What really happens when you mix medications? | Russ Altman

188,264 views ใƒป 2016-03-23

TED


์•„๋ž˜ ์˜๋ฌธ์ž๋ง‰์„ ๋”๋ธ”ํด๋ฆญํ•˜์‹œ๋ฉด ์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค.

๋ฒˆ์—ญ: Jihyeon J. Kim ๊ฒ€ํ† : hansom Lee
00:12
So you go to the doctor and get some tests.
0
12811
3321
์—ฌ๋Ÿฌ๋ถ„์€ ์˜์‚ฌ์—๊ฒŒ ๊ฐ€์„œ ๋ช‡๊ฐ€์ง€ ๊ฒ€์‚ฌ๋ฅผ ๋ฐ›์Šต๋‹ˆ๋‹ค.
00:16
The doctor determines that you have high cholesterol
1
16674
2620
์˜์‚ฌ๋Š” ์—ฌ๋Ÿฌ๋ถ„์˜ ๋†’์€ ์ฝœ๋ ˆ์Šคํ…Œ๋กค ์ˆ˜์น˜๋ฅผ ํ™•์ธํ–ˆ๊ณ 
00:19
and you would benefit from medication to treat it.
2
19318
3171
์•ฝ์„ ํ†ตํ•ด์„œ ์น˜๋ฃŒํ•ด์•ผ ํ•œ๋‹ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค.
00:22
So you get a pillbox.
3
22981
1556
๊ทธ๋ž˜์„œ ์•ฝ์„ ๋ฐ›์•˜์Šต๋‹ˆ๋‹ค.
00:25
You have some confidence,
4
25505
1199
์—ฌ๋Ÿฌ๋ถ„์€ ์–ด๋–ค ํ™•์‹ ์ด ์žˆ๊ณ 
00:26
your physician has some confidence that this is going to work.
5
26728
2937
์—ฌ๋Ÿฌ๋ถ„์˜ ์˜์‚ฌ๋Š” ์ด ์•ฝ์ด ํšจ๋Šฅ์ด ์žˆ๋‹ค๋Š” ํ™•์‹ ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
00:29
The company that invented it did a lot of studies, submitted it to the FDA.
6
29689
3553
๊ทธ ์•ฝ์„ ๋งŒ๋“  ์ œ์•ฝํšŒ์‚ฌ๋Š” ๋งŽ์€ ์ž์ฒด์‹คํ—˜ ํ–ˆ๊ณ , FDA์— ๊ทธ๊ฑธ ์ œ์ถœํ–ˆ์Šต๋‹ˆ๋‹ค.
00:33
They studied it very carefully, skeptically, they approved it.
7
33266
3107
FDA๋Š” ๋งค์šฐ ์‹ ์ค‘ํ•˜๊ณ  ํšŒ์˜์ ์œผ๋กœ ๊ฒ€ํ† ํ•œ ๋‹ค์Œ ๊ทธ ์•ฝ์„ ์Šน์ธํ–ˆ์Šต๋‹ˆ๋‹ค.
00:36
They have a rough idea of how it works,
8
36397
1889
๊ทธ๋“ค์€ ๊ทธ ์•ฝ์ด ์–ด๋–ป๊ฒŒ ์ž‘์šฉํ•˜๋Š”์ง€ ๋Œ€์ถฉ ์•Œ๊ณ  ์žˆ๊ณ 
00:38
they have a rough idea of what the side effects are.
9
38310
2453
๋ถ€์ž‘์šฉ์ด ์–ด๋–ค์ง€๋„ ๋Œ€์ถฉ ์•Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
00:40
It should be OK.
10
40787
1150
์ด๊ฒƒ์€ ๊ดœ์ฐฎ์„ ๊ฒ๋‹ˆ๋‹ค.
00:42
You have a little more of a conversation with your physician
11
42864
2818
์•ฝ ์ฒ˜๋ฐฉ ํ›„, ์—ฌ๋Ÿฌ๋ถ„์€ ์˜์‚ฌ์™€ ์กฐ๊ธˆ ๋” ๋Œ€ํ™”๋ฅผ ๋‚˜๋ˆ„์—ˆ์Šต๋‹ˆ๋‹ค.
00:45
and the physician is a little worried because you've been blue,
12
45706
2963
์˜์‚ฌ๋Š” ์‚ด์ง ๊ฑฑ์ •ํ–ˆ์Šต๋‹ˆ๋‹ค. ์—ฌ๋Ÿฌ๋ถ„์˜ ๋‚ด๋‚ด ์šฐ์šธํ•œ ๋ชจ์Šต๊ณผ
00:48
haven't felt like yourself,
13
48693
1293
์—ฌ๋Ÿฌ๋ถ„๋‹ต์ง€ ์•Š์€ ๋ชจ์Šต
00:50
you haven't been able to enjoy things in life quite as much as you usually do.
14
50010
3731
ํ‰์†Œ๋งŒํผ ์‚ถ์„ ์ฆ๊ธฐ๋Š” ๋ชปํ•˜๊ณ  ์žˆ๋Š” ๋ชจ์Šต์„ ๋ง์ž…๋‹ˆ๋‹ค.
00:53
Your physician says, "You know, I think you have some depression.
15
53765
3186
์—ฌ๋Ÿฌ๋ถ„์˜ ์˜์‚ฌ๋Š” ๋งํ•ฉ๋‹ˆ๋‹ค. "์šฐ์šธ์ฆ ์ฆ์„ธ๊ฐ€ ์žˆ๋Š” ๊ฒƒ ๊ฐ™๋„ค์š”.
00:57
I'm going to have to give you another pill."
16
57792
2315
์ œ๊ฐ€ ๋‹ค๋ฅธ ์•ฝ์„ ์ฒ˜๋ฐฉํ•ด ๋“œ๋ฆฌ์ฃ ."
01:00
So now we're talking about two medications.
17
60934
2483
์ด์ œ ์šฐ๋ฆฌ๋Š” ์ด ๋‘ ์•ฝ์— ๋Œ€ํ•œ ์ด์•ผ๊ธฐ๋ฅผ ํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
01:03
This pill also -- millions of people have taken it,
18
63441
3104
์šฐ์„์ฆ ์•ฝ ์—ญ์‹œ-- ์ˆ˜๋ฐฑ๋งŒ ๋ช…์ด ๋ณต์šฉํ•˜๊ณ  ์žˆ๊ณ ,
01:06
the company did studies, the FDA looked at it -- all good.
19
66569
3631
์ œ์•ฝํšŒ์‚ฌ๊ฐ€ ๊ฒ€ํ† ๋ฅผ ํ–ˆ๊ณ , FDA๊ฐ€ ๊ทธ ์•ฝ์„ ์‚ดํŽด๋ดค์ฃ . ๋ชจ๋“  ๊ฒƒ์ด ์ข‹์•˜์ฃ .
01:10
Think things should go OK.
20
70823
2057
์ด๊ฒƒ์ด ๊ดœ์ฐฎ์„ ๊ฑฐ๋ผ๊ณ  ์ƒ๊ฐํ•ฉ๋‹ˆ๋‹ค.
01:12
Think things should go OK.
21
72904
2197
์ด๊ฒƒ์ด ๊ดœ์ฐฎ์„ ๊ฑฐ๋ผ๊ณ  ์ƒ๊ฐํ•ฉ๋‹ˆ๋‹ค.
01:15
Well, wait a minute.
22
75125
1439
์Œ, ์ž ๊น๋งŒ์š”.
01:16
How much have we studied these two together?
23
76588
3517
์ด ๋‘ ์•ฝ์„ ๊ฐ™์ด ๋จน์—ˆ์„ ๊ฒฝ์šฐ์— ๋Œ€ํ•ด ์‹คํ—˜ํ•ด๋ณธ ์ ์ด ์–ผ๋งˆ๋‚˜ ๋ ๊นŒ์š”?
01:20
Well, it's very hard to do that.
24
80630
2300
๊ธ€์Ž„์š”, ์ด๋Ÿฐ ์‹คํ—˜์„ ํ•˜๋Š” ๊ฒƒ์ด ๊ต‰์žฅํžˆ ์–ด๋ ต์Šต๋‹ˆ๋‹ค.
01:22
In fact, it's not traditionally done.
25
82954
2130
์‚ฌ์‹ค, ์ „ํ†ต์ ์œผ๋กœ ๊ทธ๋Ÿฐ ์‹คํ—˜์„ ํ•˜์ง„ ์•Š์Šต๋‹ˆ๋‹ค.
01:25
We totally depend on what we call "post-marketing surveillance,"
26
85108
5518
์šฐ๋ฆฌ๋Š” ์•ฝ์ด ์‹œ์žฅ์— ์ถœ์‹œ๋˜์–ด ํŒ”๋ฆฐ ํ›„
์ „์ ์œผ๋กœ "์‹œํŒ ํ›„ ์กฐ์‚ฌ"๋ผ๊ณ  ๋ถ€๋ฅด๋Š” ๊ฒƒ์— ์˜์กดํ•ฉ๋‹ˆ๋‹ค.
01:30
after the drugs hit the market.
27
90650
1880
01:32
How can we figure out if bad things are happening
28
92996
2848
๋งŒ์•ฝ์— ๋‚˜์œ ์ผ์ด ๋‘ ์•ฝ ์‚ฌ์ด์— ์ผ์–ด๋‚ฌ๋‹ค๋ฉด
01:35
between two medications?
29
95868
1357
์šฐ๋ฆฌ๋Š” ์ด๊ฑธ ์–ด๋–ป๊ฒŒ ์•Œ์•„๋‚ผ ์ˆ˜ ์žˆ์„๊นŒ์š”?
01:37
Three? Five? Seven?
30
97249
2030
3๊ฐœ๋Š”? 5๊ฐœ๋Š”? 7๊ฐœ๋Š”์š”?
01:39
Ask your favorite person who has several diagnoses
31
99708
2415
์—ฌ๋Ÿฌ ๋ฒˆ ์ง„๋ฃŒ๋ฅผ ๋ฐ›์€ ์นœํ•œ ์‚ฌ๋žŒ์—๊ฒŒ
01:42
how many medications they're on.
32
102147
1834
๋ช‡ ๊ฐœ์˜ ์•ฝ์„ ๋ณต์šฉํ•˜๊ณ  ์žˆ๋Š” ์ง€ ๋ฌผ์–ด๋ณด์„ธ์š”.
01:44
Why do I care about this problem?
33
104530
1580
์™œ ์ œ๊ฐ€ ์ด ๋ฌธ์ œ์— ๋Œ€ํ•ด์„œ ์‹ ๊ฒฝ์“ฐ๋ƒ๊ณ ์š”?
01:46
I care about it deeply.
34
106134
1157
์ €๋Š” ์ง„์‹ฌ์œผ๋กœ ๊ฑฑ์ •์Šค๋Ÿฝ์Šต๋‹ˆ๋‹ค.
01:47
I'm an informatics and data science guy and really, in my opinion,
35
107315
4304
์ €๋Š” ์ •๋ณดํ•™์ž์ด์ž ๋ฐ์ดํ„ฐ ๊ณผํ•™์ž์ž…๋‹ˆ๋‹ค. ๊ทธ๋ฆฌ๊ณ  ์ •๋ง๋กœ, ์ œ ์ƒ๊ฐ์—๋Š”
01:51
the only hope -- only hope -- to understand these interactions
36
111643
3745
์ด๋Ÿฌํ•œ ์ƒํ˜ธ์ž‘์šฉ์„ ์ดํ•ดํ•˜๊ธฐ ์œ„ํ•œ ์œ ์ผํ•œ ํฌ๋ง-- ์œ ์ผํ•œ ํฌ๋ง์€
01:55
is to leverage lots of different sources of data
37
115412
3056
๋‹ค๋ฅธ ๋งŽ์€ ์ •๋ณด ์›์ฒœ์˜ ์ด์ ์„
01:58
in order to figure out when drugs can be used together safely
38
118492
3556
์•ฝ์„ ๊ฐ™์ด ๋จน์—ˆ์„๋•Œ ์•ˆ์ „ํ•œ์ง€ ์•ˆ์ „ํ•˜์ง€ ์•Š์€์ง€
์•Œ์•„๋‚ด๊ธฐ์œ„ํ•ด ํ™œ์šฉํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
02:02
and when it's not so safe.
39
122072
1777
02:04
So let me tell you a data science story.
40
124615
2051
์ œ๊ฐ€ ํ•œ๊ฐ€์ง€ ๋ฐ์ดํ„ฐ ์ •๋ณดํ•™ ์ด์•ผ๊ธฐ๋ฅผ ๋“ค๋ ค๋“œ๋ฆฌ์ฃ .
02:06
And it begins with my student Nick.
41
126690
2154
์ด ์ด์•ผ๊ธฐ๋Š” ์ œ ํ•™์ƒ ๋‹‰๊ณผ ํ•จ๊ป˜ ์‹œ์ž‘ํ•ฉ๋‹ˆ๋‹ค.
02:08
Let's call him "Nick," because that's his name.
42
128868
2380
๊ทธ๋ฅผ "๋‹‰"์ด๋ผ๊ณ  ํ•˜๋„๋ก ํ•˜์ฃ , ์™œ๋ƒํ•˜๋ฉด ๊ทธ๊ฒŒ ๊ทธ์˜ ์ด๋ฆ„์ด๊ฑฐ๋“ ์š”.
02:11
(Laughter)
43
131272
1592
(์›ƒ์Œ)
02:12
Nick was a young student.
44
132888
1201
๋‹‰์€ ์–ด๋ฆฐ ํ•™์ƒ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
02:14
I said, "You know, Nick, we have to understand how drugs work
45
134113
3079
์ €๋Š” ๋งํ–ˆ์ฃ . "์žˆ์ž–์•„, ๋‹‰, ์šฐ๋ฆฌ๋Š” ์•ฝ๋“ค์ด ์–ด๋–ป๊ฒŒ ์ž‘์šฉํ•˜๋Š”์ง€
02:17
and how they work together and how they work separately,
46
137216
2626
๊ฐ™์ด๋Š” ์–ด๋–ป๊ฒŒ ์ž‘์šฉํ•˜๊ณ  ๋”ฐ๋กœ๋Š” ์–ด๋–ป๊ฒŒ ์ž‘์šฉํ•˜๋Š”์ง€
02:19
and we don't have a great understanding.
47
139866
1922
์ดํ•ด๋ฅผ ํ•ด์•ผ ํ•˜๋Š”๋ฐ ๊ทธ๋Ÿฌํ•œ ์ดํ•ด๊ฐ€ ์ถฉ๋ถ„ํžˆ ๋˜์–ด์žˆ์ง€ ์•Š์•„.
02:21
But the FDA has made available an amazing database.
48
141812
2405
ํ•˜์ง€๋งŒ FDA๋Š” ์ด์šฉํ•  ์ˆ˜ ์žˆ๋Š” ๋†€๋ผ์šด ๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค๋ฅผ ๋งŒ๋“ค์—ˆ์ง€.
02:24
It's a database of adverse events.
49
144241
1699
์•ฝ๋ฌผ์˜ ๋ถ€์ž‘์šฉ์— ๋Œ€ํ•œ ์ž๋ฃŒ์ง€.
02:26
They literally put on the web --
50
146321
1642
๊ทธ ์ž๋ฃŒ๋Š” ๋ฌธ์ž ๊ทธ๋Œ€๋กœ ์›น์— ์˜ฌ๋ผ์™€ ์žˆ๊ณ --
02:27
publicly available, you could all download it right now --
51
147987
3119
๊ณต๊ณต์—ฐํ•˜๊ฒŒ ์ด์šฉํ•  ์ˆ˜ ์žˆ๊ณ , ์ง€๊ธˆ ๋‹น์žฅ ๊ทธ ์ž๋ฃŒ๋ฅผ ๋‹ค์šด๋ฐ›์„ ์ˆ˜ ์žˆ์ง€.
02:31
hundreds of thousands of adverse event reports
52
151130
3627
ํ™˜์ž๋“ค, ์˜์‚ฌ๋“ค, ํšŒ์‚ฌ๋“ค, ์•ฝ์‚ฌ๋“ค๋กœ๋ถ€ํ„ฐ ๋‚˜์˜จ
02:34
from patients, doctors, companies, pharmacists.
53
154781
3760
์ˆ˜๋ฐฑ ์ˆ˜์ฒœ๊ฐœ์˜ ๋ถ€์ž‘์šฉ ๊ด€๋ จ ๋ณด๊ณ ์„œ๋“ค ๋ง์ด์•ผ.
02:38
And these reports are pretty simple:
54
158565
1749
๊ทธ๋ฆฌ๊ณ  ๊ทธ ๋ณด๊ณ ์„œ์˜ ๋‚ด์šฉ์€ ๊ฝค ๊ฐ„๋‹จํ•ด.
02:40
it has all the diseases that the patient has,
55
160338
2658
ํ™˜์ž๊ฐ€ ๊ฐ€์ง€๊ณ  ์žˆ๋Š” ๋ชจ๋“  ์งˆ๋ณ‘
02:43
all the drugs that they're on,
56
163020
1767
ํ™˜์ž๊ฐ€ ๋ณต์šฉํ•˜๋Š” ๋ชจ๋“  ์•ฝ๋ฌผ
02:44
and all the adverse events, or side effects, that they experience.
57
164811
3818
๊ทธ๋ฆฌ๊ณ  ๋ชจ๋“  ๋ถ€์ž‘์šฉ ์‚ฌ๋ก€๋“ค, ํ˜น์€ ํ™˜์ž๊ฐ€ ๊ฒช๊ณ  ์žˆ๋Š” ๋ถ€์ž‘์šฉ๋“ค์ด ์žˆ์ง€.
02:48
It is not all of the adverse events that are occurring in America today,
58
168653
3436
์˜ค๋Š˜๋‚  ๋ฏธ๊ตญ์—์„œ ์ผ์–ด๋‚˜๋Š” ๋ชจ๋“  ๋ถ€์ž‘์šฉ์— ๊ด€ํ•œ ๊ฑด ์•„๋‹ˆ์ง€๋งŒ
02:52
but it's hundreds and hundreds of thousands of drugs.
59
172113
2578
์ˆ˜๋ฐฑ ์ˆ˜์ฒœ๊ฐœ์˜ ์•ฝ๋ฌผ์— ๊ด€๋ จ๋œ ๊ฑฐ์•ผ."
02:54
So I said to Nick,
60
174715
1299
๊ณ„์† ์ „ ๋‹‰์—๊ฒŒ ๋งํ–ˆ์ฃ .
02:56
"Let's think about glucose.
61
176038
1826
"ํฌ๋„๋‹น์— ๊ด€ํ•˜์—ฌ ์ƒ๊ฐํ•ด๋ณด์ž.
02:57
Glucose is very important, and we know it's involved with diabetes.
62
177888
3567
ํฌ๋„๋‹น์€ ๋งค์šฐ ์ค‘์š”ํ•˜์ง€. ๊ทธ๋ฆฌ๊ณ  ๋‹น๋‡จ๋ณ‘๊ณผ ๊ด€๋ จ์žˆ๋‹ค๋Š” ๊ฒƒ๋„ ์•Œ์ง€.
03:01
Let's see if we can understand glucose response.
63
181479
3970
ํฌ๋„๋‹น ๋ฐ˜์‘์„ ์ดํ•ดํ•  ์ˆ˜ ์žˆ๋Š”์ง€ ํ•œ๋ฒˆ ๋ณด์ž๊พธ๋‚˜.
03:05
I sent Nick off. Nick came back.
64
185473
2458
์ €๋Š” ๋‹‰์„ ๋ณด๋ƒˆ์Šต๋‹ˆ๋‹ค. ๋‹‰์€ ๋Œ์•„์™”์ฃ .
03:08
"Russ," he said,
65
188248
1786
"๋Ÿฌ์Šค," ๊ทธ๋Š” ๋งํ–ˆ์Šต๋‹ˆ๋‹ค,
03:10
"I've created a classifier that can look at the side effects of a drug
66
190351
5112
"์ œ๊ฐ€ ๊ทธ ๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค๋ฅผ ๋ฐ”ํƒ•์œผ๋กœ
์•ฝ์˜ ๋ถ€์ž‘์šฉ์„ ๋ณผ ์ˆ˜ ์žˆ๋Š” ๋ถ„๋ฅ˜ํ‘œ๋ฅผ ๋งŒ๋“ค์—ˆ์–ด์š”.
03:15
based on looking at this database,
67
195487
2051
03:17
and can tell you whether that drug is likely to change glucose or not."
68
197562
4271
๊ทธ๋ฆฌ๊ณ  ๊ทธ ๋ถ„๋ฅ˜ํ‘œ๋Š” ์•ฝ์ด ํฌ๋„๋‹น์„ ๋ณ€ํ™”์‹œํ‚ค๋Š”์ง€ ์•„๋‹Œ์ง€๋ฅผ ์•Œ๋ ค์ฃผ์ฃ .
03:21
He did it. It was very simple, in a way.
69
201857
2016
๊ทธ๋Š” ํ•ด๋ƒˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฑด ๋งค์šฐ ๊ฐ„๋‹จํ–ˆ์ฃ . ์–ด๋Š ์ •๋„๋Š”์š”.
03:23
He took all the drugs that were known to change glucose
70
203897
2635
๊ทธ๋Š” ํฌ๋„๋‹น์— ๋ณ€ํ™”์‹œํ‚จ๋‹ค๊ณ  ์•Œ๋ ค์ง„ ๋ชจ๋“  ์•ฝ๊ณผ
03:26
and a bunch of drugs that don't change glucose,
71
206556
2389
๋ณ€ํ™”์‹œํ‚ค์ง€ ์•Š๋Š” ๋ชจ๋“  ์•ฝ๋“ค์˜ ์ž‘์šฉ ์‚ฌ๋ก€๋ฅผ ๋ชจ์€ ํ›„,
03:28
and said, "What's the difference in their side effects?
72
208969
2888
์ƒ๊ฐํ–ˆ์Šต๋‹ˆ๋‹ค. "์ด ์•ฝ๋“ค์˜ ๋ถ€์ž‘์šฉ์˜ ์ฐจ์ด์ ์€ ๋ฌด์—‡์ผ๊นŒ?"
03:31
Differences in fatigue? In appetite? In urination habits?"
73
211881
4852
ํ”ผ๋กœ?, ์‹์š•?, ๋ฐฐ๋‡จ ์Šต๊ด€?์— ๋”ฐ๋ฅธ ์ฐจ์ด์ ์ธ๊ฐ€?
03:36
All those things conspired to give him a really good predictor.
74
216757
2960
์ด ๋ชจ๋“  ๊ฒƒ๋“ค์ด ๋ชจ์—ฌ์„œ ๊ทธ์—๊ฒŒ ์ •๋ง ์ข‹์€ ์˜ˆ์ธก๋ณ€์ˆ˜๊ฐ€ ๋์ฃ .
03:39
He said, "Russ, I can predict with 93 percent accuracy
75
219741
2548
๊ทธ๋Š” ๋งํ–ˆ์ฃ , "๋Ÿฌ์Šค, ์ €๋Š” 93%์˜ ์ •ํ™•์„ฑ์œผ๋กœ
03:42
when a drug will change glucose."
76
222313
1572
์•ฝ์ด ์–ธ์ œ ํฌ๋„๋‹น์œผ๋กœ ๋ณ€ํ•˜๋Š”์ง€ ์˜ˆ์ธกํ•  ์ˆ˜ ์žˆ์–ด์š”."
03:43
I said, "Nick, that's great."
77
223909
1416
์ €๋Š” ๋งํ–ˆ์ฃ , "๋‹‰, ๊ทธ๊ฑฐ ๋Œ€๋‹จํ•œ๋ฐ."
03:45
He's a young student, you have to build his confidence.
78
225349
2896
๊ทธ๋Š” ์–ด๋ฆฐ ํ•™์ƒ์ด๊ณ , ๊ทธ์˜ ์ž์‹ ๊ฐ์„ ํ‚ค์›Œ์ค˜์•ผ ํ–ˆ์–ด์š”.
03:48
"But Nick, there's a problem.
79
228269
1390
"ํ•˜์ง€๋งŒ ๋‹‰, ๋ฌธ์ œ๊ฐ€ ์žˆ๋‹จ๋‹ค.
03:49
It's that every physician in the world knows all the drugs that change glucose,
80
229683
3960
์ด ์„ธ์ƒ์˜ ๋ชจ๋“  ์˜์‚ฌ๋Š” ์•ฝ์ด ํฌ๋„๋‹น์œผ๋กœ ๋ณ€ํ•œ๋‹ค๋Š” ์‚ฌ์‹ค์„ ์•Œ์ง€.
03:53
because it's core to our practice.
81
233667
2038
๊ทธ๊ฑธ ์•„๋Š”๊ฒŒ ์˜์‚ฌ๋กœ์„œ์˜ ์ง„๋ฃŒ์˜ ํ•ต์‹ฌ์ด๋‹ˆ๊นŒ.
03:55
So it's great, good job, but not really that interesting,
82
235729
3722
๊ทธ๋ž˜์„œ ๋Œ€๋‹จํ•˜๊ณ , ์ž˜ํ–ˆ์ง€๋งŒ, ์ •๋ง๋กœ ํฅ๋ฏธ๋กญ์ง€ ์•Š๋‹จ๋‹ค.
03:59
definitely not publishable."
83
239475
1531
์ ˆ๋Œ€ ๋…ผ๋ฌธ์œผ๋กœ ๋‚ผ ์ˆ˜ ์—†๋‹ค๋Š”๊ฑฐ์ง€."
04:01
(Laughter)
84
241030
1014
(์›ƒ์Œ)
04:02
He said, "I know, Russ. I thought you might say that."
85
242068
2550
๊ทธ๊ฐ€ ๋งํ–ˆ์ฃ , "์•Œ์•„์š”, ๋Ÿฌ์Šค. ๊ทธ๋ ‡๊ฒŒ ๋งํ•  ๊ฑฐ๋ผ๊ณ  ์ƒ๊ฐํ–ˆ์–ด์š”."
04:04
Nick is smart.
86
244642
1152
๋‹‰์€ ๋˜‘๋˜‘ํ–ˆ์–ด์š”.
04:06
"I thought you might say that, so I did one other experiment.
87
246149
2874
"๊ทธ๋ ‡๊ฒŒ ๋งํ•˜์‹ค ์ค„ ์•Œ๊ณ , ๋‹ค๋ฅธ ์‹คํ—˜ ํ•˜๋‚˜๋ฅผ ๋” ํ–ˆ์–ด์š”.
04:09
I looked at people in this database who were on two drugs,
88
249047
2928
์ €๋Š” ๋‘ ์ข…๋ฅ˜์˜ ์•ฝ์„ ๋ณต์šฉํ•˜๋Š” ์‚ฌ๋žŒ๋“ค์„ ์ฐพ์•„๋ดค์–ด์š”.
04:11
and I looked for signals similar, glucose-changing signals,
89
251999
4422
๊ทธ๋ฆฌ๊ณ  ๊ทธ ์ค‘์—์„œ ํฌ๋„๋‹น ๋ณ€ํ™”์™€ ๋น„์Šทํ•œ ์ฆ์ƒ์„ ๋ณด์ด๋Š” ๊ฒƒ๋“ค์„ ์ฐพ์•„๋ดค์ฃ .
04:16
for people taking two drugs,
90
256445
1624
๋‘ ์•ฝ์„ ๋จน๋Š” ์‚ฌ๋žŒ๋“ค ์ค‘์—
04:18
where each drug alone did not change glucose,
91
258093
5569
๊ฐ๊ฐ์˜ ์•ฝ์ด ํฌ๋„๋‹น์„ ๋ณ€ํ™”์‹œํ‚ค์ง€ ์•Š์Œ์—๋„ ๋ถˆ๊ตฌํ•˜๊ณ 
04:23
but together I saw a strong signal."
92
263686
2460
๊ฐ™์ด ๋จน์œผ๋‹ˆ ์•„์ฃผ ๊ฐ•ํ•œ ๋ฐ˜์‘์„ ๋ดค์–ด์š”."
04:26
And I said, "Oh! You're clever. Good idea. Show me the list."
93
266170
3149
์ €๋Š” ๋งํ–ˆ์ฃ . "์˜ค! ๋˜‘๋˜‘ํ•˜๊ตฌ๋‚˜. ์ข‹์€ ์ƒ๊ฐ์ด์•ผ. ๊ทธ ๋ฆฌ์ŠคํŠธ ์ข€ ๋ณด์—ฌ์ค˜."
04:29
And there's a bunch of drugs, not very exciting.
94
269343
2254
์—ฌ๋Ÿฌ ์ข…๋ฅ˜์˜ ์•ฝ๋ฌผ๋“ค์ด ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค. ๋”ฑํžˆ ํฅ๋ฏธ๋กญ์ง„ ์•Š์•˜์ฃ .
04:31
But what caught my eye was, on the list there were two drugs:
95
271621
3932
ํ•˜์ง€๋งŒ ๊ทธ ๋ชฉ๋ก์—์„œ ์ œ ๋ˆˆ์„ ์‚ฌ๋กœ์žก์€ ๋‘๊ฐœ์˜ ์•ฝ๋ฌผ์ด ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
04:35
paroxetine, or Paxil, an antidepressant;
96
275577
3393
ํŒŒ๋ก์„ธํ‹ด, ํ˜น์€ ํŒ์‹ค,ํ•ญ์šฐ์šธ์ œ์™€
04:39
and pravastatin, or Pravachol, a cholesterol medication.
97
279756
3570
ํ”„๋ผ๋ฐ”์Šคํƒœํ‹ด, ํ˜น์€ ํ”„๋ผ๋ฐ”์ฝœ, ์ฝœ๋ ˆ์Šคํ…Œ๋กค ์น˜๋ฃŒ์ œ์˜€์Šต๋‹ˆ๋‹ค.
04:43
And I said, "Huh. There are millions of Americans on those two drugs."
98
283936
4283
์ „ ๋งํ–ˆ์ฃ . "์–ด, ์ด ๋‘˜์€ ์ˆ˜๋ฐฑ๋งŒ์˜ ๋ฏธ๊ตญ์ธ์ด ๋จน๊ณ  ์žˆ๋Š” ์•ฝ์ด๋„ค."
04:48
In fact, we learned later,
99
288243
1246
์‚ฌ์‹ค ๋‚˜์ค‘์— ์•Œ๊ฒŒ ๋œ ์‚ฌ์‹ค์ด์ง€๋งŒ
04:49
15 million Americans on paroxetine at the time, 15 million on pravastatin,
100
289513
6032
ํŒŒ๋ก์„ธํ‹ด๊ณผ ํ”„๋ผ๋ฐ”์Šคํƒœํ‹ด์€ ๋‹น์‹œ ๊ฐ๊ฐ 1500๋งŒ์˜ ๋ฏธ๊ตญ์ธ,
04:55
and a million, we estimated, on both.
101
295569
2817
๊ทธ๋ฆฌ๊ณ  100๋งŒ๋ช…์ด,์šฐ๋ฆฌ๊ฐ€ ์ถ”์ •ํ–ˆ์„๋•Œ. ๋‘˜ ๋‹ค ๋จน์—ˆ์ฃ .
04:58
So that's a million people
102
298767
1254
์ฆ‰ 100๋งŒ ๋ช…์˜ ์‚ฌ๋žŒ๋“ค์ด
05:00
who might be having some problems with their glucose
103
300045
2453
ํฌ๋„๋‹น์— ๋ฌธ์ œ๊ฐ€ ์žˆ๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
05:02
if this machine-learning mumbo jumbo that he did in the FDA database
104
302522
3206
FDA ๋ณด๊ณ ๋ฅผ ์ด์šฉํ•ด์„œ ๋‹‰์ด ๊ทธ๋Ÿด์‹ธํ•˜๊ฒŒ ๋งŒ๋“ค์–ด๋‚ธ
05:05
actually holds up.
105
305752
1254
๋จธ์‹ ๋Ÿฌ๋‹์— ๋”ฐ๋ฅด๋ฉด ๋ง์ด์ฃ .
05:07
But I said, "It's still not publishable,
106
307030
1927
ํ•˜์ง€๋งŒ ์ €๋Š” ๋งํ–ˆ์Šต๋‹ˆ๋‹ค. "์•„์ง ๋…ผ๋ฌธ์œผ๋กœ ๋‚ผ ์ˆ˜๋Š” ์—†์–ด.
05:08
because I love what you did with the mumbo jumbo,
107
308981
2296
๋„ˆ๊ฐ€ ์ด๋Ÿฐ ์˜ˆ์ธก๊ธฐ๋ฅผ ์ด์šฉํ•ด์„œ ๋งŒ๋“ค์–ด ๋‚ธ ์˜ˆ์ธก์„
05:11
with the machine learning,
108
311301
1246
๋‚˜๋Š” ๊ฐœ์ธ์ ์œผ๋กœ ์ฐธ ๋งˆ์Œ์— ๋“ค์ง€๋งŒ
05:12
but it's not really standard-of-proof evidence that we have."
109
312571
3864
์šฐ๋ฆฌ๊ฐ€ ๊ฐ€์ง€๊ณ  ์žˆ๋Š” ์ฆ๊ฑฐ๋Š” ์‚ฌ์‹ค ์ž…์ฆํ• ๋งŒ ์ฆ๊ฑฐ๊ฐ€ ๋˜์ง€ ๋ชปํ•ด"
05:17
So we have to do something else.
110
317618
1589
๊ทธ๋ž˜์„œ ์šฐ๋ฆฌ๋Š” ๋ญ”๊ฐ€ ๋‹ค๋ฅธ ๊ฒƒ์„ ํ•ด์•ผ ํ–ˆ์Šต๋‹ˆ๋‹ค.
05:19
Let's go into the Stanford electronic medical record.
111
319231
2876
์Šคํƒ ํฌ๋“œ์˜ ์ „์ž ์˜๋ฌด๊ธฐ๋ก์„ ์ด์šฉํ•˜๊ธฐ๋กœ ํ–ˆ์ฃ .
05:22
We have a copy of it that's OK for research,
112
322131
2064
์กฐ์‚ฌ์— ์ด์šฉํ•ด๋„ ๊ดœ์ฐฎ์€ ๊ธฐ๋ก๋“ค์„ ๋ณต์‚ฌํ–ˆ์Šต๋‹ˆ๋‹ค.
05:24
we removed identifying information.
113
324219
2046
๋ฌผ๋ก  ๊ฐœ์ธ ์ •๋ณด๋“ค์€ ์‚ญ์ œํ–ˆ์ฃ .
05:26
And I said, "Let's see if people on these two drugs
114
326581
2503
๊ทธ๋ฆฌ๊ณ  ์ €๋Š” ๋งํ–ˆ์ฃ . "์ด ๋‘ ์•ฝ์„ ๊ฐ™์ด ๋ณต์šฉํ•œ ์‚ฌ๋žŒ๋“ค์˜
05:29
have problems with their glucose."
115
329108
1769
ํฌ๋„๋‹น์— ๋ฌธ์ œ๊ฐ€ ์žˆ๋Š”์ง€ ์กฐ์‚ฌํ•ด ๋ณด์ž."
05:31
Now there are thousands and thousands of people
116
331242
2207
๊ธฐ๋ก ์•ˆ์—๋Š” ์ˆ˜์ฒœ๋งŒ ๊ทธ๋ฆฌ๊ณ  ์ˆ˜์ฒœ๋งŒ ๋ช…์˜ ์‚ฌ๋žŒ๋“ค์ด
05:33
in the Stanford medical records that take paroxetine and pravastatin.
117
333473
3459
ํŒŒ๋ก์„ธํ‹ด๊ณผ ํ”„๋ผ๋ฐ”์Šคํƒ€ํ‹ด์„ ๋ณต์šฉํ•œ ์‚ฌ๋žŒ๋“ค์ด ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
05:36
But we needed special patients.
118
336956
1799
๊ทธ๋Ÿฌ๋‚˜ ์šฐ๋ฆฌ๋Š” ํŠน๋ณ„ํ•œ ํ™˜์ž๋“ค์ด ํ•„์š”ํ–ˆ์Šต๋‹ˆ๋‹ค.
05:38
We needed patients who were on one of them and had a glucose measurement,
119
338779
4597
๋‘ ์•ฝ ์ค‘์— ํ•˜๋‚˜๋ฅผ ๋ณต์šฉํ•œ ๋’ค ํฌ๋„๋‹น ๊ฒ€์‚ฌ๋ฅผ ๋ฐ›๊ณ 
05:43
then got the second one and had another glucose measurement,
120
343400
3449
๊ทธ ๋‹ค์Œ์— ๋‘๋ฒˆ์งธ ์•ฝ์„ ๋ณต์šฉํ•œ ํ›„, ๋‹ค๋ฅธ ํฌ๋„๋‹น ๊ฒ€์‚ฌ๋ฅผ ๋ฐ›๊ณ 
05:46
all within a reasonable period of time -- something like two months.
121
346873
3615
๋‘ ๊ฒ€์‚ฌ๋ฅผ ์ผ์ • ์‹œ๊ฐ„, ์˜ˆ๋ฅผ ๋“ค์–ด 2๋‹ฌ ์‚ฌ์ด์— ๋ฐ›์€ ์‚ฌ๋žŒ๋“ค๋ง์ด์ฃ .
05:50
And when we did that, we found 10 patients.
122
350512
3159
์ด ๊ธฐ์ค€์„ ์ ์šฉํ–ˆ์„ ๋•Œ ์šฐ๋ฆฐ 10๋ช…์˜ ํ™˜์ž๋ฅผ ๋ฐœ๊ฒฌํ–ˆ์Šต๋‹ˆ๋‹ค.
05:54
However, eight out of the 10 had a bump in their glucose
123
354592
4538
๊ทธ๋Ÿฐ๋ฐ 10๋ช…์ค‘ 8๋ช…์˜ ํฌ๋„๋‹น ์ˆ˜์น˜๊ฐ€ ์˜ฌ๋ผ๊ฐ”์Šต๋‹ˆ๋‹ค.
05:59
when they got the second P -- we call this P and P --
124
359154
2645
๋‘ ๋ฒˆ์งธ p๋ฅผ ๋ณต์šฉํ–ˆ์„ ๋•Œ ๋ง์ž…๋‹ˆ๋‹ค. ์šฐ๋ฆฌ๋Š” ์ด๊ฒƒ์„ P์™€ P๋กœ ๋ถ€๋ฆ…์‹œ๋‹ค.
06:01
when they got the second P.
125
361823
1310
๋‘ ๋ฒˆ์งธ P๋ฅผ ๋ณต์šฉํ–ˆ์„ ๋•Œ๋ง์ด์ฃ .
06:03
Either one could be first, the second one comes up,
126
363157
2562
์–ด๋Š ์•ฝ์„ ๋จผ์ € ๋จน๋“  ๋‘ ๋ฒˆ์งธ ์•ฝ์„ ๋ณต์šฉํ–ˆ์„ ๋•Œ
06:05
glucose went up 20 milligrams per deciliter.
127
365743
2847
ํฌ๋„๋‹น ์ˆ˜์น˜๊ฐ€ 20mg/dl ๊ฐ€ ์˜ฌ๋ผ๊ฐ”์Šต๋‹ˆ๋‹ค.
06:08
Just as a reminder,
128
368614
1158
๋‹ค์‹œ ์ƒ๊ธฐํ•ด๋ณด์ž๋ฉด
06:09
you walk around normally, if you're not diabetic,
129
369796
2325
๋‹น๋‡จ๋ณ‘ ํ™˜์ž๊ฐ€ ์•„๋‹Œ ์ด์ƒ ํ‰์ƒ์‹œ์ฒ˜๋Ÿผ ๊ฑธ์œผ๋ฉด
06:12
with a glucose of around 90.
130
372145
1359
90์ •๋„์˜ ํฌ๋„๋‹น ์ˆ˜์น˜๊ฐ€ ๋‚˜์˜ต๋‹ˆ๋‹ค.
06:13
And if it gets up to 120, 125,
131
373528
2076
๊ทธ๋ž˜์„œ ์ˆ˜์น˜๊ฐ€ 120์ด๋‚˜ 125๊นŒ์ง€ ์ƒ์Šนํ•œ๋‹ค๋ฉด
06:15
your doctor begins to think about a potential diagnosis of diabetes.
132
375628
3450
์˜์‚ฌ๋Š” ๊ทธ๊ฒƒ์„ ๋‹น๋‡จ์˜ ์ง•ํ›„๋กœ ์ƒ๊ฐํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:19
So a 20 bump -- pretty significant.
133
379102
2991
๊ทธ๋Ÿฌ๋ฏ€๋กœ 20์˜ ์ƒ์Šน์€ -- ๊ฝค ์ค‘์š”ํ•ฉ๋‹ˆ๋‹ค.
06:22
I said, "Nick, this is very cool.
134
382601
1904
์ „ ๋งํ–ˆ์Šต๋‹ˆ๋‹ค. "๋‹‰, ์•„์ฃผ ํ›Œ๋ฅญํ•ด.
06:25
But, I'm sorry, we still don't have a paper,
135
385616
2053
ํ•˜์ง€๋งŒ ๋ฏธ์•ˆ. ์•„์ง๋„ ์šฐ๋ฆฐ ๋…ผ๋ฌธ์„ ๋ฐœํ‘œํ•  ์ˆ˜ ์—†์–ด.
06:27
because this is 10 patients and -- give me a break --
136
387693
2579
์™œ๋ƒ๋ฉด 10๋ช…์˜ ํ™˜์ž๋Š” ๊ทธ๋ฆฌ๊ณ --์ž ์‹œ๋งŒ์š”--
06:30
it's not enough patients."
137
390296
1245
๋„ˆ๋ฌด ์ ์€ ์ˆ˜๊ฑฐ๋“ ."
06:31
So we said, what can we do?
138
391565
1306
์šฐ๋ฆฐ ์–ด๋–ป๊ฒŒ ํ•˜์ง€?๋ผ๊ณ  ๋งํ–ˆ์ฃ .
06:32
And we said, let's call our friends at Harvard and Vanderbilt,
139
392895
2976
๊ทธ๋ฆฌ๊ณ  ์šฐ๋ฆฌ๋Š” ๋งํ–ˆ์ฃ . ํ•˜๋ฒ„๋“œ์™€ ๋ฐ˜๋”๋นŒํŠธ์— ์žˆ๋Š” ์นœ๊ตฌ์—๊ฒŒ ์—ฐ๋ฝํ•ด๋ณด์ž.
06:35
who also -- Harvard in Boston, Vanderbilt in Nashville,
140
395895
2587
๋ณด์Šคํ„ด์˜ ํ•˜๋ฒ„๋“œ, ๋‚ด์‰ฌ๋นŒ์˜ ๋ฐ˜๋”๋นŒํŠธ ๊ทธ ๋Œ€ํ•™๋“ค๋„
06:38
who also have electronic medical records similar to ours.
141
398506
2821
์šฐ๋ฆฌ๋ž‘ ๋น„์Šทํ•œ ์˜๋ฌด๊ธฐ๋ก์ด ์žˆ์œผ๋‹ˆ๊นŒ.
06:41
Let's see if they can find similar patients
142
401351
2020
๊ทธ๋“ค์ด ํ•˜๋‚˜์˜ P์™€ ๋˜ ๋‹ค๋ฅธ P๋ฅผ ๋ณต์šฉํ•˜๊ณ 
06:43
with the one P, the other P, the glucose measurements
143
403395
3276
ํฌ๋„๋‹น ๊ฒ€์‚ฌ๋ฅผ ๋ฐ›์€ ํ™˜์ž๋“ค์„ ์šฐ๋ฆฌ์˜ ๊ธฐ์ค€์— ๋งž์ถฐ์„œ
06:46
in that range that we need.
144
406695
1600
์ฐพ์„ ์ˆ˜ ์žˆ๋Š”์ง€ ๋ณด๋ ค๊ณ  ํ–ˆ์ฃ .
06:48
God bless them, Vanderbilt in one week found 40 such patients,
145
408787
4955
์šด์ด ์ข‹๊ฒŒ๋„, 1์ฃผ์ผ๋™์•ˆ ๋ฐ˜๋”๋นŒํŠธ ๊ธฐ๋ก์—์„œ๋Š”
๊ฐ™์€ ๊ฒฝํ–ฅ์˜ ํ™˜์ž 40๋ช…์„ ์ฐพ์•˜์Šต๋‹ˆ๋‹ค.
06:53
same trend.
146
413766
1189
06:55
Harvard found 100 patients, same trend.
147
415804
3620
ํ•˜๋ฒ„๋“œ์—์„œ๋Š” 100๋ช…์˜ ํ™˜์ž๋“ค์„ ์ฐพ์•˜์Šต๋‹ˆ๋‹ค. ๊ฐ™์€ ๊ฒฝํ–ฅ์ด์ฃ .
06:59
So at the end, we had 150 patients from three diverse medical centers
148
419448
4281
๊ฒฐ๊ตญ ์šฐ๋ฆฌ๋Š” ์„ธ ๊ฐœ์˜ ๋Œ€ํ•™๋ณ‘์›์—์„œ 150๋ช…์˜ ํ™˜์ž๋“ค์„ ์ฐพ์•„๋‚ผ ์ˆ˜ ์žˆ์—ˆ๊ณ 
07:03
that were telling us that patients getting these two drugs
149
423753
3297
๊ทธ ๊ธฐ๋ก๋“ค์ด ์šฐ๋ฆฌ์—๊ฒŒ ๋งํ•ด์ค€ ๊ฒƒ์€ ์ด๋Ÿฌํ•œ ๋‘ ๊ฐœ์˜ ์•ฝ์„ ๋ณต์šฉํ•œ ํ™˜์ž๋“ค์˜
07:07
were having their glucose bump somewhat significantly.
150
427074
2703
ํฌ๋„๋‹น ์ˆ˜์น˜๊ฐ€ ์–ด๋Š์ •๋„ ์ƒ๋‹นํžˆ ์˜ฌ๋ผ๊ฐ”๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:10
More interestingly, we had left out diabetics,
151
430317
2810
๋” ํฅ๋ฏธ๋กœ์šด ์ ์€ ์ €ํฌ๊ฐ€ ๋‹น๋‡จ๋ณ‘ํ™˜์ž๋ฅผ ์ œ์™ธํ•ด๋‘์—ˆ๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:13
because diabetics already have messed up glucose.
152
433151
2317
์™œ๋ƒ๋ฉด ์ด๋ฏธ ๋‹น๋‡จ๋ณ‘ ํ™˜์ž๋“ค์€ ํฌ๋„๋‹น์ด ์—‰๋ง์ด ๋˜์—ˆ๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
07:15
When we looked at the glucose of diabetics,
153
435492
2238
์ €ํฌ๊ฐ€ ๋‹น๋‡จํ™˜์ž์˜ ํฌ๋„๋‹น ์ˆ˜์น˜๋ฅผ ๋ดค์„ ๋•Œ
07:17
it was going up 60 milligrams per deciliter, not just 20.
154
437754
3435
20๋ณด๋‹ค ๋”ํ•œ 60mg/dl ์˜ ์ƒ์Šน์„ ๋ณด์˜€์Šต๋‹ˆ๋‹ค.
07:21
This was a big deal, and we said, "We've got to publish this."
155
441760
3452
์ด๊ฑด ์ค‘์š”ํ•œ ์ผ์ด์—ˆ๊ณ  ์šฐ๋ฆฌ๋Š” "์šฐ๋ฆฌ๋Š” ์ด๊ฑธ ๋…ผ๋ฌธ์œผ๋กœ ๋‚ด์ž."๋ผ๊ณ  ๋งํ–ˆ์ฃ .
07:25
We submitted the paper.
156
445236
1179
์šฐ๋ฆฌ๋Š” ํ•™์ˆ ์ง€์— ๋…ผ๋ฌธ์„ ์ œ์ถœํ–ˆ์ฃ .
07:26
It was all data evidence,
157
446439
2111
์ „๋ถ€ ๋ฐ์ดํ„ฐ ์ฆ๊ฑฐ์˜€์ฃ .
07:28
data from the FDA, data from Stanford,
158
448574
2483
FDA, ์Šคํƒ ํฌ๋“œ
07:31
data from Vanderbilt, data from Harvard.
159
451081
1946
๋ฐ˜๋”๋นŒํŠธ, ๊ทธ๋ฆฌ๊ณ  ํ•˜๋ฒ„๋“œ์—์„œ ๊ฐ€์ ธ์˜จ ๋ฐ์ดํ„ฐ๋“ค์ด์—ˆ์ฃ .
07:33
We had not done a single real experiment.
160
453051
2396
์šฐ๋ฆฌ๋Š” ์‹ค์ œ ์‹คํ—˜์€ ํ•˜๋‚˜๋„ ํ•˜์ง€ ์•Š์•˜์—ˆ์ฃ .
07:36
But we were nervous.
161
456495
1296
ํ•˜์ง€๋งŒ ์šฐ๋ฆฌ๋Š” ๋ถˆ์•ˆํ–ˆ์Šต๋‹ˆ๋‹ค.
07:38
So Nick, while the paper was in review, went to the lab.
162
458201
3730
๋…ผ๋ฌธ์ด ๊ฒ€ํ† ๋˜๋Š” ๋™์•ˆ, ๋‹‰์€ ์‹คํ—˜์‹ค๋กœ ํ–ฅํ–ˆ์Šต๋‹ˆ๋‹ค.
07:41
We found somebody who knew about lab stuff.
163
461955
2462
์‹คํ—˜์„ ์ž˜ ์•„๋Š” ๋ˆ„๊ตฐ๊ฐ€๋ฅผ ์ฐพ์•„๋ƒˆ์ฃ .
07:44
I don't do that.
164
464441
1393
์ „ ์‹คํ—˜์„ ํ•˜์ง€๋Š” ์•Š์ฃ .
07:45
I take care of patients, but I don't do pipettes.
165
465858
2417
ํ™˜์ž๋Š” ๋Œ๋ณด์ง€๋งŒ, ํ”ผํŽซ์€ ๋‹ค๋ฃจ์ง€ ์•Š์ฃ .
07:49
They taught us how to feed mice drugs.
166
469420
3053
์‹คํ—˜์‹ค ์‚ฌ๋žŒ๋“ค์€ ์ €ํฌ์—๊ฒŒ ์ฅ์—๊ฒŒ ์•ฝ์„ ๋จน์ด๋Š” ๋ฒ•์„ ์•Œ๋ ค์คฌ์Šต๋‹ˆ๋‹ค.
07:52
We took mice and we gave them one P, paroxetine.
167
472864
2414
์ €ํฐ ์ฅ๋“ค์—๊ฒŒ ํ•˜๋‚˜์˜ ์•ฝ (P) ํŒŒ๋ก์„ธํ‹ด์„ ํˆฌ์—ฌํ–ˆ์ฃ .
07:55
We gave some other mice pravastatin.
168
475302
2508
๋‹ค๋ฅธ ์ฅ๋“ค์—๊ฒ ํ”„๋ผ๋ฐ”์Šคํƒœํ‹ด์„ ํˆฌ์—ฌํ–ˆ์Šต๋‹ˆ๋‹ค.
07:57
And we gave a third group of mice both of them.
169
477834
3595
๊ทธ๋ฆฌ๊ณ  ์„ธ ๋ฒˆ์งธ ๊ทธ๋ฃน์—๋Š” ๋‘ ์•ฝ์„ ๋™์‹œ์— ํˆฌ์—ฌํ–ˆ์Šต๋‹ˆ๋‹ค.
08:01
And lo and behold, glucose went up 20 to 60 milligrams per deciliter
170
481893
3946
๋†€๋ž๊ฒŒ๋„, ์ฅ๋“ค์˜ ํฌ๋„๋‹น ์ˆ˜์น˜๋Š” 20์—์„œ 60๊นŒ์ง€ ์ƒ์Šนํ–ˆ์Šต๋‹ˆ๋‹ค.
08:05
in the mice.
171
485863
1171
08:07
So the paper was accepted based on the informatics evidence alone,
172
487058
3158
๋…ผ๋ฌธ์€ ๋ฐ์ดํ„ฐ ์ฆ๊ฑฐ๋“ค๋งŒ์œผ๋กœ ์ถœํŒ์ด ๋˜์—ˆ์ง€๋งŒ,
08:10
but we added a little note at the end,
173
490240
1894
์ €ํฌ๋Š” ๋’ค์— ์กฐ๊ธˆ ๋” ๋‚ด์šฉ์„ ๋ถ™์˜€์Šต๋‹ˆ๋‹ค.
08:12
saying, oh by the way, if you give these to mice, it goes up.
174
492158
2899
์ฅ ์‹คํ—˜์—์„œ๋„ ๋น„์Šทํ•œ ๋‚ด์šฉ์ด ๋‚˜์™”๋‹ค๋Š” ์‹์œผ๋กœ ๋ง์ด์ฃ .
08:15
That was great, and the story could have ended there.
175
495081
2508
ํ›Œ๋ฅญํ•œ ๋…ผ๋ฌธ์ด์—ˆ๊ณ , ์ €ํฌ์˜ ์ด์•ผ๊ธฐ๋Š” ์—ฌ๊ธฐ์„œ ๋๋‚  ์ˆ˜๋„ ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
08:17
But I still have six and a half minutes.
176
497613
1997
ํ•˜์ง€๋งŒ ์ €์—๊ฒŒ ์•„์ง๋„ 6๋ถ„ 30์ดˆ๊ฐ€ ๋” ๋‚จ์•˜์ฃ .
08:19
(Laughter)
177
499634
2807
(์›ƒ์Œ)
08:22
So we were sitting around thinking about all of this,
178
502465
2815
๊ทธ๋ž˜์„œ ์šฐ๋ฆฌ๋Š” ์•‰์•„์„œ ์ด ๋ชจ๋“  ๊ฒƒ๋“ค์— ๋Œ€ํ•ด ์ƒ๊ฐํ–ˆ์ฃ .
08:25
and I don't remember who thought of it, but somebody said,
179
505304
2735
๋ˆ„๊ตฐ์ง€๋Š” ๊ธฐ์–ต ์•ˆ๋‚˜์ง€๋งŒ, ๋ˆ„๊ตฐ๊ฐ€ ๋งํ•˜๊ธธ.
08:28
"I wonder if patients who are taking these two drugs
180
508063
3201
"๋‘ ์•ฝ์„ ๋™์‹œ์— ๋จน์—ˆ๋˜ ํ™˜์ž๋“ค์ด
08:31
are noticing side effects of hyperglycemia.
181
511288
3553
๊ณ ํ˜ˆ๋‹น๊ฐ™์€ ๋ˆˆ์— ๋„๋Š” ๋ถ€์ž‘์šฉ์„ ๊ฒช์—ˆ๋Š”์ง€ ๊ถ๊ธˆํ•˜๋„ค์š”."
08:34
They could and they should.
182
514865
1496
๊ฐ€๋Šฅํ•œ ์ผ์ด์—ˆ๊ณ , ์‚ฌ์‹ค ๊ทธ๋“ค์ด ๊ฒช์—ˆ์–ด์•ผ ํ•˜๋Š” ์ผ์ด์—ˆ์ฃ .
08:36
How would we ever determine that?"
183
516761
1877
ํ•˜์ง€๋งŒ ์šฐ๋ฆฌ๊ฐ€ ๊ทธ๊ฑธ ์–ด๋–ป๊ฒŒ ์ฐพ์•„๋‚ผ ์ˆ˜ ์žˆ์„๊นŒ?
08:39
We said, well, what do you do?
184
519551
1443
์šฐ๋ฆฌ๋Š” ๊ธ€์Ž„, ๋„ˆ๋ผ๋ฉด ๋ญ˜ ํ–ˆ์„๊นŒ? ๋ผ๊ณ  ๋งํ–ˆ์ฃ .
08:41
You're taking a medication, one new medication or two,
185
521018
2580
๋„ˆ๊ฐ€ ์ƒˆ๋กœ์šด ์•ฝ ํ•˜๋‚˜ ํ˜น์€ ๋‘๊ฐœ๋ฅผ ๋จน๊ธฐ ์‹œ์ž‘ํ–ˆ๋Š”๋ฐ
08:43
and you get a funny feeling.
186
523622
1538
๋ชธ์ด ๋ญ”๊ฐ€ ์ด์ƒํ•œ ๋Š๋‚Œ์ด ๋“ค๊ธฐ ์‹œ์ž‘ํ–ˆ์–ด.
08:45
What do you do?
187
525184
1151
๋„ˆ๋ผ๋ฉด ๋ญ˜ ํ•  ๊ฑฐ ๊ฐ™์•„?
08:46
You go to Google
188
526359
1151
๊ตฌ๊ธ€์— ๋“ค์–ด๊ฐ€์„œ
08:47
and type in the two drugs you're taking or the one drug you're taking,
189
527534
3349
๋„ˆ๊ฐ€ ๋จน๋Š” ์•ฝ ํ•œ ๊ฐœ ํ˜น์€ ๋‘ ๊ฐœ๋ฅผ ๊ฒ€์ƒ‰ํ•œ ๋‹ค์Œ
08:50
and you type in "side effects."
190
530907
1603
"๋ถ€์ž‘์šฉ"์ด๋ผ๊ณ  ์ž…๋ ฅํ•˜์ง€ ์•Š์•˜์„๊นŒ.
08:52
What are you experiencing?
191
532534
1356
๊ฒ€์ƒ‰ํ•˜๋ฉด ๋ฌด์—‡์ด ๋‚˜์˜ฌ๊นŒ?
08:54
So we said OK,
192
534239
1151
๊ทธ๋ž˜์„œ ์šฐ๋ฆฌ๋Š” ์•Œ๊ฒ ๋‹ค.
08:55
let's ask Google if they will share their search logs with us,
193
535414
3056
๊ตฌ๊ธ€์— ์—ฐ๋ฝํ•ด ๊ทธ๋“ค์˜ ๊ฒ€์ƒ‰ ๊ธฐ๋ก์„ ๊ณต์œ ํ•  ์ˆ˜ ์žˆ๋ƒ๊ณ  ๋ฌผ์–ด๋ดค์ฃ .
08:58
so that we can look at the search logs
194
538494
1833
๊ฒ€์ƒ‰์„ ๊ธฐ๋ก์„ ๋ณด๊ณ 
09:00
and see if patients are doing these kinds of searches.
195
540351
2565
ํ™˜์ž๋“ค์ด ์ •๋ง๋กœ ๊ทธ๋Ÿฐ ๊ฒ€์ƒ‰์„ ํ–ˆ๋Š”์ง€ ์•Œ์•„๋ณด๊ธฐ ์œ„ํ•ด์„œ์˜€์ฃ .
09:02
Google, I am sorry to say, denied our request.
196
542940
3275
ํ•˜์ง€๋งŒ, ์ด๋Ÿฐ ๋ง์„ ํ•ด์„œ ์œ ๊ฐ์ด์ง€๋งŒ ์šฐ๋ฆฌ์˜ ์š”์ฒญ์„ ๊ฑฐ์ ˆํ–ˆ์ฃ .
09:06
So I was bummed.
197
546819
1151
์ €๋Š” ๋ฒฝ์— ๋ถ€๋”ช์นœ ๋Š๋‚Œ์ด์—ˆ์ฃ .
09:07
I was at a dinner with a colleague who works at Microsoft Research
198
547994
3166
์–ด๋Š ๋‚ , ์ €๋Š” ๋งˆ์ดํฌ๋กœ์†Œํ”„ํŠธ์—์„œ ์ผํ•˜๋Š” ๋™๋ฃŒ์™€ ์ €๋…์„ ๋จน์—ˆ์Šต๋‹ˆ๋‹ค.
09:11
and I said, "We wanted to do this study,
199
551184
1941
์ „ ๋งํ–ˆ์ฃ . "์šฐ๋ฆฐ ์ด ์—ฐ๊ตฌ๋ฅผ ๊ผญ ํ•˜๊ณ ์‹ถ์–ด."
09:13
Google said no, it's kind of a bummer."
200
553149
1880
"๊ทผ๋ฐ ๊ตฌ๊ธ€์€ ํ˜‘์กฐ๋ฅผ ์•ˆ ํ•ด์ฃผ๊ณ , ๋‚˜์—๊ฒ ๋ฐฉ๋ฒ•์ด ์—†์–ด."
09:15
He said, "Well, we have the Bing searches."
201
555053
2086
๊ทธ๋Š” ๋งํ–ˆ์ฃ . "๊ทธ๋Ÿฌ๋ฉด. ์šฐ๋ฆฌ์—๊ฒŒ ๋น™ ๊ฒ€์ƒ‰ ๊ธฐ๋ก์ด ์žˆ๋Š”๋ฐ?"
09:18
(Laughter)
202
558195
3483
(์›ƒ์Œ)
09:22
Yeah.
203
562805
1267
์˜ค.
09:24
That's great.
204
564096
1151
๊ทธ๊ฑฐ ์ข‹๋„ค.
09:25
Now I felt like I was --
205
565271
1151
๊ทธ ๋•Œ ์ €๋Š” ์ •๋ง...
09:26
(Laughter)
206
566446
1000
(์›ƒ์Œ)
09:27
I felt like I was talking to Nick again.
207
567470
2412
๋‹‰ํ•˜๊ณ  ๋‹ค์‹œ ์ด์•ผ๊ธฐํ•˜๋Š” ๋Š๋‚Œ์ด์—ˆ์ฃ .
09:30
He works for one of the largest companies in the world,
208
570437
2624
๊ทธ๋Š” ์ „์„ธ๊ณ„์—์„œ ๊ฐ€์žฅ ํฐ ํšŒ์‚ฌ์—์„œ ์ผํ•˜๊ณ  ์žˆ์–ด์„œ
09:33
and I'm already trying to make him feel better.
209
573085
2206
์ „ ๊ทธ์˜ ๊ธฐ๋ถ„์„ ์ข‹๊ฒŒ ํ•ด์ฃผ๋ ค๊ณ  ํ•˜๊ณ  ์žˆ์—ˆ์ฃ .
09:35
But he said, "No, Russ -- you might not understand.
210
575315
2445
ํ•˜์ง€๋งŒ ๊ทธ๋Š” ๋ง๋ถ™์˜€์–ด์š”. "๋Ÿฌ์Šค, ์ข€ ๋” ์•Œ์•„์•ผ ํ•  ๊ฒŒ ์žˆ์–ด."
09:37
We not only have Bing searches,
211
577784
1500
"์šฐ๋ฆฐ ๋น™ ๊ฒ€์ƒ‰๊ธฐ๋ก๋งŒ ๊ฐ€์ง€๊ณ  ์žˆ๋Š” ๊ฒŒ ์•„๋‹ˆ์•ผ."
09:39
but if you use Internet Explorer to do searches at Google,
212
579308
3340
"์ธํ„ฐ๋„ท ์ต์Šคํ”„๋กค๋Ÿฌ๋กœ ๊ตฌ๊ธ€์ด๋‚˜, ์•ผํ›„๋‚˜, ๋น™์ด๋‚˜
09:42
Yahoo, Bing, any ...
213
582672
1891
์–ด๋””์„œ๋“  ๊ฒ€์ƒ‰ํ•˜๋Š” ๊ทธ ๊ธฐ๋ก๋“ค..
09:44
Then, for 18 months, we keep that data for research purposes only."
214
584587
3643
์šฐ๋ฆฐ ๊ทธ ๊ธฐ๋ก์„ ์˜ค๋กœ์ง€ ์—ฐ๊ตฌ ๋ชฉ์ ์œผ๋กœ 18๊ฐœ์›”๊ฐ„ ๋ณด๊ด€ํ•œ๋‹ค๊ณ ."
09:48
I said, "Now you're talking!"
215
588254
1936
์ „ ๋งํ–ˆ์ฃ . "์•„,์ด์ œ ์ดํ•ดํ–ˆ๋‹ค!"
09:50
This was Eric Horvitz, my friend at Microsoft.
216
590214
2198
์ด ์นœ๊ตฌ๋Š” ์—๋ฆญ ํ˜ธ๋น„์ธ ์ธ๋ฐ ๋งˆ์ดํฌ๋กœ์†Œํ”„ํŠธ์—์„œ ์ผํ•˜๋Š” ์ œ ์นœ๊ตฌ์ž…๋‹ˆ๋‹ค.
09:52
So we did a study
217
592436
1695
๊ทธ๋ž˜์„œ ์šฐ๋ฆฌ๋Š” ์—ฐ๊ตฌ๋ฅผ ์‹œ์ž‘ํ–ˆ์ฃ .
09:54
where we defined 50 words that a regular person might type in
218
594155
4619
์ €ํฌ๋Š” ์ผ๋ฐ˜ ์‚ฌ๋žŒ์ด ๊ณ ํ˜ˆ๋‹น์— ๊ด€ํ•ด
09:58
if they're having hyperglycemia,
219
598798
1602
๊ฒ€์ƒ‰ํ• ๋งŒํ•œ 50๊ฐœ์˜ ๋‹จ์–ด๋ฅผ ์ •์˜ํ–ˆ์Šต๋‹ˆ๋‹ค.
10:00
like "fatigue," "loss of appetite," "urinating a lot," "peeing a lot" --
220
600424
4762
"ํ”ผ๋กœ", "์‹์š•์ €ํ•˜", "์†Œ๋ณ€์„ ๋งŽ์ด ๋ณผ ๋•Œ", "์˜ค์คŒ์„ ๋งŽ์ด ์Œ€ ๋•Œ"..
10:05
forgive me, but that's one of the things you might type in.
221
605210
2767
๋“ฃ๊ธฐ์—” ์›ƒ๊ธฐ์ง€๋งŒ, ์ € ๊ฒ€์ƒ‰์–ด๋“ค์ด ์‚ฌ๋žŒ๋“ค์ด ์“ธ ๋งŒํ•œ ๋‹จ์–ด๋“ค์ด์—์š”.
10:08
So we had 50 phrases that we called the "diabetes words."
222
608001
2790
๊ทธ๋ž˜์„œ, ์ €ํฌ๋Š” 50๊ฐœ์˜ ๋‹จ์–ด๋ฅผ ๊ฐ€์ง€๊ณ  ์žˆ์—ˆ์ฃ . ์ผ๋ช… "๋‹น๋‡จ๋ณ‘ ๋‹จ์–ด๋“ค"
10:10
And we did first a baseline.
223
610815
2063
์ด ๋‹จ์–ด๋“ค์„ ๋จผ์ € ๊ธฐ์ค€์œผ๋กœ ์„ ์ •ํ–ˆ์ฃ .
10:12
And it turns out that about .5 to one percent
224
612902
2704
๊ทธ๋ฆฌ๊ณ  ์ €ํฌ๋Š” ์ธํ„ฐ๋„ท ๊ฒ€์ƒ‰์ค‘ 0.5์—์„œ 1% ๊ฐ€๋Ÿ‰์ด
10:15
of all searches on the Internet involve one of those words.
225
615630
2982
์ด ๋‹จ์–ด๋“ค์„ ํฌํ•จํ•˜๊ณ  ์žˆ์Œ์„ ๋ฐœ๊ฒฌํ–ˆ์Šต๋‹ˆ๋‹ค.
10:18
So that's our baseline rate.
226
618636
1742
์ด๊ฒŒ ์šฐ๋ฆฌ์˜ ๊ธฐ์ค€๋นˆ๋„์˜€์ฃ .
10:20
If people type in "paroxetine" or "Paxil" -- those are synonyms --
227
620402
4143
๋งŒ์•ฝ์— ์‚ฌ๋žŒ๋“ค์ด "ํ”„๋ก์„ธํ‹ด" ํ˜น์€ "ํŒ์‹ค"์„ ๊ฒ€์ƒ‰ํ•˜๊ณ  ์ด๋Ÿฌํ•œ ์ฆ์ƒ๋“ค
10:24
and one of those words,
228
624569
1215
๊ทธ๋ฆฌ๊ณ  ์ด๋Ÿฌํ•œ ๋‹จ์–ด๋“ค์ค‘
10:25
the rate goes up to about two percent of diabetes-type words,
229
625808
4890
๋‹น๋‡จ๋ณ‘๊ณผ ๊ด€๋ จํ•ด์„œ ๊ทธ ๋น„์œจ์ด 2%๊นŒ์ง€ ์˜ฌ๋ผ๊ฐ”์Šต๋‹ˆ๋‹ค.
10:30
if you already know that there's that "paroxetine" word.
230
630722
3044
๋งŒ์•ฝ์— "ํ”„๋ก์„ธํ‹ด"์ด๋ผ๋Š” ๋‹จ์–ด๋ฅผ ์•Œ๊ณ  ์žˆ๋Š” ๊ฒฝ์šฐ์— ํ•œํ•ด์„œ ๋ง์ด์ฃ .
10:34
If it's "pravastatin," the rate goes up to about three percent from the baseline.
231
634191
4547
ํ”„๋ผ๋ฐ”์Šคํƒœํ‹ด์˜ ๊ฒฝ์šฐ๋Š”, ๊ธฐ์ค€์น˜์— ๋”ฐ๋ฅด๋ฉด 3%๊นŒ์ง€ ์˜ฌ๋ผ๊ฐ”์ฃ .
10:39
If both "paroxetine" and "pravastatin" are present in the query,
232
639171
4390
๋‘ ์•ฝ์˜ ์ด๋ฆ„์„ ๋™์‹œ์— ๊ฒ€์ƒ‰ํ•  ๊ฒฝ์šฐ์—๋Š”,
10:43
it goes up to 10 percent,
233
643585
1669
10%๊นŒ์ง€ ์ƒ์Šนํ–ˆ์Šต๋‹ˆ๋‹ค.
10:45
a huge three- to four-fold increase
234
645278
3461
3์—์„œ 4๋ฐฐ์˜ ์—„์ฒญ๋‚œ ์ฆ๊ฐ€์˜€์Šต๋‹ˆ๋‹ค.
10:48
in those searches with the two drugs that we were interested in,
235
648763
3389
์šฐ๋ฆฌ๊ฐ€ ๊ด€์‹ฌ์žˆ์–ดํ•˜๋Š” ๋‘ ์•ฝ๋ฌผ๊ณผ ๊ด€๋ จ๋œ ๊ฒ€์ƒ‰๋“ค๊ณผ
10:52
and diabetes-type words or hyperglycemia-type words.
236
652176
3566
๋‹น๋‡จ๋ณ‘ ์œ ํ˜•์˜ ๋‹จ์–ด๋“ค ํ˜น์€ ๊ณ ํ˜ˆ๋‹น ์œ ํ˜•์˜ ๋‹จ์–ด๋“ค์ด ๋ง์ด์ฃ .
10:56
We published this,
237
656216
1265
์šฐ๋ฆฐ ์ด๊ฒƒ์„ ๋…ผ๋ฌธ์œผ๋กœ ์ œ์ถœํ–ˆ์Šต๋‹ˆ๋‹ค.
10:57
and it got some attention.
238
657505
1466
์ด๊ฑด ๊ฝค ์ฃผ๋ชฉ์„ ๋ฐ›์•˜์ฃ .
10:58
The reason it deserves attention
239
658995
1778
์ฃผ๋ชฉ์„ ๋ฐ›์€ ์ด์œ ๋Š”
11:00
is that patients are telling us their side effects indirectly
240
660797
4312
ํ™˜์ž๋“ค์ด ๊ฒ€์ƒ‰์„ ํ†ตํ•ด์„œ ๋ถ€์ž‘์šฉ์— ๊ด€ํ•ด
๊ฐ„์ ‘์ ์œผ๋กœ๋‚˜๋งˆ ๋งํ•˜๊ณ  ์žˆ๊ธฐ ๋•Œ๋ฌธ์ด์—ˆ์ฃ .
11:05
through their searches.
241
665133
1156
11:06
We brought this to the attention of the FDA.
242
666313
2138
์šฐ๋ฆฌ๋Š” ์ด ๋…ผ๋ฌธ์„ FDA์— ๋ณด์—ฌ์คฌ์Šต๋‹ˆ๋‹ค.
11:08
They were interested.
243
668475
1269
๊ทธ๋“ค์€ ๊ด€์‹ฌ์„ ๋ณด์˜€์ฃ .
11:09
They have set up social media surveillance programs
244
669768
3606
FDA๋Š” ์†Œ์…œ๋ฏธ๋””์–ด ๊ฐ์‹œ ํ”„๋กœ๊ทธ๋žจ์„ ๋งŒ๋“ค์—ˆ์ฃ .
11:13
to collaborate with Microsoft,
245
673398
1751
๋งˆ์ดํฌ๋กœ์†Œํ”„ํŠธ์‚ฌ์™€ ํ•จ๊ป˜ ํ–ˆ์Šต๋‹ˆ๋‹ค.
11:15
which had a nice infrastructure for doing this, and others,
246
675173
2794
์ด๋Ÿฌํ•œ ๊ฒƒ์„ ํ•˜๊ธฐ ์œ„ํ•œ ์ข‹์€ ๊ธฐ๋ฐ˜์„ ๊ฐ€์ง€๊ณ  ์žˆ๊ธฐ ๋•Œ๋ฌธ์ด์ฃ . ๋‹ค๋ฅธ ๊ฒƒ๋“ค.
11:17
to look at Twitter feeds,
247
677991
1282
ํŠธ์œ„ํ„ฐ ํ”ผ๋“œ๋ฅผ ์‚ดํ”ผ๊ฑฐ๋‚˜,
11:19
to look at Facebook feeds,
248
679297
1716
ํŽ˜์ด์Šค๋ถ ํ”ผ๋“œ๋ฅผ ์‚ดํ”ผ๊ฑฐ๋‚˜
11:21
to look at search logs,
249
681037
1311
๊ฒ€์ƒ‰ ๊ธฐ๋ก์„ ์ฐพ์•„๋ณด๋Š”๋ฐ ๋ง์ด์ฃ .
11:22
to try to see early signs that drugs, either individually or together,
250
682372
4909
๊ทธ ๊ด€์ฐฐ์„ ํ†ตํ•ด ๊ทธ๋“ค์€ ๊ทธ ์•ฝ์„, ๋”ฐ๋กœ ํ˜น์€ ๊ฐ™์ด ๋ณต์šฉํ•˜๋“ ๊ฐ„์—
11:27
are causing problems.
251
687305
1589
๋ฌธ์ œ๋ฅผ ์ผ์œผํ‚ค๋Š” ์ง€์— ๋Œ€ํ•œ ์ดˆ๊ธฐ ์ฆ์ƒ๋ฅผ ์•Œ์•„๋ณด๋ ค ํ–ˆ์Šต๋‹ˆ๋‹ค.
11:28
What do I take from this? Why tell this story?
252
688918
2174
์ด๋กœ๋ถ€ํ„ฐ ์ œ๊ฐ€ ์–ป๋Š” ๊ฑด ๋ฌด์—‡์ผ๊นŒ์š”? ์™œ ์ด ์ด์•ผ๊ธฐ๋ฅผ ํ•˜๋Š” ๊ฑธ๊นŒ์š”?
11:31
Well, first of all,
253
691116
1207
๊ธ€์Ž„์š”, ์ผ๋‹จ.
11:32
we have now the promise of big data and medium-sized data
254
692347
4037
์ €ํฌ๋Š” ์ด์ œ ์ค‘๊ฐ„ ํ˜น์€ ํฐ ๊ทœ๋ชจ์˜ ๋ฐ์ดํ„ฐ๋ฅผ ์•ฝ์† ๋ฐ›์•˜์ฃ .
11:36
to help us understand drug interactions
255
696408
2918
์•ฝ ์‚ฌ์ด์˜ ์ƒํ˜ธ์ž‘์šฉ์„ ์ดํ•ดํ•˜๊ธฐ ์œ„ํ•ด์„œ ๊ทธ๋ฆฌ๊ณ 
11:39
and really, fundamentally, drug actions.
256
699350
2420
์ •๋ง๋กœ, ๊ทผ๋ณธ์ ์ธ ์•ฝ ์ž‘์šฉ์„ ์ดํ•ดํ•˜๊ธฐ ์œ„ํ•ด์„œ ๋ง์ด์ฃ .
11:41
How do drugs work?
257
701794
1413
์–ด๋–ป๊ฒŒ ์•ฝ์ด ์ž‘์šฉํ•˜๋Š”์ง€
11:43
This will create and has created a new ecosystem
258
703231
2836
์ด ๋ฐ์ดํ„ฐ๋Š” ์•ฝ์ด ์–ด๋–ป๊ฒŒ ์ž‘์šฉํ•˜๊ณ  ์•ฝ์„ ์ž˜ ํ™œ์šฉํ•  ์ˆ˜ ์žˆ์ง€์— ๋Œ€ํ•ด
11:46
for understanding how drugs work and to optimize their use.
259
706091
3267
์ดํ•ดํ•  ์ˆ˜ ์žˆ๋Š” ์ƒˆ๋กœ์šด ํ™˜๊ฒฝ์„ ๋งŒ๋“ค ๊ฒƒ์ด๊ณ  ๋งŒ๋“ค์–ด๊ฐ€๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
11:50
Nick went on; he's a professor at Columbia now.
260
710303
2659
๋‹‰์€ ์‹œ์ž‘ํ–ˆ์ฃ ; ์ง€๊ธˆ ์ฝœ๋กฌ๋น„์•„์˜ ๊ต์ˆ˜์ž…๋‹ˆ๋‹ค.
11:52
He did this in his PhD for hundreds of pairs of drugs.
261
712986
4072
๊ทธ๋Š” ๋ฐ•์‚ฌ๊ณผ์ •๋™์•ˆ ์ด ์—ฐ๊ตฌ๋ฅผ ์ˆ˜๋ฐฑ๊ฐ€์ง€์˜ ์•ฝ์œผ๋กœ ํ™•์žฅ์‹œ์ผฐ๊ณ ,
11:57
He found several very important interactions,
262
717082
2517
์—ฌ๋Ÿฌ๊ฐ€์ง€์˜ ์ค‘์š”ํ•œ ์ƒํ˜ธ์ž‘์šฉ์„ ๋ฐœ๊ฒฌํ•˜๊ณ 
11:59
and so we replicated this
263
719623
1214
์šฐ๋ฆฌ๋Š” ์ด๊ฒƒ์„ ๋ณต์ œํ•ด์„œ
12:00
and we showed that this is a way that really works
264
720861
2574
์šฐ๋ฆฌ๋Š” ์ด ๋ฐฉ์‹์ด ์•ฝ๊ณผ ์•ฝ ์‚ฌ์ด์˜ ์‹ค์ œ ์ƒํ˜ธ ์ž‘์šฉ์„
12:03
for finding drug-drug interactions.
265
723459
2339
์ฐพ์•„๋‚ผ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์ž„์„ ๋ณด์—ฌ์คฌ์ฃ .
12:06
However, there's a couple of things.
266
726282
1734
ํ•˜์ง€๋งŒ, ์—ฌ๊ธฐ์—๋Š” ๋ช‡ ๊ฐ€์ง€ ๋ฌธ์ œ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค.
12:08
We don't just use pairs of drugs at a time.
267
728040
3046
ํ‰์†Œ์—, ์šฐ๋ฆฌ๋Š” ๋‘๊ฐ€์ง€ ์•ฝ๋งŒ ๋จน์ง„ ์•Š์ฃ .
12:11
As I said before, there are patients on three, five, seven, nine drugs.
268
731110
4469
๋งํ–ˆ๋“ฏ์ด, ์…‹, ๋‹ค์„ฏ, ์ผ๊ณฑ ํ˜น์€ ์•„ํ™‰ ์ข…๋ฅ˜์˜ ์•ฝ์„ ๋จน๋Š” ํ™˜์ž๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
12:15
Have they been studied with respect to their nine-way interaction?
269
735981
3642
๊ทธ๋“ค์€ 9๊ฐ€์ง€ ์ƒํ˜ธ์ž‘์šฉ ๋ฐฉ์‹์„ ์—ฐ๊ตฌํ• ๋•Œ ๊ฒฝ์ด๋กœ์›€์„ ๊ฐ€์ง„์ ์ด ์žˆ์„๊นŒ์š”?
12:19
Yes, we can do pair-wise, A and B, A and C, A and D,
270
739647
4208
์ง์„ ์ง€์–ด ์—ฐ๊ตฌํ•  ์ˆ˜๋„ ์žˆ๊ฒ ์ฃ . A๋ž‘ B, A๋ž‘ C ์ด๋Ÿฐ ์‹ ๋ง์ด์ฃ .
12:23
but what about A, B, C, D, E, F, G all together,
271
743879
4286
ํ•˜์ง€๋งŒ ํ•œ ํ™˜์ž๊ฐ€ ๋™์‹œ์— A,B,C,D,E,F,G ๋จน์œผ๋ฉด
12:28
being taken by the same patient,
272
748189
1762
์–ด๋–ป๊ฒŒ ํ• ๊นŒ์š”?
12:29
perhaps interacting with each other
273
749975
2118
ํ˜น์‹œ ๊ฐ๊ฐ์˜ ์ƒํ˜ธ์ž‘์šฉ์„ ํ†ตํ•˜์—ฌ
12:32
in ways that either makes them more effective or less effective
274
752117
3778
์•ฝ์˜ ํšจ๊ณผ๋ฅผ ๋” ํšจ๊ณผ์ ์ด๊ฒŒ ๋งŒ๋“ค๊ฑฐ๋‚˜ ํ˜น์€ ๋œ ํšจ๊ณผ์ ์ด๊ฒŒ ๋งŒ๋“ค๊ฑฐ๋‚˜
12:35
or causes side effects that are unexpected?
275
755919
2332
ํ˜น์€ ์˜ˆ์ƒํ•  ์ˆ˜ ์—†๋˜ ๋ถ€์ž‘์šฉ์„ ์ผ์œผํ‚ค์ง€๋Š” ์•Š์„๊นŒ์š”?
12:38
We really have no idea.
276
758275
1827
์šฐ๋ฆฐ ์ •๋ง๋กœ ์•Œ ์ˆ˜ ์—†์ฃ .
12:40
It's a blue sky, open field for us to use data
277
760126
3756
์šฐ๋ฆฌ์—๊ฒŒ ๋ฐ์ดํ„ฐ๋ฅผ ์ด์šฉํ•ด ์•ฝ์˜ ์ƒํ˜ธ์ž‘์šฉ์„ ์ดํ•ดํ•˜๋Š” ๊ฑด
12:43
to try to understand the interaction of drugs.
278
763906
2502
์•ž์œผ๋กœ ๊ณ„์† ์•Œ์•„๊ฐ€์•ผ ํ•  ๋„“์€ ๊ด‘์•ผ์™€๋„ ๊ฐ™์Šต๋‹ˆ๋‹ค.
12:46
Two more lessons:
279
766848
1370
๋‘ ๊ฐ€์ง€๋งŒ ๋” ์ด์•ผ๊ธฐํ•˜์ฃ .
12:48
I want you to think about the power that we were able to generate
280
768242
4199
์šฐ๋ฆฌ๊ฐ€ ๋งŒ๋“ค์–ด๋‚ผ ์ˆ˜ ์žˆ์—ˆ๋˜ ํž˜์— ๋Œ€ํ•ด ์ƒ๊ฐํ•ด๋ณด์‹œ๊ธธ ๋ฐ”๋ž๋‹ˆ๋‹ค .
12:52
with the data from people who had volunteered their adverse reactions
281
772465
4711
์ž์‹ ๋“ค์ด ๊ฒช๊ณ  ์žˆ๋Š” ๋ถ€์ž‘์šฉ์„ ๋ฐ์ดํ„ฐ๋ฅผ ํ†ตํ•ด์„œ ์ž๋ฐœ์ ์œผ๋กœ ์•Œ๋ ค์ค€ ์‚ฌ๋žŒ๋“ค
12:57
through their pharmacists, through themselves, through their doctors,
282
777200
3269
์•ฝ์‚ฌ๋ฅผ ํ†ตํ•ด์„œ, ํ˜น์€ ๊ทธ๋“ค ์Šค์Šค๋กœ, ์ฃผ์น˜์˜๋ฅผ ํ†ตํ•ด์„œ
13:00
the people who allowed the databases at Stanford, Harvard, Vanderbilt,
283
780493
3667
๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค๋ฅผ ์ œ๊ณตํ–ˆ๋˜ ํ•˜๋ฒ„๋“œ, ์Šคํƒ ํฌ๋“œ, ๋ฐ˜๋”๋นŒํŠธ๋Œ€์˜ ์‚ฌ๋žŒ๋“ค์ด
13:04
to be used for research.
284
784184
1427
์—ฐ๊ตฌ๋ฅผ ์œ„ํ•ด ์ œ๊ณตํ–ˆ๋˜ ๋ฐ์ดํ„ฐ๋“ค์ด์ฃ .
13:05
People are worried about data.
285
785929
1445
์‚ฌ๋žŒ๋“ค์€ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•ด ๋ถˆ์•ˆํ•ดํ•ฉ๋‹ˆ๋‹ค.
13:07
They're worried about their privacy and security -- they should be.
286
787398
3187
๊ทธ๋“ค์€ ์‚ฌ์ƒํ™œ ์นจํ•ด์— ๋Œ€ํ•ด ๋‘๋ ค์›Œํ•˜์ฃ . ๊ทธ๋“ค์€ ๊ทธ๋ž˜์•ผ๋งŒ ํ•˜์ฃ .
13:10
We need secure systems.
287
790609
1151
์šฐ๋ฆฌ๋Š” ๋ณด์•ˆ์ฒด๊ณ„๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
13:11
But we can't have a system that closes that data off,
288
791784
3406
ํ•˜์ง€๋งŒ ์šฐ๋ฆฌ๋Š” ๋ฐ์ดํ„ฐ๋ฅผ ์ฐจ๋‹จํ•˜๋Š” ์ฒด๊ณ„๋ฅผ ๊ฐ€์งˆ ์ˆ˜๋Š” ์—†์Šต๋‹ˆ๋‹ค.
13:15
because it is too rich of a source
289
795214
2752
์™œ๋ƒํ•˜๋ฉด ๊ทธ ๋ฐ์ดํ„ฐ๋Š” ์ƒˆ๋กœ์šด ์•ฝ์˜ ๊ฐœ๋ฐœ์„ ์œ„ํ•œ
13:17
of inspiration, innovation and discovery
290
797990
3971
์˜๊ฐ, ์ฐฝ์˜์„ฑ ๊ทธ๋ฆฌ๊ณ  ๋ฐœ๊ฒฌ์„
13:21
for new things in medicine.
291
801985
1578
์‹นํ‹”์šฐ๋Š” ๊ธฐ๋ฆ„์ง„ ๋•…์ด๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
13:24
And the final thing I want to say is,
292
804494
1794
๋งˆ์ง€๋ง‰์œผ๋กœ ์ด์•ผ๊ธฐํ•˜๊ณ  ์‹ถ์€ ๊ฒƒ์€
13:26
in this case we found two drugs and it was a little bit of a sad story.
293
806312
3357
์ €ํฌ ์—ฐ๊ตฌ๋Š” ์กฐ๊ธˆ์€ ์Šฌํ”ˆ ๊ฒฐ๋ก ์ด์—ˆ๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
13:29
The two drugs actually caused problems.
294
809693
1921
๋‘ ๊ฐœ์˜ ์•ฝ๋ฌผ์€ ๊ฒฐ๊ตญ ๋ฌธ์ œ๋ฅผ ์ผ์œผ์ผฐ์Šต๋‹ˆ๋‹ค.
13:31
They increased glucose.
295
811638
1475
๊ทธ ์•ฝ๋“ค์€ ํฌ๋„๋‹น ์ˆ˜์น˜๋ฅผ ์˜ฌ๋ ธ์Šต๋‹ˆ๋‹ค.
13:33
They could throw somebody into diabetes
296
813137
2446
๋ˆ„๊ตฐ๊ฐ€๋ฅผ ๋‹น๋‡จ๋ณ‘ํ™˜์ž๋กœ ๋งŒ๋“ค์—ˆ์Šต๋‹ˆ๋‹ค.
13:35
who would otherwise not be in diabetes,
297
815607
2294
์•ฝ์„ ๋จน์ง€ ์•Š์•˜๋‹ค๋ฉด, ์ •์ƒ์ธ์œผ๋กœ ์‚ด ์ˆ˜ ์žˆ์—ˆ์„ํ…๋ฐ ๋ง์ด์ฃ .
13:37
and so you would want to use the two drugs very carefully together,
298
817925
3175
๊ทธ๋Ÿฌ๋ฏ€๋กœ ์•ฝ์„ ๋™์‹œ์— ๋จน์„ ๋•Œ๋Š” ๊ต‰์žฅํžˆ ์‹ ์ค‘ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
13:41
perhaps not together,
299
821124
1151
๊ฐ™์ด ๋จน์ง€ ์•Š๋Š” ๊ฒƒ๋„ ๊ฐ€๋Šฅํ•˜๊ณ ์š”.
13:42
make different choices when you're prescribing.
300
822299
2340
์•ฝ์„ ์ฒ˜๋ฐฉ ๋ฐ›์„ ๋•Œ, ๋‹ค๋ฅธ ์•ฝ์„ ์ฒ˜๋ฐฉ๋ฐ›์„ ์ˆ˜๋„ ์žˆ๊ฒ ์ฃ .
13:44
But there was another possibility.
301
824663
1846
ํ•˜์ง€๋งŒ, ๋‹ค๋ฅธ ๊ฐ€๋Šฅ์„ฑ๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
13:46
We could have found two drugs or three drugs
302
826533
2344
์šฐ๋ฆฌ๋Š” ์„œ๋กœ ์ข‹์€ ์ž‘์šฉ์„ ํ•˜๋Š”
13:48
that were interacting in a beneficial way.
303
828901
2261
๋‘ ๊ฐœ ํ˜น์€ ์„ธ ๊ฐœ์˜ ์•ฝ์˜ ์กฐํ•ฉ์„ ์ฐพ์„ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
13:51
We could have found new effects of drugs
304
831616
2712
์šฐ๋ฆฌ๋Š” ์•ฝ์˜ ์ƒˆ๋กœ์šด ํšจ๋Šฅ์„ ์ฐพ์•„๋‚ผ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
13:54
that neither of them has alone,
305
834352
2160
์•ฝ์„ ํ˜ผ์ž ๋จน์—ˆ์„ ๋•Œ๋Š” ๋ณด์ด์ง€ ์•Š์ง€๋งŒ
13:56
but together, instead of causing a side effect,
306
836536
2493
๊ฐ™์ด ๋จน์—ˆ์„ ๋•Œ, ๋ถ€์ž‘์šฉ์„ ๋ณด์ด๋Š” ๋Œ€์‹ 
13:59
they could be a new and novel treatment
307
839053
2425
์ƒˆ๋กญ๊ณ  ๋…์ฐฝ์ ์ธ ์น˜๋ฃŒ๋ฒ•์ด ๋ฐœ๊ฒฌ๋  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
14:01
for diseases that don't have treatments
308
841502
1882
๊ทธ ์น˜๋ฃŒ๋ฒ•์€ ์–ด์ฉŒ๋ฉด ์ง€๊ธˆ๊นŒ์ง€ ์น˜๋ฃŒ๋ฒ•์ด ์—†๋Š”
14:03
or where the treatments are not effective.
309
843408
2007
ํ˜น์€ ์น˜๋ฃŒ๋ฒ•์ด ํšจ๊ณผ์ ์ด์ง€ ์•Š์€ ๋ณ‘์— ํฐ ๋„์›€์ด ๋  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
14:05
If we think about drug treatment today,
310
845439
2395
ํ˜„์žฌ์˜ ์•ฝ ์ฒ˜๋ฐฉ์— ๋Œ€ํ•ด ์ƒ๊ฐํ•ด๋ณธ๋‹ค๋ฉด
14:07
all the major breakthroughs --
311
847858
1752
๋ชจ๋“  ์ค‘์š”ํ•œ ๋ŒํŒŒ๊ตฌ๋“ค--
14:09
for HIV, for tuberculosis, for depression, for diabetes --
312
849634
4297
์—์ด์ฆˆ, ๊ฒฐํ•ต, ์šฐ์šธ์ฆ ํ˜น์€ ๋‹น๋‡จ๋ณ‘์— ๋Œ€ํ•œ ๋ŒํŒŒ๊ตฌ๋“ค์€
14:13
it's always a cocktail of drugs.
313
853955
2830
ํ•ญ์ƒ ์•ฝ์„ ์กฐํ•ฉํ–ˆ์„ ๋•Œ ๋‚˜ํƒ€๋‚ฌ์Šต๋‹ˆ๋‹ค.
14:16
And so the upside here,
314
856809
1730
๊ทธ๋ž˜์„œ ์—ฌ๊ธฐ์„œ ์ด์•ผ๊ธฐํ•œ ๊ฒƒ๊ณผ
14:18
and the subject for a different TED Talk on a different day,
315
858563
2849
๋‹ค๋ฅธ ๋‚  ,๋‹ค๋ฅธ TED ๊ฐ•์—ฐ์˜ ์ฃผ์ œ๋Š”
14:21
is how can we use the same data sources
316
861436
2593
๋˜‘๊ฐ™์€ ๋ฐ์ดํ„ฐ๋ฅผ ์ด์šฉํ•ด์„œ
14:24
to find good effects of drugs in combination
317
864053
3563
์ข‹์€ ์ž‘์šฉ์„ ์ผ์œผํ‚ค๋Š” ์•ฝ์˜ ์กฐํ•ฉ์„ ์–ด๋–ป๊ฒŒ ์ฐพ์•„์„œ
14:27
that will provide us new treatments,
318
867640
2175
์šฐ๋ฆฌ์—๊ฒŒ ์ƒˆ๋กœ์šด ์น˜๋ฃŒ๋ฒ•์ด ๋˜๊ณ 
14:29
new insights into how drugs work
319
869839
1852
์•ฝ์˜ ์ž‘์šฉ์— ๋Œ€ํ•ด ์ƒˆ๋กœ์šด ํ†ต์ฐฐ๋ ฅ๋˜์–ด์„œ
14:31
and enable us to take care of our patients even better?
320
871715
3786
์–ด๋–ป๊ฒŒ ํ™˜์ž๋ฅผ ๋” ์ž˜ ์น˜๋ฃŒํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•˜๋Š”๊ฐ€ ์ž…๋‹ˆ๋‹ค.
14:35
Thank you very much.
321
875525
1166
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
14:36
(Applause)
322
876715
3499
(๋ฐ•์ˆ˜)
์ด ์›น์‚ฌ์ดํŠธ ์ •๋ณด

์ด ์‚ฌ์ดํŠธ๋Š” ์˜์–ด ํ•™์Šต์— ์œ ์šฉํ•œ YouTube ๋™์˜์ƒ์„ ์†Œ๊ฐœํ•ฉ๋‹ˆ๋‹ค. ์ „ ์„ธ๊ณ„ ์ตœ๊ณ ์˜ ์„ ์ƒ๋‹˜๋“ค์ด ๊ฐ€๋ฅด์น˜๋Š” ์˜์–ด ์ˆ˜์—…์„ ๋ณด๊ฒŒ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ฐ ๋™์˜์ƒ ํŽ˜์ด์ง€์— ํ‘œ์‹œ๋˜๋Š” ์˜์–ด ์ž๋ง‰์„ ๋”๋ธ” ํด๋ฆญํ•˜๋ฉด ๊ทธ๊ณณ์—์„œ ๋™์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค. ๋น„๋””์˜ค ์žฌ์ƒ์— ๋งž์ถฐ ์ž๋ง‰์ด ์Šคํฌ๋กค๋ฉ๋‹ˆ๋‹ค. ์˜๊ฒฌ์ด๋‚˜ ์š”์ฒญ์ด ์žˆ๋Š” ๊ฒฝ์šฐ ์ด ๋ฌธ์˜ ์–‘์‹์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ฌธ์˜ํ•˜์‹ญ์‹œ์˜ค.

https://forms.gle/WvT1wiN1qDtmnspy7