Building explainable user models of older adults from data

The Advanced Care Research Centre at the University of Edinburgh is a new £20m interdisciplinary research collaboration aiming to transform later life with person centred integrated care

The vision of the ACRC is to play a vital role in addressing the Grand Challenge of ageing by transformational research that will support the functional ability of people in later life so they can contribute to their own welfare for longer. With fresh and diverse thinking across interdisciplinary perspectives our academy students will work to creatively embed deep understanding, data science, artificial intelligence, assistive technologies and robotics into systems of health and social care supporting the independence, dignity and quality-of-life of people living in their own homes and in supported care environments.

The ACRC Academy will equip future leaders to drive society’s response to the challenges of later life care provision; a problem which is growing in scale, complexity and urgency. Our alumni will become leaders in across a diverse range of pioneering and influential roles in the public, private and third sectors.

As artificial intelligence increasingly permeates all spheres of life, it is becoming clear that there is a need for predictive models that can explain their decisions. This is particularly important in safety-critical areas such as health and care, where the wrong decision can be a matter of life or death.

This project will explore how health and care outcomes for the older person can be improved through explainable, predictive machine learning. In particular, it will develop interpretable AI models of older adults, based on a combination of statistical and symbolic approaches using data related to care, physiological monitoring, activities of daily living and other events (e.g. social network interactions).

By developing robust, yet adaptive and transparent, user models that can support the individual’s needs and are attentive to physical/non-physical decline over time, it should be possible to increase the reliance on AI when making non-trivial care interventions.

Some of the objectives include:

• Exploring how already-labelled data about care treatment, alarm calls, history of falls etc. can be used to detect adverse events and trigger personalised alerts that are robust to noise;
• Investigate whether decline can be predicted based on reduced interactions with entertainment systems, games, frequency of audio/video chats family and friends, etc.
• Investigate how public datasets can be used to extend the explainable models with data about activities of daily living (ADL), physiological monitoring and other events.

The project will be part of the ACRC theme on New Technologies of Care and is aligned with  other themes such as the one on data-driven insight and prediction. The project will be supervised by an interdisciplinary team of academics with expertise in Artificial Intelligence, machine learning and geriatric medicine.

Eligibility

• A good undergraduate degree or Masters degree in Artificial Intelligence, Computer Science or Data Science
• Some experience with machine learning
• Some experience with knowledge representation and reasoning
• Strong interest in health and care and associated data
• Ability to work in a multi-disciplinary team