An analysis of writing patterns may help spot early signs of Alzheimer's disease years before the onset of the symptoms, says a new study by IBM researchers.
The study involved a group of 80 men and women in their 80s, The New York Times reported on Monday.
They were participants in the Framingham Heart Study, a multi-generational study initiated in 1948 that has spurred thousands of health studies.
As part of it, they took a writing test. At that time, none of the 80 participants developed Alzheimer's disease.
The IBM researchers used an artificial intelligence (AI) programme that analysed subtle differences in language to examine the word usage by the participants.
The AI programme identified that one group of the participants was more frequent in repeating some words.
They also used a simple grammatical structure in their language and tended to miss words like "the," "is" and "are."
The members of that group went on to develop Alzheimer's disease later.
In predicting who would get Alzheimer's disease, the AI programme was found to be 75 per cent accurate, according to the study, said the NYT report.
"We had no prior assumption that word usage would show anything," Ajay Royyuru, Vice President of health care and life sciences research at IBM Thomas J. Watson Research Center in Yorktown Heights, New York, where the A.I. analysis was done, was quoted as saying.