KNOWLEDGE-BASED TEMPORAL ABSTRACTION FOR DIABETIC MONITORING

We have developed a general method that solves the task of creating ab stract, interval-based concepts from time-stamped clinical data. We re fer to this method as knowledge-based temporal-abstraction (KBTA). In this paper, we focus on the knowledge representation, acquisition, mai ntenance, reuse and sharing aspects of the KBTA method. We describe fi ve problem-solving mechanisms that solve the five subtasks into which the KBTA method decomposes its task, and four types of knowledge neces sary for instantiating these mechanisms in a particular domain. We pre sent an example of instantiating the KBTA method in the clinical area of monitoring insulin-dependent-diabetes patients.