The main aim of the City4Age-project was to examine an unobtrusive, continuously running classifier, that should be able to discriminate elderly people who are robust from those who are not. Such classifier is used to timely detect people at risk of health decay, in order to enact in correspondence with effective and early interventions, aimed at keeping people at risk healthy for as long as possible. The underlying hypothesis is that modern smart cities will increasingly be able to provide such data, unobtrusively and at low cost, thereby supporting the effective implementation of a new paradigm for managing health risks in aging citizens.
In the cost-effectivness analysis, we adopted the perspective of the Public Health Authorities, in order to assess how City4Age might improve Health Related Quality of Life (HRQoL) in elderly populations, while at the same time shifting resource usage from expensive healthcare settings, typically sustained by public health systems, to a more efficient wellbeing self-management context, sustained by the private sector.
The MAFEIP analysis of the City4Age early detection approach suggests that – in a future scenario, where systematic screening for frailty may be put in place – the classifier shall be preferably geared towards the riskier layers of the elderly population, as for lower risk levels the increased precision of (even) a good classifier is not actually required.