Placeholder Image

Subtitles section Play video

  • So, well, I do applied math,

    嗯.我是做應用數學的

  • and this is a peculiar problem

    而對於任何做應用數學的人來說,

  • for anyone who does applied math, is that

    我們就像是

  • we are like management consultants.

    管理的諮詢師

  • No one knows what the hell we do.

    沒人知道我們到底幹什麼

  • So I am going to give you some -- attempt today

    因此呢我準備試試

  • to try and explain to you what I do.

    向你解釋一下我幹什麼

  • So, dancing is one of the most human of activities.

    舞蹈可以說是最具人類化的活動了

  • We delight at ballet virtuosos and tap dancers

    我們都喜歡芭蕾舞蹈和踢踏舞

  • you will see later on.

    你一會兒會看到的

  • Now, ballet requires an extraordinary level of expertise

    芭蕾要求很高的專業技巧

  • and a high level of skill,

    和很高的技術水準

  • and probably a level of initial suitability

    甚至還需要一些天賦

  • that may well have a genetic component to it.

    因此跟你的基因組成也有關

  • Now, sadly, neurological disorders such as Parkinson's disease

    不過可惜的是,像帕金森癥這樣的神經系統疾病

  • gradually destroy this extraordinary ability,

    會慢慢的毀滅這樣的能力

  • as it is doing to my friend Jan Stripling, who was

    就像發生在我一位跳芭蕾舞的朋友,

  • a virtuoso ballet dancer in his time.

    Jan Stripling的身上一樣

  • So great progress and treatment has been made over the years.

    近年來在治療上已經有很多進步和應用了

  • However, there are 6.3 million people worldwide

    但是呢,這世界上有630萬人有帕金森症

  • who have the disease, and they have to live with

    他們每天都得面對

  • incurable weakness, tremor, rigidity

    這無法治愈的虛弱,顫抖,僵硬

  • and the other symptoms that go along with the disease,

    以及其他一些的癥狀

  • so what we need are objective tools

    因此我們需要的是能夠在早期

  • to detect the disease before it's too late.

    就探測到疾病的良好工具

  • We need to be able to measure progression objectively,

    我們需要能夠客觀地測量進程,

  • and ultimately, the only way we're going to know

    並且最終,只有我們有能客觀地測量

  • when we actually have a cure is when we have

    我們才能研究出

  • an objective measure that can answer that for sure.

    能夠治愈帕金森症的方法

  • But frustratingly, with Parkinson's disease

    但是遺憾的是,帕金森症和

  • and other movement disorders, there are no biomarkers,

    其他生理障礙還是沒有一個生物標記

  • so there's no simple blood test that you can do,

    因此不可能做一個簡單的驗血就能查出來

  • and the best that we have is like

    目前我們能做到的只是一個

  • this 20-minute neurologist test.

    20分鐘的神經系統的測試

  • You have to go to the clinic to do it. It's very, very costly,

    你必須去臨床醫院去做,而且十分的貴,

  • and that means that, outside the clinical trials,

    這樣就意味著,除了在臨床試驗中,

  • it's just never done. It's never done.

    我們是不會去做這個測試的

  • But what if patients could do this test at home?

    不過要是病人在家裡能做的話會怎麼樣?

  • Now, that would actually save on a difficult trip to the clinic,

    當然這樣一來他們不必去臨床醫院,對吧?

  • and what if patients could do that test themselves, right?

    而且工作人員寶貴的

  • No expensive staff time required.

    時間也會節省下來

  • Takes about $300, by the way,

    順便提一下,做這個測試要花醫院

  • in the neurologist's clinic to do it.

    大約300美金呢

  • So what I want to propose to you as an unconventional way

    因此我想告訴你一種非傳統的方法

  • in which we can try to achieve this,

    從而達到這個目的

  • because, you see, in one sense, at least,

    因為你可以看到,至少,一定程度上

  • we are all virtuosos like my friend Jan Stripling.

    我們都是像我朋友Jan Stripling一樣的舞蹈家

  • So here we have a video of the vibrating vocal folds.

    我這有一個關於波動聲音的視頻

  • Now, this is healthy and this is somebody making speech sounds,

    這個是健康的而這個是某人在說話的聲音

  • and we can think of ourselves as vocal ballet dancers,

    我們可以把自己想像為聲音芭蕾舞者

  • because we have to coordinate all of these vocal organs

    因為我們必須使所有聲音器官都協調起來

  • when we make sounds, and we all actually

    當我們發聲的時候,我們都有

  • have the genes for it. FoxP2, for example.

    固定的基因在配合.比如說FoxP2

  • And like ballet, it takes an extraordinary level of training.

    跟芭蕾一樣,這需要很高的訓練水準

  • I mean, just think how long it takes a child to learn to speak.

    就想想一個小孩學會說話得多長時間吧

  • From the sound, we can actually track

    從發出的聲音裏,我們實際上可以

  • the vocal fold position as it vibrates,

    在它震動時找到聲音的位置

  • and just as the limbs are affected in Parkinson's,

    就跟肢體一樣,聲音器官

  • so too are the vocal organs.

    在帕金森症中也會被影響

  • So on the bottom trace, you can see an example of

    在這底下,你可以看到一個不尋常的

  • irregular vocal fold tremor.

    聲音腫瘤

  • We see all the same symptoms.

    我們看到的都是一樣的症狀

  • We see vocal tremor, weakness and rigidity.

    我們看到腫瘤,虛弱以及僵硬

  • The speech actually becomes quieter and more breathy

    說話變得越來越虛弱多氣

  • after a while, and that's one of the example symptoms of it.

    過一會,就成了其中一個症狀的表現

  • So these vocal effects can actually be quite subtle,

    這些對聲音的影響可能會很細微,

  • in some cases, but with any digital microphone,

    在有些情況下,使用精細聲音分析軟體

  • and using precision voice analysis software

    以及目前發展很快的機器製造學中的知識

  • in combination with the latest in machine learning,

    加上一個數位的麥克風

  • which is very advanced by now,

    我們就可以準確地

  • we can now quantify exactly where somebody lies

    辨認出人們在健康

  • on a continuum between health and disease

    和疾病之間的狀態

  • using voice signals alone.

    只用聲音信號就能鑒別

  • So these voice-based tests, how do they stack up against

    那麼這些聲音測試是怎麼跟專業

  • expert clinical tests? We'll, they're both non-invasive.

    的臨床測試相對比呢?嗯,他們都是不具侵略性的

  • The neurologist's test is non-invasive. They both use existing infrastructure.

    他們都使用目前存在的設備

  • You don't have to design a whole new set of hospitals to do it.

    你不需要重新設計一套新的設備去做這個測試

  • And they're both accurate. Okay, but in addition,

    而且他們都是準確的.不過呢,

  • voice-based tests are non-expert.

    聲音測試不是專家性的

  • That means they can be self-administered.

    這就意味著這個測試可以由病人自己來做

  • They're high-speed, take about 30 seconds at most.

    他們很方便,最多30秒就能做完

  • They're ultra-low cost, and we all know what happens.

    而且費用極低,而且我們知道

  • When something becomes ultra-low cost,

    有些東西一旦十分便宜,

  • it becomes massively scalable.

    就可以被大規模生產

  • So here are some amazing goals that I think we can deal with now.

    因此呢我認為我們可以實現一些十分驚人的目標

  • We can reduce logistical difficulties with patients.

    我們可以減少運輸病人的困難

  • No need to go to the clinic for a routine checkup.

    他們不再需要去臨床做常規檢查

  • We can do high-frequency monitoring to get objective data.

    我們可以做高頻率的測控去得到客觀的數據

  • We can perform low-cost mass recruitment for clinical trials,

    我們還可以為臨床檢查進行大批的低廉的雇傭

  • and we can make population-scale screening

    這樣我們就可以使得大規模的檢查

  • feasible for the first time.

    有史以來第一次變得可行

  • We have the opportunity to start to search

    我們可以及時檢查

  • for the early biomarkers of the disease before it's too late.

    初期疾病的標誌

  • So, taking the first steps towards this today,

    因此呢,我們建立了在帕金森聲音

  • we're launching the Parkinson's Voice Initiative.

    初始計畫上,邁出了第一步

  • With Aculab and PatientsLikeMe, we're aiming

    通過Aculab和像我一樣的病人,我們準備

  • to record a very large number of voices worldwide

    在全球記錄大量的聲音

  • to collect enough data to start to tackle these four goals.

    去收集足夠的數據來實現這四個目標

  • We have local numbers accessible to three quarters

    我們有這地球上7.5億人的

  • of a billion people on the planet.

    當地電話號碼

  • Anyone healthy or with Parkinson's can call in, cheaply,

    任何健康或者有帕金森症的人都可以打電話來,

  • and leave recordings, a few cents each,

    並且留下一段錄音,一次只花幾美分

  • and I'm really happy to announce that we've already hit

    而且我很高興地說我們

  • six percent of our target just in eight hours.

    已經在8個小時內得到了600萬個錄音

  • Thank you. (Applause)

    謝謝.(鼓掌)

  • (Applause)

    (鼓掌)

  • Tom Rielly: So Max, by taking all these samples of,

    Tom Rielly: Max, 通過收集這些,比如說10000人

  • let's say, 10,000 people,

    的樣本,

  • you'll be able to tell who's healthy and who's not?

    你就可以看出誰健康誰不是?

  • What are you going to get out of those samples?

    你能從這些樣本中看出什麼?

  • Max Little: Yeah. Yeah. So what will happen is that,

    Max Little: 是的,是的.在通話期間你必須

  • during the call you have to indicate whether or not

    說明你到底有沒有

  • you have the disease or not, you see. TR: Right.

    帕金森綜合症. TR: 好

  • ML: You see, some people may not do it. They may not get through it.

    ML: 不過有些人可能就不會這麼做

  • But we'll get a very large sample of data that is collected

    不過我們可以得到一大批從不同境況下

  • from all different circumstances, and it's getting it

    得到的數據,這樣的話這些數據都有用

  • in different circumstances that matter because then

    因為我們就可以找出

  • we are looking at ironing out the confounding factors,

    混淆的因子

  • and looking for the actual markers of the disease.

    這樣找到真正疾病的標誌

  • TR: So you're 86 percent accurate right now?

    TR: 那目前為止你有百分之86的正確率?

  • ML: It's much better than that.

    ML: 比百分之86還好很多

  • Actually, my student Thanasis, I have to plug him,

    實際上,我的一個學生Thanasis, 我必須把他提出來

  • because he's done some fantastic work,

    因為他做了一些極棒的工作

  • and now he has proved that it works over the mobile telephone network as well,

    現在他已經證明了在移動電話網上也可以測試

  • which enables this project, and we're getting 99 percent accuracy.

    這樣一來我們這個計畫基本就有百分之99的正確率

  • TR: Ninety-nine. Well, that's an improvement.

    TR: 99. 嗯,這改進還挺高的

  • So what that means is that people will be able to

    那麼這就意味著人們可以----

  • ML: (Laughs)

    ML: (笑)

  • TR: People will be able to call in from their mobile phones

    TR: 人們就可以從他們手機打來電話

  • and do this test, and people with Parkinson's could call in,

    來做這個測試,患有帕金森症的人

  • record their voice, and then their doctor can check up

    可以記錄他們的聲音,然後醫生可以監控

  • on their progress, see where they're doing in this course of the disease.

    他們的進程,以及他們在做些什麼

  • ML: Absolutely.

    ML: 沒錯,就是這樣

  • TR: Thanks so much. Max Little, everybody.

    TR: 非常感謝, Max Little, 在場的每隔人

  • ML: Thanks, Tom. (Applause)

    ML: 謝謝, Tom.(鼓掌)

So, well, I do applied math,

嗯.我是做應用數學的

Subtitles and vocabulary

Click the word to look it up Click the word to find further inforamtion about it