Search Results

Purpose: Staying injury free is a major factor for success in sports. Although injuries are difficult to forecast, novel technologies and data-science applications could provide important insights. Our purpose was to use machine learning for the prediction of injuries in runners, based on detailed training logs. Methods: Prediction of injuries was evaluated on a new data set of 74 high-level middle- and long-distance runners, over a period of 7 years. Two analytic approaches were applied. First, the training load from the previous 7 days was expressed as a time series, with each day’s training being described by 10 features. These features were a combination of objective data from a global positioning system watch (eg, duration, distance), together with subjective data about the exertion and success of the training. Second, a training week was summarized by 22 aggregate features, and a time window of 3 weeks before the injury was considered. Results: A predictive system based on bagged XGBoost machine-learning models resulted in receiver operating characteristic curves with average areas under the curves of 0.724 and 0.678 for the day and week approaches, respectively. The results of the day approach especially reflect a reasonably high probability that our system makes correct injury predictions. Conclusions: Our machine-learning-based approach predicts a sizable portion of the injuries, in particular when the model is based on training-load data in the days preceding an injury. Overall, these results demonstrate the possible merits of using machine learning to predict injuries and tailor training programs for athletes.

Physical activity is a health-protective factor that can reduce disease risk in later life. Designing interventions that increase physical activity participation are paramount but need to increase potency and reduce the time to effectiveness. This paper aims to outline one transdisciplinary, team science effort to increase behavioral intervention potency through the integration of the autonomous cognition model whereby data guide each decision in developing a school-based physical activity intervention. Examples of data collected by stage and a summary of potential action steps are provided.

This article discusses the practical applications of artificial intelligence in digital physical activity and falls prevention interventions for older adults. It notes the range of technologies that can be used to collect digital datasets on older adult health and how machine learning algorithms can be applied to these to improve our understanding of physical activity and falls. In particular, these advanced computational techniques could help personalize exercises, feedback, and notifications to older people, improve adherence to and reduce attrition from digital health interventions, and enhance monitoring by providing predictive analytics on the physiological and environmental conditions that contribute to physical activity and falls in aging populations.

Background: Training load is typically described in terms of internal and external load. Investigating the coupling of internal and external training load is relevant to many sports. Here, continuous kernel-density estimation (KDE) may be a valuable tool to capture and visualize this coupling. Aim: Using training load data in speed skating, we evaluated how well bivariate KDE plots describe the coupling of internal and external load and differentiate between specific training sessions, compared to training impulse scores or intensity distribution into training zones. Methods: On-ice training sessions of 18 young (sub)elite speed skaters were monitored for velocity and heart rate during 2 consecutive seasons. Training session types were obtained from the coach’s training scheme, including endurance, interval, tempo, and sprint sessions. Differences in training load between session types were assessed using Kruskal–Wallis or Kolmogorov–Smirnov tests for training impulse and KDE scores, respectively. Results: Training impulse scores were not different between training session types, except for extensive endurance sessions. However, all training session types differed when comparing KDEs for heart rate and velocity (both P < .001). In addition, 2D KDE plots of heart rate and velocity provide detailed insights into the (subtle differences in) coupling of internal and external training load that could not be obtained by 2D plots using training zones. Conclusion: 2D KDE plots provide a valuable tool to visualize and inform coaches on the (subtle differences in) coupling of internal and external training load for training sessions. This will help coaches design better training schemes aiming at desired training adaptations.

Purpose: Sport-science research consistently contains repeated measures and imbalanced data sets. This study calls for further adoption of mixed models when analyzing longitudinal sport-science data sets. Mixed models were used to understand whether the level of competition affected the intensity of women’s rugby league match play. Methods: A total of 472 observations were used to compare the mean speed of female rugby league athletes recorded during club-, state-, and international-level competition. As athletes featured in all 3 levels of competition and there were multiple matches within each competition (ie, repeated measures), the authors demonstrated that mixed models are the appropriate statistical approach for these data. Results: The authors determined that if a repeated-measures analysis of variance (ANOVA) were used for the statistical analysis in the present study, at least 48.7% of the data would have been omitted to meet ANOVA assumptions. Using a mixed model, the authors determined that mean speed recorded during Trans-Tasman Test matches was 73.4 m·min⁻¹, while the mean speeds for National Rugby League Women and State of Origin matches were 77.6 and 81.6 m·min⁻¹, respectively. Random effects of team, athlete, and match all accounted for variations in mean speed, which otherwise could have concealed the main effects of position and level of competition had less flexible ANOVAs been used. Conclusion: These data clearly demonstrate the appropriateness of applying mixed models to typical data sets acquired in the professional sport setting. Mixed models should be more readily used within sport science, especially in observational, longitudinal data sets such as movement pattern analyses.

Background: We investigated the percentage of insufficiently active adolescents who became young adults meeting moderate to vigorous physical activity (MVPA) guidelines. We also explored adolescent psychosocial and environmental factors that predicted MVPA guideline adherence in young adulthood. Methods: Participants included N = 1001 adolescents (mean age = 14.1 y) reporting < 7 hours per week of MVPA and followed (8 y later) into young adulthood through Project EAT. We examined mean weekly hours of MVPA, MVPA change between adolescence and young adulthood, and the proportion of participants meeting MVPA guidelines in young adulthood. With sex-stratified logistic regression, we tested 11 adolescent psychosocial and environmental factors predicting meeting MVPA guidelines in young adulthood. Results: Overall, 55% of insufficiently active adolescents became young adults meeting MVPA guidelines. On average, participants reported 3.0 hours per week of MVPA, which improved to 3.8 hours per week in young adulthood. Among female participants, higher MVPA in adolescence and stronger feelings of exercise compulsion predicted greater odds of meeting adult MVPA guidelines (odds ratio_MVPA = 1.18; odds ratio_compulsion = 1.13). Among female and male participants, perceived friend support for activity in adolescence predicted greater odds of meeting adult MVPA guidelines (odds ratio_female = 1.12; odds ratio_male = 1.26). Conclusions: Insufficiently active adolescents can later meet adult guidelines. Interventions that increase perceived friend support for activity may benefit individuals across development.