A simple, cheap and non-invasive blood test could help predict a person's risk of developing Alzheimer's disease and multiple sclerosis (MS) up to 20 years before symptoms show.

Physicists from the ANU Research School of Physics have used tiny holes in a silicon dioxide membrane, combined with artificial intelligence (AI) analysis to analyse proteins in blood and search for signs of early neurodegeneration via tell-tale biomarkers that point to the onset of Alzheimer’s. 

"Alzheimer's disease is the most common form of dementia and currently there is no cure," said Professor Patrick Kluth, from the ANU Research School of Physics. 

“We know the risk of developing dementia is three to five times higher for Aboriginal and Torres Strait Islander people compared to the general Australian population.”

Dementia is the second leading cause of death for Australians. It's estimated more than 400,000 Australians are living with dementia, with that number expected to more than double by 2058. 

"Current methods used to diagnose Alzheimer's normally involve invasive and expensive hospital procedures such as a lumbar puncture, which can be physically and mentally taxing for patients,” Professor Kluth said.

"Our technique, on the other hand, requires only a small blood sample and patients could receive their results in near real-time.

"The quick and simple test could be done by GPs and other clinicians, which would eliminate the need for a hospital visit and prove especially convenient for people living in regional and remote areas."

The new device is portable, about the size of a mobile phone. It contains the silicon chip membrane separating chambers of conducting solution containing the blood sample. A current is passed through the membrane, and as individual proteins pass through the tiny holes (known as nanopores) the current momentarily dips.

Highly time-resolved plots of the current dips show that each protein has a unique signature which the AI algorithm can identify, thus identifying markers of disease.

Proteins are building blocks of life and contain distinct information, unique to each individual, that holds important clues about health, including signs of decaying brain cells.  

The researchers describe finding the proteins associated with early neurodegeneration as searching for a needle in a haystack.

“Blood is a complex fluid that contains more than 10,000 different biomolecules. By employing advanced filtration techniques and harnessing our nanopore platform, combined with our intelligent machine-learning algorithms, we may be able to identify even the most elusive proteins,” PhD researcher and co-author Shankar Dutt said.

The algorithm can be trained to screen for multiple neurological conditions at the same time, including Parkinson’s disease, multiple sclerosis and amyotrophic lateral sclerosis (ALS). The extreme sensitivity of the technique allows detection of small concentrations of proteins, which is crucial as only tiny quantities of neurological proteins cross the blood-brain barrier and end up in blood samples.

The new technique is able to find biomarker needles in the blood haystack due to the high throughput and large number of individual proteins going through the pore. Despite being so thin the membrane has proved robust, Mr Dutt said.

“Our pores are so stable, that we could measure 1.8 million proteins through a single ten nanometre wide pore in a five-nanometre thick membrane, which is a world record,”

“Instead of waiting for weeks for the result, a typical measurement would take about 15 minutes and results are available in nearly real time,” he said.

The researchers are already improving their detection accuracy with a newer design based on a conical nanopore, in a much thicker membrane. In this device the proteins are slowed down by interactions with the surface of the conical entrance to the pore, giving a slower and more detailed current-dip profile.

New pore shapes, such as double cones and funnels are being fabricated using the Heavy Ion Accelerator Facility, whose ion bombardment can be controlled with exquisite accuracy to create damage tracks that can generate a wide variety of pore shapes after subsequent etching.

Although there is no cure for Alzheimer’s, Mr Dutt said knowing whether someone is at risk of developing Alzheimer’s twenty years before a potential diagnosis could significantly improve health outcomes for patients.

"If that person can find out their risk level that far in advance, then it gives them plenty of time to start making positive lifestyle changes and adopt medication strategies that may help slow down the progression of the disease,” he said.

It's hoped the ANU screening technique could be made available within the next five years. 

The research is published in Small Methods and Analytical Chemistry.