Predicting ACL Reconstruction Failure with Machine Learning: Development of Machine Learning Prediction Models.

IF 2.4 3区 医学 Q2 ORTHOPEDICS
Orthopaedic Journal of Sports Medicine Pub Date : 2025-03-25 eCollection Date: 2025-03-01 DOI:10.1177/23259671251324519
Rafael Krasic Alaiti, Caio Sain Vallio, Andre Giardino Moreira da Silva, Riccardo Gomes Gobbi, José Ricardo Pécora, Camilo Partezani Helito
{"title":"Predicting ACL Reconstruction Failure with Machine Learning: Development of Machine Learning Prediction Models.","authors":"Rafael Krasic Alaiti, Caio Sain Vallio, Andre Giardino Moreira da Silva, Riccardo Gomes Gobbi, José Ricardo Pécora, Camilo Partezani Helito","doi":"10.1177/23259671251324519","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Anterior cruciate ligament reconstruction (ACLR) is the predominant and widely accepted treatment modality for ACL injury. However, recurrence of ACL rupture or failure of the reconstruction remains a significant challenge. Despite several studies in the literature that have developed prediction models to address this issue by identifying prognostic factors for treatment outcomes using classical statistical methods, the predictive efficacy of these models is frequently suboptimal.</p><p><strong>Purpose: </strong>To (1) evaluate the predictive performance of different machine learning algorithms for the occurrence of failure in ACLR and (2) identify the most relevant predictors associated with this outcome.</p><p><strong>Study design: </strong>Cohort study; Level of evidence, 3.</p><p><strong>Methods: </strong>A total of 680 patients who underwent ACLR between January 2012 and July 2021 were evaluated. The study outcome was ACLR failure-defined as a complete tear confirmed by magnetic resonance imaging, arthroscopy, or clinical ACL insufficiency-evaluated at a minimum 2-year follow-up. Routinely collected data were used to train 9 machine learning algorithms-including k-nearest neighbors classifier, decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier, eXtreme Gradient Boosting, CatBoost classifier, and logistic regression. A random sample of 70% of patients was used to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>The predictive performance of most models was good, with AUCs ranging from 0.71 to 0.85. The models with the best AUC metric were the CatBoost classifier (0.85 [95% CI, 0.81-0.89]) and the random forest classifier (0.84 [95% CI, 0.77-0.90). Knee hyperextension consistently emerged as the primary predictor for ACLR failure across all models subjected to our analysis.</p><p><strong>Conclusion: </strong>Machine learning algorithms demonstrated good performance in predicting ACLR failure. Moreover, knee hyperextension consistently emerged as the primary predictor for failure across all models subjected to our analysis.</p><p><strong>Clinical relevance: </strong>The findings of this study highlight the potential of machine learning as a valuable clinical tool for decision-making on surgical intervention. By offering nuanced insights, these algorithms may contribute to the evolving landscape of orthopaedic practice. Also, this study confirms knee hyperextension as an important risk factor for ACLR failure.</p>","PeriodicalId":19646,"journal":{"name":"Orthopaedic Journal of Sports Medicine","volume":"13 3","pages":"23259671251324519"},"PeriodicalIF":2.4000,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11938500/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Orthopaedic Journal of Sports Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/23259671251324519","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Anterior cruciate ligament reconstruction (ACLR) is the predominant and widely accepted treatment modality for ACL injury. However, recurrence of ACL rupture or failure of the reconstruction remains a significant challenge. Despite several studies in the literature that have developed prediction models to address this issue by identifying prognostic factors for treatment outcomes using classical statistical methods, the predictive efficacy of these models is frequently suboptimal.

Purpose: To (1) evaluate the predictive performance of different machine learning algorithms for the occurrence of failure in ACLR and (2) identify the most relevant predictors associated with this outcome.

Study design: Cohort study; Level of evidence, 3.

Methods: A total of 680 patients who underwent ACLR between January 2012 and July 2021 were evaluated. The study outcome was ACLR failure-defined as a complete tear confirmed by magnetic resonance imaging, arthroscopy, or clinical ACL insufficiency-evaluated at a minimum 2-year follow-up. Routinely collected data were used to train 9 machine learning algorithms-including k-nearest neighbors classifier, decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier, eXtreme Gradient Boosting, CatBoost classifier, and logistic regression. A random sample of 70% of patients was used to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC).

Results: The predictive performance of most models was good, with AUCs ranging from 0.71 to 0.85. The models with the best AUC metric were the CatBoost classifier (0.85 [95% CI, 0.81-0.89]) and the random forest classifier (0.84 [95% CI, 0.77-0.90). Knee hyperextension consistently emerged as the primary predictor for ACLR failure across all models subjected to our analysis.

Conclusion: Machine learning algorithms demonstrated good performance in predicting ACLR failure. Moreover, knee hyperextension consistently emerged as the primary predictor for failure across all models subjected to our analysis.

Clinical relevance: The findings of this study highlight the potential of machine learning as a valuable clinical tool for decision-making on surgical intervention. By offering nuanced insights, these algorithms may contribute to the evolving landscape of orthopaedic practice. Also, this study confirms knee hyperextension as an important risk factor for ACLR failure.

求助全文
约1分钟内获得全文 求助全文
来源期刊
Orthopaedic Journal of Sports Medicine
Orthopaedic Journal of Sports Medicine Medicine-Orthopedics and Sports Medicine
CiteScore
4.30
自引率
7.70%
发文量
876
审稿时长
12 weeks
期刊介绍: The Orthopaedic Journal of Sports Medicine (OJSM), developed by the American Orthopaedic Society for Sports Medicine (AOSSM), is a global, peer-reviewed, open access journal that combines the interests of researchers and clinical practitioners across orthopaedic sports medicine, arthroscopy, and knee arthroplasty. Topics include original research in the areas of: -Orthopaedic Sports Medicine, including surgical and nonsurgical treatment of orthopaedic sports injuries -Arthroscopic Surgery (Shoulder/Elbow/Wrist/Hip/Knee/Ankle/Foot) -Relevant translational research -Sports traumatology/epidemiology -Knee and shoulder arthroplasty The OJSM also publishes relevant systematic reviews and meta-analyses. This journal is a member of the Committee on Publication Ethics (COPE).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信