Machine Learning Outperforms Logistic Regression Analysis to Predict Next-Season NHL Player Injury: An Analysis of 2322 Players From 2007 to 2017.

Autor:	Luu BC; Department of Orthopedic Surgery, Baylor College of Medicine, Houston, Texas, USA., Wright AL; Department of Orthopedic Surgery, Baylor College of Medicine, Houston, Texas, USA., Haeberle HS; Machine Learning Orthopaedics Lab, Cleveland Clinic, Cleveland, Ohio, USA.; Hospital for Special Surgery, New York, New York, USA., Karnuta JM; Machine Learning Orthopaedics Lab, Cleveland Clinic, Cleveland, Ohio, USA., Schickendantz MS; Machine Learning Orthopaedics Lab, Cleveland Clinic, Cleveland, Ohio, USA., Makhni EC; Department of Orthopaedics, Henry Ford Health System, West Bloomfield, Michigan, USA., Nwachukwu BU; Hospital for Special Surgery, New York, New York, USA., Williams RJ 3rd; Hospital for Special Surgery, New York, New York, USA., Ramkumar PN; Machine Learning Orthopaedics Lab, Cleveland Clinic, Cleveland, Ohio, USA.
Jazyk:	angličtina
Zdroj:	Orthopaedic journal of sports medicine [Orthop J Sports Med] 2020 Sep 25; Vol. 8 (9), pp. 2325967120953404. Date of Electronic Publication: 2020 Sep 25 (Print Publication: 2020).
DOI:	10.1177/2325967120953404
Abstrakt:	Background: The opportunity to quantitatively predict next-season injury risk in the National Hockey League (NHL) has become a reality with the advent of advanced computational processors and machine learning (ML) architecture. Unlike static regression analyses that provide a momentary prediction, ML algorithms are dynamic in that they are readily capable of imbibing historical data to build a framework that improves with additive data. Purpose: To (1) characterize the epidemiology of publicly reported NHL injuries from 2007 to 2017, (2) determine the validity of a machine learning model in predicting next-season injury risk for both goalies and position players, and (3) compare the performance of modern ML algorithms versus logistic regression (LR) analyses. Study Design: Descriptive epidemiology study. Methods: Professional NHL player data were compiled for the years 2007 to 2017 from 2 publicly reported databases in the absence of an official NHL-approved database. Attributes acquired from each NHL player from each professional year included age, 85 performance metrics, and injury history. A total of 5 ML algorithms were created for both position player and goalie data: random forest, K Nearest Neighbors, Naïve Bayes, XGBoost, and Top 3 Ensemble. LR was also performed for both position player and goalie data. Area under the receiver operating characteristic curve (AUC) primarily determined validation. Results: Player data were generated from 2109 position players and 213 goalies. For models predicting next-season injury risk for position players, XGBoost performed the best with an AUC of 0.948, compared with an AUC of 0.937 for LR ( P < .0001). For models predicting next-season injury risk for goalies, XGBoost had the highest AUC with 0.956, compared with an AUC of 0.947 for LR ( P < .0001). Conclusion: Advanced ML models such as XGBoost outperformed LR and demonstrated good to excellent capability of predicting whether a publicly reportable injury is likely to occur the next season. Competing Interests: One or more of the authors has declared the following potential conflicts of interest or source of funding: Internal funding for this study was provided by the Cleveland Clinic. M.S.S. has received educational support, consulting fees, and speaking fees from Arthrex. E.C.M. has received educational support from Pinnacle (Arthrex), consulting fees from Smith & Nephew, hospitality payments from Smith & Nephew and Stryker, and publishing royalties from Springer. B.U.N. has received educational support from Smith & Nephew and hospitality payments from Wright Medical and Zimmer Biomet. R.J.W. has received consulting fees from Arthrex. AOSSM checks author disclosures against the Open Payments Database (OPD). AOSSM has not conducted an independent investigation on the OPD and disclaims any liability or responsibility relating thereto. (© The Author(s) 2020.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu