Researchers from McGill University in Canada reveal how they used machine-learning techniques and beta-amyloid imaging to predict Alzheimer's development in patients with mild cognitive impairment (MCI) up to 2 years before symptoms arose.
Co-lead study author Dr. Pedro Rosa-Neto, of the departments of Neurology & Neurosurgery and Psychiatry at McGill University, and colleagues recently reported their findings in the journal Neurobiology of Aging.
MCI is a condition characterized by a decline in cognitive functions - such as memory and thinking skills - that is noticeable, but which does not impact a person's ability to carry out everyday tasks.
According to the Alzheimer's Association, studies have suggested that around 15 to 20 percent of adults aged 65 and older are likely to have MCI, and these individuals are at greater risk of Alzheimer's than the general population.
At present, there is no way to predict which MCI patients will go on to develop Alzheimer's disease, but Dr. Rosa-Neto and colleagues believe that their algorithm has the potential to fulfill this need.
Beta-amyloid, MCI, and Alzheimer's
While the precise causes of MCI and Alzheimer's disease remain unclear, the accumulation of a protein called beta-amyloid is believed to play a major role.
In people with Alzheimer's, beta-amyloid protein sticks together and forms "plaques" between brain cells. These plaques can disrupt brain cell communication and cause inflammation that leads to brain cell death.
Research has shown that in people with MCI, beta-amyloid protein may begin to accumulate up to 30 years before the onset of Alzheimer's. As such, researchers have been investigating beta-amyloid as an Alzheimer's biomarker.
However, not everyone who has MCI and beta-amyloid accumulation develops Alzheimer's disease. This begs the question, how can doctors determine which patients are most at risk?
In the new study, Dr. Rosa-Neto and team describe the development of an algorithm that could predict a patient's likelihood of progressing from MCI to Alzheimer's disease up to 2 years in advance.
Algorithm 84 percent accurate
The algorithm was created using data from 273 patients with MCI who were part of the Alzheimer's Disease Neuroimaging Initiative.
The team gathered 2 years' worth of patient data, including positron emission tomography (PET) brain scans - which displayed any beta-amyloid accumulation - whether they possessed any Alzheimer's risk genes, and whether they received a clinical diagnosis of Alzheimer's.
The researchers then "trained" state-of-the-art computer software to learn this information and use it to calculate each patient's risk of Alzheimer's based on their first PET brain scan.
The algorithm was able to predict a patient's progression from MCI to Alzheimer's disease with 84 percent accuracy, up to 2 years before any symptoms of the disease arose.
Dr. Rosa-Neto and colleagues plan to identify other Alzheimer's biomarkers that they could apply to the algorithm to make it more accurate.
The researchers believe that the tool could not only advance research into Alzheimer's treatments, but it could also be used to predict a person's risk of developing the disease years in advance.
"The novel algorithm overcomes the inherent imbalance of proportions between stable and pMCI [progressive MCI] seen in a population of MCI individuals, making it ideally suited for a clinical environment as an early diagnostic tool."