Transcript budge_2

Implementing the DxCG Likelihood of
Hospitalization Model in Kaiser Permanente
Leslee J Budge, MBA
[email protected]
Kaiser Permanente is the largest non-profit health
care program in the United States
 8.5 million members
 8 regions in 9 states
and D.C.
 30 hospitals
 431 medical offices
 13,000 physicians
 150,000 employees
 $35 billion in revenue
2
© Copyright Kaiser Permanente
Kaiser Permanente is an integrated care delivery
organization with aligned quality-based incentives
Permanente
Medical
Group
Health Plan
Members
Kaiser
Foundation
Hospitals
3
© Copyright Kaiser Permanente
Kaiser
Foundation
Health Plan
We have multiple approaches for providing care to our
member, whether they have a chronic illness or are healthy
• Program-wide electronic
health record
• Electronic registries to identify
members with chronic
conditions
• Programs for members who
need complex care
• Programs for members with
chronic conditions
 Primary care physician care
supported by a healthcare
team
4
© Copyright Kaiser Permanente
Complex
Care
Care
Management
Primary Care &
Panel Management
We identify members for specialized programs using rulesbased methodologies
Age Group-Specific Scoring System
Because of our
integrated structure
and rapid access to
clinical information, we
have relied on
utilization or laboratory
results for member
selection
5
© Copyright Kaiser Permanente
If in this Age Group:
Under 65
65 to 84
85 Plus
Sum these risk factor points:
Risk Factors
Age 45-54
2
Age 55-64
3
Age 75-84
3
Male
2
2
CHF
6
10
3
Diabetes
5
6
2
Smoker
4
5
0
Recent AMI
7
11
6
Max Score
(Sum of All Points)
27
37
13
We believed we could do a better job at targeting members
for specialized programs
The aim of KP’s
predictive modeling
pilot is to determine
the effectiveness of
predictive modeling
to identify members
at future risk for:
– utilization
– poor health outcomes
– cost
6
© Copyright Kaiser Permanente
1% of people
% of
Health care
Costs
100%
80%
30% total
cost
60%
40%
Premium level
20%
10% total cost
0% total cost
0%
0%
20%
20% of people
40%
60%
80%
70% of people
100%

% of
People
KP Southern California used the LOH in one medical center
to select members for their CCM* program
What they found:
 Comparing two DxCG models: LOH and
DCG Prospective
 Members on LOH list are older, sicker,
and more are at end-of-life.
 25 patients of the 200 had died in the first month,
prior to intervention
 25 of the patients where on both high-risk lists
 118 of the 200 were appropriate for the active
CCM program
*Chronic Conditions Management
7
© Copyright Kaiser Permanente
KP Ohio region is using the LOH to identify members for
their Advanced Care Panel pilot
Advanced Care Panel:
100-200 “Resource Intensive Members” are
being assigned to a physician and health care
team. The care process includes:
– Transition between care settings
– Enhanced ease of access
– Supportive end-of-life care
% of
Health care
Costs
1% of people
100%
80%
30% total
cost
60%
40%
Premium level
20%
10% total cost
0% total cost
0%
0%
20%
20% of people
8
© Copyright Kaiser Permanente
40%
60%
80%
70% of people
100%

% of
People
Members selected for Ohio’s Advanced Care Panel
Selecting members for the advance care panel
– Produced the LOH scores for the top 1% of 140,100
commercial members
– Filtered list to exclude diagnosis groups of cancer,
neonates, trauma, end stage renal disease, and
schizophrenia
– 122 of the 458 remaining members had either
diabetes, HF or both and met the initial criteria for
Advanced Care Panel
 LOH score for this group ranged from 0.879 to 0.167
 Baseline costs ranged from $12K to $165K
9
© Copyright Kaiser Permanente
Ohio’s reaction to the LOH results has been favorable, in fact
they were surprised a model could be so ‘good’
 The physicians reviewed charts of the first 68
members and found they were good candidates
for the program
 In the first group of eligible members reached
– 53% said yes to participation
 Reasons for non-participation
– Need to think about it
– Not sure about program
– Do not want to leave PCP
10 © Copyright Kaiser Permanente
Understand predictive modeling
Dr. Smith reported that one of the patients
identified reported no hospitalizations or ED visits
recently but still was on the top 1% list.
How did he get on the top 1% list?
By-the-way--- he has many comorbidities.
© Copyright Kaiser Permanente
The member’s score is only 0.4—why is she in the top 1%?
Top 1%
LOH Distribution in OH total Membership
100.00%
90.00%
Percent of Membership
80.00%
70.00%
60.00%
50.00%
40.00%
30.00%
LOH 0.357
20.00%
10.00%
0.00%
0 0.099
% of total 93.35%
0.1 0.199
0.2 0.299
0.3 0.399
0.4 0.499
0.5 0.599
0.6 0.699
0.7 0.799
0.8 0.899
0.9 1.00
4.15%
1.14%
0.56%
0.28%
0.18%
0.13%
0.09%
0.06%
0.05%
LOH Score
© Copyright Kaiser Permanente
What have we learned?
 First, to accept predictive modeling our
physicians need to ‘see’ that it is an effective
tool for selecting member for specialized programs
 Second, the challenge is not running the model but
getting the results into the hands of the people who will
enroll members in the program
 We have struggled with the questions of:
– What do you want to predict?
– What are you going to do with the results?
 The Resource Intensive Member program has helped us
answer these two questions
13 © Copyright Kaiser Permanente
Ongoing evaluation: Searching for evidence
of impactability…
Our hypothesis: specific care in the 6 months
prior to a predicted hospitalization will help to
avoid the hospitalization
Assumption: hospitalization for members with left
ventricular systolic dysfunction is a function of
– Physician visits
– Use of evidence-based medications
14 © Copyright Kaiser Permanente
Defining the study and control groups
 1822 NW region members in the top 1% with a
diagnosis of heart failure in the evaluation period
 Study population: members with a heart failure
HCC who were hospitalized at least once for any
reason in the evaluation period (N = 1468)
 Control population: members with a heart failure
HCC who were NOT hospitalized during the
same time period (N = 354)
15 © Copyright Kaiser Permanente
Data to evaluate Impactability
In the 6 months prior to the predicted
hospitalization collect the following data:
– Number of PCP visits
– Number of specialty care visits
– Number of hospital admissions
– Number of ED visits
– Ejection fraction value
– Rx for beta-blocker (yes/no)
– Rx for ACE-I or ARB (yes/no)
– Rx for spironolactone (yes/no)
© Copyright Kaiser Permanente
Results of evaluation for impactability…
Work in process
© Copyright Kaiser Permanente
Questions
18 © Copyright Kaiser Permanente