Voice Algorithms Spot Parkinson's Disease

← Back to Stories (view on slashdot.org)

Voice Algorithms Spot Parkinson's Disease

Posted by samzenpus on Monday June 25, 2012 @04:50AM from the diagnostic-discourse dept.

another random user writes "Mathematician Max Little discovered that Parkinson's symptoms can be detected by computer algorithms that analyze voice recordings. 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."

42 comments

Min score:

Reason:

Sort:

Now if only we had one of these for AIDS by Anonymous Coward · 2012-06-25 04:58 · Score: 0

much more practical IMHO
1. Re:Now if only we had one of these for AIDS by skids · 2012-06-25 05:06 · Score: 1
  
  You know I keep reading about all these cheap noninvasive tests, and then go to the doctor for a checkup and expecting for them to wave some gadget in front of my moutth when I exhale, but... nothing... nothing new at all. Just the usual stuff minus, it seems these days, the ball grabbing.
  I guess they are all just stuck in the pipeline.
  
  --
  Someone had to do it.
I am not really channeling Katherine Hepburn? by peter303 · 2012-06-25 04:58 · Score: 1

Warbling in the voice? She had dystardia worsening in old age.
1. Re:I am not really channeling Katherine Hepburn? by Anonymous Coward · 2012-06-25 05:09 · Score: 0
  
  No just liberalism disease.
2. Re:I am not really channeling Katherine Hepburn? by Anonymous Coward · 2012-06-25 05:30 · Score: 0
  
  ... I don't get it.
Recording by Anonymous Coward · 2012-06-25 04:58 · Score: 4, Funny

"After the tone, please say your full name; your date of birth; your address; and your social security number. And thank you for helping fund Parkinson research. BEEEEP."
1. Re:Recording by game+kid · 2012-06-25 05:43 · Score: 1
  
  It's easy to miss the part just before the ". BEEEEP." where they say " inc. A subsidiary of Parkinson Marketing Group", because they sped it up 'til it became a blip of white noise.
  
  --
  You can hold down the "B" button for continuous firing.
The insurance companies are going to love this by Anonymous Coward · 2012-06-25 04:59 · Score: 5, Insightful

When you call to buy insurance
1. Re:The insurance companies are going to love this by Anonymous Coward · 2012-06-25 05:18 · Score: 0
  
  When you call to buy insurance
  Except they don't want you to call, but sign up on line (to save money)....
2. Re:The insurance companies are going to love this by Anonymous Coward · 2012-06-25 06:47 · Score: 0
  
  imagine helping this guys service and getting a call back from him... 'umm.. you should probably go see a doctor'
Obamacare eliminates this in 2014 by peter303 · 2012-06-25 05:10 · Score: 1, Troll

But R.I.P. June 28, 2012.
1. Re:Obamacare eliminates this in 2014 by Sponge+Bath · 2012-06-25 06:35 · Score: 2
  
  We will find out this week if that protection will be allowed by SCOTUS.
Really exciting by Greenspark · 2012-06-25 05:16 · Score: 4, Interesting

This is fascinating! I wonder if this will prove to not only identify patients currently expressing symptoms, but have a predictive quality for determining who will suffer from the disease before other tools can detect it. Having an earlier look at patients and charting the developments in their brain would really improve doctors' understanding and probably advance research into treatments quite a bit! if voice can be found to accurately indicate or even predict a disease like parkinsons... what else can it demonstrate? This might be the beginning of a new form of diagnostic sciences.
1. Re:Really exciting by UnknownSoldier · 2012-06-25 05:39 · Score: 2
  
  You mean like this?
  Analyzing Speech to Detect Financial Misreporting
  www.hbs.edu/units/am/pdf/HMV010410.pdf
  How a person talks can already be used to gauge the amount of respect they have for themselves and one another.
2. Re:Really exciting by Greenspark · 2012-06-25 05:47 · Score: 0
  
  Yes definitely! But that's behavioral. I'm talking about using someones voice to quantitatively make a medical diagnosis that would be useful regardless of any learned qualities of speech.
3. Re:Really exciting by Igot1forya · 2012-06-25 07:18 · Score: 1
  
  I've been doing something like this for years - I can tell you within a small degree of error if someone is retarded simply by what they say rather than how they say it. For example, many will draw this conclusion just by reading my comments :)
  
  --
  -------- -1 for SUCK IT!
Re:LOL by Anonymous Coward · 2012-06-25 05:28 · Score: 1

Don't think you know what the word exaggerate means.
Re:LOL by kanto · 2012-06-25 05:31 · Score: 2

Will it also detect when Michael J Fox intentionally goes off his meds before going on TV to exaggerate his symptoms?
It's not like the people on Fox News do anything different.
Voice stress testing by Anonymous Coward · 2012-06-25 05:40 · Score: 0

Sounds like voice stress testing. It used to be fun to analyze public speaking in the frequency domain and find the 8 to 12 hertz oscillations. The sound equipment used in the stages at the White House appear to remove these in real time these days, though.
1. Re:Voice stress testing by Ungrounded+Lightning · 2012-06-26 04:00 · Score: 1
  
  It used to be fun to analyze public speaking in the frequency domain and find the 8 to 12 hertz oscillations. The sound equipment used in the stages at the White House appear to remove these in real time these days, though.
  Or you may be observing that pathological liars aren't stressed when they lie.
  
  --
  Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
Not News by Anonymous Coward · 2012-06-25 05:47 · Score: 1

This is great technology, but it isn't news, no matter what the BBC thinks.
UC Irvine's machine learning repository has had a set of Parkinson's and non-Parkinson's voice prints up since 2008. (Astute readers will note that it's based on Max Little's work, as is the BBC article. But it's not news.)
How about Hitler? by T.E.D. · 2012-06-25 05:57 · Score: 3, Interesting

It has been speculated that he suffered from Parkingsons. There's certianly plenty of voice recordings of him, covering many years of activity. This ought to be a great way to test both the software and the theories.
ps. Sorry for Godwining the story so early
1. Re:How about Hitler? by kanto · 2012-06-25 07:19 · Score: 1
  
  There's plenty of maniacal shouting to audiences, but afaik only one taping of him talking in conversational tones (in case that makes a difference here). Guardian has some background on how it was taped; it was in Finland and the guy who did it was lucky to live after the Germans noticed what had happened.
2. Re:How about Hitler? by X0563511 · 2012-06-25 07:33 · Score: 1
  
  Those recordings lack the fidelity for such analysis.
  
  --
  For large sets, this will be our guide even unto death, for the LORD will work for each type of data it is applied to...
3. Re:How about Hitler? by T.E.D. · 2012-06-25 07:36 · Score: 1
  
  They are really that much worse than the fidelity you get from an answering machine off of a telephone line?
4. Re:How about Hitler? by citizenr · 2012-06-25 08:42 · Score: 1
  
  You dont need fidelity for most machine learning problems. Algorithms pick up details that humans consciousness misses.
  
  --
  Who logs in to gdm? Not I, said the duck.
FBI Could probably help by Igot1forya · 2012-06-25 06:13 · Score: 1

They should contact the FBI and NSA - they have everyone's voice on file already. "Sir, you're under arrest for %OFFENSE%! By the time your trial reaches a conviction you will be in final stages of Parkinson's, my condolences"

--
-------- -1 for SUCK IT!
Needs more study by mcgrew · 2012-06-25 06:48 · Score: 1

Alcoholics undergoing withdrawal show the same shakiness as Parkensons victims, I wonder if an alkie going through DTs would show up as Parkinsons with this test?

--
Free Martian Whores!
Re:LOL by Anonymous Coward · 2012-06-25 06:50 · Score: 0

The person you responded to was lying, and is probably a mindless follower of Rush Limbaugh.
No need to point out that Fox lies too, as everyone knows that, and the only people watching want to be lied to in a desperate attempt to cling to their outmoded superstitions and bigotries..
How about 80,000 by uiucgrad · 2012-06-25 06:54 · Score: 1

http://storycorps.org/
Called my local number by Anonymous Coward · 2012-06-25 07:06 · Score: 1

and the voice recording simply said, "or vagina"
On-Once Th-There W-Was... by WilyCoder · 2012-06-25 07:35 · Score: 1

T-T-T-Today Junior!
Apple has a dandy collection of voice data by Anonymous Coward · 2012-06-25 08:00 · Score: 0

Ask Apple for their database of Siri request samples
Re:LOL by Anonymous Coward · 2012-06-25 08:53 · Score: 0

Your post smacks of projection. (Remember whenever you point your finger, three are pointing at you.)
accuracy? how about precision and recall? by Anonymous Coward · 2012-06-25 10:23 · Score: 0

Since this is machine learning, what does this accuracy measure mean? That for a batch of unknown voices, he predicted the right outcome (parkinson or not-parkinson) 86% of the time?
Here is my algorithm with a precision over 99%:
Parkinson( voice_x) = false;
1. Re:accuracy? how about precision and recall? by Harvey+Manfrenjenson · 2012-06-25 18:18 · Score: 1
  
  Since this is machine learning, what does this accuracy measure mean? That for a batch of unknown voices, he predicted the right outcome (parkinson or not-parkinson) 86% of the time?
  Here is my algorithm with a precision over 99%:
  Parkinson( voice_x) = false;
  Mod parent up, please. The phrase "86% accuracy" could mean 4 totally different things:
  86% of Parkinson's patients are positively flagged by the algorithm (86% sensitivity)
  86% of normal patients are NOT positively flagged by the algorithm (86% specificity)
  A positively-flagged result implies that you have an 86% chance of having Parkinson's (86% positive predictive value)
  A negatively-flagged result implies that you have an 86% chance of not having Parkinson's (86% negative predictive value)
  I think that's right (posting with the certainty that someone will correct me if I screwed it up). Anyway, as the parent points out, "86% accuracy" is entirely meaningless without clarification. Such is the state of science journalism.
  Also, what's the point of collecting 10,000 voiceprints (or whatever it was) if you don't have actual data on whether the owners of said voiceprint have (or later develop) Parkinson's disease (or similar dysphonia-causing diseases, like benign tremor/tardive dyskinesia/whatever)? How does that possibly help?
2. Re:accuracy? how about precision and recall? by Anonymous Coward · 2012-06-26 04:48 · Score: 0
  
  TFA
Other neuromuscular syndromes. by Ungrounded+Lightning · 2012-06-26 04:16 · Score: 1

Now if only we had one of these for AIDS
Ha ha but seriously...
Other neurological and/or muscular syndromes (such as ALS or Demyelinating diseases like MS) might produce detectable, but distinct, signatures.

--
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
Re:LOL by kanto · 2012-06-27 01:19 · Score: 1

Bleh, might as well let you in on the joke... supposedly "Michael J. Fox went off his meds before going on TV to exaggerate his symptoms" and then I say "The people on Fox News do the same". I guess I'll have to be less subtle next time so as to not get a partisan insightful mod.