Abstract: A computerized back surgery predictive model identifies a risk population for back surgery and assigns a severity level to members of the risk population. High risk members are informed of preference-sensitive surgeries and alternative treatment options. The model focuses on members of the population with back condition related claims and is trained using data for members with primary diagnoses associated with various types of visits, procedures, and treatments for back pain. In an example embodiment, the model is applied to member populations to predict a first back surgery (e.g., spinal fusion, kyphosplasty, vertebroplasty, or decompression surgery) within one year after identified triggers. Predictors are historical risk factors from a broad set of data sources. Members are scored monthly to allow for continuous monitoring of the changing risk of back surgery and to allow timely intervention. The model may be tailored for different populations such as commercial and Medicare populations.

Abstract: A system and method for determining a health indicator score for a member using public data and private health data. The disclosed system and method is capable of determining a health score for a member of a health plan before private health data is available. The score may be recomputed over time based on additional public and private measures. The accuracy of the score may increase as the member's private health data is obtained and used in the score computation.

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.