文献速递运动医学关节外科

利用机器学习基于880名女性精英运动员的大规模筛查测试组合数据预测前交叉韧带损伤

Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes.
PubMed 文献 · Am J Sports Med · 2022-08-19

该病例对照研究(证据等级3)纳入791名女性精英手球和足球运动员的三维运动分析及体能数据,使用四种常见分类器预测前交叉韧带损伤(n=60)。最佳分类器(线性支持向量机)的平均AUC-ROC为0.63,结果显著优于随机但AUC-ROC在不同重复和方法间波动于0.51-0.69。作者认为预测能力从临床评估角度看仍然较低,所纳入变量不能用于实践中的前交叉韧带预测。

要点

  • 最佳分类器线性支持向量机的平均AUC-ROC为0.63,显著优于随机但临床预测价值低。
  • AUC-ROC在不同重复和方法间波动于0.51-0.69,类别不平衡处理未改善结果。
  • 作者认为所纳入变量不能用于实践中的前交叉韧带预测。

核心结论

  • 作者的方法和数据显示出统计学显著的预测能力,表明该前瞻性数据集中存在可能有助于理解损伤因果关系的信息。
  • 然而从临床评估角度看预测能力仍然较低,提示所纳入变量不能用于实践中的前交叉韧带预测。

研究设计与样本

  • 病例对照研究,证据等级3。
  • 使用三维运动分析和体能数据,来自791名女性精英手球和足球运动员,预测前交叉韧带损伤(n=60)。
  • 使用四种常见分类器,以100次交叉验证运行的平均AUC-ROC作为性能指标,并用重复置换检验(配对Wilcoxon符号秩检验;P < .05)确认结果,同时评估最常见类别不平衡处理技术的影响。

主要发现

  • 最佳分类器(线性支持向量机)的平均AUC-ROC为0.63。
  • 无论使用哪种分类器,结果均显著优于随机,证实所用数据和方法的预测能力。
  • AUC-ROC值在不同重复和方法间波动较大(0.51-0.69)。
  • 类别不平衡处理未改善结果。

临床怎么用

  • 作者认为所纳入变量不能用于实践中的前交叉韧带预测。

局限性

  • 从临床评估角度看预测能力仍然较低。
  • AUC-ROC值在不同重复和方法间波动较大(0.51-0.69)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: 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.

来源:Am J Sports Med,查看原文。版权归原作者所有。

引用

  1. Jauhiainen S, Kauppi JP, Krosshaug T, et al. Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes. Am J Sports Med. 2022. PMID: 35984748. doi:10.1177/03635465221112095

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。