There's more proof that machine learning can greatly aid in the diagnosis of Alzheimer's disease. The latest study, conducted by researchers at UC Davis and UC San Francisco, used artificial intelligence to detect amyloid plaques in the brains of deceased patients, automating the work typically done by pathologists. The findings concluded that machine learning was extremely accurate in analyzing the type of amyloid plaque found in the brain. Beta-amyloid plaque are clumps of protein fragments in the brains of people with Alzheimer's disease that destroy nerve connections. The tool developed by the University of California scientists allows them to analyze thousands of times more data than even the most experienced pathologist would have access to but doesn't replace their job completely.
In the end it will be microbes--bacteria, viruses and fungus--found to be at the root of all disease and aging, and specifically Alzheimer's, contends geneticist Dr. Rudolph "Rudy" Emile Tanzi. "The two biggest threats to healthy aging have had to do with dealing with infection," said Tanzi, who specializes in Alzheimer's and the brain at Massachusetts General Hospital (MGH) and Harvard Medical School. When we increased the lifespan from 35 to 50, it was by covering the sewers. When we increased the lifespan from 50 to 75, it was with the use of antibiotics. Now we are looking for viruses in all of the major life-threatening diseases of our time--Alzheimer's, cancer, Parkinson's--and guess what?
Newswise -- (New York – March 4, 2019) Researchers have developed an artificial intelligence platform to detect a range of neurodegenerative disease in human brain tissue samples, including Alzheimer's disease and chronic traumatic encephalopathy, according to a study conducted at the Icahn School of Medicine at Mount Sinai and published in the Nature medical journal Laboratory Investigation. Their discovery will help scientists develop targeted biomarkers and therapeutics, resulting in a more accurate diagnosis of complex brain diseases that improve patient outcomes. The buildup of abnormal tau proteins in the brain in neurofibrillary tangles is a feature of Alzheimer's disease, but it also accumulates in other neurodegenerative diseases, such as chronic traumatic encephalopathy and additional age-related conditions. Accurate diagnosis of neurodegenerative diseases is challenging and requires a highly-trained specialist. Researchers at the Center for Computational and Systems Pathology at Mount Sinai developed and used the Precise Informatics Platform to apply powerful machine learning approaches to digitized microscopic slides prepared using tissue samples from patients with a spectrum of neurodegenerative diseases.
Blocking a protein in the brain could halt the progression of Alzheimer's disease, a study has found. Inhibiting certain chemicals stopped toxic clumps of proteins - known as plaques - forming in the brain. Plaques cause brain cells to lose connections with one another, and they eventually die, which causes symptoms such as memory loss and confusion that are the hallmark of Alzheimer's disease. Researchers say the finding could lead to effective new treatments for the neurological condition, for which there is currently no cure. When combined with other treatments, it could'eliminate' plaques from the brain, they added.
Researchers were able to create a three-dimensional model of Alzheimer's disease (AD) for the first time, using neurons and glia derived from stem cells over-expressing human amyloid-beta precursor protein or presenilin 1 (PS1), or both, each carrying familial AD mutations. A new three-dimensional cell model has for the first time produced not only amyloid-beta (Abeta) plaques, but also tau pathology with striking similarities to the tangles of Alzheimer's disease (AD). If the data can be replicated, they are likely to lend strong support to the first and simplest form of the amyloid hypothesis of AD, which holds that accumulation of Abeta plaques drives the production of tangles in the brain. The model used neurons and glia derived from stem cells over-expressing human amyloid-beta precursor protein (APP) or presenilin 1 (PS1), or both, each carrying familial AD mutations. Previous stem cell models have not been able to reproduce human AD pathology, said co-author Rudy Tanzi, PhD, a professor of neurology at Harvard Medical School.