相关实验视频

Updated: May 1, 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

使用机器学习预测晚期或转移性胰腺癌患者的化疗反应

Jamin Koo^1,2,3, Gyucheol Choi¹, Jaekyung Cheon⁴

¹ImpriMed Korea, Inc, Seoul, Republic of Korea.

JCO clinical cancer informatics

|December 2, 2025

概括

机器学习模型可以预测接受FOLFIRINOX或gemcitabine/nab-paclitaxel的晚期胰腺癌患者的生存率. 这有助于个性化化疗选择,以获得更好的结果.

科学领域:

在瘤学瘤学.
机器学习机器学习
临床数据分析临床数据分析

背景情况:

选择先进胰腺癌的第一线化疗 (FOLFIRINOX vs. gemcitabine/nab-paclitaxel) 是复杂的,因为有效性和毒性各不相同.
个性化治疗选择对于改善转移性胰腺癌的生存结果至关重要.

研究的目的:

开发机器学习 (ML) 模型,用于预测晚期或转移性胰腺癌的生存结果.
用常规可用的临床数据来指导化疗方案的选择.

主要方法:

对191名晚期或转移性胰腺癌患者的回顾性分析.
基于CatBoost的ML模型的开发,以预测FOLFIRINOX和gemcitabine/nab-paclitaxel的12个月总生存期 (OS).
使用5倍交叉验证和ROC-AUC进行风险分类的变量选择的优化.

主要成果:

ML模型实现了高的预测性能 (ROC-AUC为0.81的FOLFIRINOX,0.82的GnP).
在这两种疗法中,预测的高风险和低风险组之间的中位数OS显著差异.
两种化疗方案之间风险分类的实质性重叠,表明个性化选择的潜力.

结论:

使用多中心数据,ML模型有效预测晚期胰腺癌早期死亡风险.
基于ML预测的个性化化疗选择可能会改善临床结果.
机器学习为优化胰腺癌治疗策略提供了宝贵的工具.

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

Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase

Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase

Genetic polymorphisms in drug targets have emerged as critical determinants of interindividual variability in drug response and toxicity. Pharmacogenomic investigations increasingly focus on identifying these variations to personalize and optimize therapeutic interventions. A drug target may be a receptor, enzyme, or signaling protein involved in pharmacologic responses or disease-related pathways. While early pharmacogenetic studies focused primarily on drug metabolism, current research...