Mining Clinical Pathways Using Dual Clustering

Abstract

One of the most important tasks of data mining in a hospital is to discover structured knowledge about decision-making, which is useful for the management of clinical processes. However, most of the data in a hospital information system are stored without classification labels or the meaning of clinical actions. Thus, unsupervised learning techniques are required for analysis. This paper proposes a method which induces a clinical pathway using sample and attribute clustering of the histories of nursing orders stored in a hospital information system. The method consists of the following ve steps: first, frequencies of nursing orders are extracted from a hospital information system as a dataset in which each row and column represents nursing orders and days of the week. Second, orders are classified into several groups using sample clustering. Then, attributes clustering is applied to the data for feature selection. Fourth, for each sample and attribute clustering, the number of clusters is obtained from the sequence of the height values, and following the results of attribute clustering, the original dataset is decomposed into sub-tables. Then, the second-to-fourth steps are repeated in a recursive way until the grouping of attributes (days) are stable. Finally, a new pathway will be constructed from all the induced results. The proposed method was evaluated on datasets extracted from a hospital information system. The experiment results show that the method is useful for the construction of a clinical pathway when the distribution of length of stay is uni-modular.