clinical informatics

Research spanning multiple areas of interest in clinical informatics.

We present a novel approach to temporal clustering of patient treatment information based on the semantic similarity of longitudinal histories.

We looked at registry-based data on breast cancer care at two neighboring healthcare institutions with a specific focus on whether organizational boundaries determine the physicians that a patient will see. From an initial patient-oriented data set, we developed a social network of physicians, modeling their interactions over the course of the provided treatments.

To determine whether anomaly-driven approaches to discovery produce more accurate models than the standard approaches, we built a program called Kalpana. We also used Kalpana to explore means for identifying those anomaly resolutions that are acceptable to domain experts.