Tian Cong, Chen Haifeng, Shao Wenhui, Zhang Ruikun, Yao Xinmiao, Shu Jianlong
The Third School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou, 310053, Zhejiang, China.
Department of Chinese Internal Medicine, Funan Hospital of Chinese Medicine, Fuyang, 236300, Anhui, China.
Eur J Med Res. 2025 Apr 22;30(1):317. doi: 10.1186/s40001-025-02545-z.
The application of machine learning (ML) in predicting the requirement for total knee arthroplasty (TKA) at knee osteoarthritis (KOA) patients has been acknowledged. Nonetheless, the variables employed in the development of ML models are diverse and these different approaches yield inconsistent predictive performance of models. Therefore, we conducted this systematic review and meta-analysis to explore the feasibility of ML in identifying candidates for TKA.
This study was conducted based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. This study was registered on the international prospective register of systematic reviews registration database website, PROSPERO, with a unique ID: CRD 42023443948. The study subjects were patients diagnosed with KOA. Relevant studies were searched through PubMed, Web of Science, Cochrane, and Embase until September 15, 2024. The c-index was used as the outcome measure. The risk of bias in the primary study was assessed by Prediction model Risk of Bias Assessment Tool (PROBAST). Random or fixed effects were used for the meta-analysis.
A total of 13 articles were included in this study, but only 11 articles with 25 models were eligible for the meta-analysis. ML models in the included studies were classified based on the source of variables, including clinical features, radiomics, and the combination of clinical features and radiomics. In the training set, the c-index was 0.713 (0.628 - 0.799) for clinical features, 0.841 (0.777 - 0.904) for radiomics, and 0.844 (0.815 - 0.873) for the combination of clinical features and radiomics. In the validation set, the c-index for ML models based on clinical features, radiomics, and the combination of clinical features and radiomics was 0.656 (0.526 - 0.786), 0.861 (0.806 - 0.916), and 0.831 (0.799 - 0.863), respectively.
The results of this meta-analysis highlighted that the ML model is feasible in identifying candidates for TKA. X-ray-based ML models exhibit the best predictive performance among the models. However, there is currently a lack of high-level research available for clinical application. Furthermore, the accuracy of ML models in identifying candidates for TKA is significantly limited by the quality of modeling parameters and database architecture. Therefore, constructing a more targeted and professional database is imperative to promote the development and clinical application of ML models.
机器学习（ML）在预测膝关节骨关节炎（KOA）患者全膝关节置换术（TKA）需求方面的应用已得到认可。尽管如此，用于开发ML模型的变量多种多样，这些不同方法产生的模型预测性能不一致。因此，我们进行了这项系统评价和荟萃分析，以探讨ML在识别TKA候选者方面的可行性。
本研究基于系统评价和荟萃分析的首选报告项目（PRISMA）指南进行。本研究已在国际前瞻性系统评价注册数据库网站PROSPERO上注册，唯一标识符：CRD 42023443948。研究对象为诊断为KOA的患者。通过PubMed、科学网、Cochrane和Embase检索相关研究，检索截止至2024年9月15日。使用c指数作为结局指标。采用预测模型偏倚风险评估工具（PROBAST）评估原始研究中的偏倚风险。荟萃分析采用随机或固定效应模型。
本研究共纳入13篇文章，但只有11篇文章中的25个模型符合荟萃分析的纳入标准。纳入研究中的ML模型根据变量来源进行分类，包括临床特征、放射组学以及临床特征与放射组学的组合。在训练集中，基于临床特征的ML模型的c指数为0.713（0.628 - 0.799），基于放射组学的为0.841（0.777 - 0.904），基于临床特征与放射组学组合的为0.844（0.815 - 0.873）。在验证集中，基于临床特征、放射组学以及临床特征与放射组学组合的ML模型的c指数分别为0.656（0.526 - 0.786）、0.861（0.806 - 0.916）和0.831（0.799 - 0.863）。
本荟萃分析结果表明，ML模型在识别TKA候选者方面是可行的。基于X线的ML模型在各模型中表现出最佳的预测性能。然而，目前缺乏可用于临床应用的高水平研究。此外，ML模型在识别TKA候选者方面的准确性受到建模参数质量和数据库架构的显著限制。因此，构建更具针对性和专业性的数据库对于促进ML模型的发展和临床应用至关重要。
