文献速递胸部CT

影像检查后肺结节数学预测模型:它们具有临床相关性吗?

Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?
PubMed 文献 · Eur Radiol · 2019-04-01

研究纳入317例CT检出实性肺结节患者(80例恶性、237例良性),比较四种数学预测模型(Mayo Clinic、Brock University、Veteran's Affairs、Peking University)在校准阈值前后的表现,并评估纵向重复成像是否改善预测。校准后Mayo Clinic和Brock University模型表现最佳(AUC=0.63、0.61),仅Brock University与原推荐阈值一致,纵向时间点间无显著准确性改善。

要点

  • 校准后Mayo Clinic和Brock University模型表现最佳(AUC=0.63、0.61),优于Veteran's Affairs(0.51)和Peking University(0.55)。
  • 仅Brock University模型与原推荐阈值一致,其他模型校准阈值后准确性提高。
  • 重复成像的纵向时间点间未发现准确性显著改善,作者建议仅在初始评估时应用数学预测模型。

核心结论

  • 校准到本地队列可选择表现最佳的数学预测模型;未校准时Brock University模型在≥8 mm实性结节中表现最稳定,但仅具有中等潜力将受试者细化到适当检查流程;作者建议仅在初始评估时应用数学预测模型,因随时间推移未获得准确性提高。

研究设计与样本

  • 研究采用317例个体的共同队列,均为CT检出的实性结节(80例恶性、237例良性),用于评估数学预测模型表现;创建了基于网络的应用程序供他人校准阈值并分析本地队列;30例重复成像患者用于纵向测试表现改善。

诊断标准与关键数值

  • 使用校准阈值时,Mayo Clinic和Brock University模型表现最佳(AUC=0.63、0.61),Veteran's Affairs为0.51,Peking University为0.55;仅Brock University模型与原数学预测模型阈值一致。

临床应用与阅片要点

  • 作者建议仅在初始评估时应用数学预测模型;未校准时Brock University模型在≥8 mm实性结节中表现最稳定;校准到共同队列可为机构选择表现最佳的数学预测模型。

局限性

  • 纵向分析仅纳入30例重复成像患者。
  • 校准后最佳模型AUC仅0.63和0.61,仅具有中等潜力将受试者细化到适当检查流程。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: Post-imaging mathematical prediction models (MPMs) provide guidance for the management of solid pulmonary nodules by providing a lung cancer risk score from demographic and radiologists-indicated imaging characteristics. We hypothesized calibrating the MPM risk score threshold to a local study cohort would result in improved performance over the original recommended MPM thresholds. We compared the pre- and post-calibration performance of four MPM models and determined if improvement in MPM prediction occurs as nodules are imaged longitudinally.

MATERIALS AND METHODS: A common cohort of 317 individuals with computed tomography-detected, solid nodules (80 malignant, 237 benign) were used to evaluate the MPM performance. We created a web-based application for this study that allows others to easily calibrate thresholds and analyze the performance of MPMs on their local cohort. Thirty patients with repeated imaging were tested for improved performance longitudinally.

RESULTS: Using calibrated thresholds, Mayo Clinic and Brock University (BU) MPMs performed the best (AUC = 0.63, 0.61) compared to the Veteran's Affairs (0.51) and Peking University (0.55). Only BU had consensus with the original MPM threshold; the other calibrated thresholds improved MPM accuracy. No significant improvements in accuracy were found longitudinally between time points.

CONCLUSIONS: Calibration to a common cohort can select the best-performing MPM for your institution. Without calibration, BU has the most stable performance in solid nodules ≥ 8 mm but has only moderate potential to refine subjects into appropriate workup. Application of MPM is recommended only at initial evaluation as no increase in accuracy was achieved over time.

KEY POINTS: • Post-imaging lung cancer risk mathematical predication models (MPMs) perform poorly on local populations without calibration. • An application is provided to facilitate calibration to new study cohorts: the Mayo Clinic model, the U.S. Department of Veteran's Affairs model, the Brock University model, and the Peking University model. • No significant improvement in risk prediction occurred in nodules with repeated imaging sessions, indicating the potential value of risk prediction application is limited to the initial evaluation.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Uthoff J, Koehn N, Larson J, et al. Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant? Eur Radiol. 2019. PMID: 30937590. doi:10.1007/s00330-019-06168-x

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。