1
00:00:04,500 --> 00:00:07,510
To build an analytics model,
let us discuss the variables

2
00:00:07,510 --> 00:00:09,850
we used.

3
00:00:09,850 --> 00:00:13,280
First, we used the
13,000 diagnoses.

4
00:00:13,280 --> 00:00:18,580
It's for the codes for diagnosis
that claims data utilize.

5
00:00:18,580 --> 00:00:21,970
There were also 22,000
different codes for procedures

6
00:00:21,970 --> 00:00:24,910
and 45,000 codes for
prescription drugs.

7
00:00:24,910 --> 00:00:29,380
To work with this massive
amount of variables,

8
00:00:29,380 --> 00:00:32,150
we aggregated the
variables as follows.

9
00:00:32,150 --> 00:00:39,500
Out of the 13,000 diagnoses, we
defined 217 diagnosis groups.

10
00:00:39,500 --> 00:00:43,730
Out of the 20,000 procedures,
we aggregated the data

11
00:00:43,730 --> 00:00:46,410
to develop 213 procedure groups.

12
00:00:46,410 --> 00:00:49,330
And, finally, from 45,000
prescription drugs,

13
00:00:49,330 --> 00:00:54,530
we developed 189
therapeutic groups.

14
00:00:54,530 --> 00:00:58,620
To illustrate an example of how
we infer further information

15
00:00:58,620 --> 00:01:03,340
from the data, the
graph here shows

16
00:01:03,340 --> 00:01:08,190
on the horizontal axis, time,
and on the vertical axis,

17
00:01:08,190 --> 00:01:13,280
costs in thousands of dollars.

18
00:01:13,280 --> 00:01:23,190
So patient one is a patient
who, on a monthly basis,

19
00:01:23,190 --> 00:01:29,289
has costs on the order of
$10,000 to $15,000, a fairly

20
00:01:29,289 --> 00:01:32,570
significant cost but
fairly constant in time.

21
00:01:32,570 --> 00:01:37,340
Patient two has
also an annual cost

22
00:01:37,340 --> 00:01:39,590
of a similar size
to patient one.

23
00:01:39,590 --> 00:01:45,620
But in all but the third
month, the costs are almost $0.

24
00:01:45,620 --> 00:01:51,250
Whereas in the third month,
it cost about $70,000.

25
00:01:51,250 --> 00:01:53,020
In fact, this is
additional data we

26
00:01:53,020 --> 00:01:59,140
defined indicating
whether the patient has

27
00:01:59,140 --> 00:02:01,560
a chronic or an acute condition.

28
00:02:01,560 --> 00:02:06,360
In addition to the initial
variables, the 217 procedure

29
00:02:06,360 --> 00:02:10,150
groups, and 189 drugs,
and so forth, we also

30
00:02:10,150 --> 00:02:13,240
defined in collaboration
with medical doctors,

31
00:02:13,240 --> 00:02:17,450
269 medically-defined rules.

32
00:02:17,450 --> 00:02:20,320
For example, the
first type of rule

33
00:02:20,320 --> 00:02:23,960
indicates the interaction
between various indices.

34
00:02:23,960 --> 00:02:26,620
For example, obesity
and depression.

35
00:02:36,460 --> 00:02:39,440
Then new variables
regarding interaction

36
00:02:39,440 --> 00:02:41,110
between diagnosis and age.

37
00:02:41,110 --> 00:02:44,950
For example, more than
65 years old and coronary

38
00:02:44,950 --> 00:02:45,610
artery disease.

39
00:02:50,480 --> 00:02:51,690
Noncompliance with treatment.

40
00:02:51,690 --> 00:02:55,930
For example, non-fulfillment
of a particular drug order.

41
00:02:55,930 --> 00:02:58,790
And, finally, illness severity.

42
00:02:58,790 --> 00:03:01,000
For example, severe
depression as

43
00:03:01,000 --> 00:03:02,620
opposed to regular depression.

44
00:03:05,520 --> 00:03:09,520
And the last set of variables
involve demographic information

45
00:03:09,520 --> 00:03:11,080
like gender and age.

46
00:03:15,300 --> 00:03:18,600
An important aspect
of the variables

47
00:03:18,600 --> 00:03:22,380
are the variables
related to cost.

48
00:03:22,380 --> 00:03:24,590
So rather than using
costs directly,

49
00:03:24,590 --> 00:03:31,079
we bucketed costs and considered
everyone in the group equally.

50
00:03:31,079 --> 00:03:34,460
So we defined five buckets.

51
00:03:34,460 --> 00:03:37,579
So the buckets were
partitioned in such a way

52
00:03:37,579 --> 00:03:45,570
so that 20% of all
costs is in bucket five,

53
00:03:45,570 --> 00:03:49,700
20% is in bucket
four, and so forth.

54
00:03:52,520 --> 00:03:58,920
So the partitions were from 0
to 3,000, from 3,000 to 8,000,

55
00:03:58,920 --> 00:04:04,000
from 8,000 to 19,000,
from 19,000 to 55,000,

56
00:04:04,000 --> 00:04:06,580
and above 55,000.

57
00:04:06,580 --> 00:04:13,360
The number of patients
that were below 3,000

58
00:04:13,360 --> 00:04:22,180
was-- 78% of the patients
had costs below 3,000.

59
00:04:22,180 --> 00:04:26,010
Just to remind you,
we created a bucket

60
00:04:26,010 --> 00:04:30,980
so that the total cost in each
bucket was 20% of the total.

61
00:04:30,980 --> 00:04:33,840
But the number of patients
in bucket one, for example,

62
00:04:33,840 --> 00:04:34,670
is very high (78%).

63
00:04:37,170 --> 00:04:41,250
Let us interpret the
buckets medically.

64
00:04:41,250 --> 00:04:44,540
So this shows the
various levels of risk.

65
00:04:44,540 --> 00:04:50,170
Bucket one consists of patients
that have rather low risk.

66
00:04:50,170 --> 00:04:54,400
Bucket two has what is
called emerging risk.

67
00:04:54,400 --> 00:04:57,460
In bucket three,
moderate level of risk.

68
00:04:57,460 --> 00:04:59,230
Bucket four, high risk.

69
00:04:59,230 --> 00:05:01,880
And bucket five, very high risk.

70
00:05:01,880 --> 00:05:04,930
So from a medical perspective,
buckets two and three,

71
00:05:04,930 --> 00:05:07,820
the medical and the
moderate risk patients,

72
00:05:07,820 --> 00:05:11,620
are candidates for
wellness programs.

73
00:05:11,620 --> 00:05:13,920
Whereas bucket four,
the high risk patients,

74
00:05:13,920 --> 00:05:16,740
are candidates for disease
management programs.

75
00:05:16,740 --> 00:05:20,210
And finally bucket five,
the very high risk patients,

76
00:05:20,210 --> 00:05:22,590
are candidates for
case management.