Data mining and the implementation of a prospective payment system for inpatient rehabilitation

This paper describes the development of a new Medicare Prospective Payment System (PPS) for inpatient rehabilitation care. Congress mandated such a system in the Balanced Budget Act of 1997. To help implement this system, we assembled four years of Medicare hospitalization data, linked it to rehabilitation hospitals' information about impairment and the functional status of patients, and developed case mix groups using the CART algorithm, a common method for determining groups in health services. While CART readily produces simple and effective rules for prediction, it adheres to a restrictive functional form and its fitting algorithm does not necessarily produce a global optimum. We wanted to know how these limitations affect our results. So, we compared CART's performance with methods receiving attention in the data mining community and in the statistics literature. We estimated that the CART models explained about 90 percent of the potentially explainable variance in individual cost and they predicted annual hospital costs that were essentially identical to other methods' predictions.