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

Area of Science:

• Neurology
• Gerontology
• Computer Science

Background:

• Alzheimer's Disease (AD) is the most common dementia, progressively impairing cognitive functions.
• Loneliness and isolation accelerate cognitive decline in AD patients.
• Understanding social behavior is crucial for promoting sociability and enhancing patient quality of life.

Purpose of the Study:

• To analyze localization data of AD patients in assisted living facilities to understand social dynamics.
• To develop tools for monitoring and promoting sociability among AD patients.
• To support caregivers in planning activities that slow AD progression.

Main Methods:

• Utilized iBeacon technology with antennas and Bluetooth bracelets to collect patient localization data.
• Redefined the Relational Index to account for wandering and casual encounters.
• Developed Relational and Popularity Indexes to model and visualize social behavior.
• Introduced the Community Behaviour Prediction Table (CBPT) for sociability and place popularity visualization.

Main Results:

• The study successfully modeled and visualized social behavior using localization data and developed indexes.
• Predictive tools were created to aid caregivers in activity scheduling and sociability promotion.
• Analysis during the COVID-19 lockdown (Feb-June 2020) showed no significant impact on resident sociability despite social distancing measures.

Conclusions:

• Localization data analysis provides valuable insights into AD patient social dynamics.
• The developed system and tools can enhance sociability, slow cognitive decline, and improve quality of life for AD patients.
• The system demonstrated resilience in maintaining social behavior even during pandemic-related restrictions.