News ArchivesRead News

Voice Recognition Software Can Diagnose Parkinson’s

Tuesday June 26, 2012

Jamie Condliffe

gizmodo.com - "Siri, do I have Parkinson's?" That might sound flippant, but actually new research shows that it's possible to detect Parkinson's symptoms simply by using algorithms to detect changes in voice recordings.

Parkinson's, a degenerative disorder of the central nervous system, is usually diagnosed through analysis of symptoms along with expensive medical imaging to rule out other conditions—though there is currently no concrete method for detecting it.

Max Little, from the University of Oxford, has different ideas. He's been developing software that learns to detect differences in voice patterns, in order to spot distinctive clues associated with Parkinson's. Little explains to the BBC:

"This is machine learning. We are collecting a large amount of data when we know if someone has the disease or not and we train the database to learn how to separate out the true symptoms of the disease from other factors."

Using data from 50 patients with Parkinson's, who had their voices recorded once a week for six months, Little was able to develop an algorithm to detect changes in voice purely associated with Parkinson's. In recent tests, the software accurately picked out Parkinson's patients from a random population with 86 percent accuracy.

Now, Little is taking things further. Today, he is announcing at TEDGlobal that the project is extending, by inviting members of the general public to phone in and leave voice recordings to help him improve the software. The aim is to collect up to 10,000 voices, and people from around the world are encouraged to contribute.

If all goes well, Little hopes to roll out the technology for use by doctors in two years, and is adamant that it will help in the diagnosis of the disease. Again speaking to the BBC, he explained:

"We're not intending this to be a replacement for clinical experts, rather, it can very cheaply help identify people who might be at high risk of having the disease and for those with the disease, it can augment treatment decisions by providing data about how symptoms are changing in-between check-ups with the neurologist."

It's an impressive achievement to take a relatively young technology and turn it into a system capable of detecting a disease like Parkinson's. Now, if you excuse me, I have an important phone call to make. [Parkinson's Voice Initiative via BBC]


Recent News

Nov 22 - A caregiver's story: Living and loving through the slow process of dying
Nov 19 - Testosterone cause of sex differences in the occurrence of Parkinson’s disease, new research suggests
Nov 18 - New strategy reduces side effects in Parkinson's treatment
Nov 14 - Opinion: The never-ending tests of Parkinson's disease
Nov 13 - Parkinson’s disease: A new tool for diagnosis
Nov 10 - Parkinson's Disease Drug May Be Useful For Delaying, Preventing Blindness In Older Population
Nov 9 - Microsoft VP’s diagnosis fuels employees’ heartfelt efforts to help others
Nov 6 - Lewy body dementia: unrecognized and misdiagnosed
Nov 5 - Gait difficulties in Parkinson's linked to new blood vessels in brain
Oct 30 - Special Section: Enabling Technologies for Parkinson’s Disease Management
Oct 27 - Scientists discover a 'switchboard' of molecules that protect against Parkinson's disease
Oct 26 - Dancing improves mobility and quality of life in people with Parkinson's
Oct 23 - The amazing woman who can smell Parkinson’s disease — before symptoms appear
Oct 20 - Personal Essay: The deviousness of dementia
Oct 19 - Mechanism that 'melts' protein clumps may lead to new Parkinson's treatments
Oct 19 - Researchers find that stem cell treatment may reduce cognitive impairment related to dementia with Lewy bodies
Oct 17 - Cancer Drug Helps Parkinson's Patients
Oct 12 - Researchers identify immune gene that can prevent Parkinson's disease and dementia
Oct 12 - Blog Post: An Alert, Well-Hydrated Artist in No Acute Distress
Oct 7 - This month, a brain surgery will be broadcast on live TV for the first time ever