Title: Blue Cross
1Blue Cross Blue Shield of Rhode Island
New Approaches Focusing on Dynamic Variables
Related to Changes in Members Health Status
Suizhou Xue September 2008
2Background and Objectives
- Predictive Modeling at Blue Cross Blue Shield
of Rhode Island - Predictive Modeling for Underwriting Small Group
and Large Group - Predictive Modeling for Case Management
- New Approaches on Dynamic Variables for Early
Identification - Predictive Modeling for Disease Management
- Blue Health Intelligence for Risk Analysis
3History of Predictive Modelingat Blue Cross
Blue Shield of Rhode Island
Timeline
Rules based predictive models used for Case
Management identification
1990s
2000
Began researching Predictive Modeling/Data Mining
methodologies and software
2001
Developed Predictive Models for Case and Disease
Management using statistical methods
2003
Beta tested Johns Hopkins Predictive Modeling
Software
Incorporated Johns Hopkins Predictive Models
output into Case and Disease Management
Initiatives
2006
Incorporated Predictive Models into Underwriting
process
2007
Health risk appraisal data included in Predictive
Modeling process
Incorporated detailed Pharmacy Data into
Predictive Modeling process
Included Dental data in Predictive Modeling
process when available
2008
Remodeling Process for Disease Segmentation
Introduced dynamic variables to identify changes
in member health status for earlier identification
Implemented BHI Risk Score Benchmarks into
Account Reporting Analysis
4Technology of Predictive Modeling
- Johns Hopkins Predictive Models based on both
Diagnosis (Dx) and Pharmacy (Rx) Information - Angoss KnowledgeSTUDIO Predictive Model / Data
Mining - Combination of software allows for customization
and inclusion of claims, PHA, gaps in care,
biometric and dynamic variables - Blue Health Intelligence DCG Benchmark and
Statistics
5Blue Cross Blue Shield of Rhode Island
Distribution of Members by Product Type
Other 6
Individual Programs 3
Medicare 11
Large Account (Size gt 50) 65
Small Account (Size lt 50) 15
6Small Group Underwriting
Many Factors Involved in an Accounts Final Rates
Pools Experience
Trends
Admin. Expense
Final Rates
Medical Risk
Reserve Contribution
State Regulations
7Small Group Underwriting - Testing Mode
- Scored individual members by ACG Predictive
Modeling Score (PM) and Manual Medical
Underwriting Points (MU), and summarized to an
account score - Compared raw scores and ranking of account PM vs.
MU - Correlation coefficient of about .70
- Created a Set of Conversion Parameters between PM
and MU through regression
8Small Group Underwriting - Implementation
- Implemented for 4th quarter 2006 cycle accounts
- Developed supporting system for ongoing outlier
review and virtual medical record access - Outlier criteria includes extreme PM values and
loss ratios - Medical Underwriting reviewed 15 of accounts
based on criteria - Only modified 3 of those reviewed
- Successfully delivered final score July 2006, and
replaced manual medical underwriting system
9Small Group Underwriting System Support
10Small Group Underwriting System Support
11Small Group Underwriting - Results
- Reduced cycle timeframe from 6 to 3 months
- Allows for more current claims experience
- Reduced Medical Underwriting Staff
- Improved accuracy of Medical Underwriting
- Improved consistency and justification of results
- Coordinated Corporate Predictive Modeling
activities
12Small Group Underwriting - Evaluation
- Actual Expense Consistent with Rating
- 2nd Quarter 2007 Results
Related To Median
13Large Group Population
- BCBSRIs Large Group Market
- 385,000 Members
- 550 Accounts
of Members
of Accounts
Account Size
14Large Group (IER) Predictive Modeling
- General Process
- Produce electronic file with Predictive Modeling
scores for each account in rating cycle - Relate PM scores to specified comparable
population - Two comparable statistics for each account
provided to underwriters - Percent difference between accounts overall PM
score and the community score - Percent difference of account proportion of high
risk members compared to communities proportion
of high risk members
15Underwriting for IER Commercial Renewals
Predictive Modeling Claims Incurred 01/2007
12/2007, Paid 12/2007
Account Information Account Information Account Information Account Information Account Information PM (Relative to Commercial Pool) PM (Relative to Commercial Pool)
Account Number Account Name Self Funded Cycle Total Contract Total Risk Score High Risk
4H07 Tonys Incorporated Y May 431 9.62 64.91
959 Metro Properties N May 57 8.58 -24.56
3943 Leah Cosmetics N June 59 34.89 7.02
5V53 Goldmine Jewels N June 164 -8.27 -14.04
100444 Colonial Groceries N June 84 -11.73 -3.51
3129 Eric Simmons, Inc. N July 231 18.48 46.49
1A126 Michelle Co. N July 1,308 5.18 -10.53
102329 Califano Group N July 1,606 -26.19 -50.00
Total Quarter 16,102 1.23 -0.88
16Case Management
- Objectives
- Identify members who are likely to be high
risk/high cost in the future - Drill down to explain the major components that
contribute to the risk factor - Intervention
- Members whose health can be improved
- Members who are most likely to incur future cost
savings - Collaborate care
17Case Management PM Status
- Predictive Modeling Member
- Demographic Information
- Cost Distribution
- Predictive Modeling Risk Probability
- Hospital Dominant Marker
- Disease and Condition Profile
- Virtual Medical Record
- - By Type of Service
- - Chronological
- Case Management / Disease Management Information
- Quarterly Update
18Case Management - Challenges
- Challenges in Predictive Modeling
-
- Enhance model for predictive accuracy, and reduce
false positive members - Early identification for members whose health
status could be changed in the future - How can the predictive modeling program maximize
its value to the case management program - Actionability
- Timing and scope of intervention
19Case Management Future Health Status
- Prospective Member Health Status
-
- Its critical for Case Management to identify the
members who will change health status in the
future for possible early intervention - Medical claims, especially pharmacy data incurred
6 months or less, instead of 12 months, were
sometimes used for Case Management. It was
considered that the recent claims experience was
strongly associated with future health risks - Generally speaking, a disease or condition is
changed within a certain analysis period.
Prospective expense for the coming year will be
different depending on the conditions incurred in
the beginning of the year and end of the year - Should consider weighing the conditions incurred
in different analysis periods
20Case Management PM Enhancement Test
- Predictive Modeling Dynamic Variables
- Introduced dynamic variables those variables
change their values during the period of claim
experiences, such as medical utilization, visits
and tests. They can be expressed as their
values, rankings, or moving ratios by quarter or
month, for example, quarterly medical expenses
and their moving ratios (4th qtr expense vs. 3rd
qtr expense, etc.) - Combination of ACG Predictive Modeling results,
utilization, measures, and dynamic variables
allow us to customize the plan data and build the
enhanced predictive models Neural Network and
Decision Trees - The dynamic variables, featured at the end of the
claims period are displayed near the top of the
splits in the Decision Tree Predictive Model.
Similarly, the dynamic variables also showed the
strong contribution in the Neural Network
Predictive Model
21Case Management Predictive Modeling
22Case Management A New Approach
- Predictive Modeling A New Approach
- The strong prediction power of the dynamic
variables implies that the prediction accuracy
will increase progressively from past to present
medical experiences the current claims reflect
more in members future health status - We tested three models for the latest claims for
early identification 1) ACG predictive modeling
with local calibration 2) Customized model by
neural network and 3) ACG predictive modeling - Moved from quarterly, monthly, bi-weekly to
weekly. The members selected for Case Management
intervention are those with a probability
difference of 0.7 between current weekly results
and quarter base file. - Implemented the weekly predictive modeling
results into McKesson Disease Monitor System.
The exception rule of the system makes more
efficient use of the predictive modeling results
23Case Management System Implementation
Predictive Modeling Disease Monitor File
Claimno LineN Memberid Field break Proc code Field break2 From date Field break3 Service type
200804000032 0032 BCBSRIMEMB0031 PMCMH 20080422 PM DATA
200804000033 0033 BCBSRIMEMB0032 PMCMH 20080422 PM DATA
200804000034 0034 BCBSRIMEMB0033 PMCMH 20080422 PM DATA
200804000035 0035 BCBSRIMEMB0034 PMCMH 20080422 PM DATA
200804000036 0036 BCBSRIMEMB0035 PMCMH 20080422 PM DATA
200804000894 0894 BCBSRIMEMB0893 PMCMM 20080422 PM DATA
200804000899 0899 BCBSRIMEMB0898 PMCMM 20080422 PM DATA
200804000900 0900 BCBSRIMEMB0899 PMCMM 20080422 PM DATA
200804001632 1632 BCBSRIMEMB1631 PMCML 20080422 PM DATA
200804001634 1634 BCBSRIMEMB1633 PMCML 20080422 PM DATA
200804001635 1635 BCBSRIMEMB1634 PMCML 20080422 PM DATA
200804003939 3939 BCBSRIMEMB3938 PMCMA 20080422 PM DATA
200804003944 3944 BCBSRIMEMB3943 PMCMA 20080422 PM DATA
200804003945 3945 BCBSRIMEMB3944 PMCMA 20080422 PM DATA
200804003946 3946 BCBSRIMEMB3945 PMCMA 20080422 PM DATA
200804003947 3947 BCBSRIMEMB3946 PMCMA 20080422 PM DATA
24Case Management
- Results (Challenges) in Predictive Modeling
-
- Enhance model for predictive accuracy, and reduce
false positive members Combined ACG predictive
modeling results and other measures including
dynamic variables. Decision Tree and Neural
Network models increase the prediction accuracy - Early identification for members whose health
status could be changed in the future Reduce
time to weekly engagement in Predictive Modeling - How can predictive modeling program maximize its
value to case management program Implemented
the results into McKesson Disease Monitor System - Timing and scope of intervention Produced
weekly member list with the highest risk scores,
and grouped members in different risk tiers for
weekly intervention
25Disease Management
- Objectives
- Identify members who are likely to be high risk/
- high cost in the future within a disease segment
- Diabetes, Asthma, Heart Disease, Hypertension,
Cancer, Depression, etc. - Co-morbidity
- Stratification of risk score for intervention
26Disease Management - Diabetes
- Medical Expense Distribution
27Disease Management
- Predictive Modeling A New Approach
- The difference in expense distribution between
general commercial population and specific
population indicates that its necessary to build
a new model for a disease population rather than
use the model for commercial population - The lack of sufficient population size prohibits
us from calibrating model locally for a specific
disease - Combination of ACG predictive modeling results
and inclusion of utilization, measures, and
dynamic variables, etc. allows us to build the
robust predictive model through neural network
and decision trees
28Disease Management - Results
- Predictive Modeling Results
- The customized model for diabetic members
increases nearly 20 of predictive accuracy
compared to the general predictive model for
commercial population - Stratification based on the predicted risk score
and evaluation of co-morbidity - Produce a member listing for intervention
29Disease Management - Diabetes
30Blue Health Intelligence Risk Analysis
- DCG Risk Scores
- Brings together the claims experience of 79
million BCBS members nationwide - Detailed DCG risk score benchmarks by geography,
industry and company size - BCBSRI analytical team will be actively
incorporating BHI DCG risk score benchmarks into
analysis and reporting
31