Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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 journal

Liposomes in drugs, nutraceuticals, and cosmetics.

PeerJ·2026
Same journal

Integrating insects in circular food systems: evidence, gaps and research priorities.

PeerJ·2026
Same journal

Magnetic immunofluorescent microfluidic chips for rapid multi-parameter detection of serum antibodies to brucellosis and echinococcosis.

PeerJ·2026
Same journal

<i>In vitro</i> and <i>in vivo</i> effects of fungicides on angular leaf spot pathogen (<i>Pseudocercospora griseola</i> f. <i>griseola</i>) and common bean.

PeerJ·2026
Same journal

Micro-computed tomography of termite gut anatomy: effects of staining regime on resolvability.

PeerJ·2026
Same journal

Application of machine learning algorithms in building health diagnostics: predictive analytics evaluating indoor air quality and sick building syndrome in educational settings.

PeerJ·2026

相关实验视频

Updated: May 13, 2025

LDL Cholesterol Uptake Assay Using Live Cell Imaging Analysis with Cell Health Monitoring
08:45

LDL Cholesterol Uptake Assay Using Live Cell Imaging Analysis with Cell Health Monitoring

Published on: November 17, 2018

13.2K

基于机器学习的LDL胆固醇预测:性能评估和验证.

Jing-Bi Meng1, Zai-Jian An2, Chun-Shan Jiang2

  • 1Central Laboratory, Yanbian University Hospital, Yanji, Jilin Province, China.

PeerJ
|April 14, 2025
PubMed
概括

机器学习模型提供比传统公式更准确的低密度脂蛋白胆固醇 (LDL-C) 预测,特别是对于高甘油三的人来说. 这一进步有助于更好的心血管风险评估和治疗决策.

科学领域:

  • 生物化学和临床化学
  • 医疗保健中的人工智能
  • 心血管疾病风险预测预测

背景情况:

  • 估计低密度脂蛋白胆固醇 (LDL-C) 的传统公式存在局限性,特别是在患有高甘油三血症的患者中.
  • 准确的LDL-C测量对于心血管风险评估和管理至关重要.

研究的目的:

  • 验证和优化机器学习 (ML) 算法,以准确预测LDL-C.
  • 将各种ML模型的性能与已建立的LDL-C计算方法进行比较.

主要方法:

  • 对比多个ML模型 (随机森林,XGB,MLP等) 和传统配方 (弗里德沃尔德,马丁,桑普森) 使用超过12万名受试者的脂质资料.
  • 使用R平方 (R2),平均平方误差 (MSE) 和皮尔森相关系数 (PCC) 评估预测准确度.

主要成果:

  • 在LDL-C预测方面,ML模型显著优于传统公式.
  • 随机森林和XGBoost模型实现了最高的准确性 (R2 = 0.94).
  • 与传统方法不同,ML模型在所有甘油三水平上保持了高准确度.

结论:

  • 机器学习算法为LDL-C估计提供了卓越的准确性,特别是在具有挑战性的病例中,如高甘油三血症.
关键词:
脂质 脂质 脂质 是一种低密度脂蛋白胆固醇是低密度脂蛋白胆固醇的一种.机器学习就是机器学习.甘油三化物是一种三糖化物.

更多相关视频

Cell-free Biochemical Fluorometric Enzymatic Assay for High-throughput Measurement of Lipid Peroxidation in High Density Lipoprotein
07:29

Cell-free Biochemical Fluorometric Enzymatic Assay for High-throughput Measurement of Lipid Peroxidation in High Density Lipoprotein

Published on: October 12, 2017

9.2K
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

2.4K

相关实验视频

Last Updated: May 13, 2025

LDL Cholesterol Uptake Assay Using Live Cell Imaging Analysis with Cell Health Monitoring
08:45

LDL Cholesterol Uptake Assay Using Live Cell Imaging Analysis with Cell Health Monitoring

Published on: November 17, 2018

13.2K
Cell-free Biochemical Fluorometric Enzymatic Assay for High-throughput Measurement of Lipid Peroxidation in High Density Lipoprotein
07:29

Cell-free Biochemical Fluorometric Enzymatic Assay for High-throughput Measurement of Lipid Peroxidation in High Density Lipoprotein

Published on: October 12, 2017

9.2K
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

2.4K
  • 使用ML改善的LDL-C预测可以增强心血管风险分层和个性化治疗策略.
  • 这些先进的模型有可能通过更明智的临床决策来改善患者的治疗结果.