TEDMED 2015
Russ Altman: What really happens when you mix medications?
Russ Altman: Que ocorre cando mesturamos medicamentos?
Filmed:
Readability: 4.2
1,766,922 views
Se tomamos dous medicamentos distintos por motivos diferentes, hai algo no que deberíamos pensar seriamente: o noso médico pode non entender ben o que acontece coa combinación, dado que as interaccións entre medicamentos son dificilísimas de estudar. Nesta charla, fascinante e divulgativa, Russ Altman móstranos como estudan os médicos as interaccións inesperadas servíndose dun recurso sorprendente: as buscas por internet.
Russ Altman - Big data techno-optimist and internist
Russ Altman uses machine learning to better understand adverse effects of medication. Full bio
Russ Altman uses machine learning to better understand adverse effects of medication. Full bio
Double-click the English transcript below to play the video.
Vas ao médico
e fas análises.
e fas análises.
00:12
So you go to the doctor
and get some tests.
and get some tests.
0
811
3321
00:16
The doctor determines
that you have high cholesterol
that you have high cholesterol
1
4674
2620
O médico diche
que tes o colesterol alto
que tes o colesterol alto
00:19
and you would benefit
from medication to treat it.
from medication to treat it.
2
7318
3171
e que é mellor que te poñas en tratamento.
00:22
So you get a pillbox.
3
10981
1556
Recéitache unhas pílulas.
00:25
You have some confidence,
4
13505
1199
Tes confianza,
00:26
your physician has some confidence
that this is going to work.
that this is going to work.
5
14728
2937
o teu médico confía
en que funcionará.
en que funcionará.
00:29
The company that invented it did
a lot of studies, submitted it to the FDA.
a lot of studies, submitted it to the FDA.
6
17689
3553
A compañía que as creou fixo
moitas análises, enviounas á FDA.
moitas análises, enviounas á FDA.
00:33
They studied it very carefully,
skeptically, they approved it.
skeptically, they approved it.
7
21266
3107
Estudounas con coidado,
con escepticismo, aprobounas.
con escepticismo, aprobounas.
00:36
They have a rough idea of how it works,
8
24397
1889
Teñen unha vaga idea
de como funcionan,
de como funcionan,
00:38
they have a rough idea
of what the side effects are.
of what the side effects are.
9
26310
2453
teñen unha vaga idea
dos efectos secundarios.
dos efectos secundarios.
00:40
It should be OK.
10
28787
1150
Debería ir todo ben.
00:42
You have a little more
of a conversation with your physician
of a conversation with your physician
11
30864
2818
Falas un pouco máis
co teu médico,
co teu médico,
00:45
and the physician is a little worried
because you've been blue,
because you've been blue,
12
33706
2963
o médico está preocupado
porque estiveches deprimido,
porque estiveches deprimido,
00:48
haven't felt like yourself,
13
36693
1293
notábaste distinto,
00:50
you haven't been able to enjoy things
in life quite as much as you usually do.
in life quite as much as you usually do.
14
38010
3731
non gozabas das cousas
da vida tanto coma antes.
da vida tanto coma antes.
00:53
Your physician says, "You know,
I think you have some depression.
I think you have some depression.
15
41765
3186
O médico diche:
"Creo que tes depresión.
"Creo que tes depresión.
00:57
I'm going to have to give
you another pill."
you another pill."
16
45792
2315
Vouche ter que dar outra pílula".
01:00
So now we're talking
about two medications.
about two medications.
17
48934
2483
Así que agora falamos
de dous medicamentos.
de dous medicamentos.
01:03
This pill also -- millions
of people have taken it,
of people have taken it,
18
51441
3104
Esta pílula tamén...
moita xente a tomou,
moita xente a tomou,
01:06
the company did studies,
the FDA looked at it -- all good.
the FDA looked at it -- all good.
19
54569
3631
a compañía fixo análises,
a FDA revisouna... todo ben.
a FDA revisouna... todo ben.
01:10
Think things should go OK.
20
58823
2057
Pensas que todo debería ir ben.
Pensas que todo debería ir ben.
Pensas que todo debería ir ben.
01:12
Think things should go OK.
21
60904
2197
01:15
Well, wait a minute.
22
63125
1439
Espera un momento.
Cantos estudos se fixeron
das dúas xuntas?
das dúas xuntas?
01:16
How much have we studied
these two together?
these two together?
23
64588
3517
01:20
Well, it's very hard to do that.
24
68630
2300
Iso é complicado de facer.
01:22
In fact, it's not traditionally done.
25
70954
2130
De feito, o normal é que non se faga.
01:25
We totally depend on what we call
"post-marketing surveillance,"
"post-marketing surveillance,"
26
73108
5518
Dependemos totalmente do que chamamos
"vixilancia poscomercialización",
"vixilancia poscomercialización",
01:30
after the drugs hit the market.
27
78650
1880
cando as pílulas xa están no mercado.
01:32
How can we figure out
if bad things are happening
if bad things are happening
28
80996
2848
Como podemos saber se algo está indo mal
entre dous medicamentos?
entre dous medicamentos?
01:35
between two medications?
29
83868
1357
01:37
Three? Five? Seven?
30
85249
2030
Ou tres? Ou cinco? Ou sete?
01:39
Ask your favorite person
who has several diagnoses
who has several diagnoses
31
87708
2415
Pregúntalle canta medicación toma
a alguén con varios diagnósticos.
a alguén con varios diagnósticos.
01:42
how many medications they're on.
32
90147
1834
01:44
Why do I care about this problem?
33
92530
1580
Por que me preocupo por isto?
Preocúpame moito.
Preocúpame moito.
01:46
I care about it deeply.
34
94134
1157
Son un home da ciencia dos datos
e da informática e, na miña opinión,
e da informática e, na miña opinión,
01:47
I'm an informatics and data science guy
and really, in my opinion,
and really, in my opinion,
35
95315
4304
01:51
the only hope -- only hope --
to understand these interactions
to understand these interactions
36
99643
3745
a única esperanza... a única...
para entender estas interaccións
para entender estas interaccións
01:55
is to leverage lots
of different sources of data
of different sources of data
37
103412
3056
é aproveitar as máximas
fontes de información posibles
fontes de información posibles
01:58
in order to figure out
when drugs can be used together safely
when drugs can be used together safely
38
106492
3556
para determinar cando é seguro
usar xuntos os medicamentos
usar xuntos os medicamentos
02:02
and when it's not so safe.
39
110072
1777
e cando non é tan seguro.
02:04
So let me tell you a data science story.
40
112615
2051
Cóntovos unha historia
da ciencia dos datos.
da ciencia dos datos.
02:06
And it begins with my student Nick.
41
114690
2154
Empeza co meu alumno Nick.
02:08
Let's call him "Nick,"
because that's his name.
because that's his name.
42
116868
2380
Ímoslle chamar "Nick",
porque se chama así.
porque se chama así.
02:11
(Laughter)
43
119272
1592
(Risas)
02:12
Nick was a young student.
44
120888
1201
Nick era un alumno novo.
02:14
I said, "You know, Nick, we have
to understand how drugs work
to understand how drugs work
45
122113
3079
Eu díxenlle: "Temos que entender
como funcionan os medicamentos
como funcionan os medicamentos
02:17
and how they work together
and how they work separately,
and how they work separately,
46
125216
2626
e como funcionan xuntos e por separado,
02:19
and we don't have a great understanding.
47
127866
1922
e non sabemos moito diso”.
Pero a FDA dispoñibilizou
unha incrible base de datos.
unha incrible base de datos.
02:21
But the FDA has made available
an amazing database.
an amazing database.
48
129812
2405
É unha base de datos de efectos adversos.
02:24
It's a database of adverse events.
49
132241
1699
02:26
They literally put on the web --
50
134321
1642
Subiron a Internet...
02:27
publicly available, you could all
download it right now --
download it right now --
51
135987
3119
dispoñible para o público,
calquera pode descargalos...
calquera pode descargalos...
02:31
hundreds of thousands
of adverse event reports
of adverse event reports
52
139130
3627
centos de miles de informes
sobre efectos adversos
sobre efectos adversos
02:34
from patients, doctors,
companies, pharmacists.
companies, pharmacists.
53
142781
3760
de pacientes, médicos,
empresas, farmacéuticos.
empresas, farmacéuticos.
02:38
And these reports are pretty simple:
54
146565
1749
Son informes bastante sinxelos:
02:40
it has all the diseases
that the patient has,
that the patient has,
55
148338
2658
están todas as enfermidades
dos pacientes,
dos pacientes,
02:43
all the drugs that they're on,
56
151020
1767
os medicamentos que toman,
02:44
and all the adverse events,
or side effects, that they experience.
or side effects, that they experience.
57
152811
3818
e os efectos adversos ou
secundarios que sofren.
secundarios que sofren.
02:48
It is not all of the adverse events
that are occurring in America today,
that are occurring in America today,
58
156653
3436
Non están todos os efectos adversos
actuais dos Estados Unidos,
actuais dos Estados Unidos,
02:52
but it's hundreds and hundreds
of thousands of drugs.
of thousands of drugs.
59
160113
2578
pero hai centos e centos
de miles de medicamentos.
de miles de medicamentos.
02:54
So I said to Nick,
60
162715
1299
Entón díxenlle a Nick:
02:56
"Let's think about glucose.
61
164038
1826
"Imos pensar na glicosa.
02:57
Glucose is very important,
and we know it's involved with diabetes.
and we know it's involved with diabetes.
62
165888
3567
A glicosa é moi importante
e sabemos que ten que ver coa diabetes.
e sabemos que ten que ver coa diabetes.
03:01
Let's see if we can understand
glucose response.
glucose response.
63
169479
3970
A ver se entendemos a resposta á glicosa.
03:05
I sent Nick off. Nick came back.
64
173473
2458
Nick marchou para outro lado. Nick volveu.
03:08
"Russ," he said,
65
176248
1786
"Russ" -dixo el-
03:10
"I've created a classifier that can
look at the side effects of a drug
look at the side effects of a drug
66
178351
5112
"Creei un clasificador que pode ver
os efectos secundarios dun medicamento
os efectos secundarios dun medicamento
03:15
based on looking at this database,
67
183487
2051
buscando nesta base de datos,
03:17
and can tell you whether that drug
is likely to change glucose or not."
is likely to change glucose or not."
68
185562
4271
e pode dicir se é probable
que o medicamento altere a glicosa".
que o medicamento altere a glicosa".
03:21
He did it. It was very simple, in a way.
69
189857
2016
Fixérao. En certo modo era moi simple.
03:23
He took all the drugs
that were known to change glucose
that were known to change glucose
70
191897
2635
Colleu os medicamentos
que se sabe que alteran a glicosa
que se sabe que alteran a glicosa
03:26
and a bunch of drugs
that don't change glucose,
that don't change glucose,
71
194556
2389
e un feixe de medicamentos
que non a alteran,
que non a alteran,
03:28
and said, "What's the difference
in their side effects?
in their side effects?
72
196969
2888
e preguntou: "Que diferenza hai
entre os efectos secundarios?
entre os efectos secundarios?
03:31
Differences in fatigue? In appetite?
In urination habits?"
In urination habits?"
73
199881
4852
Hai diferenzas de fatiga? De apetito?
Dos hábitos urinarios?"
Dos hábitos urinarios?"
03:36
All those things conspired
to give him a really good predictor.
to give him a really good predictor.
74
204757
2960
Todo isto conspirou
para facer un bo método preditivo.
para facer un bo método preditivo.
03:39
He said, "Russ, I can predict
with 93 percent accuracy
with 93 percent accuracy
75
207741
2548
Dixo: "Russ, podo predicir
cun 93% de precisión
cun 93% de precisión
03:42
when a drug will change glucose."
76
210313
1572
cando vai cambiar a glicosa".
Eu dixen: "Xenial, Nick".
03:43
I said, "Nick, that's great."
77
211909
1416
É un alumno novo,
hai que reforzarlle a confianza.
hai que reforzarlle a confianza.
03:45
He's a young student,
you have to build his confidence.
you have to build his confidence.
78
213349
2896
03:48
"But Nick, there's a problem.
79
216269
1390
"Pero Nick, hai un problema.
03:49
It's that every physician in the world
knows all the drugs that change glucose,
knows all the drugs that change glucose,
80
217683
3960
Todos os médicos do mundo
saben qué medicamentos cambian a glicosa,
saben qué medicamentos cambian a glicosa,
03:53
because it's core to our practice.
81
221667
2038
porque é algo básico na nosa práctica.
03:55
So it's great, good job,
but not really that interesting,
but not really that interesting,
82
223729
3722
Así que estupendo, bo traballo,
pero non moi interesante realmente,
pero non moi interesante realmente,
03:59
definitely not publishable."
83
227475
1531
definitivamente non publicable".
04:01
(Laughter)
84
229030
1014
(Risas)
04:02
He said, "I know, Russ.
I thought you might say that."
I thought you might say that."
85
230068
2550
El dixo: "Xa sei.
Pensei que dirías iso".
Pensei que dirías iso".
Nick é listo.
04:04
Nick is smart.
86
232642
1152
04:06
"I thought you might say that,
so I did one other experiment.
so I did one other experiment.
87
234149
2874
"Pensei que o dirías,
por iso fixen outro experimento.
por iso fixen outro experimento.
04:09
I looked at people in this database
who were on two drugs,
who were on two drugs,
88
237047
2928
Busquei na base de datos
persoas que tomasen dous fármacos,
persoas que tomasen dous fármacos,
04:11
and I looked for signals similar,
glucose-changing signals,
glucose-changing signals,
89
239999
4422
e busquei sinais semellantes,
sinais de alteración da glicosa,
sinais de alteración da glicosa,
04:16
for people taking two drugs,
90
244445
1624
en xente que toma dous fármacos,
04:18
where each drug alone
did not change glucose,
did not change glucose,
91
246093
5569
cada un dos cales por si só
non alterase a glicosa,
non alterase a glicosa,
04:23
but together I saw a strong signal."
92
251686
2460
pero xuntos presentasen un sinal forte".
04:26
And I said, "Oh! You're clever.
Good idea. Show me the list."
Good idea. Show me the list."
93
254170
3149
E eu dixen: "Que listo es!
Boa idea. Ensíname a lista".
Boa idea. Ensíname a lista".
04:29
And there's a bunch of drugs,
not very exciting.
not very exciting.
94
257343
2254
E había medicamentos
apenas interesantes,
apenas interesantes,
pero chamoume a atención
que na lista había dous:
que na lista había dous:
04:31
But what caught my eye
was, on the list there were two drugs:
was, on the list there were two drugs:
95
259621
3932
04:35
paroxetine, or Paxil, an antidepressant;
96
263577
3393
paroxetina, ou Paxil, un antidepresivo,
04:39
and pravastatin, or Pravachol,
a cholesterol medication.
a cholesterol medication.
97
267756
3570
e pravastatina, ou Pravachol,
un medicamento para o colesterol.
un medicamento para o colesterol.
04:43
And I said, "Huh. There are millions
of Americans on those two drugs."
of Americans on those two drugs."
98
271936
4283
E dixen: "Ah! Millóns de estadounidenses
toman estes dous medicamentos".
toman estes dous medicamentos".
04:48
In fact, we learned later,
99
276243
1246
De feito, despois soubemos
04:49
15 million Americans on paroxetine
at the time, 15 million on pravastatin,
at the time, 15 million on pravastatin,
100
277513
6032
que 15 millóns toman paroxetina,
15 millóns pravastatina,
15 millóns pravastatina,
04:55
and a million, we estimated, on both.
101
283569
2817
e calculamos que un millón, as dúas.
04:58
So that's a million people
102
286767
1254
Entón un millón de persoas
05:00
who might be having some problems
with their glucose
with their glucose
103
288045
2453
poderían estar tendo
problemas de glicosa
problemas de glicosa
05:02
if this machine-learning mumbo jumbo
that he did in the FDA database
that he did in the FDA database
104
290522
3206
se este galimatías automático
que fixo na base de datos da FDA
que fixo na base de datos da FDA
05:05
actually holds up.
105
293752
1254
se sostén realmente.
05:07
But I said, "It's still not publishable,
106
295030
1927
Pero eu dixen: "Aínda non é publicable,
05:08
because I love what you did
with the mumbo jumbo,
with the mumbo jumbo,
107
296981
2296
encántame o que fixeches
coa lea esta, coa aprendizaxe automática
coa lea esta, coa aprendizaxe automática
05:11
with the machine learning,
108
299301
1246
pero o que temos
non é unha proba evidente".
non é unha proba evidente".
05:12
but it's not really standard-of-proof
evidence that we have."
evidence that we have."
109
300571
3864
Temos que facer algo máis.
05:17
So we have to do something else.
110
305618
1589
Imos ao rexistro médico
electrónico de Stanford.
electrónico de Stanford.
05:19
Let's go into the Stanford
electronic medical record.
electronic medical record.
111
307231
2876
05:22
We have a copy of it
that's OK for research,
that's OK for research,
112
310131
2064
Temos unha copia
que serve para investigar,
que serve para investigar,
05:24
we removed identifying information.
113
312219
2046
quitámoslle a información identificativa.
05:26
And I said, "Let's see if people
on these two drugs
on these two drugs
114
314581
2503
E dixen: "Imos ver se a xente
que toma eses fármacos
que toma eses fármacos
05:29
have problems with their glucose."
115
317108
1769
ten problemas de glicosa".
05:31
Now there are thousands
and thousands of people
and thousands of people
116
319242
2207
Hai miles de persoas
05:33
in the Stanford medical records
that take paroxetine and pravastatin.
that take paroxetine and pravastatin.
117
321473
3459
nos rexistros médicos de Stanford
que toman paroxetina e pravastatina,
que toman paroxetina e pravastatina,
05:36
But we needed special patients.
118
324956
1799
pero necesitabamos pacientes especiais.
05:38
We needed patients who were on one of them
and had a glucose measurement,
and had a glucose measurement,
119
326779
4597
Necesitabamos pacientes que tomasen
un deles e medisen a glicosa,
un deles e medisen a glicosa,
05:43
then got the second one and had
another glucose measurement,
another glucose measurement,
120
331400
3449
e despois tomasen o outro
e medisen outra vez a glicosa,
e medisen outra vez a glicosa,
05:46
all within a reasonable period of time --
something like two months.
something like two months.
121
334873
3615
todo dentro dun tempo razoable...
algo así como dous meses.
algo así como dous meses.
05:50
And when we did that,
we found 10 patients.
we found 10 patients.
122
338512
3159
E cando o fixemos
encontramos 10 pacientes.
encontramos 10 pacientes.
05:54
However, eight out of the 10
had a bump in their glucose
had a bump in their glucose
123
342592
4538
Con todo, oito de cada dez
tiveron aumento de glicosa
tiveron aumento de glicosa
05:59
when they got the second P --
we call this P and P --
we call this P and P --
124
347154
2645
cando tomaron o segundo P
—chamámoslles P e P—
—chamámoslles P e P—
06:01
when they got the second P.
125
349823
1310
cando tomaron o segundo P.
06:03
Either one could be first,
the second one comes up,
the second one comes up,
126
351157
2562
Fose cal fose o primeiro,
cando tomaban o segundo,
cando tomaban o segundo,
06:05
glucose went up
20 milligrams per deciliter.
20 milligrams per deciliter.
127
353743
2847
a glicosa subía
20 miligramos por decilitro.
20 miligramos por decilitro.
06:08
Just as a reminder,
128
356614
1158
Só para situarnos,
normalmente andamos,
se non somos diabéticos,
se non somos diabéticos,
06:09
you walk around normally,
if you're not diabetic,
if you're not diabetic,
129
357796
2325
coa glicosa arredor de 90.
06:12
with a glucose of around 90.
130
360145
1359
06:13
And if it gets up to 120, 125,
131
361528
2076
Se sobe ata 120, 125,
06:15
your doctor begins to think
about a potential diagnosis of diabetes.
about a potential diagnosis of diabetes.
132
363628
3450
o médico empeza a pensar
nun posible diagnóstico de diabetes.
nun posible diagnóstico de diabetes.
06:19
So a 20 bump -- pretty significant.
133
367102
2991
Así que un aumento de 20...
é bastante significativo.
é bastante significativo.
06:22
I said, "Nick, this is very cool.
134
370601
1904
Eu dixen: "Nick, está moi ben,
06:25
But, I'm sorry, we still
don't have a paper,
don't have a paper,
135
373616
2053
pero, síntoo, aínda non temos artigo,
06:27
because this is 10 patients
and -- give me a break --
and -- give me a break --
136
375693
2579
porque estes 10 pacientes
-necesito respirar-
-necesito respirar-
non abondan".
06:30
it's not enough patients."
137
378296
1245
06:31
So we said, what can we do?
138
379565
1306
Que podemos facer?
06:32
And we said, let's call our friends
at Harvard and Vanderbilt,
at Harvard and Vanderbilt,
139
380895
2976
Vamos chamar aos amigos
de Harvard e Vanderbilt,
de Harvard e Vanderbilt,
06:35
who also -- Harvard in Boston,
Vanderbilt in Nashville,
Vanderbilt in Nashville,
140
383895
2587
... Harvard en Boston,
Vanderbilt en Nashville,
Vanderbilt en Nashville,
06:38
who also have electronic
medical records similar to ours.
medical records similar to ours.
141
386506
2821
que tamén teñen
historias clínicas electrónicas parecidas.
historias clínicas electrónicas parecidas.
06:41
Let's see if they can find
similar patients
similar patients
142
389351
2020
A ver se encontran pacientes parecidos
06:43
with the one P, the other P,
the glucose measurements
the glucose measurements
143
391395
3276
cun P, o outro P,
as medicións de glicosa
as medicións de glicosa
06:46
in that range that we need.
144
394695
1600
no rango que necesitamos.
06:48
God bless them, Vanderbilt
in one week found 40 such patients,
in one week found 40 such patients,
145
396787
4955
Non podía crelo, Vanderbilt
nunha semana encontrou 40 pacientes deses,
nunha semana encontrou 40 pacientes deses,
06:53
same trend.
146
401766
1189
coa mesma tendencia.
06:55
Harvard found 100 patients, same trend.
147
403804
3620
e Harvard encontrou 100,
coa mesma tendencia.
coa mesma tendencia.
06:59
So at the end, we had 150 patients
from three diverse medical centers
from three diverse medical centers
148
407448
4281
Ao final, tiñamos 150 pacientes
de tres centros médicos diferentes
de tres centros médicos diferentes
07:03
that were telling us that patients
getting these two drugs
getting these two drugs
149
411753
3297
que nos dicían que os pacientes
que tomaban eses dous medicamentos
que tomaban eses dous medicamentos
07:07
were having their glucose bump
somewhat significantly.
somewhat significantly.
150
415074
2703
tiñan un aumento de glicosa considerable.
07:10
More interestingly,
we had left out diabetics,
we had left out diabetics,
151
418317
2810
Máis interesante aínda,
deixaramos fóra os diabéticos,
deixaramos fóra os diabéticos,
07:13
because diabetics already
have messed up glucose.
have messed up glucose.
152
421151
2317
porque a diabetes xa
afecta á glicosa.
afecta á glicosa.
07:15
When we looked
at the glucose of diabetics,
at the glucose of diabetics,
153
423492
2238
Cando nos fixamos
na glicosa dos diabéticos,
na glicosa dos diabéticos,
07:17
it was going up 60 milligrams
per deciliter, not just 20.
per deciliter, not just 20.
154
425754
3435
vimos que subía ata 60 miligramos
por decilitro, non só 20.
por decilitro, non só 20.
07:21
This was a big deal, and we said,
"We've got to publish this."
"We've got to publish this."
155
429760
3452
Isto era importante e dixemos:
"Temos que publicalo".
"Temos que publicalo".
07:25
We submitted the paper.
156
433236
1179
Enviamos o artigo.
07:26
It was all data evidence,
157
434439
2111
Todas as probas eran datos,
07:28
data from the FDA, data from Stanford,
158
436574
2483
datos da FDA, datos de Stanford,
07:31
data from Vanderbilt, data from Harvard.
159
439081
1946
datos de Vanderbilt, de Harvard.
07:33
We had not done a single real experiment.
160
441051
2396
Non fixeramos un só experimento real.
07:36
But we were nervous.
161
444495
1296
Pero estabamos nerviosos.
07:38
So Nick, while the paper
was in review, went to the lab.
was in review, went to the lab.
162
446201
3730
Así que Nick, mentres revisaban
o artigo, foi ao laboratorio.
o artigo, foi ao laboratorio.
07:41
We found somebody
who knew about lab stuff.
who knew about lab stuff.
163
449955
2462
Encontramos unha persoa
que entendía de laboratorio.
que entendía de laboratorio.
07:44
I don't do that.
164
452441
1393
Eu non sei diso.
07:45
I take care of patients,
but I don't do pipettes.
but I don't do pipettes.
165
453858
2417
Encárgome de pacientes,
non traballo con pipetas.
non traballo con pipetas.
07:49
They taught us how to feed mice drugs.
166
457420
3053
Ensináronnos a darlles
os medicamentos a ratos.
os medicamentos a ratos.
07:52
We took mice and we gave them
one P, paroxetine.
one P, paroxetine.
167
460864
2414
Collemos uns ratos
e démoslles un P, paroxetina.
e démoslles un P, paroxetina.
07:55
We gave some other mice pravastatin.
168
463302
2508
A outros ratos démoslles pravastatina,
07:57
And we gave a third group
of mice both of them.
of mice both of them.
169
465834
3595
e a un terceiro grupo démoslles os dous.
08:01
And lo and behold, glucose went up
20 to 60 milligrams per deciliter
20 to 60 milligrams per deciliter
170
469893
3946
Mira por onde, a glicosa aumentou
de 20 a 60 miligramos por decilitro
de 20 a 60 miligramos por decilitro
08:05
in the mice.
171
473863
1171
nos ratos.
08:07
So the paper was accepted
based on the informatics evidence alone,
based on the informatics evidence alone,
172
475058
3158
Aceptaron o artigo
só coas probas informáticas,
só coas probas informáticas,
pero engadimos unha notiña
ao final que poñía
ao final que poñía
08:10
but we added a little note at the end,
173
478240
1894
08:12
saying, oh by the way,
if you give these to mice, it goes up.
if you give these to mice, it goes up.
174
480158
2899
ah por certo,
se se proba con ratos, aumenta.
se se proba con ratos, aumenta.
08:15
That was great, and the story
could have ended there.
could have ended there.
175
483081
2508
Foi xenial e a historia
podería acabar aquí,
podería acabar aquí,
08:17
But I still have six and a half minutes.
176
485613
1997
pero aínda teño seis minutos e medio.
08:19
(Laughter)
177
487634
2807
(Risas)
08:22
So we were sitting around
thinking about all of this,
thinking about all of this,
178
490465
2815
Entón estabamos sen facer nada
pensando en todo isto,
pensando en todo isto,
08:25
and I don't remember who thought
of it, but somebody said,
of it, but somebody said,
179
493304
2735
e non recordo quen foi, pero alguén dixo:
"Pregúntome se os pacientes
que toman estes dous fármacos
que toman estes dous fármacos
08:28
"I wonder if patients
who are taking these two drugs
who are taking these two drugs
180
496063
3201
08:31
are noticing side effects
of hyperglycemia.
of hyperglycemia.
181
499288
3553
están notando efectos secundarios
de hiperglicemia.
de hiperglicemia.
08:34
They could and they should.
182
502865
1496
Poderían e deberían.
08:36
How would we ever determine that?"
183
504761
1877
Como poderiamos determinar isto?"
08:39
We said, well, what do you do?
184
507551
1443
Que é o que se fai?
08:41
You're taking a medication,
one new medication or two,
one new medication or two,
185
509018
2580
Estás tomando
un medicamento novo ou dous
un medicamento novo ou dous
08:43
and you get a funny feeling.
186
511622
1538
e tes unha sensación rara.
Que fas?
08:45
What do you do?
187
513184
1151
08:46
You go to Google
188
514359
1151
Vas a Google
08:47
and type in the two drugs you're taking
or the one drug you're taking,
or the one drug you're taking,
189
515534
3349
e introduces o nome
dos medicamentos que estás tomando.
dos medicamentos que estás tomando.
08:50
and you type in "side effects."
190
518907
1603
e escribes "efectos secundarios".
08:52
What are you experiencing?
191
520534
1356
Que sentes?
08:54
So we said OK,
192
522239
1151
Entón dixemos: vale,
imos pedirlle a Google que comparta
os rexistros de buscas con nós,
os rexistros de buscas con nós,
08:55
let's ask Google if they will share
their search logs with us,
their search logs with us,
193
523414
3056
08:58
so that we can look at the search logs
194
526494
1833
así poderemos revisalos
09:00
and see if patients are doing
these kinds of searches.
these kinds of searches.
195
528351
2565
e ver se os pacientes fan
ese tipo de buscas.
ese tipo de buscas.
09:02
Google, I am sorry to say,
denied our request.
denied our request.
196
530940
3275
Sinto dicilo, pero Google
rexeitou a petición.
rexeitou a petición.
09:06
So I was bummed.
197
534819
1151
Quedei desanimado.
09:07
I was at a dinner with a colleague
who works at Microsoft Research
who works at Microsoft Research
198
535994
3166
Nunha cea cun colega que traballa
na Microsoft Research conteillo:
na Microsoft Research conteillo:
09:11
and I said, "We wanted to do this study,
199
539184
1941
"Queriamos facer un estudo,
09:13
Google said no, it's kind of a bummer."
200
541149
1880
Google dixo que non, vaia decepción".
09:15
He said, "Well, we have
the Bing searches."
the Bing searches."
201
543053
2086
El dixo: "Temos
as buscas de Bing".
as buscas de Bing".
09:18
(Laughter)
202
546195
3483
(Risas)
09:22
Yeah.
203
550805
1267
Si.
09:24
That's great.
204
552096
1151
Estupendo.
09:25
Now I felt like I was --
205
553271
1151
Sentinme coma se...
09:26
(Laughter)
206
554446
1000
(Risas)
09:27
I felt like I was talking to Nick again.
207
555470
2412
Sentinme coma se falase con Nick.
09:30
He works for one of the largest
companies in the world,
companies in the world,
208
558437
2624
Traballa para unha das empresas
máis grandes do mundo,
máis grandes do mundo,
09:33
and I'm already trying
to make him feel better.
to make him feel better.
209
561085
2206
e eu estou intentando
facer que se sinta ben.
facer que se sinta ben.
Pero el dixo: "Non, Russ...
creo que non entendiches.
creo que non entendiches.
09:35
But he said, "No, Russ --
you might not understand.
you might not understand.
210
563315
2445
09:37
We not only have Bing searches,
211
565784
1500
Non só temos as buscas de Bing,
09:39
but if you use Internet Explorer
to do searches at Google,
to do searches at Google,
212
567308
3340
se usas Internet Explorer
para facer buscas en Google,
para facer buscas en Google,
09:42
Yahoo, Bing, any ...
213
570672
1891
Yahoo, Bing, calquera...
09:44
Then, for 18 months, we keep that data
for research purposes only."
for research purposes only."
214
572587
3643
durante 18 meses, gardamos os datos
para usalos en investigación".
para usalos en investigación".
09:48
I said, "Now you're talking!"
215
576254
1936
Eu dixen: "Agora falaches!"
O meu amigo en Microsoft
era Eric Horvitz.
era Eric Horvitz.
09:50
This was Eric Horvitz,
my friend at Microsoft.
my friend at Microsoft.
216
578214
2198
09:52
So we did a study
217
580436
1695
Así que fixemos un estudo
09:54
where we defined 50 words
that a regular person might type in
that a regular person might type in
218
582155
4619
no que definimos 50 palabras
que unha persoa podería teclear
que unha persoa podería teclear
09:58
if they're having hyperglycemia,
219
586798
1602
se padecía hiperglicemia,
10:00
like "fatigue," "loss of appetite,"
"urinating a lot," "peeing a lot" --
"urinating a lot," "peeing a lot" --
220
588424
4762
como "fatiga", "perda de apetito",
"ouriñar moito", "mexar moito"...
"ouriñar moito", "mexar moito"...
10:05
forgive me, but that's one
of the things you might type in.
of the things you might type in.
221
593210
2767
perdón, pero é unha das cousas
que se poderían escribir.
que se poderían escribir.
10:08
So we had 50 phrases
that we called the "diabetes words."
that we called the "diabetes words."
222
596001
2790
A esas 50 frases chamámoslles
"palabras de diabetes".
"palabras de diabetes".
10:10
And we did first a baseline.
223
598815
2063
Primeiro marcamos un punto de referencia.
10:12
And it turns out
that about .5 to one percent
that about .5 to one percent
224
600902
2704
Resultou que, máis ou menos,
do 0,5 ao 1 por cento
do 0,5 ao 1 por cento
10:15
of all searches on the Internet
involve one of those words.
involve one of those words.
225
603630
2982
de todas as buscas en Internet
incluían unha desas palabras.
incluían unha desas palabras.
10:18
So that's our baseline rate.
226
606636
1742
Esa foi a nosa taxa de referencia.
10:20
If people type in "paroxetine"
or "Paxil" -- those are synonyms --
or "Paxil" -- those are synonyms --
227
608402
4143
Se alguén teclea "paroxetina"
ou "Paxil" -son sinónimos-
ou "Paxil" -son sinónimos-
10:24
and one of those words,
228
612569
1215
e unha desas palabras,
10:25
the rate goes up to about two percent
of diabetes-type words,
of diabetes-type words,
229
613808
4890
a taxa sobe ata un 2%
das palabras de tipo diabetes,
das palabras de tipo diabetes,
10:30
if you already know
that there's that "paroxetine" word.
that there's that "paroxetine" word.
230
618722
3044
se xa sabemos
que está a palabra "paroxetina".
que está a palabra "paroxetina".
10:34
If it's "pravastatin," the rate goes up
to about three percent from the baseline.
to about three percent from the baseline.
231
622191
4547
Se é "pravastatina", a taxa sobe
a arredor dun 3% da referencia.
a arredor dun 3% da referencia.
10:39
If both "paroxetine" and "pravastatin"
are present in the query,
are present in the query,
232
627171
4390
Se na consulta aparecen
"paroxetina" e"pravastatina",
"paroxetina" e"pravastatina",
10:43
it goes up to 10 percent,
233
631585
1669
sobe ata o 10%,
10:45
a huge three- to four-fold increase
234
633278
3461
un grande aumento de tres a catro veces
10:48
in those searches with the two drugs
that we were interested in,
that we were interested in,
235
636763
3389
nas buscas cos dous medicamentos
que nos interesaban
que nos interesaban
10:52
and diabetes-type words
or hyperglycemia-type words.
or hyperglycemia-type words.
236
640176
3566
e as palabras relacionadas con diabetes
ou con hiperglicemia.
ou con hiperglicemia.
10:56
We published this,
237
644216
1265
Publicámolo,
10:57
and it got some attention.
238
645505
1466
e conseguiu algo de atención.
10:58
The reason it deserves attention
239
646995
1778
A razón pola que merece atención
11:00
is that patients are telling us
their side effects indirectly
their side effects indirectly
240
648797
4312
é que os pacientes estannos contando
os efectos secundarios indirectamente
os efectos secundarios indirectamente
11:05
through their searches.
241
653133
1156
a través das buscas.
11:06
We brought this
to the attention of the FDA.
to the attention of the FDA.
242
654313
2138
Chamamos a atención da FDA sobre isto.
11:08
They were interested.
243
656475
1269
Interesoulles.
Tiñan programas de vixilancia
dos medios sociais
dos medios sociais
11:09
They have set up social media
surveillance programs
surveillance programs
244
657768
3606
11:13
to collaborate with Microsoft,
245
661398
1751
para colaborar con Microsoft,
11:15
which had a nice infrastructure
for doing this, and others,
for doing this, and others,
246
663173
2794
que tiñan boa infraestrutura
para facer isto, e outros,
para facer isto, e outros,
11:17
to look at Twitter feeds,
247
665991
1282
para observar os contidos
do Twitter, do Facebook,
do Twitter, do Facebook,
11:19
to look at Facebook feeds,
248
667297
1716
11:21
to look at search logs,
249
669037
1311
os rexistros das buscas,
11:22
to try to see early signs that drugs,
either individually or together,
either individually or together,
250
670372
4909
para buscar sinais de que os medicamentos,
por separado ou en conxunto,
por separado ou en conxunto,
11:27
are causing problems.
251
675305
1589
están causando problemas.
11:28
What do I take from this?
Why tell this story?
Why tell this story?
252
676918
2174
Que saco disto?
Por que conto esta historia?
Por que conto esta historia?
11:31
Well, first of all,
253
679116
1207
Primeiro,
11:32
we have now the promise
of big data and medium-sized data
of big data and medium-sized data
254
680347
4037
temos a promesa dos datos masivos
ou de tamaño medio
ou de tamaño medio
11:36
to help us understand drug interactions
255
684408
2918
de axudarnos a entender as interaccións
entre medicamentos
entre medicamentos
11:39
and really, fundamentally, drug actions.
256
687350
2420
e, fundamentalmente, as súas accións.
Como funcionan os medicamentos?
11:41
How do drugs work?
257
689794
1413
11:43
This will create and has created
a new ecosystem
a new ecosystem
258
691231
2836
Isto creará e xa creou un novo ecosistema
11:46
for understanding how drugs work
and to optimize their use.
and to optimize their use.
259
694091
3267
para entender como funcionan
os medicamentos e optimizar o seu uso.
os medicamentos e optimizar o seu uso.
11:50
Nick went on; he's a professor
at Columbia now.
at Columbia now.
260
698303
2659
Nick seguiu adiante;
agora é profesor en Columbia.
agora é profesor en Columbia.
11:52
He did this in his PhD
for hundreds of pairs of drugs.
for hundreds of pairs of drugs.
261
700986
4072
Fixo isto no doutoramento
con centos de pares de medicamentos.
con centos de pares de medicamentos.
11:57
He found several
very important interactions,
very important interactions,
262
705082
2517
Encontrou interaccións moi importantes,
11:59
and so we replicated this
263
707623
1214
por iso o volvemos facer
12:00
and we showed that this
is a way that really works
is a way that really works
264
708861
2574
e demostramos que o método
realmente funciona
realmente funciona
12:03
for finding drug-drug interactions.
265
711459
2339
para encontrar interaccións
entre medicamentos.
entre medicamentos.
12:06
However, there's a couple of things.
266
714282
1734
Pero, hai un par de cousas.
12:08
We don't just use pairs
of drugs at a time.
of drugs at a time.
267
716040
3046
Non só usamos pares
de medicamentos á vez.
de medicamentos á vez.
12:11
As I said before, there are patients
on three, five, seven, nine drugs.
on three, five, seven, nine drugs.
268
719110
4469
Como dixen, hai pacientes que toman
tres, cinco, sete, nove medicamentos.
tres, cinco, sete, nove medicamentos.
12:15
Have they been studied with respect
to their nine-way interaction?
to their nine-way interaction?
269
723981
3642
Hai algún estudo relacionado
coa interacción dos nove?
coa interacción dos nove?
12:19
Yes, we can do pair-wise,
A and B, A and C, A and D,
A and B, A and C, A and D,
270
727647
4208
Si, podemos comparar por pares,
A e B, A e C, A e D,
A e B, A e C, A e D,
12:23
but what about A, B, C,
D, E, F, G all together,
D, E, F, G all together,
271
731879
4286
pero que pasa con A, B, C,
D, E, F, G xuntos,
D, E, F, G xuntos,
12:28
being taken by the same patient,
272
736189
1762
cando os toma o mesmo paciente,
12:29
perhaps interacting with each other
273
737975
2118
quizais interactuando entre eles
12:32
in ways that either makes them
more effective or less effective
more effective or less effective
274
740117
3778
en modos que os fan
máis eficaces ou menos
máis eficaces ou menos
12:35
or causes side effects
that are unexpected?
that are unexpected?
275
743919
2332
ou que causan efectos secundarios
inesperados?
inesperados?
12:38
We really have no idea.
276
746275
1827
Realmente non temos nin idea.
12:40
It's a blue sky, open field
for us to use data
for us to use data
277
748126
3756
Para nós é un campo aberto
o feito de utilizar datos
o feito de utilizar datos
12:43
to try to understand
the interaction of drugs.
the interaction of drugs.
278
751906
2502
para ver de entender
a interacción dos medicamentos.
a interacción dos medicamentos.
12:46
Two more lessons:
279
754848
1370
Dúas leccións máis:
12:48
I want you to think about the power
that we were able to generate
that we were able to generate
280
756242
4199
Quero que pensen na forza
que puidemos xerar
que puidemos xerar
12:52
with the data from people who had
volunteered their adverse reactions
volunteered their adverse reactions
281
760465
4711
cos datos da xente que aceptou
compartir as súas reaccións adversas
compartir as súas reaccións adversas
12:57
through their pharmacists,
through themselves, through their doctors,
through themselves, through their doctors,
282
765200
3269
por medio dos farmacéuticos,
entre eles mesmos, dos seus médicos,
entre eles mesmos, dos seus médicos,
13:00
the people who allowed the databases
at Stanford, Harvard, Vanderbilt,
at Stanford, Harvard, Vanderbilt,
283
768493
3667
a xente que permitiu que as bases de datos
de Stanford, Harvard, Vanderbilt,
de Stanford, Harvard, Vanderbilt,
13:04
to be used for research.
284
772184
1427
se usasen para investigar.
Á xente preocúpana os datos.
13:05
People are worried about data.
285
773929
1445
Preocúpaa a privacidade
e a seguridade... teñen razón.
e a seguridade... teñen razón.
13:07
They're worried about their privacy
and security -- they should be.
and security -- they should be.
286
775398
3187
Necesitamos sistemas seguros.
13:10
We need secure systems.
287
778609
1151
13:11
But we can't have a system
that closes that data off,
that closes that data off,
288
779784
3406
Pero non podemos ter un sistema
que impida acceder a eses datos,
que impida acceder a eses datos,
13:15
because it is too rich of a source
289
783214
2752
porque é unha fonte demasiado rica
13:17
of inspiration, innovation and discovery
290
785990
3971
de inspiración, innovación e descubrimento
13:21
for new things in medicine.
291
789985
1578
de cousas novas en medicina.
13:24
And the final thing I want to say is,
292
792494
1794
O último que quero dicir é:
13:26
in this case we found two drugs
and it was a little bit of a sad story.
and it was a little bit of a sad story.
293
794312
3357
neste caso encontramos dous fármacos
e foi unha historia algo triste.
e foi unha historia algo triste.
13:29
The two drugs actually caused problems.
294
797693
1921
Os dous medicamentos causaban problemas.
13:31
They increased glucose.
295
799638
1475
Aumentaban a glicosa.
13:33
They could throw somebody into diabetes
296
801137
2446
Podían provocarlle diabetes
13:35
who would otherwise not be in diabetes,
297
803607
2294
a alguén que doutro modo non a tería,
13:37
and so you would want to use
the two drugs very carefully together,
the two drugs very carefully together,
298
805925
3175
por iso o desexable é usar
os dous medicamentos xuntos con coidado,
os dous medicamentos xuntos con coidado,
13:41
perhaps not together,
299
809124
1151
quizais nin xuntos,
13:42
make different choices
when you're prescribing.
when you're prescribing.
300
810299
2340
escoller outros á hora de receitar.
13:44
But there was another possibility.
301
812663
1846
Pero hai outra posibilidade.
13:46
We could have found
two drugs or three drugs
two drugs or three drugs
302
814533
2344
Poderiamos encontrar
dous ou tres medicamentos
dous ou tres medicamentos
13:48
that were interacting in a beneficial way.
303
816901
2261
que interactuasen de forma beneficiosa.
13:51
We could have found new effects of drugs
304
819616
2712
Poderiamos encontrar efectos novos
13:54
that neither of them has alone,
305
822352
2160
que ningún dos fármacos ten por separado,
13:56
but together, instead
of causing a side effect,
of causing a side effect,
306
824536
2493
pero xuntos, en vez de causar
efectos secundarios,
efectos secundarios,
13:59
they could be a new and novel treatment
307
827053
2425
poderían ser un tratamento novidoso
14:01
for diseases that don't have treatments
308
829502
1882
para as enfermidades sen tratamentos
14:03
or where the treatments are not effective.
309
831408
2007
ou con tratamentos pouco efectivos.
14:05
If we think about drug treatment today,
310
833439
2395
Se pensamos nos tratamentos
con medicamentos hoxe,
con medicamentos hoxe,
14:07
all the major breakthroughs --
311
835858
1752
todos os avances importantes...
14:09
for HIV, for tuberculosis,
for depression, for diabetes --
for depression, for diabetes --
312
837634
4297
para o VIH, a tuberculose,
a depresión, a diabetes...
a depresión, a diabetes...
14:13
it's always a cocktail of drugs.
313
841955
2830
sempre son un cóctel de medicamentos.
14:16
And so the upside here,
314
844809
1730
O lado positivo aquí,
14:18
and the subject for a different
TED Talk on a different day,
TED Talk on a different day,
315
846563
2849
e un tema para outra conferencia TED
noutro día,
noutro día,
14:21
is how can we use the same data sources
316
849436
2593
é como podemos usar
as mesmas fontes de datos
as mesmas fontes de datos
14:24
to find good effects
of drugs in combination
of drugs in combination
317
852053
3563
para encontrar efectos positivos
na combinación de medicamentos
na combinación de medicamentos
14:27
that will provide us new treatments,
318
855640
2175
que nos proporcionen novos tratamentos,
14:29
new insights into how drugs work
319
857839
1852
ideas de como funcionan os fármacos
14:31
and enable us to take care
of our patients even better?
of our patients even better?
320
859715
3786
e nos permitan coidar dos pacientes
incluso mellor?
incluso mellor?
14:35
Thank you very much.
321
863525
1166
Moitas grazas.
14:36
(Applause)
322
864715
3499
(Aplausos)
ABOUT THE SPEAKER
Russ Altman - Big data techno-optimist and internistRuss Altman uses machine learning to better understand adverse effects of medication.
Why you should listen
Professor of bioengineering, genetics, medicine and computer science at Stanford University, Russ Altman's primary research interests are in the application of computing and informatics technologies to problems relevant to medicine. He is particularly interested in methods for understanding drug actions at molecular, cellular, organism and population levels, including how genetic variation impacts drug response.
Altman received the U.S. Presidential Early Career Award for Scientists and Engineers, a National Science Foundation CAREER Award and Stanford Medical School's graduate teaching award. He has chaired the Science Board advising the FDA Commissioner and currently serves on the NIH Director’s Advisory Committee. He is a clinically active internist, the founder of the PharmGKB knowledge base, and advisor to pharmacogenomics companies.
Russ Altman | Speaker | TED.com