Mining Hospital Data to Learn SDA* Clinical Algorithms
The practice of evidence-based medicine requires the integration of individual clinical expertise with the best available external clinical evidence from systematic research and the patient’s unique values and circumstances. This paper addresses the problem of making explicit the knowledge on individual clinical expertise which is implicit in the hospital databases as data about the daily treatment of patients. The EHRcom data model is used to represent the procedural data of the hospital to which a machine learning process is applied in order to obtain a SDA* clinical algorithm that represents the course of actions followed by the clinical treatments in that hospital. The methodology is tested with data on COPD patients in a Spanish hospital.
KeywordsHealth-care procedural knowledge machine learning
Unable to display preview. Download preview PDF.
- 1.C.P.-E: 13606-1: Health Informatics - Electronic Health Record Communication - Part 1: Reference Model (2004)Google Scholar
- 2.Eichelberg, M., Aden, T., Riesmeier, J., Dogac, A., Laleci, G.B.: A Survey and Analysis of Electronic Health care Record Standards. ACM Computing Surveys (to appear)Google Scholar
- 3.GOLD-Global Initiative for Chronic Obstructive Lung Disease. Executive Summary (2006)Google Scholar
- 5.López-Vallverdú, J.A., Riaño, D., Collado, A.: Increasing acceptability of decision trees with domain attributes partial orders. In: Proc. of the 20th IEEE International Symposium on Computer-Based Medical Systems, Maribor, Slovenia (2007)Google Scholar
- 6.Quinlan, J.R.: C4.5: Programs for ML, San Mateo, CA, USA. Morgan Kaufmann, San Francisco (1993)Google Scholar
- 7.Riaño, D.: The SDA* Model: A Set Theory Approach. In: Proc.of the 20th IEEE International Symposium on Computer-Based Medical Systems, Maribor, Slovenia (2007)Google Scholar
- 8.Sackett, D., Straus, S., Rosenberg, V., Haynes, B.: Evidence-Based Medicine: How to practice and teach EBM, 2nd edn. Chirchill Livingstone (2000)Google Scholar
- 11.Tu, S.W., Musen, M.A.: Modeling Data and Knowledge in the EON Guideline Architecture. In: Proc. MedInfo 2001, London, UK, pp. 280–284 (2001)Google Scholar