Persuasive and Pervasive Sensing: A New Frontier to Monitor, Track and Assist Older Adults Suffering from Type-2 Diabetes

Abstract

California like the entire nation is aging. There are 4.3 million Californians 65 and older accounting for about 11% of the total state population. We also find that 58% of older adults have high blood pressure; about 21% have been told that they have diabetes. California in particular has the highest incidence of new diabetes cases and nearly 4 million people (diagnosed and undiagnosed) are estimated to be suffering from the disease. Diabetes is a chronic disease, which if unchecked leads to acute and long-term complications and ultimately death. Our older adult population often lacks the cognitive resources to deal with the daily self-management regimens. Many unpaid family members are caring for them today but this is unsustainable. In this paper, we discuss the design and implementation of a wireless sensor network system within the home environment that captures activity of daily living. We mine the data and provide feedback via SMS/text (daily) and tailored newsletter (weekly). We introduce a novel idea called "persuasive sensing" and report results from two home implementations that are showing exciting promise. Moreover we show that with the help of an Artificial Neural Network, we can predict blood-glucose levels for the next day from accumulated data with an accuracy of 94%. The predictive model presented here is a break-through in at-home sensing research.