文献速递头颈外科

基于行政数据构建口咽癌二次事件病例发现算法:一项基于人群的验证研究

Developing case-finding algorithms for second events of oropharyngeal cancer using administrative data: A population-based validation study.
PubMed 文献 · Head Neck · 2019-02-01

本研究利用分类与回归树模型开发基于行政数据识别口咽癌二次事件(复发或第二原发癌)的算法,以病历回顾为参考标准。高灵敏度算法灵敏度87.9%、特异度84.5%;高阳性预测值算法特异度99.1%、阳性预测值94.2%。结论认为算法有效性可接受。

要点

  • 高灵敏度算法灵敏度87.9%,特异度84.5%,适用于需减少漏诊的场景。
  • 高阳性预测值算法特异度99.1%,阳性预测值94.2%,适用于需高置信度的场景。
  • 两种算法识别口咽癌治疗后二次事件的有效性均可接受。

核心结论

  • 基于行政数据识别口咽癌初次治疗后二次事件的算法有效性可接受。

研究设计与样本

  • 利用分类与回归树模型开发算法,以病历回顾数据作为参考标准,计算灵敏度、特异度、阳性预测值、阴性预测值和准确率。

主要发现

  • 高灵敏度算法灵敏度87.9%(95%CI 82.2%-93.6%),特异度84.5%(95%CI 81.1%-87.8%),阳性预测值61.2%(95%CI 54.1%-68.4%),阴性预测值96.2%(95%CI 94.2%-98.1%),准确率85.2%(95%CI 82.3%-88.1%)。
  • 高阳性预测值算法灵敏度52.4%(95%CI 43.6%-61.2%),特异度99.1%(95%CI 98.2%-100.0%),阳性预测值94.2%(95%CI 88.7%-99.7%),阴性预测值88.2%(95%CI 85.3%-91.0%),准确率88.9%(95%CI 86.3%-91.5%)。

局限性

  • 原文未报告局限性。

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: Second event (recurrence or second primary cancer)-free survival is an important indicator for assessing treatment efficacy. However, second events are not explicitly documented in administrative data such as cancer registries. Thus, validated algorithms using administrative data are needed to identify second events of oropharyngeal cancers. METHODS: The algorithms were developed using classification and regression tree models. Data from chart review served as the reference standard. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated. RESULTS: The high-sensitivity algorithm achieved 87.9% (95% confidence interval: 82.2%-93.6%) sensitivity, 84.5% (81.1%-87.8%) specificity, 61.2% (54.1%-68.4%) PPV, 96.2% (94.2%-98.1%) NPV, and 85.2% (82.3%-88.1%) accuracy. The high-PPV algorithm obtained 52.4% (43.6%-61.2%) sensitivity, 99.1% (98.2%-100.0%) specificity, 94.2% (88.7%-99.7%) PPV, 88.2% (85.3%-91.0%) NPV, and 88.9% (86.3%-91.5%) accuracy. CONCLUSION: The validity of the algorithms for identifying second events following primary treatment of oropharyngeal cancers was acceptable.

来源:Head Neck,查看原文。版权归原作者所有。

引用

  1. Xu Y, Kong S, Cheung WY, et al. Developing case-finding algorithms for second events of oropharyngeal cancer using administrative data: A population-based validation study. Head Neck. 2019. PMID: 30706597. doi:10.1002/hed.25682

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。