Scientific studies have shown a high incidence of depression worldwide and its co-occurrence with several important medical conditions. In this scenario of multimorbidities, Major Depressive Disorder (MDD) is commonly associated with diseases related to the metabolic syndrome, such as obesity and diabetes. Chronic changes in the circadian rhythm of sleep-wake are related with the development of depression and its associated comorbidities, by favoring the breakdown of the internal temporal organization of essential physiological and metabolic processes. Currently, making diagnoses and making accurate clinical screenings have been a persistent challenge in the area of mental health, due to the use of traditional limiting tools that do not project additional characteristics of important clinical data of the patient, including objective observations of disease biomarkers in this practice. Thus, the objective of this project is to assess the potential of variables related to the chronobiological risk and comorbidities such as excessive daytime sleepiness, obesity and diabetes in predicting MDD and mild to moderate symptoms of depression, focusing on the development of predictive models using a machine learning approach.