Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  MRC DiMeN Doctoral Training Partnership: Developing a carer-facing assessment for the automated assessment of progression of cognitive symptoms in people with Mild Cognitive Impairment (MCI)


   MRC DiMeN Doctoral Training Partnership

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Dan Blackburn, Dr H Christenson  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Background

Mild Cognitive Impairment (MCI) is a heterogenous clinical entity that describes patients with demonstrable cognitive deficits but without functional impairment. The aetiology is diverse, though a significant proportion of patients have Alzhiemer’s disease. In workshops we have run, clinicians, patients and care-partners described the frustration with current pathways. There has been a 682% increase in referral rates to memory clinics resulting in increased waiting times and people with MCI being discharged without adequate follow-up because of insufficient resources, causing anxiety and distress. CognoSpeakTM (www.cognospeak.org) represents a unique approach to assessing cognition using speech analytics. It is an online tool that engages the patient in a conversation, placing a high demand on cognitive domains. It also tracks levels of depression and anxiety. The Covid-19 pandemic highlighted the need for better, remote assessments. CognoSpeakTM can be done remotely reducing appointment-related travel time, costs and anxiety.

Objectives

This project will investigate:

1. Adapting the computerised doctor to receive responses from care partner

a. Developing a survey based in existing tools that the care-partner can complete to provide a more complete assessment of cognition and function.

b. Including an pen and paper assessment of Anosagnosia into CognoSpeak

c. Develop a semi-structured interview that could be adapted for an Intelligent Virtual agent

2. Co-design with care-partners from different ethnic minorities groups to ensure if is suitable for all participants.

3. The acceptability and accuracy of repeated caregiver surveys and semi-structured interviews to investigate longtitudinal tracking of cognition in pwMCI.

4. Investigate acceptibality and accuracy of care-partner surveys versus verbal

a. answers to a semi-structured intereview analysed using a quantitative approach.

b. Answers to semi-structured interviews analysed using Automatic Speech Recognition and Machine Learning

Experimental Approach.  

This project will progress CognoSpeakTM to become a standardised remote assessments of pwMCI , which can reduce costs and ensure high- level, consistent patient experience. We have a working prototype and over 300 recordings. In order to do this the PhD student will

1. Adapt existing tools to take a semi-structured format to collect data from care-partners. Current tools include the Cambridge Behavioural Inventory and the Informant Interview of the GPCOG Screening Test.

2. Adapt CognoSpeakTM to measure anosognosia using a discrepancy between self-and informant-evaluations of cognitive and functional performance. This can be conducted using standardised forms which the student will incorporate into the CognoSpeakTM tool.

3. The care-partner will also include 2-3 short questions asked by the PhD students but suitable for CognoSpeakTM to ask. The informant will be asked to describe their partner and the memory and functional difficulties they experience. These answers will be investigated using a qualitative approach to produce a list of themes described in people with MCI due to Alzheimer’s disease (biomarker positive) versus pwMCI who are biomarker negative.

The student will be aided by the on-going recruitment and longitudinal follow-up of cases of MCI as part of the larger CognoSpeakTM project. The student will take part in running workshops with care partners to pilot the new carer-facing component and then recruit at least 40 care-partners in year 2 of the project and investigate acceptability of repeat care-giver assessments every 3-6 months.

The student will also run a wider recruitment of carers for them to complete the surveys and answer questions about the person they care for who has an established diagnosis of MCI or AD. This recruitment will be through the Join Dementia Research Website. This will recruit larger numbers but will have a prospective viewpoint to describe the early signs of Alzheimer’s that can be tested in the prospective data collection

This project will provide training in the following areas:

  • Interdisciplinary skills (in between engineering/computational and clinical (cognitive neurology).
  • Co-design technology development with pwMCI (including those from ethnic minority groups) and clinicians will ensure accptability and scalability of tool.
  • Working with an industrial partner will provide a business approach to medical software development.
  • Quantitative skills (computation, data analytics and informatics and developing digital and technology excellence as the student will experience web design and large scale data collection.

Novelty and Timeliness

Alzheimer Research UK recently identified the urgent need to invest in `Developing digital tools for easier early detection of disease’. NIHR’s Highlight Notice (March 2021) stated the need to focus on dementia and underserved populations. There is a stark underrepresentation of people from diverse ethnic and lower socio-economic backgrounds in memory clinics. CognoSpeakTM will provide a lower-barrier (accessible, easy-to-use and “friendly”) method for underrepresented communities to access cognition. We will leverage existing work with ethnic minority groups in Sheffield to ensure we recruit people living with MCI (pwMCI) from ethnic minority groups

Department support:

There are two post-docs working on CognoSpeak along with 3 PhD students who will all be in place in Oct 2023. There is also a neurology Clinical Lecturer working in the field of post-stroke dementia who will be able to the support the student. The Sheffield BRC academy will also offer peer support and training in addition to that provided by the MRC.

Benefits of being in the DiMeN DTP:

This project is part of the Discovery Medicine North Doctoral Training Partnership (DiMeN DTP), a diverse community of PhD students across the North of England researching the major health problems facing the world today. Our partner institutions (Universities of Leeds, Liverpool, Newcastle, York and Sheffield) are internationally recognised as centres of research excellence and can offer you access to state-of the-art facilities to deliver high impact research.

We are very proud of our student-centred ethos and committed to supporting you throughout your PhD. As part of the DTP, we offer bespoke training in key skills sought after in early career researchers, as well as opportunities to broaden your career horizons in a range of non-academic sectors.

Being funded by the MRC means you can access additional funding for research placements, international training opportunities or internships in science policy, science communication and beyond. See how our current DiMeN students have benefited from this funding here: https://www.dimen.org.uk/blog

Further information on the programme and how to apply:

https://www.dimen.org.uk/how-to-apply

Biological Sciences (4) Computer Science (8) Mathematics (25) Medicine (26) Psychology (31)

Funding Notes

iCASE Award: Industrial partnership project
Fully funded by the MRC for 4yrs, including a minimum of 3 months working with an industry partner.

Funding will cover tuition fees and an enhanced stipend (around £20,168). We also aim to support the most outstanding applicants from outside the UK and are able to offer a limited number of full studentships to international applicants. Please read additional guidance here: https://www.dimen.org.uk/eligibility-criteria
Studentships commence: 1st October 2023
Good luck!

References

1) Fully automated assessment of Cognition based on speech and language. RPD O'Malley, B Mirheidari, K Harkness, M Reuber, A Venneri, T Walker. Journal of Neurology, Neurosurgery & Psychiatry 92 (1), 12-15
2) An interactional profile to assist the differential diagnosis of neurodegenerative and functional memory disorders. Markus Reuber, Daniel Blackburn, Chris Elsey, Sarah Wakefield, Kerry Ann Ardern, Kirsty Harkness, Annalena Venneri, Danielle Jones, Chloe Shaw, Paul Drew. Alzheimer’s Dementia and other Dementias. 2018. Doi.org/10.1097/WAD.0000000000000231
3) Characterising spoken responses to an intelligent virtual agent by persons with Mild Cognitive Impairment. Gareth Walker, Lee-Anne Morris, Heidi Christensen, Bahman Mirheidari, Markus Reuber and Daniel J. Blackburn. Clinical linguistics & phonetics 2020, 1-16 A comparison of acoustic and linguistics methodologies for Alzheimer’s dementia recognition N Cummins, Y Pan, Z Ren, J Fritsch, VS Nallanthighal, H Christensen,Interspeech 2020, 2182-2186
4) Detecting signs of dementia using word vector representations Bahman Mirheidari, Daniel Blackburn, Traci Walker, Annalena Venneri, Markus Reuber, and Heidi Christensen. Interspeech conference paper, 2018
5) Multi-task estimation of age and cognitive decline from speech. Y Pan, VS Nallanthighal, D Blackburn, H Christensen, A Härmä ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.