An official website of the United States government
Abstract BackgroundEmerging evidence indicates an elevated risk of post-concussion musculoskeletal injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated. ObjectiveThe purpose of this study was to model post-concussion musculoskeletal injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning. MethodsA risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant’s heath and athletic history, concussion injury and recovery-specific criteria, and outcomes from a diverse array of concussion assessments. The machine learning approach involved transforming variables by the weight of evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit. ResultsA model with 48 predictive variables yielded significant predictive performance of subsequent musculoskeletal injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at baseline and acute timepoints. At a specified false-positive rate of 6.67%, the model achieves a true-positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well-calibrated composite risk score. ConclusionsThese results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student athletes most at risk for post-concussion musculoskeletal injury.
more »
« less
Demographic Characteristics and Their Association with Instantaneous Lower Extremity Injury Occurrence in a Division I Athletic Population
Context Temporal prediction of lower extremity (LE) injury risk will benefit clinicians by allowing them to better leverage limited resources and target athletes most at risk. Objective To characterize instantaneous risk of LE injury by demographic factors sex, sport, body mass index (BMI), and previous injury history. Instantaneous injury risk was defined as injury risk at any given point in time following baseline measurement. Design Descriptive epidemiology study. Setting NCAA Division I athletic program. Patients or Other Participants 278 NCAA Division I varsity student-athletes (119 males, 159 females). Main Outcome Measure(s) LE injuries were tracked for 237±235 days. Sex-stratified univariate Cox regression models investigated the association between time to first LE injury and BMI, sport, and previous LE injury history. Relative risk ratios and Kaplan-Meier curves were generated. Variables identified in the univariate analysis were included in a multivariate Cox regression model. Results Females displayed similar instantaneous LE injury risk compared to males (HR=1.29, 95%CI=[0.91,1.83], p=0.16). Overweight athletes (BMI>25 kg/m2) had similar instantaneous LE injury risk compared with athletes with BMI<25 kg/m2 (HR=1.23, 95%CI=[0.84,1.82], p=0.29). Athletes with previous LE injuries were not more likely to sustain subsequent LE injury than athletes with no previous injury (HR=1.09, 95%CI=[0.76,1.54], p=0.64). Basketball (HR=3.12, 95%CI=[1.51,6.44], p=0.002) and soccer (HR=2.78, 95%CI=[1.46,5.31], p=0.002) athletes had higher risk of LE injury than cross-country athletes. In the multivariate model, females were at greater LE injury risk than males (HR=1.55, 95%CI=[1.00,2.39], p=0.05), and males with BMI>25 kg/m2 were at greater risk than all other athletes (HR=0.44, 95%CI=[0.19,1.00], p=0.05). Conclusions In a collegiate athletic population, previous LE injury history was not a significant contributor to risk of future LE injury, while being female or being male with BMI>25 kg/m2 resulted in increased risk of LE injury. Clinicians can use these data to extrapolate LE injury risk occurrence to specific populations.
more »
« less
- Award ID(s):
- 1924278
- PAR ID:
- 10358179
- Date Published:
- Journal Name:
- Journal of Athletic Training
- ISSN:
- 1062-6050
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract BackgroundEmerging evidence indicates an elevated risk of post-concussion musculoskeletal (MSK) injuries in collegiate athletes; however, identifying athletes at highest risk remains to be elucidated. ObjectiveThe purpose of this study was to model post-concussion MSK injury risk in collegiate athletes by integrating a comprehensive set of variables by machine learning. MethodsA risk model was developed and tested on a dataset of 194 athletes (155 in the training set and 39 in the test set) with 135 variables entered into the analysis, which included participant’s heath and athletic history, concussion injury and recovery specific criteria, and outcomes from a diverse array of concussions assessments. The machine learning approach involved transforming variables by the Weight of Evidence method, variable selection using L1-penalized logistic regression, model selection via the Akaike Information Criterion, and a final L2-regularized logistic regression fit. ResultsA model with 48 predictive variables yielded significant predictive performance of subsequent MSK injury with an area under the curve of 0.82. Top predictors included cognitive, balance, and reaction at Baseline and Acute timepoints. At a specified false positive rate of 6.67%, the model achieves a true positive rate (sensitivity) of 79% and a precision (positive predictive value) of 95% for identifying at-risk athletes via a well calibrated composite risk score. ConclusionThese results support the development of a sensitive and specific injury risk model using standard data combined with a novel methodological approach that may allow clinicians to target high injury risk student-athletes. The development and refinement of predictive models, incorporating machine learning and utilizing comprehensive datasets, could lead to improved identification of high-risk athletes and allow for the implementation of targeted injury risk reduction strategies by identifying student-athletes most at risk for post-concussion MSK injury. Key PointsThere is a well-established elevated risk of post-concussion subsequent musculoskeletal injury; however, prior efforts have failed to identify risk factors.This study developed a composite risk score model with an AUC of 0.82 from common concussion clinical measures and participant demographics.By identifying athletes at elevated risk, clinicians may be able to reduce injury risk through targeted injury risk reduction programs.more » « less
-
Abstract STUDY QUESTION To what extent is exposure to cellular telephones associated with male fertility? SUMMARY ANSWER Overall, we found little association between carrying a cell phone in the front pants pocket and male fertility, although among leaner men (BMI <25 kg/m2), carrying a cell phone in the front pants pocket was associated with lower fecundability. WHAT IS KNOWN ALREADY Some studies have indicated that cell phone use is associated with poor semen quality, but the results are conflicting. STUDY DESIGN, SIZE, DURATION Two prospective preconception cohort studies were conducted with men in Denmark (n = 751) and in North America (n = 2349), enrolled and followed via the internet from 2012 to 2020. PARTICIPANTS/MATERIALS, SETTING, METHODS On the baseline questionnaire, males reported their hours/day of carrying a cell phone in different body locations. We ascertained time to pregnancy via bi-monthly follow-up questionnaires completed by the female partner for up to 12 months or until reported conception. We used proportional probabilities regression models to estimate fecundability ratios (FRs) and 95% confidence intervals (CIs) for the association between male cell phone habits and fecundability, focusing on front pants pocket exposure, within each cohort separately and pooling across the cohorts using a fixed-effect meta-analysis. In a subset of participants, we examined selected semen parameters (semen volume, sperm concentration and sperm motility) using a home-based semen testing kit. MAIN RESULTS AND THE ROLE OF CHANCE There was little overall association between carrying a cell phone in a front pants pocket and fecundability: the FR for any front pants pocket exposure versus none was 0.94 (95% CI: 0.0.83–1.05). We observed an inverse association between any front pants pocket exposure and fecundability among men whose BMI was <25 kg/m2 (FR = 0.72, 95% CI: 0.59–0.88) but little association among men whose BMI was ≥25 kg/m2 (FR = 1.05, 95% CI: 0.90–1.22). There were few consistent associations between cell phone exposure and semen volume, sperm concentration, or sperm motility. LIMITATIONS, REASONS FOR CAUTION Exposure to radiofrequency radiation from cell phones is subject to considerable non-differential misclassification, which would tend to attenuate the estimates for dichotomous comparisons and extreme exposure categories (e.g. exposure 8 vs. 0 h/day). Residual confounding by occupation or other unknown or poorly measured factors may also have affected the results. WIDER IMPLICATIONS OF THE FINDINGS Overall, there was little association between carrying one’s phone in the front pants pocket and fecundability. There was a moderate inverse association between front pants pocket cell phone exposure and fecundability among men with BMI <25 kg/m2, but not among men with BMI ≥25 kg/m2. Although several previous studies have indicated associations between cell phone exposure and lower sperm motility, we found few consistent associations with any semen quality parameters. STUDY FUNDING/COMPETING INTEREST(S) The study was funded by the National Institutes of Health, grant number R03HD090315. In the last 3 years, PRESTO has received in-kind donations from Sandstone Diagnostics (for semen kits), Swiss Precision Diagnostics (home pregnancy tests), Kindara.com (fertility app), and FertilityFriend.com (fertility app). Dr. L.A.W. is a fibroid consultant for AbbVie, Inc. Dr. H.T.S. reports that the Department of Clinical Epidemiology is involved in studies with funding from various companies as research grants to and administered by Aarhus University. None of these studies are related to the current study. Dr. M.L.E. is an advisor to Sandstone Diagnostics, Ro, Dadi, Hannah, and Underdog. Dr. G.J.S. holds ownership in Sandstone Diagnostics Inc., developers of the Trak Male Fertility Testing System. In addition, Dr. G.J.S. has a patent pending related to Trak Male Fertility Testing System issued. TRIAL REGISTRATION NUMBER N/Amore » « less
-
Trunk strength, endurance, and dynamic control may have an effect on anterior cruciate ligament (ACL) injury rates and biomechanical ACL loading variables during athletic tasks. Individuals responsible for training athletes at risk of ACL injuries should implement training programs that address these components of athletic performance. In ski racers, deficits in trunk flexion/extension strength and decreased trunk flexion/extension strength ratios have been identified as ACL injury risk factors. Trunk strength training alone is not sufficient to decrease biomechanical ACL loading, and there is no clear association between trunk endurance and ACL injury risks. Trunk dynamic control training may improve trunk and knee movements associated with decreased ACL loading during athletic tasks. Dynamic, unanticipated, and perturbed trunk functional assessments and training are recommended to challenge the trunk more during athletic tasks. Injury prevention programs should involve exercises using unstable surfaces, sports-related dual tasks, and perturbations to address trunk dynamic control. More investigation is still needed to further understand the associations between trunk neuromuscular functions and ACL injury risks during athletic tasks.more » « less
-
null (Ed.)Introduction Water fetching for household needs can cause injury, but documentation of the burden of harm globally has been limited. We described the frequency, characteristics and correlates of water-fetching injuries in 24 sites in 21 low-income and middle-income countries in Asia, Africa and Latin America and the Caribbean. Methods In a survey of 6291 randomly selected households, respondents reported whether and how they had experienced water-fetching injuries. Responses were coded for injury type, mechanism, bodily location and physical context. We then identified correlates of injury using a multilevel, mixed-effects logistic regression model. Results Thirteen per cent of respondents reported at least one water-fetching injury. Of 879 injuries, fractures and dislocations were the most commonly specified type (29.2%), and falls were the most commonly specified mechanism (76.4%). Where specified, 61.1% of injuries occurred to the lower limbs, and dangerous terrain (69.4%) was the most frequently reported context. Significant correlates included being female (aOR=1.50, 95% CI 1.15 to 1.96); rural (aOR=4.80, 95% CI 2.83 to 8.15) or periurban residence (aOR=2.75, 95% CI 1.64 to 4.60); higher household water insecurity scores (aOR=1.09, 95% CI 1.07 to 1.10) and reliance on surface water (aOR=1.97, 95% CI 1.21 to 3.22) or off-premise water sources that required queueing (aOR=1.72, 95% CI 1.19 to 2.49). Conclusion These data suggest that water-fetching injuries are an underappreciated and largely unmeasured public health challenge. We offer guidelines for comprehensive data collection on injuries to better capture the true burden of inadequate water access. Such data can guide the design of interventions to reduce injury risk and promote equitable water access solutions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.4085/1062-6050-0673.21
