Researchers from Mount Sinai recently published research that may improve neuroscientists’ understanding of the progression of Alzheimer’s and other forms of cognitive decline.
Learningpublished on Tuesday in Acta Neuropathologica Communications, reveals a potential new target that may provide more clues about why humans fall into cognitive decline. It has been shown that white matter may be a more important region to look at than previously thought.
To make this discovery, the research team used a machine learning algorithm as opposed to traditional biomarkers such as amyloid plaques. The algorithm used multiple learning (MIL)a type of supervised machine learning, Kurt Farrell, one of the study’s authors, said in an interview.
If they had used an algorithm other than MIL, the researchers would have had to go in and annotate by hand every time they found a particular brain pathology in the slides, he said. But with the MIL approach, the research team was able to assign labels to the slides—in this case, the presence or absence of cognitive impairment. The algorithm then figured out what in each slide distinguished the two labels it was assigned. It’s a more unbiased approach than non-MIL algorithms, Farrell said.
The algorithm was trained by examining structural and cellular characteristics of postmortem human brain tissue samples that were donated by more than 700 people who had experienced cognitive decline before their death.
The samples were taken from the medial temporal lobe and frontal cortex — those areas of the brain most relevant to cognitive impairment, according to Farrell. When collecting these samples from biorepositories around the country, he said his team focused on a group of individuals who were aged and had hyperphosphorylated tau and a absence of beta amyloid, two hallmarks of Alzheimer’s disease. The first occurs when the cells’ multiple phosphorylation sites on the tau protein become fully saturated, and beta amyloid is the main component of the amyloid plaques found in the brains of people who have Alzheimer’s.
After the algorithm was trained and running on the data set, the team came across an interesting finding: the algorithm produced heat maps showing that the main reason it made the decision about whether or not someone was cognitively impaired during their lifetime was related to with the white matter in the sample.
It was a “quite striking” finding because the research team’s working hypothesis going into the study was that the algorithm would likely focus on gray matter, Farrell said. He pointed out that gray matter is often examined in neuropathology studies for Alzheimer’s, while neuroscientists have yet to look for clues in white matter.
“To distill it down, the algorithm found that an area of the brain that we don’t look at often is actually more important than the one that we do,” Farrell said.
Alzheimer’s disease and other dementia-causing conditions are multifactorial diseases, so having white matter as a new research target opens the door for neuroscientists to discover potential new involvement in the brain that can lead to cognitive decline. That makes the study’s finding “exciting knowledge,” according to Farrell.
He noted that this research is early and much more research needs to be done to fully understand the role of white matter in cognitive decline.
“If we look closely at the slides from those who have kindly donated their brains to these post-mortem tissue samples, we can provide some clues as to what was going on in their brains during their lifetime,” Farrell said. “But this is only one point in time. We hope that the research we are conducting can provide clues to others doing neuroimaging and research on living subjects and help them look at new targets.
Photo: SIphotography, Getty Images