Experimental test could help doctors detect overlapping brain diseases
When something goes wrong in the brain of a person with dementia, it’s often due to more than one thing. But it can be hard to part several brain diseasesespecially in the early stages, or even determine if multiple diseases are involved. A new experimental blood test could change that.
The test measures the levels of 15 proteins in the blood to help diagnose four major neurodegenerative diseases: Alzheimer’s disease, Parkinson’s disease, frontotemporal dementia and dementia with Lewy bodies. And it can determine whether a person has more than one of these diseases with 92.3% accuracy, researchers report in the May report. Alzheimer’s and dementia.
Dementia affects more than 6 million people in the United States and is the seventh largest cause of death global. “These diseases are more complex than we initially thought, and there is more overlap than we thought,” says Carlos Cruchaga, a human genomicist at Washington University in St. Louis. “In order to truly address and understand the biology of any of these diseases, we need to study all of these diseases together. »
Different dementias require different types of care, he says, even if the symptoms seem similar. Knowing the combination of diseases can help guide more tailored precision treatment.
Last year, the United States Food and Drug Administration approved the first blood test for Alzheimer’s disease disease. A number of other tests for Alzheimer’s disease that do not have FDA support are on the market. But these tests cannot detect anything other than Alzheimer’s disease.
The new test can. This could show that an individual has, for example, both Alzheimer’s disease and Parkinson’s disease, and suggest that of the unwanted proteins detected, 75 percent signal Alzheimer’s disease, while a smaller amount, say 20 percent, signal Parkinson’s disease. With this more complete picture, Cruchaga says, “we’re going to be able to provide much better therapy.”
The test relies on blood samples and medical records from more than 3,000 patients from two Washington University clinics in St. Louis focused on Alzheimer’s disease and Parkinson’s disease. Using an AI algorithm designed to find patterns in large data sets, the team narrowed down a panel of 123 proteins to the final 15 that best signal whether a type of dementia or Parkinson’s disease might be present in the brain, and in what proportion. This list includes proteins involved in different dementias, such as p-tau217, the cornerstone of existing blood tests for Alzheimer’s disease.
The researchers then verified the AI model’s predictions with a separate group of patients at the Banner Sun Health Research Institute in Arizona, comparing the blood test results with what was actually found in donated brain tissue during the autopsy.
The test “moves away from the simple yes/no framework of Alzheimer’s disease and instead attempts to reflect the biological complexity that we often see in the clinic,” says Davide Cappon, a neuropsychologist at Tufts Medical Center in Boston, who was not involved in the study. It is “an important conceptual shift” for the field. But he says larger, more diverse studies are needed to validate the test.
“Maybe five or six years ago, no one believed that blood biomarkers for Alzheimer’s or neurodegenerative diseases were possible,” says Cruchaga. But the pace of technology has accelerated.
He and his colleagues dubbed their test GPND-AI, short for a name: the Protein-Based Generalizable Artificial Intelligence Classifier for Neurodegenerative Diseases. The team is talking with pharmaceutical companies to integrate the test into clinical trials and begin the FDA approval process.
However, Cappon says, tests like GPND-AI are not a substitute for clinical evaluation. “Blood biomarkers can suggest underlying pathology,” he says. “They cannot fully explain how a person functions on a daily basis, why symptoms began, or how factors like sleep, depression, medications, vascular disease, or resilience influence cognition. »
