1
00:00:04,490 --> 00:00:09,180
Let us discuss data sources
in the health care industry.

2
00:00:09,180 --> 00:00:14,800
So the industry is data-rich,
but data may be hard to access.

3
00:00:14,800 --> 00:00:17,950
Sometimes it involves
unstructured data

4
00:00:17,950 --> 00:00:21,280
like doctor's notes.

5
00:00:21,280 --> 00:00:24,660
Often the data is hard
to get due to differences

6
00:00:24,660 --> 00:00:26,520
in technology.

7
00:00:26,520 --> 00:00:31,170
Hospitals in southern
Massachusetts versus California

8
00:00:31,170 --> 00:00:36,110
might use different technologies
and different platforms.

9
00:00:36,110 --> 00:00:40,460
Finally there are strong
privacy laws, HIPAA,

10
00:00:40,460 --> 00:00:42,540
around health care data sharing.

11
00:00:42,540 --> 00:00:43,420
So what is available?

12
00:00:48,170 --> 00:00:51,230
Claims data is a major source.

13
00:00:51,230 --> 00:00:54,520
Claims data are requests
for reimbursement submitted

14
00:00:54,520 --> 00:00:57,780
to insurance companies or
state-provided insurance

15
00:00:57,780 --> 00:01:00,320
from doctors, hospitals
and pharmacies.

16
00:01:03,160 --> 00:01:06,150
Another source of data is
the eligibility information

17
00:01:06,150 --> 00:01:08,660
for employees.

18
00:01:08,660 --> 00:01:12,320
And finally demographic
information: gender and age.

19
00:01:15,539 --> 00:01:20,940
Let me give you some
examples on claims data.

20
00:01:20,940 --> 00:01:25,160
So this shows six
different claims.

21
00:01:25,160 --> 00:01:28,180
Let's consider this one.

22
00:01:28,180 --> 00:01:31,560
So this is the provider's name.

23
00:01:31,560 --> 00:01:35,200
The corresponding
diagnostic code.

24
00:01:35,200 --> 00:01:41,080
This is about upper
respiratory disorders.

25
00:01:41,080 --> 00:01:46,400
This is another code
associated with the diagnosis.

26
00:01:46,400 --> 00:01:52,640
This is the scientific
term for the diagnosis.

27
00:01:52,640 --> 00:01:55,950
The specific code again.

28
00:01:55,950 --> 00:02:01,620
This was an office visit, and
it's an established patient.

29
00:02:01,620 --> 00:02:03,760
The date.

30
00:02:03,760 --> 00:02:12,460
And the amount of money that
was claimed by the physician.

31
00:02:12,460 --> 00:02:14,400
Others claims are similar.

32
00:02:17,920 --> 00:02:26,290
As we see, the claims data is
a rich, structured data source.

33
00:02:26,290 --> 00:02:29,620
It is very high dimensional.

34
00:02:29,620 --> 00:02:34,470
For example, claims
involving diagnosis

35
00:02:34,470 --> 00:02:37,329
involve thousands
of different codes.

36
00:02:37,329 --> 00:02:40,870
Similarly with drugs, where
there are tens of thousands,

37
00:02:40,870 --> 00:02:43,000
and procedures.

38
00:02:43,000 --> 00:02:46,530
However, this collection
of data does not

39
00:02:46,530 --> 00:02:49,890
capture all aspects of a
person's treatment or health.

40
00:02:49,890 --> 00:02:53,480
Many things must be inferred.

41
00:02:53,480 --> 00:02:56,300
Unlike electronic
medical records,

42
00:02:56,300 --> 00:02:58,510
we do not know the
results of a test,

43
00:02:58,510 --> 00:03:00,660
only that the test
was administered.

44
00:03:00,660 --> 00:03:07,070
For example, we do not know
the results of a blood test,

45
00:03:07,070 --> 00:03:09,240
but we do know that the
blood test was administered.

46
00:03:15,060 --> 00:03:19,550
The specific exercise we are
going to see in this lecture

47
00:03:19,550 --> 00:03:25,350
is an analytics approach
to building models starting

48
00:03:25,350 --> 00:03:28,700
with 2.4 million people
over a three year span.

49
00:03:33,150 --> 00:03:37,570
The observation period
was 2001 to 2003.

50
00:03:37,570 --> 00:03:40,270
This is where this
data is coming from.

51
00:03:40,270 --> 00:03:42,990
And then out of sample,
we make predictions

52
00:03:42,990 --> 00:03:46,590
for the period of 2003 and 2004.

53
00:03:46,590 --> 00:03:48,600
This was in the early
years of D2Hawkeye.

54
00:03:52,610 --> 00:03:56,990
Out of the 2.4 million people,
we included only people

55
00:03:56,990 --> 00:03:59,720
with data for at least 10
months in both periods,

56
00:03:59,720 --> 00:04:02,850
both in the observation
period and the results period.

57
00:04:02,850 --> 00:04:06,490
This decreased the
data to 400,000 people.