, respectively. Among 9 machine-learning models trained, the gradient boosting on decision-tree algorithms achieved the best performance to predict recovery time and protracted recovery in males and females. The models' performance improved when VOMS data were used in conjunction with the King-Devick Test and C3 Logix Trails Test data. For males and females, the AUC was 0.84 and 0.78 versus 0.74 and 0.73, respectively, for statistical models for predicting protracted recovery. CONCLUSIONS: Machine-learning models were able to manage the complexity of the vestibular-ocular motor system data. These results demonstrate the clinical utility of machine-learning models to inform prognostic evaluation for SRC recovery time and protracted recovery.