Peter van Manen: How can Formula 1 racing help ... babies?

翻译人员: Wei Wu 校对人员: Maggie Zhu

Motor racing is a funny old business.

赛车是一项充满乐趣的经典运动。

We make a new car every year,

每年我们都造出新的赛车，

and then we spend the rest of the season

然后在这一年剩下的时间中

trying to understand what it is we've built

分析和理解新赛车的特性，

to make it better, to make it faster.

改进它，让它更快。

And then the next year, we start again.

然后第二年，重新开始这个过程。

Now, the car you see in front of you is quite complicated.

你现在看到的这辆车是非常复杂的。

The chassis is made up of about 11,000 components,

光底盘就用了超过一万个零件，

the engine another 6,000,

引擎的零件数量超过六千个，

the electronics about eight and a half thousand.

电控部分有大概八千五百个组件。

So there's about 25,000 things there that can go wrong.

总零件数超过2.5万个，每个零件保证不能出错。

So motor racing is very much about attention to detail.

所以赛车运动需要非常注重细节。

The other thing about Formula 1 in particular

F1方程式赛车的另一个特别的地方，

is we're always changing the car.

是我们一直在更新和改装赛车。

We're always trying to make it faster.

我们持续性的改进它使它更快。

So every two weeks, we will be making

所以平均每两周时间，

about 5,000 new components to fit to the car.

我们就会替换掉车内大约5000个零件。

Five to 10 percent of the race car

赛车中大约5-10%的零部件

will be different every two weeks of the year.

在一年中每两周就会被更换一次。

So how do we do that?

那么我们是怎么做到的？

Well, we start our life with the racing car.

我们的改进过程从比赛开始。

We have a lot of sensors on the car to measure things.

我们用大量的传感器来记录车辆运行状态。

On the race car in front of you here

你们面前的这辆车在比赛时，

there are about 120 sensors when it goes into a race.

会携带大约120个不同的传感器。

It's measuring all sorts of things around the car.

它们记录赛车运行时的所有数据。

That data is logged. We're logging about

数据被记录并保存。

500 different parameters within the data systems,

我们的数据系统包含约500个内部参数，

about 13,000 health parameters and events

1.3万个车况信息及事件记录器，

to say when things are not working the way they should do,

当系统的某些地方工作出现问题时，

and we're sending that data back to the garage

我们将这些数据回传到车库进行分析

using telemetry at a rate of two to four megabits per second.

无线传送速率能达到2M到4M每秒

So during a two-hour race, each car will be sending

所以两个小时的比赛过程后，每辆车发送的数字

750 million numbers.

数据量超过7.5亿。

That's twice as many numbers as words that each of us

我们每个人一辈子说过的单词总数加起来，

speaks in a lifetime.

还不到其中的一半。

It's a huge amount of data.

这是很多的数据。

But it's not enough just to have data and measure it.

但是仅仅测量和记录这些数字还不够。

You need to be able to do something with it.

你需要利用这些数据做出点什么。

So we've spent a lot of time and effort

所以我们花了大量的时间和精力，

in turning the data into stories

赋予这些数据以意义，

to be able to tell, what's the state of the engine,

使我们能够知道，引擎的状态如何，

how are the tires degrading,

轮胎磨损的程度如何，

what's the situation with fuel consumption?

油耗的情势如何？

So all of this is taking data

我们所做的这一切，

and turning it into knowledge that we can act upon.

就是将数据转换成能够知道我们工作的知识。

Okay, so let's have a look at a little bit of data.

现在，让我们看看一眼原始数据。

Let's pick a bit of data from

再看看从一个三个月大的

another three-month-old patient.

病人身上采集到的一些数据。

This is a child, and what you're seeing here is real data,

这是个孩子，而你现在看到的都是真实数据，

and on the far right-hand side,

注意最右边的曲线，

where everything starts getting a little bit catastrophic,

情况开始变得有点糟糕，

that is the patient going into cardiac arrest.

患者开始出现心跳骤停的症状。

It was deemed to be an unpredictable event.

这被认为是一件无法预先判定的事件。

This was a heart attack that no one could see coming.

没有人预见到这次心脏病发作。

But when we look at the information there,

但是当我们仔细看这些曲线，

we can see that things are starting to become

我们能够看到在心跳骤停的5分钟左右，

a little fuzzy about five minutes or so before the cardiac arrest.

记录仪的数据出现了一些征兆。

We can see small changes

我们能够看到心率等数据中

in things like the heart rate moving.

出现的一些细小的改变。

These were all undetected by normal thresholds

这些改变的幅度很小，常规的检测值

which would be applied to data.

无法甄别出这些改变。

So the question is, why couldn't we see it?

那么问题变成了，为什么我们注意不到这个？

Was this a predictable event?

这个事件可以用来预测么？

Can we look more at the patterns in the data

是不是我们对于数据中模式的分析越详尽

to be able to do things better?

就可以预测的越准？

So this is a child,

这个孩子

about the same age as the racing car on stage,

跟台上的这台赛车一样大，

three months old.

三个月了。

It's a patient with a heart problem.

这个孩子患上了心脏病。

Now, when you look at some of the data on the screen above,

现在，看着屏幕上的这些数据，

things like heart rate, pulse, oxygen, respiration rates,

有心率、脉搏、血氧量、呼吸频率，

they're all unusual for a normal child,

它们跟正常的小孩子相比都存在差异，

but they're quite normal for the child there,

但是对于病房的小朋友们来说很正常，

and so one of the challenges you have in health care is,

所以医疗诊断的挑战之一，

how can I look at the patient in front of me,

就是我如何通过观察眼前的病人，

have something which is specific for her,

通过从她身上获取的特有的一些数据，

and be able to detect when things start to change,

能够在情况开始恶化之前，

when things start to deteriorate?

检测到苗头？

Because like a racing car, any patient,

这点上病人与赛车是相似的，

when things start to go bad, you have a short time

当事情恶化时，你只有很短的时间，

to make a difference.

来避免事态扩大。

So what we did is we took a data system

我们的方法是使用一个数据系统，

which we run every two weeks of the year in Formula 1

F1赛车每两周运行一次的数据系统，

and we installed it on the hospital computers

我们把该系统安装在伯明翰儿童医院的

at Birmingham Children's Hospital.

内部电脑上。

We streamed data from the bedside instruments

我们将医院儿童重症监护室中病床周围的设备

in their pediatric intensive care

接入到我们的系统中，

so that we could both look at the data in real time

这样我们就可以实时的查看到这些数据，

and, more importantly, to store the data

并且更重要的，我们将这些数据长期保存，

so that we could start to learn from it.

使我们能够从中寻找规律。

And then, we applied an application on top

然后，我们在系统上使用了一款软件，

which would allow us to tease out the patterns in the data

能够帮助我们实时的将数据中包含的模式

in real time so we could see what was happening,

梳理出来，让我们看到事情发展的过程，

so we could determine when things started to change.

让我们能够确定情势何时开始发生了变化。

Now, in motor racing, we're all a little bit ambitious,

在赛车比赛中，我们都怀有野心，

audacious, a little bit arrogant sometimes,

无所畏惧，有时候还会有些鲁莽，

so we decided we would also look at the children

所以我们觉得我们应该在孩子被送往医院的路上，

as they were being transported to intensive care.

就开始对他们进行数据采集和分析。

Why should we wait until they arrived in the hospital

为什么要等到他们到了医院才开始

before we started to look?

数据采集和分析呢？

And so we installed a real-time link

于是我们在救护车和医院之间

between the ambulance and the hospital,

搭建了一个实时数据传送的链接，

just using normal 3G telephony to send that data

采用普通的3G通信网络传送数据，

so that the ambulance became an extra bed

现在急救车也变成了移动版的

in intensive care.

重症监护室。

And then we started looking at the data.

然后我们开始分析这些数据。

So the wiggly lines at the top, all the colors,

上面的这些弯弯绕绕、五颜六色的线条，

this is the normal sort of data you would see on a monitor --

跟你在病床监视器上看到过的数据是一样的——

heart rate, pulse, oxygen within the blood,

心率、脉搏、血氧含量，

and respiration.

以及呼吸速率。

The lines on the bottom, the blue and the red,

现在，底下的两条红色和蓝色的曲线，

these are the interesting ones.

是我们关心的。

The red line is showing an automated version

红线表示的是伯明翰儿童医院

of the early warning score

正在使用的早期预警阈值

that Birmingham Children's Hospital were already running.

这是（通过数据分析）自动生成的。

从2008年就开始运行了，

They'd been running that since 2008,

and already have stopped cardiac arrests

已经在医院内成功的阻止了多次

and distress within the hospital.

心搏骤停引发的悲剧。

The blue line is an indication

蓝色的曲线向我们指示出

of when patterns start to change,

病人的情势何时开始发生变化，

and immediately, before we even started

让我们甚至不需要进行临床诊断

putting in clinical interpretation,

就能立即而直观的，

we can see that the data is speaking to us.

看到数据自己向我们传达的信息。

It's telling us that something is going wrong.

数据告诉我们出问题了。

The plot with the red and the green blobs,

这些红色和绿色的小球体，

this is plotting different components

表示的是来自不同样本群体的

of the data against each other.

同一种类型的数据。

The green is us learning what is normal for that child.

我们通过绿色的小球表示的数据来学习“正常状态”

We call it the cloud of normality.

我们称之为“常态云”。

And when things start to change,

然后当情势开始变化，

when conditions start to deteriorate,

当病情开始恶化，

we move into the red line.

数据就跳到了红色的范围。

There's no rocket science here.

这并不复杂。

It is displaying data that exists already in a different way,

我们只是将已经存在的数据用另一种方式呈现，

to amplify it, to provide cues to the doctors,

放大数据的差异，供医护人员诊断，

to the nurses, so they can see what's happening.

让他们更容易看出情势的变化。

In the same way that a good racing driver

这跟一个优秀的赛车手，

relies on cues to decide when to apply the brakes,

依赖于各种线索来决定何时刹车，

when to turn into a corner,

何时转向是一个道理，

we need to help our physicians and our nurses

我们需要帮助我们的医生和护士

to see when things are starting to go wrong.

在病情恶化的开始提前发现和处理。

So we have a very ambitious program.

我们有一个很雄伟的计划。

We think that the race is on to do something differently.

我们在这场比赛中需要打破常规。

We are thinking big. It's the right thing to do.

我们目标远大，我们在做正确的事。

We have an approach which, if it's successful,

如果我们的方法是可行的，那么没有任何理由，

there's no reason why it should stay within a hospital.

将这种方法的应用范围局限在医院内。

它可以有更广的使用范围。

It can go beyond the walls.

With wireless connectivity these days,

无线网络连接在今天已经无处不在，

there is no reason why patients, doctors and nurses

没有理由还要求病人、医生和护士

always have to be in the same place

一定要在同一个时间，出现在

at the same time.

同一个地点。

And meanwhile, we'll take our little three-month-old baby,

与此同时，我们将继续改进我们的赛车，

keep taking it to the track, keeping it safe,

确保其车况良好，确保其安全，

and making it faster and better.

并且使之更快、更好。

Thank you very much.

谢谢大家。

(Applause)

（掌声）