In the last decades, the worldwide growth and adoption of eHealth solutions has impacted life expectancy and improved quality of life, especially of people living in developed countries. One key common feature of all those novel eHealth solutions is telemonitoring, which makes possible to remotely assess health status and quality of life of individuals. Telemonitoring systems usually acquire heterogeneous data coming from sensors (physiological, biometric, environmental; wearable, non-invasive, adaptive and transparent to user) and other sources (e.g., interaction with the user through digital services). By analyzing those data, systems become aware of user context and are able to automatically infer user's behavior as well as detect anomalies. In that way, they provide elaborated and smart knowledge to clinicians, therapists, carers, families, and the patients themselves. In this paper, we present a solution aimed at automatically assessing quality of life of people. The goal is twofold: to provide support to people in need of assistance and to inform therapists, carers and families about the improvement/worsening of quality of life of monitored people. The paper presents first experiments that have been performed in Barcelona to automatically assess MOBILITY, SLEEPING and MOOD of a body-abled user. Since results show that the approach is effective in that scenario, the system has been then installed and it is currently running at three homes of people with severe disabilities.