Artificial intelligence outperforms clinical tests at predicting Alzheimer

Submit
ac.uk

Artificial intelligence outperforms clinical tests at predicting Alzheimer

AI summary of the linked article

Cambridge researchers have developed a machine learning model that predicts whether people with mild memory and thinking problems will remain stable or progress to Alzheimer's disease, and it is more accurate than current clinical tools. The model, published in eClinical Medicine, correctly identified future Alzheimer's cases in 82% of cases and correctly identified non-progressors in 81%, using only cognitive tests and MRI scans. The team, led by Professor Zoe Kourtzi of the University of Cambridge, reports it was around three times more accurate than the current standard of care. It was trained on data from over 400 people in a US research cohort and validated on data from memory clinics in the UK and Singapore.

Recommended by 1 curator
No comments yetWhat caught your eye? Start the discussion.