Machine Learning to Predict Lower Extremity Musculoskeletal Injury Risk in Student Athletes.
Ontology highlight
ABSTRACT:
SUBMITTER: Henriquez M
PROVIDER: S-EPMC7739722 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Machine Learning to Predict Lower Extremity Musculoskeletal Injury Risk in Student Athletes.
Henriquez Maria M Sumner Jacob J Faherty Mallory M Sell Timothy T Bent Brinnae B
Frontiers in sports and active living 20201119
Injury rates in student athletes are high and often unpredictable. Injury risk factors are not agreed upon and often not validated. Here, we present a random-forest machine learning methodology for identifying the most significant injury risk factors and develop a model of lower extremity musculoskeletal injury risk in student athletes with physical performance metrics spanning joint strength measured with force transducers, postural stability measured using a force plate, and flexibility, measu ...[more]
Similar Datasets
Project description:BACKGROUND AND PURPOSE:There is limited evidence regarding risk factors for lower extremity overuse bone injury (LEOBI) in collegiate athletes. The purposes of the study were to: 1) determine incidence of LEOBI in selected sports and its impact on athletic participation and ADL, 2) assess risk relationships between LEOBI and selected risk factors, and 3) establish the viability of using calcaneal densitometry as a screening tool to identify risk for LEOBI. STUDY DESIGN:Prospective analytical cohort design. METHODS:Collegiate athletes in selected sports (swimming/diving, women's soccer, field hockey, cross-country/track) at one university were invited to participate. Consenting athletes completed an initial questionnaire including demographic information, history, and menstrual function. Measurements included height/weight, hip abductor strength, foot posture index, and calcaneal bone mineral density. Athletes were monitored for potential LEOBI for nine months and an algorithm was used to determine if physician referral was required. The primary outcome of interest was the occurrence of physician-diagnosed LEOBI. If LEOBI was diagnosed by the physician, the athlete completed a follow-up visit including a repeat bone mineral density scan. All athletes were invited for a repeat scan at the end of the year and completed a final questionnaire. Athlete demographics were summarized using descriptive statistics and differences in continuous risk factors were analyzed using t-tests and ANOVA. Finally, risk relationships for categorical variables were analyzed using chi-square and relative risk. RESULTS:84 athletes (64 female, 20 male) consented to participate. Over the study period, eight athletes (one male, seven females) were diagnosed with LEOBI (LEOBI group), five with stress fractures and three with medial tibial stress syndrome. The other 76 athletes who did not have a diagnosis of LEOBI were placed in the non-LEOBI group. Five of the eight were cross-country/track athletes; no swimming/diving athletes had bone injury. Sport (cross-country/track) had a significant relative risk value of 2.26 (95% CI = 1.18-4.32) for LEOBI. There was no association between LEOBI occurrence and sex, hip abductor strength, body mass index, foot type, and menstrual function. There was no difference in bone mineral density at initial or follow-up measures between LEOBI and non-LEOBI groups (p>.05) when analyzing all athletes. When analyzing ground-based athletes only at follow-up (n=44), athletes with LEOBI had lower bone mineral density of right (p = .05) and left (p =.07) calcaneus. The relative risk for developing LEOBI based on calcaneal bone mineral density below the mean of the study participants was 2.1 (95%CI = 1.09-3.35) on the left and 1.53 (95% CI=.80- 3.06) on the right. CONCLUSION:The incidence of LEOBI in this population of athletes was approximately 10%. Risk factors were sport (cross-country/track) and decreased left calcaneal bone mineral density. This study supports the use of calcaneal bone mineral density as a screening measurement for LEOBI risk and suggests the need for further investigation into additional LEOBI risk factors. LEVEL OF EVIDENCE:2.
| S-EPMC4387723 | biostudies-other
Project description:Functional movement tests that are predictive of injury risk in National Collegiate Athletic Association (NCAA) athletes are useful tools for sports medicine professionals. The Lower Quarter Y-Balance Test (YBT-LQ) measures single-leg balance and reach distances in 3 directions.To assess whether the YBT-LQ predicts the laterality and risk of sports-related lower extremity (LE) injury in NCAA athletes.Case-control study; Level of evidence, 3.The YBT-LQ was administered to 294 NCAA Division I athletes from 21 sports during preparticipation physical examinations at a single institution. Athletes were followed prospectively over the course of the corresponding season. Correlation analysis was performed between the laterality of reach asymmetry and composite scores (CS) versus the laterality of injury. Receiver operating characteristic (ROC) analysis was used to determine the optimal asymmetry cutoff score for YBT-LQ. A multivariate regression analysis adjusting for sex, sport type, body mass index, and history of prior LE surgery was performed to assess predictors of earlier and higher rates of injury.Neither the laterality of reach asymmetry nor the CS correlated with the laterality of injury. ROC analysis found optimal cutoff scores of 2, 9, and 3 cm for anterior, posteromedial, and posterolateral reach, respectively. All of these potential cutoff scores, along with a cutoff score of 4 cm used in the majority of prior studies, were associated with poor sensitivity and specificity. Furthermore, none of the asymmetric cutoff scores were associated with earlier or increased rate of injury in the multivariate analyses.YBT-LQ scores alone do not predict LE injury in this collegiate athlete population. Sports medicine professionals should be cautioned against using the YBT-LQ alone to screen for injury risk in collegiate athletes.
| S-EPMC5555509 | biostudies-other
Project description:Injuries are common within military populations, with high incidence rates well established in the literature. Injuries cause a substantial number of working days lost, a significant cost through compensation claims and an increased risk of attrition. In an effort to address this, a considerable amount of research has gone into identifying the most prevalent types of injury and their associated risk factors. Collective evidence suggests that training and equipment contribute to a large proportion of the injuries sustained. In particular, the large loads borne by soldiers, the high intensity training programs and the influence of footwear have been identified as significant causative factors of lower limb injury in military populations. A number of preventative strategies have been developed within military bodies around the world to address these issues. The relative success of these strategies is highly variable; however, with advancements in technology, new approaches will become available and existing strategies may become more effective.
| S-EPMC4851683 | biostudies-literature
Project description:Background Ankle-brachial indexes (ABI) are a noninvasive diagnostic tool for peripheral arterial disease and a marker of increased cardiovascular risk. ABI is calculated using the highest systolic blood pressure of the 4 ankle arteries (bilateral dorsalis pedis and posterior tibial). Accordingly, patients may be assigned a normal ABI when the result would be abnormal if calculated using one of the other blood pressure readings. Cardiovascular outcomes for patients with discordant ABIs are undescribed. Methods and Results We performed a retrospective study of patients who underwent ABI measurement for any indication between January 1996 and June 2018. Those with normal ABIs (1.00-1.39) were included. We compared patients with all 4 normal ABIs (calculated using all 4 ankle arteries; n=15 577, median age 64.0 years, 54.4% men) to those with discordant ABIs (at least 1 abnormal ABI ≤0.99; n=2095, median age 66.0 years, 47.8% men). The outcomes assessed were ischemic stroke, myocardial infarction, and all-cause mortality. Compared with patients with concordant normal ABIs, patients with discordant ABIs were older; women; smoked; and had chronic kidney disease, coronary artery disease, diabetes mellitus, chronic obstructive pulmonary disease, hypertension, or prior stroke. Patients with discordant ABIs had a greater risk of myocardial infarction (hazard ratio [HR], 1.31; 95% CI, 1.10-1.56), ischemic stroke (HR, 1.53; 95% CI, 1.37-1.72), and all-cause mortality (HR, 1.27; 95% CI, 1.16-1.39), including after adjustment for baseline comorbidities. Conclusions Discordant ABI results were associated with an increased risk of myocardial infarction, stroke, and all-cause mortality in the studied population. Clinicians should examine ABI calculations using all 4 ankle arteries to better characterize a patient's cardiovascular risk.
| S-EPMC7428982 | biostudies-literature
Project description:BackgroundConcussions have been associated with elevated musculoskeletal injury risk; however, the influence of unreported and unrecognized concussions has not been investigated.HypothesisThe purpose of this study was to examine the association between concussion and lower extremity musculoskeletal injury rates across a diverse array of sports among collegiate student-athletes at the conclusion of their athletic career. The hypothesis was that there will be a positive association between athletes who reported a history of concussions and higher rates of lower extremity injuries.Study designCross-sectional study.Level of evidenceLevel 3.MethodsStudent-athletes (N = 335; 62.1% women; mean age, 21.2 ± 1.4 years) from 13 sports completed a reliable injury history questionnaire. Respondents indicated the total number of reported, unreported, and potentially unrecognized concussions as well as lower extremity injuries including ankle sprains, knee injuries, and muscle strains. Chi-square analyses were performed to identify the association between concussion and lower extremity injuries.ResultsThere were significant associations between concussion and lateral ankle sprain ( P = 0.012), knee injury ( P = 0.002), and lower extremity muscle strain ( P = 0.031). There were also significant associations between reported concussions and knee injury ( P = 0.003), unreported concussions and knee injury ( P = 0.002), and unrecognized concussions and lateral ankle sprain ( P = 0.001) and lower extremity muscle strains ( P = 0.006), with odds ratios ranging from 1.6 to 2.9.ConclusionThere was a positive association between concussion history and lower extremity injuries (odds ratios, 1.6-2.9 elevated risk) among student-athletes at the conclusion of their intercollegiate athletic careers.Clinical relevanceClinicians should be aware of these elevated risks when making return-to-participation decisions and should incorporate injury prevention protocols.
| S-EPMC5089357 | biostudies-literature
Project description:PurposeTo determine the odds of sustaining an acute lower-extremity (LE) musculoskeletal injury during the 90-day period after return-to-play (RTP) from concussion in National Basketball Association (NBA) athletes.MethodsConcussion data for NBA players were collected from the 1999-2000 to 2017-2018 seasons, from publicly available sources. Age, position, injury, time to RTP, and demographic factors were collected. The 90-day period after each case of concussion was reviewed for acute noncontact LE musculoskeletal injury. Control athletes without a documented history of concussion were matched to concussed athletes by age, body mass index, position, and experience. Conditional logistic regression with a calculated odds ratio and a 95% confidence interval were used to assess the association between concussion and subsequent risk of LE injury.ResultsIn total, 189 concussions were documented in 153 athletes. Of these, 140 cases were the first recorded instance of concussion in players with publicly available data. Thirty-six (25.7%) athletes sustained a LE injury within 90 days of concussion; 26 (20.2%) were non-season-ending and included in RTP analysis. The odds of sustaining an acute LE musculoskeletal injury within the 90-day period after concussion was 4.69 times greater in concussed players compared with controls (95% confidence interval 1.96-11.23, P < .001). There was no significant difference in games (4.2 ± 5.0 vs 4.7 ± 4.7 games, P = .566) or days (18.5 ± 39.1 days vs 10.9 ± 10.6 days, P = .912) missed between concussed players with LE injury and nonconcussed controls. The most common LE injuries in concussed athletes were ligament sprains/tears (65%).ConclusionsConcussed NBA athletes have increased odds for sustaining an acute LE musculoskeletal injury within 90 days of RTP compared with nonconcussed controls. The most common injuries were ligament strains or tears. Changes in neuromotor control and proprioception following a concussion should be evaluated in high-level basketball players returning to sport.Level of evidenceLevel III, Case-Control Study.
| S-EPMC7879202 | biostudies-literature
Project description:Myocardial injury after non-cardiac surgery (MINS) is common. We investigated the incidence and outcomes of MINS, and mechanistic underpinnings using pre-operative whole blood gene expression profiling in a prospective cohort study of individuals undergoing lower extremity revascularization (LER) for peripheral artery disease (PAD). Major adverse cardiovascular and limb events (MACLE) were defined as a composite of death, myocardial infarction, stroke, major lower extremity amputation or reoperation. Among 226 participants undergoing LER, MINS occurred in 53 (23.5%). Patients with MINS had a greater incidence of major adverse cardiovascular events (49.1% vs. 22.0%, adjusted HR 1.87, 95% CI 1.07-3.26) and MACLE (67.9% vs. 44.5%; adjusted HR 1.66, 95% CI 1.08-2.55) at median 20-month follow-up. Pre-operative whole blood transcriptome profiling of a nested matched MINS case-control cohort (n = 41) identified upregulation of pathways related to platelet alpha granules and coagulation in patients who subsequently developed MINS. Thrombospondin 1 (THBS1) mRNA expression was 60% higher at baseline in patients who later developed MINS, and was independently associated with long-term cardiovascular events in the Duke Catheterization Genetics biorepository cohort. In conclusion, pre-operative THBS1 mRNA expression is higher in patients who subsequently develop MINS and is associated with incident cardiovascular events. Pathways related to platelet activity and coagulation associated with MINS provide novel insights into mechanisms of myocardial injury.
| S-EPMC9038775 | biostudies-literature
Project description:BACKGROUND:Yearly changes in active joint stiffness may help explain when neuromuscular sex differences emerge in adolescent athletes that may relate to increased anterior cruciate ligament injury risk in females. HYPOTHESIS:Pubertal males would demonstrate increases in knee stiffness while pubertal females would not. Second, postpubertal female athletes would have significantly lower knee joint stiffness than postpubertal male athletes. STUDY DESIGN:Cohort Study; Level of Evidence 2 and Cross-Sectional Study; Level of Evidence 3. METHODS:Two hundred sixty-five females and 50 males participated in 2 testing sessions approximately 1 year apart. The subjects were classified as either pubertal (n = 182, age 12.4 +/- 0.9 years) or postpubertal (n = 133, age 14.5 +/- 1.4 years) based on the modified Pubertal Maturational Observational Scale at each visit. Active joint stiffness of the ankle, knee, and hip was estimated during a drop vertical jump. Stiffness was calculated as the slope of the moment-angle curve from a least squares linear regression during the stance phase. RESULTS:All athletes showed increased active knee stiffness during the span of a year (P < 0.05). However, this increase was not different when stiffness was normalized to body mass. Only males demonstrated greater magnitudes of ankle and hip active stiffness (P < .05). Peak ankle and hip moments, but not knee moments, in postpubertal males were significantly greater than postpubertal females (P < .05). Females had a higher knee to hip moment ratio than males (P < .05). CONCLUSION:Both males and females showed increased active knee stiffness during the span of a year; males demonstrated increased ankle and hip active stiffness as well. Differences in hip joint posture at initial contact (greater flexion in males) and external hip flexion moment (greater flexion magnitude in males) may indicate that males use a different hip recruitment strategy during drop vertical jumps than females.
| S-EPMC3968426 | biostudies-literature
Project description:During unimanual motor tasks, muscle activity may not be restricted to the contracting muscle, but rather occurs involuntarily in the contralateral resting limb, even in healthy individuals. This phenomenon has been referred to as mirror electromyographic activity (MEMG). To date, the physiological (non-pathological) form of MEMG has been observed predominately in upper extremities (UE), while remaining sparsely described in lower extremities (LE). Accordingly, evidence regarding the underlying mechanisms and modulation capability of MEMG, i.e., the extent of MEMG in dependency of exerted force during unilateral isometric contractions are insufficiently investigated in terms of LE. Furthermore, it still remains elusive if and how MEMG is affected by long-term exercise training. Here, we provide novel quantitative evidence for physiological MEMG in homologous muscles of LE (tibialis anterior (TA), rectus femoris (RF)) during submaximal unilateral dorsiflexion in healthy young adults. Furthermore, endurance athletes (EA, n = 11) show a higher extent of MEMG in LE compared to non-athletes (NA, n = 11) at high force demands (80% MVC, maximum voluntary contraction). While the underlying neurophysiological mechanisms of MEMG still remain elusive, our study indicates, at least indirectly, that sport-related long-term training might affect the amount of MEMG during strong isometric contractions specifically in trained limbs. To support this assumption of exercise-induced limb-specific MEMG modulation, future studies including different sports disciplines with contrasting movement patterns and parameters should additionally be performed.
| S-EPMC5649197 | biostudies-literature
Project description:Machine learning approaches were introduced for better or comparable predictive ability than statistical analysis to predict postoperative outcomes. We sought to compare the performance of machine learning approaches with that of logistic regression analysis to predict acute kidney injury after cardiac surgery. We retrospectively reviewed 2010 patients who underwent open heart surgery and thoracic aortic surgery. Baseline medical condition, intraoperative anesthesia, and surgery-related data were obtained. The primary outcome was postoperative acute kidney injury (AKI) defined according to the Kidney Disease Improving Global Outcomes criteria. The following machine learning techniques were used: decision tree, random forest, extreme gradient boosting, support vector machine, neural network classifier, and deep learning. The performance of these techniques was compared with that of logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUC). During the first postoperative week, AKI occurred in 770 patients (38.3%). The best performance regarding AUC was achieved by the gradient boosting machine to predict the AKI of all stages (0.78, 95% confidence interval (CI) 0.75?0.80) or stage 2 or 3 AKI. The AUC of logistic regression analysis was 0.69 (95% CI 0.66?0.72). Decision tree, random forest, and support vector machine showed similar performance to logistic regression. In our comprehensive comparison of machine learning approaches with logistic regression analysis, gradient boosting technique showed the best performance with the highest AUC and lower error rate. We developed an Internet?based risk estimator which could be used for real-time processing of patient data to estimate the risk of AKI at the end of surgery.
| S-EPMC6210196 | biostudies-other