Discovering knowledge of medical quality in total hip arthroplasty (THA).

As the incidence of THA is expected to rise with an aging population and improvements in surgery, a satisfactory outcome in health care can effectively increase medical quality. This paper uses a serious data screening function by THA physician to reduce data dimension after data collected from the NHI database, then 8576 cases are obtained from the original cases of 10,388 after screening procedure. The proposed model adopts an imbalanced sampling method to solve class imbalance problem, and utilizes rough set to locate core attributes. Based on the core attributes, the extracted rules can be comprehensive for the rules of medical quality. In verification, THA dataset is taken as case study; the performance of the proposed model is verified and compared with other data-mining methods under some criteria. And the generated decision rules and core attributes could find more managerial implication. Moreover, the result can provide stakeholders with useful THA information to help to make decision.