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

Pitch-Tracking Metrics as a Predictor of Future Shoulder and Elbow Injuries in Major League Baseball Pitchers: A Machine-Learning and Game-Theory Based Analysis

Background

Understanding interactions between multiple risk factors for shoulder and elbow injuries in Major League Baseball (MLB) pitchers is important to identify potential avenues by which risk can be reduced while minimizing impact on player performance.

Purpose

To apply a novel game theory-based approach to develop a machine-learning model predictive of next-season shoulder and elbow injuries in MLB pitchers and use this model to understand interdependencies and interaction effects between the most important risk factors.

Study Design

Case-control study; Level of evidence, 3.

Methods

Pitcher demographics, workload measures, pitch-tracking metrics, and injury data between 2017 and 2022 were used to construct a database of MLB pitcher-years, where each item in the database corresponded to a pitcher's information and metrics for that year. An extreme gradient boosting machine-learning model was trained to predict next-season shoulder and elbow injuries utilizing Shapley additive explanation values to quantify feature importance as well as interdependencies and interaction effects between predictive variables.

Results

A total of 3808 pitcher-years were included in this analysis; 606 (15.9%) of these involved a shoulder or elbow injury resulting in placement on the MLB injured list. Of the >65 candidate features (including workload, demographic, and pitch-tracking metrics), the most important contributors to predicting shoulder/elbow injury were increased: pitch velocity (all pitch types), utilization of sliders (SLs), fastball (FB) spin rate, FB horizontal movement, and player age. The strongest game theory interaction effects were that higher FB velocity did not alter a younger pitcher's predicted risk of shoulder/elbow injury versus older pitchers, risk of shoulder/elbow injury increased with the number of high-velocity pitches thrown (regardless of pitch type and in an additive fashion), and FB velocity <95 mph (<152.9 kph) demonstrated strong negative interaction effects with higher SL percentage, suggesting that the overall predicted risk of injury for pitchers throwing a high number of SLs could be attenuated by lower FB velocity.

Conclusion

Pitch-tracking metrics were substantially more predictive of future injury than player demographics and workload metrics. There were many significant game theory interdependencies of injury risk. Notably, the increased risk of injury that was conferred by throwing with a high velocity was even further magnified if the pitchers were also older, threw a high percentage of SLs, and/or threw a greater number of pitches.

Workload Risk Factors for Pitching-Related Injuries in High School Baseball Pitchers

BACKGROUND

Pitch counts are only one measure of the true workload of baseball pitchers. Newer research indicates that workload measurement and prevention of injury must include additional factors. Thus, current monitoring systems gauging pitcher workload may be considered inadequate.

PURPOSE/HYPOTHESIS

The purpose of this study was to develop a novel method to determine workload in baseball pitchers and improve processes for prevention of throwing-related injuries. It was hypothesized that our pitching workload model would better predict throwing-related injuries occurring throughout the baseball season than a standard pitch count model.

STUDY DESIGN

Cohort study; Level of evidence, 2.

METHODS

This prospective observational study was conducted at an academic medical center and community baseball fields during the 2019 to 2023 seasons. Pitchers aged 13 to 18 years were monitored for pitching-related injuries and workload (which included pitching velocity; intensity, using preseason and in-season velocity as a marker of effort; and pitch counts).

RESULTS

A total of 71 pitchers had 313 recorded pitcher outings, 11 pitching-related injuries, and 24,228 pitches thrown. Gameday pitch counts for all pitchers ranged from 19 to 219 (mean, 77.5 ± 41.0). Velocity ranged from 46.8 to 85.7 mph (mean, 71.3 ± 5.8 mph). Intensity ranged from 0.7 to 1.3 (mean, 1.0 ± 0.08). The mean workload was 74.7 ± 40.1 for all pitchers. Risk factors significant for injury included throwing at a higher velocity in game (P = .001), increased intensity (eg, an increase in mean velocity thrown from preseason to in-season; P < .001), and being an older pitcher (P = .014). No differences were found for workload between injured and noninjured pitchers because the analysis was underpowered.

CONCLUSION

Our workload model indicated that throwing at a higher velocity, throwing at a higher intensity, and older age were risk factors for injury. Thus, this novel workload model should be considered as a means to identify pitchers who may be at greater risk for injury.

Arm Health in Elite Collegiate Summer League Baseball Players Assessed by the Kerlan-Jobe Orthopaedic Clinic Score

CONTEXT

Collegiate baseball players with professional aspirations often participate in summer leagues; foremost among them is the Cape Cod Baseball League (CCBL). Injuries acquired during the collegiate baseball season can be carried into the CCBL season and vice versa.

OBJECTIVE

To assess the history of throwing arm injury and current functionality in midseason CCBL players.

DESIGN

Cross-sectional study.

SETTING

Online questionnaire.

PATIENTS OR OTHER PARTICIPANTS

A total of 123 CCBL players participated. Qualifying athletes were ≥18 years old and were rostered CCBL players with remaining collegiate eligibility.

MAIN OUTCOME MEASURE(S)

After collecting background information, we used the Kerlan-Jobe Orthopaedic Clinic (KJOC) Shoulder and Elbow questionnaire to assess the history of throwing arm injury and current functionality. The maximum KJOC score is 100.0; higher scores correspond with greater functionality.

RESULTS

The mean KJOC score was 86.6 ± 14.5 (n = 92); 24.5% (23/94) of players reported a prior diagnosis of throwing arm injury other than a strain or sprain. A total of 49 (49/96, 51.0%) players had undergone rehabilitation for a throwing arm injury, and 7 (7/96, 7.3%) had experienced a medical procedure. Players with no previous treatment (n = 41, mean KJOC score = 88.9 ± 19.0) more frequently demonstrated KJOC scores of ≥90 than players with such treatment (n = 55, 80.9 ± 17.1; P < .001). The 18 players with time-loss arm injury in the last year had lower mean KJOC scores (71.3 ± 20.0) than players with no injury or time loss (90.3 ± 9.8; P < .001). Similarly, players who reported current arm trouble (n = 15) had lower KJOC scores (71.6 ± 17.5) than players with healthy arms (89.5 ± 11.9; P < .001).

CONCLUSIONS

The average KJOC score of the CCBL players was <90, with particularly low scores in athletes with prior arm injury and treatment.

Adaptive pathology: new insights into the physical examination and imaging of the thrower's shoulder and elbow

Throwing with high velocity requires extremes of glenohumeral external rotation of the abducted arm where particularly high forces in the shoulder and elbow are endured. Repeated throwing leads to dominant-arm bony remodeling of the humerus, glenoid, and elbow, and multiple soft tissue changes that would be considered abnormal. Many of these features are thought to be adaptive and protective. The purpose of this work is to (1) define the concept of adaptive pathology; (2) review the mechanics of the throwing motion; (3) review pertinent physical examination and imaging findings seen in asymptomatic throwers' shoulders and elbows and describe how these changes develop and may be adaptive-allowing the thrower to perform at high levels; and then (4) review the principles of surgical treatment in the throwing athletes, which should focus on reducing symptoms, but not necessarily restoring the thrower's anatomy to normal.