Abstract: A system and method that generates a hierarchical tree network and uses linear-plus-nonlinear learning algorithms to form a consensus view on a member's future health status. Each leaf in the hierarchical tree network is homogeneous in clinical characteristics, experience period, and available data assets. Optimization is performed on each leaf so that features and learning algorithms can be tailored to local characteristics specific to each leaf.

Abstract: The present invention relates to a system and method for automated extraction and display of past health care use to aid in predicting future health status. A system and method that converts raw medical and pharmacy claims data into Hierarchical Major Clinical Condition (HMCC) and Place of Treatment (POT) time-series data to facilitate the health assessment of a member's total clinical conditions and aid in predicting his or her future health status. The HMCC categories are organized in body systems and likely disease progression to permit both spatio-temporal digital signal processing and the development of a dynamical learning system. Each medical and pharmacy claim of the member is mapped onto one or more HMCC/POT-time cells. At the end of mapping, multiple entries in each HMCC-time cell are accumulated with the temporal resolution determined as a function of group size and temporal fidelity required for model building.