Applying MCRDR to a Multidisciplinary Domain
This paper details updated results concerning an implementation of a Multiple Classification Ripple Down Rules (MCRDR) system which can be used to provide quality Decision Support Services to pharmacists practicing medication reviews (MRs), particularly f
- PDF / 185,951 Bytes
- 10 Pages / 430 x 660 pts Page_size
- 26 Downloads / 185 Views
University of Tasmania, School of Computing {ibindoff, bhkang, trling}@utas.edu.au 2 University of Tasmania, Unit for Medical Outcomes and Research Evaluations {Peter.Tenni, G.Peterson}@utas.edu.au
Abstract. This paper details updated results concerning an implementation of a Multiple Classification Ripple Down Rules (MCRDR) system which can be used to provide quality Decision Support Services to pharmacists practicing medication reviews (MRs), particularly for high risk patients. The system was trained on 126 genuine cases by an expert in the field; over the course of 19 hours the system had learned 268 rules and was considered to encompass over 80% of the domain. Furthermore, the system was found able to improve the quality and consistency of the medication review reports produced, as it was shown that there was a high incidence of missed classifications under normal conditions, which were repaired by the system automatically. However, shortcomings were identified including an inability to handle absent data, and shortcomings concerning standardization in the domain, proposals to solve these shortcomings are included.
1 Introduction Sub-optimal drug usage is a serious concern both in Australia and overseas [1, 2], resulting in at least 80,000 hospital admissions annually - approximately 12% of all medical admissions - the majority of these concerning elderly patients [3]. MRs are seen as an effective way to improve drug usage. However, the quality of MRs produced is inconsistent across reviewers. This paper continues discussion commenced in a earlier publications by the authors in 2006 and 2007 in which an Intelligent Decision Support System was developed in an attempt to improve the quality of MRs [4, 5]. It was suggested that to improve the consistency and quality of MRs it would be prudent to develop medication management software which includes Intelligent Decision Support features. Prior to this, the majority of incarnations of medication management software for producing MRs has lacked any genuinely “Intelligent” form of Decision Support features [6]. In response to this suggestion, a software system for medication management was developed that utilized the MCRDR method to provide Intelligent Decision Support Services in the multidisciplinary field of MR. [7, 8]. M.A. Orgun and J. Thornton (Eds.): AI 2007, LNAI 4830, pp. 519–528, 2007. © Springer-Verlag Berlin Heidelberg 2007
520
I. Bindoff
2 Medication Reviews MR is a burgeoning area in Australia and other countries, with MRs seen to be an effective way of improving drug usage and reducing drug related hospital admissions, particularly in the elderly and other high risk patients [1, 3]. To perform a MR, Pharmacists assess potential Drug Related Problems (DRPs) in a patient by examining various patient records, primarily their medical history, any available pathology results, and their drug regime (past and current) [9]. The expert looks for a variety of indicators between the case details provided checking for known problems, such as an: Untreated In
Data Loading...
