Abstract
We present a novel knowledge discovery methodology that relies on Rough Set Theory to predict the life expectancy of terminally ill patients in an effort to improve the hospice referral process. Life expectancy prognostication is particularly valuable for terminally ill patients since it enables them and their families to initiate end-of-life discussions and choose the most desired management strategy for the remainder of their lives. We utilize retrospective data from 9105 patients to demonstrate the design and implementation details of a series of classifiers developed to identify potential hospice candidates. Preliminary results confirm the efficacy of the proposed methodology. We envision our work as a part of a comprehensive decision support system designed to assist terminally ill patients in making end-of-life care decisions.