Abstract: A method for using claims data to identify high-risk members of a healthcare plan is disclosed. In one embodiment, the present invention includes searching the plurality of claims of members selected by a filtering criteria to identify the presence of an intervention flag, to identify factors influencing care intervention, and identifying a medical episode driving the member's cost. In one embodiment, the intervention flag the medical episode are displayed in association with an identification of the member. In another embodiment, the member selection criteria includes selection based on the member's predicted future health care utilization.

Abstract: A system and method is provided for determining a probability that a member of a health plan has a disease or condition within one or more disease categories, by using data from the member's pharmacy claims. Logistic regression models are generated for each condition category using therapeutic drug categories, provider information, and/or other variables including member demographic information.

Abstract: A method for using claims data to identify high-risk members of a healthcare plan is disclosed. In one embodiment, the present invention includes searching the plurality of claims of members selected by a filtering criteria to identify the presence of an intervention flag, to identify factors influencing care intervention, and identifying a medical episode driving the member's cost. In one embodiment, the intervention flag the medical episode are displayed in association with an identification of the member. In another embodiment, the member selection criteria includes selection based on the member's predicted future health care utilization.

Abstract: A system and method for modeling healthcare utilization based on usage data from physician claims, hospital claims, and pharmacy claims. The method includes extracting from a claims file the portion of the data from a base period that is relevant to modeling healthcare utilization in a target period by computing a utilization score based on the usage data. The models may be used concurrently by calibrating them with the base period equal to the target period and they may be also be used prospectively by calibrating the models with the target period representing a future time period.