Dietary Habits and Psychological States during COVID-19 Home Isolation in Italian College Students: The Role of Physical Exercise

Abstract

Social isolation has adverse effects on mental health, physical exercise, and dietary habits. This longitudinal observational study aimed to investigate the effects of mood states and exercise on nutritional choices, on 176 college students (92 males, 84 females; 23 ± 4 years old) during the COVID-19 lockdown. During 21 days, nutrition and exercise were daily monitored, and the mood states assessed. A factor analysis was used to reduce the number of nutritional variables collected. The relationships between exercise, mood and nutrition were investigated using a multivariate general linear model and a mediation model. Seven factors were found, reflecting different nutritional choices. Exercise was positively associated with fruit, vegetables and fish consumption (p = 0.004). Depression and quality of life were, directly and inversely, associated with cereals, legumes (p = 0.005; p = 0.004) and low-fat meat intake (p = 0.040; p = 0.004). Exercise mediated the effect of mood states on fruit, vegetables and fish consumption, respectively, accounting for 4.2% and 1.8% of the total variance. Poorer mood states possibly led to unhealthy dietary habits, which can themselves be linked to negative mood levels. Exercise led to healthier nutritional choices, and mediating the effects of mood states, it might represent a key measure in uncommon situations, such as home-confinement.

Keywords: diet; exercise; lifestyle; mood; quarantine; young adults.

Figure 1

Study timeframe.

Figure 2

Daily macronutrients (gr) and energy (kcal) intake, for male and female.

Figure 3

Factors possible explanations.

Figure 4

Interactions between Factors (dependent variables) and Body Mass Index (BMI), training load, and psychometric scales (PHQ-9, PANAS +, PANAS −, and SF-12). Green arrows show positive correlations, while red arrows negative correlations. Only significant interactions have been reported (p < 0.05).

Figure 5

The theoretical model of the mediating effect of training load on the relationship between psychological states and nutritional choices. Solid lines represent a direct effect (predictors on dependent, mediator on dependent), while dashed lines represent the mediation effect.

Figure 6

Plots of mediation, direct and total effects of training load on psychometric scales (PHQ-9, PANAS +, PANAS −, SF-12) for Factors 4 (fruit and fresh vegetables) and 6 (fish).