EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Machine learning-based prediction of LDL cholesterol: performance evaluation and validation

Jing-Bi Meng, Zai-Jian An, Chun-Shan Jiang

PeerJ · 2025

DOI: 10.7717/peerj.19248 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift PeerJ, 2025. Verfasst von Jing-Bi Meng und 2 weiteren Autor:innen. Beteiligte Einrichtung: Central Laboratory, Yanbian University Hospital, Yanji, Jilin Province, China. Hauptthemen laut MEDLINE: Machine Learning, Cholesterol, LDL. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study aimed to validate and optimize a machine learning algorithm for accurately predicting low-density lipoprotein cholesterol (LDL-C) levels, addressing limitations of traditional formulas, particularly in hypertriglyceridemia.

Methods

Various machine learning models—linear regression, K-nearest neighbors (KNN), decision tree, random forest, eXtreme Gradient Boosting (XGB), and multilayer perceptron (MLP) regressor—were compared to conventional formulas (Friedewald, Martin, and Sampson) using lipid profiles from 120,174 subjects (2020–2023). Predictive performance was evaluated using R-squared ( R 2 ), mean squared error (MSE), and Pearson correlation coefficient (PCC) against measured LDL-C values.

Results

Machine learning models outperformed traditional methods, with Random Forest and XGB achieving the highest accuracy ( R 2 = 0.94, MSE = 89.25) on the internal dataset. Among the traditional formulas, the Sampson method performed best but showed reduced accuracy in high triglyceride (TG) groups (TG > 300 mg/dL). Machine learning models maintained high predictive power across all TG levels.

Conclusion

Machine learning models offer more accurate LDL-C estimates, especially in high TG contexts where traditional formulas are less reliable. These models could enhance cardiovascular risk assessment by providing more precise LDL-C estimates, potentially leading to more informed treatment decisions and improved patient outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningCholesterol, LDLHumansFemaleMaleMiddle AgedTriglyceridesAdultAlgorithmsAgedHypertriglyceridemiaRisk Assessment

Stichwörter der Autor:innen

LipidsLow-density lipoprotein cholesterolMachinie learningTriglyceride

Substanzen

Cholesterol, LDLTriglycerides

Autor:innen und Institutionen

  • Central Laboratory, Yanbian University Hospital, Yanji, Jilin Province, China.
  • Department of Clinical Laboratory, Yanbian University Hospital, Yanji, Jilin Province, China.

Zitieren

APA

Meng, J. B., An, Z. J., & Jiang, C. S. (2025). Machine learning-based prediction of LDL cholesterol: performance evaluation and validation. PeerJ. https://doi.org/10.7717/peerj.19248

Vancouver

Meng JB, An ZJ, Jiang CS. Machine learning-based prediction of LDL cholesterol: performance evaluation and validation. PeerJ. 2025. doi:10.7717/peerj.19248

BibTeX
@article{Meng2025,
  author = {Meng, Jing-Bi and An, Zai-Jian and Jiang, Chun-Shan},
  title = {Machine learning-based prediction of LDL cholesterol: performance evaluation and validation},
  journal = {PeerJ},
  year = {2025},
  doi = {10.7717/peerj.19248}
}
Kostenlos starten →