This is Henry, a cute boy, and when Henry was three, his mom found him having some febrile seizures.
这位是亨利，一位可爱的男孩，亨利三岁时，他的妈妈发现他有点热痉挛。
Febrile seizures are seizures that occur when you also have a fever,
热痉挛就是在痉挛的同时还加上发烧，
and the doctor said, "Don't worry too much. Kids usually outgrow these."
而医生说：“不用太担心。通常孩子长大之后就没有了。”
When he was four, he had a convulsive seizure, the kind that you lose consciousness and shake
他四岁时出现了痉挛性癫痫，会失去意识且发抖的那一种，
a generalized tonic-clonic seizure -- and while the diagnosis of epilepsy was in the mail,
全身强直阵挛型发作--当癫痫诊断书还在邮寄的途中，
Henry's mom went to get him out of bed one morning, and as she went in his room, she found his cold, lifeless body.
一天早上亨利的妈妈去叫他起床，她进入他的房间，她发现他的身体冰冷，没有生命迹象。
Henry died of SUDEP, sudden unexpected death in epilepsy.
亨利死于SUDEP，即癫痫猝死症。
I'm curious how many of you have heard of SUDEP.
我很好奇，在座有多少人听过癫痫猝死症？
This is a very well-educated audience, and I see only a few hands.
各位是教育程度很高的观众，但我只看到几个人举手。
SUDEP is when an otherwise healthy person with epilepsy dies and they can't attribute it to anything they can find in an autopsy.
癫痫猝死症指的是健康的癫痫患者在死亡解剖后无法发现任何死因。
There is a SUDEP every seven to nine minutes.
每七到九分钟就有一个人发生癫痫猝死症。
That's on average two per TED Talk. Now, a normal brain has electrical activity.
平均每场TED演说就有两个人。正常人的大脑都会有电讯活动。
You can see some of the electrical waves coming out of this picture of a brain here.
各位可以在这张大脑的图片上看到一些电波。
And these should look like typical electrical activity that an EEG could read on the surface.
这些是脑电图从表面读到的典型脑电活动。
When you have a seizure, it's a bit of unusual electrical activity, and it can be focal.
当你发作时，就会有不寻常的脑电活动，这可能就是病灶所在。
It can take place in just a small part of your brain.
它可能只发生在大脑的一块小区域。
When that happens, you might have a strange sensation.
发生时，你可能会有很奇怪的感觉。
Several could be happening here in the audience right now, and the person next to you might not even know.
在座当中可能就有几个人现在就有这个状况，而你旁边的人可能完全不会知道。
However, if you have a seizure where that little brush fire spreads like a forest fire over the brain,
然而，如果你脑中的发作状况是从小小的火苗散播到像是森林大火，
then it generalizes, and that generalized seizure takes your consciousness away and causes you to convulse.
它就会变成全身性，而全身性的发作会夺去你的意识，造成你抽搐。
There are more SUDEPs in the United States every year than sudden infant death syndrome.
在美国，每年癫痫猝死的人数高于婴儿猝死症。
Now, how many of you have heard of sudden infant death syndrome? Right?
在座有多少人听过婴儿猝死症？是吧？
Pretty much every hand goes up. So what's going on here?
几乎人人都举手了。这是怎么回事？
Why is this so much more common and yet people haven't heard of it? And what can you do to prevent it?
为什么这种疾病这么普遍，然而大家却没听说过它呢？还有，要如何预防它呢？
Well, there are two things, scientifically shown, that prevent or reduce the risk of SUDEP.
嗯，科学指出，有两个方法可以预防或减低癫痫猝死症的风险。
The first is: "Follow your doctor's instructions, take your medications."
第一：“遵循医生指示，按时吃药。”
Two-thirds of people who have epilepsy get it under control with their medications.
三分之二的癫痫患者都能用药物来控制。
The second thing that reduces the risk of SUDEP is companionship.
能减低癫痫猝死症风险的第二个方法，就是陪伴。
It's having somebody there at the time that you have a seizure.
也就是当你发作的时候，要有人在你身边。
Now, SUDEP, even though most of you have never heard of it,
虽然大部分人没听过癫痫猝死症，
is actually the number two cause of years of potential life lost of all neurological disorders.
但它其实是所有神经疾病当中，最有可能致死的第二名。
The vertical axis is the number of deaths times the remaining life span, so higher is much worse impact.
纵轴是死亡人数，乘上剩下的生命期长，所以越高表示越糟糕的影响。
SUDEP, however, unlike these others, is something that people right here could do something to push that down.
然而，癫痫猝死症不像其他疾病，这里的人都能够做点什么来压制住它。
Now, what is Roz Picard, an AI researcher, doing here telling you about SUDEP, right? I'm not a neurologist.
为什么人工智能研究者罗莎琳·皮卡德要在这里跟大家谈癫痫猝死症？我不是神经病学家。
When I was working at the Media Lab on measurement of emotion,
我在麻省理工媒体实验室研究情绪测量时，
trying to make our machines more intelligent about our emotions, we started doing a lot of work measuring stress.
我试图要让我们的机器有更高的智能来判读我们的情绪，我们开始努力去测量压力。
We built lots of sensors that measured it in lots of different ways.
我们建造了许多传感器，用许多不同的方式来测量压力。
But one of them in particular grew out of some of this very old work with measuring sweaty palms with an electrical signal.
但其中有一种特别方式，出自用电信号来测量掌心流汗的古老研究。
This is a signal of skin conductance that's known to go up when you get nervous,
这是皮肤电导的信号，已知当你紧张时，这种信号会升高，
but it turns out it also goes up with a lot of other interesting conditions.
但结果发现，还有许多其他有趣的条件也会让它上升。
But measuring it with wires on your hand is really inconvenient.
但手上连结电线来测量实在不太方便。
So we invented a bunch of other ways of doing this at the MIT Media Lab.
所以，我们在麻省理工媒体实验室里发明了许多其他方法来做这件事。
And with these wearables, we started to collect the first-ever clinical quality data 24-7.
有了这些可穿戴的配备，我们开始能取得一周七天、一天二十四小时的高质量临床数据，这是前所未有的。
Here's a picture of what that looked like the first time an MIT student collected skin conductance on the wrist 24-7.
这张图上的是第一次从一位麻省理工学院学生的手腕收集到一周七天、一天二十四小时的皮肤电导数据。
Let's zoom in a little bit here. What you see is 24 hours from left to right, and here is two days of data.
咱们把它放大一点。从左到右是二十四小时，图上的是两天份的资料。
And first, what surprised us was sleep was the biggest peak of the day.
首先，让我们惊讶的是，一天的高峰发生在睡眠时间。
Now, that sounds broken, right? You're calm when you're asleep, so what's going on here?
听起来是故障了，对吧？你沉睡时是很冷静的，所以这是怎么回事？
Well, it turns out that our physiology during sleep is very different than our physiology during wake,
结果发现，在睡眠期间的生理机能和清醒期间非常不同，
and while there's still a bit of a mystery why these peaks are usually the biggest of the day during sleep,
虽然对于为什么一天之中的高峰通常出现在睡眠期间，这仍然有点难以理解，
we now believe they're related to memory consolidation and memory formation during sleep.
但我们现在相信，它们和记忆稳固及睡眠期间的记忆形成有关。
We also saw things that were exactly what we expected.
也有一些发现，完全在我们的预期之中。
When an MIT student is working hard in the lab or on homeworks,
当麻省理工学院学生在实验室中努力或在做功课时，
there is not only emotional stress, but there's cognitive load,
不仅有情绪压力，还有认知负荷，
and it turns out that cognitive load, cognitive effort, mental engagement, excitement about learning something
结果发现，认知负荷、认知努力、心理参与、对学习某件事物感到兴奋
those things also make the signal go up.
上述这些也都会造成信号上升。
Unfortunately, to the embarrassment of we MIT professors, the low point every day is classroom activity.
不幸的是，让我们麻省理工学院教授们很丢脸的是，一天的低点出现在教室活动期间。
Now, I am just showing you one person's data here, but this, unfortunately, is true in general.
各位在这里看到的，只是一个人的资料，但不幸的是，一般来说大家都有这个现象。
This sweatband has inside it a homebuilt skin-conductance sensor,
这条防汗带里面有自制的皮肤电导传感器，
and one day, one of our undergrads knocked on my door right at the end of the December semester,
有一天，我们的一位大学生来敲我的门，那时是十二月学期末，
and he said, "Professor Picard, can I please borrow one of your wristband sensors?
他说：“皮卡德教授，我能不能跟你借一个腕带传感器？
My little brother has autism, he can't talk, and I want to see what's stressing him out."
我弟弟有自闭症，他无法说话，我想了解是什么让他很焦虑。”
And I said, "Sure, in fact, don't just take one, take two," because they broke easily back then.
我说：“当然，事实上，拿两条去吧。”因为在那时，这种传感器很容易坏。
So he took them home, he put them on his little brother.
他把传感器带回家，让他弟弟戴上。
Now, I was back in MIT, looking at the data on my laptop,
而我在麻省理工学院里，用我的笔记本电脑看资料，
and the first day, I thought, "Hmm, that's odd, he put them on both wrists instead of waiting for one to break.
第一天，我心想：“嗯，真怪，他把两个传感器戴在两只手腕上，而不是等一个坏了。
OK, fine, don't follow my instructions."
好，不照我的指示就算了。”
I'm glad he didn't. Second day -- chill. Looked like classroom activity. A few more days ahead.
我很高兴他没照我的指示。第二天--冷淡。看起来就像教室活动期间。还要观察几天。
The next day, one wrist signal was flat and the other had the biggest peak I've ever seen,
隔天，有一只手腕的信号很平坦，另一只则有我见过最高的高峰，
and I thought, "What's going on? We've stressed people out at MIT every way imaginable. I've never seen a peak this big."
我心想：“这是怎么回事？我们在麻省理工学院里用过各种想得出来的方式制造焦虑。我从没见过这么高的高峰。”
And it was only on one side. How can you be stressed on one side of your body and not the other?
并且只发生在一只手。怎么可能身体的一边很焦虑，另一边却不会？
So I thought one or both sensors must be broken. Now, I'm an electroengineer by training,
所以我认为，至少其中一个传感器坏了。我是受过训练的电机工程师，
so I started a whole bunch of stuff to try to debug this, and long story short, I could not reproduce this.
所以我开始动手去侦错，长话短说，我无法复制这个状况。
So I resorted to old-fashioned debugging. I called the student at home on vacation.
所以，我回去用老式的侦错方法。这位学生放假在家，我打电话给他：
"Hi, how's your little brother? How's your Christmas? Hey, do you have any idea what happened to him?"
“嗨，你弟弟如何？圣诞节过得如何？嘿，你知道他发生了什么事吗？”
And I gave this particular date and time, and the data. And he said, "I don't know, I'll check the diary."
我提出了这个特定的日期、时间以及数据。他说：“我不知道，我来查一下日记。”
Diary? An MIT student keeps a diary? So I waited and he came back.
日记？麻省理工学院的学生会写日记？我等待着，他回来了。
He had the exact date and time, and he says, "That was right before he had a grand mal seizure."
他有精确的日期和时间，他说：“那刚好就是他癫痫大发作之前。”

Now, at the time, I didn't know anything about epilepsy, and did a bunch of research,
当时，我对癫痫一无所知，于是我做了一堆研究，
realized that another student's dad is chief of neurosurgery at Children's Hospital Boston,
我发现有一个学生的爸爸是波士顿儿童医院的神经外科主任，
screwed up my courage and called Dr. Joe Madsen.
我鼓起勇气，打电话给乔马德森医生。
"Hi, Dr. Madsen, my name's Rosalind Picard. Is it possible somebody could have a huge sympathetic nervous system surge"
“嗨，马德森医生，我是罗莎琳·皮卡德。有没有可能，有人会发生交感神经系统突然高涨”
that's what drives the skin conductance -- "20 minutes before a seizure?"
皮肤电导就是这么来的--“然后二十分钟后就发作？”
And he says, "Probably not." He says, "It's interesting.
他说：“应该不会。”他说：“这很有趣。
We've had people whose hair stands on end on one arm 20 minutes before a seizure."
我们见过病人一只手臂上的毛耸立，然后二十分钟后就发作。”
And I'm like, "On one arm?" I didn't want to tell him that, initially, because I thought this was too ridiculous.
我说：“一只手臂？”一开始，我还不想告诉他这件事，因为我觉得太荒谬了。
He explained how this could happen in the brain, and he got interested. I showed him the data.
他解释了大脑中可能发生了什么事，他很感兴趣，我把资料给他看。
We made a whole bunch more devices, got them safety certified.
我们又做了一大堆装置，且为它们取得安全认证。
90 families were being enrolled in a study,
一项研究招募了九十个家庭参加，
all with children who were going to be monitored 24-7 with gold-standard EEG on their scalp for reading the brain activity,
他们的孩子会受到一周七天，一天二十四小时的监控，头皮会接上高质量的脑波仪，来读取大脑活动数据，
video to watch the behavior, electrocardiogram -- ECG -- and now EDA, electrodermal activity,
有影片可观察行为，还有心电图--ECG--现在是看EDA，肤电活动，
to see if there was something in this periphery that we could easily pick up, related to a seizure.
用来寻找周围是否有什么我们可以很容易取得和发作有关的信号。
We found, in 100 percent of the first batch of grand mal seizures, this whopper of responses in the skin conductance.
我们发现，第一批的癫痫大发作全部都伴随这种超大的肤电反应。
The blue in the middle, the boy's sleep, is usually the biggest peak of the day.
中间的蓝色区段是男孩的睡眠期间，通常都是一天的高峰。
These three seizures you see here are popping out of the forest like redwood trees.
现在看到的这三次发作特别突出，就像森林中的巨杉。
Furthermore, when you couple the skin conductance at the top with the movement from the wrist
此外，如果把上面的肤电数据搭配来自手腕的活动，
and you get lots of data and train machine learning and AI on it,
就会得到很多数据，可以用来训练机器学习和人工智能，
you can build an automated AI that detects these patterns much better than just a shake detector can do.
可以建造自动化人工智能，来侦测这些模式，比晃动侦测器能做的要多太多。
So we realized that we needed to get this out,
我们知道我们得要把这些成果传出去，
and with the PhD work of Ming-Zher Poh and later great improvements by Empatica,
加上傅明哲的博士论文研究和Empatica公司后续做的大改良，
this has made progress and the seizure detection is much more accurate.
让我们有了进展，发作侦测的精确度大大提升。
But we also learned some other things about SUDEP during this.
过程中，我们也更进一步了解了癫痫猝死症。
One thing we learned is that SUDEP, while it's rare after a generalized tonic-clonic seizure,
关于癫痫猝死症，我们学到的一件事就是，虽然很少会在全身强直阵挛型发作之后，
that's when it's most likely to happen -- after that type.
那是它最可能发生的时段--在那种发作之后。
And when it happens, it doesn't happen during the seizure, and it doesn't usually happen immediately afterwards,
当它发生时，并不会在发作的过程中发生，通常不会紧接着马上发生，
but immediately afterwards, when the person just seems very still and quiet, they may go into another phase,
但紧接着，当病人还看似非常安稳的时候，可能就会进入另一个阶段，
where the breathing stops, and then after the breathing stops, later the heart stops.
在这个阶段中，呼吸停止，在呼吸停止后，心脏接着停止。
So there's some time to get somebody there.
所以还要花些时间才会到那一步。
We also learned that there is a region deep in the brain called the amygdala,
我们也发现，在大脑深处有一个区域叫做杏仁核，
which we had been studying in our emotion research a lot.
情绪研究常常会去探究这个区域。
We have two amygdalas, and if you stimulate the right one, you get a big right skin conductance response.
我们有两个杏仁核，如果去刺激右边的那个，产生的右侧肤电反应就会很大。
Now, you have to sign up right now for a craniotomy to get this done,
要愿意接受颅骨切开术才能做到这件事。
not exactly something we're going to volunteer to do, but it causes a big right skin conductance response.
我们不会想要自愿去做，但它会造成很大的右侧肤电反应。
Stimulate the left one, big left skin conductance response on the palm.
刺激左边的，手掌会有很大的左侧肤电反应。
And furthermore, when somebody stimulates your amygdala while you're sitting there and you might just be working,
此外，当有人刺激你的杏仁核，当时你坐在那里，可能正在工作，
you don't show any signs of distress, but you stop breathing, and you don't start again until somebody stimulates you.
你不会显露出任何苦难的征兆，但你会停止呼吸，而且除非有人去刺激你，你不会再次呼吸。
"Hey, Roz, are you there?" And you open your mouth to talk.
“嘿，罗莎，你在吗？”你打开你的嘴巴说话。
As you take that breath to speak, you start breathing again.
当你吸入空气以便说话，你又开始呼吸了。
So we had started with work on stress,
所以，我们开始研究压力，
which had enabled us to build lots of sensors that were gathering high quality enough data
这让我们能够打造许多传感器，用来收集质量够高的数据，
that we could leave the lab and start to get this in the wild;
能够收集实验室以外的资料；
accidentally found a whopper of a response with the seizure, neurological activation
无意间发现发作带来的高峰反应，这种神经系统活化，
that can cause a much bigger response than traditional stressors;
造成的反应远大于传统的压力因子；
lots of partnership with hospitals and an epilepsy monitoring unit,
和许多医院及一个癫痫监控单位合作，
especially Children's Hospital Boston and the Brigham;
特别是波士顿儿童医院及布莱根妇女医院；
and machine learning and AI on top of this to take and collect lots more data
此外还有机器学习和人工智能，来取得、收集更多资料，
in service of trying to understand these events and if we could prevent SUDEP.
用来试图了解这些事件，希望能够预防癫痫猝死症。
This is now commercialized by Empatica, a start-up that I had the privilege to cofound,
现在，Empatica已经将它商业化，它是家新创公司，我很荣幸是共同创办人，
and the team there has done an amazing job improving the technology to make a very beautiful sensor
那里的团队把这项技术做了很惊人的改良，做出一个很棒的传感器，
that not only tells time and does steps and sleep and all that good stuff,
它不仅能够报时，也提供睡眠相关各种信息，
but this is running real-time AI and machine learning to detect generalized tonic-clonic seizures
而且还有实时的人工智能和机器学习，可以侦测全身强直阵挛型发作，
and send an alert for help if I were to have a seizure and lose consciousness.
并在我即将发作且失去意识时发出求助警告。
This just got FDA-approved as the first smartwatch to get approved in neurology.
它刚得到食品及药物管理局的核准，是神经学领域中第一支被核准的智能手表。
Now, the next slide is what made my skin conductance go up.
下一张投影片呈现的是我的皮肤电导上升的原因。
One morning, I'm checking my email and I see a story from a mom who said she was in the shower,
有天早上，我在读电子邮件，看到了一位母亲的故事，她说她当时正在淋浴，
and her phone was on the counter by the shower, and it said her daughter might need her help.
她的手机在淋浴间的台子上，手机说她的女儿可能需要她的协助。
So she interrupts her shower and goes running to her daughter's bedroom,
所以她淋浴到一半就冲到她女儿的卧房，
and she finds her daughter facedown in bed, blue and not breathing.
她发现她的女儿面朝下趴在床上，发青，没有呼吸。
She flips her over -- human stimulation -- and her daughter takes a breath,
她把她翻过来--人类刺激--她的女儿吸了一口气，
and another breath, and her daughter turns pink and is fine.
接着再一口，她的女儿渐渐恢复血色，没事了。
I think I turned white reading this email.
我想我在读这封信时我应该是脸色发白的。
My first response is, "Oh no, it's not perfect. The Bluetooth could break, the battery could die.
我的第一个反应是：“喔，不，它不够完美。蓝牙可能会断掉，电池可能会用完。
All these things could go wrong. Don't rely on this."
这些都可能会出错。不要仰赖这个装置。”
And she said, "It's OK. I know no technology is perfect.
她说：“没关系，我知道没有任何技术是完美的。
None of us can always be there all the time.
没有人能随时都在身边。
But this, this device plus AI enabled me to get there in time to save my daughter's life."
但这个装置加上人工智能，让我能及时赶到，救了我女儿一命。”
Now, I've been mentioning children, but SUDEP peaks, actually, among people in their 20s, 30s and 40s,
我刚刚一直在谈孩子，但其实，癫痫猝死症最常发生在二十、三十、四十多岁的人身上，
and the next line I'm going to put up is probably going to make some people uncomfortable,
我接下来要说的，可能会让一些人不舒服，
but it's less uncomfortable than we'll all be if this list is extended to somebody you know.
但如果这份名单包括到你认识的人，就会更不舒服。
Could this happen to somebody you know?
这有没有可能发生在你认识的人身上？
And the reason I bring up this uncomfortable question is because one in 26 of you will have epilepsy at some point,
我之所以提出这个不舒服的问题，是因为二十六个人当中就有一个人，会在某个时点罹患癫痫，
and from what I've been learning, people with epilepsy often don't tell their friends and their neighbors that they have it.
据我所知，罹患癫痫的人通常不会告诉朋友和邻居。
So if you're willing to let them use an AI or whatever to summon you in a moment of possible need,
所以，如果你愿意让他们使用人工智能之类的东西在他们可能需要协助时呼叫你，
if you would let them know that, you could make a difference in their life.
如果你能让他们知道这点，你就能让他们的人生有所不同。
Why do all this hard work to build AIs? A couple of reasons here:
为什么要花这么多功夫来打造人工智能？这里有几个理由：
one is Natasha, the girl who lived, and her family wanted me to tell you her name.
第一个理由是娜塔莎，活下来的那位女孩，她的家人要我把她的名字告诉大家。
Another is her family and the wonderful people out there
另一个理由是她的家人以及其他美好的人，
who want to be there to support people who have conditions that they've felt uncomfortable in the past mentioning to others.
他们想要支持那些过去不敢告诉他人自己患有某些疾病的人。
And the other reason is all of you, because we have the opportunity to shape the future of AI.
还有一个理由是你们所有人，因为我们有机会形塑人工智能的未来。
We can actually change it, because we are the ones building it.
我们能够改变它，因为我们就是建造它的人。
So let's build AI that makes everybody's lives better. Thank you.
所以，咱们来打造出能改善大家生活的人工智能。谢谢。