Big data analytic tools can significantly improve clinical decisions, yet they are difficult to use at the point of care. A big data tool should show strong predictive power to be useful at the point of care, as well as harmoniously integrate within the clinical processes. In this paper we report on a prediction tool for CHF patients' readmission or death, and show its strength. We chose the WST and the WSLC as the theory underlying the design and implementation processes aimed at bringing such a tool to the point of care. In future research, we will further improve our prediction tool by adding classification algorithms, and elaborate on relationships among the WST elements, for the WS to be in harmony. We hypothesize that the methods employed for the tool development and the lessons derived from the WST adaptation would be generalizable to similar medical clinics.