Reinholz, Anna K.

Background: In professional sports, injuries resulting in loss of playing time have serious implications for both the athlete and the organization. Efforts to quantify injury probability utilizing machine learning have been met with renewed interest, and the development of effective models has the potential to supplement the decision-making process of team physicians. Purpose/Hypothesis: The purpose of this study was to (1) characterize the epidemiology of time-loss lower extremity muscle strains (LEMSs) in the National Basketball Association (NBA) from 1999 to 2019 and (2) determine the validity of a machine-learning model in predicting injury risk. It was hypothesized that time-loss LEMSs would be infrequent in this cohort and that a machine-learning model would outperform conventional methods in the prediction of injury risk. Study Design: Case-control study; Level of evidence, 3. Methods: Performance data and rates of the 4 major muscle strain injury types (hamstring, quadriceps, calf, and groin) were compiled from the 1999 to 2019 NBA seasons. Injuries included all publicly reported injuries that resulted in lost playing time. Models to predict the occurrence of a LEMS were generated using random forest, extreme gradient boosting (XGBoost), neural network, support vector machines, elastic net penalized logistic regression, and generalized logistic regression. Performance was compared utilizing discrimination, calibration, decision curve analysis, and the Brier score. Results: A total of 736 LEMSs resulting in lost playing time occurred among 2103 athletes. Important variables for predicting LEMS included previous number of lower extremity injuries; age; recent history of injuries to the ankle, hamstring, or groin; and recent history of concussion as well as 3-point attempt rate and free throw attempt rate. The XGBoost machine achieved the best performance based on discrimination assessed via internal validation (area under the receiver operating characteristic curve, 0.840), calibration, and decision curve analysis. Conclusion: Machine learning algorithms such as XGBoost outperformed logistic regression in the prediction of a LEMS that will result in lost time. Several variables increased the risk of LEMS, including a history of various lower extremity injuries, recent concussion, and total number of previous injuries.

Purpose To 1) evaluate the clinical efficacy of arthroscopic posterior capsular release for improving range of motion (ROM) in cases of recalcitrant flexion contracture and 2) determine patient‐reported outcomes (PROs) postoperatively. Methods Retrospective chart review was performed to identify patients who underwent arthroscopic posterior capsular release due to persistent extension deficit of the knee despite comprehensive nonoperative physical therapy between 2008 and 2021. Knee ROM and PROs (International Knee Documentation Committee [IKDC], Tegner, and visual analog scale [VAS]) were collected at final follow‐up. Results Overall, 22 patients were included with a median age of 37 years (interquartile range [IQR]: 20.5‐44.3). Of these, 8 (36%) were male and 14 (64%) were female, and average follow‐up was 3.7 ± 3.3 years. The most common etiology was knee flexion contracture after anterior cruciate ligament (ACL) reconstruction (59%). All patients failed a minimum of 3 months of nonoperative management. Prior to operative intervention, 100% of patients received physical therapy, 64% received extension knee bracing or casting, and 36% received corticosteroid injection. Median preoperative extension was 15° (IQR: 10‐25) compared to 2° (IQR: 0‐5) postoperatively ( P < .001). At final follow‐up, median extension was 0° (IQR: 0‐3.5). Postoperative VAS pain scores at rest (2 vs 0; P = .001) and with use (5 vs 1.8; P = .017) improved at final contact, and most (94%) patients reported maintaining their extension ROM. Patients with ACL‐related extension deficit reported better IKDC (81 vs 51.3; P = .008), Tegner (5.8 vs 3.6; P = .007), and VAS pain scores (rest: 0.2 vs 1.8; P = .008; use: 1.3 vs 5; P = .004) compared to other etiologies. Conclusion Arthroscopic posterior capsular release for recalcitrant flexion contracture provides an effective means for reducing pain and restoring terminal extension. The improvement in extension postoperatively was maintained for most (94%) patients at final follow‐up with a 14% reoperation rate.

Purpose To characterize the shoulder injuries experienced by baseball batters and position players (nonpitchers); to quantify the outcomes of these injuries with respect to time out of play, recurrence, and surgery rates; and to identify any injury patterns that are associated with worse outcomes. Methods Between 2011 and 2017, all Major League Baseball (MLB) and Minor League Baseball (MiLB) players who sustained shoulder injuries were identified using the MLB Health and Injury Tracking System (HITS). Injuries were included if they were sustained during baseball activity, resulted in at least 1 day missed (DM), and occurred in position players (nonpitchers). Results Over the study period, a total of 3,414 shoulder injuries occurred in batters, resulting in a sum of 68,808 DM and a mean of 22 DM per injury. Most injuries were a result of acute trauma (n = 2125; 62.2%) with throwing as the predominant activity (n = 1292; 38%). Rotator cuff strain/tears was the most common diagnosis (n = 790; 23.1%), and SLAP tears had the highest season‐ending rate (35.3%) and need for surgery (45.1%). There was a lower frequency of surgery (6.2% vs 9.2%; P = .002) and reinjury (2.03% vs 3.62%; P = .007) in the throwing shoulder vs the nonthrowing shoulder. There was an increased frequency of surgery for the front versus the back batting shoulder (8.2% vs 6.2%; P = .031) with similar DM (20.7 vs 22.2; P = .333) and return to play rates (94.0% vs 92.2%; P = .135). Conclusions During the 7‐season study period, there were a total of 3,414 shoulder injuries that resulted in nearly 70,000 days of out of play in professional baseball position players/batters (nonpitchers). Although pitchers were intentionally excluded from the analysis, throwing was still the most common mechanism of injury, and rotator cuff injuries were the most common injury. Labral tears were the most likely injury to be season ending and require surgery. Clinical Relevance This study is meant to help determine characteristics of shoulder injuries that occur in non‐pitchers by focusing on professional baseball batters and position players. This information could be helpful to sports medicine practitioners and shoulder specialists to better prognosticate injury recovery.