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

You might also read

Related Articles

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

Sort by
Same author

Mobile phone contamination among hospital staff: Focus on MRSA and ESBL-producing bacteria.

Journal of infection prevention·2026
Same author

Unsupervized clustering reveals a tri-phenotype model of hospitalized COVID-19 patients: Beirut cohort study and literature synthesis.

Digital health·2025
Same author

Impact of the COVID-19 pandemic on fasting blood glucose and HbA1c levels in Lebanon: An observational analysis by age and gender.

Medicine·2025
Same author

Translation, Validation, and Cross-Cultural Adaptation of an Arabic Version of the "Sleep Disturbances Scale for Children" (SDSC).

Behavioral sleep medicine·2025
Same author

Current Generics Utilization and Associated Savings in Saudi Arabia: Insights From a Private Claims Database.

Value in health regional issues·2025
Same author

Twice against thrice-weekly hemodialysis (TATH): a multicenter nonrandomized trial.

BMC nephrology·2025

Related Experiment Video

Updated: Sep 6, 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

2.7K

Prospective Validation of a Machine Learning Model for Low-Density Lipoprotein Cholesterol Estimation.

Jean Pierre Ghayad1, Vanda Barakett-Hamadé1,2,3, Ghassan Sleilaty3,4

  • 1Department of Laboratory Medicine, Hôtel-Dieu de France University Hospital, Beirut, Lebanon.

Laboratory Medicine
|June 28, 2022
PubMed
Summary

A machine learning algorithm (LDL-KNN) accurately estimates low-density lipoprotein cholesterol (LDL-C) across diverse patient groups. Further refinement is needed for very low LDL-C levels.

Keywords:
agreement studyclinical chemistrylow-density lipoprotein cholesterolmachine learningmethod validationtriglycerides

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Related Experiment Videos

Last Updated: Sep 6, 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

2.7K
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.2K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Area of Science:

  • Biomedical Informatics
  • Clinical Chemistry

Background:

  • Accurate low-density lipoprotein cholesterol (LDL-C) estimation is crucial for cardiovascular risk assessment.
  • Existing methods for LDL-C measurement can be costly and time-consuming.
  • Machine learning offers a potential avenue for improved LDL-C estimation.

Purpose of the Study:

  • To prospectively validate a previously developed machine learning algorithm, LDL-KNN, for estimating LDL-C.
  • To assess the performance of LDL-KNN across various demographic and clinical factors.

Main Methods:

  • A k-nearest neighbors (KNN) based machine learning algorithm (LDL-KNN) was evaluated.
  • Retrospective and prospective data from 31,853 and 6599 observations, respectively, were analyzed.
  • Agreement with direct LDL-C assays was assessed using intraclass correlation coefficient (ICC), considering age, sex, healthcare setting, and triglyceridemia.

Main Results:

  • LDL-KNN demonstrated strong agreement (ICC > 0.9) with direct LDL-C measurements across different ages, sexes, and disease statuses.
  • Satisfactory agreement was observed in patients with normal to mild hypertriglyceridemia.
  • Performance showed a slight decrease in severely hypertriglyceridemic patients and was lower for very low LDL-C observations.

Conclusions:

  • The LDL-KNN algorithm shows robust performance in estimating LDL-C across a wide range of patient characteristics.
  • Algorithm refinement is necessary to improve accuracy in cases of very low LDL-C.
  • Machine learning holds promise for efficient and accurate LDL-C estimation in clinical practice.