Russ Altman: What really happens when you mix medications?
Russ Altman: Apa yang terjadi ketika Anda menggabungkan obat-obatan?
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.
melakukan beberapa tes,
that you have high cholesterol
punya kolesterol tinggi
from medication to treat it.
that this is going to work.
bahwa (pengobatan) ini akan berhasil.
a lot of studies, submitted it to the FDA.
pengujian dan mengirimnya ke BPOM.
skeptically, they approved it.
dengan skeptis, dan mengizinkannya.
of what the side effects are.
of a conversation with your physician
because you've been blue,
karena Anda terlihat sedih,
in life quite as much as you usually do.
seperti biasanya Anda lakukan.
I think you have some depression.
"Menurut saya, Anda mengalami depresi.
you another pill."
about two medications.
dua jenis obat sekarang.
of people have taken it,
oleh jutaan orang,
the FDA looked at it -- all good.
BPOM memberikan izin -- semuanya aman.
these two together?
tentang penggabungan keduanya?
"post-marketing surveillance,"
"pengawasan setelah penjualan,"
if bad things are happening
jika hal buruk terjadi
yang didiagnosa beberapa penyakit,
who has several diagnoses
and really, in my opinion,
dan sebenarnya, menurut saya,
to understand these interactions
memahami interaksi (antara obat) ini
of different sources of data
berbagai sumber data
when drugs can be used together safely
aman digunakan bersamaan
ilmu data.
because that's his name.
karena itulah namanya.
to understand how drugs work
"Nick, kita harus memahami kerja obat,
and how they work separately,
dan terpisah,
an amazing database.
yang luar biasa,
download it right now --
dapat diunduh seketika --
of adverse event reports
companies, pharmacists.
that the patient has,
or side effects, that they experience.
that are occurring in America today,
terjadi di Amerika sekarang,
of thousands of drugs.
and we know it's involved with diabetes.
ada hubungannya dengan diabetes.
glucose response.
apakah kita memahami reaksi glukosa.
Saat Nick kembali,
look at the side effects of a drug
efek samping obat
is likely to change glucose or not."
mungkin mengubah glukosa atau tidak".
that were known to change glucose
mengubah glukosa,
that don't change glucose,
yang tidak mengubah glukosa,
in their side effects?
dari efek samping keduanya?
In urination habits?"
Kebiasaan buang air kecil?"
to give him a really good predictor.
prediksi yang sangat bagus.
dengan akurasi 93%
with 93 percent accuracy
mengubah glukosa."
you have to build his confidence.
saya harus membangun kepercayaan dirinya.
knows all the drugs that change glucose,
yang dapat mengubah glukosa,
but not really that interesting,
tapi ini tidak terlalu menarik,
I thought you might say that."
kamu akan bilang begitu."
jadi saya melakukan satu percobaan lain,
so I did one other experiment.
who were on two drugs,
yang menggunakan dua obat,
glucose-changing signals,
tanda perubahan glukosa,
did not change glucose,
tidak mengubah glukosa,
ada sinyal perubahan."
Good idea. Show me the list."
Tunjukkan daftarnya."
not very exciting.
tidak terlalu menarik.
was, on the list there were two drugs:
ada 2 obat dalam daftar:
a cholesterol medication.
obat kolestrerol.
of Americans on those two drugs."
Amerika menggunakan dua obat ini."
at the time, 15 million on pravastatin,
paroxetine ketika itu,
mengunakan keduanya.
with their glucose
that he did in the FDA database
database BPOM ini benar.
with the mumbo jumbo,
yang kamu lakukan
evidence that we have."
bukti yang layak.
electronic medical record.
rekam medis eletronik Stanford.
untuk penelitian,
that's OK for research,
pasien yang menggunakan kedua obat ini
on these two drugs
and thousands of people
that take paroxetine and pravastatin.
paroxetine dan pravastatin.
and had a glucose measurement,
salah satu dan diukur glukosanya,
another glucose measurement,
dan diukur lagi glukosanya,
something like two months.
misalnya dalam dua bulan.
we found 10 patients.
had a bump in their glucose
mengalami kenaikan glukosa
kita sebut kedua obat ini P dan P --
we call this P and P --
the second one comes up,
dan ketika menggunakan obat kedua
20 milligrams per deciliter.
Anda berfungsi normal
if you're not diabetic,
about a potential diagnosis of diabetes.
kemungkinan Anda terkena diabetes.
don't have a paper,
kita masih belum bisa menerbitkan ini,
and -- give me a break --
at Harvard and Vanderbilt,
di Harvard dan Vanderbilt,
Vanderbilt in Nashville,
Vanderbilt di Nashville --
medical records similar to ours.
seperti punya kita.
similar patients
pasien seperti ini
the glucose measurements
dan diukur glukosanya
in one week found 40 such patients,
dalam seminggu menemukan 40 pasien,
gejala yang sama.
from three diverse medical centers
dari 3 pusat medis berbeda
getting these two drugs
yang mengkonsumsi 2 obat ini
somewhat significantly.
we had left out diabetics,
kami mengesampingkan penderita diabetes,
have messed up glucose.
sudah kacau.
at the glucose of diabetics,
penderita diabetes,
per deciliter, not just 20.
tidak hanya 20.
"We've got to publish this."
"Kita harus menerbitkan ini."
satu percobaan apa pun.
was in review, went to the lab.
Nick pergi ke ke lab.
who knew about lab stuff.
yang mengerti tentang lab.
but I don't do pipettes.
tetapi tidak dengan pipet.
cara memberi obat pada tikus.
satu P, paroxetine.
one P, paroxetine.
pada tikus yang lain.
of mice both of them.
kami berikan kedua obat itu.
20 to 60 milligrams per deciliter
kadar glukosa meningkat
pada tikus-tikus itu.
based on the informatics evidence alone,
bukti data saja,
yang mengatakan,
if you give these to mice, it goes up.
glukosa mereka juga naik.
could have ended there.
bisa berakhir di sini.
thinking about all of this,
memikirkan semua ini,
of it, but somebody said,
saya lupa siapa, tapi dia bilang,
who are taking these two drugs
pasien yang mengkonsumsi 2 obat ini
of hyperglycemia.
hyperglycemia.
one new medication or two,
or the one drug you're taking,
atau satu obat yang Anda minum,
their search logs with us,
bisa membagi Log Pencarian pada kami
these kinds of searches.
pencarian seperti ini.
denied our request.
Google menolak permintaan kami.
who works at Microsoft Research
yang bekerja di Microsoft Research
penelitian ini,
the Bing searches."
"Kami punya mesin pencari Bing."
dengan Nick lagi.
companies in the world,
terbesar di dunia,
to make him feel better.
merasa lebih baik.
mungkin kamu tidak mengerti.
you might not understand.
to do searches at Google,
untuk melakukan pencarian di Google,
for research purposes only."
untuk penelitan saja."
my friend at Microsoft.
that a regular person might type in
yang mungkin akan diketik orang awam
"urinating a lot," "peeing a lot" --
nafsu makan," "sering kencing," --
of the things you might type in.
akan Anda ketik.
that we called the "diabetes words."
"kta-kata diabetes."
that about .5 to one percent
menggunakan salah satu kata itu.
involve one of those words.
or "Paxil" -- those are synonyms --
"Paxil" -- keduanya adalah sama --
of diabetes-type words,
kata-kata diabetes,
that there's that "paroxetine" word.
terdapat kata "paroxetine."
to about three percent from the baseline.
sekitar 3 pesen dari nilai dasar.
are present in the query,
"pravastatin" -- ada dalam pencarian,
that we were interested in,
yang menjadi fokus penelitian ini
or hyperglycemia-type words.
kata-kata hyperglycemia.
their side effects indirectly
efek samping mereka secara tidak langsung
to the attention of the FDA.
surveillance programs
di media sosial
for doing this, and others,
untuk melakukannya, dan lainnya,
either individually or together,
ketika kedua obat ini menyebabkan masalah,
Kenapa menceritakan ini?
Why tell this story?
of big data and medium-sized data
perusahaan data besar dan sedang
interaksi obat-obatan
a new ecosystem
ekosistem baru
and to optimize their use.
dan memaksimalkan fungsinya.
at Columbia now.
Dia profesor di Columbia sekarang.
for hundreds of pairs of drugs.
disertasi doktornya
very important interactions,
is a way that really works
jalan yang tepat
of drugs at a time.
pada satu waktu.
on three, five, seven, nine drugs.
ada pasien yang meminum 3, 5, 7, 9 obat.
to their nine-way interaction?
interaksinya ketika digunakan bersamaan?
A and B, A and C, A and D,
A dan B, A dan C, A dan D,
D, E, F, G all together,
secara bersamaan,
more effective or less effective
atau menjadi tidak efektif
yang tidak diharapkan?
that are unexpected?
for us to use data
terbuka bagi kita untuk menggunakan data
the interaction of drugs.
antara obat-obat ini.
that we were able to generate
kekuatan yang bisa kita hasilkan
volunteered their adverse reactions
memberikan reaksi buruk mereka
through themselves, through their doctors,
dan dokter mereka,
at Stanford, Harvard, Vanderbilt,
Stanford, Harvard, Vanderbilt,
and security -- they should be.
dan memang seharusnya begitu.
that closes that data off,
akses kita pada data,
adalah,
and it was a little bit of a sad story.
dan ceritanya agak sedih.
terkena diabetes
kedua obat ini secara bersamaan,
the two drugs very carefully together,
when you're prescribing.
menulis resep.
two drugs or three drugs
pada kedua obat ini
of causing a side effect,
alih-alih efek samping.
pengobatan saat ini,
for depression, for diabetes --
untuk depresi, untuk diabetes --
TED Talk on a different day,
sumber data yang sama
of drugs in combination
dari kombinasi obat-obatan
pengobatan baru,
of our patients even better?
merawat pasien lebih baik?
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