期刊论文

中文

中南大学学报(医学版)

1672-7347

2022

47

8

1065-1074

10.11817/j.issn.1672-7347.2022.220353

This work was supported by the Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province (2020TP1021) and the Key Laboratory of Tumor Precision Medicine, Hunan Colleges and Universities Project (2019-379), China. 第一作者(First author)：谢辉，Email: h.xie@xnu-edu-cn-s.stat.lib.xjtu.edu.cn:443, ORCID: 0000-0002-8490-1695 通信作者(Corresponding author)：李庆，Email: xnxyliqing@163-com-s.stat.lib.xjtu.edu.cn:443, ORCID: 0000-0002-0467-8148 基金项目(Foundation item)：医学影像人工智能湖南省重点实验室(2020TP1021)；湖南省高校重点实验室-肿瘤精准医学重点实验室(2019-379)。This work was supported by the Key Laboratory of Medical Imaging andArtificial Intelligence of Hunan Province (2020TP1021) and the Key Laboratory of T umor Precision Medicine, Hunan Colleges and Universities Project (2019-379), China.

本校为其他机构

目的：放射治疗是治疗女性盆腔恶性肿瘤最主要的手段，会引发一些不良反应，最常见的是放射性直肠炎（radiation proctitis,RP）。RP的发生率与放射剂量呈高度正相关。临床上急需一种科学的方法对RP的发生进行精准的预测，以帮助医师进行临床决策。本研究基于女性盆腔肿瘤患者的临床资料及放射治疗的剂量学参数，采用随机森林方法筛选与RP发生相关的核心特征，再通过机器学习算法构建RP发生的风险预测模型，以期为RP的预测和预防提供技术支持和理论依据。方法：回顾性收集2019年1月至2020年12月在湘南学院附属医院放射肿瘤科接受静态三维适形调强放射治疗的女性盆腔肿瘤患者100例，收集其临床相...

Objective: Radiation therapy is a main method for female pelvic malignancies, which can cause some adverse reactions, such as radiation proctitis (RP). The incidence of RP is highly positively correlated with radiation dose. There is an urgent need for a scientific method to accurately predict the occurrence of RP to help doctors make clinical decisions. In this study, based on the clinical data of female pelvic tumor patients and dosimetric parameters of radiotherapy, the random forest method was used to screen the hub features related to the ...