文献速递消化系统肿瘤

一种用于在基层医疗中识别非转移性结直肠癌的机器学习工具

A machine learning tool for identifying non-metastatic colorectal cancer in primary care.
PubMed 文献 · Eur J Cancer · 2023-01-20

本研究基于瑞典Västra Götaland地区2011年诊断的542例非转移性结直肠癌(NMCRC)患者及2139名匹配对照的基层医疗就诊数据,采用随机梯度提升(SGB)构建预测模型。模型敏感性73.3%、特异性83.5%,贫血和出血相关变量合计标准化相对影响(NRI)27.6%,排便习惯改变的边际效应比值比最高为28.8。作者认为机器学习有助于识别基层医疗中预测NMCRC的重要变量。

要点

  • 模型基于基层医疗诊断编码和就诊总次数预测非转移性结直肠癌,敏感性73.3%、特异性83.5%。
  • 贫血和出血相关变量合计NRI为27.6%,排便习惯改变的边际效应比值比最高为28.8。
  • 作者认为机器学习有助于识别预测NMCRC的重要变量,恶性诊断可能隐藏于痔疮等良性症状之后。

核心结论

  • 机器学习有助于识别基层医疗中预测非转移性结直肠癌的重要变量。
  • 恶性诊断可能隐藏于痔疮等良性症状之后。

研究设计与样本

  • 病例对照研究,纳入瑞典Västra Götaland地区2011年诊断的542例18岁以上非转移性结直肠癌患者及2139名匹配对照的基层医疗就诊数据。
  • 采用随机梯度提升(SGB)基于癌症诊断日期前一年内基层医疗会诊的诊断编码及会诊总次数构建预测模型。
  • 标准化相对影响(NRI)大于1%的变量被认为对模型有重要贡献,使用边际效应的比值比计算患NMCRC的风险。

主要发现

  • 随机梯度提升模型使用的361个预测变量中,184个影响非零,16个变量NRI大于1%,合计NRI为63.3%。
  • 代表贫血和出血的变量合计NRI为27.6%。
  • 模型敏感性为73.3%,特异性为83.5%。
  • 排便习惯改变的边际效应比值比最高,为28.8。

关键数值与推荐

  • 变量NRI大于1%被认为对模型有重要贡献。
  • 模型敏感性73.3%,特异性83.5%。
  • 排便习惯改变的边际效应比值比为28.8。
  • 贫血和出血相关变量合计NRI为27.6%。

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: Primary health care (PHC) is often the first point of contact when diagnosing colorectal cancer (CRC). Human limitations in processing large amounts of information warrant the use of machine learning as a diagnostic prediction tool for CRC. AIM: To develop a predictive model for identifying non-metastatic CRC (NMCRC) among PHC patients using diagnostic data analysed with machine learning. DESIGN AND SETTING: A case-control study containing data on PHC visits for 542 patients >18 years old diagnosed with NMCRC in the Västra Götaland Region, Sweden, during 2011, and 2,139 matched controls. METHOD: Stochastic gradient boosting (SGB) was used to construct a model for predicting the presence of NMCRC based on diagnostic codes from PHC consultations during the year before the date of cancer diagnosis and the total number of consultations. Variables with a normalised relative influence (NRI) >1% were considered having an important contribution to the model. Risks of having NMCRC were calculated using odds ratios of marginal effects. RESULTS: Of the 361 variables used as predictors in the stochastic gradient boosting model, 184 had non-zero influence, with 16 variables having NRI >1% and a combined NRI of 63.3%. Variables representing anaemia and bleeding had a combined NRI of 27.6%. The model had a sensitivity of 73.3% and a specificity of 83.5%. Change in bowel habit had the highest odds ratios of marginal effects at 28.8. CONCLUSION: Machine learning is useful for identifying variables of importance for predicting NMCRC in PHC. Malignant diagnoses may be hidden behind benign symptoms such as haemorrhoids.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Nemlander E, Ewing M, Abedi E, et al. A machine learning tool for identifying non-metastatic colorectal cancer in primary care. Eur J Cancer. 2023. PMID: 36758474. doi:10.1016/j.ejca.2023.01.011

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。