Dementia is a significant global healthcare challenge, affecting over 55 million people worldwide with the number of cases expected to almost treble over the next 50 years, so early detection is crucial. The main cause of dementia is Alzheimer’s disease, which accounts for 60-80% of cases.
The tool is able to identify whether people with early signs of dementia will remain stable or develop this condition in four out of five cases, using routinely collected data. This new approach can reduce the need for invasive and costly diagnostic tests like lumbar punctures, while improving treatment outcomes by indicating when early interventions like lifestyle changes or new medicines will work best.
CPFT Research and Development Director Dr Ben Underwood worked with the Trust’s memory clinics staff and patients on this study, supported by the Windsor Research Unit.
Ben (photo) said:
“Memory problems are common as we get older. In clinic I see how uncertainty about whether these might be the first signs of dementia can cause a lot of worry for people and their families, as well as being frustrating for doctors who would much prefer to give definitive answers. The fact that we might be able to reduce this uncertainty with information we already have is exciting and is likely to become even more important as new treatments emerge.”
The research team developed a machine learning model able to predict if an individual with mild memory and thinking problems will develop Alzheimer’s disease, and how quickly. Their findings published in eClinical Medicine show that it is more accurate than current clinical diagnostic tools.
Senior author Professor Zoe Kourtzi from the Department of Psychology at the University of Cambridge said: “We’ve created a tool which, despite using only data from cognitive tests and MRI scans, is much more sensitive than current approaches at predicting whether someone will progress from mild symptoms to Alzheimer’s – and if so, whether this progress will be fast or slow.
"This has the potential to significantly improve patient wellbeing, showing us which people need closest care, while removing the anxiety for those patients we predict will remain stable. At a time of intense pressure on healthcare resources, this will also help remove the need for unnecessary invasive and costly diagnostic tests.”
The algorithm was able to distinguish between people with stable mild cognitive impairment and those who progressed to Alzheimer’s disease within a three-year period. It was able to correctly identify individuals who went on to develop Alzheimer’s in 82% of cases and those who didn’t in 81% of cases and was around three times more accurate than standard clinical markers. The model can identify who would benefit from new dementia treatments as soon as possible and who needs close monitoring as their condition is likely to deteriorate rapidly, as well as who may need a different clinical care pathway for their symptoms.
The algorithm was tested on data from a research cohort but was also validated using independent data that included almost 900 individuals who attended memory clinics in the UK and Singapore. In the UK, patients were recruited through the Quantitative MRI in NHS Memory Clinics Study (QMIN-MC) led by study co-author Dr Timothy Rittman at CPFT and Cambridge University Hospitals NHS Foundation Trust.
The research team say this data shows it should be applicable in a real-world patient, clinical setting. They now hope to extend their model to other forms of dementia (vascular and frontotemporal) using different types of data, such as markers from blood tests.
They collaborated with a cross-disciplinary team including Professor Peter Tino at the University of Birmingham and Professor Christopher Chen at the National University of Singapore. It was supported by CPFT’s memory clinics, funded by Wellcome, the Royal Society, Alzheimer’s Research UK, the Alzheimer’s Drug Discovery Foundation Diagnostics Accelerator, the Alan Turing Institute, and the National Institute for Health and Care Research Cambridge Biomedical Research Centre.
Read more about this research and how the AI tool was developed on the University of Cambridge website.
