The patient transfer from hospitals to followup care and rehabilitation facilities is an important aspect for maintaining the continuity of medical care. In order to achieve flexible healthcare within the field of Internet of Vehicles (IoVs) in terms of secure patient transfer and ambulance transport, the whole organization of patients' discharge and transfer should be anticipated, based mostly on a length of stay (LOS) given at the time of inpatient admission. Therefore, the prediction of LOS has serious impact on influx coordination, bed management, ambulance scheduling, and furthermore, on the financial balance of hospitals. Based on studying medical data, the prediction with good accuracy can help hospital managers get an efficient and robust resource management. The challenge is then how to extract valuable information from medical data, which contains considerable hesitation and uncertainty elements. In this article, a hesitant fuzzy-rough nearest-neighbor algorithm has been proposed and experimented with real medical data. Hesitation interpretation has been reflected in the process of determining class labels in our algorithm via hesitant fuzzy relation determination and hesitant fuzzy-rough similarity measure. The experimental analysis has shown that the proposed algorithm has better performance and extensibility.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.