Classification Method for Differential Diagnosis Based on the Course of Episode of Care
The main goal of the paper is to propose a classification method for differential diagnosis in primary care domain. Commonly, the final diagnosis for the episode of care is related with the initial reason for encounter (RfE). However, many distinct diagnoses can follow from a single RfE and they need to be distinguished. The new method exploits the data about whole episodes of care quantified by individual patients’ encounters and it extracts episode features from electronic health record to learn the classifier. The experimental studies carried out on two primary care dataset from Malta and the Netherlands for three distinct diagnostic groups revealed the validity of the proposed approach.
KeywordsClassification Differential Diagnosis Classification Episode of Care Diagnosis
Unable to display preview. Download preview PDF.
- 4.Kortteisto, T., Komulainen, J., Kunnamo, I., Makela, M., Kaila, M.: Implementing clinical decision support for primary care professionals – the process. Finnish Journal of eHealth and eWelfare 4(3), 153–164 (2012)Google Scholar
- 7.Yang, F., Wang, H.: Using random forest for reliable classification and cost-sensitive learning for medical diagnosis. In: The Seventh Asia Pacific Bioinformatics Conference (2009)Google Scholar
- 8.WONCA: An introduction to the international classification of primary care version 2. Technical report, World Organization of Family Doctors (WONCA), WONCA International Classification Committee (WICC) (2004)Google Scholar
- 9.Olson, D., Delen, D.: Advanced Data Mining Techniques. Springer (2008)Google Scholar
- 11.Frank, E., Hall, M.A., Holmes, G., Kirkby, R., Pfahringer, B., Witten, I.H., Trigg, L.: Weka - a machine learning workbench for data mining. In: Maimon, O., Rokach, L. (eds.) The Data Mining and Knowledge Discovery Handbook, pp. 1305–1314. Springer (2005)Google Scholar