Search research articles

相关概念视频

Diabetes Mellitus: Overview and Type I Subtype

Diabetes Mellitus: Overview and Type I Subtype

Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...

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

Mathematical Modeling Shows that Overall Infection Burden is Reduced More by Vaccines that Decrease Spread or Accelerate Recovery than those that Lower Severe Infections or Death.

Bulletin of mathematical biology·2026

Same author

Comparing Two Categorical Gini Correlations with Applications to Classification Problems.

Statistical papers (Berlin, Germany)·2026

Same author

Confidence estimation based on data from independent studies.

Statistical methods in medical research·2023

Same author

Pre-vaccination RT-PCR negative contacts in workplace settings show high, SARS COV-2 neutralizing antibody levels.

BMC public health·2022

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

Search research articles

相关实验视频

Updated: Mar 7, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

在机器学习驱动的糖尿病风险预测中,用于特征选择的基于copula的监督过器.

Agnideep Aich¹, Md Monzur Murshed², Sameera Hewage³

¹Department of Mathematics, University of Louisiana at Lafayette, Lafayette, LA, USA. agnideep.aich1@louisiana.edu.

Scientific reports

|March 5, 2026

概括

此摘要是机器生成的。

这项研究引入了一种新的Gumbel copula特征选择方法,该方法可以识别患者数据中的极端风险因素. 它通过它们的上尾依赖性高效地排列预测因素,在糖尿病数据集上表现优于标准方法.

关键词:

基于Copula的特征选择.糖尿病糖尿病糖尿病贝尔的合体是贝尔的合体.机器学习机器学习公共卫生公共卫生风险预测风险预测监督的特征选择选择.尾巴的依赖性尾巴的依赖性

更多相关视频

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

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

相关实验视频

Last Updated: Mar 7, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

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

科学领域:

机器学习机器学习
生物统计学生物统计学
医疗信息学医疗信息学

背景情况:

有效的特征选择对于医学中可解释的预测模型至关重要.
传统方法可能会错过极端患者群体中重要的预测因素.
识别数据分布尾部的风险因素对于有针对性的干预至关重要.

研究的目的:

为特征选择引入一种新的,计算效率高的监督过器.
根据其倾向于极端的特征,使用Gumbel copula上尾对应法对积极类进行排名.
根据糖尿病数据集的标准基线评估拟议的方法.

主要方法:

开发了一个利用Gumbel copula暗示的上尾对应得分的监督过器.
根据相互信息,mRMR,ReliefF和L1/弹性网对过器进行了评估.
在两个糖尿病数据集 (CDC和PIMA) 上使用四个分类器进行了测试.
进行了统计测试,排列重要性和稳定性检查.

主要成果:

基于Gumbel的选择器在CDC数据集中是最快的,在最小的性能权衡下,减少了约52%的特征.
它的表现明显超过了相互信息和mRMR,并且与ReliefF.
在PIMA数据集中,该排名在数值上产生了最高的ROC-AUC.
该方法在两个数据集中一致确定了临床相关的预测因素.

结论:

通过上尾依赖的特征选择是一种高效和可解释的选方法.
这种方法可以有效地补充标准特征选择技术.
它对于公共卫生和临床风险预测特别有价值,重点关注极端患者层.