文献速递胸部肿瘤放疗消化道肿瘤放疗放疗物理与技术

10种先进机器学习算法用于放射性毒性结局预测建模的性能比较

Performance Comparison of 10 State-of-the-Art Machine Learning Algorithms for Outcome Prediction Modeling of Radiation-Induced Toxicity.
PubMed 文献 · Adv Radiat Oncol · 2024-11-13

本研究利用来自本院的3组放射性毒性数据(478例患者),涵盖胃肠毒性、放射性肺炎和放射性食管炎,比较了11种常用机器学习算法在预测正常组织并发症概率方面的表现。结果显示没有一种算法在所有数据集上均最优,LASSO在放射性食管炎中精确率-召回率曲线下面积最高,随机森林在胃肠毒性中最高,神经网络在放射性肺炎中最高。研究还开发了图形用户界面以自动比较这些算法的性能。

要点

  • LASSO在放射性食管炎中精确率-召回率曲线下面积最高(0.807 ± 0.067)。
  • 随机森林在胃肠毒性中精确率-召回率曲线下面积最高(0.726 ± 0.096)。
  • 神经网络在放射性肺炎中精确率-召回率曲线下面积最高(0.878 ± 0.060)。

核心结论

  • 结果表明没有一种算法对所有数据集都是最好的,因此在新数据集上训练结局预测模型时比较多种算法很重要。
  • 本研究创建的图形用户界面可自动比较这11种算法在任何数据集上的性能。

研究设计与样本

  • 从本院获取3组放射性毒性数据(478例患者):胃肠毒性、放射性肺炎和放射性食管炎,包含非小细胞肺癌和肛管鳞状细胞癌患者的临床病理和剂量学信息。
  • 每个数据集随机分为训练集和测试集,训练集用于创建和调优模型,测试集通过计算性能指标评估模型,每个算法对每个数据集重复100次。
  • 使用11种常用机器学习算法建模:弹性网络、最小绝对收缩和选择算子(LASSO)、随机森林、随机森林回归、支持向量机、极端梯度提升、轻量梯度提升机、k近邻、神经网络、贝叶斯-LASSO和贝叶斯神经网络。

主要发现

  • LASSO在放射性食管炎中精确率-召回率曲线下面积最高(0.807 ± 0.067),其曲线下面积为0.754 ± 0.069。
  • 随机森林在胃肠毒性中精确率-召回率曲线下面积最高(0.726 ± 0.096),其曲线下面积为0.889 ± 0.043。
  • 神经网络在放射性肺炎中精确率-召回率曲线下面积最高(0.878 ± 0.060),其曲线下面积为0.905 ± 0.045。
  • 对所有毒性平均精确率-召回率曲线下面积,贝叶斯-LASSO是最佳模型。

临床怎么用

  • 作者认为在新数据集上训练结局预测模型时,比较多种算法很重要。
  • 本研究创建的图形用户界面可自动比较这11种算法在任何数据集上的性能。

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

PURPOSE: To evaluate the efficacy of prominent machine learning algorithms in predicting normal tissue complication probability using clinical data obtained from 2 distinct disease sites and to create a software tool that facilitates the automatic determination of the optimal algorithm to model any given labeled data set. METHODS AND MATERIALS: We obtained 3 sets of radiation toxicity data (478 patients) from our clinic: gastrointestinal toxicity, radiation pneumonitis, and radiation esophagitis. These data comprised clinicopathological and dosimetric information for patients diagnosed with non-small cell lung cancer and anal squamous cell carcinoma. Each data set was modeled using 11 commonly employed machine learning algorithms (elastic net, least absolute shrinkage and selection operator [LASSO], random forest, random forest regression, support vector machine, extreme gradient boosting, light gradient boosting machine, k-nearest neighbors, neural network, Bayesian-LASSO, and Bayesian neural network) by randomly dividing the data set into a training and test set. The training set was used to create and tune the model, and the test set served to assess it by calculating performance metrics. This process was repeated 100 times by each algorithm for each data set. Figures were generated to visually compare the performance of the algorithms. A graphical user interface was developed to automate this whole process. RESULTS: LASSO achieved the highest area under the precision-recall curve (0.807 ± 0.067) for radiation esophagitis, random forest for gastrointestinal toxicity (0.726 ± 0.096), and the neural network for radiation pneumonitis (0.878 ± 0.060). The area under the curve was 0.754 ± 0.069, 0.889 ± 0.043, and 0.905 ± 0.045, respectively. The graphical user interface was used to compare all algorithms for each data set automatically. When averaging the area under the precision-recall curve across all toxicities, Bayesian-LASSO was the best model. CONCLUSIONS: Our results show that there is no best algorithm for all data sets. Therefore, it is important to compare multiple algorithms when training an outcome prediction model on a new data set. The graphical user interface created for this study automatically compares the performance of these 11 algorithms for any data set.

来源:Adv Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Salazar RM, Nair SS, Leone AO, et al. Performance Comparison of 10 State-of-the-Art Machine Learning Algorithms for Outcome Prediction Modeling of Radiation-Induced Toxicity. Adv Radiat Oncol. 2024. PMID: 39717195. doi:10.1016/j.adro.2024.101675

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。