University of Bristol Momentum Award – Dementias
Lead Research Organisation:
University of Bristol
Department Name: UNLISTED
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Technical Summary
Developing effective treatment for dementia critically depends on characterising the development and progression of cognitive decline many years prior to current dementia diagnosis. ContinUous behavioUral Biomarkers Of cognitive Impairment (CUBOId) leverages a £12M investment in the EPSRC Sensor Platform for HEalthcare in a Residential Environment (SPHERE) Interdisciplinary Research Collaboration, which aims to advance the state of the art in sensing for many different health-related behaviours at home.
The objective of this proposal is to develop novel computational behavioural analysis algorithms that derive signatures relevant to dementia from SPHERE’s sensor network. Using these new algorithms, CUBOId aims to demonstrate that it is possible to reveal previously unseen behavioural biomarkers of early Alzheimer’s disease (AD) pathology, derived from autonomous, continuous, long-term, behavioural measurement.
As proof of principle, enhancing diagnosis will be explored through testing the hypothesis that in Mild Cognitive Impairment (MCI), where subtle cognitive deficits can be difficult to interpret, there is a behavioural AD signature identifiable using SPHERE technology. Second, we explore the hypothesis that behavioural markers of AD observable with this technology will be more sensitive to treatment effects than standard cognitive measures used in clinical trials.
In so doing, the CUBOId team will have developed, tested and de-risked a unique new asset for the community of researchers in the UK Dementias Research Institute, which can also be applied to cohorts in the Dementias Platform UK as well as internationally. Importantly, the proposed proleptic appointment of a “rising star” at Bristol is intended to develop the potential of SPHERE-type sensors and algorithms specifically for use in dementia; to nurture the important interface between computer science and dementia research at the University and to personally lead engagement between Bristol and the DRI.
The objective of this proposal is to develop novel computational behavioural analysis algorithms that derive signatures relevant to dementia from SPHERE’s sensor network. Using these new algorithms, CUBOId aims to demonstrate that it is possible to reveal previously unseen behavioural biomarkers of early Alzheimer’s disease (AD) pathology, derived from autonomous, continuous, long-term, behavioural measurement.
As proof of principle, enhancing diagnosis will be explored through testing the hypothesis that in Mild Cognitive Impairment (MCI), where subtle cognitive deficits can be difficult to interpret, there is a behavioural AD signature identifiable using SPHERE technology. Second, we explore the hypothesis that behavioural markers of AD observable with this technology will be more sensitive to treatment effects than standard cognitive measures used in clinical trials.
In so doing, the CUBOId team will have developed, tested and de-risked a unique new asset for the community of researchers in the UK Dementias Research Institute, which can also be applied to cohorts in the Dementias Platform UK as well as internationally. Importantly, the proposed proleptic appointment of a “rising star” at Bristol is intended to develop the potential of SPHERE-type sensors and algorithms specifically for use in dementia; to nurture the important interface between computer science and dementia research at the University and to personally lead engagement between Bristol and the DRI.
Organisations
Publications
Diethe T
(2018)
Releasing eHealth Analytics into the Wild
Kozlowski M
(2020)
H4LO: automation platform for efficient RF fingerprinting using SLAM-derived map and poses
in IET Radar, Sonar & Navigation
McConville R
(2018)
Person Identification and Discovery With Wrist Worn Accelerometer Data
Poyiadzi R
(2018)
LABEL PROPAGATION FOR LEARNING WITH LABEL PROPORTIONS
Poyiadzi R
(2020)
FACE
Poyiadzi R
(2019)
Active Learning with Label Proportions
Poyiadzi R.
(2020)
Detecting signatures of early-stage dementia with behavioural models derived from sensor data
in CEUR Workshop Proceedings
| Description | Advisor to the National Data Guardian |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Description | Programme grant |
| Amount | £3,630,822 (GBP) |
| Funding ID | EP/R005273/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 09/2018 |
| End | 09/2021 |
| Title | Mild Cognitive Impairment Clinic |
| Description | We have established a clinical service for patients who have mild memory symptoms. The aim of this is to provide early accurate diagnosis, prognostic information and research opportunities - notably the CUBOID study when appropriate. We are using standard clinical tests - neuropsychology, blood tests, neuroimaging and CSF biomarkers - to stratify patients at an earlier stage of disease when both the patient and GP request it. |
| Type Of Material | Model of mechanisms or symptoms - human |
| Year Produced | 2017 |
| Provided To Others? | No |
| Impact | We are planning to evaluate this new service after 1 year. Important outcomes will be patient experience and research recruitment rates. |
| Description | Alzheimer's Research UK (ARUK) CUBOId Presentation for Dementia Researchers |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Other audiences |
| Results and Impact | An overview of the CUBOId project was presented to academics (basic scientists) and clinicians working in the South West of England. The purpose was to raise awareness of the project. Opportunity was given for questions, which helped address any concerns raised about privacy and security. |
| Year(s) Of Engagement Activity | 2018 |
| Description | BRACE Celebratory Event |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Public/other audiences |
| Results and Impact | An overview of the CUBOId project was presented to members of the public at the local dementia charity (BRACE) celebratory event. Opportunity was given for questions and discussion. Two members of the audience expressed an interest in the project. |
| Year(s) Of Engagement Activity | 2018 |
| Description | BRACE Charity Talk for Volunteers |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Supporters |
| Results and Impact | This talk was delivered to the local BRACE charity volunteers. The aim was to give them an update on some of our active research projects, which included an overview of CUBOId. The intended outcome was that volunteers would feel more able to discuss our research with members of the public who support the BRACE charity. |
| Year(s) Of Engagement Activity | 2019 |
| Description | Biogen |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Discussions around the viability of monitoring drug efficacy with digital behavioural monitoring similar to the CUBOID system. |
| Year(s) Of Engagement Activity | 2018 |
| Description | CUBOId Talk at the Bristol Robotics Laboratory |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Industry/Business |
| Results and Impact | The theme of this talk was new technologies in dementia care and research. We were invited to present the CUBOId project. The aim was to raise awareness of the project amongst local researchers, businesses specialising in technology for people with dementia as well as patients and carers. |
| Year(s) Of Engagement Activity | 2019 |
| Description | INSPIRE Event for Medical Students |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Undergraduate students |
| Results and Impact | A brief overview of the CUBOId project was presented to medical students interested in research. The INSPIRE event aimed to inform students of opportunities to become involved in research as undergraduates. The purpose of the CUBOId presentation was to raise awareness of the project and generate interest in becoming involved. A number of students requested contact details to register their interest in becoming involved. |
| Year(s) Of Engagement Activity | 2018 |
| Description | INSPIRE Talk for Medical Students |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Undergraduate students |
| Results and Impact | I was invited to give a talk to medical students who are interested in getting involved in medical research. Medical students were invited from universities in the South West region. The event was held in Bristol. The CUBOId project was presented and medical students were invited to get in touch after the meeting if they wished to find out more or get involved. Although no students contacted me after the event, they did find the project interesting and engaged in discussion after the presentation. |
| Year(s) Of Engagement Activity | 2019 |
| Description | MIT Boston |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Discussions around the viability of digital disease state monitoring with digital behavioural monitoring similar to the CUBOID system. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Northern lights deep learning conference 2023 |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Talk on the CUBOID TV task on leveraging structured and unstructured speech for improving early dementia detection by Dan Kumpik. |
| Year(s) Of Engagement Activity | 2023 |
| URL | http://nldl.org/program |
| Description | Patient & Public Involvement (PPI) Event |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Public/other audiences |
| Results and Impact | A PPI event was run by the ReMemBr group. The purpose was to raise awareness of the CUBOId project and collect feedback on how we should proceed with recruitment and overcome any foreseeable challenges. The event was a success, generating positive discussion. Participants felt reassured that the home sensor technology is not intrusive. Ideas were also generated on how we might reassure potential participants, such as showing them photographs of what the equipment looks like when it has been installed in people's homes. We intend to obtain permission to use photographs of people's homes that are currently involved in the related SPHERE 100 Homes project. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Pfizer |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Discussions around the viability of monitoring drug efficacy with digital behavioural monitoring similar to the CUBOID system. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Talk to selected Japanese academics and policy makers |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Policymakers/politicians |
| Results and Impact | Prof. Ian Craddock gave a talk uder the broad the theme meeting title of "UK dementia research initiatives and recent developments." where he highlighted the forthcoming work that was being funded by the MRC grant as part of the CUBOiD project at the British Embassy in Tokyo. |
| Year(s) Of Engagement Activity | 2017 |
| Description | Together 4 Dementia 2022 talks (Weisong Yang and Dan Kumpik) |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Public/other audiences |
| Results and Impact | Presenting CUBOID plus participating in the panel session organised during the event. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://www.alzheimers-brace.org/event/together-4-dementia-2022/ |
| Description | UK Remote Cognitive Testing Meeting |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Delivered a presentation at an online meeting for Dementia Platforms UK. I provided an outline of the CUBOId project and how we have adapted the study in response to the COVID19 pandemic. I specifically discussed how we developed and now run remote cognitive testing for this study. Feedback was positive with comments about the rich dataset that continues to be collected during the pandemic. |
| Year(s) Of Engagement Activity | 2020 |