A new AI model can predict the onset of Alzheimer’s disease more accurately than standard clinical techniques by analyzing how people describe a picture of a cookie theft, according to a new study. Researchers from IBM and Pfizer trained the model to detect signs of speech impairment in written descriptions of the image, which is frequently used to test for cognitive disorders. The transcriptions were taken from the Framingham Heart Study, which has tracked the health of more than 5,000 people and their families since 1948. The samples were collected before the participants began showing symptoms of Alzheimer‘s. The researchers then…
This story continues at The Next Web
Or just read more coverage about: IBM
from The Next Web https://ift.tt/2HvyQAm
