Detecting Early Alzheimer's Disease Better

Ivanhoe Newswire
Wednesday, April 18, 2007; 12:00 AM

(Ivanhoe Newswire) -- New research may lead to a better way of diagnosing early-stage Alzheimer's disease.

Researchers from Rowan University in New Jersey, the University of Pennsylvania School of Medicine and Drexel University in Philadelphia have found early Alzheimer's disease can be diagnosed accurately by using electroencephalogram (EEG) signals.

Christopher Clark, M.D., from the University of Pennsylvania was quoted as saying, "Individuals in the earliest stage of Alzheimer's disease are often not aware of their progressing memory loss, and family members often believe the changes are simply due to aging. The advantage of using a modified EEG to detect these early changes is that it is non-invasive, simple to do, can be repeated when necessary, and can be done in a physician's office. This makes it an ideal method to screen elderly individuals for the earliest indication of this common scourge of late life."

The researchers used EEG signals to monitor how patients' brains reacted to a series of auditory stimuli. Patients hear a series of low- and high-frequency tones as well as some novel sounds. Patients were instructed to press a button when they heard a high-frequency tone, which generates event-related potentials (ERP) in the EEG. In patients without Alzheimer's disease, the ERP registers a peak about 300 milliseconds after the high-frequency tone. People who have dementia or Alzheimer's disease show that peak much later than 300 milliseconds, have a weaker peak or have no peak at all.

The researchers studied patients using complicated signal processing, pattern recognition and artificial intelligence techniques to determine whether the entire ERP signal (not just the peak indicator) would uncover markers that had previously not been associated with Alzheimer's disease. After conducting the experiments on 71 patients -- some who had Alzheimer's, some who didn't -- researchers found their EEG method had an accuracy rate of diagnosing Alzheimer's disease between 82 percent and 85 percent.