Healthcare-Associated Infections (HAI) are important quality indicators of healthcare, a leading cause of mortality and morbidity worldwide, and contributors to lower medical quality and increases in medical costs. Based on the definition and determining criteria of healthcare-related infections stipulated by Taiwan’s Centers for Disease Control, Department of Health, this study created a program for an HAI determining rule, as well as an HAI monitoring system environment and proposed the HAI prediction model to predict antimicrobial resistance (AR). By using the developed system, we can discover healthcare-related infection abnormalities earlier and provide infection control professionals with the ability to check on and conduct pre-decision analyses. Prediction model experimental result shows that identified by cluster analysis of the important characteristics of HAI including sex, ward classification, department etc. Other the proposed prediction model AR with relatively satisfactory accuracy. In this study, the data mining approach for HAI control not only predicts, but also hopes to contribute a sense of control officers to immediately grasp the situation and reduce the chances of expanding infection and enhance the validity of antibiotics.