Advanced Care Research Centre

Research and Development: New Technologies of Care

The sixth work package of the Advanced Care Research Centre.

Dissemination Outputs and Impact

This research programme will develop practical, care-driven technologies that are fit for people in later life. In particular, this means exploring and developing sensor-specific data-driven IoT platforms that can produce accurate data about instant events (e.g. vital signs and serious incidents such as falls), short-term activities (e.g. those of daily living) and long-term pursuits (e.g. physical and mental activities over weeks and months) in order to extract (predictive) information and patterns that can be used, among other things, for the prevention of adverse events, adherence to care pathways and effective interventions.  When it comes to care for people in later life, additional challenges related to conditions such as frailty, multi-morbidity and cognitive impairment means that a judicious choice and deployment of technology is essential. Such technology will be of direct value to a range of stakeholders and also aligns with L&G’s vision for the ACRC in designing and delivering insight-driven products and services to support independent living and well-being for people in later life. 


In WP6, we propose to create a community collaboratory that will provide the long-term context for the development and evaluation of multiple new technologies of care in a collaboration between academics from several disciplines, people in later life and their families, health and social care professionals, and businesses in this market.  The collaboration will initially be formed around the implementation of routine physiological and functional monitoring in a highly vulnerable community-based population in order to detect deterioration early, with a prioritisation process to inform the focus of future work. By proceeding in a staged manner, we will both make an immediate contribution to knowledge and practice, and support long-term iterative and participatory development of new technical capability. For this purpose, we identify three main research goals: 1) implementing routine physiological monitoring in a home setting, 2) development and implementation of additional sensing modalities and devices, and 3) development of decision support and intervention management.  

Research Plan

The overall design of this WP is based on a set of 7 linked and complementary tasks that take advantage of an opportunity to generate sensors and technologies that complement care provided to people in later life. The research, which spans engineering and informatics, will use a variety of methods to produce platforms that combine elements such as multi-modal sensor integration, data analysis and fusion, AI-based decision and prediction modelling and assistive technologies to facilitate care for people in later life. For this work, we have established partnerships with a number of health and care partners who have agreed to provide expertise, data and other resources towards the development and validation of the outputs from the project. We will also work with colleagues in WP4 (focused on understanding how people in later life prioritise and respond to need) and WP7 (focused on understanding innovation in health and social care delivery) to prioritise the development of additional sensing parameters, AI-based decision support and assistive technologies, thereby ensuring we develop future-facing, innovative technologies that deliver the right care to people in later life. 


The aim of this task is to carry out comprehensive reviews of the sensors and devices used for the monitoring of physiological parameters and activities and of the assistive technologies used for their care. These reviews will mainly inform the research being done in Tasks 2 and 7 but we expect them to be relevant to other tasks in WP6 and to WP7. 


This task will investigate the use of a number of available sensing modalities to validate their effectiveness in capturing key physiological parameters, as well as, detect and predict the onset of falls through a number of key parameters. In the first instance, sensors will be integrated/embedded into fixed objects. Another approach would be to investigate efficient integration of these sensors with personal items, such as bedsheets, clothes, patches, and other wearable items that are available in the care environment.  


In a continuous monitoring regime, it is imperative to process data online and in a timely manner in order to capture events such as falls or domestic accidents, that occur either unexpectedly or triggered by a sequence of events, behaviours and external factors taking place over short intervals. This task is focused on developing a data sketching framework suitable to maintaining a summary of the streaming data collected via the multi-sensory platform in Task 2 in order to streamline their processing as envisioned in Tasks 4 and 5.  


This task will develop digitized models of care to allow for meaningful inference and decision support. This includes process-based workflow models that capture knowledge about care pathways, guidelines, and practices, as well as individual needs and circumstances. These will be used to inform new models of care for WP7. Explainable and predictive user models using AI approaches on existing data to produce actionable alerts and insights towards meaningful interventions. Finally, we will use these digital models to provide predictive performance measures (gaps, bottlenecks, capacity, etc.) under different circumstances and the ageing population trends predicted in WP5.   


This task will involve the manual or semi-automated creation of human-decision making models that can symbolically encode pre-existing decision points about critical care aspects and augment the workflows from Task 4. It will also derive data-driven decision models that capture causal behaviour in order to provide coaching, e.g. helping the person better cope with exercise or medication regimes, and advice to the carer, regarding how activity variables are influencing measured outcomes. 


In this task, we will build proof-of-concepts platforms for the different features developed across Tasks 2-5. More specifically, we will develop prototypes aimed at (a) IoT and data management, (b) the care receiver, and (c) the care provider. In a later phase, we will seek to integrate our prototypes with existing user-facing platforms as a testbed for our work in real environments. Issues of robustness, security, privacy, and always-on availability will be key consideration towards effective, AI-supported decision making and interaction at both the customer and carer ends. 


This task will initially involve the simulated ‘in situ’ development and evaluation of our technology as part of the Bayes Centre/School of Informatics ‘Living Lab’.  It will involve a close collaboration with WP4 colleagues and our health and social care collaborators to leverage their understanding of the older person. This will ensure a user-centred, iterative design of our technology and of its evaluation. In a later phase, in collaboration with WP7 and our care partners, we will explore the possibility of setting up a real-world case-study to investigate a complex intervention and its evaluation.