CASESIAN: A knowledge-based system using statistical and experiential perspectives for improving the knowledge sharing in the medical prescription process

Knowledge sharing is crucial for better patient care in the healthcare industry, but it is challenging for physicians to exchange their clinical insights and practice experiences, particularly with regard to the issuing of prescriptions for medicine. The aim of our study is to facilitate knowledge sharing and information exchange in this area by means of a knowledge-based system. We propose a knowledge-based system, CASESIAN, to automatically model each physician’s prescription experience. This is done by collecting as many as possible instances of when the physician has issued a prescription. These occasions will be analyzed from a statistical perspective to form a reciprocal interactive knowledge sharing process for the issuing of medical prescriptions which we will call the prescription process. With the help of the prescription data in medical organizations, the knowledge-based system employs the Bayesian Theorem to correlate the experience of peers in order to evaluate individual prescription knowledge as retrieved through the case-based reasoning technique. In addition, a system prototype was implemented in a Hong Kong medical organization to evaluate the feasibility of such an approach. Our evaluation indicates that there is a significant improvement in knowledge sharing after the adoption of the system. CASESIAN obtains a higher rating in both recall and precision measurement when compared to traditional knowledge-based system. In particular, its information retrieval is much stronger than the baseline in around 40%. Furthermore, regarding the result of the interviews, physicians agree that the system can improve the storing and sharing of medical prescription knowledge.