Researchers say AI can predict Alzheimer’s disease with close to 93 percent accuracy
Researchers say they are now able to predict Alzheimer’s disease with close to 93 percent accuracy using artificial intelligence.
More than 800 brain scans helped the AI to identify anatomical changes in the brain that signaled the start of the most common form of dementia, the Worcester Polytechnic Institute in Massachusetts said on Thursday.
The findings follow years of previous research showing that AI could help spot early risk factors for Alzheimer’s, predict risk and identify patients with undiagnosed Alzheimer’s disease.
Being able to use AI to help diagnose Alzheimer’s earlier could give patients and doctors crucial time to prepare and potentially slow the progression of the disease.
“Early diagnosis of Alzheimer’s disease can be difficult because symptoms can be mistaken for normal aging,” Benjamin Nephew, an assistant research professor at the institute, explained in a statement.
“We found that machine-learning technologies, however, can analyze large amounts of data from scans to identify subtle changes and accurately predict Alzheimer’s disease and related cognitive states,” he said.
The MRI scans were collected from 344 people aged 69 to 84, including 281 scans with normal mental function, 332 with mild cognitive impairment and 202 with Alzheimer’s.
The scans included 95 of the brain’s nearly 200 distinct regions and used an AI algorithm to predict patients’ health.
The analysis showed that one of the top predictive factors for Alzheimer’s disease was brain volume loss, which occurs as brain cells stop functioning in the memory-forming hippocampus, the fear-processing amygdala, and the entorhinal cortex, which provides a sense of time.
That was true across age and sex, with both men and women aged 69 to 76 showing a loss of brain volume in the right part of the hippocampus. That suggests it is an important area for early diagnosis, the researchers noted.
The research also showed that how brain regions shrink differs by sex. In females, brain volume loss occurred in the brain’s left middle temporal cortex, which is involved in language and visual perception. For men, it was mainly seen in the right entorhinal cortex.
The researchers believe this could be due to changes in sex hormones, including the loss of estrogen in women and testosterone in men.
These conclusions could help improve methods of diagnosis and treatment going forward, Nephew said. More than 7.2 million Americans are living with Alzheimer’s, according to the Alzheimer’s Association.
More research is being done to reveal other impacting factors.
“The critical challenge in this research is to build a generalizable machine-learning model that captures the difference between healthy brains and brains from people with mild cognitive impairment or Alzheimer’s disease,” Nephew said.
