Return to Play Prediction Accuracy of the MLG-R Classification System for Hamstring Injuries in Football Players: A Machine Learning Approach.
Journal
Sports medicine (Auckland, N.Z.)
ISSN: 1179-2035
Titre abrégé: Sports Med
Pays: New Zealand
ID NLM: 8412297
Informations de publication
Date de publication:
09 2022
09 2022
Historique:
accepted:
15
03
2022
pubmed:
25
5
2022
medline:
23
8
2022
entrez:
24
5
2022
Statut:
ppublish
Résumé
Muscle injuries are one of the main daily problems in sports medicine, football in particular. However, we do not have a reliable means to predict the outcome, i.e. return to play from severe injury. The aim of the present study was to evaluate the capability of the MLG-R classification system to grade hamstring muscle injuries by severity, offer a prognosis for the return to play, and identify injuries with a higher risk of re-injury. Furthermore, we aimed to assess the consistency of our proposed system by investigating its intra-observer and inter-observer reliability. All male professional football players from FC Barcelona, senior A and B and the two U-19 teams, with injuries that occurred between February 2010 and February 2020 were reviewed. Only players with a clinical presentation of a hamstring muscle injury, with complete clinic information and magnetic resonance images, were included. Three different statistical and machine learning approaches (linear regression, random forest, and eXtreme Gradient Boosting) were used to assess the importance of each factor of the MLG-R classification system in determining the return to play, as well as to offer a prediction of the expected return to play. We used the Cohen's kappa and the intra-class correlation coefficient to assess the intra-observer and inter-observer reliability. Between 2010 and 2020, 76 hamstring injuries corresponding to 42 different players were identified, of which 50 (65.8%) were grade 3 The main determinant for a long return to play after a hamstring injury is the injury affecting the connective tissue structures of the hamstring. We developed a reliable hamstring muscle injury classification system based on magnetic resonance imaging that showed excellent results in terms of reliability, prognosis capability and objectivity. It is easy to use in clinical daily practice, and can be further adapted to future knowledge. The adoption of this system by the medical community would allow a uniform diagnosis leading to better injury management.
Sections du résumé
BACKGROUND AND OBJECTIVE
Muscle injuries are one of the main daily problems in sports medicine, football in particular. However, we do not have a reliable means to predict the outcome, i.e. return to play from severe injury. The aim of the present study was to evaluate the capability of the MLG-R classification system to grade hamstring muscle injuries by severity, offer a prognosis for the return to play, and identify injuries with a higher risk of re-injury. Furthermore, we aimed to assess the consistency of our proposed system by investigating its intra-observer and inter-observer reliability.
METHODS
All male professional football players from FC Barcelona, senior A and B and the two U-19 teams, with injuries that occurred between February 2010 and February 2020 were reviewed. Only players with a clinical presentation of a hamstring muscle injury, with complete clinic information and magnetic resonance images, were included. Three different statistical and machine learning approaches (linear regression, random forest, and eXtreme Gradient Boosting) were used to assess the importance of each factor of the MLG-R classification system in determining the return to play, as well as to offer a prediction of the expected return to play. We used the Cohen's kappa and the intra-class correlation coefficient to assess the intra-observer and inter-observer reliability.
RESULTS
Between 2010 and 2020, 76 hamstring injuries corresponding to 42 different players were identified, of which 50 (65.8%) were grade 3
CONCLUSIONS
The main determinant for a long return to play after a hamstring injury is the injury affecting the connective tissue structures of the hamstring. We developed a reliable hamstring muscle injury classification system based on magnetic resonance imaging that showed excellent results in terms of reliability, prognosis capability and objectivity. It is easy to use in clinical daily practice, and can be further adapted to future knowledge. The adoption of this system by the medical community would allow a uniform diagnosis leading to better injury management.
Identifiants
pubmed: 35610405
doi: 10.1007/s40279-022-01672-5
pii: 10.1007/s40279-022-01672-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2271-2282Informations de copyright
© 2022. The Author(s), under exclusive licence to Springer Nature Switzerland AG.
Références
Ekstrand J, Hägglund M, Waldén M. Epidemiology of muscle injuries in professional football (soccer). Am J Sports Med. 2011;39(6):1226–32.
pubmed: 21335353
doi: 10.1177/0363546510395879
Williams S, Trewartha G, Kemp S, Stokes K. A meta-analysis of injuries in senior men’s professional rugby union. Sports Med. 2013;43(10):1043–55.
pubmed: 23839770
doi: 10.1007/s40279-013-0078-1
Olson D, Sikka RS, Labounty A, Christensen T. Injuries in professional football: current concepts. Curr Sports Med Rep. 2013;12(6):38–90.
doi: 10.1249/JSR.0000000000000015
Feddermann-Demont N, Junge A, Edouard P, Branco P, Alonso J-M. Injuries in 13 international athletics championships between 2007–2012. Br J Sports Med. 2014;48(7):513–22.
pubmed: 24620039
doi: 10.1136/bjsports-2013-093087
Ekstrand J, Healy JC, Waldén M, Lee JC, English B, Hägglund M. Hamstring muscle injuries in professional football: the correlation of MRI findings with return to play. Br J Sports Med. 2012;46(2):112–7.
pubmed: 22144005
doi: 10.1136/bjsports-2011-090155
Orchard J, Best TM, Verrall GM. Return to play following muscle strains. Clin J Sport Med. 2005;15(6):436–41.
pubmed: 16278548
doi: 10.1097/01.jsm.0000188206.54984.65
Carling C, Le Gall F, Orhant E. A four-season prospective study of muscle strain reoccurrences in a professional football club. Res Sports Med. 2011;19(2):92–102.
pubmed: 21480056
doi: 10.1080/15438627.2011.556494
Koulouris G, Connell DA, Brukner P, Schneider-Kolsky M. Magnetic resonance imaging parameters for assessing risk of recurrent hamstring injuries in elite athletes. Am J Sports Med. 2007;35(9):1500–6.
pubmed: 17426283
doi: 10.1177/0363546507301258
Ekstrand J, Waldén M, Hägglund M. Hamstring injuries have increased by 4% annually in men’s professional football, since 2001: a 13-year longitudinal analysis of the UEFA Elite Club injury study. Br J Sports Med. 2016;50(12):731–7.
pubmed: 26746908
doi: 10.1136/bjsports-2015-095359
Delvaux F, Rochcongar P, Bruyère O, Bourlet G, Daniel C, Diverse P, et al. Return-to-play criteria after hamstring injury: actual medicine practice in professional soccer teams. J Sports Sci Med. 2014;13(3):721.
pubmed: 25177206
pmcid: 4126316
Barnes C, Archer D, Hogg B, Bush M, Bradley P. The evolution of physical and technical performance parameters in the English Premier League. Int J Sports Med. 2014;35(13):1095–100.
pubmed: 25009969
doi: 10.1055/s-0034-1375695
Valle X, L.Tol J, Hamilton B, Rodas G, Malliaras P, et al. Hamstring Muscle Injuries, a Rehabilitation Protocol Purpose. Asian J Sports Med. 2015;6(4):e25411
pubmed: 26715969
pmcid: 4691307
doi: 10.5812/asjsm.25411
Dellal A, Lago-Peñas C, Rey E, Chamari K, Orhant E. The effects of a congested fixture period on physical performance, technical activity and injury rate during matches in a professional soccer team. Br J Sports Med. 2015;49(6):390–4.
pubmed: 23422422
doi: 10.1136/bjsports-2012-091290
Vermeulen R, Almusa E, Buckens S, et al. Complete resolution of a hamstring intramuscular tendon injury on MRI is not necessary for a clinically successful return to play. Br J Sports Med. 2021;55:397–402.
doi: 10.1136/bjsports-2019-101808
Isern-Kebschull J, Mechó S, Pruna R, Kassarjian A, Valle X, Yanguas X, et al. Sports-related lower limb muscle injuries: pattern recognition approach and MRI review. Insights Imaging. 2020;11(1):108.
pubmed: 33026534
pmcid: 7539263
doi: 10.1186/s13244-020-00912-4
Valle X, Alentorn-Geli E, Tol JL, Hamilton B, Garrett WE, Pruna R, et al. Muscle injuries in sports: a new evidence-informed and expert consensus-based classification with clinical application. Sports Med. 2017;47(7):1241–53.
pubmed: 27878524
doi: 10.1007/s40279-016-0647-1
Hamilton B, Valle X, Rodas G, Til L, Grive RP, Rincon JAG, et al. Classification and grading of muscle injuries: a narrative review. Br J Sports Med. 2015;49(5):306.
pubmed: 25394420
doi: 10.1136/bjsports-2014-093551
Patel A, Chakraverty J, Pollock N, Chakraverty R, Suokas A, James S. British athletics muscle injury classification: a reliability study for a new grading system. Clin Radiol. 2015;70(12):1414–20.
pubmed: 26385202
doi: 10.1016/j.crad.2015.08.009
Wangensteen A, Tol JL, Roemer FW, Bahr R, Dijkstra HP, Crema MD, et al. Intra-and interrater reliability of three different MRI grading and classification systems after acute hamstring injuries. Eur J Radiol. 2017;89:182–90.
pubmed: 28267537
doi: 10.1016/j.ejrad.2017.02.010
Hamilton B, Alonso J-M, Best TM. Time for a paradigm shift in the classification of muscle injuries. J Sport Health Sci. 2017;6(3):255–61.
pubmed: 30356632
pmcid: 6189241
doi: 10.1016/j.jshs.2017.04.011
Valle X, Mechó S, Pruna R, Pedret C, Isern J, Monllau JC, et al. The MLG-R muscle injury classification for hamstrings: examples and guidelines for its use. Apunts Medicina de l" Esport (English Edition). FC Barcelona and Consell Catala de l'Esport. Madrid: Elsevier; 2018.
Gillies AR, Lieber RL. Structure and function of the skeletal muscle extracellular matrix. Muscle Nerve. 2011;44(3):318–31.
pubmed: 21949456
pmcid: 3177172
doi: 10.1002/mus.22094
Wilke J, Hespanhol L, Behrens M. Is it all about the fascia? A systematic review and meta-analysis of the prevalence of extramuscular connective tissue lesions in muscle strain injury. Orthop J Sports Med. 2019;7(12):2325967119888500.
pubmed: 31903399
pmcid: 6931154
doi: 10.1177/2325967119888500
McLoon LK, Vicente A, Fitzpatrick KR, Lindström M, Domellöf FP. Composition, architecture, and functional implications of the connective tissue network of the extraocular muscles. Invest Ophthalmol Vis Sci. 2018;59(1):322–9.
pubmed: 29346490
pmcid: 5773232
doi: 10.1167/iovs.17-23003
de Dios B-J, Garrigosa AL, Cuevas PD, Riaza LM, Terés XP, Alonso JM, et al. Translation into Spanish and proposal to modify the Orchard Sports Injury Classification System (OSICS) version 12. Apunts Sports Med. 2020;55(207):105–9.
doi: 10.1016/j.apunsm.2020.05.002
Pérez LT, Orchard J, Rae K. El sistema de clasificación y codificación OSICS-10 traducido del inglés. Apunts Medicina de l’Esport. 2008;43(159):109–12.
doi: 10.1016/S1886-6581(08)70092-6
Pruna R, Andersen TE, Clarsen B, McCall A, HUB BI. Muscle injury guide: prevention of and return to play from muscle injuries, 1st edn. 2019. FC Barcelona: Barça Innovation Hub
Moen M, Reurink G, Weir A, Tol J, Maas M, Goudswaard GJ. Predicting return to play after hamstring injuries. Br J Sports Med. 2014;48(18):1358–63.
pubmed: 25037199
doi: 10.1136/bjsports-2014-093860
Jacobsen P, Witvrouw E, Muxart P, Tol JL, Whiteley R. A combination of initial and follow-up physiotherapist examination predicts physician-determined time to return to play after hamstring injury, with no added value of MRI. Br J Sports Med. 2016;50(7):431–9.
pubmed: 26843538
doi: 10.1136/bjsports-2015-095073
Breiman L. Bagging predictors. Mach Learn. 1996;24(2):123–40.
Chen T, Guestrin C, editors. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 13–17 Aug 2016; San Francisco (CA).
Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inform Process Syst. 2017;30.
Apley DW, Zhu J. Visualizing the effects of predictor variables in black box supervised learning models. arXiv preprint. 2016:161208468.
R Core Team. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria; 2020. https://www.R-project.org/ .
Mueller-Wohlfahrt H-W, Haensel L, Mithoefer K, Ekstrand J, English B, McNally S, et al. Terminology and classification of muscle injuries in sport: the Munich consensus statement. Br J Sports Med. 2013;47(6):342–50.
pubmed: 23080315
doi: 10.1136/bjsports-2012-091448
Pollock N, Patel A, Chakraverty J, Suokas A, James SL, Chakraverty R. Time to return to full training is delayed and recurrence rate is higher in intratendinous (‘c’) acute hamstring injury in elite track and field athletes: clinical application of the British Athletics Muscle Injury Classification. Br J Sports Med. 2016;50(5):305–10.
pubmed: 26888072
doi: 10.1136/bjsports-2015-094657
Fournier-Farley C, Lamontagne M, Gendron P, Gagnon DH. Determinants of return to play after the nonoperative management of hamstring injuries in athletes: a systematic review. Am J Sports Med. 2016;44(8):2166–72.
pubmed: 26672025
doi: 10.1177/0363546515617472
Brukner P, Connell D. ‘Serious thigh muscle strains’: beware the intramuscular tendon which plays an important role in difficult hamstring and quadriceps muscle strains. Br J Sports Med. 2016;50(4):205–8.
pubmed: 26519522
doi: 10.1136/bjsports-2015-095136
Lempainen L, Kosola J, Pruna R, Puigdellivol J, Sarimo J, Niemi P, et al. Central tendon injuries of hamstring muscles: case series of operative treatment. Orthop J Sports Med. 2018;6(2):2325967118755992.
pubmed: 29479545
pmcid: 5818092
doi: 10.1177/2325967118755992
Garrett JRWE, Nikolaou PK, Ribbeck BM, Glisson RR, Seaber AV. The effect of muscle architecture on the biomechanical failure properties of skeletal muscle under passive extension. Am J Sports Med. 1988;16(1):7–12.
pubmed: 3344884
doi: 10.1177/036354658801600102
Nikolaou PK, Macdonald BL, Glisson RR, Seaber AV, Garrett JRWE. Biomechanical and histological evaluation of muscle after controlled strain injury. Am J Sports Med. 1987;15(1):9–14.
pubmed: 3812867
doi: 10.1177/036354658701500102
Valle X, Malliaropoulos N, Párraga Botero JD, Bikos G, Pruna R, Mónaco M, et al. Hamstring and other thigh injuries in children and young athletes. Scand J Med Sci Sports. 2018;28(12):2630–7.
pubmed: 30120838
doi: 10.1111/sms.13282
Schache AG, Koulouris G, Kofoed W, Morris HG, Pandy MG. Rupture of the conjoint tendon at the proximal musculotendinous junction of the biceps femoris long head: a case report. Knee Surg Sports Traumatol Arthrosc. 2008;16(8):797–802.
pubmed: 18360748
doi: 10.1007/s00167-008-0517-y
Hijikata T, Ishikawa H. Functional morphology of serially linked skeletal muscle fibers. Cells Tissues Organs. 1997;159(2–3):99–107.
doi: 10.1159/000147972
Roberts TJ, Eng CM, Sleboda DA, Holt NC, Brainerd EL, Stover KK, et al. The multi-scale, three-dimensional nature of skeletal muscle contraction. Physiology. 2019;34(6):402–8.
pubmed: 31577172
pmcid: 7002870
doi: 10.1152/physiol.00023.2019
Järvinen TA, Józsa L, Kannus P, Järvinen TL, Järvinen M. Organization and distribution of intramuscular connective tissue in normal and immobilized skeletal muscles. J Muscle Res Cell Motility. 2002;23(3):245–54.
doi: 10.1023/A:1020904518336
Gillies AR, Chapman MA, Bushong EA, Deerinck TJ, Ellisman MH, Lieber RL. High resolution three-dimensional reconstruction of fibrotic skeletal muscle extracellular matrix. J Physiol. 2017;595(4):1159–71.
pubmed: 27859324
doi: 10.1113/JP273376
Chan O, Del Buono A, Best TM, Maffulli N. Acute muscle strain injuries: a proposed new classification system. Knee Surg Sports Traumatol Arthrosc. 2012;20(11):2356–62.
pubmed: 22773066
doi: 10.1007/s00167-012-2118-z
Entwisle T, Ling Y, Splatt A, Brukner P, Connell D. Distal musculotendinous T junction injuries of the biceps femoris: an MRI case review. Orthop J Sports Med. 2017;5(7):2325967117714998.
pubmed: 28795071
pmcid: 5524253
doi: 10.1177/2325967117714998
Pasta G, Nanni G, Molini L, Bianchi S. Sonography of the quadriceps muscle: examination technique, normal anatomy, and traumatic lesions. J Ultrasound. 2010;13(2):76–84.
pubmed: 23396806
pmcid: 3553199
doi: 10.1016/j.jus.2010.07.004
Connell DA, Schneider-Kolsky ME, Hoving JL, Malara F, Buchbinder R, Koulouris G, et al. Longitudinal study comparing sonographic and MRI assessments of acute and healing hamstring injuries. Am J Roentgenol. 2004;183(4):975–84.
doi: 10.2214/ajr.183.4.1830975
Cross TM, Gibbs N, Houang MT, Cameron M. Acute quadriceps muscle strains: magnetic resonance imaging features and prognosis. Am J Sports Med. 2004;32(3):710–9.
pubmed: 15090389
doi: 10.1177/0363546503261734
Pomeranz SJ, Heidt R Jr. MR imaging in the prognostication of hamstring injury: work in progress. Radiology. 1993;189(3):897–900.
pubmed: 8234722
doi: 10.1148/radiology.189.3.8234722
Bianchi S, Martinoli C, Waser N, Bianchi-Zamorani M, Federici E, Fasel J. Central aponeurosis tears of the rectus femoris: sonographic findings. Skeletal Radiol. 2002;31(10):581–6.
pubmed: 12324827
doi: 10.1007/s00256-002-0559-z
Muscle SGot, Traumatology TSftSSoS, Balius R, Blasi M, Pedret C, Alomar X, et al. A histoarchitectural approach to skeletal muscle injury: searching for a common nomenclature. Orthop J Sports Med. 2020;8(3):2325967120909090.
Adstrum S, Nicholson H. A history of fascia. Clin Anat. 2019;32(7):862–70.
pubmed: 30873669
doi: 10.1002/ca.23371
Schleip R, Hedley G, Yucesoy CA. Fascial nomenclature: update on related consensus process. Clin Anat. 2019;32(7):929–33.
pubmed: 31183880
pmcid: 6852276
doi: 10.1002/ca.23423
Kjær M, Magnusson P, Krogsgaard M, Møller JB, Olesen J, Heinemeier K, et al. Extracellular matrix adaptation of tendon and skeletal muscle to exercise. J Anat. 2006;208(4):445–50.
pubmed: 16637870
pmcid: 2100210
doi: 10.1111/j.1469-7580.2006.00549.x