文献速递头颈部肿瘤放疗放疗物理与技术

学习型医疗体系内持续模型更新对放疗所致毒性预测模型准确性的需求与获益

The Needs and Benefits of Continuous Model Updates on the Accuracy of RT-Induced Toxicity Prediction Models Within a Learning Health System.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2018-10-06

研究基于2008—2015年头颈部调强放疗患者的前瞻性临床与剂量学数据,构建3—6个月随访时≥2级口干预测模型,并比较四种模型更新方式的AUC。结果显示不更新时AUC降至0.5284,定期更新可显著改善预测性能,提示持续前瞻性数据收集与模型更新有助于维持口干预测模型的表现。

要点

  • 不更新模型时,测试集预测≥2级口干的AUC降至0.5284。
  • 定期更新模型可显著改善AUC(A法0.6164、B法0.6084,P<.05)。
  • 持续前瞻性数据收集与模型更新可能维持口干预测模型性能。

核心结论

  • 定期更新预测模型并持续前瞻性收集数据,对维持口干预测模型的性能有效。
  • 作者认为机器学习框架可应对放疗临床实践中的动态变化,并可能成为构建学习型医疗体系的重要组成部分。

研究设计与样本

  • 研究前瞻性收集2008—2015年接受调强放疗的头颈部患者的临床与剂量学数据,作为常规临床工作流程的一部分并匿名化用于分析。
  • 采用双变量逻辑回归,基于腮腺和颌下腺的剂量-体积直方图构建随访3—6个月时≥2级口干的预测模型。
  • 以2008—2009年数据为训练集建立基线预测模型,并用4种模型更新方法(A、B、C、D)比较测试数据集的AUC。

主要发现

  • 2008—2015年共297例患者,腮腺和颌下腺剂量及口干分级随年份呈下降趋势(P<.001)。
  • 初始训练集(2008—2009年,41例)预测≥2级口干的AUC为0.6196。
  • 模型不更新(D)时,测试集(2010—2015年,256例)的AUC降至0.5284。
  • 模型更新后AUC显著改善:A法0.6164、B法0.6084(P<.05);条件更新(C法)时AUC为0.6072。

局限性

  • 原文称结果为初步结果(preliminary results)。
  • 原文结论使用suggests、may be等限定性表述。

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

PURPOSE: Clinical data collection and development of outcome prediction models by machine learning can form the foundation for a learning health system offering precision radiation therapy. However, changes in clinical practice over time can affect the measures and patient outcomes and, hence, the collected data. We hypothesize that regular prediction model updates and continuous prospective data collection are important to prevent the degradation of a model's predication accuracy. METHODS AND MATERIALS: Clinical and dosimetric data from head and neck patients receiving intensity modulated radiation therapy from 2008 to 2015 were prospectively collected as a routine clinical workflow and anonymized for this analysis. Prediction models for grade ≥2 xerostomia at 3 to 6 months of follow-up were developed by bivariate logistic regression using the dose-volume histogram of parotid and submandibular glands. A baseline prediction model was developed with a training data set from 2008 to 2009. The selected predictor variables and coefficients were updated by 4 different model updating methods. (A) The prediction model was updated by using only recent 2-year data and applied to patients in the following test year. (B) The model was updated by increasing the training data set yearly. (C) The model was updated by increasing the training data set on the condition that the area under the curve (AUC) of the recent test year was less than 0.6. (D) The model was not updated. The AUC of the test data set was compared among the 4 model updating methods. RESULTS: Dose to parotid and submandibular glands and grade of xerostomia showed decreasing trends over the years (2008-2015, 297 patients; P < .001). The AUC of predicting grade ≥2 xerostomia for the initial training data set (2008-2009, 41 patients) was 0.6196. The AUC for the test data set (2010-2015, 256 patients) decreased to 0.5284 when the initial model was not updated (D). However, the AUC was significantly improved by model updates (A: 0.6164; B: 0.6084; P < .05). When the model was conditionally updated, the AUC was 0.6072 (C). CONCLUSIONS: Our preliminary results demonstrate that updating prediction models with prospective data collection is effective for maintaining the performance of xerostomia prediction. This suggests that a machine learning framework can handle the dynamic changes in a radiation oncology clinical practice and may be an important component for the construction of a learning health system.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Nakatsugawa M, Cheng Z, Kiess A, et al. The Needs and Benefits of Continuous Model Updates on the Accuracy of RT-Induced Toxicity Prediction Models Within a Learning Health System. Int J Radiat Oncol Biol Phys. 2018. PMID: 30300689. doi:10.1016/j.ijrobp.2018.09.038

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。