TEDMED 2015
Russ Altman: What really happens when you mix medications?
Russ Altman: 混合不同药物会如何？
Filmed:
Readability: 4.2
1,766,922 views
如果你为了治疗两种不同病症而服用不同的药物，这就有一个发人省醒的问题：由于药物的协同机理很难研究，你的医生可能不会通晓同时服用的后果。在这个有趣而又易懂的谈话中，Russ Altman揭示了医生是怎样用一种新奇的资源研究未知的药物间作用的：搜索引擎索引。
Russ Altman - Big data techno-optimist and internist
Russ Altman uses machine learning to better understand adverse effects of medication. Full bio
Russ Altman uses machine learning to better understand adverse effects of medication. Full bio
Double-click the English transcript below to play the video.
00:12
So you go to the doctor
and get some tests.
and get some tests.
0
811
3321
你去看医生的时候做了一些检查
00:16
The doctor determines
that you have high cholesterol
that you have high cholesterol
1
4674
2620
医生说你的血脂高
00:19
and you would benefit
from medication to treat it.
from medication to treat it.
2
7318
3171
所以吃药会有帮助
00:22
So you get a pillbox.
3
10981
1556
那么你就买了一盒药
00:25
You have some confidence,
4
13505
1199
你有信心，
你的医生也有信心
觉得这会对你有帮助
觉得这会对你有帮助
00:26
your physician has some confidence
that this is going to work.
that this is going to work.
5
14728
2937
00:29
The company that invented it did
a lot of studies, submitted it to the FDA.
a lot of studies, submitted it to the FDA.
6
17689
3553
发明这个的药物公司做过很多研究
呈送到FDA
呈送到FDA
00:33
They studied it very carefully,
skeptically, they approved it.
skeptically, they approved it.
7
21266
3107
他们充满怀疑地研究，后来许可了。
00:36
They have a rough idea of how it works,
8
24397
1889
他们大概地知道这个药的机理
00:38
they have a rough idea
of what the side effects are.
of what the side effects are.
9
26310
2453
和药物的副作用
00:40
It should be OK.
10
28787
1150
它应该可以
00:42
You have a little more
of a conversation with your physician
of a conversation with your physician
11
30864
2818
你跟你的医生又谈了一会儿
00:45
and the physician is a little worried
because you've been blue,
because you've been blue,
12
33706
2963
医生对你有点儿担心
因为你有些抑郁
因为你有些抑郁
00:48
haven't felt like yourself,
13
36693
1293
感觉你不是自己
00:50
you haven't been able to enjoy things
in life quite as much as you usually do.
in life quite as much as you usually do.
14
38010
3731
你对生活不像以前那么充满兴趣
00:53
Your physician says, "You know,
I think you have some depression.
I think you have some depression.
15
41765
3186
你的医生说，“你知道吗，
我觉得你有些抑郁。
我觉得你有些抑郁。
00:57
I'm going to have to give
you another pill."
you another pill."
16
45792
2315
我会给你另一种药“
01:00
So now we're talking
about two medications.
about two medications.
17
48934
2483
所以 现在我们所谈论的是两种药物
01:03
This pill also -- millions
of people have taken it,
of people have taken it,
18
51441
3104
这种药－－上百万人服用过
01:06
the company did studies,
the FDA looked at it -- all good.
the FDA looked at it -- all good.
19
54569
3631
公司做过很多研究，FDA许可的－－
不会错
不会错
01:10
Think things should go OK.
20
58823
2057
你会想应该没问题
01:12
Think things should go OK.
21
60904
2197
应该没问题
01:15
Well, wait a minute.
22
63125
1439
等等
01:16
How much have we studied
these two together?
these two together?
23
64588
3517
我们知道两种药物一起服用的研究吗
01:20
Well, it's very hard to do that.
24
68630
2300
而这是很难做到的。
01:22
In fact, it's not traditionally done.
25
70954
2130
实际上 还从来没有
在药物上市之后
01:25
We totally depend on what we call
"post-marketing surveillance,"
"post-marketing surveillance,"
26
73108
5518
我们完全地依赖于我们叫做
“市场后监测”
“市场后监测”
01:30
after the drugs hit the market.
27
78650
1880
我们如何能够弄清楚
01:32
How can we figure out
if bad things are happening
if bad things are happening
28
80996
2848
在两种，三种或五种药物
01:35
between two medications?
29
83868
1357
混合之后 会有哪些坏处呢？
01:37
Three? Five? Seven?
30
85249
2030
01:39
Ask your favorite person
who has several diagnoses
who has several diagnoses
31
87708
2415
问问你最喜欢的被诊断了
几个不同疾病的人
几个不同疾病的人
他们在吃多少种药
01:42
how many medications they're on.
32
90147
1834
我为什么关心这个问题呢？
01:44
Why do I care about this problem?
33
92530
1580
我对这非常在意
01:46
I care about it deeply.
34
94134
1157
我是信息和数据科学家
真的，以我的意见来说
真的，以我的意见来说
01:47
I'm an informatics and data science guy
and really, in my opinion,
and really, in my opinion,
35
95315
4304
唯一的能够理解这些药物相互作用
的希望
的希望
01:51
the only hope -- only hope --
to understand these interactions
to understand these interactions
36
99643
3745
就是平衡不同来源的数据
01:55
is to leverage lots
of different sources of data
of different sources of data
37
103412
3056
以便弄清楚药物在一起什么时候安全
01:58
in order to figure out
when drugs can be used together safely
when drugs can be used together safely
38
106492
3556
什么时候不安全
02:02
and when it's not so safe.
39
110072
1777
让我来告诉你们一些数据科学的故事
02:04
So let me tell you a data science story.
40
112615
2051
它来自于我的学生尼克
02:06
And it begins with my student Nick.
41
114690
2154
我们叫他“尼克”
因为那是他的名字
因为那是他的名字
02:08
Let's call him "Nick,"
because that's his name.
because that's his name.
42
116868
2380
笑声
02:11
(Laughter)
43
119272
1592
尼克是一个年轻学生
02:12
Nick was a young student.
44
120888
1201
我说，“你知道吗，尼克
我们需要理解药物的工作机理
我们需要理解药物的工作机理
02:14
I said, "You know, Nick, we have
to understand how drugs work
to understand how drugs work
45
122113
3079
不仅是它们单独作用
还有它们的协同机理
还有它们的协同机理
02:17
and how they work together
and how they work separately,
and how they work separately,
46
125216
2626
目前我们还知道得不多
02:19
and we don't have a great understanding.
47
127866
1922
但FDA已经提供了一个惊人的数据库
02:21
But the FDA has made available
an amazing database.
an amazing database.
48
129812
2405
是关于反作用事件的数据库
02:24
It's a database of adverse events.
49
132241
1699
他们发表在互联网上－－
02:26
They literally put on the web --
50
134321
1642
可公开使用 你现在就可以下载
02:27
publicly available, you could all
download it right now --
download it right now --
51
135987
3119
成千上万例的
02:31
hundreds of thousands
of adverse event reports
of adverse event reports
52
139130
3627
从病人，医生，公司，
药房的反作用报告
药房的反作用报告
02:34
from patients, doctors,
companies, pharmacists.
companies, pharmacists.
53
142781
3760
02:38
And these reports are pretty simple:
54
146565
1749
这些报告很简单：
02:40
it has all the diseases
that the patient has,
that the patient has,
55
148338
2658
它具有病人所有的疾病
他们在用的所有药物
02:43
all the drugs that they're on,
56
151020
1767
以及他们所经过的所有的
反作用、副作用
反作用、副作用
02:44
and all the adverse events,
or side effects, that they experience.
or side effects, that they experience.
57
152811
3818
02:48
It is not all of the adverse events
that are occurring in America today,
that are occurring in America today,
58
156653
3436
它还不是所有的在美國发生的
反作用事件
反作用事件
但它有成百上千种药物
02:52
but it's hundreds and hundreds
of thousands of drugs.
of thousands of drugs.
59
160113
2578
02:54
So I said to Nick,
60
162715
1299
所以我对尼克说
“让我们考虑葡萄糖
02:56
"Let's think about glucose.
61
164038
1826
02:57
Glucose is very important,
and we know it's involved with diabetes.
and we know it's involved with diabetes.
62
165888
3567
血糖很重要
我们知道它和糖尿病相关
我们知道它和糖尿病相关
让我们看看是否理解血糖的反应
03:01
Let's see if we can understand
glucose response.
glucose response.
63
169479
3970
我让尼克去做了。尼克又回来了。
03:05
I sent Nick off. Nick came back.
64
173473
2458
”罗斯，“ 他说
03:08
"Russ," he said,
65
176248
1786
”我已经根据这个数据库
创建了一个分类
创建了一个分类
03:10
"I've created a classifier that can
look at the side effects of a drug
look at the side effects of a drug
66
178351
5112
可以查看一个药物的副作用
03:15
based on looking at this database,
67
183487
2051
并告诉你这个药物是否会改变血糖。“
03:17
and can tell you whether that drug
is likely to change glucose or not."
is likely to change glucose or not."
68
185562
4271
他这样做了，而且在他来说很简单
03:21
He did it. It was very simple, in a way.
69
189857
2016
他把所有我们知道会改变血糖的药物
03:23
He took all the drugs
that were known to change glucose
that were known to change glucose
70
191897
2635
还有很多不会改变血糖的都分了类
03:26
and a bunch of drugs
that don't change glucose,
that don't change glucose,
71
194556
2389
他说，“他们的副作用有不同吗？”
03:28
and said, "What's the difference
in their side effects?
in their side effects?
72
196969
2888
在疲劳？胃口？
以及排尿习惯方面有不同吗？
以及排尿习惯方面有不同吗？
03:31
Differences in fatigue? In appetite?
In urination habits?"
In urination habits?"
73
199881
4852
所有这些指标都给予他
一个很好的预测
一个很好的预测
03:36
All those things conspired
to give him a really good predictor.
to give him a really good predictor.
74
204757
2960
他说，“罗斯，
我能以93%的精确度预测
我能以93%的精确度预测
03:39
He said, "Russ, I can predict
with 93 percent accuracy
with 93 percent accuracy
75
207741
2548
一个药物会改变血糖”
03:42
when a drug will change glucose."
76
210313
1572
我说，“尼克， 那很好。”
03:43
I said, "Nick, that's great."
77
211909
1416
他是一个年轻的学生
你得帮他建立自信
你得帮他建立自信
03:45
He's a young student,
you have to build his confidence.
you have to build his confidence.
78
213349
2896
“但是尼克， 有一个问题
03:48
"But Nick, there's a problem.
79
216269
1390
要让这世界上的每一个医生都知道
所有改变血糖的药物
所有改变血糖的药物
03:49
It's that every physician in the world
knows all the drugs that change glucose,
knows all the drugs that change glucose,
80
217683
3960
这是我们作业的核心
03:53
because it's core to our practice.
81
221667
2038
很好 做的好
但并不是那么有趣
但并不是那么有趣
03:55
So it's great, good job,
but not really that interesting,
but not really that interesting,
82
223729
3722
绝对不能发表
03:59
definitely not publishable."
83
227475
1531
（笑声）
04:01
(Laughter)
84
229030
1014
他说，“我知道，罗斯
我知道你会那样说。”
我知道你会那样说。”
04:02
He said, "I know, Russ.
I thought you might say that."
I thought you might say that."
85
230068
2550
尼克很聪明
04:04
Nick is smart.
86
232642
1152
“我想到你会这么说，
所以我做了另一个试验。
所以我做了另一个试验。
04:06
"I thought you might say that,
so I did one other experiment.
so I did one other experiment.
87
234149
2874
我查看了在这个数据中
服用两种药物的病人，
服用两种药物的病人，
04:09
I looked at people in this database
who were on two drugs,
who were on two drugs,
88
237047
2928
我查看相似的，血糖改变信号，
04:11
and I looked for signals similar,
glucose-changing signals,
glucose-changing signals,
89
239999
4422
对那些服用两种药物的人，
04:16
for people taking two drugs,
90
244445
1624
一种药物本身不改变血糖，
04:18
where each drug alone
did not change glucose,
did not change glucose,
91
246093
5569
但一起的时候，我看到了很强的信号。“
04:23
but together I saw a strong signal."
92
251686
2460
我说，”喔！你真聪明。
好主意。给我看看列表。“
好主意。给我看看列表。“
04:26
And I said, "Oh! You're clever.
Good idea. Show me the list."
Good idea. Show me the list."
93
254170
3149
有很多药物
但并不令人兴奋
但并不令人兴奋
04:29
And there's a bunch of drugs,
not very exciting.
not very exciting.
94
257343
2254
但在列表上有两种药物
吸引了我的眼球：
吸引了我的眼球：
04:31
But what caught my eye
was, on the list there were two drugs:
was, on the list there were two drugs:
95
259621
3932
paroxetine, 或 Paxil，
一种抗抑郁药物
一种抗抑郁药物
04:35
paroxetine, or Paxil, an antidepressant;
96
263577
3393
04:39
and pravastatin, or Pravachol,
a cholesterol medication.
a cholesterol medication.
97
267756
3570
和pravastatin, 或Pravachol，
抗胆固醇药物
抗胆固醇药物
04:43
And I said, "Huh. There are millions
of Americans on those two drugs."
of Americans on those two drugs."
98
271936
4283
然后我说，“呵
上百万的美国人都在用这两种药物。”
上百万的美国人都在用这两种药物。”
事实上，我们后来知道，
04:48
In fact, we learned later,
99
276243
1246
04:49
15 million Americans on paroxetine
at the time, 15 million on pravastatin,
at the time, 15 million on pravastatin,
100
277513
6032
一千五百万的美国人在用paroxetine
而同时 一千五百万人服用pravastatin
而同时 一千五百万人服用pravastatin
我们估计 有一百万人 两者同时服用
04:55
and a million, we estimated, on both.
101
283569
2817
所以是一百万人
04:58
So that's a million people
102
286767
1254
可能在血糖上会有问题
05:00
who might be having some problems
with their glucose
with their glucose
103
288045
2453
但会不会他在FDA数据库
的异想天开
的异想天开
05:02
if this machine-learning mumbo jumbo
that he did in the FDA database
that he did in the FDA database
104
290522
3206
05:05
actually holds up.
105
293752
1254
只是瞎猫碰上了死老鼠呢？
05:07
But I said, "It's still not publishable,
106
295030
1927
但我说，“还是不能发表。”
因为我喜欢你用搜索技术
05:08
because I love what you did
with the mumbo jumbo,
with the mumbo jumbo,
107
296981
2296
所做出来的奇思妙想
05:11
with the machine learning,
108
299301
1246
但它不是我们真正的标准证据
05:12
but it's not really standard-of-proof
evidence that we have."
evidence that we have."
109
300571
3864
所以我们必须再做些其他的
05:17
So we have to do something else.
110
305618
1589
让我们进入斯坦福的医疗记录电子库
05:19
Let's go into the Stanford
electronic medical record.
electronic medical record.
111
307231
2876
我们有拷贝权，搜索时许可的
05:22
We have a copy of it
that's OK for research,
that's OK for research,
112
310131
2064
我们挪开了个人信息
05:24
we removed identifying information.
113
312219
2046
然后我说，
“让我们看看同时服用这两种药物的人
“让我们看看同时服用这两种药物的人
05:26
And I said, "Let's see if people
on these two drugs
on these two drugs
114
314581
2503
和他们的血糖问题。”
05:29
have problems with their glucose."
115
317108
1769
在斯坦福的医疗记录里
有成千上万的人
有成千上万的人
05:31
Now there are thousands
and thousands of people
and thousands of people
116
319242
2207
05:33
in the Stanford medical records
that take paroxetine and pravastatin.
that take paroxetine and pravastatin.
117
321473
3459
在服用paroxetine and pravastatin
但我们需要很特别的病人
05:36
But we needed special patients.
118
324956
1799
我们需要服用其中一种药物的病人
有血糖纪录
有血糖纪录
05:38
We needed patients who were on one of them
and had a glucose measurement,
and had a glucose measurement,
119
326779
4597
05:43
then got the second one and had
another glucose measurement,
another glucose measurement,
120
331400
3449
然后在服用第二种以后
有另一次血糖纪录
有另一次血糖纪录
并且是在一个比较合理的阶段以内
比如像两个月
比如像两个月
05:46
all within a reasonable period of time --
something like two months.
something like two months.
121
334873
3615
当我们这样做以后
我们发现了10个病人
我们发现了10个病人
05:50
And when we did that,
we found 10 patients.
we found 10 patients.
122
338512
3159
然而，10个中有8个在血糖上有变化
05:54
However, eight out of the 10
had a bump in their glucose
had a bump in their glucose
123
342592
4538
当他们服用第二个P药物的时候
我们把这个叫做P和P--
我们把这个叫做P和P--
05:59
when they got the second P --
we call this P and P --
we call this P and P --
124
347154
2645
当他们服用第二个P时
06:01
when they got the second P.
125
349823
1310
可以是任意一个在先
第二个服用后
第二个服用后
06:03
Either one could be first,
the second one comes up,
the second one comes up,
126
351157
2562
血糖升高了20mg／dl
06:05
glucose went up
20 milligrams per deciliter.
20 milligrams per deciliter.
127
353743
2847
给一个小小的提示
06:08
Just as a reminder,
128
356614
1158
当你没有糖尿病
正常的四处活动时
正常的四处活动时
06:09
you walk around normally,
if you're not diabetic,
if you're not diabetic,
129
357796
2325
你的血糖是90
06:12
with a glucose of around 90.
130
360145
1359
如果升高到120， 125，
06:13
And if it gets up to 120, 125,
131
361528
2076
你的医生会认为是潜在的糖尿病。
06:15
your doctor begins to think
about a potential diagnosis of diabetes.
about a potential diagnosis of diabetes.
132
363628
3450
所以 一个20 的升高－－太明显了。
06:19
So a 20 bump -- pretty significant.
133
367102
2991
我说，“尼克，这太好了。
06:22
I said, "Nick, this is very cool.
134
370601
1904
但很抱歉，我们还是没有文章
06:25
But, I'm sorry, we still
don't have a paper,
don't have a paper,
135
373616
2053
因为这是10个病人，而且
让我想想
让我想想
06:27
because this is 10 patients
and -- give me a break --
and -- give me a break --
136
375693
2579
没有足够的病人。“
06:30
it's not enough patients."
137
378296
1245
06:31
So we said, what can we do?
138
379565
1306
所以我们说 我们还能怎么做呢？
后来我们决定打电话
给我们在Harvard和Vanderbilt的朋友
给我们在Harvard和Vanderbilt的朋友
06:32
And we said, let's call our friends
at Harvard and Vanderbilt,
at Harvard and Vanderbilt,
139
380895
2976
在波士顿的哈佛和纳什维尔的
范德比尔
范德比尔
06:35
who also -- Harvard in Boston,
Vanderbilt in Nashville,
Vanderbilt in Nashville,
140
383895
2587
06:38
who also have electronic
medical records similar to ours.
medical records similar to ours.
141
386506
2821
也都有和我们相似的医疗电子记录
我们想看看他们是否能够找到
相似的病人
相似的病人
06:41
Let's see if they can find
similar patients
similar patients
142
389351
2020
服用一种P， 然后另一种P
06:43
with the one P, the other P,
the glucose measurements
the glucose measurements
143
391395
3276
并在我们需要的那个范围内
做过血糖检测
做过血糖检测
06:46
in that range that we need.
144
394695
1600
上帝祝福他们。范德贝尔
在一周内发现40个这样的病人
在一周内发现40个这样的病人
06:48
God bless them, Vanderbilt
in one week found 40 such patients,
in one week found 40 such patients,
145
396787
4955
都有同样的血糖增长
06:53
same trend.
146
401766
1189
06:55
Harvard found 100 patients, same trend.
147
403804
3620
哈佛发现100个同样的病人，
也有着一样的增长
也有着一样的增长
所以，最后我们有150个病人
来自三个不同的的医学中心
来自三个不同的的医学中心
06:59
So at the end, we had 150 patients
from three diverse medical centers
from three diverse medical centers
148
407448
4281
这150个病人的记录告诉我们
这些使用这两种药物的病人
这些使用这两种药物的病人
07:03
that were telling us that patients
getting these two drugs
getting these two drugs
149
411753
3297
在某种程度上都有血糖的明显改变
07:07
were having their glucose bump
somewhat significantly.
somewhat significantly.
150
415074
2703
更令人感兴趣的是
我们没有算上糖尿病人
我们没有算上糖尿病人
07:10
More interestingly,
we had left out diabetics,
we had left out diabetics,
151
418317
2810
因为糖尿病人的血糖本身就是
一本糊涂账
一本糊涂账
07:13
because diabetics already
have messed up glucose.
have messed up glucose.
152
421151
2317
当我们查看糖尿病人的血糖
07:15
When we looked
at the glucose of diabetics,
at the glucose of diabetics,
153
423492
2238
它通常是升高60mg以上
而不是只有20
而不是只有20
07:17
it was going up 60 milligrams
per deciliter, not just 20.
per deciliter, not just 20.
154
425754
3435
这是一个了不起的结果。然后我们说，
“我们一定要发表这个结果。”
“我们一定要发表这个结果。”
07:21
This was a big deal, and we said,
"We've got to publish this."
"We've got to publish this."
155
429760
3452
我们呈送了文章
07:25
We submitted the paper.
156
433236
1179
全是数据证据
07:26
It was all data evidence,
157
434439
2111
来自FDA，来自斯坦福
07:28
data from the FDA, data from Stanford,
158
436574
2483
来自范德贝尔，来自哈佛
07:31
data from Vanderbilt, data from Harvard.
159
439081
1946
我们还没做一个实验
07:33
We had not done a single real experiment.
160
441051
2396
但我们很紧张
07:36
But we were nervous.
161
444495
1296
所以当文章在审查阶段
尼克去了实验室
尼克去了实验室
07:38
So Nick, while the paper
was in review, went to the lab.
was in review, went to the lab.
162
446201
3730
我们找到了一些懂得实验的人
07:41
We found somebody
who knew about lab stuff.
who knew about lab stuff.
163
449955
2462
我做不了那个活
07:44
I don't do that.
164
452441
1393
07:45
I take care of patients,
but I don't do pipettes.
but I don't do pipettes.
165
453858
2417
我看病人
我不用移液器
我不用移液器
他们教我们怎样喂老鼠吃药
07:49
They taught us how to feed mice drugs.
166
457420
3053
07:52
We took mice and we gave them
one P, paroxetine.
one P, paroxetine.
167
460864
2414
我们拿过老鼠
给它们喂一种P paroxetine
给它们喂一种P paroxetine
07:55
We gave some other mice pravastatin.
168
463302
2508
我们又给某些老鼠pravastatin.
我们给了第三组老鼠两种药
07:57
And we gave a third group
of mice both of them.
of mice both of them.
169
465834
3595
08:01
And lo and behold, glucose went up
20 to 60 milligrams per deciliter
20 to 60 milligrams per deciliter
170
469893
3946
老鼠的血糖
升高了20-60毫克／分升
08:05
in the mice.
171
473863
1171
08:07
So the paper was accepted
based on the informatics evidence alone,
based on the informatics evidence alone,
172
475058
3158
所以 基于尽有信息考据的文章
被接受了
被接受了
但是我门在文章的结尾
加上了一个小小的注解
加上了一个小小的注解
08:10
but we added a little note at the end,
173
478240
1894
顺便说一下
如果你给老鼠喂两种药 血糖会升高
如果你给老鼠喂两种药 血糖会升高
08:12
saying, oh by the way,
if you give these to mice, it goes up.
if you give these to mice, it goes up.
174
480158
2899
这太棒了 故事在此应该了结了
08:15
That was great, and the story
could have ended there.
could have ended there.
175
483081
2508
但我还要讲六分半钟
08:17
But I still have six and a half minutes.
176
485613
1997
笑声
08:19
(Laughter)
177
487634
2807
当我们坐在一起
想着这件事时
想着这件事时
08:22
So we were sitting around
thinking about all of this,
thinking about all of this,
178
490465
2815
我记不得是谁说的了
但有人说：
但有人说：
08:25
and I don't remember who thought
of it, but somebody said,
of it, but somebody said,
179
493304
2735
“我好奇那些服用
这两种药的病人
这两种药的病人
08:28
"I wonder if patients
who are taking these two drugs
who are taking these two drugs
180
496063
3201
是否注意到自己有高血糖的症状
08:31
are noticing side effects
of hyperglycemia.
of hyperglycemia.
181
499288
3553
他们理应注意到的
08:34
They could and they should.
182
502865
1496
我们又怎样确定他们
是否真有呢
是否真有呢
08:36
How would we ever determine that?"
183
504761
1877
08:39
We said, well, what do you do?
184
507551
1443
我们说：那你怎么做呢？
“如果你在服用一种新药
或者是两种
或者是两种
08:41
You're taking a medication,
one new medication or two,
one new medication or two,
185
509018
2580
然后你有了一种奇怪的感觉
08:43
and you get a funny feeling.
186
511622
1538
你会怎么做？
08:45
What do you do?
187
513184
1151
你会在谷歌上查找
08:46
You go to Google
188
514359
1151
你会在搜索栏上打出
两种药物的名称
两种药物的名称
08:47
and type in the two drugs you're taking
or the one drug you're taking,
or the one drug you're taking,
189
515534
3349
然后输入”副作用“
08:50
and you type in "side effects."
190
518907
1603
你觉得这想法怎么样？”
08:52
What are you experiencing?
191
520534
1356
08:54
So we said OK,
192
522239
1151
于是我们说还不错
08:55
let's ask Google if they will share
their search logs with us,
their search logs with us,
193
523414
3056
我们可以试着问问谷歌
他们能不能与我们分享搜索记录
他们能不能与我们分享搜索记录
然后我们可以通过这些搜索记录
08:58
so that we can look at the search logs
194
526494
1833
09:00
and see if patients are doing
these kinds of searches.
these kinds of searches.
195
528351
2565
进而知道病人是否在做这种搜索
很遗憾的是，谷歌拒绝了我们的请求
09:02
Google, I am sorry to say,
denied our request.
denied our request.
196
530940
3275
于是我有点闷闷不乐
09:06
So I was bummed.
197
534819
1151
当时我在和一个微软公司的同事吃饭
09:07
I was at a dinner with a colleague
who works at Microsoft Research
who works at Microsoft Research
198
535994
3166
我说：”我们想要做一个调查，
09:11
and I said, "We wanted to do this study,
199
539184
1941
但谷歌拒绝了，这真令人烦恼”
09:13
Google said no, it's kind of a bummer."
200
541149
1880
他说“哦，我们有必应bing搜索啊”
09:15
He said, "Well, we have
the Bing searches."
the Bing searches."
201
543053
2086
（笑声）
09:18
(Laughter)
202
546195
3483
是的
09:22
Yeah.
203
550805
1267
09:24
That's great.
204
552096
1151
这太棒了
我感觉我就像要...了一样
09:25
Now I felt like I was --
205
553271
1151
（笑声）
09:26
(Laughter)
206
554446
1000
09:27
I felt like I was talking to Nick again.
207
555470
2412
我感觉我就像又在和尼克说话了
他在全世界最大的公司工作
09:30
He works for one of the largest
companies in the world,
companies in the world,
208
558437
2624
我不想伤害他的自信心
09:33
and I'm already trying
to make him feel better.
to make him feel better.
209
561085
2206
但他说：“不，罗斯...
你可能不知道
你可能不知道
09:35
But he said, "No, Russ --
you might not understand.
you might not understand.
210
563315
2445
我们不只有必应bing
09:37
We not only have Bing searches,
211
565784
1500
但是如果你用IE浏览器
在谷歌上搜索词条
在谷歌上搜索词条
09:39
but if you use Internet Explorer
to do searches at Google,
to do searches at Google,
212
567308
3340
或是在雅虎，bing上
09:42
Yahoo, Bing, any ...
213
570672
1891
然后我们将这些搜索信息
为了学术目的自动保存18个月
为了学术目的自动保存18个月
09:44
Then, for 18 months, we keep that data
for research purposes only."
for research purposes only."
214
572587
3643
我于是说：”你真有两下子！“
09:48
I said, "Now you're talking!"
215
576254
1936
他叫 Eric Horvitz，我在微软的朋友
09:50
This was Eric Horvitz,
my friend at Microsoft.
my friend at Microsoft.
216
578214
2198
因此我们就这样做了调查
09:52
So we did a study
217
580436
1695
09:54
where we defined 50 words
that a regular person might type in
that a regular person might type in
218
582155
4619
我们先确定了高血糖症患者
可能会搜索的50个词条
09:58
if they're having hyperglycemia,
219
586798
1602
比如”疲劳“”食欲不振“”尿频“等
10:00
like "fatigue," "loss of appetite,"
"urinating a lot," "peeing a lot" --
"urinating a lot," "peeing a lot" --
220
588424
4762
10:05
forgive me, but that's one
of the things you might type in.
of the things you might type in.
221
593210
2767
不好意思，但这些是你可能输入的词语
于是我们有了50个
叫做“肥胖词语”的词条
叫做“肥胖词语”的词条
10:08
So we had 50 phrases
that we called the "diabetes words."
that we called the "diabetes words."
222
596001
2790
10:10
And we did first a baseline.
223
598815
2063
我们先是确定了基线搜索率
大概0.5-1%的网络搜索
10:12
And it turns out
that about .5 to one percent
that about .5 to one percent
224
600902
2704
10:15
of all searches on the Internet
involve one of those words.
involve one of those words.
225
603630
2982
含有一个这些词语
这就是我们的底线比率
10:18
So that's our baseline rate.
226
606636
1742
如果人们输入paroxetine或Paxil
—它们是同义词—
—它们是同义词—
10:20
If people type in "paroxetine"
or "Paxil" -- those are synonyms --
or "Paxil" -- those are synonyms --
227
608402
4143
它们其中的一个
10:24
and one of those words,
228
612569
1215
10:25
the rate goes up to about two percent
of diabetes-type words,
of diabetes-type words,
229
613808
4890
那么如果搜索者已经知道了
这个药物术语的话
这个药物术语的话
则在肥胖类内容的搜索中
它们出现的概率升高到了大约2%
它们出现的概率升高到了大约2%
10:30
if you already know
that there's that "paroxetine" word.
that there's that "paroxetine" word.
230
618722
3044
如果是pravastatin
概率则超过了基线3%
概率则超过了基线3%
10:34
If it's "pravastatin," the rate goes up
to about three percent from the baseline.
to about three percent from the baseline.
231
622191
4547
如果paroxetine和pravastatin同时出现
10:39
If both "paroxetine" and "pravastatin"
are present in the query,
are present in the query,
232
627171
4390
那么比例则到达了10%
10:43
it goes up to 10 percent,
233
631585
1669
这是在那些肥胖类或高血糖类
搜索中
搜索中
10:45
a huge three- to four-fold increase
234
633278
3461
出现我们研究的两种药物的概率的
10:48
in those searches with the two drugs
that we were interested in,
that we were interested in,
235
636763
3389
三至四倍的增长
10:52
and diabetes-type words
or hyperglycemia-type words.
or hyperglycemia-type words.
236
640176
3566
我们发表了这个结果
10:56
We published this,
237
644216
1265
获取了一些注意
10:57
and it got some attention.
238
645505
1466
这个研究值得注意的原因是
10:58
The reason it deserves attention
239
646995
1778
病人在通过他们的网上搜索
11:00
is that patients are telling us
their side effects indirectly
their side effects indirectly
240
648797
4312
向我们间接地传达他们的副作用
11:05
through their searches.
241
653133
1156
我们吸引了FDA的注意
11:06
We brought this
to the attention of the FDA.
to the attention of the FDA.
242
654313
2138
他们很感兴趣
11:08
They were interested.
243
656475
1269
他们建立了社交网站监测项目
11:09
They have set up social media
surveillance programs
surveillance programs
244
657768
3606
和有着可以完成这些项目的设施的
11:13
to collaborate with Microsoft,
245
661398
1751
11:15
which had a nice infrastructure
for doing this, and others,
for doing this, and others,
246
663173
2794
微软合作
在推特网页上
11:17
to look at Twitter feeds,
247
665991
1282
脸书上
11:19
to look at Facebook feeds,
248
667297
1716
观察人们的搜索内容
11:21
to look at search logs,
249
669037
1311
11:22
to try to see early signs that drugs,
either individually or together,
either individually or together,
250
670372
4909
以此来发现一种或多种药物
可能在产生问题的
可能在产生问题的
早期迹象
11:27
are causing problems.
251
675305
1589
11:28
What do I take from this?
Why tell this story?
Why tell this story?
252
676918
2174
那么我们由此学到了什么？
为什么讲这个故事？
为什么讲这个故事？
第一
11:31
Well, first of all,
253
679116
1207
我们现在有了大数据的支持
11:32
we have now the promise
of big data and medium-sized data
of big data and medium-sized data
254
680347
4037
来帮助我们了解药物的相互作用
11:36
to help us understand drug interactions
255
684408
2918
更本上就是药物的机理
11:39
and really, fundamentally, drug actions.
256
687350
2420
11:41
How do drugs work?
257
689794
1413
药物是怎样起效的？
这已经创造了一种新的系统
11:43
This will create and has created
a new ecosystem
a new ecosystem
258
691231
2836
来了解药物的工作原理
以及优化它们的使用
以及优化它们的使用
11:46
for understanding how drugs work
and to optimize their use.
and to optimize their use.
259
694091
3267
尼克继续从事着这事
他现在是哥伦比亚大学的教授
他现在是哥伦比亚大学的教授
11:50
Nick went on; he's a professor
at Columbia now.
at Columbia now.
260
698303
2659
他在他的PhD中研究了
成百对的药物
成百对的药物
11:52
He did this in his PhD
for hundreds of pairs of drugs.
for hundreds of pairs of drugs.
261
700986
4072
他发现了几种十分重要的药物反应
11:57
He found several
very important interactions,
very important interactions,
262
705082
2517
于是我们记录了这些结果
11:59
and so we replicated this
263
707623
1214
而且我们展示了这种方法
12:00
and we showed that this
is a way that really works
is a way that really works
264
708861
2574
在发现药物相互作用上的可行性
12:03
for finding drug-drug interactions.
265
711459
2339
然而，这有几件事
12:06
However, there's a couple of things.
266
714282
1734
我们不只是研究一对药物
12:08
We don't just use pairs
of drugs at a time.
of drugs at a time.
267
716040
3046
像我之前说的，有的人同时服用
3.5.7.9种药物
3.5.7.9种药物
12:11
As I said before, there are patients
on three, five, seven, nine drugs.
on three, five, seven, nine drugs.
268
719110
4469
12:15
Have they been studied with respect
to their nine-way interaction?
to their nine-way interaction?
269
723981
3642
他们的九种药物反应有被研究过吗？
是的，我们确实可以用排列组合
a和b,a和c,a和d
a和b,a和c,a和d
12:19
Yes, we can do pair-wise,
A and B, A and C, A and D,
A and B, A and C, A and D,
270
727647
4208
12:23
but what about A, B, C,
D, E, F, G all together,
D, E, F, G all together,
271
731879
4286
但如果是a,b,c,d,e,f,g全部混在一起呢？
它们被同一个患者服用
12:28
being taken by the same patient,
272
736189
1762
可能会和对方反应
12:29
perhaps interacting with each other
273
737975
2118
有可能是让药效增强或是减弱
12:32
in ways that either makes them
more effective or less effective
more effective or less effective
274
740117
3778
更甚是始料不及的副作用？
12:35
or causes side effects
that are unexpected?
that are unexpected?
275
743919
2332
我们真不知道
12:38
We really have no idea.
276
746275
1827
我们可以很自由地使用数据
12:40
It's a blue sky, open field
for us to use data
for us to use data
277
748126
3756
来了解药物的协同机理
12:43
to try to understand
the interaction of drugs.
the interaction of drugs.
278
751906
2502
另外两个教训：
12:46
Two more lessons:
279
754848
1370
我想让你们想想
我们使用人们
我们使用人们
12:48
I want you to think about the power
that we were able to generate
that we were able to generate
280
756242
4199
通过他们的药师，医生或是自己
上传的药物反作用案例
上传的药物反作用案例
12:52
with the data from people who had
volunteered their adverse reactions
volunteered their adverse reactions
281
760465
4711
那些为斯坦福，哈佛和范德比尔数据库
提供了资料的案例
提供了资料的案例
12:57
through their pharmacists,
through themselves, through their doctors,
through themselves, through their doctors,
282
765200
3269
来用作研究
13:00
the people who allowed the databases
at Stanford, Harvard, Vanderbilt,
at Stanford, Harvard, Vanderbilt,
283
768493
3667
能够产生的力量有多大
13:04
to be used for research.
284
772184
1427
13:05
People are worried about data.
285
773929
1445
人们担心自己的数据被泄露
他们害怕自己的隐私和信息安全被偷取
--他们理应这样想
--他们理应这样想
13:07
They're worried about their privacy
and security -- they should be.
and security -- they should be.
286
775398
3187
因此我们需要安全的网络系统
13:10
We need secure systems.
287
778609
1151
但是我们不应该容忍那些
垄断这些数据的网络系统
垄断这些数据的网络系统
13:11
But we can't have a system
that closes that data off,
that closes that data off,
288
779784
3406
因为网络资源是在药理方面
13:15
because it is too rich of a source
289
783214
2752
创造灵感，创新和发现的
13:17
of inspiration, innovation and discovery
290
785990
3971
强大资源
13:21
for new things in medicine.
291
789985
1578
我最后想说的是
13:24
And the final thing I want to say is,
292
792494
1794
在这个案例中
我们发现了两种药物，十分遗憾
我们发现了两种药物，十分遗憾
13:26
in this case we found two drugs
and it was a little bit of a sad story.
and it was a little bit of a sad story.
293
794312
3357
这两种药物实际上产生了麻烦
13:29
The two drugs actually caused problems.
294
797693
1921
它们增加血糖含量
13:31
They increased glucose.
295
799638
1475
它们可能让
原本没有糖尿病的人
原本没有糖尿病的人
13:33
They could throw somebody into diabetes
296
801137
2446
患上糖尿病
13:35
who would otherwise not be in diabetes,
297
803607
2294
所以当你同时使用这两种药时
会千万小心
会千万小心
13:37
and so you would want to use
the two drugs very carefully together,
the two drugs very carefully together,
298
805925
3175
分开用时也是
13:41
perhaps not together,
299
809124
1151
订购药物时做出其他选择
13:42
make different choices
when you're prescribing.
when you're prescribing.
300
810299
2340
但也有另一种可能
13:44
But there was another possibility.
301
812663
1846
我们可能可以发现
二至三种药物
二至三种药物
13:46
We could have found
two drugs or three drugs
two drugs or three drugs
302
814533
2344
能通过有益的方式相互反应
13:48
that were interacting in a beneficial way.
303
816901
2261
我们也可以发现药物的新作用
13:51
We could have found new effects of drugs
304
819616
2712
单独不具有的
13:54
that neither of them has alone,
305
822352
2160
但是在一起服用，
不是产生副作用
不是产生副作用
13:56
but together, instead
of causing a side effect,
of causing a side effect,
306
824536
2493
而是成为一种新型治疗手段
13:59
they could be a new and novel treatment
307
827053
2425
治疗那些无药可医的病症
14:01
for diseases that don't have treatments
308
829502
1882
或是旧的治疗方法效果不明显的疾病
14:03
or where the treatments are not effective.
309
831408
2007
如果我们今天纵观药物治疗
14:05
If we think about drug treatment today,
310
833439
2395
所有的重大突破--
14:07
all the major breakthroughs --
311
835858
1752
治疗艾滋病，肺结核，抑郁症
或是糖尿病的--
或是糖尿病的--
14:09
for HIV, for tuberculosis,
for depression, for diabetes --
for depression, for diabetes --
312
837634
4297
14:13
it's always a cocktail of drugs.
313
841955
2830
都是几种药物的混合疗法
所以我们目前所做的
14:16
And so the upside here,
314
844809
1730
也是TED大会今后探讨的话题
14:18
and the subject for a different
TED Talk on a different day,
TED Talk on a different day,
315
846563
2849
就是我们怎样使用同样的数据资源
14:21
is how can we use the same data sources
316
849436
2593
来寻找药物混合使用后的好处
14:24
to find good effects
of drugs in combination
of drugs in combination
317
852053
3563
这将会为我们提供新的疗法
14:27
that will provide us new treatments,
318
855640
2175
药物工作原理的新视角
14:29
new insights into how drugs work
319
857839
1852
14:31
and enable us to take care
of our patients even better?
of our patients even better?
320
859715
3786
使我们可以更好地治愈我们的病人
十分感谢
14:35
Thank you very much.
321
863525
1166
掌声
14:36
(Applause)
322
864715
3499
Subtitled by:治洋 Liu
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