Using CBR as Design Methodology for Developing Adaptable Decision Support Systems - Efficient Decision Support Systems: Practice and Challenges from Current to Future - page 130

The final developed system used in the experiments carried out (see Figure 4) was set up to
forecast the total amount (kilograms) of each feed type consumed by each lot from its entry
date to its slaughter. Moreover, further experiments have been carried out to compare the
performance of the SP4 system with several other forecasting approaches. These include
standard statistical forecasting algorithms, decision trees and the application of neural
networks methods. The results obtained from experimentation revealed that the proposed
system performed optimally, being able to track the dynamic non-linear trend and
seasonality, as well as the numerous interactions between correlated variables.
3.2 Biomedical domain
In recent years DNA microarray technology has become a fundamental tool in genomic
research, making it possible to investigate global gene expression in all aspects of human
disease (Russo et al. 2003). Microarray technology is based on a database of over 40,000
fragments of genes called expressed sequence tags (ESTs), which are used to measure target
abundance using the scanned intensities of fluorescence from tagged molecules hybridized
to ESTs. Following the advent of high-throughput microarray technology it is now possible
to simultaneously monitor the expression levels of thousands of genes during important
biological processes and across collections of related samples. Since the number of examined
genes in an experiment runs to the thousands, different data mining techniques have been
intensively used to analyze and discover knowledge from gene expression data (Piatetsky-
Shapiro & Tamayo 2003). However, having so many fields relative to so few samples creates
a high likelihood of finding false positives. This problem is increased if we consider the
potential errors that can be present in microarray data.
Bioinformatics and medical informatics are two research fields that serve the needs of
different but related communities. Both domains share the common goal of providing new
algorithms, methods and technological solutions to biomedical research, and contributing to
the treatment and cure of diseases. Although different microarray techniques have been
successfully used to investigate useful information for cancer diagnosis at the gene
expression level, the true integration of existing methods into day-to-day clinical practice is
still a long way off (Sittig et al. 2008). Within this context, case-based reasoning emerges as a
suitable paradigm specially intended for the development of biomedical informatics
applications and decision support systems, given the support and collaboration involved in
such a translational development (Jurisica & Glasgow, 2004).
In addressing the issue of bridging the existing gap between biomedical researchers and
clinicians who work in the domain of cancer diagnosis, prognosis and treatment using
microarray data, we have developed and made accessible a common interactive framework:
the geneCBR decision support system (Glez-Peña et al. 2009a). Our geneCBR system
implements a freely available software tool that allows the use of combined techniques that
can be applied to gene selection, clustering, knowledge extraction and prediction for aiding
diagnosis in cancer research. For biomedical researches, geneCBR expert mode offers a core
workbench for designing and testing new techniques and experiments. For pathologists or
oncologists, geneCBR diagnostic mode implements an effective and reliable system that can
diagnose cancer subtypes based on the analysis of microarray data using CBR architecture.
For programmers, geneCBR programming mode includes an advanced edition module for
run-time modification of previous coded techniques.
In order to initially construct the knowledge base starting from the available patient's data
showed in Table 2, geneCBR stores the gene expression levels of each microarray sample in
its case base (lower part of Figure 5).