演讲MP3+双语文稿:监测疾病发作的智能手表
听力课堂TED音频栏目主要包括TED演讲的音频MP3及中英双语文稿，供各位英语爱好者学习使用。本文主要内容为演讲MP3+双语文稿:监测疾病发作的智能手表，希望你会喜欢！
[演讲者及介绍]RosalindPicard
科学家、发明家、企业家，麻省理工学院(MIT)教授罗莎琳德•皮卡德(Rosalind Picard)发明了一项技术，帮助人们更好地理解影响人类健康的情绪和行为。
[演讲主题]监测癫痫发作的智能手表
[中英文字幕]
翻译者 Jingle duan 校对者 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。一个很可爱的男孩。在他三岁的时候，他的母亲发现他患有发热性痉挛。发热性痉挛是在发热时产生的癫痫症状。医生说，“不用太过担心，儿童一般在长大后症状就会消失。”四岁的时候，他出现了抽搐型癫痫。就是那种让人失去意识，并且颤抖不止的癫痫——全身强直型阵挛性癫痫。当癫痫的诊断书还没寄到的时候，一天早晨，亨利的妈妈去叫他起床。进入到他的寝室时，她发现了他冰冷、无生命体征的身体。
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：即癫痫猝死症。我很好奇你们当中有多少人听说过 SUDEP。在座各位都受过良好的教育，而我却只看到了少数人举手。SUDEP 会让一个原本健康的癫痫病人死亡后，法医在其尸检中找不到任何可以致死的原因。每7到9分钟就会有一例 SUDEP 发生。也就是说平均一场 TED 演讲的时间会发生两起 SUDEP。正常的大脑都会有电流产生。大家可以在这张大脑的图片中，看到一些脑电波。它们看起来和脑电图在头皮部位读取到的普通的电流一样。一旦遇到癫痫发作，你的脑电波会有异常，这可能就是病灶所在。它可能只发生于你大脑中的一小部分区域。当它发生时，你可能会有一种奇怪的感觉。就在当下的听众中，现在可能就在发生着几例。而你邻座的人并不知道。然而，如果你的癫痫像小火苗触发的森林大火一样在大脑中蔓延开，这时，它就形成了一般意义上的癫痫。这种癫痫会带走你的意识并且引起你的抽搐。
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.
美国每年发生的 SUDEP 比婴儿突发综合症死亡数量还多。你们当中有多少人听说过婴儿突发死亡综合症？对吧? 几乎每个人都举起手了。所以，这里到底发生了什么？为什么癫痫这么普遍，人们却没有听说过它呢？我们可以做什么来阻止癫痫呢？好的，科学证明有两件事情可以阻止或者减少 SUDEP 的风险。第一件事情就是：“遵循医嘱，按时吃药。”三分之二的癫痫病患者，通过药物可以把病情控制住。第二件可以减少 SUDEP 风险的事情是陪伴。也就是说在你发生癫痫时有人陪在身边。现在，虽然你们中的大多数人从未听说过SUDEP，是在神经系统疾病患者的潜在死因排行榜上 SUDEP 多年位居第二。竖轴是死亡人数，乘以剩余寿命。越高越糟糕。然而，SUDEP不像其它症状，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，罗兹·皮卡德，一个AI研究者能告诉你们有关 SUDEP 什么呢？我又不是一个神经学家。当我在研究情绪测量的多媒体实验室工作时, 我们研究如何让机器对我们的情感更智能。为此，我们启动了很多测量压力的工作。我们构建了很多传感器以很多不同的方式来测量压力。但脱颖而出的是一个用电子信号来测量手掌出汗的老研究。这是一个皮肤电导率的信号，很多人知道，它在你紧张时会上升，它也会随着其它有趣的环境而上升。但是通过手上绑一根电线的方式来测量确实很不方便。所以我们发明了其它的方法在MIT的多媒体实验室进行测试。这些可穿戴测量仪让我们能一周七天，24小时无间断地获取这些临床质量数据，这是前所未有的。这张照片就是一个MIT在第一次7/24周期从手腕上收集到的皮肤电导率。我们放大这里。你们可以看到从左到右是24小时这里有两天的数据。首先，令我们震惊的是睡眠时，数据达到一天中最高峰。现在，听上去好像是仪器坏了？你在睡觉时是平静的，所以，究竟发生了什么？
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.
研究发现我们在睡眠时的生理机能与我们在清醒时的生理机能大为不同。虽然我们对此的了解还不全面，“为什么通常总是在睡眠时出现一天的最高峰？”我们现在认为它们和睡眠时的记忆固化以及记忆形成有关。
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.
我们同样看到了我们精确期待会发生的事情。当一个MIT的学生在努力在实验室工作或者在写作业时，他承受的不仅有情感压力，还有认知负载，研究表明认知负载，认知努力，精神上的专注还有对所学习东西的兴奋等, 这些东西都会让这个信号上升。
05:55
Unfortunately, to the embarrassment of weMIT professors,
很不幸，这让我们MIT的教授们有些难堪，
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.
因为，每天的低点是课堂活动。我在这里只给你们展示了一个人的数据。但是这点，很不幸，却基本上是真实的。
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.
这个防汗带内置了一个自主研发的皮肤电传导传感器，一天，我们的一个大学生在12月学期结束的时候敲开了我的门然后他说到：“皮卡德教授我能借一个您的腕部传感器吗？我幼小的弟弟有自闭症，他不能说话，我想要知道什么东西会给他压力。”我说到： “当然可以，实际上，不要拿一个，拿两个吧” 因为它们那时很容易坏掉。所以他把它们带回家，并给他弟弟穿戴上了。然后，我回到了 MIT，看着我笔记本上的数据第一天，我想到：“额，这个有些古怪”“他把传感器戴在了两个手腕上，而不是等一个先坏掉。不过没事，不用遵守我的指令。”我很欣慰他没有按照我的指令。第二天 -- 数据平稳低迷，看起来像课堂活动。
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.
又过去了几天。一天，一个手腕的信号变平直了而另外一个手腕的信号出现了我从未遇到过的峰值。我当时在想，“到底发生了什么？“我们在 MIT 给人们各种可以想象到的压力。我从来没见到过这么大的峰值。”而且它还只是一边的数据。你的身体怎样才能做到一边有压力而不是另外一边呢？所以，我以为其中一个或者两个传感器一定是坏了。我是一个受过培训的电子工程师，所以，我尝试了一堆方法来调试它，简短的说，我不能重现这个现象。
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，我又诉诸于老式的排障技术。我给那个在家休假的学生挂了电话。“你好，你的弟弟情况如何？你的圣诞节怎么样？”你弟弟发生了什么事吗？”我告诉他了这个特殊的日期和时间还有当时的数据。他说到：“我不知道，我会检查日记的”
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."
日记？ 一个 MIT 学生 会保持写日记？ 所以，我等待着，他一会儿就回话。他告诉我精确的日期和时间，并且他说到： “那正是在他癫痫严重发作之前。”
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.
在那时，我对癫痫一无所知，然后我做了很多研究，而后我了解到另外一个学生的父亲是波士顿儿童医院的首席神经外科医生，我鼓足勇气，打电话给乔·马森医生。
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，乔·马森医生，我叫罗莎琳德·皮卡尔。有没有可能某个人会产生巨大的交叉神经系统激增” -- 这就是驱动表层电导率激增的原因 -- “并且这会在癫痫发作前 20分钟出现？” 他说： “可能不会。” 他说： “这很有趣。我们有病人出现一只手臂的汗毛 竖起来的情况 在癫痫发作前20分钟。“ 我说：“一只胳膊？” 起初，我并不想告诉他那件事情，因为我认为这太荒谬了。
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.
他解释到这种情况如何在大脑中发生，他也很感兴趣，我给他展示了数据。我们制作了更多的设备，并且通过安全认证。90 个家庭参与到这个研究中，这些家庭的孩子每时每刻都会被监视测量，就通过装置于他们头皮上的配备标准的脑电图分析器来读取脑部活动，还有视频来观察行为。心电监护仪还有皮肤电活动等用来检查在这范围之内是否存在某物 使得我们能很快的发现，并且它和癫痫有关。
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.
我们发现，在第一批的癫痫大发作中，100%的情况都有这种皮肤电导率的巨大波动。中间的蓝色，男孩的睡眠，通常是一天中的最大高峰值。这里看到的三个癫痫就像从森林里冒出来的红杉树。另外，如果你把顶部的表皮电导率与腕部的运动连接起来，加上你得到的大量数据，并且训练这方面的机器学习和AI，你就能构建一个自动的人工智能来更好地监测这些数据变动远比一个震动探测器能做的多。我们意识到我们需要把它做出来，随着博明哲博士的工作以及后来Empatica公司的巨大改进后，这个传感器取得了进步，而且对癫痫的检测也变的更加精确。
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.
另外在这个过程中，我们又学到了更多关于SUDEP的知识。其中一个是，SUDEP虽然很少会在强直阵痉挛发生后这是最有可能发生的时刻 -- 在那种类型之后。SUDEP 并不在癫痫发作时发生，并且它通常不会马上发生，但是，紧接着，当病人看起来非常安稳时，他们可能会进入另外一个阶段，他们会停止呼吸在呼吸停止后，后来心脏停止。所以，存在一段时间可以让某人赶过去。我们还了解到大脑深处存在一个区域叫作杏仁核区我们在情感实验室一直对它做了许多研究。我们有两个杏仁核，如果你刺激右边那一个你就会得到一个巨大的右侧皮层传导率反应。现在，你需要进行穿颅手术来做到这一点 这并不是什么我们会自愿去做的事情，但是它的确会引起一个巨大的右侧表皮传导率反应。刺激左侧那个，会引起手掌上左侧的皮层传导率反应。更进一步说，当某人刺激你的杏仁核时，你可能正坐着工作。你并不会表现出来任何悲痛的信号但你会停止呼吸。并且在某人再次刺激你之前你不会恢复呼吸。“你好，罗兹，你还好吧？”这时你张开口开始说话。当你为了说话而吸了那口气之后，你开始继续呼吸。
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，我们开始研究压力，这使得我们可以建造许多传感器，它们能收集足够多的高质量数据，使得我们可以收集实验室之外的数据。我们无意间还发现了癫痫引发的高峰反应神经系统激活，相对于传统的压力来说，能够引起更大的反应。许多医院正与癫痫监控单元合作，特别是波士顿儿童医院和布里格姆医院。现在还可利用机器学习和人工智能的技术 用来获取和收集更多的数据 以便尝试理解这些事件，看看我们是否能够阻止 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 公司已将这些商业化 这是一家初创企业，我有幸是它的联合创办人，他们团队出色地改进了 制造更完美的传感器的技术，这个传感器不止告诉我们时间，步数，睡眠这些好数据，它还实时运行着一个AI和机器学习程序 用来检测常规的强直阵痉挛型癫痫，并会在我要发生癫痫并且失去意识时发出警报。这个已经被食药监局批准作为第一个在神经系统方面被批准的智能腕表。
13:06
(Applause)
（掌声）
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.
现在，接下来的这张幻灯片导致我的皮层传导率上升。一天，我检查我的邮箱我看到了一封来自一个妈妈的故事。她说她正在淋浴，她的手机放在淋浴房的柜台上，手机告诉她女儿可能需要她的帮助。所以她中断洗澡奔跑进女儿的卧室她发现女儿在被窝里脸朝下，发紫并且没有呼吸。她把她翻转过来——人类刺激 然后她女儿吸了一口气，接着另外一口气，最终她女儿脸色变粉并且好了。
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."
我想我在读到这封邮件时脸色变白了。我的第一反应是“噢，不，这还不完善。“蓝牙可能会坏掉，电池会耗尽。这些都可能出错。你不能依赖这个。“然后她说 “没关系的，我知道没有技术是完美的。我们没有人可以一直在患者身边。但是这个设备加上AI，让我能够及时挽救我女儿的性命。”
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.
现在，我一直在谈论小孩。但是实际上，SUDEP 在20岁，30岁和 40岁人群中达到峰值。还有下一个我将要展示的曲线很可能会令一些人感到不舒适，但这其中若包括你们认识的人，你们可能会更不适。这可能发生在你认识的某个人身上吗？我提出这个令人不适的问题的原因是因为你们当中每26个人就有1个将会在某个点发生癫痫，并且根据我所学到的，患有癫痫的人通常不会告诉他们的朋友和邻居他们患有这种病的。所以如果你愿意让他们使用一个AI或者其它东西在急需时刻召唤你的话，如果你让他们知道这些，你就可以改变他们的生活。
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.
为什么做这么多辛苦工作来构建这些AI？有几个原因： 一个就是娜塔莎，那个活下来的女孩，她的家人想要我告诉你们她的名字。另外一个是她的家庭还有世界各地美好的人们，他们想去帮助那些患有癫痫却在过去不敢告诉他人的人们。另外一个原因就是你们所有人。因为我们有机会去塑造 AI 的未来。我们可以改变它因为我们就是建设它的人。
15:42
So let's build AI that makes everybody'slives better.
所以，让我们来建设 AI 来让每一个人的生活更好一些。
15:48
Thank you.
谢谢。
15:49
(Applause)
（掌声）
