This poster describes a system to analyze self-monitoring data of gestational diabetic patients, for obtaining an assessment of their metabolic control with the final goal of supporting decision-making in therapy adjustment. The system is able to manage incomplete data and to make temporal reasoning under uncertainty, the two most important constraints when analyzing ambulatory monitoring data. Two different formalism have been used to represent and manage the knowledge: a dynamic Bayesian network and a production system based on rules. The outcomes provided by the whole system are: information on possible patient transgressions of the prescribed treatment and recommendations of treatment adjustments.