ABOUT THE SPEAKER
Peter van Manen - Electronic systems expert
Peter van Manen is the Managing Director of McLaren Electronics, which provides data systems to major motorsports series.

Why you should listen

To say that Peter van Manen has a high-speed job would be an understatement. As Managing Director of McLaren Electronics, which provides electronics and data collection software to motorsports events, he and his team work in real time during a race to improve cars on about 500 different parameters. That's about 750 million data points in two hours.

But recently van Manen and his team have been wondering: Why can't the extremely precise and subtle data-collection and analysis systems used in motorsports be applied elsewhere, for the benefit of all? They have applied their systems to ICU units at Birmingham Children's Hospital with real-time analysis that allows them to proactively prevent cardiac arrests. The unit has seen a 25 percent decrease in life-threatening events. And it's just the beginning.

More profile about the speaker
Peter van Manen | Speaker | TED.com
TEDxNijmegen

Peter van Manen: Better baby care -- thanks to Formula 1

Peter van Manen: Jinsi mbio za magari zinavyoweza kuwasaidia watoto wachanga?

Filmed:
845,406 views

Wakati wa mbio za magari za Formula 1, gari linatuma mamia ya mamilioni ya taarifa mbalimbali karakana yake kwa ajili ya uchunguzi na upashanaji taarifa kwa wakati huo huo. Kwa hiyo kwa nini tusitumie mfumo huu wa taarifa sehemu nyingine, kama ... katika hospitali za watoto? Peter Van Manen anatueleza zaidi
- Electronic systems expert
Peter van Manen is the Managing Director of McLaren Electronics, which provides data systems to major motorsports series. Full bio

Double-click the English transcript below to play the video.

00:12
MotorMagari racingracing is a funnyfunny oldzamani businessbiashara.
0
336
2257
Mbio za magari ni biashara ya zamani ya kufurahisha
00:14
We make a newmpya cargari everykila yearmwaka,
1
2593
2317
Tunatengeneza gari jipya kila mwaka,
00:16
and then we spendtumia the restpumzika of the seasonmsimu
2
4910
2188
halafu tunatumia msimu wote
00:19
tryingkujaribu to understandkuelewa what it is we'vetumekuwa builtkujengwa
3
7098
2776
kujaribu kuelewa ni nini ambacho tumekijenga
00:21
to make it better, to make it fasterharaka.
4
9874
3221
kuifanya iwe bora zaidi, na kuifanya iende kasi zaidi.
00:25
And then the nextijayo yearmwaka, we startkuanza again.
5
13095
3275
halafu mwaka unaofuata, tunaanza upya.
00:28
Now, the cargari you see in frontmbele of you is quitekabisa complicatedngumu.
6
16370
4238
Gari lililo mbele yako
00:32
The chassischasisi is madealifanya up of about 11,000 componentsvipengele,
7
20608
3619
chesisi inaundwa na vifaa mbalimbali takribani 11,000
00:36
the engineinjini anothermwingine 6,000,
8
24227
2468
Injini vingine 6000,
00:38
the electronicsumeme about eightnane and a halfnusu thousandelfu.
9
26695
3093
vya elektroniki takriban 8500
00:41
So there's about 25,000 things there that can go wrongsi sawa.
10
29788
4401
kwa hiyo kuna vitu kama 25,000 hivi vinavyoweza kuharibika.
00:46
So motormagari racingracing is very much about attentiontazama to detailmaelezo zaidi.
11
34189
4826
kwa umakini wa hali ya juu ni muhimu sana katika mbio za magari
00:51
The other thing about FormulaFomula 1 in particularhasa
12
39015
3263
Kitu kingine kuhusu mbio za magari hasa ya langa langa
00:54
is we're always changingkubadilisha the cargari.
13
42278
2124
ni kwamba kila wakati tunabadilisha gari.
00:56
We're always tryingkujaribu to make it fasterharaka.
14
44402
2280
Kila wakati tunajaribu kulifanya bora zaidi.
00:58
So everykila two weekswiki, we will be makingkufanya
15
46682
2984
Kila baada ya wiki mbili, tunakuwa tunatengeneza
01:01
about 5,000 newmpya componentsvipengele to fitinafaa to the cargari.
16
49666
4200
vifaa vipya 5000 kwa ajili ya kuweka katika gari.
01:05
FiveTano to 10 percentasilimia of the racembio cargari
17
53866
2178
asilimia 5 mpaka 10 ya gari la mbio.
01:08
will be differenttofauti everykila two weekswiki of the yearmwaka.
18
56044
3752
linabadilishwa kila baada ya wiki mbili.
01:11
So how do we do that?
19
59796
2309
Kwa hiyo tunafanyaje haya yote?
01:14
Well, we startkuanza our life with the racingracing cargari.
20
62105
3744
Tunaanza na gari la mashindano,
01:17
We have a lot of sensorssensorer on the cargari to measurekupima things.
21
65849
3991
Tuna vifaa vya kupima mambo mbalimbali vingi sana.
01:21
On the racembio cargari in frontmbele of you here
22
69840
1882
katika gari la mashindano mbele
01:23
there are about 120 sensorssensorer when it goeshuenda into a racembio.
23
71722
3159
kuna vifaa vya kupima mambo mbalimbali kama 120 linapoenda mashindanoni.
01:26
It's measuringkupima all sortsaina of things around the cargari.
24
74881
3652
vinapima vitu mbalimbali katika gari
01:30
That datadata is loggedumeingia. We're loggingkuingia about
25
78533
2052
Taarifa zinawekwa katika kumbukumbu. tunatunza kumbukumbu
01:32
500 differenttofauti parametersvigezo withinndani the datadata systemsmifumo,
26
80585
3704
500 mbalimbali za vitu mbalimbali,
01:36
about 13,000 healthafya parametersvigezo and eventsmatukio
27
84289
3665
vitu mbalimbali kuhusu afya ya gari na matukio
01:39
to say when things are not workingkufanya kazi the way they should do,
28
87954
4565
kuelezea mambo yanapoenda vibaya,
01:44
and we're sendingkutuma that datadata back to the garagekarakana
29
92519
2825
tunatuma taarifa hizi kwenda kitengo cha matengenezo
01:47
usingkutumia telemetrytelemetry at a ratekiwango of two to fournne megabitsmegabits perkwa kila secondpili.
30
95344
4979
Kwa kutumia kifaa cha kupima taarifa mbalimbali
01:52
So duringwakati a two-hoursaa mbili racembio, eachkila mmoja cargari will be sendingkutuma
31
100323
3127
kila masaa mawili ya mbio,kila gari linatuma
01:55
750 millionmilioni numbersnambari.
32
103450
2275
namba 750 millioni
01:57
That's twicemara mbili as manywengi numbersnambari as wordsmaneno that eachkila mmoja of us
33
105725
3143
hiyo ni mara mbili ya maneno ambayo
02:00
speaksanasema in a lifetimemaisha.
34
108868
1631
tunazungumza katika maisha yetu
02:02
It's a hugekubwa amountkiasi of datadata.
35
110499
2618
ni kiasi kikubwa cha taarifa.
02:05
But it's not enoughkutosha just to have datadata and measurekupima it.
36
113117
2645
lakini haitoshi tu, kuwa na taarifa na vipimo.
02:07
You need to be ableinaweza to do something with it.
37
115762
2158
unahitaji kuwa na uwezo wa kuzifanyia kazi.
02:09
So we'vetumekuwa spentalitumia a lot of time and effortjuhudi
38
117920
2394
Kwa hiyo tumetumia muda mwingi na juhudi
02:12
in turningkugeuka the datadata into storieshadithi
39
120314
1869
kubadilisha taarifa kuwa hadithi
02:14
to be ableinaweza to tell, what's the statehali of the engineinjini,
40
122183
3105
ili kuweza kueleza, hali ya injini,
02:17
how are the tiresmatairi degradingkutotambua,
41
125288
2272
Matairi yanachoka vipi,
02:19
what's the situationhali with fuelmafuta consumptionmatumizi?
42
127560
3748
mafuta yanatumikaje?
02:23
So all of this is takingkuchukua datadata
43
131308
2788
hiyo yote inachukua taarifa
02:26
and turningkugeuka it into knowledgeujuzi that we can acttenda uponjuu.
44
134096
3802
na kuzibadilisha kuwa maarifa tunayoweza kujifunza.
02:29
Okay, so let's have a look at a little bitkidogo of datadata.
45
137898
2638
Sawa,kwa hiyo tuangalie kidogo kuhusu taarifa.
02:32
Let's pickpick a bitkidogo of datadata from
46
140536
2030
tuangalie kiasi kidogo cha taarifa kutoka
02:34
anothermwingine three-month-oldmwenye umri wa miezi mitatu patientsubira.
47
142566
3079
kwa mgonjwa wa miezi mitatu.
02:37
This is a childmtoto, and what you're seeingkuona here is realhalisi datadata,
48
145645
4171
Huyu ni mtoto, na unachokiona hapa ni taarifa halisi,
02:41
and on the farmbali right-handmkono wa kulia sideupande,
49
149816
1977
na upande huu wa kulia,
02:43
where everything startskuanza gettingkupata a little bitkidogo catastrophicjanga,
50
151793
2587
mahali ambapo kila kitu kiaanza kuwa cha hatari,
02:46
that is the patientsubira going into cardiacmoyo arrestkukamatwa.
51
154380
3584
ambapo mgonjwa anapata mshituko wa moyo.
02:49
It was deemedimeonekana to be an unpredictablehaitabiriki eventtukio.
52
157964
3232
inaonekana kuwa ni tukio lisilotabirika..
02:53
This was a heartmoyo attackkushambulia that no one could see comingkuja.
53
161196
3789
Hili lilikuwa ni shambulio la moyo ambalo hakuna mtu aliyeliona.
02:56
But when we look at the informationhabari there,
54
164985
2550
Lakini tunapoangalia taarifa pale,
02:59
we can see that things are startingkuanzia to becomekuwa
55
167535
2349
tunaona vitu vinaanza kuwa
03:01
a little fuzzyfuzzy about fivetano minutesdakika or so before the cardiacmoyo arrestkukamatwa.
56
169884
4029
havieleweki kama dakika tano hivi kabla ya shambulio la la moyo.
03:05
We can see smallndogo changesmabadiliko
57
173913
2037
Tunaona mabadiliko madogo
03:07
in things like the heartmoyo ratekiwango movingkusonga.
58
175950
2383
katika vitu kama mapigo ya moyo
03:10
These were all undetectedbila ya kugundulika by normalkawaida thresholdsvizingiti vya
59
178333
2486
hivi vilikuwa haviwezekani kugundulika na vipimo vya kawaida
03:12
whichambayo would be appliedkutumika to datadata.
60
180819
2408
ambazo zitatumika na taarifa
03:15
So the questionswali is, why couldn'thaikuweza we see it?
61
183227
3143
kwa hiyo swali, lilikuwa ni kwa nini hatukuweza kuona?
03:18
Was this a predictableinatabirika eventtukio?
62
186370
2581
Je hili lilikuwa ni tukio la kutabirika?
03:20
Can we look more at the patternschati in the datadata
63
188951
3010
je tunaweza kuangalia tabia za taarifa
03:23
to be ableinaweza to do things better?
64
191961
3380
ili kuweza kufanya vitu upya?
03:27
So this is a childmtoto,
65
195341
2650
Kwa hiyo huyu ni mtoto,
03:29
about the samesawa ageumri as the racingracing cargari on stagehatua,
66
197991
3232
umri sawa na gari la mbio jukwaani,
03:33
threetatu monthsmiezi oldzamani.
67
201223
1630
miezi mitatu.
03:34
It's a patientsubira with a heartmoyo problemtatizo.
68
202853
2605
Ni mgonjwa mwenye tatizo la moyo
03:37
Now, when you look at some of the datadata on the screenskrini abovehapo juu,
69
205458
3468
Ukiangalia baadhi ya taarifa hapo juu,
03:40
things like heartmoyo ratekiwango, pulsepigo, oxygenoksijeni, respirationupumuaji ratesviwango,
70
208926
4902
mapigo ya moyo,oksijeni,upumuaji,
03:45
they're all unusualisiyo ya kawaida for a normalkawaida childmtoto,
71
213828
3076
vyote sio sawa kwa mtoto wa kawaida,
03:48
but they're quitekabisa normalkawaida for the childmtoto there,
72
216904
2642
lakini ni sawa kwa mtoto yule,
03:51
and so one of the challengeschangamoto you have in healthafya carehuduma is,
73
219546
4138
kwa hiyo moja kati ya changamoto tuliyo nayo katika huduma za afya,
03:55
how can I look at the patientsubira in frontmbele of me,
74
223684
2851
Nawezaje kumwangalia mgonjwa mbele yangu
03:58
have something whichambayo is specificz zara for her,
75
226535
3047
na kuwa na kitu maalum kwake
04:01
and be ableinaweza to detectkuchunguza when things startkuanza to changemabadiliko,
76
229582
2788
na kugundua mambo yanapoanza kubadilika,
04:04
when things startkuanza to deterioratekuzorota?
77
232370
2099
mambo yanapoharibika?
04:06
Because like a racingracing cargari, any patientsubira,
78
234469
3050
Kwa sababu kama vile gari la mashindano,mgonjwa yeyote,
04:09
when things startkuanza to go badmbaya, you have a shortmfupi time
79
237519
2976
mambo yanapoharibika,unakuwa na muda mfupi
04:12
to make a differencetofauti.
80
240495
1831
kuleta mabadiliko.
04:14
So what we did is we tookalichukua a datadata systemmfumo
81
242326
2754
tulichofanya ni kuchukua mfumo wa taarifa
04:17
whichambayo we runkukimbia everykila two weekswiki of the yearmwaka in FormulaFomula 1
82
245080
3131
ambao unafanya kazi kila baada ya wiki mbili za mwaka
04:20
and we installedimewekwa it on the hospitalhospitali computerskompyuta
83
248211
3002
na kuufunga katika kompyuta za hospitali
04:23
at BirminghamBirmingham Children'sWa watoto HospitalHospitali.
84
251213
2290
katika hospitali ya watoto ya Birmingham.
04:25
We streamedmoja kwa moja datadata from the bedsidekitanda instrumentsvyombo
85
253503
2439
Tulisafirisha taarifa kutoka katika vifaa vya vitandani
04:27
in theirwao pediatricupasuaji intensivekubwa carehuduma
86
255942
2557
katika wodi ya watoto mahututi
04:30
so that we could bothwote wawili look at the datadata in realhalisi time
87
258499
3456
ili tuweze kuona taarifa kwa wakati huo huo
04:33
and, more importantlymuhimu, to storekuhifadhi the datadata
88
261955
2871
na muhimu zaidi,kutunza taarifa
04:36
so that we could startkuanza to learnkujifunza from it.
89
264826
3057
ili tuweze kujifunza
04:39
And then, we appliedkutumika an applicationprogramu on topjuu
90
267883
4384
na baadae tukatumia mfumo
04:44
whichambayo would allowkuruhusu us to teasetease out the patternschati in the datadata
91
272267
3270
ambao uliruhusu kufanya majaribio na taarifa
04:47
in realhalisi time so we could see what was happeningkinachotokea,
92
275537
2956
kw awakati huo huo ili kuona kilichokuwa kinatokea,
04:50
so we could determinekuamua when things startedilianza to changemabadiliko.
93
278493
3713
ili tuweze kujua wakati mambo yanapobadilika.
04:54
Now, in motormagari racingracing, we're all a little bitkidogo ambitiouskabambe,
94
282206
3863
katika mbio za magari, tuna kuwa tumejaa matumaini
04:58
audaciousjasiri, a little bitkidogo arrogantkiburi sometimesmara nyingine,
95
286069
2549
na wakati mwingine kujivuna kiasi,
05:00
so we decidedaliamua we would alsopia look at the childrenwatoto
96
288618
3398
kwa hiyo tukaamua kuangalia watoto
05:04
as they were beingkuwa transportedkusafirishwa to intensivekubwa carehuduma.
97
292016
2957
walipokuwa wanapelekwa katika wodi ya watu mahututi.
05:06
Why should we wait untilmpaka they arrivedaliwasili in the hospitalhospitali
98
294973
2154
Kwa nini tusubiri mpaka wanapowasili katika hospitali
05:09
before we startedilianza to look?
99
297127
1994
kabla ya kuanza kuangalia?
05:11
And so we installedimewekwa a real-timeMuda halisi linkkiungo
100
299121
2997
Kwa hiyo tukaweka kiunganishi cha wakati huo huo
05:14
betweenkati the ambulanceambulensi and the hospitalhospitali,
101
302118
2836
kati ya gari ya wagonjwa na hospitali,
05:16
just usingkutumia normalkawaida 3G telephonysimu to sendtuma that datadata
102
304954
3776
na kwa kutumia mfumo wa simu wa 3G kutuma taarifa
05:20
so that the ambulanceambulensi becameikawa an extraziada bedkitanda
103
308730
2487
Kwa hiyo gari ya wagonjwa likawa ni kitanda cha ziada
05:23
in intensivekubwa carehuduma.
104
311217
3136
katika wodi ya wagonjwa mahututi.
05:26
And then we startedilianza looking at the datadata.
105
314353
3702
Na baadae tukaanza kuangalia taarifa.
05:30
So the wigglywiggly linesmistari at the topjuu, all the colorsrangi,
106
318055
2921
Mistari yote hii juu,rangi zote,
05:32
this is the normalkawaida sortfanya of datadata you would see on a monitorkufuatilia --
107
320976
3194
Ni taarifa za kawaida kuziona katika kirusha picha
05:36
heartmoyo ratekiwango, pulsepigo, oxygenoksijeni withinndani the blooddamu,
108
324170
3772
mapigo ya moyo,oksijeni katika damu,
05:39
and respirationupumuaji.
109
327942
2635
na kupumua.
05:42
The linesmistari on the bottomchini, the bluebluu and the rednyekundu,
110
330577
2753
Mistari hapo chini, ya bluu na myekundu
05:45
these are the interestingkuvutia oneswale.
111
333330
1360
hii ni ya kustaajabisha.
05:46
The rednyekundu linemstari is showingkuonesha an automatedautomatiska versiontoleo
112
334690
3209
Mstari mwekundu unaonyesha mfumo wa moja kwa moja
05:49
of the earlymapema warningonyo scorealama
113
337899
1597
wa maonyo ya mapema
05:51
that BirminghamBirmingham Children'sWa watoto HospitalHospitali were alreadytayari runningKimbia.
114
339496
2487
ambayo yalikuwa yanaendeshwa na hospitali ya watoto ya birmingham
05:53
They'dWangeweza been runningKimbia that sincetangu 2008,
115
341983
2338
Walikuwa wanaiendesha toka 2008,
05:56
and alreadytayari have stoppedkusimamishwa cardiacmoyo arrestskukamatwa
116
344321
2256
na tayari imesimamamisha mistuko ya moyo
05:58
and distressdhiki withinndani the hospitalhospitali.
117
346577
2757
na msongo wa mawazo hospitalini
06:01
The bluebluu linemstari is an indicationdalili
118
349334
2432
Mstari wa bluu ni kiashiria
06:03
of when patternschati startkuanza to changemabadiliko,
119
351766
2500
cha mwenendo unapoanza kubadilika,
06:06
and immediatelymara moja, before we even startedilianza
120
354266
2309
na haraka,kabla hata ya kuanza
06:08
puttingkuweka in clinicalkliniki interpretationTafsiri,
121
356575
1708
na kuweka utafsiri wa kitabibu
06:10
we can see that the datadata is speakingakizungumza to us.
122
358283
2870
tunaweza kuona taarifa zikuzungumza nasi.
06:13
It's tellingkuwaambia us that something is going wrongsi sawa.
123
361153
3536
zinatuambia kuwa kitu si sawa.
06:16
The plotnjama with the rednyekundu and the greenkijani blobshuzuia,
124
364689
3816
mistari ya rangi nyekundu na kijani
06:20
this is plottingwanapanga differenttofauti componentsvipengele
125
368505
2805
hii inaonyesha kitu kingine
06:23
of the datadata againstdhidi eachkila mmoja other.
126
371310
2547
kuhusu taarifa.
06:25
The greenkijani is us learningkujifunza what is normalkawaida for that childmtoto.
127
373857
3840
Kijani inaonyesha kilicho sawa kwa mtoto
06:29
We call it the cloudwingu of normalityyanaonyesha kawaida.
128
377697
2610
tunaiita kuwa ni wingu la kawaida.
06:32
And when things startkuanza to changemabadiliko,
129
380307
2241
na mambo yanapobadilika,
06:34
when conditionshali startkuanza to deterioratekuzorota,
130
382548
2564
na hali kuwa mbaya
06:37
we movehoja into the rednyekundu linemstari.
131
385112
2238
tunaenda katika mstari mwekundu.
06:39
There's no rocketroketi sciencesayansi here.
132
387350
1657
Hakuna kitu cha ajabu hapa.
06:41
It is displayingkuonyesha datadata that existsipo alreadytayari in a differenttofauti way,
133
389007
4113
inaonyesha taarifa ambazo zipo katika njia nyingine,
06:45
to amplifyinahusu it, to providekutoa cuesishara to the doctorsmadaktari,
134
393120
3391
kuwaonyesha madaktari
06:48
to the nurseswauguzi, so they can see what's happeningkinachotokea.
135
396511
2738
na manesi, ili wajue kinachoendelea.
06:51
In the samesawa way that a good racingracing driverdereva
136
399249
3130
sawa sawa na jinsi dereva wa mbio za magari
06:54
relieshutegemea on cuesishara to decidekuamua when to applytumia the brakesbreki,
137
402379
4044
anavyotegemea kama kuna foleni ili ajue wakati wa kupiga breki,
06:58
when to turnkugeuka into a cornerkona,
138
406423
1476
wakati wa kukata kona,
06:59
we need to help our physiciansmadaktari and our nurseswauguzi
139
407899
2918
tunahitaji kuwasaidia madaktari na manesi wetu
07:02
to see when things are startingkuanzia to go wrongsi sawa.
140
410817
3620
kuona ni wakati gani mambo yanapoanza kuharibika,
07:06
So we have a very ambitiouskabambe programprogramu.
141
414437
2946
kwa hiyo tuna mpango wa kutia matumaini.
07:09
We think that the racembio is on to do something differentlytofauti.
142
417383
4736
Tunaamini mbio zinaenda kufanya kitu tofauti.
07:14
We are thinkingkufikiri bigkubwa. It's the right thing to do.
143
422119
2904
Tunawaza mbali, ni kitu sahihi kabisa kufanyika,
07:17
We have an approachmbinu whichambayo, if it's successfulimefanikiwa,
144
425023
3412
tuna njia ambayo kama itafanikiwa,
07:20
there's no reasonsababu why it should staykaa withinndani a hospitalhospitali.
145
428435
2531
hakuna sababu ibaki hospitalini tu.
07:22
It can go beyondzaidi the wallskuta.
146
430966
1841
inaweza kwenda zaidi ya hapo.
07:24
With wirelesswireless connectivitykuunganishwa these dayssiku,
147
432807
2071
na mawasiliano ya bila waya ya siku hizi,
07:26
there is no reasonsababu why patientswagonjwa, doctorsmadaktari and nurseswauguzi
148
434878
3444
hakuna sababu wagonjwa,daktari na nesi
07:30
always have to be in the samesawa placemahali
149
438322
2171
ya kuwafanya wawe sehemu moja
07:32
at the samesawa time.
150
440493
1993
kwa wakati mmoja
07:34
And meanwhilewakati huo huo, we'llvizuri take our little three-month-oldmwenye umri wa miezi mitatu babymtoto,
151
442486
3995
na wakati huo huo,tutachukua mtoto wetu wa miezi mitatu,
07:38
keep takingkuchukua it to the trackkufuatilia, keepingkuweka it safesalama,
152
446481
3757
tutaendelea kumpeleka uwanjani salama,
07:42
and makingkufanya it fasterharaka and better.
153
450238
2333
na kuifanya kuwa ya haraka na nzuri zaidi.
07:44
Thank you very much.
154
452571
1405
Asante Sana.
07:45
(ApplauseMakofi)
155
453976
4954
(Makofi)
Translated by Joachim Mangilima
Reviewed by Nelson Simfukwe

▲Back to top

ABOUT THE SPEAKER
Peter van Manen - Electronic systems expert
Peter van Manen is the Managing Director of McLaren Electronics, which provides data systems to major motorsports series.

Why you should listen

To say that Peter van Manen has a high-speed job would be an understatement. As Managing Director of McLaren Electronics, which provides electronics and data collection software to motorsports events, he and his team work in real time during a race to improve cars on about 500 different parameters. That's about 750 million data points in two hours.

But recently van Manen and his team have been wondering: Why can't the extremely precise and subtle data-collection and analysis systems used in motorsports be applied elsewhere, for the benefit of all? They have applied their systems to ICU units at Birmingham Children's Hospital with real-time analysis that allows them to proactively prevent cardiac arrests. The unit has seen a 25 percent decrease in life-threatening events. And it's just the beginning.

More profile about the speaker
Peter van Manen | Speaker | TED.com