Abstract
Clinical Decision Support Systems (CDSS) are active knowledge resources that use patient data to generate case specific advice. The fast pace of change of clinical knowledge imposes to CDSS the continuous update of the domain knowledge and decision criteria. Traditional approaches require costly tedious manual maintenance of the CDSS knowledge bases and repositories. Often, such an effort cannot be assumed by
medical teams, hence maintenance is often faulty. In this article, we propose a (semi-)automatic update process of the underlying knowledge bases and decision criteria of CDSS, following a learning paradigm based on previous experiences, such as the continuous learning that clinicians carry out in real life. In this process clinical decisional events are acquired and formalized inside the system by the use of the SOEKS and Decisional DNA experiential knowledge representation techniques. We propose three algorithms processingg clinical experience to: (a) provide a weighting of the different decision criteria, (b) obtain their fine-tuning, and (c) achieve the formalization of new decision criteria. Finally, we present an implementation instance of a CDSS for the domain of breast cancer diagnosis and treatment.Eider Sanchez a, b, c, Peng Wang d, Carlos Toro a, b,Cesar Sanin d, Manuel Graña c, Edward Szczerbicki d, e, Eduardo Carrasco a, b, Frank Guijarro f, Luis Brualla g, h
a Vicomtech-IK4 Research
b Biodonostia Health Research Institute, eHealth Group, Bioengineering
c University of the Basque Country UPV/EHU, Computational Intelligence Group,
d School of Engineering, Faculty of Engineering and Built Environment, The University of Newcastle,
e Gdansk University of Technology,
f Bilbomatica.
g ERESA SA
h Valencia General University Hospital,
.jpg)