Using Advanced IoT-based Machine Learning for In-Home Quality Ageing

The Challenge

Australia confronts the prospect of a vulnerable ageing population. In 2017, the number of people aged of 65 and over was 3.8m. In 2030, it is projected to be 5.4m people aged 65 years and over. The Australian Government aged care expenditure in 2017-2018 was $18.1bn and is projected to rise to $24.0bn in 2021-2022.

To ensure sustainability in delivering high quality and accessible care, a paradigm shift in aged care support is required focusing on “ageing in place”. This refers to the ability to live in one's own home and community safely, independently, and comfortably, in contrast to living in a residential environment or a nursing home. Importantly reducing the cost to Government, Age care facilities and the hospital system.

The Solution

Researchers from the University of Sydney and Macquarie University are working with InteliCare to build machine learning (ML) algorithms to predict and prevent health events that are likely to impact the elderly’s quality of life. ML is a subset of AI that allows machines to learn from big data without being programmed explicitly. It is a powerful method to structure data and identify patterns.

The solution will extend InteliCare’s artificial intelligence (AI) accuracy at predicting risks of chronic disease and mental health deterioration that can lead to loss of independence, and in some cases, injury.

The project was awarded funding under the first round of NSSN Grand Challenge Fund in 2020. The funding will accelerate Machine Learning capability of the sensor to predict events within InteliCare, which to date has focussed on detecting events, rather than predicting and hence preventing adverse events.

Industry Partner

University Partner