Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Blood Studies for Cardiovascular System III: Serum Lipid Profile01:25

Blood Studies for Cardiovascular System III: Serum Lipid Profile

326
Understanding serum lipids is crucial for maintaining cardiovascular health and preventing heart disease and stroke.
Serum lipids are fats and fatty substances in the blood and are crucial for various bodily functions, including energy storage, cellular structure, and hormone production. Serum lipids consist of cholesterol, triglycerides, and phospholipids.
Cholesterol is a soft, fat-like substance found in all body cells. It is crucial for producing hormones, vitamin D, and substances that aid...
326
Lipid-Lowering Drugs: Statins and Miscellaneous Agents01:20

Lipid-Lowering Drugs: Statins and Miscellaneous Agents

932
Hyperlipidemia, a medical condition often referred to as high cholesterol, is characterized by abnormally elevated levels of lipids in the bloodstream. When present in excess, these lipids, specifically cholesterol and triglycerides, can lead to serious health complications, often involving cardiovascular diseases. Illnesses like atherosclerosis, heart attacks, and pancreatitis have all been linked to untreated hyperlipidemia. This means controlling and regulating cholesterol and triglyceride...
932
Cholesterol: Significance and Regulation01:29

Cholesterol: Significance and Regulation

731
Although not a source of energy, cholesterol plays a significant role as a foundational structure for bile salts, steroid hormones, and vitamin D, as well as being a crucial component of plasma membranes. Approximately 15% of blood cholesterol is derived from our diet, with the remainder synthesized from acetyl CoA by the liver and intestines. Cholesterol is eliminated from the body through its conversion into bile salts, which are eventually discarded in the feces.
Considering cholesterol and...
731
Coronary Artery Disease IV: Preventive Measures01:26

Coronary Artery Disease IV: Preventive Measures

188
Effective preventive measures for coronary artery disease (CAD) focus on controlling modifiable risk factors, including cholesterol abnormalities and lifestyle changes.Cholesterol ManagementFirst, the Mediterranean diet and the American Heart Association advocate for maintaining low-density lipoprotein (LDL) cholesterol levels below 100 mg/dL, with a more stringent recommendation of below 70 mg/dL for individuals at high risk. LDL cholesterol, often termed "bad cholesterol," can lead to the...
188
Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration01:28

Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration

10
Glomerular filtration rate (GFR) can be estimated from serum creatinine using the modification of diet in renal disease (MDRD) formula or the chronic kidney disease–epidemiology collaboration (CKD–EPI) equation. Both methods are widely used in clinical practice to assess kidney function and guide treatment decisions.The MDRD equation does not require weight or height measurements and is normalized to the body surface area of 1.73 m², considered the average adult surface area.
10

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Contemporary Clinical Practices in Korean Patients With Coronary Chronic Total Occlusion: Results From the K-CTO Nationwide Retrospective Registry.

Korean circulation journal·2026
Same author

The medical impact of emergent banning of N-nitrosodimethylamine: contaminated antihypertensive drug.

The Korean journal of internal medicine·2026
Same author

High-urgency heart transplantation and outcome trade-offs: early post-transplant infection and mortality.

ESC heart failure·2026
Same author

Efficacy and Safety Profile of a Triple Single-Pill Combination of Valsartan/Amlodipine/Chlorthalidone in Patients with Uncontrolled Hypertension.

Clinical therapeutics·2026
Same author

Efficacy and Safety of Fimasartan/Indapamide Combination Therapy versus Fimasartan Monotherapy in Patients with Essential Hypertension Inadequately Responding to Fimasartan 30 mg (FINEDUO): A Randomized, Double-Blind, Multicenter, Phase III Study.

Drug design, development and therapy·2026
Same author

Coronary Computed Tomographic Angiography Versus Functional Testing in Patients With Newly Diagnosed Type 2 Diabetes and Suspected Coronary Artery Disease: Real-world Evidence from the Nationwide Cohort.

Korean circulation journal·2026

Related Experiment Video

Updated: Oct 5, 2025

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

2.8K

Estimation of low-density lipoprotein cholesterol levels using machine learning.

Gyu Chul Oh1, Taehoon Ko2, Jin-Hyu Kim3

  • 1Department of Cardiology, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea.

International Journal of Cardiology
|January 22, 2022
PubMed
Summary

Machine learning models accurately estimate low-density lipoprotein-cholesterol (LDL-C), outperforming traditional equations, especially for high triglycerides. This advancement offers a more precise method for dyslipidemia management.

Keywords:
Cost-effectivenessHypercholesterolemiaLow-density lipoprotein cholesterolMachine-learningTriglycerides

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Differential Effects of Lipid-lowering Drugs in Modulating Morphology of Cholesterol Particles
09:15

Differential Effects of Lipid-lowering Drugs in Modulating Morphology of Cholesterol Particles

Published on: November 10, 2017

14.8K

Related Experiment Videos

Last Updated: Oct 5, 2025

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

2.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Differential Effects of Lipid-lowering Drugs in Modulating Morphology of Cholesterol Particles
09:15

Differential Effects of Lipid-lowering Drugs in Modulating Morphology of Cholesterol Particles

Published on: November 10, 2017

14.8K

Area of Science:

  • Cardiovascular Medicine
  • Biomedical Informatics
  • Computational Biology

Background:

  • Low-density lipoprotein-cholesterol (LDL-C) is a critical biomarker for dyslipidemia management.
  • The Friedewald equation, commonly used for LDL-C estimation, exhibits inaccuracies, particularly with elevated triglycerides or non-fasting samples.
  • Accurate LDL-C measurement is essential for effective cardiovascular risk stratification and treatment decisions.

Purpose of the Study:

  • To develop and validate novel machine learning (ML) algorithms for estimating LDL-C.
  • To compare the performance of ML-based LDL-C estimation against conventional methods like the Friedewald and Martin equations.
  • To assess the accuracy of ML models across diverse patient populations, including those with high triglyceride levels.

Main Methods:

  • Utilized a large electronic health record database comprising over 1 million lipid profiles and direct LDL-C measurements.
  • Developed ML algorithms, including gradient boosting (LDL-CX) and neural networks (LDL-CN), using standard lipid profiles and patient characteristics.
  • Trained and validated models on a substantial subset of the data (823,657 tests).

Main Results:

  • ML algorithms (LDL-CX and LDL-CN) demonstrated superior correlation with directly measured LDL-C (r = 0.9662, 0.9668) compared to Friedewald (r = 0.9563) and Martin (r = 0.9585) equations.
  • LDL-CX and LDL-CN exhibited significantly smaller bias (-0.27 mg/dL and -0.01 mg/dL, respectively) than Friedewald (-3.80 mg/dL) and Martin (-2.00 mg/dL) equations.
  • The improved accuracy of ML models was particularly pronounced in patients with high triglyceride levels.

Conclusions:

  • Machine learning algorithms provide a more accurate estimation of LDL-C than conventional Friedewald and Martin equations.
  • ML-based LDL-C estimation holds potential for integration into electronic health records, enhancing clinical decision-making.
  • Further external validation and refinement could establish ML as a reliable substitute for direct LDL-C measurement in routine practice.