Comparing a novel machine learning method to the Friedewald formula and Martin-Hopkins equation for low-density lipoprotein estimation
- PMID: 32997716
- PMCID: PMC7526877
- DOI: 10.1371/journal.pone.0239934
Comparing a novel machine learning method to the Friedewald formula and Martin-Hopkins equation for low-density lipoprotein estimation
Abstract
Background: Low-density lipoprotein cholesterol (LDL-C) is a target for cardiovascular prevention. Contemporary equations for LDL-C estimation have limited accuracy in certain scenarios (high triglycerides [TG], very low LDL-C).
Objectives: We derived a novel method for LDL-C estimation from the standard lipid profile using a machine learning (ML) approach utilizing random forests (the Weill Cornell model). We compared its correlation to direct LDL-C with the Friedewald and Martin-Hopkins equations for LDL-C estimation.
Methods: The study cohort comprised a convenience sample of standard lipid profile measurements (with the directly measured components of total cholesterol [TC], high-density lipoprotein cholesterol [HDL-C], and TG) as well as chemical-based direct LDL-C performed on the same day at the New York-Presbyterian Hospital/Weill Cornell Medicine (NYP-WCM). Subsequently, an ML algorithm was used to construct a model for LDL-C estimation. Results are reported on the held-out test set, with correlation coefficients and absolute residuals used to assess model performance.
Results: Between 2005 and 2019, there were 17,500 lipid profiles performed on 10,936 unique individuals (4,456 females; 40.8%) aged 1 to 103. Correlation coefficients between estimated and measured LDL-C values were 0.982 for the Weill Cornell model, compared to 0.950 for Friedewald and 0.962 for the Martin-Hopkins method. The Weill Cornell model was consistently better across subgroups stratified by LDL-C and TG values, including TG >500 and LDL-C <70.
Conclusions: An ML model was found to have a better correlation with direct LDL-C than either the Friedewald formula or Martin-Hopkins equation, including in the setting of elevated TG and very low LDL-C.
Conflict of interest statement
Gurpreet Singh became affiliated with GlaxoSmithKline after working on this project. Benjamin C. Lee receives consulting fees from Cleerly Inc, but has not receive that consulting fee since 2019. Leslee J. Shaw reports having an equity interest in Cleerly Inc. There are no patents, products in development or marketed products associated with this research to declare This does not alter our adherence to PLOS ONE policies on sharing data and materials.
Figures
![Fig 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7526877/bin/pone.0239934.g001.gif)
![Fig 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7526877/bin/pone.0239934.g002.gif)
![Fig 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7526877/bin/pone.0239934.g003.gif)
Similar articles
-
Best practice for LDL-cholesterol: when and how to calculate.J Clin Pathol. 2023 Mar;76(3):145-152. doi: 10.1136/jcp-2022-208480. Epub 2023 Jan 17. J Clin Pathol. 2023. PMID: 36650044 Review.
-
Comparison of Methods to Estimate Low-Density Lipoprotein Cholesterol in Patients With High Triglyceride Levels.JAMA Netw Open. 2021 Oct 1;4(10):e2128817. doi: 10.1001/jamanetworkopen.2021.28817. JAMA Netw Open. 2021. PMID: 34709388 Free PMC article.
-
Comparability of 11 different equations for estimating LDL cholesterol on different analysers.Clin Chem Lab Med. 2021 Aug 12;59(12):1930-1943. doi: 10.1515/cclm-2021-0747. Print 2021 Nov 25. Clin Chem Lab Med. 2021. PMID: 34384146
-
Comparison of Low-Density Lipoprotein Cholesterol Assessment by Martin/Hopkins Estimation, Friedewald Estimation, and Preparative Ultracentrifugation: Insights From the FOURIER Trial.JAMA Cardiol. 2018 Aug 1;3(8):749-753. doi: 10.1001/jamacardio.2018.1533. JAMA Cardiol. 2018. PMID: 29898218 Free PMC article.
-
Targeting low HDL-cholesterol to decrease residual cardiovascular risk in the managed care setting.J Manag Care Pharm. 2008 Oct;14(8 Suppl):S3-28; quiz S30-1. J Manag Care Pharm. 2008. PMID: 19891279 Review.
Cited by
-
Applicability of Artificial Intelligence in the Field of Clinical Lipidology: A Narrative Review.J Lipid Atheroscler. 2024 May;13(2):111-121. doi: 10.12997/jla.2024.13.2.111. Epub 2024 Feb 27. J Lipid Atheroscler. 2024. PMID: 38826186 Free PMC article. Review.
-
A new equation for estimating low-density lipoprotein cholesterol concentration based on machine learning.Medicine (Baltimore). 2024 Apr 12;103(15):e37766. doi: 10.1097/MD.0000000000037766. Medicine (Baltimore). 2024. PMID: 38608093 Free PMC article.
-
Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review.Front Med (Lausanne). 2023 Oct 2;10:1227168. doi: 10.3389/fmed.2023.1227168. eCollection 2023. Front Med (Lausanne). 2023. PMID: 37849490 Free PMC article.
-
Comparison of Newly Proposed LDL-Cholesterol Estimation Equations.J Korean Med Sci. 2023 May 15;38(19):e145. doi: 10.3346/jkms.2023.38.e145. J Korean Med Sci. 2023. PMID: 37191848 Free PMC article.
-
The Impact of Low-Density Lipoprotein Equation Changes on Cholesterol Treatment in Canada.CJC Open. 2022 Oct 1;5(1):37-42. doi: 10.1016/j.cjco.2022.09.007. eCollection 2023 Jan. CJC Open. 2022. PMID: 36700190 Free PMC article.
References
-
- Ference Brian A., Ginsberg Henry N., Graham Ian, Ray Kausik K., Packard EB Chris J. et al. Low-density lipoproteins cause atherosclerotic cardiovascular disease. 1. Evidence from genetic, epidemiologic, and clinical studies. A consensus statement from the European Atherosclerosis Society Consensus Panel | European Heart Journal | Oxford Academi. Eur Heart J [Internet]. 2017. [cited 2020 Mar 12];38(32):2459–72. Available from: 10.1093/eurheartj/ehx144 - DOI - PMC - PubMed
-
- Benjamin EJ, Blaha MJ, Chiuve SE, Cushman M, Das SR, Deo R, et al. Heart Disease and Stroke Statistics—2017 Update: A Report From the American Heart Association. Circulation [Internet]. 2017. March 7 [cited 2020 Mar 9];135(10):e146–603. Available from: https://www.ahajournals.org/doi/10.1161/CIR.0000000000000485 - DOI - PMC - PubMed
-
- Smith S, Benjamin E, … RB-J of the, 2011 undefined. AHA/ACCF secondary prevention and risk reduction therapy for patients with coronary and other atherosclerotic vascular disease: 2011 update: a guideline from the. onlinejacc.org [Internet]. [cited 2020 Mar 12]; Available from: http://www.onlinejacc.org/content/58/23/2432.abstract
-
- Vallejo-Vaz AJ, Robertson M, Catapano AL, Watts GF, Kastelein JJ, Packard CJ, et al. LDL-Cholesterol Lowering for the Primary Prevention of Cardiovascular Disease Among Men with Primary Elevations of LDL-Cholesterol Levels of 190 mg/dL or Above: Analyses from the WOSCOPS 5-year Randomised Trial and 20-year Observational Follow-Up. Circulation [Internet]. 2017. [cited 2020 Mar 12];136(20):CIRCULATIONAHA.117.027966. Available from: http://circ.ahajournals.org/lookup/doi/10.1161/CIRCULATIONAHA.117.027966 - DOI - PubMed
-
- Anderson TJ, Grégoire J, Pearson GJ, Barry AR, Couture P, Dawes M, et al. 2016. Canadian Cardiovascular Society Guidelines for the Management of Dyslipidemia for the Prevention of Cardiovascular Disease in the Adult. Can J Cardiol. 2016. November 1;32(11):1263–82. 10.1016/j.cjca.2016.07.510 - DOI - PubMed
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Medical
Miscellaneous