TEDGlobal 2012
Max Little: A test for Parkinson's with a phone call
Max Little: 用電話測試帕金森症
Filmed:
Readability: 4.5
1,296,740 views
帕金森症在全世界影響630萬人，帶來了虛弱和顫抖，不過沒有一個客觀的方法可以在前期檢測到。應用數學家及TED Fellow Max Little正在測試一個準確度高達99%的帕金森症的檢驗方法---這個測試只需要一次30秒的通話。
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
嗯.我是做應用數學的
00:18
and this is a peculiar problem
1
2770
1524
而對於任何做應用數學的人來說,
00:20
for anyone who does applied math, is that
2
4294
2173
我們就像是
00:22
we are like management consultants.
3
6467
1933
管理的諮詢師
00:24
No one knows what the hell we do.
4
8400
1946
沒人知道我們到底幹什麼
00:26
So I am going to give you some -- attempt today
5
10346
2274
因此呢我準備試試
00:28
to try and explain to you what I do.
6
12620
2293
向你解釋一下我幹什麼
00:30
So, dancing is one of the most human of activities.
7
14913
3321
舞蹈可以說是最具人類化的活動了
00:34
We delight at ballet virtuosos and tap dancers
8
18234
3682
我們都喜歡芭蕾舞蹈和踢踏舞
00:37
you will see later on.
9
21916
1148
你一會兒會看到的
00:38
Now, ballet requires an extraordinary level of expertise
10
23064
2690
芭蕾要求很高的專業技巧
00:41
and a high level of skill,
11
25754
2914
和很高的技術水準
00:44
and probably a level of initial suitability
12
28668
2531
甚至還需要一些天賦
00:47
that may well have a genetic component to it.
13
31199
1847
因此跟你的基因組成也有關
00:48
Now, sadly, neurological disorders such as Parkinson's disease
14
33046
3393
不過可惜的是,像帕金森癥這樣的神經系統疾病
00:52
gradually destroy this extraordinary ability,
15
36439
2087
會慢慢的毀滅這樣的能力
00:54
as it is doing to my friend Jan Stripling, who was
16
38526
2323
就像發生在我一位跳芭蕾舞的朋友,
00:56
a virtuoso ballet dancer in his time.
17
40849
2967
Jan Stripling的身上一樣
00:59
So great progress and treatment has been made over the years.
18
43816
3054
近年來在治療上已經有很多進步和應用了
01:02
However, there are 6.3 million people worldwide
19
46870
2944
但是呢,這世界上有630萬人有帕金森症
01:05
who have the disease, and they have to live with
20
49814
3448
他們每天都得面對
01:09
incurable weakness, tremor, rigidity
21
53262
2568
這無法治愈的虛弱,顫抖,僵硬
01:11
and the other symptoms that go along with the disease,
22
55830
1857
以及其他一些的癥狀
01:13
so what we need are objective tools
23
57687
2383
因此我們需要的是能夠在早期
01:15
to detect the disease before it's too late.
24
60070
3057
就探測到疾病的良好工具
01:19
We need to be able to measure progression objectively,
25
63127
2554
我們需要能夠客觀地測量進程,
01:21
and ultimately, the only way we're going to know
26
65681
3173
並且最終,只有我們有能客觀地測量
01:24
when we actually have a cure is when we have
27
68854
2192
我們才能研究出
01:26
an objective measure that can answer that for sure.
28
71046
3398
能夠治愈帕金森症的方法
01:30
But frustratingly, with Parkinson's disease
29
74444
2850
但是遺憾的是,帕金森症和
01:33
and other movement disorders, there are no biomarkers,
30
77294
2353
其他生理障礙還是沒有一個生物標記
01:35
so there's no simple blood test that you can do,
31
79647
2229
因此不可能做一個簡單的驗血就能查出來
01:37
and the best that we have is like
32
81876
1802
目前我們能做到的只是一個
01:39
this 20-minute neurologist test.
33
83678
2241
20分鐘的神經系統的測試
01:41
You have to go to the clinic to do it. It's very, very costly,
34
85919
2458
你必須去臨床醫院去做,而且十分的貴,
01:44
and that means that, outside the clinical trials,
35
88377
2757
這樣就意味著,除了在臨床試驗中,
01:47
it's just never done. It's never done.
36
91134
2728
我們是不會去做這個測試的
01:49
But what if patients could do this test at home?
37
93862
3077
不過要是病人在家裡能做的話會怎麼樣?
01:52
Now, that would actually save on a difficult trip to the clinic,
38
96939
2098
當然這樣一來他們不必去臨床醫院,對吧?
01:54
and what if patients could do that test themselves, right?
39
99037
4254
而且工作人員寶貴的
01:59
No expensive staff time required.
40
103291
1920
時間也會節省下來
02:01
Takes about $300, by the way,
41
105211
1418
順便提一下,做這個測試要花醫院
02:02
in the neurologist's clinic to do it.
42
106629
1993
大約300美金呢
02:04
So what I want to propose to you as an unconventional way
43
108622
2681
因此我想告訴你一種非傳統的方法
02:07
in which we can try to achieve this,
44
111303
1514
從而達到這個目的
02:08
because, you see, in one sense, at least,
45
112817
1808
因為你可以看到,至少,一定程度上
02:10
we are all virtuosos like my friend Jan Stripling.
46
114625
3256
我們都是像我朋友Jan Stripling一樣的舞蹈家
02:13
So here we have a video of the vibrating vocal folds.
47
117881
3755
我這有一個關於波動聲音的視頻
02:17
Now, this is healthy and this is somebody making speech sounds,
48
121636
3229
這個是健康的而這個是某人在說話的聲音
02:20
and we can think of ourselves as vocal ballet dancers,
49
124865
3464
我們可以把自己想像為聲音芭蕾舞者
02:24
because we have to coordinate all of these vocal organs
50
128329
2214
因為我們必須使所有聲音器官都協調起來
02:26
when we make sounds, and we all actually
51
130543
2295
當我們發聲的時候,我們都有
02:28
have the genes for it. FoxP2, for example.
52
132838
2296
固定的基因在配合.比如說FoxP2
02:31
And like ballet, it takes an extraordinary level of training.
53
135134
2713
跟芭蕾一樣,這需要很高的訓練水準
02:33
I mean, just think how long it takes a child to learn to speak.
54
137847
2585
就想想一個小孩學會說話得多長時間吧
02:36
From the sound, we can actually track
55
140432
2382
從發出的聲音裏,我們實際上可以
02:38
the vocal fold position as it vibrates,
56
142814
2281
在它震動時找到聲音的位置
02:40
and just as the limbs are affected in Parkinson's,
57
145095
2543
就跟肢體一樣,聲音器官
02:43
so too are the vocal organs.
58
147638
2781
在帕金森症中也會被影響
02:46
So on the bottom trace, you can see an example of
59
150419
1880
在這底下,你可以看到一個不尋常的
02:48
irregular vocal fold tremor.
60
152299
1698
聲音腫瘤
02:49
We see all the same symptoms.
61
153997
1168
我們看到的都是一樣的症狀
02:51
We see vocal tremor, weakness and rigidity.
62
155165
2930
我們看到腫瘤,虛弱以及僵硬
02:53
The speech actually becomes quieter and more breathy
63
158095
2104
說話變得越來越虛弱多氣
02:56
after a while, and that's one of the example symptoms of it.
64
160199
2233
過一會,就成了其中一個症狀的表現
02:58
So these vocal effects can actually be quite subtle,
65
162432
2847
這些對聲音的影響可能會很細微,
03:01
in some cases, but with any digital microphone,
66
165279
3216
在有些情況下,使用精細聲音分析軟體
03:04
and using precision voice analysis software
67
168495
2545
以及目前發展很快的機器製造學中的知識
03:06
in combination with the latest in machine learning,
68
171040
2409
加上一個數位的麥克風
03:09
which is very advanced by now,
69
173449
1578
我們就可以準確地
03:10
we can now quantify exactly where somebody lies
70
175027
2886
辨認出人們在健康
03:13
on a continuum between health and disease
71
177913
2881
和疾病之間的狀態
03:16
using voice signals alone.
72
180794
2596
只用聲音信號就能鑒別
03:19
So these voice-based tests, how do they stack up against
73
183390
2314
那麼這些聲音測試是怎麼跟專業
03:21
expert clinical tests? We'll, they're both non-invasive.
74
185704
2150
的臨床測試相對比呢?嗯,他們都是不具侵略性的
03:23
The neurologist's test is non-invasive. They both use existing infrastructure.
75
187854
3982
他們都使用目前存在的設備
03:27
You don't have to design a whole new set of hospitals to do it.
76
191836
3004
你不需要重新設計一套新的設備去做這個測試
03:30
And they're both accurate. Okay, but in addition,
77
194840
2302
而且他們都是準確的.不過呢,
03:33
voice-based tests are non-expert.
78
197142
3327
聲音測試不是專家性的
03:36
That means they can be self-administered.
79
200469
1992
這就意味著這個測試可以由病人自己來做
03:38
They're high-speed, take about 30 seconds at most.
80
202461
2580
他們很方便,最多30秒就能做完
03:40
They're ultra-low cost, and we all know what happens.
81
205041
2294
而且費用極低,而且我們知道
03:43
When something becomes ultra-low cost,
82
207335
2440
有些東西一旦十分便宜,
03:45
it becomes massively scalable.
83
209775
2296
就可以被大規模生產
03:47
So here are some amazing goals that I think we can deal with now.
84
212071
3675
因此呢我認為我們可以實現一些十分驚人的目標
03:51
We can reduce logistical difficulties with patients.
85
215746
2426
我們可以減少運輸病人的困難
03:54
No need to go to the clinic for a routine checkup.
86
218172
2312
他們不再需要去臨床做常規檢查
03:56
We can do high-frequency monitoring to get objective data.
87
220484
2320
我們可以做高頻率的測控去得到客觀的數據
03:58
We can perform low-cost mass recruitment for clinical trials,
88
222804
4105
我們還可以為臨床檢查進行大批的低廉的雇傭
04:02
and we can make population-scale screening
89
226909
2115
這樣我們就可以使得大規模的檢查
04:04
feasible for the first time.
90
229024
1596
有史以來第一次變得可行
04:06
We have the opportunity to start to search
91
230620
2202
我們可以及時檢查
04:08
for the early biomarkers of the disease before it's too late.
92
232822
3541
初期疾病的標誌
04:12
So, taking the first steps towards this today,
93
236363
2758
因此呢,我們建立了在帕金森聲音
04:15
we're launching the Parkinson's Voice Initiative.
94
239121
2126
初始計畫上,邁出了第一步
04:17
With Aculab and PatientsLikeMe, we're aiming
95
241247
2232
通過Aculab和像我一樣的病人,我們準備
04:19
to record a very large number of voices worldwide
96
243479
1928
在全球記錄大量的聲音
04:21
to collect enough data to start to tackle these four goals.
97
245407
3140
去收集足夠的數據來實現這四個目標
04:24
We have local numbers accessible to three quarters
98
248547
1700
我們有這地球上7.5億人的
04:26
of a billion people on the planet.
99
250247
1610
當地電話號碼
04:27
Anyone healthy or with Parkinson's can call in, cheaply,
100
251857
3077
任何健康或者有帕金森症的人都可以打電話來,
04:30
and leave recordings, a few cents each,
101
254934
2139
並且留下一段錄音,一次只花幾美分
04:32
and I'm really happy to announce that we've already hit
102
257073
2190
而且我很高興地說我們
04:35
six percent of our target just in eight hours.
103
259263
3543
已經在8個小時內得到了600萬個錄音
04:38
Thank you. (Applause)
104
262806
3751
謝謝.(鼓掌)
04:42
(Applause)
105
266557
6320
(鼓掌)
04:48
Tom Rielly: So Max, by taking all these samples of,
106
272877
3575
Tom Rielly: Max, 通過收集這些,比如說10000人
04:52
let's say, 10,000 people,
107
276452
2776
的樣本,
04:55
you'll be able to tell who's healthy and who's not?
108
279228
2854
你就可以看出誰健康誰不是?
04:57
What are you going to get out of those samples?
109
282082
1685
你能從這些樣本中看出什麼？
04:59
Max Little: Yeah. Yeah. So what will happen is that,
110
283767
1830
Max Little: 是的,是的.在通話期間你必須
05:01
during the call you have to indicate whether or not
111
285597
1657
說明你到底有沒有
05:03
you have the disease or not, you see. TR: Right.
112
287254
1267
帕金森綜合症. TR: 好
05:04
ML: You see, some people may not do it. They may not get through it.
113
288521
2507
ML: 不過有些人可能就不會這麼做
05:06
But we'll get a very large sample of data that is collected
114
291028
2717
不過我們可以得到一大批從不同境況下
05:09
from all different circumstances, and it's getting it
115
293745
3408
得到的數據,這樣的話這些數據都有用
05:13
in different circumstances that matter because then
116
297153
1905
因為我們就可以找出
05:14
we are looking at ironing out the confounding factors,
117
299058
3384
混淆的因子
05:18
and looking for the actual markers of the disease.
118
302442
2161
這樣找到真正疾病的標誌
05:20
TR: So you're 86 percent accurate right now?
119
304603
2497
TR: 那目前為止你有百分之86的正確率?
05:23
ML: It's much better than that.
120
307100
1194
ML: 比百分之86還好很多
05:24
Actually, my student Thanasis, I have to plug him,
121
308294
1720
實際上,我的一個學生Thanasis, 我必須把他提出來
05:25
because he's done some fantastic work,
122
310014
1870
因為他做了一些極棒的工作
05:27
and now he has proved that it works over the mobile telephone network as well,
123
311884
3770
現在他已經證明了在移動電話網上也可以測試
05:31
which enables this project, and we're getting 99 percent accuracy.
124
315654
3390
這樣一來我們這個計畫基本就有百分之99的正確率
05:34
TR: Ninety-nine. Well, that's an improvement.
125
319044
1576
TR: 99. 嗯,這改進還挺高的
05:36
So what that means is that people will be able to —
126
320620
2201
那麼這就意味著人們可以----
05:38
ML: (Laughs)
127
322821
1852
ML: (笑)
05:40
TR: People will be able to call in from their mobile phones
128
324673
1906
TR: 人們就可以從他們手機打來電話
05:42
and do this test, and people with Parkinson's could call in,
129
326579
3072
來做這個測試,患有帕金森症的人
05:45
record their voice, and then their doctor can check up
130
329651
2870
可以記錄他們的聲音,然後醫生可以監控
05:48
on their progress, see where they're doing in this course of the disease.
131
332521
2681
他們的進程,以及他們在做些什麼
05:51
ML: Absolutely.
132
335202
970
ML: 沒錯,就是這樣
05:52
TR: Thanks so much. Max Little, everybody.
133
336172
1743
TR: 非常感謝, Max Little, 在場的每隔人
05:53
ML: Thanks, Tom. (Applause)
134
337915
5157
ML: 謝謝, Tom.(鼓掌)
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