Experts in machine learning and dementia research convening at the University of Exeter identified that machine learning can be used to predict incorrect initial diagnoses.
The Datathon is a collaboration bringing together researchers from across a variety of disciplines, with the aim to accelerate dementia research using large datasets and real-world clinical data.
They also identified people who were initially diagnosed with dementia who then improved, and now know that machine learning can be used to predict patients whose initial diagnosis may be incorrect.
With further refinement, the researchers believe this has the potential to inform how patients at risk of dementia are identified and recruited to clinical trials.
Over three days, researchers worked together to tackle and digest the data, and presented their findings. The event was the inaugural meeting of the Deep Dementia Phenotyping (DEMON) Network which works to enhance UK capacity for data science and AI applied to dementia.
Dr David Llewelyn, Associate Professor of Neuroepidemiology and Digital Health, at the University of Exeter Medical School, said: “The Datathon was a fantastic success largely because of the talented, diverse and engaged people who came. It was a great example of how different organisations can work together to really drive things forward, and we’re excited to see what comes next.
“We’ve secured funding to set up a DEMON Network to follow-up on the Datathon and develop data science and AI capacity for dementia research. It was also made possible by the passionate support from the University ofExeter, Dementias Platform UK, the Alan Turing Institute and Alzheimer’s Research UK.”
Dr Sarah Bauermeister, Senior Researcher & Senior Data Manager at the University of Oxford, said: “The Exeter datathon was incredibly inspiring. We had 22 participants with research skills ranging from data science, machine learning to epidemiology and psychology – some travelling from Canada and Europe to work collaboratively to uncover the origins of dementia. The first wave of feedback we’ve received has been tremendously positive – the five researchers we interviewed highlighted the amazing learning experience of the datathon, the benefits of collaboration and the privilege of working with big real-world data sets.”
The Datathon is supported by the Alan Turing Institute, Alzheimer’s Research UK, Dementias Platform UK and the University of Exeter.