Digital Innovation & Data Science for Dementia and Longevity Research Event – Top 5 takeaways
Event hosted by the Deep Dementia Phenotyping (DEMON) Network and Ageing Research at King’s (ARK)
Blog written by Chris Albertyn, King’s College London DEMON Network Regional Lead & ARK Project Manager
On Thursday 26th November 2020, the Deep Dementia Phenotyping (DEMON) Network and Ageing Research at King’s (ARK) co-hosted a launch event highlighting the crossover between dementia and longevity research*. In particular, the focus was on the nascent impact of digital technology, such as monitoring healthy ageing through apps and wearables, and data science approaches to human ‘omics data & biomarkers. I was delighted to chaperone the event & learn about the wonderful work the speakers were doing. In my personal opinion, I felt my top 5 takeaways were:
1. Longevity & Dementia research are ‘two sides of the same coin’.
It seems to me that longevity research is predominantly about extending ‘health span’ by promoting personal, social and economic behaviours, at an individual and community level, that broadly increase independence & resilience to age-related adversity. Whereas dementia research identifies ‘risks’ and ‘causes’ of cognitive decline, and how we can optimally mitigate and reduce these to avoid or stall its progression. Longevity also seems to take a wider holistic approach, for example including financial, political & consumer behaviour in addition to health outcomes. Whereas dementia research is more focused on a biopsychosocial model of ageing. An alliance between these two streams of work is highly complementary, and an exciting prospect for future collaborations.
2. The ‘earlier the better’.
Both longevity & dementia research accept that we must take a full lifespan approach – ageing starts with your parents. This is the same for promoting healthy ageing and preventing decline. Collecting rich longitudinal data, including genetic information, is exceptionally valuable in that it affords us the opportunity to identify key inflection points in individual & population ageing. Prof Llewellyn mentions at the very beginning, that a major issue with the dementia diseases clinical trials is that we’re often too far along the patient’s clinical progression. So we need to target pathology earlier. More accessible & less invasive markers, such as blood-based biomarkers introduced by Dr Petra Proitsi, and digital technologies described by Dr Claire Steves & Dr Andrew Owens will provide critical data to allow us to do this.
3. Digital technology allows us to reach much farther & wider than ever.
Smartphones, apps, wearables, augmented reality software and home-based monitoring sensors. All of these were mentioned in the event, and offer exciting promise for researchers to reach a significantly higher proportion of the population than ever before. Typically, participants for dementia studies have mostly been recruited at the point of clinical assessment (or after). However, by using digital technologies we can now access participants, without geographical restriction, at any point in their lives as long as they have access to the technology & wi-fi. To quote Dr Andrew Owens: “digital biomarkers produced by Remote measurement technologies (RMTs) could move us away from a ‘diagnose & treat’ to a ‘predict & pre-empt’ model of care”. While not as detailed as a clinical examination, we can obtain continuous and objective data such as physical activity/gait, sleep, vital signs (heart rate etc), financial transactions, online behaviour, and self-administered cognitive & lifestyle assessments. Partnered with healthcare data, this is an incredibly rich and exciting resource not only for researchers, but also clinical practitioners!
4. Data science & artificial intelligence techniques are exciting & progressive, but we must be cautious.
Dr Cassandra Coburn raises a pertinent point, applied data science is hugely valuable & exciting, but this must be tempered with appropriate caution. The stakes are just too high to be complacent. It still has many limitations, such as ensuring reproducibility, data security & validity, including contextual information, and interest from industry pushing unconscious incentives potentially compromising scientific integrity. The last point is particularly true in the longevity research space (although not remiss in dementia research either) where I think researchers need to remain vigilant for an encroachment of industry bias or influence. There is significant investment in healthy ageing, but not always appropriately targeted. The institutional processes determining academic integrity in research must be robust to ensure scientific and ethical rigor is not compromised. It is easy to be lured in by the talk of an ‘AI summer’, but I personally think it’s much too early for that…we’re still learning our way, the frost is melting and not everything is turning into flowers, and therefore we’re closer to an ‘AI spring’.
5. Our strongest asset resulting in most immediate impact – collaboration!
Finally, what seemed most clear to me, and echoed by the responses of panel members in the final few minutes of the discussion, is that our best chance of immediate impact are facilitating diverse and extensive collaborative relationships. This is born out particularly with Dr Claire Steves example of the ‘COVID collaborative’: an initiative led by junior doctors in over 55 hospitals in 12 countries to recruit over 4 million people to the COVID symptom tracker app! In a broader context, ARK brings together such a wealth of expertise across disciplines to create the Longevity AI Consortium which will have impact across the international ageing society! And finally, with the DEMON network now having over 700 members of different expertise across 32 countries, there is a firm foundation for innovative dementia research to take root and thrive! For example, I for one am very excited about cross-over explorations of digital technology and biomarkers in dementia research. Something that DEMON can easily facilitate through its network of bespoke working groups. But more than that, what is really highlighted is that we have only just scratched the surface. There is so much more to do and explore – come join us!
The Deep Dementia Phenotyping (DEMON) Network:
Ageing Research at King’s (ARK)
* for a list of the speakers & titles, please see: https://www.kcl.ac.uk/events/digital-innovation-data-science-for-dementia-and-longevity-research
Working Group meetings launch
We’re excited to announce that our inaugural Working Group meetings are now underway. Yesterday Dr Danielle Newby Prevention Working Group Lead from the University of Oxford kicked us off with the our first meeting. This was followed today by Dr Timothy Rittman, University of Cambridge, and Dr Michele Veldsman, University of Oxford, Co-Leads of the Imaging Working Group. We’re staggering the Working Group meetings over the month to make it easier for people who are keen to be involved in more than one. We will be holding regular Working Group meetings in Applied Models and Digital Health, Genetics and Omics, Biomarkers, Experimental Models, Drug Discovery and Trials Optimisation, and Methods Optimisation.
The focus of these meetings will be on our tangible outcomes: collaborative papers and grants, knowledge transfer activities and new partnerships. DEMON Network members are invited to get involved in these Working Group meetings, and between meetings we’ll be using our Working Group Slack channels to throw around ideas. Join the Network here for free if you’re not already a member.
A year on from our launch in November 2019 and we already have 687 members from six continents. The launch of these Working Group meetings is a major step forward in achieving our vision to revolutionise dementia research and healthcare by bringing innovators together and harnessing the power of data science and AI. Thank you to everyone who’s passion has made such fast progress possible.
Monthly seminar series launched
We are launching the DEMON Network Monthly Seminar Series in response to huge demand from our members.
Seminars will include live streamed events covering a range of topics related to the application of data science and AI to dementia research and healthcare. All seminars are freely available to Network members and will be advertised in our newsletter. (Join here for free if you’re not already a member of the DEMON Network.) The first event, and each alternate month thereafter, will be hosted jointly with the UK Dementia Research Institute (DRI) with whom we have an official partnership. Many of our members have expressed an interest in giving talks, but we welcome additional speaker suggestions. We’re also interested in mixing up the format, for example holding debates and interactive workshops. Contact us with your ideas.
This Friday 2nd October you are invited to the inaugural seminar featuring talks and Q&A with two outstanding speakers:
Dr Timothy Rittman
Senior Clinical Research Associate, University of Cambridge
Consultant Neurologist, Addenbrookes Hospital
DEMON Network East UK Regional Lead
Understanding tauopathies – from neuroimaging to mechanisms
Neurodegenerative tauopathies such as Progressive Supranuclear Palsy and Corticobasal Degeneration allow us to investigate how tau and its associated pathologies cause clinical syndromes. Neuroimaging gives us the opportunity to study these diseases in vivo, to understand how pathology links to macroscopic changes in brain structure and functional organisation, and ultimately to clinical syndromes. In this talk I will cover some of the advances we have made to understand the links between tau pathology, brain volume loss and functional brain networks. I will also discuss how these advanced neuroimaging techniques that are shedding light on neuropathology, can become clinically useful biomarkers.
Prof Valentina Escott-Price
Group Leader at UK DRI at Cardiff
From genes to treatment or how to find a needle in a haystack
Advances in the treatment of Alzheimer’s Disease (AD) are more pressing than ever due to socioeconomic needs. The field notably shifted away from a purely neurocentric view, largely since Genome-Wide Association Studies identified several risk genes that are primarily expressed in microglia and not in neurons. The challenge is now to leverage the massive amount of genetic data to decipher disease mechanisms and design effective therapeutic interventions for AD. In my talk I will provide an overview of the methodologies for reliable detection of individuals at high risk of AD using common genomic variation, outline my current research in incorporating rare variants for disease probability calculation, describe data and methods needed to recover “missing heritability” in AD, and challenges associated with it.
DPUK datathon at Ulster University Postponed
*** Due to Coronavirus the DPUK datathon at Ulster University has been postponed ***
Hopefully it will be rearranged for later in the year. You can sign up for updates about the DPUK datathon series here.
Innovate in multidisciplinary teams to reveal new insights for dementia treatment
– Free cohort analysis workshop to kick-start new research
– For specialists in statistics or machine learning methods
– 12-14 May, 2020, Ulster University,
Why should I join?
Clinical trials for dementia are moving to intervene at a much earlier stage in the disease progression – before the onset of dementia itself. As the amount of data that we have available to us increases rapidly, it is becoming vital to innovate in order to make sense of it and gain new insights.
At the Ulster datathon, you will work with others in the DPUK Data Portal. You will experiment with different methodologies to predict dementia risk and likelihood of conversion from mild cognitive impairment to dementia. Research questions will centre around longitudinal modelling of disease and dementias progression.
Successful applicants may have a dementia or data science specialism, experience in machine learning or experience in applied classical statistics. Participants will be carefully selected to ensure a complementary interdisciplinary mix of skills.
You will be part of an interdisciplinary research collaboration. Teams will receive ongoing support via DPUK Reach to develop their ideas into full study proposals and published research following the datathon.
What will the Ulster datathon be like?
How should I join?
Complete the application form via the link below. Any questions, please contact us.
- Data scientists with some experience of working with complex data.
- Experience of statistical techniques.
- Experience of working in dementia or health research will be useful, but is not essential.
- University or industry-based.
- UK and further afield.
- The deadline for applications is 9am on Thursday 3 April 2020.
- Three-day intensive workshop format from 12-14 May 2020. If you can’t make these dates, find out about other future DPUK datathons.
- The datathon takes place at the Ulster University Magee Campus, Derry~Londonderry.
- Places are selective and strictly limited.
- Attendance is free.
- Travel bursaries will be available for early career scientists travelling from outside of Ireland. Please indicate on your application form if you would like to be considered for one.
Machine Learning for Dementia Datathon
Are you a data scientist interested in dementia? We’re looking for innovators with expertise in machine learning to take part in an exciting datathon on the 1st-3rd of May 2019 at the University of Exeter.
The event will bring together scientists to develop new ways of predicting and diagnosing dementia with real-world clinical data. This will be the inaugural meeting of the Deep Dementia Phenotyping (DEMON) Network which will enhance UK capacity for data science and AI applied to dementia.
Travel bursaries will be available to support early career researchers on a competitive basis. The datathon is supported by the Alan Turing Institute, Alzheimer’s Research UK, Dementias Platform UK, and the University of Exeter.
So – go on then – why will the @UniofExeter #DPUKdatathon be so exciting? @DrDJLlewellyn & @S_Bauermeister will be leading our first on 1-3 May. Sign ups this way👉 https://t.co/EzUO7aWrqN @ARUKscientist @turinginst #ARUKconf pic.twitter.com/rNsp6jlQqq
— Dementias PlatformUK (@DementiasUK) 19 March 2019