Missing Information Prediction in Ripple Down Rule Based Clinical Decision Support System

Abstract

Clinical Decision Support System (CDSS) plays an indispensable role in decision making and solving complex problems in the medical domain. However, CDSS expects complete information to deliver an appropriate recommendation. In real scenarios, the user may not be able to provide complete information while interacting with CDSS. Therefore, the CDSS may fail to deliver accurate recommendations. The system needs to predict and complete missing information for generating appropriate recommendations. In this research, we extended Ripple Down Rules (RDR) methodology that identifies the missing information in terms of key facts by analyzing similar previous patient cases. Based on identified similar cases, the system requests the user about the existence of missing facts. According to the user’s response, the system resumes current case and infers the most appropriate recommendation. Alternatively, the system generates an initial recommendation based on provided partial information.