相关实验视频

Updated: Sep 17, 2025

Profiling Sensitivity to Targeted Therapies in EGFR-Mutant NSCLC Patient-Derived Organoids

Profiling Sensitivity to Targeted Therapies in EGFR-Mutant NSCLC Patient-Derived Organoids

Published on: November 22, 2021

基于多原子的贝叶斯网络毒性建模,用于同时预测NSCLC中多重毒性结果

Saurabh S Nair¹, Ramon M Salazar¹, Ting Xu²

¹Departments of Radiation Physics and Thoaracic Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology

|July 3, 2025

概括

一个新的贝叶斯网络模型准确地预测了非小细胞肺癌患者的辐射肺炎和辐射食道炎. 这种方法整合了多原子数据,以改善放射治疗中的毒性预测.

科学领域:

在瘤学瘤学.
辐射疗法辐射疗法
生物信息学是一种生物信息学.
医学物理医学物理

背景情况:

放射性肺炎 (RP) 和放射性食道炎 (RE) 是非小细胞肺癌 (NSCLC) 放射治疗中的显著剂量限制毒性.
准确预测这些毒性对于优化治疗计划和患者结果至关重要.

研究的目的:

开发一个多目标贝叶斯网络 (BN) 模型,用于同时预测RP和RE.
整合剂量体积图谱 (DVH),临床和多原子特征,以提高预测准确度.

主要方法:

分析了179名NSCLC患者的队列,根据CTCAE v5.0.0收集的毒性数据.
为了从672个提取的特征中选择特征,使用了具有L1-规范惩罚和处罚后勤回归的并行维度减少技术.
一个基于分数的结构学习算法 (Tabu search) 构建了BN模型,用于交叉验证的70%/30%的训练/测试分割.

主要成果:

在试验组中,BN模型实现了0.86的曲线下面积 (AUC) 和0.76的精度回忆曲线下面积 (AUPRC) 的RP预测.
对于RE预测,该模型的AUC为0.81和AUPRC为0.50.
通过自由反应AUC (FRAUC) 评估的联合预测性能在测试组上为0.74.

结论:

成功开发了一个高度预测性的多目标BN模型.
该模型有效地利用多原子共变量来同时预测RP和RE.
这一进步为管理NSCLC放射治疗中的关键毒性提供了一个有希望的工具.

关键词:

人工智能的人工智能是人工智能.机器学习是机器学习.无线电学 (Radiomics) 是一种无线电学.毒性建模有毒性建模

更多相关视频

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Impact Assessment of Repeated Exposure of Organotypic 3D Bronchial and Nasal Tissue Culture Models to Whole Cigarette Smoke

Impact Assessment of Repeated Exposure of Organotypic 3D Bronchial and Nasal Tissue Culture Models to Whole Cigarette Smoke

Published on: February 12, 2015

相关概念视频

Mutagenicity and Carcinogenicity

Mutagenicity and Carcinogenicity

Mutagenicity and carcinogenicity refer to the ability of drugs to cause genetic defects and induce cancer, respectively. The International Agency for Research on Cancer (IARC) classifies agents into four groups based on their carcinogenic potential. Group 1 agents are known human carcinogens; group 2A agents are probably carcinogenic to humans; group 3 agents lack data to support their role in carcinogenesis; and group 4 includes agents for which data support that they are not likely to be...