TEDGlobal 2012
Max Little: A test for Parkinson's with a phone call
Max Little: Test za Parkinsonovu bolest putem telefonskog poziva
Filmed:
Readability: 4.5
1,296,740 views
Parkinsonova bolest pogađa 6,3 milijuna ljudi diljem svijeta i uzrokuje slabost i tremor. No, ne postoji nikakav objektivan način za rano otkrivanje. Primijenjeni matematičar i TED Fellow Max Little testira jeftino i jednostavno pomagalo koje je u pokusima uspjelo otkriti Parkinsonovu bolest s točnošću od 99% – i to jednim pozivom od 30 sekundi.
Max Little - Applied mathematician
Max Little is a mathematician whose research includes a breakthrough technique to monitor – and potentially screen for – Parkinson's disease through simple voice recordings. Full bio
Max Little is a mathematician whose research includes a breakthrough technique to monitor – and potentially screen for – Parkinson's disease through simple voice recordings. Full bio
Double-click the English transcript below to play the video.
00:16
So, well, I do applied math,
0
667
2103
Bavim se primijenjenom matematikom,
00:18
and this is a peculiar problem
1
2770
1524
a problem svojstven
00:20
for anyone who does applied math, is that
2
4294
2173
svima koji se bave primijenjenom matematikom
00:22
we are like management consultants.
3
6467
1933
jest da smo poput savjetnika za poslovanje.
00:24
No one knows what the hell we do.
4
8400
1946
Nitko ne zna što zapravo radimo.
00:26
So I am going to give you some -- attempt today
5
10346
2274
Ja ću vam danas pokušati
00:28
to try and explain to you what I do.
6
12620
2293
objasniti što radim.
00:30
So, dancing is one of the most human of activities.
7
14913
3321
Ples je jedna od najljudskijih aktivnosti.
00:34
We delight at ballet virtuosos and tap dancers
8
18234
3682
Oduševljavaju nas baletni virtuozi i plesači stepa
00:37
you will see later on.
9
21916
1148
koje ćete vidjeti kasnije.
00:38
Now, ballet requires an extraordinary level of expertise
10
23064
2690
Balet zahtijeva izvanrednu razinu vještine
00:41
and a high level of skill,
11
25754
2914
i visoku razinu umijeća
00:44
and probably a level of initial suitability
12
28668
2531
i vjerojatno neku razinu početne prikladnosti
00:47
that may well have a genetic component to it.
13
31199
1847
koja bi mogla imati genetski element.
00:48
Now, sadly, neurological disorders such as Parkinson's disease
14
33046
3393
Nažalost, neurološki poremećaji,
kao što je Parkinsonova bolest,
kao što je Parkinsonova bolest,
00:52
gradually destroy this extraordinary ability,
15
36439
2087
postupno uništavaju ovu izvranrednu sposobnost.
00:54
as it is doing to my friend Jan Stripling, who was
16
38526
2323
To čine i mom prijatelju Janu Striplingu, koji je
00:56
a virtuoso ballet dancer in his time.
17
40849
2967
u svoje vrijeme bio virtuozni baletan.
00:59
So great progress and treatment has been made over the years.
18
43816
3054
Velik napredak i tretman
postignuti su tijekom godina.
postignuti su tijekom godina.
01:02
However, there are 6.3 million people worldwide
19
46870
2944
Međutim, 6,3 milijuna ljudi diljem svijeta
01:05
who have the disease, and they have to live with
20
49814
3448
ima ovu bolest i mora živjeti
01:09
incurable weakness, tremor, rigidity
21
53262
2568
s neizlječivom slabošću, tremorom, ukočenošću
01:11
and the other symptoms that go along with the disease,
22
55830
1857
i ostalim simptomima te bolesti.
01:13
so what we need are objective tools
23
57687
2383
Stoga trebamo objektivne instrumente
01:15
to detect the disease before it's too late.
24
60070
3057
za otkrivanje bolesti dok nije prekasno.
01:19
We need to be able to measure progression objectively,
25
63127
2554
Moramo moći objektivno mjeriti razvoj bolesti,
01:21
and ultimately, the only way we're going to know
26
65681
3173
i konačno, jedini način na koji ćemo znati
01:24
when we actually have a cure is when we have
27
68854
2192
kad budemo imali lijek jest kad bude postojala
01:26
an objective measure that can answer that for sure.
28
71046
3398
objektivna mjera koja će na to
moći sa sigurnošću odgovoriti.
moći sa sigurnošću odgovoriti.
01:30
But frustratingly, with Parkinson's disease
29
74444
2850
Frustrira to što kod Parkinsonove bolesti
01:33
and other movement disorders, there are no biomarkers,
30
77294
2353
i ostalih poremećaja kretanja ne postoje biomarkeri,
01:35
so there's no simple blood test that you can do,
31
79647
2229
stoga nema jednostavnog krvnog nalaza
koji biste mogli napraviti,
koji biste mogli napraviti,
01:37
and the best that we have is like
32
81876
1802
i najbolje što imamo jest
01:39
this 20-minute neurologist test.
33
83678
2241
20-minutni neurološki test.
01:41
You have to go to the clinic to do it. It's very, very costly,
34
85919
2458
Da biste ga napravili, morate
otići u bolnicu. Veoma je skup,
otići u bolnicu. Veoma je skup,
01:44
and that means that, outside the clinical trials,
35
88377
2757
što znači da se osim u kliničkim ispitivanjima
01:47
it's just never done. It's never done.
36
91134
2728
nikad ne obavlja. Nikad se ne obavlja.
01:49
But what if patients could do this test at home?
37
93862
3077
No, što kad bi pacijenti mogli
ovaj test obaviti kod kuće?
ovaj test obaviti kod kuće?
01:52
Now, that would actually save on a difficult trip to the clinic,
38
96939
2098
Time bi se poštedjeli teškog puta do bolnice.
01:54
and what if patients could do that test themselves, right?
39
99037
4254
Što kad bi pacijenti mogli sami napraviti taj test?
01:59
No expensive staff time required.
40
103291
1920
Bez skupog osoblja.
02:01
Takes about $300, by the way,
41
105211
1418
Inače, testiranje u neurološkoj klinici
02:02
in the neurologist's clinic to do it.
42
106629
1993
stoji oko 300 dolara.
02:04
So what I want to propose to you as an unconventional way
43
108622
2681
Stoga vam želim predložiti jedan
nekonvencionalan način
nekonvencionalan način
02:07
in which we can try to achieve this,
44
111303
1514
na koji to možemo pokušati postići,
02:08
because, you see, in one sense, at least,
45
112817
1808
zato što smo svi mi u jednu ruku, na kraju krajeva,
02:10
we are all virtuosos like my friend Jan Stripling.
46
114625
3256
virtuozi poput mog prijatelja Jana Striplinga.
02:13
So here we have a video of the vibrating vocal folds.
47
117881
3755
Ovo je snimka koja prikazuje glasnice koje vibriraju.
02:17
Now, this is healthy and this is somebody making speech sounds,
48
121636
3229
Zdrave su i ovdje netko
proizvodi govorne zvukove.
proizvodi govorne zvukove.
02:20
and we can think of ourselves as vocal ballet dancers,
49
124865
3464
Možemo zamisliti sebe
kao vokalne plesače baleta
kao vokalne plesače baleta
02:24
because we have to coordinate all of these vocal organs
50
128329
2214
zato što moramo uskladiti
sve ove govorne organe
sve ove govorne organe
02:26
when we make sounds, and we all actually
51
130543
2295
kad prozvodimo zvukove.
02:28
have the genes for it. FoxP2, for example.
52
132838
2296
Svi imamo gene za to. Na primjer, gen FoxP2.
02:31
And like ballet, it takes an extraordinary level of training.
53
135134
2713
Kao i kod baleta, potrebna je
izvanredna razina uvježbanosti.
izvanredna razina uvježbanosti.
02:33
I mean, just think how long it takes a child to learn to speak.
54
137847
2585
Samo se sjetite koliko treba
djetetu da nauči govoriti.
djetetu da nauči govoriti.
02:36
From the sound, we can actually track
55
140432
2382
Pomoću zvuka zapravo možemo pratiti
02:38
the vocal fold position as it vibrates,
56
142814
2281
položaj glasnica dok vibriraju,
02:40
and just as the limbs are affected in Parkinson's,
57
145095
2543
Parkinson zahvaća glasnice,
02:43
so too are the vocal organs.
58
147638
2781
baš kao i udove.
02:46
So on the bottom trace, you can see an example of
59
150419
1880
Na donjem ispisu možete vidjeti primjer
02:48
irregular vocal fold tremor.
60
152299
1698
nepravilnog tremora glasnica.
02:49
We see all the same symptoms.
61
153997
1168
Vidimo iste simptome.
02:51
We see vocal tremor, weakness and rigidity.
62
155165
2930
Vidimo glasovni tremor, slabost i ukočenost.
02:53
The speech actually becomes quieter and more breathy
63
158095
2104
Govor zapravo postaje tiši i zadihaniji
02:56
after a while, and that's one of the example symptoms of it.
64
160199
2233
nakon nekog vremena
i to je jedan primjer simptoma.
i to je jedan primjer simptoma.
02:58
So these vocal effects can actually be quite subtle,
65
162432
2847
Ovi govorni učinci mogu biti vrlo suptilni,
03:01
in some cases, but with any digital microphone,
66
165279
3216
u nekim slučajevima,
ali s bilo kojim digitalnim mikrofonom
ali s bilo kojim digitalnim mikrofonom
03:04
and using precision voice analysis software
67
168495
2545
te koristeći precizni program za glasovnu analizu
03:06
in combination with the latest in machine learning,
68
171040
2409
u kombinaciji s najnovijim
dostignućima u strojnom učenju,
dostignućima u strojnom učenju,
03:09
which is very advanced by now,
69
173449
1578
koje je veoma napredovalo,
03:10
we can now quantify exactly where somebody lies
70
175027
2886
sad možemo točno izmjeriti gdje se netko nalazi
03:13
on a continuum between health and disease
71
177913
2881
na pravcu između zdravlja i bolesti,
03:16
using voice signals alone.
72
180794
2596
i to koristeći samo glasovne signale.
03:19
So these voice-based tests, how do they stack up against
73
183390
2314
Kakvi su ovi testovi temeljeni na glasu
u usporedbi sa
u usporedbi sa
03:21
expert clinical tests? We'll, they're both non-invasive.
74
185704
2150
stručnim kliničkim testovima?
Pa, i jedni i drugi su neinvazivni.
Pa, i jedni i drugi su neinvazivni.
03:23
The neurologist's test is non-invasive. They both use existing infrastructure.
75
187854
3982
Neurološki test je neinvazivan.
Oba koriste postojeću infrastrukturu.
Oba koriste postojeću infrastrukturu.
03:27
You don't have to design a whole new set of hospitals to do it.
76
191836
3004
Ne morate graditi nove bolnice da biste to napravili.
03:30
And they're both accurate. Okay, but in addition,
77
194840
2302
I oba su točna. No, uz to,
03:33
voice-based tests are non-expert.
78
197142
3327
testovi utemeljeni na glasu nestručni su.
03:36
That means they can be self-administered.
79
200469
1992
To znači da ih možete izvesti sami.
03:38
They're high-speed, take about 30 seconds at most.
80
202461
2580
Vrlo su brzi, potrebno je najviše 30-ak sekundi.
03:40
They're ultra-low cost, and we all know what happens.
81
205041
2294
Veoma su jeftini i svi znamo što se događa.
03:43
When something becomes ultra-low cost,
82
207335
2440
Kad nešto postane vrlo jeftino,
03:45
it becomes massively scalable.
83
209775
2296
također postane masovno mjerljivo.
03:47
So here are some amazing goals that I think we can deal with now.
84
212071
3675
Ovo su neki čudesni ciljevi
s kojima se sad možemo nositi.
s kojima se sad možemo nositi.
03:51
We can reduce logistical difficulties with patients.
85
215746
2426
Možemo smanjiti logističke teškoće s pacijentima.
03:54
No need to go to the clinic for a routine checkup.
86
218172
2312
Nema potrebe za odlaskom
u bolnicu na rutinski pregled.
u bolnicu na rutinski pregled.
03:56
We can do high-frequency monitoring to get objective data.
87
220484
2320
Možemo provoditi česte nadzore
kako bismo dobili objektivne podatke.
kako bismo dobili objektivne podatke.
03:58
We can perform low-cost mass recruitment for clinical trials,
88
222804
4105
Možemo jeftino i masovno pronalaziti
subjekte za kliničke pokuse
subjekte za kliničke pokuse
04:02
and we can make population-scale screening
89
226909
2115
i po prvi put je izvedivo napraviti procjenu
04:04
feasible for the first time.
90
229024
1596
na razini cijelog stanovništva.
04:06
We have the opportunity to start to search
91
230620
2202
Imamo mogućnost početi tražiti
04:08
for the early biomarkers of the disease before it's too late.
92
232822
3541
rane biomarkere bolesti prije nego bude prekasno.
04:12
So, taking the first steps towards this today,
93
236363
2758
Kako bismo učinili prvi korak prema tome,
04:15
we're launching the Parkinson's Voice Initiative.
94
239121
2126
danas lansiramo Parkinsonovu glasovnu inicijativu.
04:17
With Aculab and PatientsLikeMe, we're aiming
95
241247
2232
Zajedno s tvrtkom Aculab
i stranicom PatientsLikeMe
i stranicom PatientsLikeMe
04:19
to record a very large number of voices worldwide
96
243479
1928
ciljamo na snimanje jako velikog broja
glasova diljem svijeta
glasova diljem svijeta
04:21
to collect enough data to start to tackle these four goals.
97
245407
3140
kako bismo skupili dovoljno podataka
da se počnemo baviti s ova četiri cilja.
da se počnemo baviti s ova četiri cilja.
04:24
We have local numbers accessible to three quarters
98
248547
1700
Dostupni su nam lokalni telefonski brojevi
04:26
of a billion people on the planet.
99
250247
1610
kojima pristup ima 750 milijuna ljudi u svijetu.
04:27
Anyone healthy or with Parkinson's can call in, cheaply,
100
251857
3077
Svi zdravi, ili koji imaju Parkinsona,
mogu jeftino nazvati
mogu jeftino nazvati
04:30
and leave recordings, a few cents each,
101
254934
2139
i ostaviti zapise, koji stoje po nekoliko centa,
04:32
and I'm really happy to announce that we've already hit
102
257073
2190
i vrlo sam sretan što mogu reći
da smo već dostigli
da smo već dostigli
04:35
six percent of our target just in eight hours.
103
259263
3543
6% od našeg cilja, za samo osam sati.
04:38
Thank you. (Applause)
104
262806
3751
Hvala. (Pljesak)
04:42
(Applause)
105
266557
6320
(Pljesak)
04:48
Tom Rielly: So Max, by taking all these samples of,
106
272877
3575
Tom Rielly: Dakle, Maxe, uzimajući sve ove uzorke od,
04:52
let's say, 10,000 people,
107
276452
2776
recimo, 10 000 ljudi,
04:55
you'll be able to tell who's healthy and who's not?
108
279228
2854
moći ćete reći tko je zdrav, a tko nije?
04:57
What are you going to get out of those samples?
109
282082
1685
Što ćete dobiti iz tih uzoraka?
04:59
Max Little: Yeah. Yeah. So what will happen is that,
110
283767
1830
Max Litlle: Da. Dakle, kako to ide.
05:01
during the call you have to indicate whether or not
111
285597
1657
Tijekom poziva morate reći
05:03
you have the disease or not, you see. TR: Right.
112
287254
1267
imate li bolest ili ne. TR: Dobro.
05:04
ML: You see, some people may not do it. They may not get through it.
113
288521
2507
ML: Vidite, neki ljudi možda to ne učine.
Možda ne prođu kroz to.
Možda ne prođu kroz to.
05:06
But we'll get a very large sample of data that is collected
114
291028
2717
Ali dobit ćemo jako velik uzorak podataka prikupljen
05:09
from all different circumstances, and it's getting it
115
293745
3408
iz mnogo različitih okolnosti,
05:13
in different circumstances that matter because then
116
297153
1905
a upravo je to važno, zato što
05:14
we are looking at ironing out the confounding factors,
117
299058
3384
želimo riješiti zbunjujuće faktore
05:18
and looking for the actual markers of the disease.
118
302442
2161
i tražiti stvarne znakove bolesti.
05:20
TR: So you're 86 percent accurate right now?
119
304603
2497
TR: Dakle, trenutna točnost iznosi 86%?
05:23
ML: It's much better than that.
120
307100
1194
ML: Mnogo je bolje od toga.
05:24
Actually, my student Thanasis, I have to plug him,
121
308294
1720
Zapravo, moj učenik Thanasis,
moram ga spomenuti
moram ga spomenuti
05:25
because he's done some fantastic work,
122
310014
1870
zato što je napravio fantastičan posao
05:27
and now he has proved that it works over the mobile telephone network as well,
123
311884
3770
i dokazao da funkcionira i preko mobilnih mreža,
05:31
which enables this project, and we're getting 99 percent accuracy.
124
315654
3390
što omogućuje ovaj projekt. Dobili smo točnost od 99%.
05:34
TR: Ninety-nine. Well, that's an improvement.
125
319044
1576
TR: Devedeset devet. To se zove poboljšanje.
05:36
So what that means is that people will be able to —
126
320620
2201
Dakle, to znači da će ljudi moći –
05:38
ML: (Laughs)
127
322821
1852
ML: (Smijeh)
05:40
TR: People will be able to call in from their mobile phones
128
324673
1906
TR: Ljudi će moći nazvati sa svojih mobitela
05:42
and do this test, and people with Parkinson's could call in,
129
326579
3072
i napraviti ovaj test.
I ljudi sa Parkinsonom će moći nazvati,
I ljudi sa Parkinsonom će moći nazvati,
05:45
record their voice, and then their doctor can check up
130
329651
2870
snimiti svoj glas i onda će
njihov liječnik moći provjeriti
njihov liječnik moći provjeriti
05:48
on their progress, see where they're doing in this course of the disease.
131
332521
2681
njihov napredak, vidjeti gdje su u tijeku bolesti.
05:51
ML: Absolutely.
132
335202
970
ML: Apsolutno.
05:52
TR: Thanks so much. Max Little, everybody.
133
336172
1743
TR: Hvala puno. Maxe Little, ljudi.
05:53
ML: Thanks, Tom. (Applause)
134
337915
5157
ML: Hvala, Tome. (Pljesak)
ABOUT THE SPEAKER
Max Little - Applied mathematicianMax Little is a mathematician whose research includes a breakthrough technique to monitor – and potentially screen for – Parkinson's disease through simple voice recordings.
Why you should listen
Max Little is an applied mathematician whose goal is to "see connections between subjects, not boundaries … to see how things are related, not how they are different." He has a background in applied mathematics, statistics, signal processing and computational engineering, and his work has been applied across disciplines like biomedicine, extreme rainfall analysis and forecasting, biophysical signal processing, and hydrogeomorphology and open channel flow measurement. Little is best known for his work on the Parkinson's Voice Initiative, in which he and his team developed a cheap and simple tool that uses precise voice analysis software to detect Parkinson's with 99 percent accuracy. Little is a TEDGlobal 2012 Fellow and a Wellcome Trust-MIT Postdoctoral Research Fellow.
Max Little | Speaker | TED.com