Clinical pathways are widely adopted by many large hospitals around the world in order to provide high-quality patient treatment and reduce the length of hospital stay of each patient. The development of clinical pathways is a lengthy process, and may require the collaboration among physicians, nurses, and staffs in a hospital. However, the individual differences cause great variances in the execution of clinical pathways. It calls for a more dynamic and adaptive process to improve the performance of clinical pathways. This paper proposes a data mining technique to discover the time dependency pattern of clinical pathways for curing brain stroke. The mining of time dependency pattern is to discover patterns of process execution sequences and to identify the dependent relation between activities in a majority of cases. By obtaining the time dependency patterns, we can predict the paths for new patients when he/she is admitted into a hospital, and, in turn, the health care procedure will be more effective and efficient.