手部影像学中的算法方法用于风湿性肌肉骨骼疾病:一项系统文献综述
本系统文献综述遵循PRISMA指南并在PROSPERO注册,检索PubMed、EMBASE和Scopus(2024年10月执行),纳入32项关于机器学习在手部影像中应用于骨关节炎、类风湿关节炎和银屑病关节炎的研究。类风湿关节炎研究最多(88%),卷积神经网络最常用(50%),标准X线为主要影像模态(59%);仅15%研究进行外部验证,6%数据集公开,28%研究使用可解释性工具。结论认为机器学习有潜力改善诊断与疾病管理,但需增加外部验证、扩大疾病覆盖和改进数据共享。
要点
- 类风湿关节炎占纳入研究的88%,骨关节炎22%,银屑病关节炎9%。
- 卷积神经网络使用率50%,标准X线占59%,MRI占16%。
- 仅15%研究进行外部验证,6%数据集公开,28%使用可解释性工具。
核心结论
- 机器学习在手部影像中对风湿性肌肉骨骼疾病的诊断和疾病管理具有显著潜力,但外部验证不足、疾病覆盖需扩大至骨关节炎和银屑病关节炎、数据共享实践有待改进以提升可重复性和临床采用。
研究设计与样本
- 系统文献综述,遵循PRISMA指南并在PROSPERO注册,检索PubMed、EMBASE和Scopus,检索于2024年10月执行,手动检索并结合基于人工智能的文献综述工具BiBot。
- 从最初识别的400项研究中纳入32项符合标准的研究,聚焦机器学习在骨关节炎、类风湿关节炎和银屑病关节炎中的应用。
主要发现
- 类风湿关节炎是研究最多的疾病(88%),其次为骨关节炎(22%)和银屑病关节炎(9%)。
- 卷积神经网络是最常用的算法(50%),标准X线是主要影像模态(59%),其次为MRI(16%)。
- 仅15%的研究进行了外部验证,仅6%的数据集公开可用,28%的研究采用可解释性工具以增强临床相关性。
局限性
- 外部验证仅在15%的研究中开展。
- 仅6%的数据集公开可用。
- 疾病覆盖需扩大至骨关节炎和银屑病关节炎。
- 需改进数据共享实践以提升可重复性和临床采用。
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
OBJECTIVE: This systematic literature review provides a comprehensive overview of the use of machine learning (ML) in hand imaging of rheumatic musculoskeletal diseases (RMDs). The review evaluates ML algorithms, imaging modalities, patient populations, validation methods, and areas for improvement. METHODS: The review was conducted following PRISMA guidelines and registered with PROSPERO. Articles were retrieved from PubMed, EMBASE, and Scopus using relevant MeSH terms and keywords. The search, executed in October 2024, was conducted manually and with BiBot, an AI-based tool for literature reviews. Studies focusing on ML applications in osteoarthritis (OA), rheumatoid arthritis (RA), and psoriatic arthritis (PsA) were included. RESULTS: From 400 initially identified studies, 32 met the inclusion criteria. RA was the most studied disease (88 %), followed by OA (22 %) and PsA (9 %). Convolutional neural networks (CNNs) were the most frequently used algorithms (50 %). Standard radiographs (59 %) were the predominant imaging modality, followed by MRI (16 %). Despite recommendations for ML studies, external validation was conducted in only 15 % of studies, and just 6 % of datasets were publicly available. Interpretability tools were employed in 28 % of studies to enhance clinical relevance. CONCLUSION: ML has significant potential to improve diagnostics and disease management in hand imaging of RMDs. However, key challenges remain, including the need for increased external validation, broader disease coverage (OA and PsA), and improved data-sharing practices to enhance reproducibility and clinical adoption.
引用
- Perronne L, Binvignat M, Foulquier N, et al. Algorithmic approaches in hand imaging for rheumatic musculoskeletal diseases: A systematic literature review. Semin Arthritis Rheum. 2025. PMID: 40349420. doi:10.1016/j.semarthrit.2025.152750
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。