演講MP3+雙語文稿:監(jiān)測疾病發(fā)作的智能手表

00:00

00:00

MP3下載

https://online2.tingclass.net/lesson/shi0529/10000/10387/tedyp216.mp3

https://image.tingclass.net/statics/js/2012

聽力課堂TED音頻欄目主要包括TED演講的音頻MP3及中英雙語文稿，供各位英語愛好者學(xué)習(xí)使用。本文主要內(nèi)容為演講MP3+雙語文稿:監(jiān)測疾病發(fā)作的智能手表，希望你會喜歡！

[演講者及介紹]RosalindPicard

科學(xué)家、發(fā)明家、企業(yè)家，麻省理工學(xué)院(MIT)教授羅莎琳德?皮卡德(Rosalind Picard)發(fā)明了一項技術(shù)，幫助人們更好地理解影響人類健康的情緒和行為。

[演講主題]監(jiān)測癲癇發(fā)作的智能手表

[中英文字幕]

翻譯者 Jingle duan 校對者 Cissy Yun

00:14

This is Henry, a cute boy, and when Henrywas three, his mom found him having some febrile seizures. Febrile seizures areseizures that occur when you also have a fever, and the doctor said,"Don't worry too much. Kids usually outgrow these." When he was four,he had a convulsive seizure, the kind that you lose consciousness and shake --a generalized tonic-clonic seizure -- and while the diagnosis of epilepsy wasin the mail, Henry's mom went to get him out of bed one morning, and as shewent in his room, she found his cold, lifeless body.

他叫亨利。一個很可愛的男孩。在他三歲的時候，他的母親發(fā)現(xiàn)他患有發(fā)熱性痙攣。發(fā)熱性痙攣是在發(fā)熱時產(chǎn)生的癲癇癥狀。醫(yī)生說，“不用太過擔(dān)心，兒童一般在長大后癥狀就會消失。”四歲的時候，他出現(xiàn)了抽搐型癲癇。就是那種讓人失去意識，并且顫抖不止的癲癇——全身強(qiáng)直型陣攣性癲癇。當(dāng)癲癇的診斷書還沒寄到的時候，一天早晨，亨利的媽媽去叫他起床。進(jìn)入到他的寢室時，她發(fā)現(xiàn)了他冰冷、無生命體征的身體。

01:08

Henry died of SUDEP, sudden unexpecteddeath in epilepsy. I'm curious how many of you have heard of SUDEP. This is avery well-educated audience, and I see only a few hands. SUDEP is when anotherwise healthy person with epilepsy dies and they can't attribute it toanything they can find in an autopsy. There is a SUDEP every seven to nineminutes. That's on average two per TED Talk. Now, a normal brain has electricalactivity. You can see some of the electrical waves coming out of this pictureof a brain here. And these should look like typical electrical activity that anEEG could read on the surface. When you have a seizure, it's a bit of unusualelectrical activity, and it can be focal. It can take place in just a smallpart of your brain. When that happens, you might have a strange sensation.Several could be happening here in the audience right now, and the person nextto you might not even know. However, if you have a seizure where that littlebrush fire spreads like a forest fire over the brain, then it generalizes, andthat generalized seizure takes your consciousness away and causes you toconvulse.

亨利死于 SUDEP：即癲癇猝死癥。我很好奇你們當(dāng)中有多少人聽說過 SUDEP。在座各位都受過良好的教育，而我卻只看到了少數(shù)人舉手。SUDEP 會讓一個原本健康的癲癇病人死亡后，法醫(yī)在其尸檢中找不到任何可以致死的原因。每7到9分鐘就會有一例 SUDEP 發(fā)生。也就是說平均一場 TED 演講的時間會發(fā)生兩起 SUDEP。正常的大腦都會有電流產(chǎn)生。大家可以在這張大腦的圖片中，看到一些腦電波。它們看起來和腦電圖在頭皮部位讀取到的普通的電流一樣。一旦遇到癲癇發(fā)作，你的腦電波會有異常，這可能就是病灶所在。它可能只發(fā)生于你大腦中的一小部分區(qū)域。當(dāng)它發(fā)生時，你可能會有一種奇怪的感覺。就在當(dāng)下的聽眾中，現(xiàn)在可能就在發(fā)生著幾例。而你鄰座的人并不知道。然而，如果你的癲癇像小火苗觸發(fā)的森林大火一樣在大腦中蔓延開，這時，它就形成了一般意義上的癲癇。這種癲癇會帶走你的意識并且引起你的抽搐。

02:31

There are more SUDEPs in the United Statesevery year than sudden infant death syndrome. Now, how many of you have heardof sudden infant death syndrome? Right? Pretty much every hand goes up. Sowhat's going on here? Why is this so much more common and yet people haven'theard of it? And what can you do to prevent it? Well, there are two things,scientifically shown, that prevent or reduce the risk of SUDEP. The first is:"Follow your doctor's instructions, take your medications." Two-thirdsof people who have epilepsy get it under control with their medications. Thesecond thing that reduces the risk of SUDEP is companionship. It's havingsomebody there at the time that you have a seizure. Now, SUDEP, even thoughmost of you have never heard of it, is actually the number two cause of yearsof potential life lost of all neurological disorders. The vertical axis is thenumber of deaths times the remaining life span, so higher is much worse impact.SUDEP, however, unlike these others, is something that people right here coulddo something to push that down.

美國每年發(fā)生的 SUDEP 比嬰兒突發(fā)綜合癥死亡數(shù)量還多。你們當(dāng)中有多少人聽說過嬰兒突發(fā)死亡綜合癥？對吧? 幾乎每個人都舉起手了。所以，這里到底發(fā)生了什么？為什么癲癇這么普遍，人們卻沒有聽說過它呢？我們可以做什么來阻止癲癇呢？好的，科學(xué)證明有兩件事情可以阻止或者減少 SUDEP 的風(fēng)險。第一件事情就是：“遵循醫(yī)囑，按時吃藥?！比种陌d癇病患者，通過藥物可以把病情控制住。第二件可以減少 SUDEP 風(fēng)險的事情是陪伴。也就是說在你發(fā)生癲癇時有人陪在身邊。現(xiàn)在，雖然你們中的大多數(shù)人從未聽說過SUDEP，是在神經(jīng)系統(tǒng)疾病患者的潛在死因排行榜上 SUDEP 多年位居第二。豎軸是死亡人數(shù)，乘以剩余壽命。越高越糟糕。然而，SUDEP不像其它癥狀，在座各位可以做一些小事就能把它降低。

03:50

Now, what is Roz Picard, an AI researcher,doing here telling you about SUDEP, right? I'm not a neurologist. When I wasworking at the Media Lab on measurement of emotion, trying to make our machinesmore intelligent about our emotions, we started doing a lot of work measuringstress. We built lots of sensors that measured it in lots of different ways.But one of them in particular grew out of some of this very old work withmeasuring sweaty palms with an electrical signal. This is a signal of skinconductance that's known to go up when you get nervous, but it turns out it alsogoes up with a lot of other interesting conditions. But measuring it with wireson your hand is really inconvenient. So we invented a bunch of other ways ofdoing this at the MIT Media Lab. And with these wearables, we started tocollect the first-ever clinical quality data 24-7. Here's a picture of whatthat looked like the first time an MIT student collected skin conductance onthe wrist 24-7. Let's zoom in a little bit here. What you see is 24 hours fromleft to right, and here is two days of data. And first, what surprised us wassleep was the biggest peak of the day. Now, that sounds broken, right? You'recalm when you're asleep, so what's going on here?

我，羅茲·皮卡德，一個AI研究者能告訴你們有關(guān) SUDEP 什么呢？我又不是一個神經(jīng)學(xué)家。當(dāng)我在研究情緒測量的多媒體實驗室工作時, 我們研究如何讓機(jī)器對我們的情感更智能。為此，我們啟動了很多測量壓力的工作。我們構(gòu)建了很多傳感器以很多不同的方式來測量壓力。但脫穎而出的是一個用電子信號來測量手掌出汗的老研究。這是一個皮膚電導(dǎo)率的信號，很多人知道，它在你緊張時會上升，它也會隨著其它有趣的環(huán)境而上升。但是通過手上綁一根電線的方式來測量確實很不方便。所以我們發(fā)明了其它的方法在MIT的多媒體實驗室進(jìn)行測試。這些可穿戴測量儀讓我們能一周七天，24小時無間斷地獲取這些臨床質(zhì)量數(shù)據(jù)，這是前所未有的。這張照片就是一個MIT在第一次7/24周期從手腕上收集到的皮膚電導(dǎo)率。我們放大這里。你們可以看到從左到右是24小時這里有兩天的數(shù)據(jù)。首先，令我們震驚的是睡眠時，數(shù)據(jù)達(dá)到一天中最高峰?，F(xiàn)在，聽上去好像是儀器壞了？你在睡覺時是平靜的，所以，究竟發(fā)生了什么？

05:15

Well, it turns out that our physiologyduring sleep is very different than our physiology during wake, and whilethere's still a bit of a mystery why these peaks are usually the biggest of theday during sleep, we now believe they're related to memory consolidation andmemory formation during sleep.

研究發(fā)現(xiàn)我們在睡眠時的生理機(jī)能與我們在清醒時的生理機(jī)能大為不同。雖然我們對此的了解還不全面，“為什么通?？偸窃谒邥r出現(xiàn)一天的最高峰？”我們現(xiàn)在認(rèn)為它們和睡眠時的記憶固化以及記憶形成有關(guān)。

05:32

We also saw things that were exactly whatwe expected. When an MIT student is working hard in the lab or on homeworks,there is not only emotional stress, but there's cognitive load, and it turnsout that cognitive load, cognitive effort, mental engagement, excitement aboutlearning something -- those things also make the signal go up.

我們同樣看到了我們精確期待會發(fā)生的事情。當(dāng)一個MIT的學(xué)生在努力在實驗室工作或者在寫作業(yè)時，他承受的不僅有情感壓力，還有認(rèn)知負(fù)載，研究表明認(rèn)知負(fù)載，認(rèn)知努力，精神上的專注還有對所學(xué)習(xí)東西的興奮等, 這些東西都會讓這個信號上升。

05:55

Unfortunately, to the embarrassment of weMIT professors,

很不幸，這讓我們MIT的教授們有些難堪，

05:59

(Laughter)

（大笑）

06:00

the low point every day is classroomactivity. Now, I am just showing you one person's data here, but this,unfortunately, is true in general.

因為，每天的低點是課堂活動。我在這里只給你們展示了一個人的數(shù)據(jù)。但是這點，很不幸，卻基本上是真實的。

06:13

This sweatband has inside it a homebuiltskin-conductance sensor, and one day, one of our undergrads knocked on my doorright at the end of the December semester, and he said, "Professor Picard,can I please borrow one of your wristband sensors? My little brother hasautism, he can't talk, and I want to see what's stressing him out." And Isaid, "Sure, in fact, don't just take one, take two," because theybroke easily back then. So he took them home, he put them on his littlebrother. Now, I was back in MIT, looking at the data on my laptop, and thefirst day, I thought, "Hmm, that's odd, he put them on both wrists insteadof waiting for one to break. OK, fine, don't follow my instructions." I'mglad he didn't. Second day -- chill. Looked like classroom activity.

這個防汗帶內(nèi)置了一個自主研發(fā)的皮膚電傳導(dǎo)傳感器，一天，我們的一個大學(xué)生在12月學(xué)期結(jié)束的時候敲開了我的門然后他說到：“皮卡德教授我能借一個您的腕部傳感器嗎？我幼小的弟弟有自閉癥，他不能說話，我想要知道什么東西會給他壓力?！蔽艺f到： “當(dāng)然可以，實際上，不要拿一個，拿兩個吧” 因為它們那時很容易壞掉。所以他把它們帶回家，并給他弟弟穿戴上了。然后，我回到了 MIT，看著我筆記本上的數(shù)據(jù)第一天，我想到：“額，這個有些古怪”“他把傳感器戴在了兩個手腕上，而不是等一個先壞掉。不過沒事，不用遵守我的指令。”我很欣慰他沒有按照我的指令。第二天 -- 數(shù)據(jù)平穩(wěn)低迷，看起來像課堂活動。

07:02

(Laughter)

（大笑）

07:04

A few more days ahead. The next day, onewrist signal was flat and the other had the biggest peak I've ever seen, and Ithought, "What's going on? We've stressed people out at MIT every wayimaginable. I've never seen a peak this big." And it was only on one side.How can you be stressed on one side of your body and not the other? So Ithought one or both sensors must be broken. Now, I'm an electroengineer bytraining, so I started a whole bunch of stuff to try to debug this, and longstory short, I could not reproduce this.

又過去了幾天。一天，一個手腕的信號變平直了而另外一個手腕的信號出現(xiàn)了我從未遇到過的峰值。我當(dāng)時在想，“到底發(fā)生了什么？“我們在 MIT 給人們各種可以想象到的壓力。我從來沒見到過這么大的峰值。”而且它還只是一邊的數(shù)據(jù)。你的身體怎樣才能做到一邊有壓力而不是另外一邊呢？所以，我以為其中一個或者兩個傳感器一定是壞了。我是一個受過培訓(xùn)的電子工程師，所以，我嘗試了一堆方法來調(diào)試它，簡短的說，我不能重現(xiàn)這個現(xiàn)象。

07:41

So I resorted to old-fashioned debugging. Icalled the student at home on vacation. "Hi, how's your little brother?How's your Christmas? Hey, do you have any idea what happened to him?" AndI gave this particular date and time, and the data. And he said, "I don'tknow, I'll check the diary."

所以，我又訴諸于老式的排障技術(shù)。我給那個在家休假的學(xué)生掛了電話。“你好，你的弟弟情況如何？你的圣誕節(jié)怎么樣？”你弟弟發(fā)生了什么事嗎？”我告訴他了這個特殊的日期和時間還有當(dāng)時的數(shù)據(jù)。他說到：“我不知道，我會檢查日記的”

08:03

Diary? An MIT student keeps a diary? So Iwaited and he came back. He had the exact date and time, and he says,"That was right before he had a grand mal seizure."

日記？ 一個 MIT 學(xué)生 會保持寫日記？ 所以，我等待著，他一會兒就回話。他告訴我精確的日期和時間，并且他說到： “那正是在他癲癇嚴(yán)重發(fā)作之前。”

08:15

Now, at the time, I didn't know anythingabout epilepsy, and did a bunch of research, realized that another student'sdad is chief of neurosurgery at Children's Hospital Boston, screwed up mycourage and called Dr. Joe Madsen.

在那時，我對癲癇一無所知，然后我做了很多研究，而后我了解到另外一個學(xué)生的父親是波士頓兒童醫(yī)院的首席神經(jīng)外科醫(yī)生，我鼓足勇氣，打電話給喬·馬森醫(yī)生。

08:28

"Hi, Dr. Madsen, my name's RosalindPicard. Is it possible somebody could have a huge sympathetic nervous systemsurge" -- that's what drives the skin conductance -- "20 minutesbefore a seizure?" And he says, "Probably not." He says,"It's interesting. We've had people whose hair stands on end on one arm 20minutes before a seizure." And I'm like, "On one arm?" I didn'twant to tell him that, initially, because I thought this was too ridiculous.

“你好，喬·馬森醫(yī)生，我叫羅莎琳德·皮卡爾。有沒有可能某個人會產(chǎn)生巨大的交叉神經(jīng)系統(tǒng)激增” -- 這就是驅(qū)動表層電導(dǎo)率激增的原因 -- “并且這會在癲癇發(fā)作前 20分鐘出現(xiàn)？” 他說： “可能不會?！?他說： “這很有趣。我們有病人出現(xiàn)一只手臂的汗毛 豎起來的情況 在癲癇發(fā)作前20分鐘?！?我說：“一只胳膊？” 起初，我并不想告訴他那件事情，因為我認(rèn)為這太荒謬了。

09:01

He explained how this could happen in thebrain, and he got interested. I showed him the data. We made a whole bunch moredevices, got them safety certified. 90 families were being enrolled in a study,all with children who were going to be monitored 24-7 with gold-standard EEG ontheir scalp for reading the brain activity, video to watch the behavior,electrocardiogram -- ECG -- and now EDA, electrodermal activity, to see ifthere was something in this periphery that we could easily pick up, related toa seizure.

他解釋到這種情況如何在大腦中發(fā)生，他也很感興趣，我給他展示了數(shù)據(jù)。我們制作了更多的設(shè)備，并且通過安全認(rèn)證。90 個家庭參與到這個研究中，這些家庭的孩子每時每刻都會被監(jiān)視測量，就通過裝置于他們頭皮上的配備標(biāo)準(zhǔn)的腦電圖分析器來讀取腦部活動，還有視頻來觀察行為。心電監(jiān)護(hù)儀還有皮膚電活動等用來檢查在這范圍之內(nèi)是否存在某物 使得我們能很快的發(fā)現(xiàn)，并且它和癲癇有關(guān)。

09:31

We found, in 100 percent of the first batchof grand mal seizures, this whopper of responses in the skin conductance. Theblue in the middle, the boy's sleep, is usually the biggest peak of the day.These three seizures you see here are popping out of the forest like redwoodtrees. Furthermore, when you couple the skin conductance at the top with themovement from the wrist and you get lots of data and train machine learning andAI on it, you can build an automated AI that detects these patterns much betterthan just a shake detector can do. So we realized that we needed to get thisout, and with the PhD work of Ming-Zher Poh and later great improvements byEmpatica, this has made progress and the seizure detection is much moreaccurate.

我們發(fā)現(xiàn)，在第一批的癲癇大發(fā)作中，100%的情況都有這種皮膚電導(dǎo)率的巨大波動。中間的藍(lán)色，男孩的睡眠，通常是一天中的最大高峰值。這里看到的三個癲癇就像從森林里冒出來的紅杉樹。另外，如果你把頂部的表皮電導(dǎo)率與腕部的運動連接起來，加上你得到的大量數(shù)據(jù)，并且訓(xùn)練這方面的機(jī)器學(xué)習(xí)和AI，你就能構(gòu)建一個自動的人工智能來更好地監(jiān)測這些數(shù)據(jù)變動遠(yuǎn)比一個震動探測器能做的多。我們意識到我們需要把它做出來，隨著博明哲博士的工作以及后來Empatica公司的巨大改進(jìn)后，這個傳感器取得了進(jìn)步，而且對癲癇的檢測也變的更加精確。

10:26

But we also learned some other things aboutSUDEP during this. One thing we learned is that SUDEP, while it's rare after ageneralized tonic-clonic seizure, that's when it's most likely to happen --after that type. And when it happens, it doesn't happen during the seizure, andit doesn't usually happen immediately afterwards, but immediately afterwards,when the person just seems very still and quiet, they may go into anotherphase, where the breathing stops, and then after the breathing stops, later theheart stops. So there's some time to get somebody there. We also learned thatthere is a region deep in the brain called the amygdala, which we had beenstudying in our emotion research a lot. We have two amygdalas, and if youstimulate the right one, you get a big right skin conductance response. Now,you have to sign up right now for a craniotomy to get this done, not exactlysomething we're going to volunteer to do, but it causes a big right skinconductance response. Stimulate the left one, big left skin conductanceresponse on the palm. And furthermore, when somebody stimulates your amygdalawhile you're sitting there and you might just be working, you don't show anysigns of distress, but you stop breathing, and you don't start again untilsomebody stimulates you. "Hey, Roz, are you there?" And you open yourmouth to talk. As you take that breath to speak, you start breathing again.

另外在這個過程中，我們又學(xué)到了更多關(guān)于SUDEP的知識。其中一個是，SUDEP雖然很少會在強(qiáng)直陣痙攣發(fā)生后這是最有可能發(fā)生的時刻 -- 在那種類型之后。SUDEP 并不在癲癇發(fā)作時發(fā)生，并且它通常不會馬上發(fā)生，但是，緊接著，當(dāng)病人看起來非常安穩(wěn)時，他們可能會進(jìn)入另外一個階段，他們會停止呼吸在呼吸停止后，后來心臟停止。所以，存在一段時間可以讓某人趕過去。我們還了解到大腦深處存在一個區(qū)域叫作杏仁核區(qū)我們在情感實驗室一直對它做了許多研究。我們有兩個杏仁核，如果你刺激右邊那一個你就會得到一個巨大的右側(cè)皮層傳導(dǎo)率反應(yīng)?，F(xiàn)在，你需要進(jìn)行穿顱手術(shù)來做到這一點 這并不是什么我們會自愿去做的事情，但是它的確會引起一個巨大的右側(cè)表皮傳導(dǎo)率反應(yīng)。刺激左側(cè)那個，會引起手掌上左側(cè)的皮層傳導(dǎo)率反應(yīng)。更進(jìn)一步說，當(dāng)某人刺激你的杏仁核時，你可能正坐著工作。你并不會表現(xiàn)出來任何悲痛的信號但你會停止呼吸。并且在某人再次刺激你之前你不會恢復(fù)呼吸。“你好，羅茲，你還好吧？”這時你張開口開始說話。當(dāng)你為了說話而吸了那口氣之后，你開始繼續(xù)呼吸。

11:55

So we had started with work on stress,which had enabled us to build lots of sensors that were gathering high qualityenough data that we could leave the lab and start to get this in the wild;accidentally found a whopper of a response with the seizure, neurologicalactivation that can cause a much bigger response than traditional stressors;lots of partnership with hospitals and an epilepsy monitoring unit, especiallyChildren's Hospital Boston and the Brigham; and machine learning and AI on topof this to take and collect lots more data in service of trying to understandthese events and if we could prevent SUDEP.

所以，我們開始研究壓力，這使得我們可以建造許多傳感器，它們能收集足夠多的高質(zhì)量數(shù)據(jù)，使得我們可以收集實驗室之外的數(shù)據(jù)。我們無意間還發(fā)現(xiàn)了癲癇引發(fā)的高峰反應(yīng)神經(jīng)系統(tǒng)激活，相對于傳統(tǒng)的壓力來說，能夠引起更大的反應(yīng)。許多醫(yī)院正與癲癇監(jiān)控單元合作，特別是波士頓兒童醫(yī)院和布里格姆醫(yī)院。現(xiàn)在還可利用機(jī)器學(xué)習(xí)和人工智能的技術(shù) 用來獲取和收集更多的數(shù)據(jù) 以便嘗試?yán)斫膺@些事件，看看我們是否能夠阻止 SUDEP。

12:30

This is now commercialized by Empatica, astart-up that I had the privilege to cofound, and the team there has done anamazing job improving the technology to make a very beautiful sensor that notonly tells time and does steps and sleep and all that good stuff, but this isrunning real-time AI and machine learning to detect generalized tonic-clonicseizures and send an alert for help if I were to have a seizure and loseconsciousness. This just got FDA-approved as the first smartwatch to getapproved in neurology.

Empatica 公司已將這些商業(yè)化 這是一家初創(chuàng)企業(yè)，我有幸是它的聯(lián)合創(chuàng)辦人，他們團(tuán)隊出色地改進(jìn)了 制造更完美的傳感器的技術(shù)，這個傳感器不止告訴我們時間，步數(shù)，睡眠這些好數(shù)據(jù)，它還實時運行著一個AI和機(jī)器學(xué)習(xí)程序 用來檢測常規(guī)的強(qiáng)直陣痙攣型癲癇，并會在我要發(fā)生癲癇并且失去意識時發(fā)出警報。這個已經(jīng)被食藥監(jiān)局批準(zhǔn)作為第一個在神經(jīng)系統(tǒng)方面被批準(zhǔn)的智能腕表。

13:06

(Applause)

（掌聲）

13:15

Now, the next slide is what made my skinconductance go up. One morning, I'm checking my email and I see a story from amom who said she was in the shower, and her phone was on the counter by theshower, and it said her daughter might need her help. So she interrupts hershower and goes running to her daughter's bedroom, and she finds her daughterfacedown in bed, blue and not breathing. She flips her over -- humanstimulation -- and her daughter takes a breath, and another breath, and herdaughter turns pink and is fine.

現(xiàn)在，接下來的這張幻燈片導(dǎo)致我的皮層傳導(dǎo)率上升。一天，我檢查我的郵箱我看到了一封來自一個媽媽的故事。她說她正在淋浴，她的手機(jī)放在淋浴房的柜臺上，手機(jī)告訴她女兒可能需要她的幫助。所以她中斷洗澡奔跑進(jìn)女兒的臥室她發(fā)現(xiàn)女兒在被窩里臉朝下，發(fā)紫并且沒有呼吸。她把她翻轉(zhuǎn)過來——人類刺激 然后她女兒吸了一口氣，接著另外一口氣，最終她女兒臉色變粉并且好了。

13:50

I think I turned white reading this email.My first response is, "Oh no, it's not perfect. The Bluetooth could break,the battery could die. All these things could go wrong. Don't rely onthis." And she said, "It's OK. I know no technology is perfect. Noneof us can always be there all the time. But this, this device plus AI enabledme to get there in time to save my daughter's life."

我想我在讀到這封郵件時臉色變白了。我的第一反應(yīng)是“噢，不，這還不完善?！八{(lán)牙可能會壞掉，電池會耗盡。這些都可能出錯。你不能依賴這個?！叭缓笏f “沒關(guān)系的，我知道沒有技術(shù)是完美的。我們沒有人可以一直在患者身邊。但是這個設(shè)備加上AI，讓我能夠及時挽救我女兒的性命。”

14:18

Now, I've been mentioning children, butSUDEP peaks, actually, among people in their 20s, 30s and 40s, and the nextline I'm going to put up is probably going to make some people uncomfortable,but it's less uncomfortable than we'll all be if this list is extended tosomebody you know. Could this happen to somebody you know? And the reason Ibring up this uncomfortable question is because one in 26 of you will haveepilepsy at some point, and from what I've been learning, people with epilepsyoften don't tell their friends and their neighbors that they have it. So ifyou're willing to let them use an AI or whatever to summon you in a moment ofpossible need, if you would let them know that, you could make a difference intheir life.

現(xiàn)在，我一直在談?wù)撔『ⅰ５菍嶋H上，SUDEP 在20歲，30歲和 40歲人群中達(dá)到峰值。還有下一個我將要展示的曲線很可能會令一些人感到不舒適，但這其中若包括你們認(rèn)識的人，你們可能會更不適。這可能發(fā)生在你認(rèn)識的某個人身上嗎？我提出這個令人不適的問題的原因是因為你們當(dāng)中每26個人就有1個將會在某個點發(fā)生癲癇，并且根據(jù)我所學(xué)到的，患有癲癇的人通常不會告訴他們的朋友和鄰居他們患有這種病的。所以如果你愿意讓他們使用一個AI或者其它東西在急需時刻召喚你的話，如果你讓他們知道這些，你就可以改變他們的生活。

15:08

Why do all this hard work to build AIs? Acouple of reasons here: one is Natasha, the girl who lived, and her familywanted me to tell you her name. Another is her family and the wonderful peopleout there who want to be there to support people who have conditions thatthey've felt uncomfortable in the past mentioning to others. And the otherreason is all of you, because we have the opportunity to shape the future ofAI. We can actually change it, because we are the ones building it.

為什么做這么多辛苦工作來構(gòu)建這些AI？有幾個原因： 一個就是娜塔莎，那個活下來的女孩，她的家人想要我告訴你們她的名字。另外一個是她的家庭還有世界各地美好的人們，他們想去幫助那些患有癲癇卻在過去不敢告訴他人的人們。另外一個原因就是你們所有人。因為我們有機(jī)會去塑造 AI 的未來。我們可以改變它因為我們就是建設(shè)它的人。

15:42

So let's build AI that makes everybody'slives better.

所以，讓我們來建設(shè) AI 來讓每一個人的生活更好一些。

15:48

Thank you.

謝謝。

15:49

(Applause)

（掌聲）