Performance-environment mutual flow model using big data on baseball pitchers data
Ontology highlight
ABSTRACT: The present study investigated the baseball pitching performance for the release speed, spin rate, and 3D coordinate data of the release point, depending on the ball and strike counts. We used open data registered on the official website of Major League Baseball (MLB), including 580 pitchers who pitched in the MLB between 2015 and 2019.
Project description:Purpose To evaluate and describe the differences in characteristics between the Major League Baseball (MLB) pitchers with greater workload and career longevity in terms of innings pitched (IP) and performance-matched controls who have not experienced similar length careers. Methods Using publicly available data, we identified the top 100 MLB pitchers in terms of career IP. Controls were matched to the top 100 pitchers by draft year and round. Pitchers with fewer than 400 IP were excluded. Demographic information, performance statistics, and injury history were reviewed. Logistic regression analysis and Mann–Whitney U tests were used to compare data. Results Compared with controls, the top 100 pitchers in terms of IP were drafted at a younger age (19.35 vs 19.83, P < .001) and in later rounds (6.16 vs 2.45, P < .001). They made their MLB debut at a younger age (21.77 vs 23.12, P < .001). They also pitched fewer innings before debut (470.59 vs 632.07, P = .007), were older at their first (30.72 vs 27.50 years, P < .001) and second (32.42 vs 29.43 years, P < .001) designations to the injured list (IL), and had a significantly longer time from debut to first (3063.50 vs 1565.59 days, P < .001) and second (3712.10 vs 2202.03 days, P < .001) IL trips. The top 100 pitchers were 7.45 times less likely to have made a trip to the IL within 8 seasons from their debut and were 4.04 times more likely to be younger than 24 years at their major league debut. Conclusions Pitchers with the greatest number of IP in their MLB careers were significantly younger when drafted and when they made their major league debut, although this age difference is likely clinically insignificant. Pitchers who were drafted or debuted at a later age accumulate more pre-debut innings and this may contribute to fewer total IP in the MLB. Similarly, later trips to the injured list and longer duration from debut to first or second trip to the IL, but not total IL trips, are predictive of longer careers compared to age and draft class matched controls. Level of Evidence III, retrospective cohort study.
Project description:ContextHip strength may influence the energy flow through the kinematic chain during baseball pitching, affecting athlete performance as well as the risk for injury.ObjectiveTo identify associations between hip strength and pitching biomechanics in adolescent baseball pitchers during 3 key events of the pitching cycle.DesignCross-sectional study.SettingBiomechanics laboratory.Patients or other participantsA total of 26 adolescent male baseball pitchers (age = 16.1 ± 0.8 years, height = 184.29 ± 5.5 cm, mass = 77.5 ± 8.5 kg).Main outcome measure(s)The main outcome measure was hip strength (external rotation, internal rotation, flexion, abduction, adduction, and extension). After strength measurements were acquired, motion capture was used to obtain a full-body biomechanical analysis at 3 events during the pitching cycle (foot contact, maximal external rotation, and ball release). We then evaluated these values for associations between hip strength and pitching biomechanics. Scatterplots were examined for linearity to identify an appropriate correlation test. The associations were linear; thus, 2-tailed Pearson correlation coefficients were used to determine correlations between biomechanical metrics. An α level of .01 was chosen.ResultsTen strong correlations were found between pitching biomechanics and hip strength: 8 correlations between hip strength and kinematics at key points during the pitch and 2 correlations of hip strength with peak elbow-varus torque.ConclusionsSeveral correlations were noted between lower extremity strength and pitching biomechanics. This information provides data that may be used to improve performance or reduce injury (or both) in pitchers. Increased hip strength in adolescent pitchers may both improve performance and decrease the risk of injury.
Project description:ContextInadequate hip active range of motion (AROM) may stifle the energy flow through the kinematic chain and decrease pitching performance while increasing the risk for pitcher injury.ObjectiveTo examine the relationship between hip AROM and pitching biomechanics during a fastball pitch in adolescent baseball pitchers.DesignCross-sectional study.SettingBiomechanics laboratory.Patients or other participantsA sample of 21 adolescent male baseball pitchers (age = 16.1 ± 0.8 years, height = 183.9 ± 5.2 cm, mass = 77.9 ± 8.3 kg).Main outcome measure(s)Bilateral hip external-rotation (ER), internal-rotation, flexion, abduction, and extension AROM were measured. Three-dimensional biomechanics were assessed as participants threw from an indoor pitching mound to a strike-zone net at regulation distance. Pearson product moment correlation coefficients were used to determine relationships between hip AROM and biomechanical metrics.ResultsNegative correlations were found at foot contact between back-hip ER AROM and torso-rotation angle (r = -0.468, P = .03), back-hip ER AROM and back-hip abduction angle (r = -0.474, P = .03), and back-hip abduction AROM and lead-hip abduction angle (r = -0.458, P = .04). Back-hip extension AROM was positively correlated with increased stride length (r = 0.446, P = .043). Lead-hip abduction AROM was also positively correlated with normalized elbow-varus torque (r = 0.464, P = .03).ConclusionsWe observed several relationships between hip AROM and biomechanical variables during the pitching motion. These findings support the influence that hip AROM can have on pitching biomechanics. Overall, greater movement at the hips allows the kinematic chain to work at maximal efficiency, increasing the pitch velocity potential.
Project description:BackgroundWeighted-ball throwing programs are commonly used in training baseball pitchers to increase ball velocity. The purpose of this study was to compare kinematics and kinetics among weighted-ball exercises with values from standard pitching (ie, pitching standard 5-oz baseballs from a mound).HypothesisBall and arm velocities would be greater with lighter balls and joint kinetics would be greater with heavier balls.Study designControlled laboratory study.MethodsTwenty-five high school and collegiate baseball pitchers experienced with weighted-ball throwing were tested with an automated motion capture system. Each participant performed 3 trials of 10 different exercises: pitching 4-, 5-, 6-, and 7-oz baseballs from a mound; flat-ground crow hop throws with 4-, 5-, 6-, and 7-oz baseballs; and flat-ground hold exercises with 14- and 32-oz balls. Twenty-six biomechanical parameters were computed for each trial. Data among the 10 exercises were compared with repeated measures analysis of variance and post hoc paired t tests against the standard pitching data.ResultsBall velocity increased as ball mass decreased. There were no differences in arm and trunk velocities between throwing a standard baseball and an underweight baseball (4 oz), while arm and trunk velocities steadily decreased as ball weight increased from 5 to 32 oz. Compared with values pitching from a mound, velocities of the pelvis, shoulder, and ball were increased for flat-ground throws. In general, as ball mass increased arm torques and forces decreased; the exception was elbow flexion torque, which was significantly greater for the flat-ground holds. There were significant differences in body positions when pitching on the mound, flat-ground throws, and holds.ConclusionsWhile ball velocity was greatest throwing underweight baseballs, results from the study did not support the rest of the hypothesis. Kinematics and kinetics were similar between underweight and standard baseballs, while overweight balls correlated with decreased arm forces, torques, and velocities. Increased ball velocity and joint velocities were produced with crow hop throws, likely because of running forward while throwing.Clinical relevanceAs pitching slightly underweight and overweight baseballs produces variations in kinematics without increased arm kinetics, these exercises seem reasonable for training pitchers. As flat-ground throwing produces increased shoulder internal rotation velocity and elbow varus torque, these exercises may be beneficial but may also be stressful and risky. Flat-ground holds with heavy balls should not be viewed as enhancing pitching biomechanics, but rather as hybrid exercises between throwing and resistance training.
Project description:Stock correlation networks use stock price data to explore the relationship between different stocks listed in the stock market. Currently this relationship is dominantly measured by the Pearson correlation coefficient. However, financial data suggest that nonlinear relationships may exist in the stock prices of different shares. To address this issue, this work uses mutual information to characterize the nonlinear relationship between stocks. Using 280 stocks traded at the Shanghai Stocks Exchange in China during the period of 2014-2016, we first compare the effectiveness of the correlation coefficient and mutual information for measuring stock relationships. Based on these two measures, we then develop two stock networks using the Minimum Spanning Tree method and study the topological properties of these networks, including degree, path length and the power-law distribution. The relationship network based on mutual information has a better distribution of the degree and larger value of the power-law distribution than those using the correlation coefficient. Numerical results show that mutual information is a more effective approach than the correlation coefficient to measure the stock relationship in a stock market that may undergo large fluctuations of stock prices.
Project description:BackgroundFatigue in baseball pitchers is a process linked to lowered physical and mental performance, injury, and changes in kinematics. Numerous studies have associated fatigue with overuse, high ball velocities, lack of rest time, poor mechanics, and degree of self-satisfaction. The aim of this study was to systematically review the literature to identify a theoretical framework for the relationship between outcomes and the manifestation of fatigue on baseball pitching. The synthesized data may identify areas requiring further research.MethodologyThis protocol was registered with PROSPERO (ID: CRD42018114194). SPORTDiscus, Medline, PubMed, Cochrane Database of Systematic Reviews, and Google Scholar were searched, using keywords such as fatigue in pitchers and changes in kinematics (e.g., pitching mechanics, valgus elbow torque), performance (e.g., pitch count, pitch type), and injury (e.g., pain, elbow, and shoulder soreness). Three reviewers independently screened the articles, selected relevant literature based on abstract eligibility, and assessed the methods described therein for final inclusion.ResultsA total of 31,860 articles were screened for eligibility and 25 articles were included for the review. The selected articles included epidemiological, longitudinal, experimental, conference papers, and crossover laboratory studies. Evidence extracted from the 25 studies demonstrates a relationship between fatigue in baseball pitching, and three overarching outcomes: changes in kinematics, a decrease in performance, and an increase in injury risk.ConclusionsFindings show that a co-dependence between changes in kinematics and a decrease in performance, which stems from central and peripheral fatigue, is a contributing factor of injury in baseball pitchers. A large percentage of baseball pitchers exhibit pain or soreness in either their elbow or shoulder, or both at some point in a season. Initially, kinematic changes occur that could maintain performance, but may increase joint and tissue loading. Performance decreased with elevated pitch counts and innings thrown, and pitching further into games or the season. Evidence was found to be consistent across all studies; however, more work is needed in the area of fatigue as an injury mechanism during pitching. With a proof of concept established, the prevention of negative outcomes associated with fatigue must be the focus of future research and performance should not be the only criteria.
Project description:PurposeTo evaluate preseason shoulder magnetic resonance images (MRIs) obtained from pitchers entering either major or minor league baseball (MLB) and correlate findings with subsequent injury, operative repair, and placement on the injured list (IL).MethodsPreseason-MRI of the throwing shoulders of professional-level baseball pitchers, taken during routine evaluations at a single organization (2004-2017) were retrospectively reviewed. Publicly available databases were queried to exclude pitchers with known injuries prior to pre-signing imaging. Three blinded reviewers reviewed all MRI scans independently to evaluate for the presence of abnormalities in the rotator cuff (RTC), labrum, capsule, long-head of the biceps tendon (LHBT), and humeral head. Binary imaging findings were correlated to future placement on the IL for subsequent shoulder complaints. Bivariate statistics using Student's t-tests and Fisher exact tests (both α = .05) were used in this study.ResultsA total of 38 asymptomatic pitchers with shoulder MRIs were included. Pitchers had a mean (±SD) age of 28.2 ± 4.9 and had pitched an average of 119.6 ± 143.8 career games. Pitchers with partial articular-sided RTC tears (P = .04) or intra-articular BT hyperintensity (P = .04) on preseason MRI demonstrated an association with the need for future surgery. Pitchers with evidence of labral heterogeneity demonstrated greater total career pitch counts (10,034.1 vs 2,465.3; P = .04). Evidence of a posterior-superior humeral cyst was associated with decreased strikeouts per 9 innings (6.1 vs 8.0; P = .039) and total strikeout percentage (16.1% vs 23.2%; P = .04).ConclusionAlthough there was a significant difference in the percent of various radiographic findings between the injured and healthy cohort, no MRI findings were predictive of future IL placement or duration of placement. The presence of a posterior superior humeral cyst was associated with decreased strikeout rates at 2 and 3 years, the presence of a labral tear was associated with decreased earned run average (ERA) at 3 years and decreased career strikeout percentages, and increased capsular signal was associated with decreased 5-year ERA.Level of evidenceLevel IV, retrospective study.
Project description:BackgroundAlthough risk adjustment remains a cornerstone for comparing outcomes across hospitals, optimal strategies continue to evolve in the presence of many confounders. We compared conventional regression-based model to approaches particularly suited to leveraging big data.Methods and resultsWe assessed hospital all-cause 30-day excess mortality risk among 8952 adults undergoing percutaneous coronary intervention between October 1, 2011, and September 30, 2012, in 24 Massachusetts hospitals using clinical registry data linked with billing data. We compared conventional logistic regression models with augmented inverse probability weighted estimators and targeted maximum likelihood estimators to generate more efficient and unbiased estimates of hospital effects. We also compared a clinically informed and a machine-learning approach to confounder selection, using elastic net penalized regression in the latter case. Hospital excess risk estimates range from -1.4% to 2.0% across methods and confounder sets. Some hospitals were consistently classified as low or as high excess mortality outliers; others changed classification depending on the method and confounder set used. Switching from the clinically selected list of 11 confounders to a full set of 225 confounders increased the estimation uncertainty by an average of 62% across methods as measured by confidence interval length. Agreement among methods ranged from fair, with a κ statistic of 0.39 (SE: 0.16), to perfect, with a κ of 1 (SE: 0.0).ConclusionsModern causal inference techniques should be more frequently adopted to leverage big data while minimizing bias in hospital performance assessments.
Project description:Several studies have investigated factors influencing baseball pitching velocity. However, some measurements require expensive equipment, and some tests need familiarity to perform well. In this study, we adopted field tests executed using affordable equipment in a tryout event for a professional baseball team in Taiwan, 2019. We use half day to test 64 players, and the result of measurement are used to develop a model for predicting pitching velocity of amateur adult pitchers (age: 23.9 ± 2.8 years; height: 180.3 ± 5.9 cm; weight: 81.4 ± 10.9 kg). The measurements and tests in tryout settings should be easy to implement, take short time, do not need high skill levels, and correlate to the pitching velocity. The outcome measures included maximum external shoulder rotation, maximum internal shoulder rotation, countermovement jump (CMJ) height, 20-kg loaded CMJ height, 30-m sprint time, height, age, and weight tests. Multiple regression indicated a moderate correlation between these tests and pitching velocity (adjusted R2 = 0.230, p = 0.0003). Among the measures, the ratio of loaded CMJ to CMJ, ratio of first 10-m sprint time to 30-m sprint time, and height were significant contributors to pitching velocity. Overall, these measures explained 23% of the variance in the predicted pitching velocity. These field tests can be adopted in tryout events to predict a prospect's potential and to identify underestimated players. Coaches can obtain an expectation of a pitcher's performance by comparing his pitching velocity with the predicted value derived from the statistical model presented herein, and the room of growth by comparing his current strength to average strength growth after being drafted and trained with professional coaches.
Project description:BackgroundNumerous studies have discussed the risk factors for shoulder and elbow injuries in high school baseball players worldwide.PurposeTo determine the risk factors for pitching-related shoulder and elbow injuries in Taiwanese high school pitchers.Study designCross-sectional study; Level of evidence, 3.MethodsIncluded in the study were 144 pitchers from 11 top-ranked Taiwanese high school baseball teams between 2016 and 2017 high school baseball season. The participants answered a 55-item questionnaire concerning physical characteristics, pitching activities, injury history, and off-season activities. Univariate analyses were conducted separately for participants with and those without a pitching-related injury in the 12-month study period. The chi-square test or Fisher exact test was applied to categorical variables, and the F test or t test was applied to continuous variables. A stepwise multivariate logistic regression analysis was used to identify factors related to pitching-related injuries, and those results were calculated as odds ratios (ORs).ResultsHaving a pitching-related injury was significantly related to the number of pitches per week in the past 12 months (OR, 1.01; P = .006), pain over the shoulder and/or elbow in the past 12 months (OR, 3.56; P = .008), pitching competitive baseball for more than 8 of the past 12 months (OR, 2.53; P = .036), throwing sliders (OR, 2.97; P = .026), and lack of participating in other over-the-shoulder activities (0.03-0.11 fewer odds; P ≤ .010).ConclusionFor elite high school pitchers in Taiwan, pitching-related shoulder and elbow injuries were related to the number of pitches per week, pitching competitive baseball for more than 8 of the past 12 months, pain over the shoulder and/or elbow in the past 12 months, throwing sliders, and a lack of participation in other sports with over-the-shoulder activities.