Biometric voice recognition software can detect Parkinson’s Disease
Professor Max Little, from the University of Oxford, has been using algorithms in voice recognition software to detect changes in voice of a person to see if he or she exhibits symptoms of Parkinson’s Disease. Parkinson’s is a degenerative disorder of the central nervous system that could manifest in tremors in speech.
In an interview with the BBC, Little said that for years he has used algorithms to rule out other factors except the ones that reflect the true symptoms.
He was able to collect large amounts of data from one of the research projects that Andy Grove of Intel funded in 2000. The project collected the data of 50 patients with Parkinson’s who had their voices recorded once a week for six months. Due to the myriad of data collected, the system can separate voices having Parkinson’s from those with normal ones. In fact, when Little tested the software, it garnered 86 percent accuracy in picking out patients suffering from Parkinson’s from random population.
Little did not expect that a system which started out as a PhD project in 2003, could lead to software that could detect patients with Parkinson’s and other movement disorders.
Now, Little wants to collect up to 10,000 voices so he can improve the software. He has set up a website called Parkinson’s Voice and made announcement at TedGlobal2012 that he wants the English-speaking general public, across the globe, to phone in and leave a three-minute voice recording:
During a BBC interview, Little said: “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.”
Little hopes to have this technology out in two years to make it available for doctors. “The technology makes it easy for people to report their progress whilst on a new drug, for example.”
He added: “If you can catch the disease early, it will make a huge difference to care costs. It could become a key technology in reducing the burden of care on the NHS.”
For those interested to volunteer, all you need to do is make a low-cost, anonymous, three-minute phone call at numbers posted at Parkinson’s Voice Initiative.
Do you think that the application of biometric technologies will be able to cure other hereditary diseases?