Physicists at the Australian National University (ANU) have combined nanotechnology, artificial intelligence and molecular biology to devise a new way to search for protein markers of Alzheimer's disease in the blood. These markers are telltale signs of early neurodegeneration, and early detection is our best defense against effectively intervening in the progression of Alzheimer's disease. While there is currently no cure for the disease, if symptoms can be detected up to 20 years in advance when symptoms first appear, it has the potential to dramatically change health outcomes.
While much research has focused on developing targeted therapies to treat late-stage Alzheimer's disease, much progress has also been made in the field of advanced diagnostics.
Co-author Professor Patrick Kluth, from the Australian National University's School of Research Physics, said: "Currently, Alzheimer's diagnosis is mainly based on evidence of intellectual deterioration at a stage when the disease has severely damaged the brain. Early detection is crucial for effective treatment, but often requires invasive and expensive procedures such as lumbar punctures in hospital, which can place a physical and mental burden on patients."
Researchers have developed an ultra-thin silicon chip covered with nanoscale holes, known as solid nanopores. A small amount of blood is then placed on the chip, and through the nanopore transfer process, the complex mixture of proteins in the blood can be separated. The chip is then inserted into a mobile phone-sized device, where an artificial intelligence algorithm searches for proteins that match a protein signature associated with early-onset Alzheimer's disease.
The researchers found that by classifying protein signals based on signal properties, the model had significantly high accuracy (96.4% specificity) in identifying four machine-learned protein combinations. Because proteins contain unique, personalized genetic blueprints, they could play an even greater role in medical diagnosis given the right technology.
Co-author Shankar Dutt, a researcher at the Australian National University, said: "If the person can discover their risk level that far in advance, then they have enough time to start making aggressive lifestyle changes and drug treatment strategies that may help slow the progression of the disease."
The researchers note that while the new technology focuses on Alzheimer's disease, the algorithms it uses can be trained to look for other diseases and detect them simultaneously. These diseases include Parkinson's disease, multiple sclerosis (MS) and amyotrophic lateral sclerosis (ALS).
"Blood is a complex fluid containing more than 10,000 different biological molecules," Dutt said. "By employing advanced filtration techniques and leveraging our nanopore platform, combined with our intelligent machine learning algorithms, we may be able to identify the most elusive proteins."
Clouse added that the team hopes the screening technology will be available within the next five years, allowing patients to get results in "near real-time."
"This quick and easy test can be carried out by GPs and other clinicians, eliminating the need for hospital visits and is particularly convenient for people living in regional and remote areas," he said.
The research was published in the journal SmallMethods.