Intravenous Electromedical Equipment: A Proposal to Improve Accuracy in Generating Alerts

Abstract

The incidence of false alerts in a hospital environment undermines the health professionals’ tasks, since: (i) they stressful the teams, their caregivers and the patients themselves; (ii) promote additional costs of time and attention; (iii) may cause risky situations, some of which have severe health implications in patients. Considering this scenario, the objectives of this work are to discuss the ocurrency of alerts in intravenous systems and to contribute to the reduction of the emission of false alerts in electromedical equipments, in particular in infusion pumps. To this purpose, the developed proposal, called BIRB, explores the use of Bayesian Networks to minimize the occurrence of false alerts when occurs a change in the flow rate caused by occlusions in infusion pumps. The occlusion is the procedure with the highest index of false alerts in this type of equipment. The achivied results with the BIRB proposal are promising, reaching 85% of accuracy, based on data from actual infusion pumps.