The UPA (Underwriting Profitability Analysis) application embodies a new approach to mining Property & Casualty (P&C) insurance policy and claims data for the purpose of constructing predictive models for insurance risks. UPA utilizes the ProbE (Probabilistic Estimation) predictive modeling data mining kernel to discover risk characterization rules by analyzing large and noisy insurance data se...

Medical planning for Operation Iraqi Freedom included predictive models of expected number of burn casualties. In all but the best-case scenario, casualty estimates exceeded the capacity of the only Department of Defense burn center. Examination of existing federal-civilian disaster plans for military hospital augmentation revealed that bed availability data were neither timely nor accurate. Re...

Catastrophic mass casualty events (MCEs), such as pandemic influenza outbreaks, earthquakes, or large-scale terrorism-related events, quickly and suddenly yield thousands of victims whose needs overwhelm local and regional health care systems, personnel, and resources. Such conditions require deploying scarce resources in a manner that is different from the more common multiple casualty event. ...

When designing a decision support program for use in coordinating the response to Mass Casualty Incidents, the modelling of the health of casualties presents a significant challenge. In this paper we propose one such health model, capable of acknowledging both the uncertain and dynamic nature of casualty health. Incorporating this into a larger optimisation model capable of use in real-time and...