Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

Data scientists from many different backgrounds combined their expertise to take on dementia in an unusual format for disease research: a three-day datathon. The intensive research event saw teams come together to work on data that is now available in the DPUK Data Portal.

The datathon was jointly organised by DPUK, the Deep and Frequent Phenotyping (DFP) study, and the Alan Turing Institute. The DFP pilot study provided the data and the DPUK Data Portal was the means to work with it. The Alan Turing Institute hosted and organised the event, and, as the national institute for data science in the UK, was an ideal partner to bring big data specialists to the great challenges in dementia research. 

By the end of the marathon analysis, in which the analysts were getting to grips with the complexity and richness of the data in brain scan data, cognitive tests and blood samples, many left keen to make applications for further studies in the Data Portal.

The datathon attracted analysts of all stripes, many of whom had not worked with dementia cohort datasets before. Terry Lyons is a leading mathematician with innovative contributions to the analysis of multimodal streamed data and methods that have applied successfully in mental health contexts. He is also a Turing Fellow. With Dr Andrey Kormilitzin, he helped to bring the event to fruition.

 

Getting Turing and DPUK together seems a very natural objective. Dementia is such an important challenge and the effective use of data to find early signs to direct future research is a key step. This project brings together several modes of information for people with dementia and will likely play a critical role in understanding how to contrast and compare the different perspectives provided by different types of data. - Professor Terry Lyons, Wallis Professor of Mathematics at the University of Oxford and Turing Fellow
Most of the participants were genuinely excited about the data, datathon and the presentations. We are planning on follow up events, perhaps more focussed on each data type at a time. We're hoping to create a community of experts in these particular data and applications of innovative data science methods for Alzheimer's research. - Dr Andrey Kormilitzin, University of Oxford 

 

 

 

 

 

 

 

 

 

 

 

 

Working with the Alan Turing Institute helped to emphasise one of DPUK's core areas of focus: dementia is not just a challenge that psychiatrists or cognitive neuroscientists can solve alone. Data scientists have a hugely important role to play now that we the data and the DPUK technology available.

It's a fantastic result for our first datathon. The data scientists were working with raw, highly complex data from the Deep and Frequent Phenotyping study pilot. I'm in awe. Datathons provide exciting potential for engaging multidisciplinary research. I think the enthusiasm, technology and data resources we have now show great promise for the future in dementia research.
- Dr Sarah Bauermeister, DPUK Data Manager and Senior Researcher

The analysts were working with pilot data from the Deep and Frequent Phenotyping Study. As is the case for all records in the Data Portal, this participant data is pseudonomised.

Read more about the Deep and Frequent Phenotyping Study data.

More on DPUK's data security standards.