Russ Altman: What really happens when you mix medications?
Russ Altman: Cfarë ndodh në të vërtetë kur i përzien ilacet?
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
kemi kolesterolin e lartë
from medication to treat it.
that this is going to work.
që ilaçet do funksionojnë.
a lot of studies, submitted it to the FDA.
aprovimin e agjensisë amerikane FDA.
skeptically, they approved it.
dhe skeptikisht, e aprovuan.
of what the side effects are.
efektet anësore.
of a conversation with your physician
because you've been blue,
ndopak i trishtuar
in life quite as much as you usually do.
si gjithmonë.
I think you have some depression.
vuani pak nga depresioni
you another pill."
about two medications.
of people have taken it,
the FDA looked at it -- all good.
dhe ka marrë aprovimin e FDA-s
these two together?
ilaçet së bashku njëkohësisht?
"post-marketing surveillance,"
''Kontrolli post-marketing''
if bad things are happening
efekte anësore të rrezikshme
who has several diagnoses
vuan nga sëmundje të ndryshme.
and really, in my opinion,
shkencore dhe sipas mendimit tim
to understand these interactions
reaksionet që shkaktojnë ilaçet
of different sources of data
bazave të dhënash të ndryshme
when drugs can be used together safely
ilaçe mund të merren bashkë
një bazë të dhënash.
because that's his name.
sepse ky është emri i tij.
to understand how drugs work
si funksionojnë ilaçet.
and how they work separately,
e kur i marrim veç e veç
an amazing database.
një databazë të gjerë të dhënash
download it right now --
mund ti shkarkoni kur të doni.
of adverse event reports
efekte negative
companies, pharmacists.
nga bizneset, nga farmacistët.
that the patient has,
mbi sëmundjet e pacientëve
or side effects, that they experience.
që kanë eksperimentuar.
that are occurring in America today,
që po ndodhin në Amerikë
of thousands of drugs.
and we know it's involved with diabetes.
dhe niveli i saj ka të bëjë me diabetin.
glucose response.
mbi glukozën
look at the side effects of a drug
e efekteve anësore të çdo ilaçi
bazën e të dhënave online
is likely to change glucose or not."
mbi glukozën.
that were known to change glucose
ndikojnë mbi glukozën
that don't change glucose,
in their side effects?
efekteve anësore të tyre?
In urination habits?"
Në mënyrën e urinimit?
to give him a really good predictor.
si parashikues i besueshëm.
with 93 percent accuracy
me 93% saktësi
you have to build his confidence.
duhet ti tregoj që kam besim te ai.
knows all the drugs that change glucose,
mbi nivelin e glukozës
but not really that interesting,
por jo aq shumë interesante.
I thought you might say that."
e dija që do ma thoje.
so I did one other experiment.
prandaj bëra një eksperiment tjetër.
who were on two drugs,
që marrin dy ilaçe
glucose-changing signals,
e ndikimit mbi glukozën
did not change glucose,
nuk sjell asnjë ndryshim mbi glukozën
Good idea. Show me the list."
Ide perfekte, më trego rezultatet
not very exciting.
shumë interesante.
was, on the list there were two drugs:
ishin dy ilaçe:
a cholesterol medication.
kurë për kolesterolin.
of Americans on those two drugs."
at the time, 15 million on pravastatin,
dhe 15 milionë përdorin pravastatin.
with their glucose
that he did in the FDA database
duke u bazuar në të dhënat e FDA-s
with the mumbo jumbo,
evidence that we have."
një provë shkencore.
electronic medical record.
dhënave mjekësore të Stanford.
that's OK for research,
on these two drugs
personat që marrin dy ilaçe
and thousands of people
that take paroxetine and pravastatin.
që përdorin Paroxetin dhe pravastatin.
and had a glucose measurement,
një nivel glukoze kur marrin një ilaç
another glucose measurement,
niveli i glukozës ndryshon krejt
something like two months.
një periudhë prej dy muajsh.
we found 10 patients.
had a bump in their glucose
të papritur në glukozë
we call this P and P --
i quajmë P1 e P2,
the second one comes up,
20 milligrams per deciliter.
if you're not diabetic,
lëvizni normalisht
për diabet
about a potential diagnosis of diabetes.
tonë në Harvard dhe Vanderbilt
don't have a paper,
Vanderbilt në Nashville
and -- give me a break --
mjekësore si ne.
at Harvard and Vanderbilt,
Vanderbilt in Nashville,
gjeti 40 pacientë të tillë
medical records similar to ours.
similar patients
the glucose measurements
nga 3 qëndra mjekësore
të dy ilaçeve
in one week found 40 such patients,
në glukozë.
ne nuk konsideruam diabetikët
me glukozën.
from three diverse medical centers
tek diabetikët
getting these two drugs
për decilitër, dhe jo më 20.
somewhat significantly.
thamë: duhet ta publikojmë.
we had left out diabetics,
have messed up glucose.
at the glucose of diabetics,
per deciliter, not just 20.
"We've got to publish this."
Nick vendosi të bëj eksperimentin.
eksperimente në laborator.
por nuk merrem me pikatore.
was in review, went to the lab.
who knew about lab stuff.
i dhamë të dyja ilaçet.
but I don't do pipettes.
arriti 60 miligram për deciliter
one P, paroxetine.
vetëm tek provat e të dhënave
e laboratorit
of mice both of them.
dhanë të njëjtat rezultate tek minjtë.
20 to 60 milligrams per deciliter
mund të mbaronte ktu.
based on the informatics evidence alone,
if you give these to mice, it goes up.
could have ended there.
që përdorin kto dy ilaçe
të hiperglicemisë.
thinking about all of this,
of it, but somebody said,
who are taking these two drugs
of hyperglycemia.
one new medication or two,
të dhënat e kërkuesve në internet
or the one drug you're taking,
Google nuk pranoi kërkesën tonë.
their search logs with us,
punon për Microsoft Research
these kinds of searches.
denied our request.
who works at Microsoft Research
the Bing searches."
më të mëdha në botë
ta bëj të ndjehet mirë.
për kërkime në Google
companies in the world,
to make him feel better.
kërkimeve për raste studimesh.
you might not understand.
im në Microsoft.
to do searches at Google,
që një person mund të përdorë në kërkim
for research purposes only."
"urinim i shpeshtë", "urinim i shumtë"
my friend at Microsoft.
shprehjet që kërkohet shpesh.
që quajtëm ''fjalë për diabetin''
that a regular person might type in
"urinating a lot," "peeing a lot" --
përdorin një nga këto fjalë.
of the things you might type in.
that we called the "diabetes words."
ose ''paxil''që janë sinonime
that about .5 to one percent
përsa i përket fjalëve mbi diabetin
involve one of those words.
përqindja rritet 3 pikë nga baza.
or "Paxil" -- those are synonyms --
në kërkim
of diabetes-type words,
that there's that "paroxetine" word.
mbi dy ilaçet që na interesonin
to about three percent from the baseline.
me diabetin dhe hipergliceminë.
are present in the query,
that we were interested in,
mbi efektet anësore tërthorazi
or hyperglycemia-type words.
për të vëzhguar mediat sociale
their side effects indirectly
to the attention of the FDA.
surveillance programs
ilaçet, njësh apo bashkë
for doing this, and others,
të dhënash në shkallë të gjëre
either individually or together,
Why tell this story?
të krijojë një ekosistem të ri
of big data and medium-sized data
dhe si të optimizojmë ilaçet.
është profesor tek Columbia.
gjatë doktoratës
a new ecosystem
and to optimize their use.
at Columbia now.
for hundreds of pairs of drugs.
very important interactions,
që përdorin 3,5,7,9 ilaçe bashkë
is a way that really works
A e B, A e C, A e D
of drugs at a time.
on three, five, seven, nine drugs.
to their nine-way interaction?
A and B, A and C, A and D,
të papritura?
D, E, F, G all together,
studimi i të dhënave
more effective or less effective
that are unexpected?
ngjarjet negative
for us to use data
nga doktorët,
the interaction of drugs.
në Stanford, Harvard, Vanderbilt
that we were able to generate
volunteered their adverse reactions
dhe sigurinë e tyre, është normale.
through themselves, through their doctors,
at Stanford, Harvard, Vanderbilt,
and security -- they should be.
that closes that data off,
dy ilaçe me një histori të trishtueshme.
and it was a little bit of a sad story.
the two drugs very carefully together,
when you're prescribing.
të shkaktojë efekt anësor
two drugs or three drugs
of causing a side effect,
diabetin
në TED Talk në të ardhmen,
for depression, for diabetes --
në kombinimin e ilaçeve
e ilaçeve
TED Talk on a different day,
më mirë pacientët tonë?
of drugs in combination
of our patients even better?
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