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

Abstract

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.

Sports Medicine and Artificial Intelligence: A Primer

“…3,34,35,37,38 Most recently, this group applied ML techniques to predict next-season injury risk for National Hockey League and Major League Baseball players. 15,20 For hockey players, Karnuta et al 15 compiled yearly injury data as well as player-specific metrics such as age, performance metrics, and injury history. Multiple ML algorithms were trained and compared in performance for predicting next-season injury.…”

Machine Learning for Predicting Lower Extremity Muscle Strain in National Basketball Association Athletes

“…Investigators have previously developed machine learning injury-prediction models for recreational athletes 17 as well as in professional sports, including the NFL, 42 National Hockey League, 26 and MLB. 18 These models utilized a range of inputs, from performance metrics to video recordings and motion kinematics. The present study evaluated a number of performance metrics as well as clinical injury history, which may present more actionable findings for the team physician.…”

Effect of Preoperative Imaging and Patient Factors on Clinically Meaningful Outcomes and Quality of Life After Osteochondral Allograft Transplantation: A Machine Learning Analysis of Cartilage Defects of the Knee

“…More than just an increasingly popular statistical analysis, ML has been demonstrated in the sports literature to outperform multivariate and regression-based analyses in terms of predicting player injury in Major League Baseball and the National Hockey League. 12,16 As such, ML modeling offers the intrinsic capability and competitive advantage of analyzing contributions of multiple variables simultaneously and learning the weighted value of complex relationships. In this case, ML was chosen as the ideal tool since the relationship between preoperative imaging, baseline PROMs, and patient demographics and meaningful postoperative outcomes after OCA of the knee has never been described.…”