The severe or prolonged exposure to stress-inducing factors in occupational and academic settings is a growing concern. The literature describes several potentially stressful moments experienced by medical students throughout the course, affecting cognitive functioning and learning. In this paper, we introduce the EUSTRESS Solution, that aims to create an Information System to monitor and assess, continuously and in real-time, the stress levels of the individuals in order to predict chronic stress. The Information System will use a measuring instrument based on wearable devices and machine learning techniques to collect and process stress-related data from the individual without his explicit interaction. A big database has been built through physiological, psychological, and behavioral assessments of medical students. In this paper, we focus on heart rate and heart rate variability indices, by comparing baseline and stress condition. In order to develop a predictive model of stress, we performed different statistical tests. Preliminary results showed the neural network had the better model fit. As future work, we will integrate salivary samples and self-report questionnaires in order to develop a more complex and intelligent model.