Rapid advances in information and sensor technology have led to the development of tools and methods for personalized health monitoring. These techniques support timely and efficient healthcare services by tracking the vital signs, detecting physiological changes and predicting health risks. In this paper, we propose an integrated system to monitor the wellness condition of elderly. This system is conceptualized to provide a computer-aided decision support for clinicians and community nurses, by means of which they can easily monitor and analyze an elderly’s overall activity and vital signs using a wearable wellness tacker and an all-in-one satiation based monitoring device, offering an efficient solution with a reduction in time cost and human error. We design a data-preparing scheme for acquiring data and processing data from multiple monitoring devices, and propose a personalized scheme for forecasting the elderly’s one-day-ahead wellness condition via data integration and statistical learning. We conduct a pilot study at a nursing home in Hong Kong to demonstrate the implementation of the proposed system. The proposed forecasting scheme is validated by the collected data.