An Alzheimer’s diagnosis can be a complicated process, with several cognitive tests, along with brain scans. Researchers have been working to find a simpler method, and a new study may have found one.
A team at Imperial College London has developed a single MRI brain scan using machine learning technology that was found to be 98% effective in detecting Alzheimer’s. It was also 79% accurate in differentiating between the early and late stages of the disease. The technology breaks up the brain into 115 regions and focuses on 660 different features to analyze each region. The researchers programmed it to identify where changes in these features could predict Alzheimer’s. The technology was adapted from an algorithm used to classify cancerous tumors.
The findings, published in the journal Communications Medicine, could simplify the process of diagnosing Alzheimer’s and identify it early enough to get patients what they need sooner.
Eric Aboagye, lead researcher and professor at Imperial’s Department of Surgery and Cancer, says, “Currently no other simple and widely available methods can predict Alzheimer’s disease with this level of accuracy, so our research is an important step forward. Many patients who present with Alzheimer’s at memory clinics do also have other neurological conditions, but even within this group our system could pick out those patients who had Alzheimer’s from those who did not.”
The team’s research involved more than 400 patients with early and later stage Alzheimer’s, patients with other neurological conditions like frontotemporal dementia and Parkinson’s disease, and a healthy control group. They also tested the method with data from more than 80 patients being screened for Alzheimer’s at Imperial College Healthcare NHS Trust.
In addition to its accuracy in detecting the disease, the technology found changes in parts of the brain that had not been linked with Alzheimer’s, including those that control physical activity and the senses. The hope is that this may help scientists better understand the development of the disease.
If proven effective in further research, this method could also make diagnosis less stressful and provide further options for those with early stage Alzheimer’s.
Aboagye says, “Waiting for a diagnosis can be a horrible experience for patients and their families. If we could cut down the amount of time they have to wait, make diagnosis a simpler process, and reduce some of the uncertainty, that would help a great deal. Our new approach could also identify early-stage patients for clinical trials of new drug treatments or lifestyle changes, which is currently very hard to do.”
To learn more about the technology, you can read the journal article here.Whizzco