Explaining Medical Model Exceptions - Computational Intelligence in Healthcare: Advanced Methodologies - page 270

The second kind of adaptation modifies an imputation formula. This kind of adap-
tation can not be done entirely automatically but the expert has to be involved. When
a (usually short) list of solutions is retrieved, ISOR at first checks whether all required
values of the exact calculation formulae are available. If required parameter values are
not available, there are three alternatives to proceed. First, to find an exact solution
formula where all required parameter values are available, second to find an estima-
tion formula, and third to attempt to impute the required values too. Since for the third
alternative there is the danger that this might lead to an endless loop, this process can
be manually stopped by pressing a button in the dialogue menu. When for an esti-
mated solution required values are missing, ISOR asks the expert.
The expert can suggest an exact or an estimated solution. Of course, such an expert
solution also has to be checked for the availability of the required data. However, the
expert can even provide just a numerical solution, a value to replace the missing data
- with or without an explanation of this suggested value.
Furthermore, adaptation can be differentiated according to its domain dependency.
Domain dependent adaptation rules have to be provided by the expert and they are
only applicable to specific parameters. Domain independent adaptation uses general
mathematical formulae that can be applied to many parameters. Two or more adapta-
tion methods can be combined.
In ISOR a revision occurs. However, it is a rather simple one. It is not as sophisti-
cated as, for example, the theoretically one described by Lieber [29]. Here, it is just an
attempt to find better solutions. An exact solution is obviously better than an esti-
mated one. So, if a value has been imputed by estimation and later on (for a later case)
the expert has provided an appropriate exact formula, this formula should be applied
to the former case too. Some estimation rules are better than others. So it may happen
that later on a more appropriate rule is incorporated in ISOR. In principle, the more
new solution methods are included in ISOR, the more former already imputed values
can be revised.
Artificial cases. Since every piece of knowledge provided by a medical expert is sup-
posed to be valuable, ISOR saves it for future use. If an expert solution cannot be
used for adaptation for the query case (required values for this solution might be miss-
ing too), the expert user can generate an artificial case. In ISOR exists a special dia-
logue menu to do this. Artificial cases have the same structure as real ones, and they
are also stored in the case base.
5 Results
At first, we undertook some experiments to assess the quality of our imputation
method, subsequently we attempted to impute the real missing data and finally we set
up a new model for the original hypothesis that actively participating in the fitness
program improves the conditions of the patients.
5.1 Experimental Results
Since ISOR is a dialogue system and the solutions are generated within a conversation
process with the expert user, the quality of the solutions not only depends on ISOR
but also on the expert user.