Reference: Shahar, Y. & Musen, M. A. Knowledge-Based Temporal Abstraction in Clinical Domains. Knowledge Systems Laboratory, Medical Computer Science, February, 1995.
Abstract: We have defined a knowledge-based framework for solving the task of creating abstract, interval-based concepts from time-stamped clinical data_the knowledge-based temporal-abstraction (KBTA) method. The KBTA method decomposes the temporal-abstraction task into five tasks; a formal mechanism is proposed for solving each subtask. The KBTA framework emphasizes the explicit representation of the knowledge required for abstraction of time-oriented clinical data, and facilitates its acquisition, maintenance, reuse, and sharing. The RESUME system implements the KBTA method. We tested RESUME in several clinical domains in which the task of monitoring patients is prominent. In particular, we tested the KBTA framework in the domain of monitoring patients who have insulin-dependent diabetes. We acquired from a diabetes-therapy expert a diabetes-therapy temporal-abstraction knowledge base. Two diabetes-therapy experts (including the first one) created temporal abstractions relevant to the therapy-monitoring task from about 800 points of data from cases of diabetic patients. The RESUME system generated about 80% of the abstractions agreed by both experts; about 97% of the overall generated abstractions were valid. We discuss the advantages and limitations of the current architecture.