Show simple item record

dc.contributor.authorOliver, Jon
dc.contributor.authorAyala, Francisco
dc.contributor.authorDe Ste Croix, Mark
dc.contributor.authorLloyd, Rhodri S.
dc.contributor.authorMyer, Greg
dc.contributor.authorRead, Paul
dc.date.accessioned2020-04-30T14:58:13Z
dc.date.available2020-04-30T14:58:13Z
dc.date.issued2020-05-18
dc.identifierhttps://repository.cardiffmet.ac.uk/bitstream/id/45459/JSAMS%20Manuscript%20R2.pdf
dc.identifier.citationOliver, J.L., Ayala, F., Croix, M.B.D.S., Lloyd, R.S., Myer, G.D. and Read, P.J. (2020) 'Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players', Journal of Science and Medicine in Sport. https://doi.org/10.1016/j.jsams.2020.04.021
dc.identifier.issn1440-2440
dc.identifier.urihttp://hdl.handle.net/10369/11019
dc.descriptionArticle published in Journal of Science and Medicine in Sport on 18 May 2020, available at: https://doi.org/10.1016/j.jsams.2020.04.021.en_US
dc.description.abstractObjectives: The purpose of this study was to examine whether the use of machine learning improved the ability of a neuromuscular screen to identify injury risk factors in elite male youth football players. Methods: 355 elite youth football players aged 10 to 18 years old completed a prospective pre-season neuromuscular screen that included anthropometric measures of size, as well as single leg countermovement jump (SLCMJ), single leg hop for distance (SLHD), 75% hop distance and stick (75%Hop), Y-balance anterior reach and tuck jump assessment. Injury incidence was monitored over one competitive season. Risk profiling was assessed using traditional regression analyses and compared to supervised machine learning algorithms constructed using decision trees. Results: Using continuous data, multivariate logistic analysis identified SLCMJ asymmetry as the sole significant predictor of injury (OR 0.94, 0.92-0.97, p<0.001), with a specificity of 97.7% and sensitivity of 15.2% giving an AUC of 0.661. The best performing decision tree model provided a specificity of 74.2% and sensitivity of 55.6% with an AUC of 0.663. All variables contributed to the final machine model, with asymmetry in the SLCMJ, 75%Hop and Y-balance, plus tuck jump knee valgus and anthropometrics being the most frequent contributors. Conclusions: Although both statistical methods reported similar accuracy, logistic regression provided very low sensitivity and only identified a single neuromuscular injury risk factor. The machine learning model provided much improved sensitivity to predict injury and identified interactions of asymmetry, knee valgus angle and body size as contributing factors to an injurious profile in youth football players.en_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofseriesJournal of Science and Medicine in Sport;
dc.titleUsing machine learning to improve our understanding of injury risk and prediction in elite male youth football playersen_US
dc.typeArticleen_US
dc.typeacceptedVersion
dcterms.dateAccepted2020-04-30
rioxxterms.funderCardiff Metropolitan Universityen_US
rioxxterms.identifier.projectCardiff Metropolian (Internal)en_US
rioxxterms.versionAMen_US
rioxxterms.versionofrecordhttps://doi.org/10.1016/j.jsams.2020.04.021
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en_US
rioxxterms.licenseref.startdate2020-04-30
rioxxterms.publicationdate2020-05-18
dc.date.refFCD2020-04-30
rioxxterms.freetoread.startdate2022-05-18
rioxxterms.funder.project37baf166-7129-4cd4-b6a1-507454d1372een_US


Files in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record