July 2, 2012
You Can Help Test A New Technique To Diagnose Parkinson's
Mathematician Max Little has made a public appeal for people to call a phone number so data can be gathered to hone a voice-pattern tool for diagnosing Parkinson’s disease. Little, a research fellow at the Massachusetts Institute of Technology, made the announcement during the opening of the TEDGlobal conference in Edinburgh, June 25.
Little was recently made a TED fellow. The non-profit organization behind TED (Technology, Entertainment and Design) creates 40 such fellowships each year. The program targets innovators under the age of 40 and offers them free entry to conferences and other events.
Difficulty in Detecting Parkinson's
After Alzheimer’s, Parkinson’s is the most common neuro-degenerative disease. Since it is incurable, early diagnosis can affect an individual’s quality of life.
Currently, there is no simple diagnosis tool -- no blood test can identify Parkinson’s. I suspect I probably had PD several years before it was finally diagnosed. That's when I first noticed I was losing my sense of smell -- an early symptom of Parkinson's... but one that could also be attributed to other factors. When I was diagnosed, it was by the process of elimination. I got brain scans and other tests to make sure something else wasn't causing my problems with balance and arm rigidity. I didn't -- still don't -- have the hand tremors often associated with PD, which made my case more difficult to detect. When no other cause was found, I was given the standard Parkinson's medication to try out. When the med seemed to work, my doc said "PD."
The system Little has devised for testing voice patterns could, he says, "very cheaply help identify people who might be at high risk of having the disease." He adds that "we're not intending this to be a replacement for clinical experts." In my case, his voice tests might have resulted in my getting an earlier clinical evaluation.
Vocal tremors, breathiness, and reduced speech volume are some of the first symptoms recorded in nearly all patients. These can be very subtle at the start, however, and Little’s system could conceivably pick up the slightest abnormal intonations. Most PWPs -- up to 90% of us -- report some vocal impairment following the onset of the disease. Little’s system represents an opportunity for widespread, easy, inexpensive, from-home diagnosis.
While studying at Oxford University, Little developed an algorithm that identifies the unique characteristics in the voices of PWPs.
He first reported his diagnostic tool’s success in a paper published earlier this year in the IEEE Transactions journal. Little and co-author Athanasios Tsanas explained how 43 candidates were asked to hold one sound frequency for as long as possible. They collected 263 data samples in this way, from which they extracted 132 different vocal impairments. Using only ten of these recorded impairments, the algorithm could accurately diagnose Parkinson’s speech markers 99 percent of the time.
The system could also be used to assess how patients are progressing after diagnosis. "The technology makes it easy for people to report their progress whilst on a new drug," Little noted.
In his address at the Edinburgh conference, Little reported that his system correctly identified PD with 86% accuracy during a blind test of voices.
Little now seeks 10,000 volunteers to contribute to his voice database, and created the Parkinson's Voice Initiative website for volunteers to use. It provides local phone numbers in ten countries. Here in the U.S., the number is 1-857-281-8035.
I gave it a try. The call lasted less than three minutes. The instructions were clear, simple and easy to follow. Anyone can call. They are interested in healthy volunteers as well as those with Parkinson's. By getting non-sufferers to call in, the system can learn to weed out unnecessary voice patterns, such as those brought on by a cold or heavy smoking.
Little hopes the technology will be available to doctors within the next two years.