文献速递其他结缔组织病

原发性干燥综合征骨质疏松预测:机器学习比较模型的开发与外部验证

Osteoporosis prediction in primary Sjögren's syndrome: development and external validation of a machine-learning comparison model.
PubMed 文献 · Rheumatology (Oxford) · 2026-01-01

本研究基于1000例原发性干燥综合征(pSS)患者开发并外部验证(266例)骨质疏松预测模型,最终保留7个预测因子,外部验证AUC为0.787,校准良好,并开发了网页计算器。

要点

  • 7变量逻辑回归模型外部验证AUC为0.787,校准良好。
  • 机器学习模型训练AUC更高但可迁移性较差。
  • 模型可用于常规就诊时优先安排骨密度检测。

核心结论

  • 透明且经外部验证的7变量模型可个体化估计pSS患者DXA定义的骨质疏松风险,帮助临床优先安排骨密度检测。

研究设计与样本

  • 回顾性队列研究,纳入龙华医院1000例pSS患者按7:3随机分为训练集与内部验证集,另设上海第七人民医院266例独立外部验证队列。

主要发现

  • 最终逻辑回归模型保留7个预测因子:性别、年龄、当前糖皮质激素使用、EULAR Sjögren综合征疾病活动指数评分、25-羟基维生素D、I型前胶原N端前肽和I型胶原β-C端端肽。
  • 训练集、内部验证集和外部验证集的AUC分别为0.820、0.807和0.787,校准良好。
  • 机器学习模型训练AUC更高但可迁移性较差。
  • 开发了可免费访问的网页计算器用于床旁使用。

关键数值与推荐

  • 外部验证AUC为0.787。
  • 训练集AUC为0.820,内部验证集AUC为0.807。

临床怎么用

  • 可在pSS患者常规就诊时使用该7变量模型评估骨质疏松风险,优先安排高风险患者进行骨密度检测。

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

OBJECTIVES: Osteoporosis and fragility fractures are clinically important complications of primary Sjögren's syndrome (pSS) that may accelerate functional decline and excess mortality. In practice, osteoporosis risk is often assessed using general-population tools that do not incorporate disease activity, glucocorticoid exposure or inflammation-related bone remodelling. We aimed to develop and externally validate a prediction model for DXA-defined osteoporosis in pSS using routinely available clinical and laboratory indicators. METHODS: This retrospective cohort study included 1000 patients with pSS from Longhua Hospital, randomly split into training and internal validation sets (7:3), and an independent external validation cohort of 266 patients from Shanghai Seventh People's Hospital. Candidate predictors were screened by univariable analysis, multivariable logistic regression and LASSO. Logistic regression was compared with seven supervised machine-learning algorithms. Performance was evaluated by area under the receiver operating characteristic curve (AUC), calibration and decision curve analysis. RESULTS: The final logistic regression model retained seven predictors: sex, age, current glucocorticoid use, EULAR Sjögren's Syndrome Disease Activity Index score, 25-hydroxyvitamin D, procollagen type 1 N-terminal propeptide and β-C-terminal telopeptide of type I collagen. AUCs were 0.820, 0.807 and 0.787 in the training, internal validation and external validation cohorts, respectively, with good calibration. Machine-learning models achieved higher training AUCs but showed poorer transportability. A freely accessible web-based calculator was developed for point-of-care use. CONCLUSION: A transparent, externally validated seven-variable model provides individualized DXA-defined osteoporosis risk estimation in pSS and may help clinicians prioritize bone density testing during routine visits.

来源:Rheumatology (Oxford),查看原文。版权归原作者所有。

引用

  1. Yang L, Shao Y, Zhang C, et al. Osteoporosis prediction in primary Sjögren's syndrome: development and external validation of a machine-learning comparison model. Rheumatology (Oxford). 2026. PMID: 42616665. doi:10.1093/rheumatology/keag446

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。