相关实验视频

Updated: May 24, 2025

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

在可解释的机器学习模型中强调了手术前最大标准化摄取值,用于预测切除非小细胞肺癌复发风险

Takafumi Iguchi¹, Kensuke Kojima¹, Daiki Hayashi¹

¹Department of General Thoracic Surgery, NHO Kinki Chuo Chest Medical Center, Osaka, Japan.

JCO clinical cancer informatics

|March 5, 2025

概括

在18F-FDG PET-CT中,术前最大标准化吸收值 (SUVmax) 预测了手术后非小细胞肺癌 (NSCLC) 的复发. 较高的SUVmax值表明复发风险显著增加,有助于早期识别高风险患者.

科学领域:

在瘤学瘤学.
放射学放射学是一门学科.
医疗成像医学成像

背景情况:

切除后非小细胞肺癌 (NSCLC) 复发是一个重大的临床挑战.
准确预测术后复发对于个性化治疗策略至关重要.

研究的目的:

分析18F-氧葡萄糖正子发射断层扫描-计算机断层扫描 (18F-FDG PET-CT) 的手术前最大标准化吸收值 (SUVmax) 与切除NSCLC的术后复发之间的关联.
利用机器学习 (ML) 和统计方法来预测复发风险.

主要方法:

对643名切除NSCLC的患者进行了回顾性分析.
开发和评估ML模型 (随机森林,梯度增强,AdaBoost,极端梯度增强) 和随机生存森林模型.
使用ROC AUC和C指数进行性能评估;通过SHAP和PDP进行解释;用于SUVmax和复发风险的多变量Cox比例危险模型.

主要成果:

随机森林模型显示出高预测性能 (ROC AUC,0.90).
SUVmax被确定为SHAP和排列重要性分析的关键预测因子.
在SUVmax和复发风险之间观察到非线性关系,SUVmax值的急剧增加为2-5.
增加的SUVmax与更高的复发风险显著相关 (调整后的危险比率1.03).

结论:

术前SUVmax是切除的NSCLC术后复发的重要预测因素.
非线性关联表明SUVmax的潜力作为一个敏感的生物标志物,用于早期识别高风险患者.
研究结果支持更精确的复发风险评估和NSCLC个性化治疗策略.

更多相关视频

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

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...