相关实验视频

Updated: Jul 15, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

使用基于放射学和剂量计的可解释机器学习模型,预测晚期宫癌患者的血液毒性

Jun Zhu¹, Qionghui Zhou¹, Luqiao Chen²

¹Department of Radiation Oncology, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University/Hunan Cancer Hospital, Changsha, China.

|October 6, 2025

概括

整合放射学和剂量学特征的机器学习模型可以准确预测经过化学放射治疗的晚期宫癌患者的血液毒性 (HT). SHAP价值分析提高了用于临床应用的模型解释性.

科学领域:

放射学和瘤学放射学和瘤学
医疗成像医学成像
机器学习在医学中的应用

背景情况:

血液毒性 (HT) 是晚期宫癌患者接受化疗放射治疗的重大并发症.
准确预测HT对于优化患者管理和治疗结果至关重要.
本研究重点是开发用于HT预测的可解释机器学习模型.

研究的目的:

开发和评估机器学习模型,使用放射性和剂量学特征来预测HT.
评估独立放射学,剂量学和混合模型的性能.
通过可解释性分析提高模型透明度和临床实用性.

主要方法:

对205名接受化疗或放射治疗的晚期宫癌患者的回顾性分析.
从CT图像和剂量文件中提取放射性和剂量学特征.
开发极端梯度增强树木模型 (放射学,剂量学,混合) 随机森林特征选择.
使用灵敏度,特异性和AUC进行评估;通过SHAP值进行解释性分析.

主要成果:

与独立模型相比,集成放射学和剂量学的混合模型显示出更高的性能 (AUC=0.83).
提供SHAP值的功能重要性排名和阐明决策过程.
可解释性分析增强了对模型预测和特征相互作用的理解.

结论:

整合放射学和剂量学特征显著改善了在晚期宫癌中对HT的预测模型性能.
基于SHAP价值的可解释性分析有助于临床理解和采用预测模型.
这些发现为改进治疗策略和改善患者治疗结果提供了潜力.

关键词:

剂量剂量剂量血液学毒性血液学毒性机器学习机器学习无线电学 (Radiomics) 是一种无线电学.这就是 SHAP SHAP 的意思.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

相关概念视频

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...