Multisensor Data Fusion for Patient Risk Level Determination and Decision-support in Wireless Body Sensor Networks

Abstract

Wireless Body Sensor Networks (WBSNs) are a low-cost solution for healthcare applications allowing continuous and remote monitoring. However, many challenges are addressed in WBSNs such as limited energy resources, early detection of emergencies and fusion of large amount of heterogeneous data in order to take decisions. In this paper, we propose a multisensor data fusion approach enabling one to determine the patient risk level based on vital signs scores. Consequently, a corresponding decision is taken routinely and each time an emergency is detected. This approach is based on early warning score systems, a fuzzy inference system and a technique determining the score of a vital sign given its past and current value. We evaluate our approach on real healthcare datasets.