Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Repeated mild spinal cord contusions exacerbate tauopathy development in PS19 mice.

Acta neuropathologica communications·2026

Same author

Impact of a computerized intervention to optimize laboratory tests ordering: one-year follow-up in a geriatric unit.

Clinical chemistry and laboratory medicine·2026

Same author

<i>CEBP</i> and <i>ZEB2</i> alterations define three distinct subtypes of B-cell acute lymphoblastic leukemia.

HemaSphere·2026

Same author

A comprehensive multicenter study assessing the impact of abelacimab, asundexian and milvexian on coagulation assays.

Blood advances·2026

Same author

Jet ventilation and hemodynamic stability during pulmonary vein isolation: ventilatory and hemodynamic outcomes from a randomized controlled trial (Secondary analysis under EEG-Guided Total Intravenous Anesthesia).

BMC anesthesiology·2026

Same author

AdamiForge: a modular reverse genetics tool for human adenovirus type 12 (HAdV-A12).

Microbiology spectrum·2026

Search research articles

相关实验视频

Updated: May 10, 2025

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

使用机器学习算法预测淋巴瘤的攻击性

Julien Cabo¹, Benoît Bihin², Nicolas Debortoli³

¹Université Catholique de Louvain, CHU UCL Namur, Namur Thrombosis and Hemostasis Center (NTHC), Hematology Laboratory, Yvoir, Belgium.

International journal of laboratory hematology

|April 24, 2025

概括

在多变量模型中将淋巴结细胞学 (LNC) 和流细胞学 (FC) 与其他临床数据相结合,可以准确预测侵袭性淋巴瘤. 这种方法提供了有价值的诊断信息,可以在等待最终的病理学结果时迅速启动治疗.

关键词:

具有侵略性的淋巴瘤.组合学习算法组合学习算法淋巴结细胞学淋巴结细胞学机器学习是机器学习.预测建模预测建模

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

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

相关实验视频

Last Updated: May 10, 2025

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

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

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

科学领域:

血液学血液学血液学
在瘤学瘤学.
诊断病理学的诊断病理学

背景情况:

淋巴结检查对于诊断淋巴瘤新生病,转移和感染至关重要.
侵略性淋巴瘤,如侵略性非霍奇金淋巴瘤 (NHL),需要紧急诊断.
整合各种诊断参数可以为患者管理提供及时的信息.

研究的目的:

开发和评估用于识别攻击性淋巴瘤的多变量预测模型.
评估结合淋巴结细胞学 (LNC) 和流细胞计 (FC) 与其他临床参数的诊断价值.
在需要紧急淋巴瘤评估的情况下提高诊断效率.

主要方法:

对196个淋巴结样本进行了回顾性分析.
包括参数:年龄,性别,LNC,FC,正子发射断层扫描,淋巴细胞,白细胞,乳酸脱酶 (LDH) 和血红蛋白.
构建五个多变量模型:三个逻辑回归模型和两个集体学习模型 (回收和提升).
使用十倍交叉验证的性能评估,包括灵敏度,特异性和AUC.

主要成果:

与单个变量 (AUC 0.690.87) 相比,多变量模型显示出更高的性能 (AUC 0.880.94).
性能最好的模型 (增强) 获得了77%的灵敏度和94%的特异性.
快速可用的参数,包括LNC和FC,是淋巴瘤攻击性的重要预测指标.

结论:

淋巴结细胞学,流细胞测量和其他随时可用的临床数据与淋巴瘤的攻击性有关.
综合这些参数的多变量模型提供了有价值的诊断见解.
这种方法有助于迅速启动侵袭性淋巴瘤的治疗.