Abstract: A computerized system and method for analyzing encounter data representing encounters between patients and health care providers to predict whether one or more of the patients may have an undiagnosed condition. This prediction can be made by a machine learning algorithm that determines a probability that an undiagnosed condition may be present for encounters. The system identifies health care providers of patients that may have an undiagnosed condition. In some embodiments, the identification of health care providers could be plotted geographically on a map. In some cases, the system may provide an interface element that allows the user to filter health care providers that are identified by adjusting a probability threshold for those health care providers that are identified.

Abstract: A computer system and method for creating a network model of health care providers comprising individuals that are connected to a particular influencer or health care provider. The system determines an influence rank that is assigned to each network that corresponds to the level of influence in comparison to other networks in a cohort. For example, the influence rank could be based, at least in part, on the number of patients treated by a health care provider and that provider's patient referrals. In some cases, the system provides a graphical user interface through which the networks can be visualized. These networks can be filtered based on a variety of categories to pinpoint specific networks, such as by geographic regions, specialties, diseases, and/or specific health care providers.