EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting Metabolic Syndrome Using Supervised Machine Learning: A Multivariate Parameter Approach

Rodolfo Iván Valdez Vega iD, Jacqueline Alejandra Noboa-Velástegui iD, Ana Lilia Fletes-Rayas iD, Iñaki Álvarez, Martha Eloisa Ramos-Marquez iD, Sandra Luz Ruíz-Quezada iD, Nora Magdalena Torres-Carrillo iD, Rosa Elena Navarro-Hernández iD

International Journal of Molecular Sciences · 2025

DOI: 10.3390/ijms26209897 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2025. Verfasst von Rodolfo Iván Valdez Vega und 7 weiteren Autor:innen. Beteiligte Einrichtung: Programa de Doctorado en Ciencias Biomédicas, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara C.P. 44340, Jalis…. Hauptthemen laut MEDLINE: Metabolic Syndrome, Supervised Machine Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad de Guadalajara-ProSNI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metabolic syndrome (MetS) is a complex condition characterized by a group of interconnected metabolic abnormalities. Due to its increasing prevalence, better predictive markers are needed. Therefore, this study aims to develop predictive models for MetS by integrating adipokines, metabolic and cardiovascular risk factors, and anthropometric indices. Data were collected from 381 subjects aged 20 to 59 years (242 women and 139 men) from Guadalajara, Jalisco, Mexico, who were classified as having MetS or non-MetS based on the ATP-III criteria. Four supervised machine learning models were developed—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—and their performance was evaluated using the Area under the Curve (AUC), calibration curves, Decision Curve Analysis (DCA), and local interpretability analysis. The RF and XGBoost models achieved the highest AUCs (0.940 and 0.954). The RF and LR models were the best calibrated and showed the highest net benefit in DCA. Key variables included age, anthropometric indices (BRI and DAI), insulin resistance measures (HOMA-IR), lipid profiles (sdLDL-C and LDL-C), and high-molecular-weight adiponectin, used to classify the presence of MetS. The results highlight the usefulness of specific models and the importance of anthropometric variables, cardiovascular risk factors, metabolic profiles, and adiponectin as indicators of MetS.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Metabolic SyndromeSupervised Machine LearningHumansFemaleMaleAdultMiddle AgedYoung AdultRisk FactorsMexicoSupport Vector MachineBiomarkersInsulin ResistanceMachine Learning

Stichwörter der Autor:innen

body roundness indexhigh-molecular-weight adiponectinmachine learningmetabolic syndromesdLDL-C

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Programa de Doctorado en Ciencias Biomédicas, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara C.P. 44340, Jalisco, Mexico.
  • Departamento de Biología Celular, Fisiología e Inmunología, Institut de Biotecnologia i Biomedicina, Campus de Bellaterra, 08193 Bellaterra, Barcelona, Spain.
  • Departamento de Enfermería Aplicada, Instituto de Investigación en Enfermería y Salud Traslacional, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara C.P. 44340, Jalisco, Mexico.
  • Departamento de Biología Molecular, Instituto de Investigación en Enfermedades Crónico-Degenerativas, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara C.P. 44340, Jalisco, Mexico.
  • Departamento de Farmacobiología, Centro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Guadalajara C.P.44430, Jalisco, Mexico.
  • Departamento de Microbiología y Patología, Centro de Investigación de Enfermedades Infectocontagiosas, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Calle Sierra Mojada No. 950, Colonia Indep…

ORCID-Profile: Rodolfo Iván Valdez Vega, Jacqueline Alejandra Noboa-Velástegui, Ana Lilia Fletes-Rayas, Martha Eloisa Ramos-Marquez, Sandra Luz Ruíz-Quezada, Nora Magdalena Torres-Carrillo, Rosa Elena Navarro-Hernández

Förderung

  • Universidad de Guadalajara-ProSNI

Zitieren

APA

Valdez Vega, R. I., Noboa-Velástegui, J. A., Fletes-Rayas, A. L., Álvarez, I., Ramos-Marquez, M. E., Ruíz-Quezada, S. L., Torres-Carrillo, N. M., & Navarro-Hernández, R. E. (2025). Predicting Metabolic Syndrome Using Supervised Machine Learning: A Multivariate Parameter Approach. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms26209897

Vancouver

Valdez Vega RI, Noboa-Velástegui JA, Fletes-Rayas AL, Álvarez I, Ramos-Marquez ME, Ruíz-Quezada SL, et al. Predicting Metabolic Syndrome Using Supervised Machine Learning: A Multivariate Parameter Approach. International Journal of Molecular Sciences. 2025. doi:10.3390/ijms26209897

BibTeX
@article{ValdezVega2025,
  author = {Valdez Vega, Rodolfo Iván and Noboa-Velástegui, Jacqueline Alejandra and Fletes-Rayas, Ana Lilia and Álvarez, Iñaki and Ramos-Marquez, Martha Eloisa and Ruíz-Quezada, Sandra Luz and Torres-Carrillo, Nora Magdalena and Navarro-Hernández, Rosa Elena},
  title = {Predicting Metabolic Syndrome Using Supervised Machine Learning: A Multivariate Parameter Approach},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  doi = {10.3390/ijms26209897}
}
Kostenlos starten →