EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identifying Key Features Associated with Excessive Fructose Intake: A Machine Learning Analysis of a Mexican Cohort

Guadalupe Gutiérrez-Esparza iD, Mireya Martínez-García iD, María Del Carmen González Salazar, Luis M Amezcua-Guerra iD, Malinalli Brianza-Padilla iD, Tania Ramírez-delReal iD, Enrique Hernández-Lemus iD

Nutrients · 2025

DOI: 10.3390/nu17223623 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nutrients, 2025. Verfasst von Guadalupe Gutiérrez-Esparza und 6 weiteren Autor:innen. Beteiligte Einrichtung: "Researcher for Mexico" Program, Secretaría de Ciencia, Humanidades, Tecnología e Innovación (SECIHTI), Mexico City 03940, Mexico. Hauptthemen laut MEDLINE: Fructose, Machine Learning, Diet. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SECIHTI, Secretariat of Science, Humanities, Technology and Innovation (SECIHTI, México), Investigadores por México.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Excessive fructose intake has been linked to adverse metabolic outcomes, yet few studies have comprehensively described the clinical, behavioral, and nutritional patterns associated with different intake levels using machine learning.

Methods

In this study, unsupervised and supervised algorithms were applied to a healthy Mexican cohort to examine features related to high fructose consumption, defined as intake above 25 g per day.

Results

K-Means clustering identified three distinct profiles, with one subgroup showing less favorable anthropometric, biochemical, and behavioral characteristics. Supervised models, including Extreme Gradient Boosting, Random Forest, and Histogram-based Gradient Boosting, distinguished fructose intake levels with balanced accuracies around 80% and AUC up to 88.1%. Shapley Additive Explanations (SHAPs)-based interpretation highlighted body mass index, triglycerides, sleep duration, alcohol consumption, and anxiety indicators as features most consistently associated with high intake.

Conclusions

These findings emphasize the multifactorial nature of fructose consumption and illustrate the utility of machine learning for uncovering dietary and metabolic patterns that warrant further investigation and may guide future nutrition-focused strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FructoseMachine LearningDietHumansMexicoMaleFemaleAdultCohort StudiesMiddle AgedBody Mass IndexYoung AdultAlgorithmsCluster AnalysisTriglycerides

Stichwörter der Autor:innen

artificial sweetenerscluster analysisdietary sugarsfructosemachine learningnutritional statusrisk factors

Substanzen

FructoseTriglycerides

Autor:innen und Institutionen

  • "Researcher for Mexico" Program, Secretaría de Ciencia, Humanidades, Tecnología e Innovación (SECIHTI), Mexico City 03940, Mexico.
  • Diagnostic and Treatment Services, Instituto Nacional de Cardiología Ignacio Chávez, Mexico City 14080, Mexico.
  • Department of Immunology, Instituto Nacional de Cardiología Ignacio Chávez, Mexico City 14080, Mexico.
  • Dental Public Health Department, Division of Graduate Studies and Research, School of Dentistry, Universidad Nacional Autónoma de México, Mexico City 04510, Mexico.
  • Department of Nutrition, Ambulatory Care Services, Instituto Nacional de Cardiología Ignacio Chávez, Mexico City 14080, Mexico.
  • Centro de Investigación en Ciencias de Información Geoespacial, Aguascalientes 20313, Mexico.

ORCID-Profile: Guadalupe Gutiérrez-Esparza, Mireya Martínez-García, Luis M Amezcua-Guerra, Malinalli Brianza-Padilla, Tania Ramírez-delReal, Enrique Hernández-Lemus

Förderung

  • SECIHTI
  • Secretariat of Science, Humanities, Technology and Innovation (SECIHTI, México), Investigadores por México

Zitieren

APA

Gutiérrez-Esparza, G., Martínez-García, M., González Salazar, M. D. C., Amezcua-Guerra, L. M., Brianza-Padilla, M., Ramírez-delReal, T., & Hernández-Lemus, E. (2025). Identifying Key Features Associated with Excessive Fructose Intake: A Machine Learning Analysis of a Mexican Cohort. Nutrients. https://doi.org/10.3390/nu17223623

Vancouver

Gutiérrez-Esparza G, Martínez-García M, González Salazar MDC, Amezcua-Guerra LM, Brianza-Padilla M, Ramírez-delReal T, et al. Identifying Key Features Associated with Excessive Fructose Intake: A Machine Learning Analysis of a Mexican Cohort. Nutrients. 2025. doi:10.3390/nu17223623

BibTeX
@article{GutirrezEsparza2025,
  author = {Gutiérrez-Esparza, Guadalupe and Martínez-García, Mireya and González Salazar, María Del Carmen and Amezcua-Guerra, Luis M and Brianza-Padilla, Malinalli and Ramírez-delReal, Tania and Hernández-Lemus, Enrique},
  title = {Identifying Key Features Associated with Excessive Fructose Intake: A Machine Learning Analysis of a Mexican Cohort},
  journal = {Nutrients},
  year = {2025},
  doi = {10.3390/nu17223623}
}
Kostenlos starten →