文献速递医学人工智能与信息学组学、生物样本库与精准医学基础与转化研究

DNA甲基化谱的机器学习分析可区分原发性肺鳞状细胞癌与头颈部转移癌

Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases.
PubMed 文献 · Sci Transl Med · 2019-01-01

研究对原发肿瘤进行DNA甲基化谱分析,训练三种机器学习方法区分转移性头颈部鳞状细胞癌(HNSC)与原发性肺鳞状细胞癌(LUSC)。人工神经网络在279例HNSC、LUSC及正常肺对照验证队列中正确分类96.4%,优于支持向量机(95.7%)和随机森林(87.8%)。对51例有HNSC病史且发生第二肺肿瘤的患者进行独立临床验证,基于临床病理特征实现了正确分类。该方法可能有助于可靠鉴别HNSC肺转移与原发性LUSC以指导治疗决策。

要点

  • DNA甲基化谱联合机器学习可区分HNSC肺转移与原发性LUSC。
  • 神经网络在279例验证队列中正确分类96.4%,优于支持向量机95.7%和随机森林87.8%。
  • 应用概率评分阈值并排除低置信度样本后,92.1%的病例预测准确率超过99%。

核心结论

  • 该方法可能有助于可靠鉴别HNSC肺转移与原发性LUSC,以指导治疗决策。

研究设计与样本

  • 对原发肿瘤进行DNA甲基化谱分析,训练三种机器学习方法区分转移性HNSC与原发性LUSC。
  • 验证队列纳入279例HNSC、LUSC及正常肺对照患者。
  • 独立临床验证分析51例有HNSC病史且发生第二肺肿瘤的患者。

主要发现

  • 人工神经网络在279例验证队列中正确分类96.4%,支持向量机为95.7%,随机森林为87.8%。
  • 应用概率评分阈值并排除低置信度样本后,92.1%的神经网络病例、90%的支持向量机病例和43%的随机森林病例预测准确率超过99%。
  • 51例有HNSC病史且发生第二肺肿瘤的患者基于临床病理特征实现了正确分类。

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

Head and neck squamous cell carcinoma (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we performed DNA methylation profiling of primary tumors and trained three different machine learning methods to distinguish metastatic HNSC from primary LUSC. We developed an artificial neural network that correctly classified 96.4% of the cases in a validation cohort of 279 patients with HNSC and LUSC as well as normal lung controls, outperforming support vector machines (95.7%) and random forests (87.8%). Prediction accuracies of more than 99% were achieved for 92.1% (neural network), 90% (support vector machine), and 43% (random forest) of these cases by applying thresholds to the resulting probability scores and excluding samples with low confidence. As independent clinical validation of the approach, we analyzed a series of 51 patients with a history of HNSC and a second lung tumor, demonstrating the correct classifications based on clinicopathological properties. In summary, our approach may facilitate the reliable diagnostic differentiation of pulmonary metastases of HNSC from primary LUSC to guide therapeutic decisions.

来源:Sci Transl Med,查看原文。版权归原作者所有。

引用

  1. Jurmeister P, Bockmayr M, Seegerer P, et al. Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases. Sci Transl Med. 2019. PMID: 31511427. doi:10.1126/scitranslmed.aaw8513

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。