A new study published in the journal Radiology demonstrates how artificial intelligence (AI) can improve brain imaging to predict the onset of Alzheimer’s disease. The study found that using AI may help doctors detect Alzheimer’s six years before a medical diagnosis is made – opening the door for more lifestyle changes, preparation and treatment methods.
Learn more about how AI can help medical professionals detect Alzheimer’s.
Researchers Focus on an Early Diagnosis of Alzheimer’s
When it comes to diagnosing Alzheimer’s, earlier is better. With more interventions available in the early stages of the disease, an early diagnosis means more time to prepare financially, legally and personally, as well as more time for treatment. However, it is very hard to diagnose the disease early.
As more research is done, new ways to diagnose Alzheimer’s and related forms of dementia continue to be tested. From blood tests to brain imaging, researchers are on the hunt for the most affordable and least invasive way to diagnose the disease – preferably before symptoms begin.
Jae Ho Sohn, M.D., from the Biomedical Imaging and Radiology Department at the University of California in San Francisco and co-author of the study, explains, “People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.”
He also notes the importance of early intervention:
“If we diagnose Alzheimer’s when all the symptoms have manifested, the brain volume loss is so significant that it’s too late to intervene. If we can detect it earlier, that’s an opportunity for investigators to potentially find better ways to slow down… the disease process.”
What AI Can Do to Help Researchers Predict Alzheimer’s
Researchers have recently developed an algorithm to find changes in brain metabolism that can be predictive of Alzheimer’s. The researchers used a deep learning algorithm, one that acts like a human brain and learns by example. They trained the deep learning algorithm on a special type of imaging called “FDG-PET” that shows metabolic activity.
Using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) that includes more than 2,000 FDG-PET brain scans from over 1,000 people, researchers found that the algorithm was able to teach itself the metabolic patterns that predicted Alzheimer’s.
Using that information, researchers then used 40 additional imaging exams from different people that the algorithm had never seen before. The algorithm was 100% accurate at detecting the disease an average of six years before an Alzheimer’s diagnosis was made.
Dr. Sohn says, “We were very pleased with the algorithm’s performance. It was able to predict every single case that advanced to Alzheimer’s disease.”
He is hopeful about the implications of the study, saying, “If FDG-PET with AI can predict Alzheimer’s disease this early, beta-amyloid plaque and tau protein PET imaging can possibly add another dimension of important predictive power.”
Do you think there is an advantage to using AI to detect Alzheimer’s? We’d like to hear your thoughts in the comments below.