Semantic and Association Rule Mining-Based Knowledge Extension for Reusable Medical Equipment Lifecycle Management

摘要

For healthcare providers, using Reusable Medical Equipment (RME) has a strength in the cost-efficiency since it can be reused and reprocessed to multiple patients. Hence, estimating the maintenance (i.e., repair) cost during RME lifecycle has been a topic in healthcare domain. However, most of the existing research regarding RME has focused on the prediction without considering the domain knowledge of the cost in healthcare. This aim of the research is to propose the method of knowledge extension based on the post-mining (i.e., Association Rule Mining) interpreted by the domain knowledge (i.e., RME ontology and statistical cost domain knowledge) for RME lifecycle management. This contains finding the frequent rule patterns from the tremendous volumes of decision rules (i.e., Random Forest Rules) of the non-profit hospital's legacy database, which can make the pruned frameworks of each rule pattern linked and interpreted to the proper domain knowledge. The interpreted rule patterns make healthcare providers utilize them in the RME lifecycle management decision making.