HAL与HOMER模型预测非小细胞肺癌淋巴结转移的前瞻性外部与时间验证
本研究为多中心前瞻性观察队列,纳入1799例PET-CT分期T1-3、N0-3、M0的非小细胞肺癌患者,在EBUS-TBNA分期前验证HAL与HOMER模型。两模型判别能力良好,HAL预测N2|3的ROC-AUC为0.876,HOMER预测N1|2|3和N2|3的ROC-AUC分别为0.837和0.876;校准图良好但Hosmer-Lemeshow检验提示存在小幅但有统计学意义的校准误差。
要点
- HAL预测N2|3的ROC-AUC为0.876,HOMER预测N1|2|3为0.837、N2|3为0.876。
- 校准图显示校准良好,但Hosmer-Lemeshow检验提示小幅校准误差(P=.034和.002)。
核心结论
- HAL与HOMER在多中心验证中显示出良好的判别与校准能力,虽存在小幅校准误差但模型仍具信息价值。
主要发现
- HAL预测N1|2|3的ROC-AUC为0.873(95%CI 0.856-0.891),预测N2|3为0.876(95%CI 0.855-0.897)。
- HOMER预测N1|2|3的ROC-AUC为0.837(95%CI 0.814-0.859),预测N2|3为0.876(95%CI 0.855-0.897)。
- HAL与HOMER的Brier评分分别为0.117和0.349。
- 校准图显示两模型校准良好;HAL预测N2|3的预测与观察概率差为+0.012,HOMER预测N1|2|3差为-0.018、N2|3差为+0.002。
- Hosmer-Lemeshow检验两模型均显著(P=.034和.002),提示存在小幅但有统计学意义的校准误差。
临床怎么用
- 在EBUS-TBNA分期前,可参考HAL与HOMER模型估算NSCLC患者淋巴结转移概率以辅助临床决策。
- 应用模型时需注意其存在小幅校准误差,结果应结合临床综合判断。
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: Two models, the Help with the Assessment of Adenopathy in Lung cancer (HAL) and Help with Oncologic Mediastinal Evaluation for Radiation (HOMER), were recently developed to estimate the probability of nodal disease in patients with non-small cell lung cancer (NSCLC) as determined by endobronchial ultrasound-transbronchial needle aspiration (EBUS-TBNA). The objective of this study was to prospectively externally validate both models at multiple centers. RESEARCH QUESTION: Are the HAL and HOMER models valid across multiple centers? STUDY DESIGN AND METHODS: This multicenter prospective observational cohort study enrolled consecutive patients with PET-CT clinical-radiographic stages T1-3, N0-3, M0 NSCLC undergoing EBUS-TBNA staging. HOMER was used to predict the probability of N0 vs N1 vs N2 or N3 (N2|3) disease, and HAL was used to predict the probability of N2|3 (vs N0 or N1) disease. Model discrimination was assessed using the area under the receiver operating characteristics curve (ROC-AUC), and calibration was assessed using the Brier score, calibration plots, and the Hosmer-Lemeshow test. RESULTS: Thirteen centers enrolled 1,799 patients. HAL and HOMER demonstrated good discrimination: HAL ROC-AUC = 0.873 (95%CI, 0.856-0.891) and HOMER ROC-AUC = 0.837 (95%CI, 0.814-0.859) for predicting N1 disease or higher (N1|2|3) and 0.876 (95%CI, 0.855-0.897) for predicting N2|3 disease. Brier scores were 0.117 and 0.349, respectively. Calibration plots demonstrated good calibration for both models. For HAL, the difference between forecast and observed probability of N2|3 disease was +0.012; for HOMER, the difference for N1|2|3 was -0.018 and for N2|3 was +0.002. The Hosmer-Lemeshow test was significant for both models (P = .034 and .002), indicating a small but statistically significant calibration error. INTERPRETATION: HAL and HOMER demonstrated good discrimination and calibration in multiple centers. Although calibration error was present, the magnitude of the error is small, such that the models are informative.
引用
- Martinez-Zayas G, Almeida FA, Yarmus L, et al. Predicting Lymph Node Metastasis in Non-small Cell Lung Cancer: Prospective External and Temporal Validation of the HAL and HOMER Models. Chest. 2021. PMID: 33932466. doi:10.1016/j.chest.2021.04.048
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。