Alzheimer’s diagnostics gets Cambridge AI boost

Published in eClinical Medicine, the study describes how the team built an algorithm using cognitive tests and MRI scans showing grey matter atrophy in over 400 individuals from a research cohort in the US. The AI model was then tested using real-world patient data from a further 600 participants from the same US cohort, as well as longitudinal data from 900 people from memory clinics in the UK and Singapore.

The algorithm could distinguish between stable mild cognitive impairment and those who progressed to Alzheimer’s disease within a three-year period. It was able to correctly predict the development of Alzheimer’s in 82 per cent of cases and correctly identify those who did not develop the disease in 81 per cent of cases – figures roughly three times more accurate than current clinical diagnostics.  

“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,” said senior author Professor Zoe Kourtzi, from Cambridge’s Department of Psychology.