Document Type

Article

Source of Publication

Frontiers in Nutrition

Publication Date

7-18-2025

Abstract

Background: Obesity and underweight are increasingly common among young adult women, often resulting from complex interactions between diet, lifestyle, and socioeconomic factors. This study addresses that gap by applying machine learning to a wide range of behavioral, dietary, and demographic data. The main research question asks: What are the key factors influencing weight status among female university students, and how accurately can machine learning models identify them? We hypothesize that different factors are significantly associated with underweight, overweight, and obesity, and that machine learning can reliably detect these patterns. The aim is to identify the strongest predictors and support more targeted weight management strategies. Methods: This cross-sectional study analyzed data from 7,092 female university students (aged 18–30 years) in Palestine and the UAE. Sociodemographic, dietary, and lifestyle predictors were evaluated using machine learning (Random Forest, SVM, logistic regression, gradient boosting, decision trees, and ensemble methods). Synthetic Minority Over-sampling (SMOTE) addressed class imbalance. Model performance was assessed via 10-fold cross-validation, with significance determined by the chi-square test (p <  0.05, 95% CI). Results: The Random Forest model achieved the highest accuracy (obesity: 96.8%, underweight: 94.6%, overweight: 90.3%) and AUC (0.95–0.97). The main drivers of weight status categories were as follows: underweight was associated with low water/milk intake and preference for fast food; overweight with added oil, large eating quantity, and low physical activity; and obesity with energy drink consumption, salty snacks, and irregular meals. All findings were statistically significant (p <  0.001). Socio-demographic factors (e.g., low income and marital status) and lifestyle habits (e.g., sleep < 5 h and fast eating) were also significantly related to weight status. Conclusion: The integration of these findings into weight management frameworks can significantly enhance the detection and understanding of modifiable determinants, thereby informing public health interventions, guiding the development of targeted weight management strategies, and contributing to the global movement toward healthier bodies.

ISSN

2296-861X

Publisher

Frontiers Media SA

Volume

12

Disciplines

Computer Sciences | Medicine and Health Sciences

Keywords

body mass index, dietary patterns, lifestyle behaviors, machine learning, obesity, weight management

Scopus ID

105012301717

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Gold: This publication is openly available in an open access journal/series

Download

Share

COinS