An exciting new study suggests a single MRI scan can accurately predict whether a person will develop dementia up to three years before any cognitive symptoms are detectable. It's hoped the prospective diagnostic tool will be able to better identify at-risk patients so preventative measures can be deployed to slow the onset of neurodegeneration.

The race is on to find a clear and consistent diagnostic tool that can detect the onset of dementia before clinical symptoms appear. Many researchers suspect it takes many years of progressive neurodegeneration before visible symptoms of conditions such as dementia and Alzheimer's disease become evident. Once a person is suffering from apparent dementia-related memory loss, for example, it may be too late to reverse, or even slow the condition.

Several interesting studies are suggesting that imaging tools such as PET scans may be helpful in detecting Alzheimer's disease years before it appears, however these types of scans are expensive and not widely available. A team of scientists from the Washington University School of Medicine in St. Louis and the University of California, San Francisco has now revealed a new dementia-detecting method that uses more commonly accessible MRI imaging technology.

The novel method uses a technique called diffusion tensor imaging. This technique can scan a person's brain, identifying signs of damage to their white matter.

"Diffusion tensor imaging is a way of measuring the movement of water molecules along white matter tracts," says lead author on the new study, Cyrus A. Raji. "If water molecules are not moving normally it suggests underlying damage to white tracts that can underlie problems with cognition."

Using scans of the whole brain, the technique was able to effectively predict cognitive decline with 89 percent accuracy, up to three years before symptoms appeared. Homing in on more specific areas of the brain, the accuracy rate of the method rose to a striking 95 percent.

"We could tell that the individuals who went on to develop dementia have these differences on diffusion MRI, compared with scans of cognitively normal people whose memory and thinking skills remained intact," says Raji.

While the sample size of this early study was small, it seems inevitable that as more data is collected, the technique will only become even more accurate. Raji notes that the team plans to develop computerized tools that can analyze patient's scans, allowing for even more accurate predictions to be made.

This particular diagnostic tool will most likely become just a part of a larger arsenal that looks set to help clinicians better detect the very earliest stages of cognitive decline. Earlier this year an AI algorithm was revealed that had been trained to predict Alzheimer's disease at an early stage from a variety of diagnostic data. It was suggested that the more data points a system such as this could study, the better its predictions would be, and this kind of new MRI breakthrough is exactly the kind of additional small biomarker that will help these algorithms.

On a smaller scale, Raji suggests that there is still immense value in this single imaging tool, helping doctors advise patients of preventative treatments and lifestyle recommendations.

"We showed that a single MRI scan can predict dementia on average 2.6 years before memory loss is clinically detectable," says Raji, "which could help doctors advise and care for their patients."

The new research will be presented on Sunday, Nov. 25 at the Radiological Society of North America meeting in Chicago.