Anthropometric, Nutritional, and Lifestyle Factors Involved in Predicting Food Addiction: An Agnostic Machine Learning Approach

Food addiction (FA) is an emerging psychiatric condition that presents behavioral and neurobiological similarities with other addictions, and its early identification is essential to prevent the development of more severe disorders. The aim of the present study was to determine the ability of anthropometric measures, eating habits, symptoms related to eating disorders (ED), and lifestyle features to predict the symptoms of food addiction. Methodology: A cross-sectional study was conducted in a sample of 702 university students (77.3% women; age: 22 ± 6 years). The Food Frequency Questionnaire (FFQ), the Yale Food Addiction Scale 2.0 (YFAS 2.0), the Eating Attitudes Test (EAT-26), anthropometric measurements, and a set of self-report questions on substance use, physical activity level, and other questions were administered. A total of 6.4% of participants presented symptoms compatible with food addiction, and 8.1% were at risk for ED. Additionally, 26.5% reported daily smoking, 70.6% consumed alcohol, 2.9% used illicit drugs, and 29.4% took medication; 35.3% did not engage in physical activity. Individuals with food addiction had higher BMI (<i>p</i> = 0.010), waist circumference (<i>p</i> = 0.001), and body fat (<i>p</i> < 0.001) values, and a higher risk of eating disorders (<i>p</i> = 0.010) compared to those without this condition. In the multivariate logistic model, non-dairy beverage consumption (such as coffee or alcohol), vitamin D deficiency, and waist circumference predicted food addiction symptoms (R²_Nagelkerke = 0.349). Indeed, the machine learning approaches confirmed the influence of these variables. Conclusions: The prediction models allowed an accurate prediction of FA in the university students; moreover, the individualized approach improved the identification of people with FA, involving complex dimensions of eating behavior, body composition, and potential nutritional deficits not previously studied.