Sunday, 24 June 2012

Voice algorithms spot Parkinson's disease

Mr Little wants to create a database of voices to help diagnose Parkinson's

Parkinson's is a devastating disease for those living with the condition and currently there is no cure.
Diagnosis can also be slow as there are no blood tests to detect it.
But now mathematician Max Little has come up with a non-invasive, cheap test which he hopes will offer a quick new way to identify the disease.
He will be kicking off the TEDGlobal conference in Edinburgh calling for volunteers to contribute to a huge voice database.
Mr Little has discovered that Parkinson's symptoms can be detected by computer algorithms that analyse voice recordings.
In a blind test of voices, the system was able to spot those with Parkinson's with an accuracy of 86%.
Mr Little was recently made a TED Fellow.
The non-profit organisation behind the TED (Technology, Entertainment and Design) conference creates 40 such fellowships each year. The programme aims to target innovators under the age of 40 and offers them free entry to conferences and other events.
Intel founder
Mr Little became interested in understanding voice from a mathematical perspective while he was studying for a PhD at Oxford University in 2003.
"I was looking for a practical application and I found it in analysing voice disorders, for example when someone's voice has broken down from over-use or after surgery on vocal chords," he told the BBC.
"I didn't occur to me at the time that people with Parkinson's and other movement disorders could also be detected by the system."
But a chance meeting with someone from Intel changed that.
Andy Grove, one of Intel's founders and ex-chief executive, was diagnosed with Parkinson's in 2000 and has since pledged millions of his personal fortune to fund research into the disease.
This includes funds for the chipmaker to develop its own projects to monitor the symptoms.
"They were using devices that detect breakdown in dexterity and accelerometers but they had also recorded the voices of around 50 patients with Parkinson's," explained Mr Little.
The recordings were detailed as the team had recorded the patients once a week over a six-month period.
"They had an enormous amount of data but they didn't know what to do with it. So we wondered whether my technique would work," said Mr Little.
"They set me a blind test to see if I can tell them which ones had Parkinson's. I had 86% accuracy using the techniques I'd developed."
Voice tremors
Vocal folds in action, credit James P.ThomasThe technology works partly by tracking the motion of vocal chords
The system "learns" to detect differences in voice patterns.
"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."
Voice patterns can change for a number of reasons, including throat surgery, heavy smoking and even just having a common cold.
But Mr Little believes the system will be smart enough to tell the difference.
"It is not as simple as listening for a tremor in the voice. That tremor has to be in context of other measures and the system has to take in other factors such as if someone has a cold."
Now he is looking for volunteers to contribute to a vast voice bank to help the database to learn even more.
He is aiming to record up to 10,000 voices and has set up local numbers in 10 countries around the world. In the UK the number is 01865 521168.
Anyone can call and they need to state whether or not they have been diagnosed with the disease.
There is also a website where people can find out more about the project.
"The more people that call in, the better," he said.
"If we get 10,000 recordings we'd be very happy but even a tenth of that would be great,"
Clinical trials
He hopes that the technology will be available to doctors within the next two years.
"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," he said.
There could also be a role for the technology in clinical trials.
"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."

Wednesday, 6 June 2012

CT scans on children 'could triple brain cancer risk'

The study looked at the records of nearly 180,000 young patients

Multiple CT scans in childhood can triple the risk of developing brain cancer or leukaemia, a study suggests.
The Newcastle University-led team examined the NHS medical records of almost 180,000 young patients.
But writing in The Lancet the authors emphasised that the benefits of the scans usually outweighed the risks.
They said the study underlined the fact the scans should only be used when necessary and that ways of cutting their radiation should be pursued.
During a CT (computerised tomography) scan, an X-ray tube rotates around the patient's body to produce detailed images of internal organs and other parts of the body.
In the first long-term study of its kind, the researchers looked at the records of patients aged under 21 who had CT scans at a range of British hospitals between 1985 and 2002.
Because radiation-related cancer takes time to develop, they examined data on cancer cases and mortality up until 2009.
Brain cancer and leukaemia are rare diseases.
'Significant increases'
The study estimated that the increased risk translated into one extra case of leukaemia and one extra brain tumour among 10,000 CT head scans of children aged under ten.
Dr Mark Pearce, an epidemiologist from Newcastle University who led the study, said: "We found significant increases in the risk of leukaemia and brain tumours, following CT in childhood and young adulthood.
"The immediate benefits of CT outweigh the risks in many settings.
"Doses have come down dramatically over time - but we need to do more to reduce them. This should be a priority for the clinical community and manufacturers."
CT scans are useful for children because anaesthesia and sedation are not required.
This type of check is often ordered after serious accidents, to look for internal injuries, and for finding out more about possible lung disease.
Regulations on their use in the UK mean CT scans should only be done when clinically justified - and the researchers said their study underlined that point.
Professor Sir Alan Craft, a co-author and leading expert in child health, said: "The important thing is that parents can be reassured that if a doctor in the UK suggests a child should have a CT scan, the radiation and cancer risks will have been taken into account.
"There's a much greater risk of not doing a CT scan when it's suggested.
"This study will push us to be even more circumspect about using it. We have much stricter rules here about using CT than in the United States, for example."
Dr Hilary Cass, the president of the Royal College of Paediatrics and Child Health, said: "We have to take very seriously the link between repeated CT scans and increased risk of these cancers amongst children and young people.
"But with both tumours rare, the absolute risk remains low."
A Department of Health spokesman said: "The UK uses lower levels of radiation in CT scans than other countries.
"We also have clear regulations to ensure a CT scan is only carried out when clinically justified."