Predictors of Ulnar Collateral Ligament Reconstruction in Major League Baseball Pitchers

Kinematic Modeling of Pitch Velocity in High School and Professional Baseball Pitchers: Comparisons With the Literature

Background

Kinematic parameters predictive of pitch velocity have been evaluated in adolescent and collegiate baseball pitchers; however, they have not been established for high school or professional pitchers.

Purpose

To create multiregression models using anthropometric and kinematics features most predictive for pitch velocity in high school and professional pitchers and compare them with prior multiregression models evaluating other playing levels.

Study Design

Descriptive laboratory study.

Methods

High school (n = 59) and professional (n = 337) baseball pitchers threw 8 to 12 fastballs while being evaluated with 3-dimensional motion capture (480 Hz). Using anthropometric and kinematic variables, multiregression models for pitch velocity were created for each group. A systematic review was conducted to determine previous studies that established kinematic models for ball velocity in youth, high school, and collegiate pitchers.

Results

Leg length was predictive of pitch velocity for high school and professional pitchers (P < .001 for both). When compared with previously established models for pitch velocity, almost all groups were distinct from one another when assessing age (P maximum < .001), weight (P max = .0095), and pitch velocity (P max < .001). Stride length was a significant predictor for the youth/high school pitchers, as well as the current study's high school and professional pitchers (P < .001 for all). Maximal shoulder external rotation (collegiate: P = .001; professional: P < .001) and maximal elbow extension velocity (high school/collegiate: P = .024; collegiate: P < .001; professional: P = .006) were shared predictors for the collegiate and current study's professional group multiregression models. Trunk flexion at ball release was a commonly shared predictor in the youth/high school (P = .04), high school/collegiate (P = .003), collegiate (P < .001), and the current study's professional group (P < .001).

Conclusion

Youth, high school, collegiate, and professional pitchers had unique, predictive kinematic and anthropometric features predictive of pitch velocity. Leg length, stride length, trunk flexion at ball release, and maximal shoulder external rotation were predictive features that were shared between playing levels.

Clinical Relevance

Coaches, clinicians, scouts, and pitchers can consider both the unique and the shared predictive features at each playing level when attempting to maximize pitch velocity.

A Retrospective Analysis of Major League Baseball Hit-by-Pitch Rates before and after the Crackdown on Foreign Substance Use

OBJECTIVE

Determine whether there was an increased incidence of hit-by-pitch events in Major League Baseball (MLB) following the decision to enforce the foreign substance ban for pitchers during the 2021 season.

DESIGN

Descriptive Epidemiological Study.

SETTING

Major League Baseball hit-by-pitch data from publicly available Web sites ( mlb.com and fangraphs.com ).

PARTICIPANTS

Major League Baseball players during the 2017, 2018, 2019, 2021, and 2022 seasons.

INDEPENDENT VARIABLES

Hit-by-pitch exposure data by season and individual pitch type.

MAIN OUTCOME MEASURES

Hit-by-pitch incidence rates from the 2017 to 2019 seasons (preenforcement) and the 2021 to 2022 seasons (postenforcement). Rates were compared with incidence rate ratios (IRRs).

RESULTS

Hit-by-pitch incidence rate increased from 2.66 to 3.06 per 1000 total pitches (IRR, 1.15 [95% CI, 1.08-1.23]; P < 0.0001) following the enforcement. Incidence rates for 2017, 2018, and 2019 did not differ from each other individually, but incidence rate of all 3 seasons individually were significantly lower than that for the 2021 season ( P < 0.005). Sliders were 29% more likely to hit batters following the enforcement ( P = 0.0015).

CONCLUSIONS

Major League Baseball batters were hit by pitches at a significantly higher rate following the league's crackdown on foreign substance use for the 2021 seasons compared with the same time of year during the 2017 to 2019 seasons. This was followed by a slight regression toward preenforcement levels during the 2022 season.

Biomechanical effects of foot placement during pitching

Baseball coaches often focus on the landing position of a pitcher's front foot as a key aspect of mechanics. Furthermore, controversy persists regarding positioning the rear foot on the first base or third base end of the rubber. The purpose of this study was to determine the effect of rear and front foot placement on pitching biomechanics. Our hypotheses were that there would be significant kinematic and kinetic differences associated with foot placement. This was a retrospective review including 144 healthy right-handed adult baseball pitchers divided into groups based on their rear and front foot placements: first base open (1B-Open), first base closed (1B-Closed), third base open (3B-Open), and third base closed (3B-Closed). Two-way ANOVAs detected no statistically significant main effects for kinetic variables but several for kinematic variables. Open pitchers had less shoulder abduction at the time of ball release and greater maximum shoulder internal rotation velocity in comparison with closed pitchers. They also had less forearm pronation at the time of ball release and greater maximum elbow extension velocity. Additional statistically significant results were found; however, low effect sizes may lessen the clinical significance of many of the results.

Use of Publicly Obtained Data in Sports Medicine Research: A Systematic Review and Bibliometric Analysis

BACKGROUND

Publicly obtained data (POD) have recently been utilized frequently by sports medicine researchers to describe injury patterns, risk factors, and outcomes in elite athletes. The relative ease of this type of research that is based solely on internet and media sources has resulted in a near exponential increase in the number of these POD studies.

PURPOSE

To systematically review the sports medicine literature for studies based solely on POD.

STUDY DESIGN

Systematic review and bibliometric analysis; Level of evidence, 4.

METHODS

A systematic review of POD studies published since 2000 was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies of interest were those relying on publicly available injury reports or online media for data acquisition in collegiate, semiprofessional, and professional athletes.

RESULTS

There were 209 POD studies published between 2000 and 2022, with 173 (82.8%) of these studies published after 2016. Studies were published most frequently on athletes participating in North American professional leagues: National Football League (n = 69 [28.4%]), Major League Baseball (n = 56 [23.0%]), National Basketball Association (n = 37 [15.2%]), and National Hockey League (n = 33 [13.6%]). The most common injuries assessed were head injuries/concussions (n = 43 [21.1%]), anterior cruciate ligament injuries (n = 33 [16.2%]), and ulnar collateral ligament injuries (n = 23 [11.3%]). One-quarter of the studies (n = 53 [25.4%]) reported only 1 POD source, and 1 study (0.5%) reported no source. Additionally, 65 studies (31.1%) listed nonspecific POD resources or solely cited previous literature to describe the POD search methodology and data acquisition.

CONCLUSION

POD studies are exponentially increasing in number, particularly across major North American professional sports leagues, with significant variability in the injury of interest, search methodology, and number of data sources. The accuracy of the conclusions reached based on the POD methodology appears highly variable. Given the potential impact of these publications as both contributors to current knowledge and drivers of future research, the sports medicine community should be aware of the inherent biases and limitations of POD injury studies.

Pitch-classifier model for professional pitchers utilizing 3D motion capture and machine learning algorithms

Introduction

A pitcher's ability to achieve pitch location precision after a complex series of motions is of paramount importance. Kinematics have been used in analyzing performance benefits like ball velocity, as well as injury risk profile; however, prior utilization of such data for pitch location metrics is limited.

Objective

To develop a pitch classifier model utilizing machine learning algorithms to explore the potential relationships between kinematic variables and a pitcher's ability to throw a strike or ball.

Methods

This was a descriptive laboratory study involving professional baseball pitchers (n = 318) performing pitching tests under the setting of 3D motion-capture (480 Hz). Main outcome measures included accuracy, sensitivity, specificity, F1 score, positive predictive value (PPV), and negative predictive value (NPV) of the random forest model.

Results

The optimized random forest model resulted in an accuracy of 70.0 %, sensitivity of 70.3 %, specificity of 48.5 %, F1 equal to 80.6 %, PPV of 94.3 %, and a NPV of 11.6 %. Classification accuracy for predicting strikes and balls achieved an area under the curve of 0.67. Kinematics that derived the highest % increase in mean square error included: trunk flexion excursion(4.06 %), pelvis obliquity at foot contact(4.03 %), and trunk rotation at hand separation(3.94 %). Pitchers who threw strikes had significantly less trunk rotation at hand separation(p = 0.004) and less trunk flexion at ball release(p = 0.003) compared to balls. The positive predictive value for determining a strike was within an acceptable range, while the negative predictive value suggests if a pitch was determined as a ball, the model was not adequate in its prediction.

Conclusions

Kinematic measures of pelvis and trunk were crucial determinants for the pitch classifier sequence, suggesting pitcher kinematics at the proximal body segments may be useful in determining final pitch location.

Association Between Draft Order and Stress Sonography of the Ulnar Collateral Ligament of the Elbow in Professional Baseball Pitchers: An 18-Year Study

BACKGROUND

The Major League Baseball (MLB) draft is a common route for players to enter professional baseball in the United States. Players taken in earlier rounds are typically higher-performing players. When looking at pitchers specifically, higher performance at the amateur level may be associated with an increased frequency of adaptive change in the throwing elbow.

PURPOSE

To determine whether pitchers taken in earlier rounds of the MLB draft have a greater frequency or extent of pathological change in the elbow, as measured by dynamic stress ultrasound.

STUDY DESIGN

Cross-sectional study; Level of evidence, 3.

METHODS

Dynamic stress ultrasounds (SUSs) were performed over 18 years on the dominant and nondominant arms of 651 professional pitchers. The 383 drafted players were grouped according to the round in which they were drafted (rounds 1-5, 6-10, 11-20, 21+). Groups were compared with respect to "relative" ulnar collateral ligament (UCL) thickness (dominant-nondominant), relative ulnohumeral joint laxity (joint space distance under stress minus joint space at rest), and the presence of pathology (calcifications, tears, hypoechoic foci, osteophytes). In addition, a subgroup analysis was done to compare the progression of SUS findings over 3 years in players for which data were available.

RESULTS

Draft round groups did not differ by age, number of previous spring training, or handedness. Comparing baseline measurements, there was no significant relationship between draft round and relative UCL thickness (P = .932), relative laxity (P = .996), or presence of pathology detectable on SUS (P = .642). However, increased relative UCL thickness was significantly associated with the presence of pathology on SUS (odds ratio, 1.45; 95% CI, 1.26-1.69; P < .001). Longitudinally, there was no significant relationship between draft round and 3-year progression of relative laxity, relative UCL thickness, or clinical progression of pathology.

CONCLUSION

Higher-performing pitchers are drafted earlier in the MLB draft. This may be attributable to peak pitch velocity, in-game performance, visibility gained during player showcases, or any number of other sport-specific variables. However, despite this, there was no significant relationship between draft round and adaptive changes to the elbow or specific properties of the UCL on stress ultrasound.

The Trade Secret Taboo: Open Science Methods are Required to Improve Prediction Models in Sports Medicine and Performance

Clinical prediction models in sports medicine that utilize regression or machine learning techniques have become more widely published, used, and disseminated. However, these models are typically characterized by poor methodology and incomplete reporting, and an inadequate evaluation of performance, leading to unreliable predictions and weak clinical utility within their intended sport population. Before implementation in practice, models require a thorough evaluation. Strong replicable methods and transparency reporting allow practitioners and researchers to make independent judgments as to the model's validity, performance, clinical usefulness, and confidence it will do no harm. However, this is not reflected in the sports medicine literature. As shown in a recent systematic review of models for predicting sports injury models, most were typically characterized by poor methodology, incomplete reporting, and inadequate performance evaluation. Because of constraints imposed by data from individual teams, the development of accurate, reliable, and useful models is highly reliant on external validation. However, a barrier to collaboration is a desire to maintain a competitive advantage; a team's proprietary information is often perceived as high value, and so these 'trade secrets' are frequently guarded. These 'trade secrets' also apply to commercially available models, as developers are unwilling to share proprietary (and potentially profitable) development and validation information. In this Current Opinion, we: (1) argue that open science is essential for improving sport prediction models and (2) critically examine sport prediction models for open science practices.

Kinematic and Kinetic Comparisons of Arm Slot Position Between High School and Professional Pitchers

Background

Throwing arm kinetics differ in pitchers at varying arm slot (AS) positions (frontal-plane arm position at ball release relative to the vertical axis).

Purpose

To determine how kinematic and kinetic values differ between professional and high school pitchers with varying AS positions, and whether these differences are similarly observed in both populations.

Methods

High school (n = 130) and professional (n = 288) pitchers threw 8 to 12 fastballs under 3-dimensional motion capture technology. Pitchers in each cohort were subdivided based on mean AS position at ball release: AS1 (least degree of AS: most overhand throwing styles), AS2 (intermediate degree of AS: three-quarter throwing styles), or AS3 (greatest degree of AS: most sidearm throwing styles). Kinetic and kinematic parameters were compared between groups.

Study Design

Controlled laboratory study.

Results

High school pitchers had a more overhand AS at ball release (50° ± 11°) compared with professional pitchers (58° ± 14°) (P < .001). In both cohorts, AS1 pitchers had significantly greater shoulder abduction (high school, P <0.001; professional, P <0.0001) and lateral trunk flexion (high school, P < 0.001; professional, P <0.0001) at ball release compared with AS3 pitchers. Professional pitchers with an AS3 position had significantly delayed timing of maximum upper trunk angular velocity compared with AS1 pitchers (64% ± 7% vs 57% ± 7% of pitch time, respectively; P < .0001). A significant positive correlation between AS and elbow flexion torque was found in high school pitchers (P = .002; β = 0.28), and a significant negative correlation between AS and elbow varus torque (P < .001; β = -0.22) and shoulder internal rotation torque (P < .001; β = -0.20) was noted in professional pitchers.

Conclusion

AS position was related to shoulder abduction and trunk lateral tilt. Professional and high school pitchers with varying AS positions did not experience similar changes in throwing arm kinetics.

Clinical Relevance

In professional pitchers, the earlier onset of maximum upper trunk angular velocity with overhand throwing style may reflect inappropriate pelvis-trunk timing separation, a parameter implicated in upper extremity injury, and the negative correlation between AS and elbow varus and shoulder internal rotation torque suggests that both excessive and minimal AS positions have negative implications.

Characteristics Associated With Noncompliance of Current Pitch Smart Guidelines in High School Baseball Pitchers Throughout the United States

Background

Although pitch count and rest guidelines have been promoted for youth and adolescent baseball players for nearly 2 decades, compliance with guidelines remains poorly understood.

Purpose/Hypothesis

The purpose of this study was to determine the frequency of compliance with Major League Baseball (MLB) Pitch Smart guidelines as well as the association between compliance and range of motion (ROM), strength, velocity, injury, and pitcher utilization. It was hypothesized that pitchers in violation of current recommendations would have increased strength, velocity, and injury.

Study Design

Case-control study; Level of evidence, 3.

Methods

This was a prospective, multicenter study of 115 high school pitchers throughout the United States. Pitchers were surveyed about their compliance with current off-season, rest-related guidelines, and history of injury. During the preseason, pitchers underwent standardized physical examinations, and pitch velocity was measured. Pitch counts were collected during the baseball season that followed. Dynamometer strength testing of shoulder forward flexion, and external rotation as well as grip strength was recorded. We compared pitchers who were compliant with recommendations with those who were noncompliant using Student t and Mann-Whitney U tests.

Results

Based on preseason data, 84% of pitchers had violated current Pitch Smart guidelines. During the season, 14% had at least 1 violation of the Pitch Smart guidelines. Across both the preseason survey and in-season pitch counts, 89% of players had at least 1 violation of the Pitch Smart guidelines. While there were no significant differences in ROM or strength, the noncompliant group had higher maximum pitch velocity than the compliant group (74 ± 8 vs 69 ± 5 mph [119 ± 13 vs 111 ± 8 kph], respectively; P = .009). Players' self-reported velocity differed significantly from the direct measurement, for both peak velocity (80 ± 6 vs 73 ± 8 mph [129 ± 9 vs 117 ± 13 kph], respectively; P < .001) and mean velocity (73 ± 8 vs 53 ± 27 mph [117 ± 13 vs 85 ± 43 kph], respectively; P < .001).

Conclusion

Most high school pitchers were not fully compliant with current Pitch Smart guidelines, and they tended to overestimate their peak velocity by 7 mph (11 kph). Pitchers who threw with greater velocity were at higher risk for violating Pitch Smart recommendations.

A novel method intersecting three-dimensional motion capture and medial elbow strength dynamometry to assess elbow injury risk in baseball pitchers

In baseball pitching, resultant elbow varus torque reaches the peak value of 50-120 N m, exceeding the joint failure limit that risks damage to the ulnar collateral ligament (UCL). In-vivo methodology is lacking to assess whether pitchers have sufficient muscular strength to shield UCL and how strongly the elbow musculature must contract to minimize valgus loading on UCL. This study introduces a method to assess relative percentages of muscular varus strength required to unload the UCL. The maximum voluntary isometric varus strength (MVIVS) produced by the medial elbow musculature and the maximum resultant varus torques at elbow in pitching fastballs and other types were measured for two professional pitchers. Simulation was conducted to determine the relative percentages of MVIVS required to unload the UCL to varying degrees and the impact of athletes' previous UCL reconstruction on the relative percentages was examined. The maximum resultant varus torque in pitching was found to range 72-97%MVIVS depending on the type of pitch. The elbow musculature had to produce 21-49%MVIVS to avoid acute failure of intact UCL whereas the corresponding requirements were 39-63%MVIVS for UCL reconstructed joint. The method offers new insight into baseball pitcher's training/rehabilitation and physical assessment to reduce the risk of UCL injury.

Comparison of the "Tall and Fall" Versus "Drop and Drive" Pitching Styles: Analysis of Major League Baseball Pitchers During a Single Season

Background

Previous research has documented the proportion of "tall and fall" (TF) and "drop and drive" (DD) pitching styles among Major League Baseball (MLB) pitchers who underwent ulnar collateral ligament reconstruction (UCLR). The proportion of these 2 styles among all MLB pitchers remains unknown.

Purpose

To determine the proportion of the TF and DD pitching styles in all rostered MLB pitchers during a single season as well as the proportion of TF and DD pitchers who sustained an upper extremity (UE) injury and those who underwent UCLR.

Study Design

Cross-sectional study; Level of evidence, 3.

Methods

Pitcher demographic characteristics from the 2019 MLB season and pitching information were obtained via open-access sources. Two-dimensional video analysis was used to categorize the included pitchers into TF and DD groups. Statistical comparisons and contrasts were made using 2-tailed t tests, chi-square tests, and Pearson correlation analyses as appropriate.

Results

Of the 660 MLB rostered pitchers in 2019 (age, 27.39 ± 3.51 years; body mass index, 26.34 ± 2.47 kg/m²; fastball velocity, 150.49 ± 3.99 kph [93.51 ± 2.48 mph]), 412 (62.4%) pitchers used the TF style and 248 (37.6%) pitchers used the DD style. Significantly more UE injuries were seen in the TF group compared with the DD group (112 vs 38 injuries, respectively; P < .001). Twelve pitchers underwent UCLR (TF, 10; DD, 2), representing a 1.8% UCLR rate among all pitchers. This was a second surgery for 2 pitchers, both of whom used the TF pitching style. Significantly more pitchers in the TF group than the DD group had undergone UCLR before 2019 (135 vs 56 pitchers, respectively; P = .005).

Conclusion

The results of the present study demonstrated a higher prevalence of both UE injury and prior UCLR in TF pitchers. Further research is needed to explore the potential association between pitching style and UE injury.

Changes in Elbow Stress and Ball Velocity During Reduced Effort Pitching: A Marker-Based Motion Capture Analysis

BACKGROUND

Baseball pitchers often participate in throwing programs that involve throwing at reduced effort levels to gradually increase the amount of stress experienced across the elbow. It is currently unknown how reduced effort pitching compares with maximum effort with respect to elbow stress and ball velocity.

PURPOSE/HYPOTHESIS

The purpose was to determine the correlation between elbow stress and ball velocity with reduced effort pitching. We hypothesized that decreased perceived effort would disproportionately correlate with elbow stress and ball velocity.

STUDY DESIGN

Descriptive laboratory study.

METHODS

Ten healthy male high school baseball pitchers threw 5 pitches from a regulation pitching mound at 3 effort levels: maximum effort, 75% effort, and 50% effort. Elbow stress, specifically elbow varus torque, was calculated for all pitches using a validated marker-based 3-dimensional motion capture system. Ball velocity was measured using a Doppler radar gun. Intrathrower variability was calculated for each effort level.

RESULTS

Elbow stress and ball velocity decreased with reduced effort throws (P < .001 and P = .003, respectively). However, the reductions in elbow stress and ball velocity were not proportional. At 75% effort throws, elbow stress measured 81% (intraclass correlation coefficient [ICC], 0.95), and ball velocity measured 90% (ICC, 0.80) of maximum, respectively. At 50% effort throws, elbow stress measured 75% (ICC, 0.93), and ball velocity measured 85% (ICC, 0.87) of maximum. Intrathrower reliability was excellent for elbow stress and ball velocity, with all ICCs ≥0.80.

CONCLUSION

Pitching at a reduced effort level resulted in decreased elbow stress and ball velocity. However, for every 25% reduction in perceived effort, elbow stress decreased by a mean 13%, and ball velocity decreased 7.5%. When baseball pitchers attempt to throw at a reduced effort of maximum, throwing metrics do not decrease proportionately.

CLINICAL RELEVANCE

While pitching at a reduced effort of maximum decreases elbow stress and ball velocity, the decrease is not proportional, subjecting the elbow to more stress than intended. This has significant clinical importance to pitchers, coaches, and medical professionals in the setting of injury prevention and return to sports.

Effect of High School Showcase Exposures and Timing of Ulnar Collateral Ligament Tear on Professional Baseball Careers in Elite Pitchers

BACKGROUND

Showcase participation has been considered a risk factor for elbow injuries. It remains unclear whether high school (HS) showcase volume negatively affects pitchers' career paths. Because pitchers are achieving 90 mph thresholds at younger ages, it is unknown whether shorter time intervals between achieving 90 mph thresholds and dates of ulnar collateral ligament reconstruction (UCL-R), known as time to tear (TTT), may affect career trajectory.

HYPOTHESIS

Elite pitchers with higher HS showcase volumes would be less likely to reach Major League Baseball (MLB) level compared with elite pitchers with fewer HS showcase appearances. Elite pitchers with longer TTT intervals would be more likely to achieve MLB level.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

Demographic, HS showcase and professional performance, and injury data from pitchers selected in the first 5 rounds of the MLB draft (2011-2017) were gathered from publicly available databases. Continuous and categorical variables were compared for the following subgroups: UCL-R group and pitcher group not undergoing UCL-R; "early" and "late" UCL-R groups; and pitchers achieving and pitchers not achieving MLB level. Multivariable analysis was performed using logistic regression. Standard deviations of ±1 SD were used to define early career versus late career UCL-R subgroups after normal distribution was confirmed (Shapiro-Wilk test; P = .227). The early UCL-R group was defined as those pitchers undergoing UCL-R ≤-1 SD from the mean age at first injury (group mean age, 19.43 years), whereas the late UCL-R group was defined as ≥+1 SD from that age (group mean age, 25.19 years).

RESULTS

Of 611 pitchers, 455 (74.5%) had HS showcase performance data, and 608 (99.5%) had professional performance data. In total, 184 (30.1%) pitchers underwent UCL-R. Fewer pitchers who underwent early UCL-R achieved the MLB level compared with pitchers who underwent late UCL-R (48.1% vs 86.2%; P = .006). Elite pitchers who pitched in ≥10 showcases in HS had half the odds of achieving the MLB level compared with pitchers who participated in <10 HS showcases (adjusted odds ratio, 0.50; 95% CI, 0.29-0.86; P = .012). For every year longer that an elite pitcher did not tear his UCL after achieving the 90 mph threshold at an HS showcase (TTT after 90 mph [per year]), the likelihood of achieving the MLB level increased by 24% (adjusted odds ratio, 1.24; 95% CI, 1.02-1.52; P = .032).

CONCLUSION

Higher HS showcase volume in elite pitchers was associated with a lower likelihood of achieving MLB level. A longer TTT after 90 mph (per year) was significantly associated with achieving MLB level in elite pitchers.

Increased Pitch Velocity Is Associated With Throwing Arm Kinetics, Injury Risk, and Ulnar Collateral Ligament Reconstruction in Adolescent, Collegiate, and Professional Baseball Pitchers: A Qualitative Systematic Review

PURPOSE

To assess the relationship between pitch velocity and throwing arm kinetics, injury, and ulnar collateral ligament reconstruction (UCLr) among high school, collegiate, and professional baseball pitchers.

METHODS

The Cochrane Database of Systematic Reviews, the Cochrane Central Register of Controlled Trials, PubMed (2008-2019), and OVID/MEDLINE (2008-2019) were queried for articles that reported on pitch velocity predicting throwing arm kinetics, injury, or UCLr. The Methodological Index for Non-randomized Studies checklist was used to evaluate the quality of all included studies. Descriptive statistics with ranges were used to quantify data where appropriate.

RESULTS

A total of 24 studies examining 2,896 pitchers, with Level of Evidence II-V were included. Intergroup analysis noted pitch velocity was significantly correlated with elbow varus torque in high school (R² = 0.36), collegiate (R² = 0.29), and professional (R² = 0.076) pitchers. Elbow distraction force was positively associated with ball velocity in interpitcher analyses of high school (R² = 0.373), professional (R² = 0.175), and mixed-cohort evaluations (R² = 0.624). Intragroup analysis demonstrated a strong association between pitch velocity and elbow varus torque (R² = 0.922-0.957) and elbow distraction force (R² = 0.910) in professional pitchers. Faster ball velocity was positively associated with a history of throwing arm injury (R² = 0.194) in nonadult pitchers. In 2 studies evaluating professionals, injured pitchers had faster pitch velocity before injury compared with uninjured controls (P = .014; P = .0354). The need for UCLr was positively correlated with pitch velocity (R² = 0.036) in professional pitchers. The consequences of UCLr noted little to no decrease in pitch velocity.

CONCLUSIONS

Professional baseball pitchers with faster pitch velocity may be at the greatest risk of elbow injury and subsequent UCLr, potentially through the mechanism of increased distractive forces on the medial elbow complex. When a pitcher ultimately undergoes UCLr, decreases in pitching performance are unlikely, but may occur, which should encourage pitchers to caution against maximizing pitch velocity.

LEVEL OF EVIDENCE

Level IV, systematic review of Level II-IV studies.

A Number of Modifiable and Nonmodifiable Factors Increase the Risk for Elbow Medial Ulnar Collateral Ligament Injury in Baseball Players: A Systematic Review

PURPOSE

To analyze the current literature regarding risk factors associated with medial ulnar collateral ligament (MUCL) injury in baseball players and to serve as a robust source for identifying modifiable risk factors that once optimized, have the potential to reduce injury risk.

METHODS

Comprehensive search of the available literature was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Studies were included if they evaluated risk factors for MUCL injuries in the elbow of baseball players. Risk of bias assessment was performed via Methodological Index for Non-randomized Studies (MINORS) scoring system. The Oxford Centre for Evidence-Based Medicine was used to determine level of evidence. Variables of interest; player age, position, shoulder motion, humeral retrotorsion, joint laxity, strength, balance, geography, velocity, pitch count, pitch types, throwing volumes, and throwing mechanics were recorded.

RESULTS

Twenty-one studies were included in this systematic review. MINORS scores ranged from 75 to 87%, and variables demonstrated significant heterogeneity. Performance-based risk factors for MUCL injury included: increased pitch count (both annual and per game), higher percentage of fastballs thrown, smaller pitch repertoire, and/or a loss of pitching velocity. Biomechanical studies demonstrated the relationship between decreased shoulder range of motion (total ROM, ER, IR, and abduction), increased humeral retrotorsion, increased elbow valgus opening in the throwing arm, lower Y-Balance score, and increased lateral release position to increased MUCL injury.

CONCLUSION

Risk factors for MUCL injury can generally be categorized into 4 primary groups: 1) various player demographics and characteristics, 2) throwing too hard (high velocity), 3) throwing too much (pitch count/volume), and 4) throwing with poor mechanics. In this systematic review, the most significant nonmodifiable risk factors for MUCL injuries included: increased glenohumeral retrotorsion and elbow valgus opening. The most consistent modifiable risk factors included: total shoulder range of motion, pitch count, pitch selection, Y balance score, and lateral release position. Pitch velocity was inconsistent in literature, but most studies found this as a risk for injury. These risk factors may serve as appropriate targets for future evidence-based injury mitigation strategies.

LEVEL OF EVIDENCE

Level IV, systematic review of Level II-IV studies.

Pitching mechanics and performance of adult baseball pitchers: A systematic review and meta-analysis for normative data

OBJECTIVES

The aim of this systematic review was to critically review and synthesise the findings from primary studies on pitching mechanics and performance of healthy adult baseball pitchers.

DESIGN

Systematic review with meta-analysis.

METHODS

Eight English- and Japanese-language databases were systematically searched from inception to 22nd July 2022.

RESULTS

In total, 29 descriptive biomechanical studies were included. Overall study quality was moderate. In subgroup analyses, professional pitchers showed significantly higher stride length, peak shoulder internal rotation velocity, peak shoulder proximal force and ball velocity compared to collegiate pitchers. Conversely, collegiate pitchers were found to have significantly higher peak pelvis rotation velocity.

CONCLUSIONS

Available normative data suggested potentially heterogeneous pitching mechanics and performance between professional and collegiate pitchers. However, the findings in this review should be interpreted cautiously. Since statistical heterogeneity was significant within most data sets, more detailed subgroup analyses are required. Additionally, more high-quality studies utilising measurement systems with established reliability are required to obtain accurate data in baseball pitching mechanics and performance.

Kinetic and kinematic comparisons in high school pitchers with low and high pitch location consistency

BACKGROUND

Although ball velocity has often been associated with increased kinetics at the upper extremity and risk of injury in youth and adolescent pitchers, it is unclear if the performance metric pitch location consistency has any positive or negative associations with pitching kinetics.

METHODS

High school pitchers (n = 59) pitched 8-12 fastballs using 3D motion capture (480 Hz). Pitchers were divided into high-consistency (HiCon) and low-consistency (LoCon) groups based on the absolute center deviation of each pitcher's pitch to the center of the pitcher's mean pitch location. Ninety-five percent confidence ellipses with major and minor radii were constructed, and kinematics and kinetics were compared between groups.

RESULTS

Compared with LoCon pitchers, HiCon pitchers had decreased lead hip flexion at elbow extension (40° ± 12° vs. 52° ± 13°, respectively, P = .008), and at foot contact, decreased back hip extension (-1° ± 10° vs. -10° ± 13°, respectively, P = .038) and increased back hip internal rotation (9° ± 15° vs. -2° ± 15°, respectively, P = .043). LoCon pitchers achieved maximum lead hip flexion earlier in the pitch (61.3% ± 23.2% vs. 75.8% ± 15.1%, respectively, P = .039). A multiregression model predicted 0.49 of variance in pitch location consistency using kinematic inputs.

DISCUSSSION AND CONCLUSION

Pitchers who differ in pitch location consistency outcomes do not appear to demonstrate physiologically unsafe kinematics. High school pitchers who strive for improved pitch consistency can consider adjusting parameters of hip kinematics during early portions of the pitch.

The 50 most impactful articles on the medial ulnar collateral ligament: An altmetric analysis of online media

The purpose of this study was to use the Altmetric Attention Score to determine the 50 most impactful medial ulnar collateral ligament articles in online media and compare their characteristics to the most-cited medial ulnar collateral ligament articles in the scientific literature. The Altmetric database was queried to identify all published articles about the medial ulnar collateral ligament, and this list was stratified by the Altmetric Attention Score to identify the 50 highest scoring articles. Several data elements were extracted, including article topic, article type, journal name, and the number of online mentions on Facebook, Twitter, news, and other platforms. Each article's geographic origin was determined based on the institutional affiliation of the first author. Our index search yielded 1283 articles published between 1987 and 2020, from which the 50 articles with the highest Altmetric Attention Scores were included for analysis. Altmetric Attention Scores of the top 50 medial ulnar collateral ligament articles ranged from 20 to 482 (median: 32, interquartile range: 20-62). The most common article type was original research (72%), and the most common topic was epidemiology/risk factors (26%). A majority of studies were Level 3 (36%) or Level 4 evidence (36%). Of the top 50 medial ulnar collateral ligament articles, 94% originated from the United States. A few articles had a high Altmetric Attention Score, suggesting that medial ulnar collateral ligament research does not generate consistently high online attention. The lack of Level 1 studies suggests the need for high-level studies on the medial ulnar collateral ligament. Most studies originated in the United States and were published in the American Orthopaedic Society for Sports Medicine-affiliated journals. The medial ulnar collateral ligament articles included in this study differed substantially from a previous report of the most-cited medial ulnar collateral ligament articles in the literature, suggesting that alternative metrics add a unique dimension to understanding the overall impact of published research on the medial ulnar collateral ligament.

Retrospective Analysis of Ulnar Collateral Ligament Reconstructions in Major League Baseball Pitchers: A Comparison of the "Tall and Fall" Versus "Drop and Drive" Pitching Styles

Background

Previous pilot research has investigated differences in elbow valgus torque between the "tall and fall" (TF) and "drop and drive" (DD) pitching styles. Whether one of these pitching styles is associated with a greater rate of ulnar collateral ligament reconstruction (UCLR) is currently unknown.

Purpose

To determine the proportion of Major League Baseball (MLB) pitchers using the TF and DD pitching styles who underwent UCLR over a 10-year period.

Study Design

Cross-sectional study; Level of evidence, 3.

Methods

The demographic characteristics of pitchers who underwent UCLR between 2007 and 2017 were obtained via the open-source database MLB Player Analysis Tommy John Surgery List. Other information, such as previous UCLR and pitching videos and graphics, was obtained from other open-source databases. A comprehensive, 2-dimensional, kinesiology-based multicomponent definition of each pitching style was formulated and used to categorize the included pitchers into the TF and DD groups. Statistical comparisons and contrasts were made using chi-square and Pearson correlation tests.

Results

Included were 223 MLB pitchers (mean ± SD age, 27.5 ± 3.6 years; body mass index [BMI], 27.6 ± 2.2; throwing velocity, 92.9 ± 2.6 mph [149.5 ± 4.2 km/h]) who underwent UCLR between 2007 and 2017. Of these pitchers, 162 were categorized as TF pitchers (72.6%) and 61 as DD pitchers (27.4%). Pitching velocity for injured pitchers was significantly correlated to BMI (P < .001). We found no significant associations of pitching style with year of UCLR (P = .941), BMI (P = .549), age (P = .647), handedness (P = .501), or average pitch velocity (P = .921).

Conclusion

The study findings demonstrated that a higher proportion of UCL-injured MLB pitchers (72.6%) used the TF pitching style. Further research is needed to explore the potential association between pitching style and UCL injury.

Supervised machine learning and associated algorithms: applications in orthopedic surgery

Supervised learning is the most common form of machine learning utilized in medical research. It is used to predict outcomes of interest or classify positive and/or negative cases with a known ground truth. Supervised learning describes a spectrum of techniques, ranging from traditional regression modeling to more complex tree boosting, which are becoming increasingly prevalent as the focus on "big data" develops. While these tools are becoming increasingly popular and powerful, there is a paucity of literature available that describe the strengths and limitations of these different modeling techniques. Typically, there is no formal training for health care professionals in the use of machine learning models. As machine learning applications throughout medicine increase, it is important that physicians and other health care professionals better understand the processes underlying application of these techniques. The purpose of this study is to provide an overview of commonly used supervised learning techniques with recent case examples within the orthopedic literature. An additional goal is to address disparities in the understanding of these methods to improve communication within and between research teams.

Ulnar Collateral Ligament Tear in Elite Baseball Pitchers: Are High School Showcase Exposures Associated With Injury?

BACKGROUND

Ulnar collateral ligament reconstruction (UCLR) surgeries have increased significantly in amateur and professional baseball pitchers. Although showcase participation has been considered an injury risk factor, limited data are available to corroborate this association.

HYPOTHESIS

Elite pitchers achieving fastball velocities ≥90, ≥92, and ≥95 mph at younger ages would be more likely to undergo UCLR earlier in their careers compared with pitchers not achieving these velocity thresholds at younger ages. Elite pitchers participating in high showcase volumes would be more likely to undergo UCLR compared with elite pitchers participating in fewer showcases.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

Descriptive, showcase performance, and injury data from pitchers selected in the first 5 rounds of the Major League Baseball draft (2011-2020) were gathered from publicly available databases. Continuous and categorical variables for pitchers undergoing UCLR and those not undergoing UCLR were compared, and multivariable analysis was performed using logistic regression. We used standard deviations (SDs) of ±1 SD of mean age at first UCLR to define early-career versus late-career UCLR subgroups after normal distribution was confirmed (Shapiro-Wilk test; P = .183). The "early" UCLR group was defined as ≤-1 SD (19.09 years), whereas the "late" UCLR group was defined as ≥+1 SD (24.79 years). Trends in time were evaluated using linear regression.

RESULTS

Of the 845 pitchers selected, 659 pitchers (78.0%) had retrievable showcase performance data. Of the 845 pitchers, 229 (27.1%) underwent UCLR. Peak fastball velocity recorded at showcases was the strongest predictor of UCLR (adjusted odds ratio, 1.19; 95% CI, 1.02 to 1.39; P = .03). Peak fastball velocity in high school (HS) was significantly higher among pitchers who underwent UCLR compared with pitchers in the no-UCLR group (91.57 vs 90.71 mph, respectively; 95% CI, -1.43 to -0.29; P < .01). Age at which pitchers participated in their first HS showcase was significantly younger for the early versus the late UCLR group (15.53 vs 16.51 years, respectively; 95% CI, -1.53 to -0.41; P < .01). Elite pitchers with early UCLR participated in nearly twice as many showcases compared with the late UCLR group (5.38 vs 2.89, respectively; 95% CI, 0.43 to 4.54; P = .02). The mean number of HS showcases that elite pitchers attended more than doubled during the 2011-2020 study period (from 2.88 to 6.00 total showcases; P < .001). Mean age at which pitchers attended their first HS showcase steadily declined as well over the 10-year period (from 16.52 to 15.63 years; P < .001).

CONCLUSION

Peak fastball velocity was the strongest predictor of UCLR in elite pitchers before initiating professional careers. Elite amateur pitchers attended more showcases at younger ages in a decade-long trend. Overall, the variables included in this multivariable analysis were weak predictors, explaining only 3.8% of the variance in UCLR rates.

Variability in Pitch Count Limits and Rest Day Requirements by State: Implications of Season-Long Pitch Counts in High School Baseball Pitchers

BACKGROUND

It is unknown how different pitch count limits and rest day requirements affect cumulative pitch counts during a baseball season.

PURPOSE

To determine (1) the variability of pitch count rules in high school baseball and (2) the theoretical effect of different pitch count limits and rest day combinations on game, weekly, and seasonal pitch totals in high school baseball pitchers.

STUDY DESIGN

Cross-sectional study.

METHODS

Pitch count rules for the 2019-2020 academic year for 48 sanctioned states were recorded from each state's athletic association website. Maximum pitch count limits were recorded along with the number of pitches allowed before requiring 0 to 5 rest days before the next pitching outing. Rules were also analyzed for several distinctions, including the athlete's level of competition, age, and grade. To determine the effect of pitch count rules and rest days, a theoretical 3-month season was calculated in the following scenarios: (1) variable maximum pitch count limits with a universal 3-day rest requirement, (2) universal 110 pitch count limit with variable rest day requirements (3, 4, or 5 days), and (3) actual pitch count limits and required rest days for every state assuming pitchers throw as many pitches as allowed. Analysis of variance and Student t tests were used to compare between-group and intragroup seasonal pitch totals based on variations in required rest days.

RESULTS

The most common maximum pitch count limit for a varsity high school athlete was 110 pitches (range, 100-125 pitches) with 4 rest days (range, 0-5 days). We found that 23 states (48%) did not make distinctions for pitch count rules based on the athlete's level of competition, age, or grade. We noted a 25% increase in total seasonal pitch counts between the smallest and largest pitch count limit when assuming constant 3-day rest. We found a 53% difference in total seasonal pitch count when rest days varied between 3 and 5 days with a constant 110-pitch limit. Allowing 140 pitches in a 4-day span without a specific rest day requirement resulted in the highest seasonal pitch count (Nevada). There was a 49% difference in maximum seasonal pitch counts between the most and least restrictive states (P < .001). Submaximum pitch limits resulted in higher seasonal pitch counts than maximum pitch limits in 56% of states.

CONCLUSION

Pitch count rules vary widely by state. Required rest days influenced total seasonal pitch counts more than maximum or submaximum pitch count limits.

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Injuries limit the athletes' ability to participate fully in their training and competitive process. They are detrimental to performance, affecting the athletes psychologically while limiting physiological adaptations and long-term development. This study aims to present a framework for developing random forest classifier models, forecasting injuries in the upcoming 1 to 7 days, to assist the performance support staff in reducing injuries and maximizing performance within the Canadian National Female Short-Track Speed Skating Program. Forty different variables monitored daily over two seasons (2018-2019 and 2019-2020) were used to develop two sets of forecasting models. One includes only training load variables (TL), and a second (ALL) combines a wide array of monitored variables (neuromuscular function, heart rate variability, training load, psychological wellbeing, past injury type, and location). The sensitivity (ALL: 0.35 ± 0.19, TL: 0.23 ± 0.03), specificity (ALL: 0.81 ± 0.05, TL: 0.74 ± 0.03) and Matthews Correlation Coefficients (MCC) (ALL: 0.13 ± 0.05, TL: -0.02 ± 0.02) were computed. Paired T-test on the MCC revealed statistically significant (p < 0.01) and large positive effects (Cohen d > 1) for the ALL forecasting models' MCC over every forecasting window (1 to 7 days). These models were highly determined by the athletes' training completion, lower limb and trunk/lumbar injury history, as well as sFatigue, a training load marker. The TL forecasting models' MCC suggests they do not bring any added value to forecast injuries. Combining a wide array of monitored variables and quantifying the injury etiology conceptual components significantly improve the injury forecasting performance of random forest models. The ALL forecasting models' performances are promising, especially on one time windows of one or two days, with sensitivities and specificities being respectively above 0.5 and 0.7. They could add value to the decision-making process for the support staff in order to assist the Canadian National Female Team Short-Track Speed Skating program in reducing the number of incomplete training days, which could potentially increase performance. On longer forecasting time windows, ALL forecasting models' sensitivity and MCC decrease gradually. Further work is needed to determine if such models could be useful for forecasting injuries over three days or longer.

Using Advanced Data to Analyze the Impact of Injury on Performance of Major League Baseball Pitchers: A Narrative Review

Major league baseball (MLB) pitchers are at risk of numerous injuries during play, and there is an increasing focus on evaluating their performance in the context of injury. Historically, performance after return to play (RTP) from injury has focused on general descriptive statistics, such as innings or games played, or rate statistics with inherent variability (eg, earned run average, walks and hits per inning pitched, strikeouts per 9 innings, or walks per 9 innings). However, in recent years, MLB has incorporated advanced technology and tracking systems in every stadium, allowing for more in-depth analysis of pitcher-specific data that are captured with every pitch of every game. This technology allows for the ability to delve into the pitching performance on a basis that is more specific to each pitcher and allows for more in-depth analysis of different aspects of pitching performance. The purpose of this narrative review was to illustrate the current state of injury recording for professional baseball pitchers, highlight recent technological advances in MLB, and describe the advanced data available for analysis. We used advanced data in the literature to review the current state of performance analysis after RTP in MLB pitchers after injury. Finally, we strived to provide a framework for future studies to more meticulously assess RTP performance given the current available resources for analysis.

Just How Confident Can We Be in Predicting Sports Injuries? A Systematic Review of the Methodological Conduct and Performance of Existing Musculoskeletal Injury Prediction Models in Sport

BACKGROUND

An increasing number of musculoskeletal injury prediction models are being developed and implemented in sports medicine. Prediction model quality needs to be evaluated so clinicians can be informed of their potential usefulness.

OBJECTIVE

To evaluate the methodological conduct and completeness of reporting of musculoskeletal injury prediction models in sport.

METHODS

A systematic review was performed from inception to June 2021. Studies were included if they: (1) predicted sport injury; (2) used regression, machine learning, or deep learning models; (3) were written in English; (4) were peer reviewed.

RESULTS

Thirty studies (204 models) were included; 60% of studies utilized only regression methods, 13% only machine learning, and 27% both regression and machine learning approaches. All studies developed a prediction model and no studies externally validated a prediction model. Two percent of models (7% of studies) were low risk of bias and 98% of models (93% of studies) were high or unclear risk of bias. Three studies (10%) performed an a priori sample size calculation; 14 (47%) performed internal validation. Nineteen studies (63%) reported discrimination and two (7%) reported calibration. Four studies (13%) reported model equations for statistical predictions and no machine learning studies reported code or hyperparameters.

CONCLUSION

Existing sport musculoskeletal injury prediction models were poorly developed and have a high risk of bias. No models could be recommended for use in practice. The majority of models were developed with small sample sizes, had inadequate assessment of model performance, and were poorly reported. To create clinically useful sports musculoskeletal injury prediction models, considerable improvements in methodology and reporting are urgently required.

Decreased Trunk Rotation at Foot Contact in Professional Baseball Pitchers With Prior Conservatively Managed SLAP Tears: A Propensity Score-Matched Analysis

PURPOSE

To compare kinematic and kinetic parameters between a cohort of fully recovered professional pitchers with prior shoulder injury treated conservatively and a cohort with no prior shoulder injury.

METHODS

Twenty-six fully recovered professional baseball pitchers with a history of shoulder injury treated conservatively pitched 8 to 10 fastball pitches using 3-dimensional motion capture (480 Hz). All shoulder injuries occurred within a 1- to 4-year time span from biomechanical evaluation and were severe enough to prevent pitchers from playing for between 1 and 12 months. These pitchers were propensity score matched by age, height, weight, handedness, and ball velocity to pitchers with no prior injury history (control) at a ratio of 1:4. We compared 21 kinematic and 11 kinetic parameters between groups using appropriate parametric testing. Subanalysis comparisons of pitchers with prior SLAP injury as well as rotator cuff tendinitis were also performed.

RESULTS

SLAP tears (n = 11, 42.3%) were the most frequently reported injury, followed by rotator cuff tendinitis and/or shoulder impingement (n = 7, 26.9%). Compared with the control group, the 26 pitchers with prior injury showed no significant differences across the kinematic and kinetic factors. However, the SLAP tear subgroup did show significantly less trunk rotation at foot contact compared with controls (34.1° ± 4.9° vs 39.2° ± 10.2°, P = .0075).

CONCLUSIONS

Fully recovered professional baseball pitchers with shoulder injuries treated conservatively showed no significant differences in kinetics or kinematics compared with their propensity score-matched counterparts, suggesting that shoulder injury alone may not greatly alter pitching mechanics. However, whereas prior groups have shown a decrease in trunk rotation at foot contact after surgical repair for SLAP tears, our study suggests that this kinematic change may alternatively originate with the injury itself.

CLINICAL RELEVANCE

Understanding the cause of biomechanical adaptations by pitchers after injury can better aid clinicians and coaching staff in providing individualized and specific care to the throwing athlete.

Using Pitch-Tracking Data to Identify Risk Factors for Medial Ulnar Collateral Ligament Reconstruction in Major League Baseball Pitchers

Background:

Approximately 25% of Major League Baseball (MLB) pitchers undergo medial ulnar collateral ligament reconstruction (UCLR) during their careers.

Purpose:

To identify risk factors for UCLR that are specific to 2 subgroups of MLB pitchers: right (RHPs)- versus left-handed pitchers (LHPs) and starting (SPs) versus relief pitchers (RPs).

Study Design:

Case-control study; Level of evidence, 3.

Methods:

We included 109 MLB pitchers who had undergone UCLR between 2007 and 2019 and had sufficient preinjury data in the 3 years before surgery (T3, T2, T1). A 2:1 matched control cohort was selected for comparison. Pitch velocity, release location, and ball movement were compared between the UCLR and control cohorts in both subgroups in the years before surgery (RHPs vs LHPs and SPs vs RPs). Binary logistic regression was used to identify independent risk factors for UCLR.

Results:

The mean horizontal release location for the UCLR group was 5.8 cm more lateral than for the control group (P = .028). For all pitchers, every 2.5-cm lateral shift in release location in the years leading up to UCLR equated to a 3.7% increase in the odds of UCLR. For RPs, this risk was more substantial: a 5.8% increase in odds per 2.5 cm. SPs in the UCLR group demonstrated significantly different T1 horizontal release locations compared with SPs in the control group, though not to a statistically significant change over the 3 years before surgery. However, in the 3 years before surgery, the horizontal release location for RPs in the UCLR group moved 2.1 cm more lateral, as compared with 2.7 cm more medial for RPs in the control group (P = .007). For LHPs, a decrease in mean pitch velocity by 1 mph (1.6 km/h) in the years leading up to surgery increased the odds of UCLR by 45%.

Conclusion:

Increasing lateralization of release point in the years before surgery increased the risk of UCLR, specifically for relievers. Our findings add to the growing body of evidence that release location is an important variable in analyzing the risk of UCLR in MLB and that risk stratification may be dependent on pitcher characteristics such as position, handedness, and weight.

Pitching Mechanics and the Relationship to Accuracy in Professional Baseball Pitchers

BACKGROUND

Biomechanical predictors of pitching accuracy are underevaluated in baseball research. It is unclear how pitchers with higher accuracy differ in terms of kinematics and upper extremity kinetics.

PURPOSE

To differentiate high- and low-accuracy professional pitchers by full-body kinematic and upper extremity kinetic parameters.

STUDY DESIGN

Descriptive laboratory study.

METHODS

In total, 121 professional baseball pitchers threw 8 to 12 fastballs while assessed with motion-capture technology (480 Hz). Pitchers were divided into high-accuracy (n = 33), moderate-accuracy (n = 52), and low-accuracy (n = 36) groups based on the absolute center deviation of each pitcher's average pitch to the center of the pitching chart by greater or less than 0.5 SD from the mean, respectively. The 95% confidence ellipses with comparisons of major and minor radii and pitching probability density grids were constructed. Analysis of variance was used to compare kinematic and kinetic values between groups.

RESULTS

The absolute center deviation (14.5% ± 6.7% vs 33.5% ± 3.7% grid width; P < .001) was significantly lower in the high-accuracy compared with the low-accuracy group, with no significant difference in ball velocity (38.0 ± 1.7 vs 38.5 ± 2.0 m/s; P = .222). Lead knee flexion at ball release (30.6°± 17.8° vs 40.1°± 16.3°; P = .023) was significantly less for the high-accuracy pitchers. Peak normalized shoulder internal rotation torque (5.5% ± 1.0% vs 4.9% ± 0.7% body weight [BW] × body height [BH]; P = .008), normalized elbow varus torque (5.4% ± 1.0% vs 4.8% ± 0.7% BW × BH; P = .008), and normalized elbow medial force (42.9% ± 7.3% vs 38.6% ± 6.2% BW; P = .024) were significantly greater for the low-accuracy group compared with the high-accuracy group.

CONCLUSION

Professional pitchers with increased accuracy experienced decreased throwing arm kinetics. These pitchers had increased lead knee extension at later stages of the pitch, potentially providing more stable engagement with the ground and transference of kinetic energy to the upper extremities. Professional pitchers can consider increasing lead knee extension at the final stages of the pitch to improve the accuracy of their throws and mitigate elbow varus torque.

CLINICAL RELEVANCE

Increased elbow varus torque, shoulder internal rotation torque, and elbow medial force in less accurate pitchers may contribute to increased injury risk in this group.

Seasonal and monthly trends in elbow ulnar collateral ligament injuries and surgeries: a national epidemiological study

Background

Monthly incidence of elbow ulnar collateral ligament (UCL) injuries and surgeries is relatively unknown. Defining seasonal peaks of UCL injuries and surgeries may identify opportunities for injury-prevention strategies. The purpose of this study is to analyze seasonal and monthly variations in UCL injuries and surgeries across the United States with emphasis on the timing of baseball season.

Methods

The Truven Health MarketScan database (2013-2015) was queried for patients younger than 40 years with a diagnosis code of elbow UCL sprain and a procedural code for UCL repair or reconstruction. Differences in patient characteristics were evaluated using chi-square and Mann-Whitney U-tests. Negative binomial regression models were calculated for UCL injuries and surgeries to assess monthly trends.

Results

UCL injuries were sustained by 13,894 patients, with 1404 (10.1%) patients having undergone surgery. The median age at first diagnosis was 17 years, and the median age of patients requiring surgery decreased from 20 to 18 years from 2013 to 2015 (P = .75). Most UCL injuries (n = 3785) and surgeries (n = 438) occurred during the spring season (March 21-June 20), and spring injuries were most likely to result in surgical management (11.6%). During the baseball season (March to September), the number of UCL injuries peaked in April/May, then declined, except for a second peak in September/October (incidence rate ratio 0.97; confidence interval 0.95, 0.99; P = .01). The number of UCL surgeries steadily increased from March (n = 116) to June (n = 152), followed by a gradual decline (incidence rate ratio 1.00; confidence interval 0.96, 1.04; P = .99).

Conclusion

Athletes frequently experienced UCL injuries and surgeries in the early months (April-June) of the baseball season. More emphasis should be paid to rehabilitative strategies at the beginning of a baseball season to help mitigate injury risk.

Intra- versus inter-pitcher comparisons: Associations of ball velocity with throwing-arm kinetics in professional baseball pitchers

BACKGROUND

The association between ball velocity and elbow varus torque has shown differences when evaluated within a single pitcher and within a cohort. The impact of increasing ball velocity on additional throwing-arm kinetics, in particular shoulder distraction forces, with intra- vs. inter-pitcher evaluations has not been evaluated, even though these kinetic measures have been implicated in injury risk. The purpose of this study was to compare intra- vs. inter-pitcher relationships between ball velocity and all major kinetics at the shoulder and elbow in professional pitchers.

METHODS

A total of 323 professional baseball pitchers threw 8-12 fastball pitches while simultaneously being evaluated with 3-dimensional motion-capture technology (480 Hz). A linear regression analysis was performed to evaluate pitch velocity as a predictor of peak kinetic values at the shoulder and elbow among pitchers. A linear mixed model with random intercepts was then created to evaluate ball velocity as a predictor of peak kinetic values when comparing pitches within an individual pitcher.

RESULTS

91 pitchers were included in the analyses. Ball velocity among pitchers had weak correlations with shoulder distraction force (R² = 0.228, P < .001) and elbow distraction force (R² = 0.175, P < .001). Within an individual pitcher, strong correlations (R² > 0.85) were observed for (1) shoulder internal rotation torque (P < .001), (2) shoulder horizontal adduction torque (P = .006), (3) shoulder superior force (P < .001), (4) shoulder anterior force (P < .001), (5) elbow varus torque (P < .001), (6) elbow medial force (P < .001), (7) elbow anterior force (P < .001), (8) elbow flexion torque (P < .001), (9) shoulder distractive force (P < .001), and (10) elbow distractive force (P < .001).

CONCLUSION

Faster pitch velocity is a weak predictor of shoulder and elbow distraction forces experienced among professional pitchers. However, when controlling for an individual pitcher, peak kinetics at the shoulder and elbow can be strongly predicted by ball velocity. Therefore, the assumption that higher peak throwing-arm kinetic values are experienced by pitchers with faster ball velocity is likely an inappropriate assumption among pitchers but may be correct for each player who increases pitch velocity.

Effect of COVID-19 on Ulnar Collateral Ligament Reconstruction in Major League Baseball Pitchers

Background:

The coronavirus disease of 2019 (COVID-19) pandemic led to the suspension and shortening of the 2020 Major League Baseball (MLB) season from 162 to 60 regular season games. The effect of this disruption on injury rates, specifically injury to the ulnar collateral ligament (UCL), has not been quantified.

Purpose/Hypothesis:

The purpose of this study was to compare the rate of UCL reconstruction (UCLR), surgery timing, and pitching workload in MLB pitchers from before and after the COVID-19 pandemic lockdown. We hypothesized that UCLR rates relative to games played would be increased and pitching workload would be decreased in 2020 compared with previous seasons.

Study Design:

Cohort study; Level of evidence, 3.

Methods:

An extensive online search using publicly available data was conducted to identify all MLB pitchers who underwent UCLR between January 1, 2017, and December 31, 2020. Only pitchers who were competing at the MLB level when undergoing reconstruction were included. Player characteristics and surgery date, as well as career and season of surgery pitching workload, were collected for all included pitchers. All data were compared as a pooled sample (2017-2019 vs 2020).

Results:

A similar number of pitchers underwent UCLR during or after the 2020 regular season (n = 18) compared with the 2017-2019 seasons (n = 16, 20, and 16, respectively). However, after accounting for the decrease in games played during the 2020 regular season, an MLB pitcher was 2.9 times more likely to undergo surgery per game after the COVID-19 lockdown compared with the previous years (P < .001). MLB pitchers who underwent surgery in 2020 threw fewer preseason innings than did pitchers who underwent surgery between 2017 and 2019 (5.98 vs 9.39; P = .001).

Conclusion:

MLB pitchers were almost 3 times more likely to undergo UCLR per game after the COVID-19 lockdown. A decreased preseason pitching workload because of the COVID-19 lockdown may have had an effect on per game UCLR rates.

Kinematic and kinetic findings in high vs. low consistency professional baseball pitchers

While the performance metric ball velocity has often been associated with increased kinetics at the upper extremity and risk of injury in baseball pitchers, it is unclear if the performance metric pitch location consistency has any positive/negative associations with pitching kinetics. Professional pitchers subdivided into high(Hcon) and low(Lcon) consistency groups were instructed to throw 8-12 fastballs while assessed with motion-capture technology(480 Hz). To further assess pitching consistency, 95% confidence ellipses with comparisons of major and minor radii were conducted with an external comparison to a cohort of high school pitchers. Lastly, kinematic and kinetic values were compared between Hcon and Lcon professional pitchers. Professional baseball pitchers(n = 338) had consistency in pitch location comparable to high school pitchers(n = 59) (22.0 ± 6.7 vs. 23.2 ± 7.5% grid width respectively, p-value = 0.21). Hcon professional pitchers(n = 91) compared to Lcon pitchers(n = 98) had a smaller major radius(15.2 ± 3.0 vs. 26.3 ± 5.9 respectively, p-value<0.001) and a smaller minor radius(9.4 ± 1.9 vs. 16.1 ± 4.4 respectively, p-value<0.001) in the 95% confidence ellipses. Hcon pitchers compared to Lcon pitchers had increased arm slot(59.7 ± 13.5 vs. 54.7 ± 12.4° respectfully, p-value = 0.009), trunk tilt(-33.4 ± 9.1 vs. -37.2 ± 8.9° respectfully, p-value = 0.004), and trunk lateral flexion(-27.1 ± 9.3 vs. -31.8 ± 9.0° respectfully, p-value<0.001) at ball release. These pitchers also had lower shoulder(112.4 ± 15.9 vs. 118.3 ± 15.1% BW respectfully, p-value = 0.001) and elbow distraction forces(110.5 ± 17 vs. 117.0 ± 15.2% BW respectfully, p-value = 0.006) during arm deceleration. Professional pitchers who approach a sidearm style of pitching, typically involving less contralateral trunk tilt, may achieve higher consistency in their throws while also experiencing diminished peak distractive forces at the elbow and shoulder.

Epidemiology of Injuries in National Collegiate Athletic Association Men's Baseball: 2014-2015 Through 2018-2019

CONTEXT

The National Collegiate Athletic Association has supported men's baseball championships since 1947. Since its inception, the number of participating teams and athletes has considerably expanded.

BACKGROUND

Frequently conducting injury surveillance of collegiate baseball athletes is essential for identifying developing temporal patterns.

METHODS

Exposure and injury data collected in the National Collegiate Athletic Association Injury Surveillance Program during 2014-2015 through 2018-2019 were analyzed. Injury counts, rates, and proportions were used to describe injury characteristics; injury rate ratios were used to examine differential injury rates.

RESULTS

The overall injury rate was 3.16 per 1000 athlete-exposures. The preseason injury rate was significantly higher than the regular season injury rate. The most commonly injured body parts were shoulder (16.1%), arm or elbow (16%), and hand or wrist (13.9%). The most reported specific injury was hamstring tear (7.9%).

CONCLUSIONS

The findings of this study aligned with previous studies-most injuries were due to noncontact and overuse mechanisms, less than one-half of injuries were related to upper extremity body parts, and one-third of all injuries were reported among pitchers.

Players' perspectives on successfully returning to professional baseball after medial ulnar collateral ligament reconstruction

BACKGROUND

As the incidence of ulnar collateral ligament reconstruction (UCLR) surgery continues to rise, an improved understanding of baseball pitchers' perspectives on the postoperative recovery process and return to pitching is needed. The purpose of this study was to analyze pitchers' perspectives on recovery after UCLR.

METHODS

^dDuring the 2018 baseball season, an online questionnaire was distributed to the certified athletic trainers of all 30 Major League Baseball (MLB) organizations. These athletic trainers then administered the survey to all players within their organization including MLB and 6 levels of Minor League Baseball. MLB or Minor League Baseball pitchers who had previously undergone UCLR and participated in a rehabilitation program (or were currently participating in one at time of the survey) were included in the study.

RESULTS

There were 530 professional pitchers who met inclusion criteria. The majority (81%) of pitchers began rehabilitation within 2 weeks of surgery, with 51% beginning within 1 week. The majority of pitchers began a long-toss throwing program at 5 and 6 months after surgery (27% and 21%), with 52% making their first throw off a mound between 7 and 9 months. The number of pitchers who participated in a weighted ball throwing program decreased significantly after surgery (20%-11%, P < .001). After UCLR, 56% of pitchers reported no changes regarding pitching mechanics or types of pitches thrown, 42% reported changed mechanics, and only 3% either decreased or stopped throwing a certain pitch type. Overall, 54% believed that their current throwing velocity was faster than their velocity before ulnar collateral ligament injury. Twenty percent of pitchers reported experiencing a setback that resulted in temporary stoppage of their rehabilitation program, the most common reason being flexor tightness or tendonitis (53%). Seventy-six percent reported that they were not concerned about sustaining another elbow injury; however, significantly less (61%; P < .001) stated that they would have UCLR again if necessary.

CONCLUSIONS

Although UCLR is generally reported to have excellent clinical outcomes, 20% of pitchers experienced a significant setback during their rehabilitation and only 61% of pitchers, having gone through UCLR and the subsequent recovery, would be willing to undergo revision surgery and repeat the rehabilitation process if it were to become necessary. In addition, 42% of pitchers felt that they had to alter their throwing mechanics to return to pitching. Surgeons and athletic trainers should aim to understand the UCLR recovery process from the pitchers' perspective to better counsel future patients recovering from UCLR.

Machine learning methods in sport injury prediction and prevention: a systematic review

PURPOSE

Injuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention.

METHODS

A search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle-Ottawa Scale. Study quality was evaluated using the GRADE working group methodology.

RESULTS

Eleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%).

CONCLUSIONS

Current ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.

Efficacy of Arm Care Programs for Injury Prevention

PURPOSE OF REVIEW

Arm care programs for baseball players are an increasingly popular area of interest for players, parents, coaches, sports performance staff, and team physicians. Once a general afterthought, the design of arm care programs is now heavily scrutinized in order to maximize performance and help reduce injury risk. Given the recent spike in interest for arm care programs for baseball players of all ages, the purpose of this work is to review the relevant literature regarding the efficacy of arm care programs and to discuss the authors' preferred, evidence-based principles for arm care programs.

RECENT FINDINGS

Arm care programs appear to provide favorable results for performance, maintenance of strength and flexibility, and reduced injury risk. These programs should be tailored to the demands of the athlete, which can change based on the time of year and physical demands of the player's position. A good program will incorporate flexibility, strengthening, proprioception, and joint mobility for the entire kinetic chain. Appropriate warm-up and cool-down periods are also important. Arm care programs should start with basic movement patterns before progressing to more advanced, coordinated exercises. Arm care programs are an important piece of a holistic approach to caring for the throwing arm of baseball athletes. In general, they appear to be a safe and efficacious way to help prevent a portion of throwing arm injuries. Further research is needed to determine the optimal arm care program for each athlete.

Machine Learning Outperforms Regression Analysis to Predict Next-Season Major League Baseball Player Injuries: Epidemiology and Validation of 13,982 Player-Years From Performance and Injury Profile Trends, 2000-2017

Background:

Machine learning (ML) allows for the development of a predictive algorithm capable of imbibing historical data on a Major League Baseball (MLB) player to accurately project the player's future availability.

Purpose:

To determine the validity of an ML model in predicting the next-season injury risk and anatomic injury location for both position players and pitchers in the MLB.

Study Design:

Descriptive epidemiology study.

Methods:

Using 4 online baseball databases, we compiled MLB player data, including age, performance metrics, and injury history. A total of 84 ML algorithms were developed. The output of each algorithm reported whether the player would sustain an injury the following season as well as the injury’s anatomic site. The area under the receiver operating characteristic curve (AUC) primarily determined validation.

Results:

Player data were generated from 1931 position players and 1245 pitchers, with a mean follow-up of 4.40 years (13,982 player-years) between the years of 2000 and 2017. Injured players spent a total of 108,656 days on the disabled list, with a mean of 34.21 total days per player. The mean AUC for predicting next-season injuries was 0.76 among position players and 0.65 among pitchers using the top 3 ensemble classification. Back injuries had the highest AUC among both position players and pitchers, at 0.73. Advanced ML models outperformed logistic regression in 13 of 14 cases.

Conclusion:

Advanced ML models generally outperformed logistic regression and demonstrated fair capability in predicting publicly reportable next-season injuries, including the anatomic region for position players, although not for pitchers.

The Influence of Pitch Velocity on Medial Elbow Pain and Medial Epicondyle Abnormality Among Youth Baseball Players

BACKGROUND

Pitch velocity is associated with elbow injuries among skillful baseball players. However, the relationship between pitch velocity and throwing elbow injuries among youth players has not yet been clarified.

PURPOSE

To investigate the influence of pitch velocity on medial elbow pain and medial epicondyle abnormality among youth baseball players.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

The participants consisted of 256 elementary school players (mean age, 11 ± 1 years; range, 9-12 years). The medial aspect of the elbow was evaluated using ultrasound imaging. A questionnaire was used to investigate past or present pain in the elbow, background of the players (age, height, body mass index, and years of baseball experience), and playing environment (number of days of practice in a week, experience as a pitcher, and cryotherapy of the shoulder and elbow after practice). Positioning of the scapula, range of motion in shoulder internal/external rotations and hip internal rotation, angle of the straight-leg raise, and heel-to-buttock distance were measured. The pitch velocity was recorded using a pitch velocity radar gun. The relationship between these variables and the presence of medial epicondyle abnormality, as well as past or present elbow pain, were statistically analyzed.

RESULTS

A medial epicondyle abnormality was observed in 130 players (51%), elbow pain in the past in 65 players (25%), and elbow pain during the examination in 14 players (5%). Sixty-nine players (27%) experienced elbow pain either in the past or during examination. Abnormality of the medial epicondyle had a relationship with the pitch velocity (odds ratio [OR], 1.1 for increase of 1 km/h; 95% CI, 1.1-1.2; P < .0001) and the number of practice days in a week (OR, 1.8 for increase of the practice days; 95% CI, 1.4-2.5; P < .0001). Pitch velocity was also significantly related with past pain, present pain, and past and/or present pain of the elbow (OR [km/h], 1.1, 1.1, 1.1; 95% CI, 1.0-1.1, 1.0-1.2, 1.1-1.2; P < .0001, P = .002, P < .0001, respectively).

CONCLUSION

Pitch velocity was significantly associated with abnormality of the medial epicondyle and elbow pain. A 10-km/h increase in pitch velocity would increase the risk of medial epicondyle abnormality and medial elbow pain by 3 times.

Elbow Ulnar Collateral Ligament Injuries: Indications, Management, and Outcomes

Ulnar collateral ligament (UCL) injuries continue to be a major source of morbidity in baseball players. The throwing motion creates nearly supraphysiological levels of valgus stress on the medial elbow, placing these athletes at high risk of UCL injury. The incidence of injury continues to rise at an alarming rate, especially among adolescent baseball pitchers. Certain risk factors for UCL injury have been identified, including pitch velocity, fewer days between outings, and overall workload. Treatment of UCL injuries depends on the type of tear. Low- to medium-grade partial UCL tears (i.e., grade I or II tears) are usually amenable to a period of rest and a graduated throwing program. Recently, platelet-rich plasma has been described as another treatment modality to consider in a throwing athlete with a partial UCL tear, although robust clinical data are currently lacking. Most athletes can return to competitive throwing in 3 to 4 months after nonoperative management of a low-grade partial UCL tear. Indications for surgical management of a UCL injury are a complete (type III) tear or failure of extensive conservative management after a partial UCL tear. UCL reconstruction remains the gold standard for operative management of a complete UCL tear. Both the modified Jobe technique and the docking technique have shown excellent results with return-to-play rates between 80% and 90%. Recently, UCL repair with collagen-dipped suture tape augmentation has gained some popularity. However, long-term results are lacking, especially in elite athletes. Time to return to play after UCL reconstruction is variable. Most athletes return to full competition in 12 to 15 months, although professional pitchers often require 15 to 18 months to return to their previous level of competition. Revision rates remain low (1%-7%), yet the revision rate is expected to rise as the number of UCL reconstructions performed in the United States continues to increase.

What Can a Jump Tell Us About Elbow Injuries in Professional Baseball Pitchers?

BACKGROUND

The incidence rate of elbow injuries has been rising in recent years among professional baseball pitchers. Determining valid screening procedures that allow practitioners to identify pitchers at an increased risk of such injuries is therefore of critical importance.

PURPOSE

To validate the use of countermovement jump (CMJ) tests as a diagnostic tool for pitcher conditioning.

STUDY DESIGN

Case-control study; Level of evidence, 3.

METHODS

More than 500 pitchers at a single professional baseball organization performed preseason CMJ assessments on a force plate before the 2013 to 2018 seasons. Three measurements were extracted from ground-reaction force data during the test: eccentric rate of force development (ERFD), average vertical concentric force (AVCF), and concentric vertical impulse (CVI). Athletic trainers at the organization collected detailed information on elbow and shoulder injury rates as well as workload (pitch count) throughout the rest of the season. Poisson regression models were fit to investigate the dependency of injury rates on CMJ test performance.

RESULTS

ERFD, CVI, and AVCF were all significant predictors of elbow injury risk after accounting for pitcher age, weight, and workload. The analysis identified 3 specific indicators of heightened risk based on the results of a CMJ scan: low ERFD, a combination of low AVCF and high CVI, and a combination of high AVCF and low CVI. In contrast, shoulder injury risk was roughly independent of all 3 CMJ test measurements.

CONCLUSION

This study supports the hypothesis of the entire kinetic chain's involvement in pitching by establishing a link between CMJ test performance and elbow injury risk in professional baseball pitchers. CMJ assessment may be a powerful addition to injury risk alert and prevention protocols. Pitchers in high-risk groups can be prescribed specific exercise plans to improve movement imbalances.

Current Workload Recommendations in Baseball Pitchers: A Systematic Review

BACKGROUND

Several recommendations have been made regarding pitch counts and workload for baseball players of different levels, including Little League, high school, collegiate, and professional baseball. However, little consensus is found in the literature regarding the scientific basis for many of these recommendations.

PURPOSE

The primary purpose of this study was to summarize the evidence regarding immediate and long-term musculoskeletal responses to increasing pitching workload in baseball pitchers of all levels. A secondary purpose of this review was to evaluate the extent to which workload influences injury and/or performance in baseball pitchers.

STUDY DESIGN

Systematic review.

METHODS

We performed a systematic search in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for studies addressing physiologic and/or pathologic musculoskeletal changes in response to a quantifiable pitching workload. We included studies examining the effects of pitching workload on performance, injury rate, and musculoskeletal changes in Little League, high school, collegiate, and professional baseball players.

RESULTS

We identified 28 studies that met our inclusion and exclusion criteria: 16 studies regarding Little League and high school pitchers and 12 studies regarding collegiate and professional pitchers. The current evidence presented suggests that increased pitching workload may be associated with an increased risk of pain, injury, and arm fatigue in Little League and high school pitchers. However, little consensus was found in the literature regarding the association between pitching workload and physiologic or pathologic changes in collegiate and professional pitchers.

CONCLUSION

Evidence, although limited, suggests the use of pitch counts to decrease injury rates and pain in Little League and high school baseball pitchers. However, further research must be performed to determine the appropriate number of pitches (or throws) for players of different ages. This systematic review reported conflicting evidence regarding the use of pitch counts in college and professional baseball. Future high-quality research is required to determine the role, if any, of pitch counts for collegiate and professional pitchers.

Advanced Baseball Metrics Indicate Significant Decline in MLB Pitcher Value After Tommy John Surgery

There are conflicting reports regarding the efficacy of Major League Baseball (MLB) pitchers following medial ulnar collateral ligament reconstruction (UCLR). As advanced baseball metrics have revolutionized the way general managers define pitchers' value, the authors believe that these should be used to measure clinical outcomes after UCLR. All MLB pitchers who underwent UCLR from April 1, 1991, through July 1, 2016, were compiled (N=253). Pitcher demographics and statistics were collected for up to 3 full seasons preceding and following surgery. Data for pitching controls (all MLB [AMLB] pitchers) were also collected (N=14,756). Prior to surgery, pitchers with UCLR were significantly better than the AMLB pitchers in nearly all advanced value-based statistics: higher wins above replacement (WAR; 0.93 vs 0.78; 95% confidence interval [CI], 0.80-1.06), lower fielding independent pitching (FIP; 4.23 vs 4.51; 95% CI, 4.12-4.34), lower expected fielding independent pitching (xFIP; 4.17 vs 4.38; 95% CI, 4.06-4.28), higher win probability added (WPA; 0.21 vs 0.05; 95% CI, 0.1-0.32), and higher leverage index (pLI; 1.03 vs 0.96; 95% CI, 0.99-1.06). Pitchers who returned to play after UCLR demonstrated significantly lower value with worse WAR, FIP, WPA, and pLI (P<.05). Conversely, after excluding pitchers who failed to achieve a sustained return to play of greater than 1 year, there were no significant decreases in value after surgery. The authors conclude that, prior to injury, pitchers who have UCLR are more valuable than average MLB pitchers. However, UCLR pitchers perform worse when compared with their presurgical values. This may be affected by players not being able to continue their careers for more than 1 year. [Orthopedics. 2019; 42(6):349-354.].

Revision Ulnar Collateral Ligament Reconstruction in Professional Baseball: Current Trends, Surgical Techniques, and Outcomes

Background:

Ulnar collateral ligament (UCL) reconstruction of the elbow is commonly performed on professional baseball pitchers. Recent reports have suggested that revision rates are on the rise and may be higher than previously thought.

Purpose:

To provide a comprehensive report on current trends, surgical techniques, and outcomes of revision UCL reconstructions performed on professional baseball pitchers between 2010 and 2016.

Study Design:

Case series; Level of evidence, 4.

Methods:

The Major League Baseball Health and Injury Tracking System (HITS) was used to compile records of all revision UCL reconstructions performed on professional baseball pitchers between 2010 and 2016. Player data and outcomes were obtained from HITS, and surgical details were obtained from operative reports. Descriptive statistical analysis was performed on epidemiologic data. Outcomes (return to play [RTP] rates, RTP times, subsequent injuries, and subsequent surgeries) were compared across the most common surgical techniques (docking vs modified Jobe) and graft sources (palmaris longus autograft vs hamstring autograft).

Results:

A total of 69 professional baseball pitchers underwent revision UCL reconstruction from 2010 to 2016 at an average of 1424 days (47 months) after their primary surgery. A trend was seen toward increasing numbers of revision surgeries over time (R² = 0.441; P = .104). The most commonly used tunnel configuration was the modified Jobe technique (n = 41; 59.4%), and the most commonly used graft was hamstring autograft (n = 34; 49.3%). A majority (76.6%) of pitchers achieved RTP, and 55.3% were able to return to the same level of play. Mean time to RTP was 436 days (14.5 months) for players with a palmaris longus autograft versus 540 days (18 months) for those with a hamstring autograft (P = .108). Further, the mean time to RTP was 423 days (14 months) for the docking technique versus 519 days (17 months) for the modified Jobe technique (P = .296). Similar rates of subsequent injuries and surgeries were noted between the 2 revision techniques and 2 most commonly used graft constructs.

Conclusion:

Revision UCL reconstruction showed relatively high RTP rates (77%), but only 55% of players returned to their same level of play. Mean time to RTP was shorter than that found in other, smaller investigations. Although general trends were seen toward decreased time to RTP for the docking technique and palmaris longus autograft, these differences did not reach statistical significance.

Current Approaches to the Use of Artificial Intelligence for Injury Risk Assessment and Performance Prediction in Team Sports: a Systematic Review

Background

The application of artificial intelligence (AI) opens an interesting perspective for predicting injury risk and performance in team sports. A better understanding of the techniques of AI employed and of the sports that are using AI is clearly warranted. The purpose of this study is to identify which AI approaches have been applied to investigate sport performance and injury risk and to find out which AI techniques each sport has been using.

Methods

Systematic searches through the PubMed, Scopus, and Web of Science online databases were conducted for articles reporting AI techniques or methods applied to team sports athletes.

Results

Fifty-eight studies were included in the review with 11 AI techniques or methods being applied in 12 team sports. Pooled sample consisted of 6456 participants (97% male, 25 ± 8 years old; 3% female, 21 ± 10 years old) with 76% of them being professional athletes. The AI techniques or methods most frequently used were artificial neural networks, decision tree classifier, support vector machine, and Markov process with good performance metrics for all of them. Soccer, basketball, handball, and volleyball were the team sports with more applications of AI.

Conclusions

The results of this review suggest a prevalent application of AI methods in team sports based on the number of published studies. The current state of development in the area proposes a promising future with regard to AI use in team sports. Further evaluation research based on prospective methods is warranted to establish the predictive performance of specific AI techniques and methods.

Electronic supplementary material

The online version of this article (10.1186/s40798-019-0202-3) contains supplementary material, which is available to authorized users.

Influence of Pitching Release Location on Ulnar Collateral Ligament Reconstruction Risk Among Major League Baseball Pitchers

Background:

Medial ulnar collateral ligament (UCL) reconstruction is a common procedure performed among Major League Baseball (MLB) pitchers. The etiology of UCL injury is complex and is not entirely understood.

Hypothesis:

To better understand risk factors for requiring UCL reconstruction, we hypothesized that pitchers who eventually undergo the procedure will exhibit different throwing mechanics as measured by pitch-tracking data points, such as velocity and release location.

Study Design:

Case-control study; Level of evidence, 3.

Methods:

Pitch-tracking and demographic data were gathered for 140 MLB pitchers who had undergone UCL reconstruction between the 2010 and 2017 seasons. Pitch type, release location, and velocity were compared between the surgical cohort and a matched-control cohort.

Results:

When compared with controls, the mean pitch release location for pitchers who required UCL reconstruction was 12.2 cm more lateral in the year immediately preceding surgery (P = .001). Furthermore, within the surgical cohort, the horizontal release location was 3.4 cm more lateral immediately preceding surgery compared with 2 years earlier (P = .036). Binary logistic regression indicated an odds ratio of 0.51, suggesting a roughly 5% increased odds of UCL reconstruction for every 10 cm of increased lateral release location (P = .048). Both the surgical and the control cohorts threw similar rates of fastballs and had similar mean pitch velocity and fastball velocity. Control pitchers displayed a significant decrease over time in mean pitch velocity (P = .005) and mean fastball velocity, while pitchers in the UCL reconstruction cohort did not (P = .012).

Conclusion:

Pitch tracking indicates that the mean release point is more lateral in pitchers preceding UCL reconstruction as compared with controls, suggesting that a more lateral pitch release location is an independent risk factor for UCL injury and reconstruction.