This is an archived article and the information in the article may be out of date. Please look at the history’s timestamp to see when it was last updated.
DENVER (KDVR) – New research shows you may be able to predict whether a person is likely to develop Alzheimer’s disease later in life based on their writing style.
The fascinating discovery was discovered by researchers at IBM who used an artificial intelligence program to sift through written tests submitted by 80 men and women in their 80s.
“This is in addition to a lot of research and work that has already been done in this space,” said Dr. Peter S. Pressman, neurologist at UCHealth.
Using certain algorithms, the researchers were able to identify a specific part of the group that exhibited similarities in their writing styles.
“Some words that we use every day in speech, like: ‘a’, ‘and’ – short little words started to fade, fade away as the speech got simpler over time. time in writing ”, Dr. Pressman.
Spelling and grammar errors have been identified in almost all subjects who eventually developed Alzheimer’s disease.
In Colorado alone, approximately 76,000 adults over 65 have Alzheimer’s disease. That figure is expected to climb to 92,000 by 2025, according to the Alzheimer’s Association of Colorado.
“I think it’s really important because we really need to diagnose Alzheimer’s disease as early as possible,” said Dr. Pressman.
According to the data collected, the AI program’s prediction had an accuracy rate of 75%.
“75% accuracy is pretty good for a machine learning algorithm. I think it wouldn’t be considered good enough to fit into daily care at this time. So there will be more work that will be required, ”said Dr Pressman.
To learn more about the new study, Click here.