The Interpretation of Time-Varying Data

Applying the methods of Artificial Intelligence to clinical monitoring requires some kind of signal-to-symbol conversion as a prior step. Subsequent processing of the derived symbolic information must also be sensitive to history and development, as the failure to address temporal relationships between findings invariably leads to inferior re- sults. DIAMON-1, a framework for the design of diagnostic monitors, provides two methods for the interpretation of time-varying data: one for the detection of trends based on classes of courses, and one for the tracking of disease histories modelled through deterministic automata. Both methods make use of fuzzy set theory, taking account of the elasticity of medical categories and allowing discrete disease models to mirror the patient's continuous progression through the stages of illness. As pointed out in (36), developments in a patient can be observed on different levels. At the low end of the spectrum the change in one or a number of sampled physiological variables can hint at an alteration in the patient's present condition. Here, methods of trend detection lend themselves to identifying clinically relevant developments. At the high end of the spectrum the patient's progression through the natural or therapy-induced stages of a disease is reflected in a sequence of characteristic conditions; formalized models of disease histories allow their automated tracking and prediction. Covering both ends of the spectrum this article presents two of D IAMON-1's time-sensitive methods, one for the detection of trends and one for the tracking of disease histories, and demonstrates their effectiveness by interpreting recorded data from an on-line monitored case in critical care.