1
00:00:04,810 --> 00:00:09,240
So let us explain
what claims data is.

2
00:00:09,240 --> 00:00:17,720
So medical claims are generated
when a patient visits a doctor.

3
00:00:17,720 --> 00:00:22,600
Medical claims include diagnosis
code, procedures codes,

4
00:00:22,600 --> 00:00:25,370
as well as costs.

5
00:00:25,370 --> 00:00:31,070
Pharmacy claims involve drugs,
the quantity of these drugs,

6
00:00:31,070 --> 00:00:36,150
the prescribing doctor, as
well as the medication costs.

7
00:00:36,150 --> 00:00:39,500
Claims data are
electronically available, they

8
00:00:39,500 --> 00:00:43,490
are standardized, they use
well-established codes.

9
00:00:43,490 --> 00:00:45,630
However, since
humans generate them,

10
00:00:45,630 --> 00:00:47,980
they are not 100% accurate.

11
00:00:47,980 --> 00:00:52,250
And often, under-reporting
is common in the sense

12
00:00:52,250 --> 00:00:55,730
that it's a tedious job
to record these claims,

13
00:00:55,730 --> 00:00:58,320
and as a result, often
people under-report them.

14
00:00:58,320 --> 00:01:03,950
Also, claims for hospital
visits can be vague.

15
00:01:03,950 --> 00:01:07,430
In creating a data
set, our objective

16
00:01:07,430 --> 00:01:11,590
was to assess quality,
health care quality.

17
00:01:11,590 --> 00:01:15,820
So we used a large health
insurance claims database,

18
00:01:15,820 --> 00:01:22,270
and we randomly selected
131 diabetes patients.

19
00:01:22,270 --> 00:01:27,360
The ages ranged between
35 to 55 and the costs

20
00:01:27,360 --> 00:01:32,340
were in the neighborhood
of $10,000 to $20,000.

21
00:01:32,340 --> 00:01:35,190
The period in which these
claims were recorded

22
00:01:35,190 --> 00:01:41,780
were September 1, 2003
to August 31, 2005.

23
00:01:41,780 --> 00:01:44,590
An expert physician
reviewed the claims

24
00:01:44,590 --> 00:01:48,020
and wrote descriptive
notes, like "ongoing use

25
00:01:48,020 --> 00:01:52,210
of narcotics"; "only on Avandia,
not a good first choice drug";

26
00:01:52,210 --> 00:01:55,140
"had regular visits,
mammogram, and immunizations";

27
00:01:55,140 --> 00:01:59,100
"was given home
testing supplies".

28
00:01:59,100 --> 00:02:02,810
After this review,
this expert physician

29
00:02:02,810 --> 00:02:07,520
rated the quality of care on a
two-point scale, poor or good.

30
00:02:07,520 --> 00:02:12,000
Examples included,
I'd say care was poor.

31
00:02:12,000 --> 00:02:13,080
Poorly treated diabetes.

32
00:02:13,080 --> 00:02:17,900
Not an eye exam, but overall
I'd say high quality.

33
00:02:17,900 --> 00:02:20,900
So based on these comments,
we extracted variables.

34
00:02:20,900 --> 00:02:24,070
The dependent variable
was the quality of care.

35
00:02:24,070 --> 00:02:27,720
The independent variables
involve the ongoing use

36
00:02:27,720 --> 00:02:32,150
of narcotics; only on Avandia,
not a good first choice drug;

37
00:02:32,150 --> 00:02:34,520
had regular visits,
mammogram, and immunizations;

38
00:02:34,520 --> 00:02:37,540
was given home testing supplies.

39
00:02:37,540 --> 00:02:39,660
Overall, the
independent variables

40
00:02:39,660 --> 00:02:41,900
involved diabetes
treatment variables,

41
00:02:41,900 --> 00:02:45,710
patient demographics, health
care utilization, providers,

42
00:02:45,710 --> 00:02:47,160
claims, and prescriptions.

43
00:02:50,720 --> 00:02:55,270
The dependent variable was
modeled as a binary variable --

44
00:02:55,270 --> 00:02:59,100
1 for low-quality care and
0 for high-quality care.

45
00:02:59,100 --> 00:03:01,770
This is by its nature
a categorical variable.

46
00:03:01,770 --> 00:03:05,040
It only takes two
possible values.

47
00:03:05,040 --> 00:03:08,530
We have seen linear
regression as a way

48
00:03:08,530 --> 00:03:11,740
of predicting
continuous outcomes.

49
00:03:11,740 --> 00:03:17,190
Of course, we can
utilize linear regression

50
00:03:17,190 --> 00:03:19,470
to predict quality of
care here, but then we

51
00:03:19,470 --> 00:03:22,710
have to round the
outcome to 0 or 1.

52
00:03:22,710 --> 00:03:28,260
Instead, we will
explain in this lecture

53
00:03:28,260 --> 00:03:31,090
how we can use logistic
regression, which

54
00:03:31,090 --> 00:03:33,290
is an extension of
linear regression,

55
00:03:33,290 --> 00:03:36,590
to environments where
the dependent variable is

56
00:03:36,590 --> 00:03:37,280
categorical.

57
00:03:37,280 --> 00:03:40,460
In our case, 0 or 1.