文献速递头颈部肿瘤放疗放疗物理与技术

神经网络与样条回归预测接受放射治疗患者唾液腺功能减退

Neural network and spline-based regression for the prediction of salivary hypofunction in patients undergoing radiation therapy.
PubMed 文献 · Radiat Oncol · 2023-05-08

本研究利用510例头颈癌患者的腮腺剂量体积直方图,比较LKB模型、样条模型和神经网络预测放疗后唾液腺功能减退的性能。神经网络模型AUC为0.75–0.83,优于LKB模型(拟合0.70–0.80,文献参数0.67–0.77),样条模型AUC为0.75–0.84。

要点

  • 神经网络模型在每一个截断点均优于LKB模型,AUC范围0.75–0.83。
  • 样条模型AUC范围0.75–0.84,除0.55截断点外几乎均优于LKB模型。
  • 拟合LKB模型AUC为0.70–0.80,文献参数LKB模型AUC为0.67–0.77。

核心结论

  • 神经网络模型性能优于LKB模型和其他机器学习方法,可提供有临床意义的唾液腺功能减退预测,且不依赖汇总指标。

研究设计与样本

  • 回顾性队列研究,纳入510例头颈癌患者,利用放疗前后唾液流率拟合三种预测模型:LKB模型、样条模型和神经网络,另设使用文献参数的LKB模型作参考,采用截断点依赖的AUC分析评价预测性能。

主要发现

  • 神经网络模型在每个截断点均优于LKB模型,AUC范围为0.75至0.83,具体取决于所选截断点。
  • 样条模型几乎优于LKB模型,AUC范围为0.75至0.84;仅拟合LKB模型在0.55截断点表现更好。
  • LKB模型预测能力最低,拟合LKB模型AUC为0.70至0.80,文献参数LKB模型AUC为0.67至0.77。

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: This study leverages a large retrospective cohort of head and neck cancer patients in order to develop machine learning models to predict radiation induced hyposalivation from dose-volume histograms of the parotid glands. METHODS: The pre and post-radiotherapy salivary flow rates of 510 head and neck cancer patients were used to fit three predictive models of salivary hypofunction, (1) the Lyman-Kutcher-Burman (LKB) model, (2) a spline-based model, (3) a neural network. A fourth LKB-type model using literature reported parameter values was included for reference. Predictive performance was evaluated using a cut-off dependent AUC analysis. RESULTS: The neural network model dominated the LKB models demonstrating better predictive performance at every cutoff with AUCs ranging from 0.75 to 0.83 depending on the cutoff selected. The spline-based model nearly dominated the LKB models with the fitted LKB model only performing better at the 0.55 cutoff. The AUCs for the spline model ranged from 0.75 to 0.84 depending on the cutoff chosen. The LKB models had the lowest predictive ability with AUCs ranging from 0.70 to 0.80 (fitted) and 0.67 to 0.77 (literature reported). CONCLUSION: Our neural network model showed improved performance over the LKB and alternative machine learning approaches and provided clinically useful predictions of salivary hypofunction without relying on summary measures.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Smith DK, Clark H, Hovan A, et al. Neural network and spline-based regression for the prediction of salivary hypofunction in patients undergoing radiation therapy. Radiat Oncol. 2023. PMID: 37158946. doi:10.1186/s13014-023-02274-9

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。