A method for automatic analysis of time-oriented clinical narratives would be of significant practical import for medical decision making, data modeling and biomedical research. This paper proposes a robust corpus-based approach for temporal analysis of medical discharge summaries. We characterize temporal organization of clinical narratives in terms of temporal segments and their ordering. We consider a temporal segment to be a fragment of text that does not exhibit abrupt changes in temporal focus. Our method derives temporal order based on a range of linguistic and contextual features that are integrated in a supervised machine-learning framework. Our learning method achieves 83% F-measure in tempo-ral segmentation, and 78.3% accuracy in inferring pairwise temporal relations.