Like many developed countries, Singapore faces the challenges of an ageing population.
The number of Singaporeans aged 65 and above is increasing rapidly as population growth
slows. The number of seniors has doubled from 220,000 in 2000 to 440,000 in 2015, and is
expected to increase to 900,000 by 2030. Amongst the elderly people, close to 10% are
living alone (from 35,000 in 2012 to 83,000 by 2030). The changing demographic not only
increases healthcare costs but also the demand on healthcare services and care provision.
Preventing frailty and MCI is key for the elderly to maintain their day-to-day activities
and remain healthy and independent at home. Prior research has shown that frailty, like
disability, is a dynamic process with older individuals moving back and forth between
different frailty states. Transition to frailty is a gradual progression that occurs over
the course of several months or years, and there are surprisingly high rates of recovery.
However, it is important to intervene within the right time window before a person goes
into full blown frailty. Hence it is important to detect the onset and progression of
frailty and to identify the factors that may facilitate transitions to less frail states.
This can inform the development of interventions to manage elderly at risk for fraility.
City for All Ages project seeks to demonstrate that smart cities can play a pivotal role
in "prevention" (i.e. the early detection and consequent intervention) of MCI and
frailty-related risks. The core idea is that "smart cities", enabled by the deployment of
sensor technologies and analytics can collect data about individuals: a) to identify
segments of population potentially at risk, in order to start more stringent monitoring;
b) to closely monitor selected individuals, in order to start a proactive intervention.
In both cases adverse changes of behaviors that are identified through a set of
indicators can prompt preventive actions. The aim is to advance the research on
healthcare towards a proactive rather than reactive system.
The research team will leverage the existing experimentations and pilot sites that have
focused on detection of elderly risky behaviors both in France and Singapore. Lessons
learnt from dealing with challenges either in terms of understanding the data (such as
false positives, meaningful information, etc.) or providing the appropriate and timely
intervention (such as difficulty in identifying and organizing the intervention
effectively, large panel of stakeholders, excessive solicitation of caregivers, etc.)
would be useful for this project.
Our goal is to use sensing technologies installed in the elderly's home to monitor and
detect their activities such as cooking, sleeping, going to the bathroom, going out of
the apartment or potential wandering, bathroom falls. Sensor data will be collected
unobtrusively and managed using a privacy-aware linked open data paradigm. Basic
reasoning and learning algorithms will be applied to the data to identify relevant
behaviours of individuals, and to detect behavioral changes that can be correlated with
risks of MCI/frailty. The appropriate ICT based interventions (e.g. data visualization
and alerts to caregivers) will then be applied to mitigate these risks.