Russ Altman: What really happens when you mix medications?
Расс Альтман: Що насправді відбувається, коли ви змішуєте ліки?
Russ Altman uses machine learning to better understand adverse effects of medication. Full bio
Double-click the English transcript below to play the video.
and get some tests.
that you have high cholesterol
from medication to treat it.
that this is going to work.
a lot of studies, submitted it to the FDA.
провела багато досліджень.
skeptically, they approved it.
of what the side effects are.
можуть бути побічні ефекти.
of a conversation with your physician
because you've been blue,
in life quite as much as you usually do.
повсякденними речима.
I think you have some depression.
у вас невелика депресія.
you another pill."
about two medications.
про два препарати.
of people have taken it,
людей приймають їх,
the FDA looked at it -- all good.
вони пройшли всі тести - все гаразд.
these two together?
"post-marketing surveillance,"
if bad things are happening
яка має декілька діагнозів,
who has several diagnoses
і, як на мене,
and really, in my opinion,
to understand these interactions
взаємодії між ліками -
джерел інформації,
of different sources of data
безпечно вживати разом,
when drugs can be used together safely
про аналіз даних.
because that's his name.
to understand how drugs work
як працюють ліки,
and how they work separately,
an amazing database.
з побічними ефектами.
download it right now --
скачати її прямо зараз:
of adverse event reports
фармацевтів.
companies, pharmacists.
that the patient has,
or side effects, that they experience.
that are occurring in America today,
відбувається в Америці,
of thousands of drugs.
що вона пов'язана з діабетом.
and we know it's involved with diabetes.
glucose response.
Він повернувся.
подивитись побічні ефекти
look at the side effects of a drug
змінювати рівень глюкози.
is likely to change glucose or not."
рівень глюкози,
that were known to change glucose
that don't change glucose,
побічними ефектами?
in their side effects?
Сечовипусканні?"
In urination habits?"
to give him a really good predictor.
дійсно хороший визначник.
з точністю в 93%,
with 93 percent accuracy
додавати впевненості у собі.
you have to build his confidence.
змінюють рівень глюкози,
knows all the drugs that change glucose,
але не надто цікава,
but not really that interesting,
що ви це скажете."
I thought you might say that."
so I did one other experiment.
тож я провів інший експеримент.
які приймали два препарати,
who were on two drugs,
glucose-changing signals,
did not change glucose,
відчутний сигнал.
Покажи мені список."
Good idea. Show me the list."
not very exciting.
були два препарати:
was, on the list there were two drugs:
a cholesterol medication.
ліки від холестерину.
of Americans on those two drugs."
приймають їх одночасно."
at the time, 15 million on pravastatin,
15 мільйонів -
- обидва препарати одночасно.
with their glucose
that he did in the FDA database
не можна публікувати,
with the mumbo jumbo,
як ти начаклував
що ми маємо рацію."
evidence that we have."
записи Стенфорда.
electronic medical record.
тож все гаразд,
that's OK for research,
ідентифікаційну інформацію.
on these two drugs
з рівнем глюкози
and thousands of people
, тисячі і тисячі людей
that take paroxetine and pravastatin.
and had a glucose measurement,
і також слідкували за рівнем глюкози,
another glucose measurement,
something like two months.
часу - наприклад, 2 місяці.
ми знайшли 10 пацієнтів.
we found 10 patients.
had a bump in their glucose
стрибок глюкози,
we call this P and P --
ми називаємо їх "П" і "П" -
вони починають приймати другий -
the second one comes up,
20 milligrams per deciliter.
if you're not diabetic,
що у вас може бути діабет.
about a potential diagnosis of diabetes.
don't have a paper,
не тягне на публікацію,
and -- give me a break --
at Harvard and Vanderbilt,
Vanderbilt in Nashville,
medical records similar to ours.
similar patients
схожих пацієнтів
the glucose measurements
змінами в рівні глюкози,
in one week found 40 such patients,
з такою ж динамікою.
from three diverse medical centers
з 3 різних медичних центрів,
які приймали обидва препарати,
getting these two drugs
somewhat significantly.
we had left out diabetics,
не включили туди діабетиків,
have messed up glucose.
добре з глюкозою.
глюкози діабетиків,
at the glucose of diabetics,
на децилітр, а не на 20.
per deciliter, not just 20.
"We've got to publish this."
"Ми мусимо опублікувати це."
was in review, went to the lab.
Нік пішов у лабораторію.
who knew about lab stuff.
but I don't do pipettes.
препарати мишам.
one P, paroxetine.
дали їм один "П" - пароксетин.
of mice both of them.
20 to 60 milligrams per deciliter
based on the informatics evidence alone,
мишам, рівень глюкози підніметься."
if you give these to mice, it goes up.
могла б закінчитись тут.
could have ended there.
з половиною хвилин.
thinking about all of this,
але хтось сказав:
of it, but somebody said,
які приймали обидва препарати,
who are taking these two drugs
of hyperglycemia.
one new medication or two,
чи два,
or the one drug you're taking,
their search logs with us,
поділитись з нами даними запитів,
these kinds of searches.
denied our request.
що працює в Microsoft,
who works at Microsoft Research
провести дослідження,
що за розчарування!"
the Bing searches."
companies in the world,
компаній у світі,
to make him feel better.
you might not understand.
ти, схоже, не зрозумів.
в Bing, а й запити
to do searches at Google,
for research purposes only."
цю інформацію тільки для досліджень.
my friend at Microsoft.
that a regular person might type in
"urinating a lot," "peeing a lot" --
"багато пісяю" -
of the things you might type in.
що дійсно можуть шукати.
"діабетичними словами".
that we called the "diabetes words."
that about .5 to one percent
involve one of those words.
or "Paxil" -- those are synonyms --
або "Паксил" -
of diabetes-type words,
є слово "пароксетин".
that there's that "paroxetine" word.
to about three percent from the baseline.
частота піднімається на
є і "пароксетин",
are present in the query,
that we were interested in,
or hyperglycemia-type words.
their side effects indirectly
to the attention of the FDA.
surveillance programs
щоб співпрацювати
for doing this, and others,
за стрічкою в Twitter,
either individually or together,
разом чи окремо,
Why tell this story?
of big data and medium-sized data
a new ecosystem
для розуміння
and to optimize their use.
і як оптимізувати їх використання.
at Columbia now.
Колумбійського університету.
дисертації з сотнями ліків.
for hundreds of pairs of drugs.
важливих взаємодій,
very important interactions,
is a way that really works
of drugs at a time.
on three, five, seven, nine drugs.
три, п'ять, сім, дев'ять препаратів.
to their nine-way interaction?
A and B, A and C, A and D,
А і В, А і С, А і D,
D, E, F, G all together,
more effective or less effective
that are unexpected?
край роботи,
for us to use data
зрозуміти ці взаємодії.
the interaction of drugs.
які ми отримали
that we were able to generate
про свої скарги
volunteered their adverse reactions
through themselves, through their doctors,
at Stanford, Harvard, Vanderbilt,
and security -- they should be.
захищені системи.
які обмежують доступ
that closes that data off,
and it was a little bit of a sad story.
два препарати,
Вони дійсно викликали
the two drugs very carefully together,
when you're prescribing.
two drugs or three drugs
of causing a side effect,
for depression, for diabetes --
TED Talk on a different day,
виступу на TED,
ті ж джерела даних,
of drugs in combination
of our patients even better?
пацієнтів ще краще.
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