Comparison of conventional formulas and machine learning models for estimating serum low-density lipoprotein cholesterol

常规公式与机器学习模型估计血清低密度脂蛋白胆固醇的比较

📚 期刊: Practical Laboratory Medicine 📅 发表: 2026-03-10 🔬 PMID: 41853761 🔗 DOI: 10.1016/j.plabm.2026.e00524 👁️ 浏览: 42

👤 作者: Rashid Al Dhuhli, Noureldin Al Riyami, Fatma Al Farsi, Ahmed Al Khamyasi, Hamza Al Saadi, Said Al Alawi, Qasim Alfarai, Hasan Zidoum, Fatma Alsalmani, Yaqoot Almarshodi, Fatma Zadjali

血脂

📑 引用格式

APA Vancouver 国标 GB/T 7714 BibTeX RIS

Rashid Al Dhuhli, Noureldin Al Riyami, Fatma Al Farsi, Ahmed Al Khamyasi, Hamza Al Saadi, Said Al Alawi, Qasim Alfarai, Hasan Zidoum, Fatma Alsalmani, Yaqoot Almarshodi, Fatma Zadjali (2026). Comparison of conventional formulas and machine learning models for estimating serum low-density lipoprotein cholesterol. Practical Laboratory Medicine. https://doi.org/10.1016/j.plabm.2026.e00524

🔗 分享文献

📝 摘要

准确估计低密度脂蛋白胆固醇（LDL-C）对于心血管风险评估和监测至关重要。由于β定量法操作繁琐且不适用于常规使用，已开发了多种方程来估计LDL-C浓度。然而，在甘油三酯水平升高、低LDL-C或非空腹样本等临床条件下，传统方程的性能可能下降。本研究比较了常规估计公式（Friedewald、Martin-Hopkins和Sampson-Nielsen公式）与机器学习模型在估计血清LDL-C方面的性能。研究使用了一个大型临床实验室数据库，涵盖了广泛的脂质谱特征。结果显示，机器学习模型在广泛的临床条件下均优于传统方程，特别是在甘油三酯升高和低LDL-C水平的情况下。机器学习方法通过利用多种脂质参数之间的非线性关系，提供了更准确的LDL-C估计，有望改善基于脂质的心血管风险分层，特别是在传统公式准确性有限的临床场景中。

📝 阅读笔记

📄 相关文献

← 返回血脂查看原文 →

Comparison of conventional formulas and machine learning models for estimating serum low-density lipoprotein cholesterol

📑 引用格式

🔗 分享文献

📝 摘要

📝 阅读笔记

📄 相关文献

Hypertriglyceridemia Does Not Worsen Thoracic Aortic Aneurysm and Dissection in ...

A 35-Year-Old Woman With Recurrent Hypertriglyceridemia-Induced Pancreatitis in ...

Upper Arm to Upper Leg Length Ratio and Dyslipidemia: A Novel Application of a F...

[A case of acetaminophen-induced cholestatic liver injury accompanying severe hy...

Cystine: A Key Protective Factor Against Childhood Hypo-HDL Cholesterolemia and ...

[Influenza virus infection affects the efficacy of the treatment of dyslipidemia...