‘One Step Closer To Early Intervention’: New Computer Program Could Diagnose Alzheimer’s Much Earlier, Study Shows

A new computer program could enable researchers to diagnose Alzheimer’s disease much earlier so that it can be treated much earlier after its onset.

Boston University researchers, using audio recordings from neuropsychological interviews with 1,000 people, used speech recognition tools that enabled computers to transcribe the recordings and then translate them into numbers. The chances of cognitive impairment were then determined by those numbers, demographic data, and diagnoses from neurologists and neuropsychologists.

“This approach brings us one step closer to early intervention,”  said Ioannis Paschalidis, a co-author on the paper. “It can form the basis of an online tool that could reach everyone and could increase the number of people who get screened early.”

The researchers were surprised to learn that the fluidity of speech among people who were recorded was less important than what they were saying.

“It surprised us that speech flow or other audio features are not that critical; you can automatically transcribe interviews reasonably well, and rely on text analysis through AI to assess cognitive impairment,” Paschalidis admitted.

The researchers discovered that the Boston Naming Test, which requires participants to label a picture with one word, was vital in ascertaining an accurate dementia diagnosis.

“Our models can help clinicians assess patients in terms of their chances of cognitive decline,” Paschalidis stated, “and then best tailor resources to them by doing further testing on those that have a higher likelihood of dementia.”

Alzheimer’s, which some researchers expect to strike triple the number of people by 2050, cripples the brain as human beings age, as beta-amyloid proteins in the brain get stuck together and tau proteins start to tangle, both of which inhibit neural connections.

In July 2019, researchers from the University of New Mexico Health Sciences Department declared they had created a vaccine that could prevent the development of Alzheimer’s disease.

The department’s newsroom website stated that the vaccine used virus-like particles (VLPs) to eliminate the tangling of the tau protein, which when accumulated in the brain can interrupt neurons in the brain from communicating.

Nicole Maphis, a PhD candidate who was working in the lab of Kiran Bhaskar, PhD, an associate professor in UNM’s Department of Molecular Genetics & Microbiology, stated, “We’re excited by these findings, because they seem to suggest that we can use the body’s own immune system to make antibodies against these tangles, and that these antibodies actually bind and clear these tau tangles.”

Maphis tested the vaccine in mice and they showed a marked improvement in their capacity to deal with mazes. The UNM Health Department site stated, “MRI scans showed that the vaccinated animals had less brain shrinkage, suggesting that the vaccine prevented neurons from dying. Maphis also found significantly fewer tangles in both the cortex and the hippocampus – areas in the brain that are important for learning and memory, and which are destroyed in Alzheimer’s.”

In November 2018, a study published in Alzheimer’s Research & Therapy touted a new Alzheimer’s vaccine developed by scientists at the University of Texas Southwestern that could conceivably cut the number of dementia cases in half. The research team tested four groups of mice; the vaccinated mice experienced as much as 40% of their beta-amyloid plaques reduced and as much as 50% of their tau tangles diminished. No adverse immune response was observed.