The current existence of massive data has not proved to be sufficient, by itself, for the quality of decision-making in organizations that provide health services. Thus, decision support systems (DSS) have a high strategic potential. However, initiatives focusing on the implementation of such systems commonly frustrate the involved professionals, precisely because of the challenges at data-collection stage. In this context, here we propose a conceptual model of DSS, prioritizing pipelines composed of simple algorithms, presenting low resource consumption for implementation. Our experimental implementation confirmed the computational characteristics preconized by the conceptual model, presenting the potential to mitigate a series of critical points reported by other authors and that negatively impact the real-world implementation of DSSs. Future work should empirically quantify the gains that the implementation of our model can yield, as well as experimentally explore its implementation for more complex organizational scenarios.