Temporal abstraction (TA) and dynamic Bayesian networks (DBNs) became two topics of much interest and research in clinical systems. TA is a knowledge-based process that abstracts raw temporal data into higher level interval-based concepts. TA techniques were utilized in various medical systems for summarizing and managing patient data. DBNs are temporal probabilistic graphical models that model temporal events and their causal and temporal dependencies. They model stochastic processes in discrete time and their state changes through time in a sequence of time slices. In this paper, we present an extended DBN model (‘DBN-extended’) that integrates TA methods with DBNs for the prognosis of the risk of coronary heart disease. More specifically, we demonstrate the derivation of TAs from data, which are used for building the network structure. We use machine learning algorithms to learn the parameters of the model through data. We apply the extended model to a longitudinal medical dataset and during the training and evaluation stages, we addressed the class imbalance problem on both training and testing datasets. Moreover, we compare the performance of a DBN-extended model to the performance of a DBN implemented without TAs. The results we obtain demonstrate the predictive accuracy of our model and the effectiveness of our proposed approach.