The new AI algorithm was able to efficiently automate classifying amyloid plaques and blood vessel abnormalities in postmortem brains of Alzheimer's patients. Researchers at UC Davis and UC San Francisco have found a way to teach a computer to precisely detect one of the hallmarks of Alzheimer's disease in human brain tissue, delivering a proof of concept for a machine-learning approach capable of automating a key component of Alzheimer's research. Amyloid plaques are clumps of protein fragments in the brains of people with Alzheimer's disease that destroy nerve cell connections. Much like the way Facebook recognizes faces based on captured images, the machine learning tool developed by a team of University of California scientists can "see" if a sample of brain tissue has one type of amyloid plaque or another -- and do it very quickly. The findings, published May 15, 2019 in Nature Communications, suggest that machine learning can augment the expertise and analysis of an expert neuropathologist.
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.
The leading cause of dementia in adults is Alzheimer's disease (AD), which accounts for more than 80% of dementia cases worldwide (1). This progressive neurodegenerative disorder is defined by the accumulation of toxic senile amyloid plaques and neurofibrillary tangles in the brain, accompanied by synapse and neuron loss (2). The deposits are composed of misfolded protein aggregates, which can also be seeded in a prion-like manner (3); AD is therefore commonly characterized as a protein-misfolding disease. Treatment is limited to the deceleration of progression and symptomatic relief (1). On page 116 of this issue, Gremer et al. (4) present a near-atomic resolution structure of amyloid Aβ(1–42) fibrils, which are the main components of amyloid plaques found in AD brains (see the figure).
New research from the Keck School of Medicine at USC may have identified the earliest sign yet of Alzheimer's disease. According to the new study, adults can develop elevated levels of amyloid plaque in the brain up to 10 years before they experience any of the cognitive decline associated with Alzheimer's. Discovering these plaques so early could help certain patients take better preventive measures. The appearance of plaques suggests that the brain destruction associated with Alzheimer's disease can begin years before any symptoms are detected, but it also means that treatment can begin earlier, too. "This study is trying to support the concept that the disease starts before symptoms, which lays the groundwork for conducting early interventions," said Michael Donohue, lead author of the study, in a statement."We've