Understanding Social Behaviour in a Health-Care Facility from Localization Data: A Case Study

Abstract

The most frequent form of dementia is Alzheimer's Disease (AD), a severe progressive neurological pathology in which the main cognitive functions of an individual are compromised. Recent studies have found that loneliness and living in isolation are likely to cause an acceleration in the cognitive decline associated with AD. Therefore, understanding social behaviours of AD patients is crucial to promote sociability, thus delaying cognitive decline, preserving independence, and providing a good quality of life. In this work, we analyze the localization data of AD patients living in assisted care homes to gather insights about the social dynamics among them. We use localization data collected by a system based on iBeacon technology comprising two components: a network of antennas scattered throughout the facility and a Bluetooth bracelet worn by the patients. We redefine the Relational Index to capture wandering and casual encounters, these being common phenomena among AD patients, and use the notions of Relational and Popularity Indexes to model, visualize and understand the social behaviour of AD patients. We leverage the data analyses to build predictive tools and applications to enhance social activities scheduling and sociability monitoring and promotion, with the ultimate aim of providing patients with a better quality of life. Predictions and visualizations act as a support for caregivers in activity planning to maximize treatment effects and, hence, slow down the progression of Alzheimer's disease. We present the Community Behaviour Prediction Table (CBPT), a tool to visualize the estimated values of sociability among patients and popularity of places within a facility. Finally, we show the potential of the system by analyzing the Coronavirus Disease 2019 (COVID-19) lockdown time-frame between February and June 2020 in a specific facility. Through the use of the indexes, we evaluate the effects of the pandemic on the behaviour of the residents, observing no particular impact on sociability even though social distancing was put in place.

Keywords: ambient assisted living; data-driven design; social behaviour prediction; social wellness assessment.

Figure 1

Il Paese Ritrovato. (a) Village chapel. (b) Bricolage lab. (c) Piazza.

Figure 2

The network of antennas at Il Paese Ritrovato. The red areas are the private places of the structure while the white ones denote the areas outside the facility. The rest are the public areas of the facility. Notice that the top north street is the car access, so it is forbidden to dwellers.

Figure 3

Comparison between computed and smoothed times series of the Popularity Index ($PI$). (a) Before Smoothing. (b) After Smoothing.

Figure 4

Triangular fuzzy set on the seasons of the year.

Figure 5

Community behaviour Prediction Table.

Figure 6

Community relational index ($RI$) trend during COVID-19 lockdown (January–June 2020).

Figure 7

$PI$ trend of public places at Il Paese Ritrovato (January–June 2020).

Figure 8

$PI$ trend of private places at Il Paese Ritrovato (January–June 2020).