We make a new car every year,

每年我們都會造一部新車

and then we spend the rest of the season

而當季的其他時間

trying to understand what it is we've built

就用來了解我們達成了那些

to make it better, to make it faster.

然後想辦法突破、讓車子能跑得更快

And then the next year, we start again.

下一年，重新開始

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

大家眼前的這部車結構相當複雜

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

車子底盤大約由一萬一千組零件所構成

the engine another 6,000,

引擎則使用了六千組零件

the electronics about eight and a half thousand.

電子設備將近八千五百組零件

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

所以總共約有兩萬五千組零件可能出錯

So motor racing is very much about attention to detail.

因此賽車是非常重視細節的

The other thing about Formula 1 in particular

尤其是一級方程式賽車

is we're always changing the car.

我們不斷地改車

We're always trying to make it faster.

總想盡辦法讓它能跑得更快

So every two weeks, we will be making

所以每兩週，我們就會製造

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

大約五千組新零件來組裝

Five to 10 percent of the race car

該年度會有 5% 到 10% 的賽車

will be different every two weeks of the year.

每兩週就會改頭換面一次

So how do we do that?

我們是如何辦到的呢？

Well, we start our life with the racing car.

嗯，我們的生活是從賽車開始的

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

我們在車子裡安裝了許多感應器來監測車況

On the race car in front of you here

你們眼前的這部賽車

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

比賽時裝了約一百廿個感應器

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

來測量整部車的車況

That data is logged. We're logging about

資料會被記錄下來，我們在資料系統裡

500 different parameters within the data systems,

記錄了大約五百種不同的參數

about 13,000 health parameters and events

大約一萬三千個健康參數和事件

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

車子出狀況時，這些紀錄能派上用場

and we're sending that data back to the garage

我們利用遙測技術

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

以每秒 2-4 兆位元的速率 將資料傳回修車廠

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

所以一場兩小時的比賽中 每部車會傳送出

750 million numbers.

七億五千萬個數字

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

這是我們每個人一輩子

speaks in a lifetime.

說話用字的兩倍之多

It's a huge amount of data.

這是很龐大的資料

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

但是光有資料或能測量資料是不夠的

You need to be able to do something with it.

還必須要懂得如何運用這些資料

So we've spent a lot of time and effort

所以我們花了很多時間和精力

in turning the data into stories

把數據轉換成故事

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

可以解讀引擎的狀況如何、

how are the tires degrading,

輪胎的耗損情形、

what's the situation with fuel consumption?

車子油耗又是如何？

So all of this is taking data

所以這些就是紀錄資料

and turning it into knowledge that we can act upon.

並將其轉換為 我們能採取行動的知識

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

好，讓我們來看看一點點資料

Let's pick a bit of data from

這些資料取自於

another three-month-old patient.

一個三個月大的病童

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

他是個小孩子，大家現在看到的是真實數據

and on the far right-hand side,

在最右手邊

where everything starts getting a little bit catastrophic,

可以看到情況開始變的有點糟糕

that is the patient going into cardiac arrest.

這病患的心搏漸漸停止

It was deemed to be an unpredictable event.

這是出乎預料的事情

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

沒人料想到會心臟病發

But when we look at the information there,

但是當我們檢查這些資訊時

we can see that things are starting to become

我們可以發現，大約在心搏停止前五分鐘

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

數據開始變得有點模糊不清

We can see small changes

我們可以看到如心搏速率等

in things like the heart rate moving.

有些微的變化

These were all undetected by normal thresholds

這些原本能應用在數據資料上的

which would be applied to data.

都沒有被正常閾值偵測到

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

所以問題在於為什麼我們看不到？

Was this a predictable event?

這是可以預測的事嗎？

Can we look more at the patterns in the data

我們能不能從資料的模式中看出端倪

to be able to do things better?

並採取更好的行動呢？

So this is a child,

這個小孩

about the same age as the racing car on stage,

年紀跟台上這輛賽車相仿

three months old.

都是三個月大

It's a patient with a heart problem.

這是一名心臟疾病患者

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

現在你看看螢幕上方的資料

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

心跳速率、脈搏、含氧量、呼吸速率

they're all unusual for a normal child,

都不是一個正常小朋友該有的數據

but they're quite normal for the child there,

但是對這個小朋友卻相當正常

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

因此在醫療照護上所面臨的挑戰之一是

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

如何判斷眼前的病人

have something which is specific for her,

有她專屬的資料模式

and be able to detect when things start to change,

並在情況改變、病情開始惡化時

when things start to deteriorate?

有所察覺？

Because like a racing car, any patient,

因為跟賽車的道理一樣，任何患者

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

遇到緊急狀況時，我們只有極短的時間

to make a difference.

扭轉命運

So what we did is we took a data system

所以我們使用一個 在一級方程式賽車年度裡

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

每兩週執行一次的資料系統

and we installed it on the hospital computers

並將其安裝於

at Birmingham Children's Hospital.

伯明罕兒童醫院的電腦裡

We streamed data from the bedside instruments

我們從小兒科加護病房內的

in their pediatric intensive care

床邊儀器得到數據

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

如此一來我們可以即時掌握資料

and, more importantly, to store the data

而且更重要的是，能夠儲存資料

so that we could start to learn from it.

讓我們能開始從資料中學習

And then, we applied an application on top

然後，我們運用一個可以即時讓我們

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

整理出資料模式的應用程式

in real time so we could see what was happening,

我們就能看到發生了什麼事

so we could determine when things started to change.

我們就能判斷什麼時候開始有狀況

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

之於賽車，我們都有點企圖心、

audacious, a little bit arrogant sometimes,

有點大膽、有時也有點自負

so we decided we would also look at the children

所以我們決定當那些小朋友 被送往加護病房的途中

as they were being transported to intensive care.

也要能觀察到他們的資料

Why should we wait until they arrived in the hospital

為什麼我們要等到他們抵達醫院

before we started to look?

才開始呢？

And so we installed a real-time link

因此我們在救護車及醫院之間

between the ambulance and the hospital,

安裝了一個即時連結機制

just using normal 3G telephony to send that data

只需使用一般 3G 通訊傳送資料

so that the ambulance became an extra bed

這樣一來，救護車就等同於

in intensive care.

加護病房裡的床位了

And then we started looking at the data.

然後我們開始看那些數據

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

上面那些波浪狀的線，所有顏色

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

都是我們在監測器上 會看到的正常數據資料

heart rate, pulse, oxygen within the blood,

心跳速率、脈搏、血中的含氧量

and respiration.

及呼吸速率

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

底部的藍線和紅線

these are the interesting ones.

滿有趣的

The red line is showing an automated version

紅線代表自動感應的

of the early warning score

預警分數

that Birmingham Children's Hospital were already running.

這些資料是伯明罕兒童醫院 已經跑過的數據

They'd been running that since 2008,

他們從 2008 年就開始跑這些數據

and already have stopped cardiac arrests

而且已經成功阻止了

and distress within the hospital.

院內心搏停止和心臟窘迫的案例

The blue line is an indication

而藍線呢

of when patterns start to change,

是資料模式開始產生變化的指標

and immediately, before we even started

立即地，甚至在我們開始

putting in clinical interpretation,

臨床解讀這些數據之前

we can see that the data is speaking to us.

數據已經在對我們說話

It's telling us that something is going wrong.

告訴我們情況不妙

The plot with the red and the green blobs,

這張有紅點與綠點的圖表

this is plotting different components

標示出相互對立資料的不同成分

of the data against each other.

標示出相互對立資料的不同成分

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

綠色是我們所知那位病童的正常情況資料

We call it the cloud of normality.

我們稱之為常態雲圖

And when things start to change,

當情況開始轉變、

when conditions start to deteriorate,

病情開始惡化時

we move into the red line.

我們會移到紅線上

There's no rocket science here.

這完全不涉及艱深的學問

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

只是以不同的方式呈現既有的資料

to amplify it, to provide cues to the doctors,

詳述它、提供醫生護士更多線索

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

他們就能了解正在發生什麼事

In the same way that a good racing driver

同樣地，一位優秀的賽車手

relies on cues to decide when to apply the brakes,

也仰賴線索來決定他何時該煞車、

when to turn into a corner,

何時該轉彎

we need to help our physicians and our nurses

我們須要幫助我們的醫生和護士

to see when things are starting to go wrong.

讓他們在情況不妙時能夠察覺

So we have a very ambitious program.

所以我們有一個野心勃勃的計畫

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

我們認為賽車該採取不同的行動了

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

我們目標很高，這是對的事情

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

我們有這個方法，而且如果它成功了

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

我們就沒理由只在醫院裡運用它

It can go beyond the walls.

這方法能走出醫院之牆

With wireless connectivity these days,

現在到處都有無線連結

there is no reason why patients, doctors and nurses

沒有理由病人、醫生和護士

always have to be in the same place

為何總是必須同時在同一個地方

at the same time.

為何總是必須同時在同一個地方

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

此刻，我們會讓這個三個月大的寶寶

keep taking it to the track, keeping it safe,

安安全全地待在軌道上

and making it faster and better.

跑得更快更好

Thank you very much.

謝謝大家

(Applause)

（掌聲）