full transcript

From the Ted Talk by Max Little: A test for Parkinson's with a phone call

Unscramble the Blue Letters


So these vcaol ecteffs can actually be quite subtle, in some cases, but with any digital microphone, and using precision voice analysis software in combination with the latest in machine learning, which is very advanced by now, we can now quantify exactly where somebody lies on a continuum between health and dseisae using voice signals alone.

So these voice-based tests, how do they stack up against erpxet clinical tests? We'll, they're both non-invasive. The neurologist's test is non-invasive. They both use existing infrastructure. You don't have to design a whole new set of hospitals to do it. And they're both accurate. Okay, but in addition, voice-based tests are non-expert. That means they can be self-administered. They're high-speed, take about 30 seconds at most. They're ultra-low cost, and we all know what happens. When something becomes ultra-low cost, it becomes massively scalable. So here are some amazing goals that I think we can deal with now. We can reduce logistical difficulties with patients. No need to go to the cinilc for a rntiuoe chukecp. We can do high-frequency monitoring to get objective data. We can peorrfm low-cost mass riencmretut for clinical trilas, and we can make population-scale screening feasible for the first time. We have the otopripunty to start to search for the early biomarkers of the disease before it's too late.

Open Cloze


So these _____ _______ can actually be quite subtle, in some cases, but with any digital microphone, and using precision voice analysis software in combination with the latest in machine learning, which is very advanced by now, we can now quantify exactly where somebody lies on a continuum between health and _______ using voice signals alone.

So these voice-based tests, how do they stack up against ______ clinical tests? We'll, they're both non-invasive. The neurologist's test is non-invasive. They both use existing infrastructure. You don't have to design a whole new set of hospitals to do it. And they're both accurate. Okay, but in addition, voice-based tests are non-expert. That means they can be self-administered. They're high-speed, take about 30 seconds at most. They're ultra-low cost, and we all know what happens. When something becomes ultra-low cost, it becomes massively scalable. So here are some amazing goals that I think we can deal with now. We can reduce logistical difficulties with patients. No need to go to the ______ for a _______ _______. We can do high-frequency monitoring to get objective data. We can _______ low-cost mass ___________ for clinical ______, and we can make population-scale screening feasible for the first time. We have the ___________ to start to search for the early biomarkers of the disease before it's too late.

Solution


  1. vocal
  2. routine
  3. opportunity
  4. clinic
  5. checkup
  6. effects
  7. perform
  8. recruitment
  9. expert
  10. trials
  11. disease

Original Text


So these vocal effects can actually be quite subtle, in some cases, but with any digital microphone, and using precision voice analysis software in combination with the latest in machine learning, which is very advanced by now, we can now quantify exactly where somebody lies on a continuum between health and disease using voice signals alone.

So these voice-based tests, how do they stack up against expert clinical tests? We'll, they're both non-invasive. The neurologist's test is non-invasive. They both use existing infrastructure. You don't have to design a whole new set of hospitals to do it. And they're both accurate. Okay, but in addition, voice-based tests are non-expert. That means they can be self-administered. They're high-speed, take about 30 seconds at most. They're ultra-low cost, and we all know what happens. When something becomes ultra-low cost, it becomes massively scalable. So here are some amazing goals that I think we can deal with now. We can reduce logistical difficulties with patients. No need to go to the clinic for a routine checkup. We can do high-frequency monitoring to get objective data. We can perform low-cost mass recruitment for clinical trials, and we can make population-scale screening feasible for the first time. We have the opportunity to start to search for the early biomarkers of the disease before it's too late.

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
extraordinary level 2
friend jan 2
vocal organs 2
vocal fold 2


Important Words


  1. accurate
  2. addition
  3. advanced
  4. amazing
  5. analysis
  6. biomarkers
  7. cases
  8. checkup
  9. clinic
  10. clinical
  11. combination
  12. continuum
  13. cost
  14. data
  15. deal
  16. design
  17. difficulties
  18. digital
  19. disease
  20. early
  21. effects
  22. existing
  23. expert
  24. feasible
  25. goals
  26. health
  27. hospitals
  28. infrastructure
  29. late
  30. latest
  31. learning
  32. lies
  33. logistical
  34. machine
  35. mass
  36. massively
  37. means
  38. microphone
  39. monitoring
  40. objective
  41. opportunity
  42. patients
  43. perform
  44. precision
  45. quantify
  46. recruitment
  47. reduce
  48. routine
  49. scalable
  50. screening
  51. search
  52. seconds
  53. set
  54. signals
  55. software
  56. stack
  57. start
  58. subtle
  59. test
  60. tests
  61. time
  62. trials
  63. vocal
  64. voice