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 inaugural Imaging Working Group meeting earlier today

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.

Prof David Llewellyn
DEMON Network Director

Podcast: Using AI & data to fight dementia

Dr Megan O’Hare interviews Professor Bart De Strooper and Professor David Llewellyn, discussing the new UK Dementia Research Institute and DEMON Network partnership to unlock the potential of Artificial Intelligence (AI).

Professor Bart De Strooper is National Director and Group Leader at the UK Dementia Research Institute and Group Leader in his own research he looks at the cellular and molecular mechanisms underlying Alzheimer’s disease and other neurodegenerative disorders.

Professor David Llewellyn is the DEMON Network Director and a Professor at the University of Exeter Medical School and a Fellow at the Alan Turing Institute. His research aims to enhance the timely detection of dementia, with a focus on developing strategies for primary and secondary prevention using machine learning.

The Deep Dementia Phenotyping (DEMON) Network brings together academics, clinicians and other partners from across the world, and now it has joined forces with the UK Dementia Research Institute. The aim of this new collaboration is to rapidly speed up the transformation of data into clinical and biologically relevant knowledge in neurodegeneration research, to strengthen links with clinical researchers and industry, and to drive forward experimental dementia research using data science and artificial intelligence.

There is no universally agreed definition of AI. The term broadly refers to computing technologies that resemble processes associated with human intelligence, such as reasoning, learning and adaptation, sensory understanding, and interaction. An important feature of contemporary AI technologies is that they are increasingly able to make sense of varied and unstructured kinds of data – so what could happen when you combine AI with large amounts of health and societal data? The potential is amazing, and could be the key to unlocking improved dementia risk analysis, diagnosis and treatments.

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.

500 members and climbing!

Our membership has more than doubled since March, and we now have over 500 members from six continents. I’d like to thank our core team (Deputy Director Dr Janice Ranson, Postdoctoral Researcher Dr Charlotte James and Network Administrator Jan Alcott) in particular for all of their hard work in building the Network up from scratch so quickly. What an amazing success. We’ve been promoting our Network through a number of different channels, including Twitter (@DEMONNetworkUK), and we now have a DEMON LinkedIn page:

Our focus has now shifted from growing the Network to organising ourselves and achieving impact. It’s really exciting to see how quickly we’re developing and what diverse interests our members have. Members are now invited to join one or more of our practical Working Groups which will focus on writing papers, applying for funding, transferring knowledge and securing new partnerships. See our latest bumper newsletter for more information:

How big will our Network become? 700 members? A thousand? To be honest I didn’t think we’d manage to get to this point so quickly, so I don’t know. We’re still greedy for new members, so please continue to signpost people to our our webpage: However, I’m satisfied that we now have the critical mass necessary to achieve our ambitious goals. I look forward to working with our members to achieve our vision of revolutionising dementia research and healthcare by bringing innovators together and harnessing the power of data science and AI.

Prof David Llewellyn, DEMON Network Director

National Strategy Workshop Reflections

What a week it’s been for the DEMON Network. Our National Strategy Workshop last Wednesday was the first chance our Steering Committee, National Leads, and Regional Leads have had to meet. During the Workshop Dr Janice Ranson, our Deputy Director, gave a really engaging presentation about the amazing growth of the Network to well over 400 members in just a few months. Our multidisciplinary Network now includes a fantastic mix of data scientists, clinicians, dementia researchers, computer scientists and industry, all keen to collaborate and innovate. Ms Nonye Nwuke, Research Assistant, then gave a fascinating presentation about the results of our recent Collaborative Research Initiatives Survey. In a nutshell it’s clear that our members have wide-ranging interests and are keen to commercialise their research.

Those findings informed our discussions about what we should be doing and how we can most effectively work together. We agreed our five Grand Challenges (see below), and set out our plans for eight Working Groups to deliver practical and tangible outputs over the next year and beyond. Knowledge sharing, collaborative papers and funding applications, and deeper partnerships with organisations including industry will all be key to our success. We’re aiming to get our Working Groups set up and launched within a month so that we don’t lose momentum. Similarly we’ll get our National Strategy Report out to you soon, which will outline our vision and the concrete steps we’ll be taking.

There’s also lots of other exciting stuff in the pipeline, for example we’re establishing a formal partnership with the UK Dementia Research Institute (DRI) – see our newsletter for your invitation to the upcoming launch event. Thank you to everyone who’s helped make the Network so successful; particularly given the difficult circumstances we’ve found ourselves in recently. Now that we’ve built the Network it’s time to get serious and make a real difference. I’m delighted to be working with such an exciting bunch of innovators to do just that.

     Prof David Llewellyn, University of Exeter and the Alan Turing Institute, DEMON Network Lead

Feedback from the Workshop:

“Great @DEMONNetworkUK national strategy meeting today. Exciting times ahead for collaborative dementia research!”

  Dr Timothy Rittman, University of Cambridge, East Regional Lead

“Really interesting morning attending the @DEMONNetworkUK National Strategy workshop. Exciting things to come out in the National Strategy Report, including our grand challenges and new working groups – watch this space!”

     Dr Ríona McArdle, Newcastle University, North Regional Lead

“The workshop provided a significant opportunity to discuss the way forward with the DEMON network and facilitated a common focus for the wide group of experts that are members.  I was extremely impressed at the breadth of skills and experience in the network and the coming together of individuals from so many disciplines with a common purpose.  From the workshop it feels like the network has a real momentum now and I was impressed by the collegiate attitude of the members.  I look forward to further meetings and feel great things will come from the network’s efforts.  I will not hesitate to recommend membership to my colleagues working in the dementia and Artificial Intelligence research areas.”

     Prof Graham Ball, Nottingham Trent University, Midlands Regional Lead

“Meeting the full UK-wide Network for the first time was really exciting.  After hearing about the themes on intelligent experimental medicine and biomarkers, I look forward to next steps when we start the collaborations on these new ideas.”

     Dr Laura Winchester, University of Oxford, Thames Valley Regional Lead

220 members already!

The DEMON Network is off to a great start with 220 members already. That’s fantastic news as the bigger the Network the better the collaborative opportunities there will be for all of us.

We have a fantastic mix of data scientists, AI specialists, clinicians, dementia researchers and industry partners. This diversity will really help people to mix with others with different expertise and from different disciplines.

Members come from across the UK and further afield, which reflects our strategy of recruiting people through regional networks.

We’re really excited at the level of interest, and as you can see the membership is continuing to increase:

Members have expressed an interest in a wide range of Network activities to facilitate interdisciplinary collaboration:

A big thank you to everyone who’s helped us to make so much progress in such a short amount of time. We still want more members of all types, so please promote membership as widely as possible. It’s free and easy using the following link:

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,
N. Ireland


Why should I join?

The need

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.

Your focus

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.

Your skills

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.

The result

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.

Apply now – places are limited

Eligibility criteria

  • 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.

Key facts

  • 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.

DEMON Network Podcast

Stream Dementia Researcher’s latest podcast now discussing the new Deep Dementia Phenotyping (DEMON) Network!   


Today’s topic is the new DEMON Network the new national network for the application for data science and AI applied to dementia research. Led by Professor David Llewellyn at the University of Exeter and supported by Alzheimer’s Research UK, the Alan Turing Institute and Dementias Platform UK. It aims to unite experts from a wide range of fields to find new solutions to research in dementia.

In this podcast, first time host Piers Kotting is with Professor David Llewellyn from the University of Exeter and Dr Carol Routledge, Director of Research from Alzheimer’s Research UK. To discuss what the they hope to achieve through the network and how Early Career Researchers from across all fields and countries, and not only in dementia, can become involved.

A full transcript of this podcast is available for download here.

Machine Learning Datathon to Combat Dementia Blog

A branch of artificial intelligence which is based on training computers to learn patterns has the ability to transform our understanding of dementia. David Llewellyn co-leads the first Dementias Platform UK datathon next month. He explains why machine learning could be the beginning of the end for this devastating condition.

Dementia isn’t a single disease and people with dementia, or who are at risk of dementia, vary enormously. Some forms of dementia are caused by neurodegeneration, including Alzheimer’s disease, and others are caused by vascular problems such as stroke. Not being able to diagnose it early enough is one of the biggest problems, and it’s in this area that AI techniques like machine learning give me hope.

Machine learning is a branch of artificial intelligence which relies on our ability to train computers to learn from data and identify hidden patterns. As computers have become more powerful, so has our ability to harness them and make sense of rich and large datasets. Machine learning already enhances our smartphones and makes internet searching efficient, and we suspect that machine learning has the potential to transform clinical medicine. Machine learning is particularly well suited to dealing with clinical data relating to complex conditions such as dementia, and for that reason we are excited to explore its potential in a datathon.

My hope is that machine learning will help us diagnose the disease early enough so people can receive better support and access ongoing research studies. Why haven’t we been able to diagnose it early? Simply put, the early stages of dementia are invisible. Clinicians are often unsure who to refer for costly, time-consuming and potentially worrying investigations at memory clinics. Some people never go to their doctor and around a third of cases are never diagnosed. As a result it is very challenging to assess patients and recruit them to trials that will be right for them. We need research that gives us new insights into the complex ‘disease signatures’ that underpin dementia and have the potential to enhance clinical practice. But where do we start? Many of my colleagues and I think machine learning is a very promising approach.

Not all machine learning scientists will be familiar with the datathon format but we’re already seeing enthusiasm within the community for this way of working. A datathon is an event where scientists come together to conduct analyses, challenge themselves, learn new techniques, and have fun. It’s a fantastic opportunity to meet other interesting people and make a difference to what is a really big societal challenge. My hope is that this will be the key to improving care, and fuelling the trials which we hope will result in new disease-modifying treatments.

More details on our datathon

When and where is it?

Our machine learning for dementia datathon is running from 1-3 May 2019, at the University of Exeter, Forum

Who is organising it?

The datathon is a collaboration between Dementias Platform UK (DPUK), Alzheimer’s Research UK (ARUK), the Alan Turing Institute and the University of Exeter who have all helped to fund and organise the event. The lead organisers are Dr Sarah Bauermeister (DPUK and University of Oxford), and Professors David Llewellyn and Richard Everson (University of Exeter).

What will it involve?

We will have some brief talks to introduce the event, explain how it works and plan for the future. However, the emphasis will be on getting to know each other and getting our teeth into the data. Over three days we will work in groups to experiment and share knowledge. At the end of the datathon we will reflect on what we’ve learnt and think about how we might want to work together in the future.

Who are you looking for?

Places are limited but people will be selected on merit and enthusiasm. Under-represented groups are particularly encouraged to apply. To get the most out of the event people will need to be able to program and have experience of machine learning techniques. Experience of dementia-related data or research is not necessary as clinical support will be provided.

How do people apply?

Fill in the online form here.

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.

Apply now!


Artificial Intelligence and Dementia: Q&A

Artificial Intelligence (AI) – human intelligence exhibited by machines – in healthcare is developing rapidly, with many applications currently in use or in development in the UK and worldwide.

We speak to Dr David Llewellyn, a Senior Research Fellow in Clinical Epidemiology at the University of Exeter Medical School, about the impact of AI on dementia diagnosis. David’s research focuses on how data science and AI can improve the way in which we conceptualise neurocognitive disorders in order to improve diagnosis, treatment and prevention.

How do you define AI as it relates to healthcare and what are some of the biggest transformations that it will bring to the field?
In its broadest sense, artificial intelligence is the creation of generalisable intelligence. At the moment the majority of progress is being made with machine learning, where we’re teaching machines to learn patterns in real clinical data. We’re taking techniques that have been developed for a wide range of purposes, for example, self-driving cars and search engines, and applying this to real clinical data. This gives us a massive advantage in that we’re able to handle a much richer range of data than we were able to do so before with traditional statistical methods. We’re developing pieces of software which can be used by clinicians or patients to improve healthcare efficiency, patient safety, and patient outcomes.

How close are we to a world where AI are used to diagnose and treat patients?
I think that AI is already used to diagnose and treat patients but in limited ways. For example, before patients come and see their GP, they’re increasingly using the internet. They’re using AI through search engines to work out what their symptoms might mean. Doctors are also increasingly using various forms of AI and we’re seeing the growth in decision-making aid. It’s very much that the doctor is still in control, but they’re getting more targeted information about individual patients.

Do you foresee a future where AI technologies can operate autonomously in healthcare?
We’re much further away from systems that can actually make decisions autonomously without the doctor and without any clinical oversight. If we think about autonomous cars as an analogy, we’ve got cruise control. Similarly with AI in healthcare, we’ve got aids to decision-making. What we don’t have are ‘robot doctors’ that can diagnose and treat patients without any human oversight. I think that will come, but we’re a long way from that.

The biggest question at the moment is how we are going to regulate that process. If it’s an aid for doctors but the doctor is still in control, then you can regulate it as a medical device. But if it’s autonomous, then actually what it’s doing is practicing medicine, not supporting a doctor who practices medicine. Medical societies regulate people who practice medicine but who exactly is going to regulate machines that have the capacity to practice medicine? I don’t think we’re anywhere near to reaching a solution for that and there is certainly no way which we can effectively regulate that at the moment.

Are there any common misconceptions or general misunderstandings about AI that you believe could use some clarity?
When we think about how AI can influence medicine, there’s often the misconception that it’s going to deskill the workforce and put people out of a job. However, when you bear in mind the immense pressures that the NHS is under, I think AI technologies in healthcare should be seen as a massive opportunity to improve patient outcomes and to make the jobs themselves better for clinicians. Particularly things that are routine – they can be taken away from a clinician’s job. It will become less about whether AI will replace clinicians, but more about how clinicians will use the technology to enhance their own abilities. That’s a tremendous opportunity if you can empower clinicians to think in that way. It will allow them to focus on the human side of medicine, which for most medical professionals is the most interesting bit!

Identifying people with dementia is clinically challenging given the non-specific pattern of symptoms associated with it. You’ve recently developed a computerised decision support system called DECODE to help address this. Can you tell us more about it?
It’s a very difficult clinical challenge assessing patients who you may not know well and who are concerned about their memory and thinking, and trying to work out whether they are just ageing normally as no two cases of dementia are exactly alike. If you’re a non-specialist, you may not have seen a patient with a particular combination of signs and symptoms before. So one of the advantages of DECODE, a machine learning-driven system, is that it can learn to recognise patterns in hundreds, thousands, potentially millions of dementia cases and work out what needs to happen clinically to benefit that patient. So it’s the idea it doesn’t get tired or distracted and it’s very consistent. It’s not a completely objective system though, as it captures the human expert decision-making that we used to train it in the first place.