肺癌风险预测模型的全球表现:系统综述
该研究通过系统检索10 210篇文献,纳入35项研究、21个肺癌风险预测模型和42种预测因子,比较其外部验证的区分度(C-index)与校准度(E:O比)。结果显示模型性能在不同人群差异明显,北美C-index为0.60–0.87,亚洲为0.54–0.87,部分模型在特定数据子组表现不佳,强调目标人群外部验证或重校准的必要性。
要点
- 肺癌风险预测模型外部验证性能在不同地区人群差异显著。
- PLCOm2012在英国生物银行子组校准最佳,E:O比1.00(95%CI 0.93–1.08)。
- 模型应用前需在目标人群中进行严格外部验证或重校准。
核心结论
- 肺癌风险预测模型虽已充分开发与验证,但在不同人群中的性能存在差异。
- 模型开发存在显著地区不平衡,应用前需按指南在目标人群进行严格外部验证或重校准。
研究设计与样本
- 系统综述,检索10 210篇文章后纳入35项研究,涉及21个不同预测模型和42种预测因子(分属七类)。
- 比较模型外部验证的区分度(C-index)与校准度(E:O比)。
主要发现
- 北美队列中C-index范围为0.60–0.87,E:O比范围为0.62–3.70。
- 欧洲队列中Trøndelag健康研究HUNT和CanPredict的C-index超过0.870。
- Bach、LCRAT、PLCOm2012和PLCOall2014在Qresearch数据库子组电子健康记录中C-index低于0.60。
- 亚洲队列中C-index范围为0.54–0.87,仅Korean Men、LCRAT和LLPi的C-index超过0.80。
关键数值与推荐
- PLCOm2012在英国生物银行子组达到最佳E:O比1.00(95%CI:0.93–1.08)。
- LCRAT校准表现最佳,Hoggart校准表现最差。
临床怎么用
- 在目标人群应用肺癌风险预测模型前,应进行严格外部验证或重校准。
- 选择模型时需考虑地区人群差异对区分度和校准度的影响。
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: Numerous lung cancer risk prediction models have been developed and validated worldwide. It is imperative to offer a comprehensive overview and comparative analysis of their performances. METHODS: We conducted an extensive literature search to identify studies developing and/or validating lung cancer risk prediction models. Then we summarised and compared the external performance of these models, focusing on discriminative accuracy (C-index) and calibration performance (E:O ratio). RESULTS: After an initial screening of 10 210 articles, 35 studies on 21 distinct prediction models were identified, which used 42 different types of predictors spanning seven categories. Notable performance variations were observed in external validations. In North American cohorts, the C-index ranged from 0.60 to 0.87, with E:O ratios from 0.62 to 3.70. Among the European cohorts, the Trøndelag health study HUNT and CanPredict exhibited C-indices surpassing 0.870. Conversely, the Bach, lung cancer risk assessment tool (LCRAT), prostate, lung, colorectal and ovarian cancer screening (PLCO)m2012 and PLCOall2014 performed poorly in electronic health records of the Qresearch database subgroup, with C-indices falling below 0.60. PLCOm2012 reached the best E:O ratio of 1.00 (95% CI: 0.93 to 1.08) in the UK Biobank subgroup. In Asian cohorts, the C-index ranged from 0.54 to 0.87. Only three models, Korean Men, LCRAT and Liverpool lung project incidence risk model (LLPi), achieved a C-index exceeding 0.80. LCRAT demonstrated the best calibration, while Hoggart performed the worst. CONCLUSIONS: Performance of lung cancer risk prediction models, despite being well developed and validated, varies in diverse populations. Significant regional imbalance persists in the development of these models. Rigorous external validation or recalibration study in the target population is crucial in accordance with the guidance prior to model implementation. PROSPERO REGISTRATION NUMBER: CRD42022324602.
引用
- Zhang L, Wang X, Chen Q, et al. Lung cancer risk assessment by prediction model: a global perspective. Thorax. 2025. PMID: 40425295. doi:10.1136/thorax-2023-221253
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。