Information Technology Reference
In-Depth Information
ISOR deals with situations where neither a well-developed theory nor reliable
knowledge nor a proper case base is available. So, instead of theoretical knowledge
and intelligent experience, just a theoretical hypothesis and a set of measurements are
given. In such situations the usual question is, “how do measured data fit to a theo-
retical hypothesis?” To statistically confirm a hypothesis it is necessary that the ma-
jority of cases fit the hypothesis. Mathematical statistics determines the exact quantity
of necessary confirmation [14]. However, usually a few cases do not satisfy the
hypothesis. These cases need to be examined to find out why they do not fit the
hypothesis. ISOR offers a dialogue to guide the search for possible reasons in all
components of the data system. The exceptional cases belong to the case base. This
approach is justified by a certain mistrust of statistical models by doctors, because
modelling results are usually non-specific and “average oriented” [15], which reflects
a lack of attention to individual "imperceptible" features of specific patients.
Observed Data Set
Setting up a Model
Pointing out
Exceptional Cases
Medical Expert
Searching for
Explanations
Patients
Medical Histories
Case Base
Accepted Solutions
Fig. 1.
ISOR's general program flow
The usual Case-Based Reasoning assumption is that a case base with complete so-
lutions is available [2, 3, 16]. Our approach starts in a situation where such a case
base is not available but has to be set up incrementally. The general program flow is
shown in figure 1. The main steps are:
Search WWH ::
Custom Search