Challenges in Data Quality Assurance in Pervasive Health Monitoring Systems

TLDR: A deeper look at potential health- Monitoring usage scenarios is taken and research challenges required to ensure and assess quality of sensor data in health-monitoring systems are highlighted.

Abstract: Wearable, portable, and implantable medical sensors have ushered in a new paradigm for healthcare in which patients can take greater responsibility and caregivers can make well-informed, timely decisions. Health-monitoring systems built on such sensors have huge potential benefit to the quality of healthcare and quality of life for many people, such as patients with chronic medical conditions (such as blood-sugar sensors for diabetics), people seeking to change unhealthy behavior (such as losing weight or quitting smoking), or athletes wishing to monitor their condition and performance. To be effective, however, these systems must provide assurances about the quality of the sensor data. The sensors must be applied to the patient by a human, and the sensor data may be transported across multiple networks and devices before it is presented to the medical team. While no system can guarantee data quality, we anticipate that it will help for the system to annotate data with some measure of confidence. In this paper, we take a deeper look at potential health-monitoring usage scenarios and highlight research challenges required to ensure and assess quality of sensor data in health-monitoring systems.