文献速递消化道肿瘤与早癌

使用梯度提升机开发和验证预测结直肠癌生存的模型

Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine.
PubMed 文献 · Gut · 2020-09-04

基于前列腺、肺、结直肠和卵巢癌筛查试验(PLCO)中154900名参与者,选取随访期间确诊的2359例结直肠癌患者,训练梯度提升模型预测确诊后10年内死亡风险。模型受试者工作特征曲线下面积为0.84(±0.04),准确度为0.83(±0.04),分类阈值为0.5,使用Shapley值确定20个最相关特征并解释预测。

要点

  • 模型预测结直肠癌确诊后10年内死亡风险,受试者工作特征曲线下面积0.84(±0.04)。
  • 准确度0.83(±0.04),分类阈值为0.5,模型已在线开放供研究使用。
  • 随访期间2359例确诊结直肠癌,其中686例(29%)死于结直肠癌。

核心结论

  • 研究使用大型多中心队列的前瞻性数据训练并验证了一个模型,该模型在个体层面具有高预测性能,可用于讨论治疗策略。

研究设计与样本

  • 在前列腺、肺、结直肠和卵巢癌筛查(PLCO)试验中,参与者(n=154900)被随机分配至软式乙状结肠镜筛查(3年或5年重复筛查)或常规照护组。
  • 选取随访期间确诊为结直肠癌的患者,训练梯度提升模型预测确诊后10年内死亡风险。
  • 使用Shapley值确定20个最相关特征,并对预测提供解释。

主要发现

  • 随访期间2359例患者确诊为结直肠癌,死亡随访中位时间为16.8年(14.4-18.9)。
  • 随访期间共686例患者(29%)死于结直肠癌。
  • 数据集随机分为训练集(n=1887)和测试集(n=472)。
  • 受试者工作特征曲线下面积为0.84(±0.04),准确度为0.83(±0.04),分类阈值为0.5。
  • 模型已在线开放供研究使用。

关键数值与推荐

  • 受试者工作特征曲线下面积0.84(±0.04),准确度0.83(±0.04),分类阈值为0.5。
  • 使用Shapley值确定20个最相关特征。

临床怎么用

  • 原文结论指出该模型在个体层面具有高预测性能,可用于讨论治疗策略。

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

OBJECTIVE: The success of treatment planning relies critically on our ability to predict the potential benefit of a therapy. In colorectal cancer (CRC), several nomograms are available to predict different outcomes based on the use of tumour specific features. Our objective is to provide an accurate and explainable prediction of the risk to die within 10 years after CRC diagnosis, by incorporating the tumour features and the patient medical and demographic information. DESIGN: In the prostate, lung, colorectal and ovarian cancer screening (PLCO) Trial, participants (n=154 900) were randomised to screening with flexible sigmoidoscopy, with a repeat screening at 3 or 5 years, or to usual care. We selected patients who were diagnosed with CRC during the follow-up to train a gradient-boosted model to predict the risk to die within 10 years after CRC diagnosis. Using Shapley values, we determined the 20 most relevant features and provided explanation to prediction. RESULTS: During the follow-up, 2359 patients were diagnosed with CRC. Median follow-up was 16.8 years (14.4-18.9) for mortality. In total, 686 patients (29%) died from CRC during the follow-up. The dataset was randomly split into a training (n=1887) and a testing (n=472) dataset. The area under the receiver operating characteristic was 0.84 (±0.04) and accuracy was 0.83 (±0.04) with a 0.5 classification threshold. The model is available online for research use. CONCLUSIONS: We trained and validated a model with prospective data from a large multicentre cohort of patients. The model has high predictive performances at the individual scale. It could be used to discuss treatment strategies.

来源:Gut,查看原文。版权归原作者所有。

引用

  1. Bibault JE, Chang DT, Xing L, et al. Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine. Gut. 2020. PMID: 32887732. doi:10.1136/gutjnl-2020-321799

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。