Abstract
This paper proposes a method for construction of a clinical pathway based on attribute and sample clustering, called dual clustering. The method consists of the following four steps: first, histories of nursing orders are extracted from a hospital information system. Second, orders are classified into several groups by using clustering on the pricipal components (sample clustering). Third, attribute clustering is applied to the data. Finally, original temporal data are split into several sub-tables and the first step will be repeated in a recursive way. After the grouping results become stable, a new pathway will be constructed from all the induced results. The method was applied to datasets of a disease extracted from a hospital information system. The results show that the proposed method constructed a clinical pathway, which was not only similar to the pathway manually acquired from medical experts but also discovered nursing orders which they forget to include.
Keywords: Clinical pathway, decision support, dual clustering, temporal data mining, hospital information system.
Graphical Abstract
13