What really happens when you mix medications? | Russ Altman

Translator: Susana Brandariz Reviewer: Serv. de Norm. Lingüística U. de Santiago de Compostela

So you go to the doctor and get some tests.

Vas ao médico e fas análises.

The doctor determines that you have high cholesterol

O médico diche que tes o colesterol alto

and you would benefit from medication to treat it.

e que é mellor que te poñas en tratamento.

So you get a pillbox.

Recéitache unhas pílulas.

You have some confidence,

Tes confianza,

your physician has some confidence that this is going to work.

o teu médico confía en que funcionará.

The company that invented it did a lot of studies, submitted it to the FDA.

A compañía que as creou fixo moitas análises, enviounas á FDA.

They studied it very carefully, skeptically, they approved it.

Estudounas con coidado, con escepticismo, aprobounas.

They have a rough idea of how it works,

Teñen unha vaga idea de como funcionan,

they have a rough idea of what the side effects are.

teñen unha vaga idea dos efectos secundarios.

It should be OK.

Debería ir todo ben.

You have a little more of a conversation with your physician

Falas un pouco máis co teu médico,

and the physician is a little worried because you've been blue,

o médico está preocupado porque estiveches deprimido,

haven't felt like yourself,

notábaste distinto,

you haven't been able to enjoy things in life quite as much as you usually do.

non gozabas das cousas da vida tanto coma antes.

Your physician says, "You know, I think you have some depression.

O médico diche: "Creo que tes depresión.

I'm going to have to give you another pill."

Vouche ter que dar outra pílula".

So now we're talking about two medications.

Así que agora falamos de dous medicamentos.

This pill also -- millions of people have taken it,

Esta pílula tamén... moita xente a tomou,

the company did studies, the FDA looked at it -- all good.

a compañía fixo análises, a FDA revisouna... todo ben.

Think things should go OK.

Pensas que todo debería ir ben. Pensas que todo debería ir ben.

Think things should go OK.

Well, wait a minute.

Espera un momento.

How much have we studied these two together?

Cantos estudos se fixeron das dúas xuntas?

Well, it's very hard to do that.

Iso é complicado de facer.

In fact, it's not traditionally done.

De feito, o normal é que non se faga.

We totally depend on what we call "post-marketing surveillance,"

Dependemos totalmente do que chamamos "vixilancia poscomercialización",

after the drugs hit the market.

cando as pílulas xa están no mercado.

How can we figure out if bad things are happening

Como podemos saber se algo está indo mal entre dous medicamentos?

between two medications?

Three? Five? Seven?

Ou tres? Ou cinco? Ou sete?

Ask your favorite person who has several diagnoses

Pregúntalle canta medicación toma a alguén con varios diagnósticos.

how many medications they're on.

Why do I care about this problem?

Por que me preocupo por isto? Preocúpame moito.

I care about it deeply.

I'm an informatics and data science guy and really, in my opinion,

Son un home da ciencia dos datos e da informática e, na miña opinión,

the only hope -- only hope -- to understand these interactions

a única esperanza... a única... para entender estas interaccións

is to leverage lots of different sources of data

é aproveitar as máximas fontes de información posibles

in order to figure out when drugs can be used together safely

para determinar cando é seguro usar xuntos os medicamentos

and when it's not so safe.

e cando non é tan seguro.

So let me tell you a data science story.

Cóntovos unha historia da ciencia dos datos.

And it begins with my student Nick.

Empeza co meu alumno Nick.

Let's call him "Nick," because that's his name.

Ímoslle chamar "Nick", porque se chama así.

(Laughter)

(Risas)

Nick was a young student.

Nick era un alumno novo.

I said, "You know, Nick, we have to understand how drugs work

Eu díxenlle: "Temos que entender como funcionan os medicamentos

and how they work together and how they work separately,

e como funcionan xuntos e por separado,

and we don't have a great understanding.

e non sabemos moito diso”.

But the FDA has made available an amazing database.

Pero a FDA dispoñibilizou unha incrible base de datos.

It's a database of adverse events.

É unha base de datos de efectos adversos.

They literally put on the web --

Subiron a Internet...

publicly available, you could all download it right now --

dispoñible para o público, calquera pode descargalos...

hundreds of thousands of adverse event reports

centos de miles de informes sobre efectos adversos

from patients, doctors, companies, pharmacists.

de pacientes, médicos, empresas, farmacéuticos.

And these reports are pretty simple:

Son informes bastante sinxelos:

it has all the diseases that the patient has,

están todas as enfermidades dos pacientes,

all the drugs that they're on,

os medicamentos que toman,

and all the adverse events, or side effects, that they experience.

e os efectos adversos ou secundarios que sofren.

It is not all of the adverse events that are occurring in America today,

Non están todos os efectos adversos actuais dos Estados Unidos,

but it's hundreds and hundreds of thousands of drugs.

pero hai centos e centos de miles de medicamentos.

So I said to Nick,

Entón díxenlle a Nick:

"Let's think about glucose.

"Imos pensar na glicosa.

Glucose is very important, and we know it's involved with diabetes.

A glicosa é moi importante e sabemos que ten que ver coa diabetes.

Let's see if we can understand glucose response.

A ver se entendemos a resposta á glicosa.

I sent Nick off. Nick came back.

Nick marchou para outro lado. Nick volveu.

"Russ," he said,

"Russ" -dixo el-

"I've created a classifier that can look at the side effects of a drug

"Creei un clasificador que pode ver os efectos secundarios dun medicamento

based on looking at this database,

buscando nesta base de datos,

and can tell you whether that drug is likely to change glucose or not."

e pode dicir se é probable que o medicamento altere a glicosa".

He did it. It was very simple, in a way.

Fixérao. En certo modo era moi simple.

He took all the drugs that were known to change glucose

Colleu os medicamentos que se sabe que alteran a glicosa

and a bunch of drugs that don't change glucose,

e un feixe de medicamentos que non a alteran,

and said, "What's the difference in their side effects?

e preguntou: "Que diferenza hai entre os efectos secundarios?

Differences in fatigue? In appetite? In urination habits?"

Hai diferenzas de fatiga? De apetito? Dos hábitos urinarios?"

All those things conspired to give him a really good predictor.

Todo isto conspirou para facer un bo método preditivo.

He said, "Russ, I can predict with 93 percent accuracy

Dixo: "Russ, podo predicir cun 93% de precisión

when a drug will change glucose."

cando vai cambiar a glicosa".

I said, "Nick, that's great."

Eu dixen: "Xenial, Nick".

He's a young student, you have to build his confidence.

É un alumno novo, hai que reforzarlle a confianza.

"But Nick, there's a problem.

"Pero Nick, hai un problema.

It's that every physician in the world knows all the drugs that change glucose,

Todos os médicos do mundo saben qué medicamentos cambian a glicosa,

because it's core to our practice.

porque é algo básico na nosa práctica.

So it's great, good job, but not really that interesting,

Así que estupendo, bo traballo, pero non moi interesante realmente,

definitely not publishable."

definitivamente non publicable".

(Laughter)

(Risas)

He said, "I know, Russ. I thought you might say that."

El dixo: "Xa sei. Pensei que dirías iso".

Nick is smart.

Nick é listo.

"I thought you might say that, so I did one other experiment.

"Pensei que o dirías, por iso fixen outro experimento.

I looked at people in this database who were on two drugs,

Busquei na base de datos persoas que tomasen dous fármacos,

and I looked for signals similar, glucose-changing signals,

e busquei sinais semellantes, sinais de alteración da glicosa,

for people taking two drugs,

en xente que toma dous fármacos,

where each drug alone did not change glucose,

cada un dos cales por si só non alterase a glicosa,

but together I saw a strong signal."

pero xuntos presentasen un sinal forte".

And I said, "Oh! You're clever. Good idea. Show me the list."

E eu dixen: "Que listo es! Boa idea. Ensíname a lista".

And there's a bunch of drugs, not very exciting.

E había medicamentos apenas interesantes,

But what caught my eye was, on the list there were two drugs:

pero chamoume a atención que na lista había dous:

paroxetine, or Paxil, an antidepressant;

paroxetina, ou Paxil, un antidepresivo,

and pravastatin, or Pravachol, a cholesterol medication.

e pravastatina, ou Pravachol, un medicamento para o colesterol.

And I said, "Huh. There are millions of Americans on those two drugs."

E dixen: "Ah! Millóns de estadounidenses toman estes dous medicamentos".

In fact, we learned later,

De feito, despois soubemos

15 million Americans on paroxetine at the time, 15 million on pravastatin,

que 15 millóns toman paroxetina, 15 millóns pravastatina,

and a million, we estimated, on both.

e calculamos que un millón, as dúas.

So that's a million people

Entón un millón de persoas

who might be having some problems with their glucose

poderían estar tendo problemas de glicosa

if this machine-learning mumbo jumbo that he did in the FDA database

se este galimatías automático que fixo na base de datos da FDA

actually holds up.

se sostén realmente.

But I said, "It's still not publishable,

Pero eu dixen: "Aínda non é publicable,

because I love what you did with the mumbo jumbo,

encántame o que fixeches coa lea esta, coa aprendizaxe automática

with the machine learning,

but it's not really standard-of-proof evidence that we have."

pero o que temos non é unha proba evidente".

So we have to do something else.

Temos que facer algo máis.

Let's go into the Stanford electronic medical record.

Imos ao rexistro médico electrónico de Stanford.

We have a copy of it that's OK for research,

Temos unha copia que serve para investigar,

we removed identifying information.

quitámoslle a información identificativa.

And I said, "Let's see if people on these two drugs

E dixen: "Imos ver se a xente que toma eses fármacos

have problems with their glucose."

ten problemas de glicosa".

Now there are thousands and thousands of people

Hai miles de persoas

in the Stanford medical records that take paroxetine and pravastatin.

nos rexistros médicos de Stanford que toman paroxetina e pravastatina,

But we needed special patients.

pero necesitabamos pacientes especiais.

We needed patients who were on one of them and had a glucose measurement,

Necesitabamos pacientes que tomasen un deles e medisen a glicosa,

then got the second one and had another glucose measurement,

e despois tomasen o outro e medisen outra vez a glicosa,

all within a reasonable period of time -- something like two months.

todo dentro dun tempo razoable... algo así como dous meses.

And when we did that, we found 10 patients.

E cando o fixemos encontramos 10 pacientes.

However, eight out of the 10 had a bump in their glucose

Con todo, oito de cada dez tiveron aumento de glicosa

when they got the second P -- we call this P and P --

cando tomaron o segundo P —chamámoslles P e P—

when they got the second P.

cando tomaron o segundo P.

Either one could be first, the second one comes up,

Fose cal fose o primeiro, cando tomaban o segundo,

glucose went up 20 milligrams per deciliter.

a glicosa subía 20 miligramos por decilitro.

Just as a reminder,

Só para situarnos,

you walk around normally, if you're not diabetic,

normalmente andamos, se non somos diabéticos,

coa glicosa arredor de 90.

with a glucose of around 90.

And if it gets up to 120, 125,

Se sobe ata 120, 125,

your doctor begins to think about a potential diagnosis of diabetes.

o médico empeza a pensar nun posible diagnóstico de diabetes.

So a 20 bump -- pretty significant.

Así que un aumento de 20... é bastante significativo.

I said, "Nick, this is very cool.

Eu dixen: "Nick, está moi ben,

But, I'm sorry, we still don't have a paper,

pero, síntoo, aínda non temos artigo,

because this is 10 patients and -- give me a break --

porque estes 10 pacientes -necesito respirar-

non abondan".

it's not enough patients."

So we said, what can we do?

Que podemos facer?

And we said, let's call our friends at Harvard and Vanderbilt,

Vamos chamar aos amigos de Harvard e Vanderbilt,

who also -- Harvard in Boston, Vanderbilt in Nashville,

... Harvard en Boston, Vanderbilt en Nashville,

who also have electronic medical records similar to ours.

que tamén teñen historias clínicas electrónicas parecidas.

Let's see if they can find similar patients

A ver se encontran pacientes parecidos

with the one P, the other P, the glucose measurements

cun P, o outro P, as medicións de glicosa

in that range that we need.

no rango que necesitamos.

God bless them, Vanderbilt in one week found 40 such patients,

Non podía crelo, Vanderbilt nunha semana encontrou 40 pacientes deses,

same trend.

coa mesma tendencia.

Harvard found 100 patients, same trend.

e Harvard encontrou 100, coa mesma tendencia.

So at the end, we had 150 patients from three diverse medical centers

Ao final, tiñamos 150 pacientes de tres centros médicos diferentes

that were telling us that patients getting these two drugs

que nos dicían que os pacientes que tomaban eses dous medicamentos

were having their glucose bump somewhat significantly.

tiñan un aumento de glicosa considerable.

More interestingly, we had left out diabetics,

Máis interesante aínda, deixaramos fóra os diabéticos,

because diabetics already have messed up glucose.

porque a diabetes xa afecta á glicosa.

When we looked at the glucose of diabetics,

Cando nos fixamos na glicosa dos diabéticos,

it was going up 60 milligrams per deciliter, not just 20.

vimos que subía ata 60 miligramos por decilitro, non só 20.

This was a big deal, and we said, "We've got to publish this."

Isto era importante e dixemos: "Temos que publicalo".

We submitted the paper.

Enviamos o artigo.

It was all data evidence,

Todas as probas eran datos,

data from the FDA, data from Stanford,

datos da FDA, datos de Stanford,

data from Vanderbilt, data from Harvard.

datos de Vanderbilt, de Harvard.

We had not done a single real experiment.

Non fixeramos un só experimento real.

But we were nervous.

Pero estabamos nerviosos.

So Nick, while the paper was in review, went to the lab.

Así que Nick, mentres revisaban o artigo, foi ao laboratorio.

We found somebody who knew about lab stuff.

Encontramos unha persoa que entendía de laboratorio.

I don't do that.

Eu non sei diso.

I take care of patients, but I don't do pipettes.

Encárgome de pacientes, non traballo con pipetas.

They taught us how to feed mice drugs.

Ensináronnos a darlles os medicamentos a ratos.

We took mice and we gave them one P, paroxetine.

Collemos uns ratos e démoslles un P, paroxetina.

We gave some other mice pravastatin.

A outros ratos démoslles pravastatina,

And we gave a third group of mice both of them.

e a un terceiro grupo démoslles os dous.

And lo and behold, glucose went up 20 to 60 milligrams per deciliter

Mira por onde, a glicosa aumentou de 20 a 60 miligramos por decilitro

in the mice.

nos ratos.

So the paper was accepted based on the informatics evidence alone,

Aceptaron o artigo só coas probas informáticas,

pero engadimos unha notiña ao final que poñía

but we added a little note at the end,

saying, oh by the way, if you give these to mice, it goes up.

ah por certo, se se proba con ratos, aumenta.

That was great, and the story could have ended there.

Foi xenial e a historia podería acabar aquí,

But I still have six and a half minutes.

pero aínda teño seis minutos e medio.

(Laughter)

(Risas)

So we were sitting around thinking about all of this,

Entón estabamos sen facer nada pensando en todo isto,

and I don't remember who thought of it, but somebody said,

e non recordo quen foi, pero alguén dixo:

"Pregúntome se os pacientes que toman estes dous fármacos

"I wonder if patients who are taking these two drugs

are noticing side effects of hyperglycemia.

están notando efectos secundarios de hiperglicemia.

They could and they should.

Poderían e deberían.

How would we ever determine that?"

Como poderiamos determinar isto?"

We said, well, what do you do?

Que é o que se fai?

You're taking a medication, one new medication or two,

Estás tomando un medicamento novo ou dous

and you get a funny feeling.

e tes unha sensación rara.

What do you do?

Que fas?

You go to Google

Vas a Google

and type in the two drugs you're taking or the one drug you're taking,

e introduces o nome dos medicamentos que estás tomando.

and you type in "side effects."

e escribes "efectos secundarios".

What are you experiencing?

Que sentes?

So we said OK,

Entón dixemos: vale,

let's ask Google if they will share their search logs with us,

imos pedirlle a Google que comparta os rexistros de buscas con nós,

so that we can look at the search logs

así poderemos revisalos

and see if patients are doing these kinds of searches.

e ver se os pacientes fan ese tipo de buscas.

Google, I am sorry to say, denied our request.

Sinto dicilo, pero Google rexeitou a petición.

So I was bummed.

Quedei desanimado.

I was at a dinner with a colleague who works at Microsoft Research

Nunha cea cun colega que traballa na Microsoft Research conteillo:

and I said, "We wanted to do this study,

"Queriamos facer un estudo,

Google said no, it's kind of a bummer."

Google dixo que non, vaia decepción".

He said, "Well, we have the Bing searches."

El dixo: "Temos as buscas de Bing".

(Laughter)

(Risas)

Yeah.

Si.

That's great.

Estupendo.

Now I felt like I was --

Sentinme coma se...

(Laughter)

(Risas)

I felt like I was talking to Nick again.

Sentinme coma se falase con Nick.

He works for one of the largest companies in the world,

Traballa para unha das empresas máis grandes do mundo,

and I'm already trying to make him feel better.

e eu estou intentando facer que se sinta ben.

But he said, "No, Russ -- you might not understand.

Pero el dixo: "Non, Russ... creo que non entendiches.

We not only have Bing searches,

Non só temos as buscas de Bing,

but if you use Internet Explorer to do searches at Google,

se usas Internet Explorer para facer buscas en Google,

Yahoo, Bing, any ...

Yahoo, Bing, calquera...

Then, for 18 months, we keep that data for research purposes only."

durante 18 meses, gardamos os datos para usalos en investigación".

I said, "Now you're talking!"

Eu dixen: "Agora falaches!"

This was Eric Horvitz, my friend at Microsoft.

O meu amigo en Microsoft era Eric Horvitz.

So we did a study

Así que fixemos un estudo

where we defined 50 words that a regular person might type in

no que definimos 50 palabras que unha persoa podería teclear

if they're having hyperglycemia,

se padecía hiperglicemia,

like "fatigue," "loss of appetite," "urinating a lot," "peeing a lot" --

como "fatiga", "perda de apetito", "ouriñar moito", "mexar moito"...

forgive me, but that's one of the things you might type in.

perdón, pero é unha das cousas que se poderían escribir.

So we had 50 phrases that we called the "diabetes words."

A esas 50 frases chamámoslles "palabras de diabetes".

And we did first a baseline.

Primeiro marcamos un punto de referencia.

And it turns out that about .5 to one percent

Resultou que, máis ou menos, do 0,5 ao 1 por cento

of all searches on the Internet involve one of those words.

de todas as buscas en Internet incluían unha desas palabras.

So that's our baseline rate.

Esa foi a nosa taxa de referencia.

If people type in "paroxetine" or "Paxil" -- those are synonyms --

Se alguén teclea "paroxetina" ou "Paxil" -son sinónimos-

and one of those words,

e unha desas palabras,

the rate goes up to about two percent of diabetes-type words,

a taxa sobe ata un 2% das palabras de tipo diabetes,

if you already know that there's that "paroxetine" word.

se xa sabemos que está a palabra "paroxetina".

If it's "pravastatin," the rate goes up to about three percent from the baseline.

Se é "pravastatina", a taxa sobe a arredor dun 3% da referencia.

If both "paroxetine" and "pravastatin" are present in the query,

Se na consulta aparecen "paroxetina" e"pravastatina",

it goes up to 10 percent,

sobe ata o 10%,

a huge three- to four-fold increase

un grande aumento de tres a catro veces

in those searches with the two drugs that we were interested in,

nas buscas cos dous medicamentos que nos interesaban

and diabetes-type words or hyperglycemia-type words.

e as palabras relacionadas con diabetes ou con hiperglicemia.

We published this,

Publicámolo,

and it got some attention.

e conseguiu algo de atención.

The reason it deserves attention

A razón pola que merece atención

is that patients are telling us their side effects indirectly

é que os pacientes estannos contando os efectos secundarios indirectamente

through their searches.

a través das buscas.

We brought this to the attention of the FDA.

Chamamos a atención da FDA sobre isto.

They were interested.

Interesoulles.

They have set up social media surveillance programs

Tiñan programas de vixilancia dos medios sociais

to collaborate with Microsoft,

para colaborar con Microsoft,

which had a nice infrastructure for doing this, and others,

que tiñan boa infraestrutura para facer isto, e outros,

to look at Twitter feeds,

para observar os contidos do Twitter, do Facebook,

to look at Facebook feeds,

to look at search logs,

os rexistros das buscas,

to try to see early signs that drugs, either individually or together,

para buscar sinais de que os medicamentos, por separado ou en conxunto,

are causing problems.

están causando problemas.

What do I take from this? Why tell this story?

Que saco disto? Por que conto esta historia?

Well, first of all,

Primeiro,

we have now the promise of big data and medium-sized data

temos a promesa dos datos masivos ou de tamaño medio

to help us understand drug interactions

de axudarnos a entender as interaccións entre medicamentos

and really, fundamentally, drug actions.

e, fundamentalmente, as súas accións.

How do drugs work?

Como funcionan os medicamentos?

This will create and has created a new ecosystem

Isto creará e xa creou un novo ecosistema

for understanding how drugs work and to optimize their use.

para entender como funcionan os medicamentos e optimizar o seu uso.

Nick went on; he's a professor at Columbia now.

Nick seguiu adiante; agora é profesor en Columbia.

He did this in his PhD for hundreds of pairs of drugs.

Fixo isto no doutoramento con centos de pares de medicamentos.

He found several very important interactions,

Encontrou interaccións moi importantes,

and so we replicated this

por iso o volvemos facer

and we showed that this is a way that really works

e demostramos que o método realmente funciona

for finding drug-drug interactions.

para encontrar interaccións entre medicamentos.

However, there's a couple of things.

Pero, hai un par de cousas.

We don't just use pairs of drugs at a time.

Non só usamos pares de medicamentos á vez.

As I said before, there are patients on three, five, seven, nine drugs.

Como dixen, hai pacientes que toman tres, cinco, sete, nove medicamentos.

Have they been studied with respect to their nine-way interaction?

Hai algún estudo relacionado coa interacción dos nove?

Yes, we can do pair-wise, A and B, A and C, A and D,

Si, podemos comparar por pares, A e B, A e C, A e D,

but what about A, B, C, D, E, F, G all together,

pero que pasa con A, B, C, D, E, F, G xuntos,

being taken by the same patient,

cando os toma o mesmo paciente,

perhaps interacting with each other

quizais interactuando entre eles

in ways that either makes them more effective or less effective

en modos que os fan máis eficaces ou menos

or causes side effects that are unexpected?

ou que causan efectos secundarios inesperados?

We really have no idea.

Realmente non temos nin idea.

It's a blue sky, open field for us to use data

Para nós é un campo aberto o feito de utilizar datos

to try to understand the interaction of drugs.

para ver de entender a interacción dos medicamentos.

Two more lessons:

Dúas leccións máis:

I want you to think about the power that we were able to generate

Quero que pensen na forza que puidemos xerar

with the data from people who had volunteered their adverse reactions

cos datos da xente que aceptou compartir as súas reaccións adversas

through their pharmacists, through themselves, through their doctors,

por medio dos farmacéuticos, entre eles mesmos, dos seus médicos,

the people who allowed the databases at Stanford, Harvard, Vanderbilt,

a xente que permitiu que as bases de datos de Stanford, Harvard, Vanderbilt,

to be used for research.

se usasen para investigar.

People are worried about data.

Á xente preocúpana os datos.

They're worried about their privacy and security -- they should be.

Preocúpaa a privacidade e a seguridade... teñen razón.

We need secure systems.

Necesitamos sistemas seguros.

But we can't have a system that closes that data off,

Pero non podemos ter un sistema que impida acceder a eses datos,

because it is too rich of a source

porque é unha fonte demasiado rica

of inspiration, innovation and discovery

de inspiración, innovación e descubrimento

for new things in medicine.

de cousas novas en medicina.

And the final thing I want to say is,

O último que quero dicir é:

in this case we found two drugs and it was a little bit of a sad story.

neste caso encontramos dous fármacos e foi unha historia algo triste.

The two drugs actually caused problems.

Os dous medicamentos causaban problemas.

They increased glucose.

Aumentaban a glicosa.

They could throw somebody into diabetes

Podían provocarlle diabetes

who would otherwise not be in diabetes,

a alguén que doutro modo non a tería,

and so you would want to use the two drugs very carefully together,

por iso o desexable é usar os dous medicamentos xuntos con coidado,

perhaps not together,

quizais nin xuntos,

make different choices when you're prescribing.

escoller outros á hora de receitar.

But there was another possibility.

Pero hai outra posibilidade.

We could have found two drugs or three drugs

Poderiamos encontrar dous ou tres medicamentos

that were interacting in a beneficial way.

que interactuasen de forma beneficiosa.

We could have found new effects of drugs

Poderiamos encontrar efectos novos

that neither of them has alone,

que ningún dos fármacos ten por separado,

but together, instead of causing a side effect,

pero xuntos, en vez de causar efectos secundarios,

they could be a new and novel treatment

poderían ser un tratamento novidoso

for diseases that don't have treatments

para as enfermidades sen tratamentos

or where the treatments are not effective.

ou con tratamentos pouco efectivos.

If we think about drug treatment today,

Se pensamos nos tratamentos con medicamentos hoxe,

all the major breakthroughs --

todos os avances importantes...

for HIV, for tuberculosis, for depression, for diabetes --

para o VIH, a tuberculose, a depresión, a diabetes...

it's always a cocktail of drugs.

sempre son un cóctel de medicamentos.

And so the upside here,

O lado positivo aquí,

and the subject for a different TED Talk on a different day,

e un tema para outra conferencia TED noutro día,

is how can we use the same data sources

é como podemos usar as mesmas fontes de datos

to find good effects of drugs in combination

para encontrar efectos positivos na combinación de medicamentos

that will provide us new treatments,

que nos proporcionen novos tratamentos,

new insights into how drugs work

ideas de como funcionan os fármacos

and enable us to take care of our patients even better?

e nos permitan coidar dos pacientes incluso mellor?

Thank you very much.

Moitas grazas.

(Applause)

(Aplausos)