What Happened: Researchers from the two companies designed artificial intelligence to detect language data to predict whether a person would develop Alzheimer’s disease, according to a Thursday press release.
The study looked at misspellings, use of punctuation, repetition, object naming and memory in tests.
The study used data from the Framingham Heart Study, a multigenerational study initiated in 1948.
Why It’s Important: Alzheimer’s disease is estimated to effect 5.5 million Americans. It is estimated to be the third leading cause of death in the United States behind heart disease and cancer.
The prediction method using AI from IBM and Pfizer showed 71% accuracy in detecting which people had developed Alzheimer’s.
The results surpassed the 59% accuracy rate shown by current models.
The study from IBM and Pfizer was one of the first to assess the risk of Alzheimer’s disease in the general population.
Previous studies focused on individuals already showing signs of cognitive decline or having a family history of the disease.
“Alzheimer’s disease can affect a wide spectrum of individuals — including those with no family history of the disease or other risk factors — making this broader study critical,” IBM said in a statement.
What's Next: Using the general population could help with clinical studies of drug treatments for Alzheimer’s, as people with a high likelihood of developing the disease would also be included.
Alzheimer’s has no approved drugs or treatment options.
“Our vision is that one day clinicians will have multiple AI and machine learning tools to help identify if an individual is at risk of developing Alzheimer’s disease. One day, doctors might be able to use speed and blood tests in conjunction with each other, leveraging AI to help them predict the risk of Alzheimer’s disease and laying the groundwork for preventative measures,” IBM said.
See more from Benzinga
© 2020 Benzinga.com. Benzinga does not provide investment advice. All rights reserved.