The surprising seeds of a big-data revolution in healthcare
-
0:01 - 0:03There's an old joke about a cop
-
0:03 - 0:05who's walking his beat
in the middle of the night, -
0:05 - 0:07and he comes across a guy
under a street lamp -
0:07 - 0:10who's looking at the ground
and moving from side to side, -
0:10 - 0:12and the cop asks him what he's doing.
-
0:12 - 0:14The guys says he's looking for his keys.
-
0:14 - 0:15So the cop takes his time
-
0:15 - 0:17and looks over and kind of
makes a little matrix -
0:17 - 0:20and looks for about two, three minutes.
-
0:20 - 0:21No keys.
-
0:21 - 0:23The cop says, "Are you sure?
-
0:23 - 0:25Hey buddy, are you sure
you lost your keys here?" -
0:25 - 0:28And the guy says,
"No, actually I lost them -
0:28 - 0:29down at the other end of the street,
-
0:29 - 0:31but the light is better here."
-
0:31 - 0:33(Laughter)
-
0:34 - 0:37There's a concept that people talk
about nowadays called "big data." -
0:37 - 0:40And what they're talking
about is all of the information -
0:40 - 0:42that we're generating
through our interaction -
0:42 - 0:44with and over the Internet,
-
0:44 - 0:45everything from Facebook and Twitter
-
0:45 - 0:49to music downloads, movies,
streaming, all this kind of stuff, -
0:49 - 0:51the live streaming of TED.
-
0:51 - 0:54And the folks who work
with big data, for them, -
0:54 - 0:56they talk about that their biggest problem
-
0:56 - 0:57is we have so much information.
-
0:57 - 1:01The biggest problem is: how do we
organize all that information? -
1:01 - 1:03I can tell you that,
working in global health, -
1:03 - 1:06that is not our biggest problem.
-
1:06 - 1:09Because for us, even though
the light is better on the Internet, -
1:11 - 1:14the data that would help us solve
the problems we're trying to solve -
1:14 - 1:17is not actually present on the Internet.
-
1:17 - 1:18So we don't know, for example,
-
1:18 - 1:21how many people right now
are being affected by disasters -
1:21 - 1:23or by conflict situations.
-
1:23 - 1:27We don't know for, really,
basically, any of the clinics -
1:27 - 1:28in the developing world,
-
1:28 - 1:31which ones have medicines
and which ones don't. -
1:31 - 1:34We have no idea of what
the supply chain is for those clinics. -
1:34 - 1:38We don't know -- and this is really
amazing to me -- we don't know -
1:38 - 1:42how many children were born --
or how many children there are -- -
1:42 - 1:45in Bolivia or Botswana or Bhutan.
-
1:46 - 1:48We don't know how many kids died last week
-
1:48 - 1:49in any of those countries.
-
1:49 - 1:52We don't know the needs
of the elderly, the mentally ill. -
1:52 - 1:56For all of these different
critically important problems -
1:56 - 1:59or critically important areas
that we want to solve problems in, -
1:59 - 2:01we basically know nothing at all.
-
2:04 - 2:06And part of the reason
why we don't know anything at all -
2:07 - 2:11is that the information technology systems
that we use in global health -
2:11 - 2:15to find the data to solve
these problems is what you see here. -
2:15 - 2:17This is about a 5,000-year-old technology.
-
2:17 - 2:19Some of you may have used it before.
-
2:19 - 2:21It's kind of on its way out now,
-
2:21 - 2:23but we still use it
for 99 percent of our stuff. -
2:23 - 2:26This is a paper form.
-
2:26 - 2:28And what you're looking at is a paper form
-
2:28 - 2:31in the hand of a Ministry of Health
nurse in Indonesia, -
2:31 - 2:34who is tramping out across the countryside
-
2:34 - 2:37in Indonesia on, I'm sure,
a very hot and humid day, -
2:37 - 2:40and she is going to be knocking
on thousands of doors -
2:40 - 2:42over a period of weeks or months,
-
2:42 - 2:44knocking on the doors and saying,
-
2:44 - 2:47"Excuse me, we'd like to ask
you some questions. -
2:47 - 2:50Do you have any children?
Were your children vaccinated?" -
2:50 - 2:52Because the only way
we can actually find out -
2:52 - 2:55how many children were vaccinated
in the country of Indonesia, -
2:55 - 2:57what percentage were vaccinated,
-
2:57 - 3:01is actually not on the Internet,
but by going out and knocking on doors, -
3:01 - 3:03sometimes tens of thousands of doors.
-
3:03 - 3:07Sometimes it takes months to even years
to do something like this. -
3:07 - 3:09You know, a census of Indonesia
-
3:09 - 3:12would probably take
two years to accomplish. -
3:12 - 3:14And the problem, of course,
with all of this -
3:14 - 3:16is that, with all those paper forms --
-
3:16 - 3:19and I'm telling you, we have
paper forms for every possible thing: -
3:19 - 3:21We have paper forms
for vaccination surveys. -
3:21 - 3:24We have paper forms to track
people who come into clinics. -
3:24 - 3:28We have paper forms to track
drug supplies, blood supplies -- -
3:28 - 3:31all these different paper forms
for many different topics, -
3:31 - 3:34they all have a single, common endpoint,
-
3:34 - 3:36and the common endpoint
looks something like this. -
3:36 - 3:40And what we're looking
at here is a truckful of data. -
3:41 - 3:45This is the data from a single
vaccination coverage survey -
3:45 - 3:47in a single district
in the country of Zambia -
3:47 - 3:50from a few years ago,
that I participated in. -
3:50 - 3:52The only thing anyone
was trying to find out -
3:52 - 3:55is what percentage of Zambian
children are vaccinated, -
3:55 - 3:59and this is the data,
collected on paper over weeks, -
3:59 - 4:00from a single district,
-
4:00 - 4:02which is something like a county
in the United States. -
4:03 - 4:05You can imagine that,
for the entire country of Zambia, -
4:05 - 4:08answering just that single question ...
-
4:09 - 4:10looks something like this.
-
4:11 - 4:13Truck after truck after truck,
-
4:13 - 4:16filled with stack after stack
after stack of data. -
4:16 - 4:20And what makes it even worse
is that's just the beginning. -
4:20 - 4:22Because once you've collected
all that data, -
4:22 - 4:24of course, someone --
some unfortunate person -- -
4:24 - 4:27is going to have to type that
into a computer. -
4:27 - 4:28When I was a graduate student,
-
4:28 - 4:31I actually was that unfortunate
person sometimes. -
4:31 - 4:34I can tell you, I often wasn't
really paying attention. -
4:34 - 4:36I probably made a lot
of mistakes when I did it -
4:36 - 4:38that no one ever discovered,
so data quality goes down. -
4:39 - 4:42But eventually that data, hopefully,
gets typed into a computer, -
4:42 - 4:43and someone can begin to analyze it,
-
4:43 - 4:46and once they have
an analysis and a report, -
4:46 - 4:49hopefully, then you can take
the results of that data collection -
4:49 - 4:51and use it to vaccinate children better.
-
4:51 - 4:57Because if there's anything worse
in the field of global public health -- -
4:57 - 5:00I don't know what's worse
than allowing children on this planet -
5:00 - 5:02to die of vaccine-preventable diseases --
-
5:03 - 5:05diseases for which
the vaccine costs a dollar. -
5:06 - 5:09And millions of children die
of these diseases every year. -
5:09 - 5:12And the fact is, millions
is a gross estimate, -
5:12 - 5:15because we don't really know
how many kids die each year of this. -
5:16 - 5:19What makes it even more frustrating
is that the data-entry part, -
5:19 - 5:21the part that I used to do
as a grad student, -
5:21 - 5:23can take sometimes six months.
-
5:23 - 5:26Sometimes it can take two years
to type that information into a computer, -
5:26 - 5:29And sometimes, actually not infrequently,
-
5:29 - 5:30it actually never happens.
-
5:30 - 5:33Now try and wrap your head
around that for a second. -
5:33 - 5:35You just had teams of hundreds of people.
-
5:35 - 5:38They went out into the field
to answer a particular question. -
5:38 - 5:40You probably spent hundreds
of thousands of dollars -
5:40 - 5:43on fuel and photocopying and per diem.
-
5:44 - 5:46And then for some reason, momentum is lost
-
5:46 - 5:48or there's no money left,
-
5:48 - 5:50and all of that comes to nothing,
-
5:50 - 5:53because no one actually types it
into the computer at all. -
5:53 - 5:54The process just stops.
-
5:54 - 5:56Happens all the time.
-
5:56 - 5:59This is what we base
our decisions on in global health: -
5:59 - 6:02little data, old data, no data.
-
6:04 - 6:05So back in 1995,
-
6:05 - 6:09I began to think about ways
in which we could improve this process. -
6:09 - 6:11Now 1995 -- obviously,
that was quite a long time ago. -
6:11 - 6:14It kind of frightens me to think
of how long ago that was. -
6:14 - 6:17The top movie of the year
was "Die Hard with a Vengeance." -
6:17 - 6:20As you can see, Bruce Willis
had a lot more hair back then. -
6:20 - 6:23I was working in the Centers
for Disease Control -
6:23 - 6:25and I had a lot more
hair back then as well. -
6:26 - 6:28But to me, the most significant
thing that I saw in 1995 -
6:28 - 6:30was this.
-
6:30 - 6:33Hard for us to imagine, but in 1995,
-
6:33 - 6:36this was the ultimate elite mobile device.
-
6:36 - 6:39It wasn't an iPhone.
It wasn't a Galaxy phone. -
6:39 - 6:40It was a PalmPilot.
-
6:40 - 6:44And when I saw the PalmPilot
for the first time, I thought, -
6:44 - 6:46"Why can't we put the forms
on these PalmPilots? -
6:47 - 6:49And go out into the field
just carrying one PalmPilot, -
6:49 - 6:53which can hold the capacity
of tens of thousands of paper forms? -
6:53 - 6:55Why don't we try to do that?
-
6:55 - 6:56Because if we can do that,
-
6:56 - 7:00if we can actually just collect
the data electronically, digitally, -
7:00 - 7:01from the very beginning,
-
7:01 - 7:05we can just put a shortcut right
through that whole process -
7:05 - 7:10of typing, of having somebody type
that stuff into the computer. -
7:10 - 7:12We can skip straight to the analysis
-
7:12 - 7:15and then straight to the use
of the data to actually save lives." -
7:15 - 7:17So that's what I began to do.
-
7:17 - 7:22Working at CDC, I began to travel
to different programs around the world -
7:22 - 7:26and to train them in using
PalmPilots to do data collection, -
7:26 - 7:27instead of using paper.
-
7:27 - 7:29And it actually worked great.
-
7:29 - 7:32It worked exactly as well
as anybody would have predicted. -
7:32 - 7:33What do you know?
-
7:34 - 7:37Digital data collection is actually
more efficient than collecting on paper. -
7:37 - 7:39While I was doing it, my business partner,
-
7:39 - 7:42Rose, who's here with her husband,
Matthew, here in the audience, -
7:42 - 7:45Rose was out doing similar stuff
for the American Red Cross. -
7:45 - 7:48The problem was,
after a few years of doing that, -
7:48 - 7:52I realized -- I had been to maybe
six or seven programs -- -
7:52 - 7:55and I thought, you know,
if I keep this up at this pace, -
7:55 - 7:56over my whole career,
-
7:56 - 7:59maybe I'm going to go
to maybe 20 or 30 programs. -
7:59 - 8:02But the problem is, 20 or 30 programs,
-
8:02 - 8:05like, training 20 or 30 programs
to use this technology, -
8:05 - 8:07that is a tiny drop in the bucket.
-
8:07 - 8:11The demand for this, the need
for data to run better programs -
8:11 - 8:14just within health -- not to mention
all of the other fields -
8:14 - 8:16in developing countries -- is enormous.
-
8:16 - 8:20There are millions and millions
and millions of programs, -
8:20 - 8:22millions of clinics
that need to track drugs, -
8:22 - 8:24millions of vaccine programs.
-
8:24 - 8:26There are schools
that need to track attendance. -
8:26 - 8:30There are all these different things
for us to get the data that we need to do. -
8:30 - 8:35And I realized if I kept up
the way that I was doing, -
8:35 - 8:38I was basically hardly
going to make any impact -
8:38 - 8:39by the end of my career.
-
8:40 - 8:42And so I began to rack my brain,
-
8:42 - 8:45trying to think about, what
was the process that I was doing? -
8:45 - 8:46How was I training folks,
-
8:46 - 8:49and what were the bottlenecks
and what were the obstacles -
8:49 - 8:52to doing it faster
and to doing it more efficiently? -
8:52 - 8:55And, unfortunately, after thinking
about this for some time, -
8:55 - 8:58I identified the main obstacle.
-
8:58 - 9:00And the main obstacle, it turned out --
-
9:00 - 9:02and this is a sad realization --
-
9:02 - 9:04the main obstacle was me.
-
9:04 - 9:06So what do I mean by that?
-
9:07 - 9:08I had developed a process
-
9:08 - 9:13whereby I was the center
of the universe of this technology. -
9:14 - 9:18If you wanted to use this technology,
you had to get in touch with me. -
9:18 - 9:19That means you had to know I existed.
-
9:19 - 9:23Then you had to find the money
to pay for me to fly out to your country -
9:23 - 9:27and the money to pay for my hotel
and my per diem and my daily rate. -
9:27 - 9:30So you could be talking
about 10- or 20- or 30,000 dollars, -
9:30 - 9:32if I actually had the time
or it fit my schedule -
9:32 - 9:33and I wasn't on vacation.
-
9:34 - 9:36The point is that anything,
-
9:36 - 9:38any system that depends
on a single human being -
9:38 - 9:40or two or three or five human beings --
-
9:40 - 9:42it just doesn't scale.
-
9:42 - 9:45And this is a problem for which
we need to scale this technology, -
9:45 - 9:46and we need to scale it now.
-
9:46 - 9:49And so I began to think of ways
in which I could basically -
9:49 - 9:52take myself out of the picture.
-
9:54 - 9:56And, you know, I was thinking,
-
9:56 - 9:58"How could I take myself
out of the picture?" -
9:58 - 9:59for quite some time.
-
10:00 - 10:03I'd been trained that the way
you distribute technology -
10:03 - 10:05within international development
-
10:05 - 10:06is always consultant-based.
-
10:06 - 10:09It's always guys
that look pretty much like me, -
10:09 - 10:12flying from countries
that look pretty much like this -
10:12 - 10:14to other countries
with people with darker skin. -
10:15 - 10:17And you go out there,
and you spend money on airfare -
10:17 - 10:20and you spend time and you spend per diem
-
10:21 - 10:23and you spend for a hotel
and all that stuff. -
10:23 - 10:26As far as I knew, that was the only way
you could distribute technology, -
10:26 - 10:28and I couldn't figure out a way around it.
-
10:28 - 10:30But the miracle that happened --
-
10:31 - 10:33I'm going to call it Hotmail for short.
-
10:33 - 10:36You may not think of Hotmail
as being miraculous, -
10:36 - 10:37but for me it was miraculous,
-
10:37 - 10:41because I noticed, just as I
was wrestling with this problem -- -
10:41 - 10:44I was working in sub-Saharan
Africa, mostly, at the time -- -
10:44 - 10:47I noticed that every sub-Saharan
African health worker -
10:47 - 10:50that I was working with
had a Hotmail account. -
10:51 - 10:54And it struck me, "Wait a minute --
-
10:54 - 10:59I know the Hotmail people surely didn't
fly to the Ministry of Health in Kenya -
10:59 - 11:01to train people in how to use Hotmail.
-
11:01 - 11:06So these guys are distributing technology,
getting software capacity out there, -
11:06 - 11:08but they're not actually
flying around the world. -
11:08 - 11:10I need to think about this more."
-
11:10 - 11:11While I was thinking about it,
-
11:11 - 11:14people started using even more
things like this, just as we were. -
11:14 - 11:17They started using LinkedIn and Flickr
and Gmail and Google Maps -- -
11:18 - 11:19all these things.
-
11:19 - 11:21Of course, all of these things
are cloud based -
11:21 - 11:24and don't require any training.
-
11:24 - 11:25They don't require any programmers.
-
11:25 - 11:27They don't require consultants.
-
11:27 - 11:29Because the business model
for all these businesses -
11:29 - 11:32requires that something be so simple
we can use it ourselves, -
11:32 - 11:34with little or no training.
-
11:34 - 11:36You just have to hear about it
and go to the website. -
11:36 - 11:40And so I thought, what would happen
if we built software -
11:40 - 11:43to do what I'd been consulting in?
-
11:43 - 11:47Instead of training people
how to put forms onto mobile devices, -
11:47 - 11:50let's create software that lets them
do it themselves with no training -
11:50 - 11:51and without me being involved.
-
11:51 - 11:53And that's exactly what we did.
-
11:53 - 11:58So we created software called Magpi,
which has an online form creator. -
11:58 - 11:59No one has to speak to me,
-
11:59 - 12:02you just have to hear about it
and go to the website. -
12:02 - 12:05You can create forms,
and once you've created the forms, -
12:05 - 12:07you push them to a variety
of common mobile phones. -
12:07 - 12:11Obviously, nowadays, we've moved
past PalmPilots to mobile phones. -
12:11 - 12:14And it doesn't have to be a smartphone,
it can be a basic phone, -
12:14 - 12:17like the phone on the right,
the basic Symbian phone -
12:17 - 12:19that's very common
in developing countries. -
12:19 - 12:23And the great part about this
is it's just like Hotmail. -
12:23 - 12:24It's cloud based,
-
12:24 - 12:27and it doesn't require any training,
programming, consultants. -
12:27 - 12:29But there are some
additional benefits as well. -
12:29 - 12:31Now we knew when we built this system,
-
12:31 - 12:34the whole point of it,
just like with the PalmPilots, -
12:34 - 12:36was that you'd be able to collect the data
-
12:37 - 12:39and immediately upload
the data and get your data set. -
12:39 - 12:42But what we found, of course,
since it's already on a computer, -
12:42 - 12:45we can deliver instant maps
and analysis and graphing. -
12:45 - 12:47We can take a process that took two years
-
12:47 - 12:50and compress that
down to the space of five minutes. -
12:50 - 12:52Unbelievable improvements in efficiency.
-
12:53 - 12:56Cloud based, no training,
no consultants, no me. -
12:58 - 13:00And I told you that in the first few years
-
13:00 - 13:02of trying to do this
the old-fashioned way, -
13:02 - 13:03going out to each country,
-
13:03 - 13:07we probably trained about 1,000 people.
-
13:08 - 13:10What happened after we did this?
-
13:10 - 13:11In the second three years,
-
13:11 - 13:13we had 14,000 people find the website,
-
13:13 - 13:15sign up and start using it
to collect data: -
13:15 - 13:17data for disaster response,
-
13:17 - 13:22Canadian pig farmers
tracking pig disease and pig herds, -
13:22 - 13:24people tracking drug supplies.
-
13:24 - 13:28One of my favorite examples, the IRC,
International Rescue Committee, -
13:28 - 13:31they have a program
where semi-literate midwives, -
13:31 - 13:33using $10 mobile phones,
-
13:33 - 13:37send a text message
using our software, once a week, -
13:37 - 13:39with the number of births
and the number of deaths, -
13:39 - 13:43which gives IRC something that no one
in global health has ever had: -
13:43 - 13:46a near-real-time system
of counting babies, -
13:46 - 13:48of knowing how many kids are born,
-
13:48 - 13:51of knowing how many children
there are in Sierra Leone, -
13:51 - 13:53which is the country
where this is happening, -
13:53 - 13:55and knowing how many children die.
-
13:55 - 13:57Physicians for Human Rights --
-
13:57 - 14:00this is moving a little bit
outside the health field -- -
14:00 - 14:04they're basically training people
to do rape exams in Congo, -
14:04 - 14:06where this is an epidemic,
-
14:06 - 14:08a horrible epidemic,
-
14:08 - 14:11and they're using our software
to document the evidence they find, -
14:11 - 14:13including photographically,
-
14:13 - 14:16so that they can bring
the perpetrators to justice. -
14:17 - 14:21Camfed, another charity
based out of the UK -- -
14:21 - 14:23Camfed pays girls' families
to keep them in school. -
14:24 - 14:28They understand this is the most
significant intervention they can make. -
14:28 - 14:32They used to track the disbursements,
the attendance, the grades, on paper. -
14:32 - 14:35The turnaround time between a teacher
writing down grades or attendance -
14:35 - 14:38and getting that into a report
was about two to three years. -
14:38 - 14:39Now it's real time.
-
14:39 - 14:42And because this is such a low-cost
system and based in the cloud, -
14:42 - 14:46it costs, for the entire five countries
that Camfed runs this in, -
14:46 - 14:48with tens of thousands of girls,
-
14:48 - 14:51the whole cost combined
is 10,000 dollars a year. -
14:51 - 14:53That's less than I used to get
-
14:53 - 14:56just traveling out for two weeks
to do a consultation. -
14:58 - 15:02So I told you before that when
we were doing it the old-fashioned way, -
15:02 - 15:05I realized all of our work was really
adding up to just a drop in the bucket -- -
15:05 - 15:0710, 20, 30 different programs.
-
15:08 - 15:09We've made a lot of progress,
-
15:09 - 15:11but I recognize that right now,
-
15:11 - 15:14even the work that we've done
with 14,000 people using this -
15:14 - 15:16is still a drop in the bucket.
-
15:16 - 15:19But something's changed,
and I think it should be obvious. -
15:19 - 15:21What's changed now is,
-
15:21 - 15:24instead of having a program
in which we're scaling at such a slow rate -
15:24 - 15:27that we can never reach
all the people who need us, -
15:28 - 15:31we've made it unnecessary
for people to get reached by us. -
15:31 - 15:36We've created a tool
that lets programs keep kids in school, -
15:36 - 15:40track the number of babies that are born
and the number of babies that die, -
15:40 - 15:44catch criminals and successfully
prosecute them -- -
15:44 - 15:48to do all these different things
to learn more about what's going on, -
15:48 - 15:50to understand more,
-
15:50 - 15:51to see more ...
-
15:52 - 15:54and to save lives and improve lives.
-
15:56 - 15:57Thank you.
-
15:57 - 16:01(Applause)
- Title:
- The surprising seeds of a big-data revolution in healthcare
- Speaker:
- Joel Selanikio
- Description:
-
Collecting global health data was an imperfect science: Workers tramped through villages to knock on doors and ask questions, wrote the answers on paper forms, then input the data -- and from this gappy information, countries would make huge decisions. Data geek Joel Selanikio talks through the sea change in collecting health data in the past decade -- starting with the PalmPilot and Hotmail, and now moving into the cloud. (Filmed at TEDxAustin.)
- Video Language:
- English
- Team:
- closed TED
- Project:
- TEDTalks
- Duration:
- 16:18
Brian Greene edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Krystian Aparta commented on English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Krystian Aparta edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Krystian Aparta edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Krystian Aparta edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Krystian Aparta edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Thu-Huong Ha edited English subtitles for The surprising seeds of a big-data revolution in healthcare | ||
Thu-Huong Ha approved English subtitles for The surprising seeds of a big-data revolution in healthcare |
Krystian Aparta
The English transcript was updated on 1/11/2016.