Cluster-based real-time analysis of mobile healthcare application for prediction of physiological data

In recent years, interest in medical healthcare applications using Wireless Body Sensor Network (WBSN) has grown considerably. A WBSN can be used to develop a patient monitoring system, which offers flexibility and mobility to monitor patient’s health condition. When the value of the physiological signal reaches threshold, the system raises an alarm. However, earlier patient monitoring systems may not be accurate all the time and do not support mobility which lead to false positive prediction. This paper presents, a data mining algorithm to predict the health risk of the patient in real time with 96% accuracy using historical medical records. Proposed Online Distribution Resource Aware (ODRA) algorithm gives accurate condition of the patients so as to inform the status to physician whenever immediate attention is required. The worst health conditions are predicted by risk components which are extracted using signal windows of the vital signal. The proposed algorithm of real-time patient monitoring system uses online signals to monitor the patient’s physiological data with increased mobility even in the ubiquitous environment. HR, SpO 2 , and Blood Pressure signals of 64 patients with different illness have been tested and verified. Results confirmed that the proposed algorithm gives better accuracy and reduce False Positive Rate (FPR) for predicting risk status of the patient compared to Resource Aware High-Quality Clustering (RAH).