Teena Arora

Supervisors: Dr Venki Balasubramanian and Associate Professor Andrew Stranieri
School of Science, Engineering and Information Technology, Centre for Informatics and Applied Optimisation (CIAO)
t.arora@students.federation.edu.au
Doctor of Philosophy

“Rank alarms for Remote Patient Monitoring”

The use of wearable sensors is an emerging trend in healthcare. Sensors monitor vital signs such as heart rate, blood pressure, temperature, respiratory rate and SpO2 and reduces work-load of nurses. These sensors are capable of transmitting health data, where doctors can check a patient’s condition remotely. Recent studies have demonstrated that generation of alarms for Remote Patient Monitoring (RPM) is useful for diagnosis of a patient’s deteriorating health condition at very early stages, helps in commencement of treatment, which in turn helps in reducing the mortality rate.

However, the sensitivity of devices and data processing algorithms results in high false alarm rates. Which reduces the effectiveness of medical monitoring resulting in alarm fatigue. In this work, vital signs data patterns have been observed by considering RPM data factors such as Multiple Early Warning Score (MEWS) values, frequency of MEWS pattern, the slope of the pattern and the pattern trend, can help to rank alarms based on the criticality level. Literature shows a model that produces overall alarm data assessment in RPM setting has not been advanced. The integration of these RPM factors to rank the alarm can help health care professionals to assess alarm instance for early intervention.

Teena Arora is supported by an Australian Government Research Training Program (RTP) Fee-Offset Scholarship through Federation University.