Speech software spots most Parkinson's cases

Software offers a potential new way to quickly identify Parkinson's disease, the common neurological disorder that afflicts Michael J. Fox and hundreds of thousands of other Americans.

As USA Today reports, a team from Michigan State University developed an algorithm that could determine whether a patient has Parkinson's disease 9 times out of 10 and in two seconds. The Michigan State group developed the technology using recordings of patients with Parkinson's, tracking their speech patterns that might be undetectable with the naked ear.

Their software and other similar technologies offer the ability to rapidly screen patients for diseases without invasive procedures or even simple blood tests. In many cases, detecting a disease is the first step in stemming the advance of an illness. And researchers have struggled for years to make disease diagnostics as easy and accurate as possible to improve treatment outcomes.

"We anticipated good results, but getting two seconds and 90 percent--that was a surprise," Rahul Shrivastav, professor and chairman of Michigan State University's Department of Communicative Sciences and Disorders, told USA Today.

- check out the article