文献速递关节外科

基于投票机制的机器学习方法确定全膝关节置换与单髁膝关节置换候选患者

A Machine Learning Method to Determine Candidates for Total and Unicompartmental Knee Arthroplasty Based on a Voting Mechanism.
PubMed 文献 · J Arthroplasty · 2025-06-06

该研究从高手术量关节置换中心收集277例全膝关节置换(TKA)和293例单髁膝关节置换(UKA)的X线影像数据,以术中观察结果作为标签,构建基于投票机制的机器学习模型。该方法在五折交叉验证中达到94.2%的准确率和0.98%的受试者工作特征曲线下面积,性能优于现有模型。作者认为该方法仅需标准X线即可辅助TKA与UKA的手术决策,在自动化转诊和术前规划方面具有临床应用潜力。

要点

  • 基于投票机制的机器学习模型利用正位、侧位和髌骨轴位X线,以术中观察为标签区分TKA与UKA候选者。
  • 该方法在277例TKA和293例UKA数据集中达到94.2%的准确率和0.98%的受试者工作特征曲线下面积。
  • 投票机制整合三种X线视图的细节特征,提升了预测准确性和模型可解释性。

核心结论

  • 该研究提供了一种高准确率的方法,用于KOA患者TKA与UKA的手术决策,仅需标准X线,在自动化转诊和术前规划方面具有临床应用潜力。

研究设计与样本

  • 从高手术量关节置换中心收集正位、侧位和髌骨轴位X线影像数据,数据集包括277例TKA和293例UKA,每例通过术中观察标注TKA或UKA是否为合适选择。
  • 采用五折交叉验证进行训练和验证,先分别在单视图图像上独立训练三个基础模型,再通过投票机制聚合模型输出。
  • 使用准确率和受试者工作特征曲线下面积等指标评估所提方法的性能。

主要发现

  • 所提方法达到94.2%的准确率和0.98%的受试者工作特征曲线下面积,表现优于现有模型。
  • 投票机制使基础模型能够有效利用三种X线视图的细节特征,从而提升预测准确性和模型可解释性。

临床怎么用

  • 作者认为该方法仅需标准X线即可用于KOA患者TKA与UKA的手术决策,在自动化转诊和术前规划方面具有临床应用潜力。

局限性

  • 原文未报告局限性。

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: Knee osteoarthritis (KOA) is a prevalent condition. Accurate selection between total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA) is crucial for optimal treatment in patients who have end-stage KOA, particularly for improving clinical outcomes and reducing health care costs. This study proposes a machine learning model based on a voting mechanism to enhance the accuracy of surgical decision-making for KOA patients. METHODS: Radiographic data were collected from a high-volume joint arthroplasty practice, focusing on anterior-posterior, lateral, and skyline X-ray views. The dataset included 277 TKA and 293 UKA cases, each labeled through intraoperative observations (indicating whether TKA or UKA was the appropriate choice). A five-fold cross-validation approach was used for training and validation. In the proposed method, three base models were first trained independently on single-view images, and a voting mechanism was implemented to aggregate model outputs. The performance of the proposed method was evaluated by using metrics such as accuracy and the area under the receiver operating characteristic curve. RESULTS: The proposed method achieved an accuracy of 94.2% and an area under the receiver operating characteristic curve of 0.98%, demonstrating superior performance compared to existing models. The voting mechanism enabled base models to effectively utilize the detailed features from all three X-ray views, leading to enhanced predictive accuracy and model interpretability. CONCLUSIONS: This study provides a high-accuracy method for surgical decision-making between TKA and UKA for KOA patients, requiring only standard X-rays and offering potential for clinical application in automated referrals and preoperative planning.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Zhang N, Li Z, Zhang L, et al. A Machine Learning Method to Determine Candidates for Total and Unicompartmental Knee Arthroplasty Based on a Voting Mechanism. J Arthroplasty. 2025. PMID: 40482935. doi:10.1016/j.arth.2025.06.005

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。