Show simple item record

dc.contributor.authorJauhiainen, Susanne
dc.contributor.authorKauppi, Jukka-Pekka
dc.contributor.authorKrosshaug, Tron
dc.contributor.authorBahr, Roald
dc.contributor.authorBartsch, Julia
dc.contributor.authorÄyrämö, Sami
dc.date.accessioned2022-08-24T12:00:37Z
dc.date.available2022-08-24T12:00:37Z
dc.date.issued2022
dc.identifier.citationJauhiainen, S., Kauppi, J.-P., Krosshaug, T., Bahr, R., Bartsch, J., & Äyrämö, S. (2022). Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes. <i>American Journal of Sports Medicine</i>, <i>50</i>(11), 2917-2924. <a href="https://doi.org/10.1177/03635465221112095" target="_blank">https://doi.org/10.1177/03635465221112095</a>
dc.identifier.otherCONVID_151758896
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/82784
dc.description.abstractBackground: Injury risk prediction is an emerging field in which more research is needed to recognize the best practices for accurate injury risk assessment. Important issues related to predictive machine learning need to be considered, for example, to avoid overinterpreting the observed prediction performance. Purpose: To carefully investigate the predictive potential of multiple predictive machine learning methods on a large set of risk factor data for anterior cruciate ligament (ACL) injury; the proposed approach takes into account the effect of chance and random variations in prediction performance. Study Design: Case-control study; Level of evidence, 3. Methods: The authors used 3-dimensional motion analysis and physical data collected from 791 female elite handball and soccer players. Four common classifiers were used to predict ACL injuries (n = 60). Area under the receiver operating characteristic curve (AUC-ROC) averaged across 100 cross-validation runs (mean AUC-ROC) was used as a performance metric. Results were confirmed with repeated permutation tests (paired Wilcoxon signed-rank-test; P \ .05). Additionally, the effect of the most common class imbalance handling techniques was evaluated. Results: For the best classifier (linear support vector machine), the mean AUC-ROC was 0.63. Regardless of the classifier, the results were significantly better than chance, confirming the predictive ability of the data and methods used. AUC-ROC values varied substantially across repetitions and methods (0.51-0.69). Class imbalance handling did not improve the results. Conclusion: The authors’ approach and data showed statistically significant predictive ability, indicating that there exists information in this prospective data set that may be valuable for understanding injury causation. However, the predictive ability remained low from the perspective of clinical assessment, suggesting that included variables cannot be used for ACL prediction in practice.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherSAGE Publications
dc.relation.ispartofseriesAmerican Journal of Sports Medicine
dc.rightsCC BY 4.0
dc.subject.otherpredictive methods
dc.subject.othermachine learning
dc.subject.otherprediction significance
dc.subject.othercross-validation
dc.subject.othermotion analysis
dc.subject.otherACL injury
dc.subject.otherteam sports
dc.titlePredicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202208244317
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineHuman and Machine based Intelligence in Learningfi
dc.contributor.oppiaineComputing, Information Technology and Mathematicsfi
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiaineHuman and Machine based Intelligence in Learningen
dc.contributor.oppiaineComputing, Information Technology and Mathematicsen
dc.contributor.oppiaineComputational Scienceen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.format.pagerange2917-2924
dc.relation.issn0363-5465
dc.relation.numberinseries11
dc.relation.volume50
dc.type.versionpublishedVersion
dc.rights.copyright© 2022 the Authors
dc.rights.accesslevelopenAccessfi
dc.subject.ysoennustettavuus
dc.subject.ysojoukkueurheilu
dc.subject.ysosuorituskyky
dc.subject.ysokoneoppiminen
dc.subject.ysourheiluvammat
dc.subject.ysourheilu
dc.subject.ysoloukkaantuminen (fyysinen)
dc.subject.ysoliikeanalyysi
dc.subject.ysourheilijat
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p9701
jyx.subject.urihttp://www.yso.fi/onto/yso/p2478
jyx.subject.urihttp://www.yso.fi/onto/yso/p14041
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
jyx.subject.urihttp://www.yso.fi/onto/yso/p12766
jyx.subject.urihttp://www.yso.fi/onto/yso/p965
jyx.subject.urihttp://www.yso.fi/onto/yso/p336
jyx.subject.urihttp://www.yso.fi/onto/yso/p24952
jyx.subject.urihttp://www.yso.fi/onto/yso/p3315
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.1177/03635465221112095
jyx.fundinginformationS.J. was funded by the Jenny and Antti Wihuri Foundation (grant 00190110) and by the Emil Aaltonen Foundation (personal travel grant). The Oslo Sports Trauma Research Center has been established at the Norwegian School of Sport Sciences through generous grants from the Royal Norwegian Ministry of Culture, the South-Eastern Norway Regional Health Authority, the International Olympic Committee, the Norwegian Olympic Committee & Confederation of Sport, and Norsk Tipping AS. 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.
dc.type.okmA1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

CC BY 4.0
Except where otherwise noted, this item's license is described as CC BY 4.0