Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 16, 2026

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

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

Published on: October 12, 2017

Development and Validation of a Simplified Martin-Hopkins LDL-C Equation Using Machine Learning.

Jihwan Park¹, Leon Fan², Mark A Marzinke³

¹Welch Center for Prevention, Epidemiology and Clinical Research, Johns Hopkins University Bloomberg School of Public Health, Baltimore, Maryland.

JAMA Cardiology

|July 15, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

A High Granularity Machine Learning Model to Predict Successful Weaning During V-V ECMO.

Artificial organs·2026

Same author

Comparative outcomes of proton and photon therapy in the management of malignant peripheral nerve sheath tumors.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026

Same author

Psychological Factors Applicable to App Development for Overcoming Problematic Smartphone Use: A Structural Equation Modeling Approach.

Psychiatry investigation·2026

Same author

Elevated CSF Beta Trace Protein Levels in Patients with CSF-Venous Fistulas.

AJNR. American journal of neuroradiology·2026

Same author

A Co-opted Developmental Gene Regulatory Program in Endothelial Progenitors Promotes Tumor Angiogenic Phenotypes.

Cancer research·2026

Same author

Microcirculation and Cerebrovascular Autoregulation in Patients With Mechanical Circulatory Support Devices.

Journal of stroke·2026

A new machine learning equation for estimating low-density lipoprotein cholesterol (LDL-C) provides results comparable to the established Martin-Hopkins method. This simplified equation streamlines implementation and broadens adoption for clinical care.

Area of Science:

Cardiovascular Medicine
Biochemistry
Data Science in Healthcare

Background:

The Martin-Hopkins equation is a validated method for estimating low-density lipoprotein cholesterol (LDL-C).
A simplified equation could improve clinical implementation and adoption.
Existing equations like Friedewald, Sampson-NIH, and Modified Sampson have limitations in accuracy.

Purpose of the Study:

To develop a simplified machine learning-based alternative to the Martin-Hopkins equation for LDL-C estimation.
To compare the performance of the new equation (LDL-C-MH-MARS) against established methods: Friedewald (LDL-C-F), Sampson-NIH (LDL-C-S), Modified Sampson (LDL-C-MS), and Martin-Hopkins (LDL-C-MH).

Main Methods:

Utilized the Very Large Database of Lipids, a large cross-sectional dataset of lipid measurements.

More Related Videos

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

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

Published on: November 17, 2018

Related Experiment Videos

Last Updated: Jul 16, 2026

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

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

Published on: October 12, 2017

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

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

Published on: November 17, 2018

Developed a machine learning model using multivariate adaptive regression splines (MARS) to create the LDL-C-MH-MARS equation.

Validated the equation against ultracentrifugation-based LDL-C measurements in internal and external datasets (Mayo Clinic, FOURIER trial).

Main Results:

The LDL-C-MH-MARS equation demonstrated very low bias (-0.1 IQR: -2.1 to 1.8 mg/dL), comparable to the Martin-Hopkins equation.
LDL-C-MH-MARS had the smallest root mean square error (RMSE) at 4.7 mg/dL, closely followed by LDL-C-MH (4.9 mg/dL).
Classification accuracy was highest for LDL-C-MH-MARS (89.7%) and LDL-C-MH (89.6%), outperforming other equations.

Conclusions:

The developed machine learning-based LDL-C equation (LDL-C-MH-MARS) offers comparable accuracy to the Martin-Hopkins equation.
The simplified nature of LDL-C-MH-MARS facilitates easier implementation and wider clinical use.
This advancement holds relevance for improving lipid management and cardiovascular risk assessment.