Soyal Momin MS, MBA

1
Maximizing the Value of Predictive Modeling The
BlueCross BlueShield of Tennessee Experience
Soyal Momin MS, MBA December 14th, 2007
2
Outline

• Understanding Population Needs
• Historical View Care Management at BCBST
• Concept Next Generation Care Management (NGCM)
• Implementation of NGCM
• Improving the
• Process Efficiency
• Information Shared with CM
• Using Predictive Modeling to Evaluate Care Mgmt.
  ROI
• Conclusions

3
Understanding Population Needs
4
Cumulative Total Healthcare Cost
5
Cumulative Professional and Outpatient Cost
6
Cumulative Pharmacy Cost
7
Cumulative Inpatient Cost
8
Population Assessment
Population Assessment is an analysis of claims
and membership data to determine characteristics
of a given population (Network, Region, Group)
that might affect the populations interaction
with the health care system
9
Major Analysis Variables

• Propensity to Utilize Index The average
  number of episodes of illness for a member month
• Episode Seriousness Index A measure of the
  average cost to treat the categories of illness
  experienced by a population
• Illness Burden A measure of the level of
  illness within a group determined by multiplying
  the propensity to utilize index by the Episode
  Seriousness Index

10
Major Analysis Variables, Continued

• Provider Efficiency Index A measure of the
  efficiency to treat a specific episode of illness
  determined by dividing the cost to treat the
  specific episode by the average cost for the
  category of illness
• PMPM Cost Index An index that measures the PMPM
  submitted costs for a population determined by
  multiplying the Illness Burden by the Provider
  Efficiency Index

11
Population Profile
12
Illness Burden by Major Practice Category
13
Provider Efficiency by Major Practice Category
14
PMPM Cost Index by Major Practice Category
15
Total Cost Assessment

• Direct costs are dollars paid out for medical
  treatment
• Indirect costs are labor resources lost due to
  illness

Direct Costs Inpatient Professional/Outpatient
Pharmacy Indirect Costs Sick Leave
Presenteeism Family Medical Leave
Short Term Disability Long Term Disability
Turnover Workers Compensation
16
Total Cost Assessment Company XYZ
Total Healthcare Cost 23,237,422
Total Healthcare Cost 23,237,422
Total Healthcare Cost 23,237,422
Total Healthcare Cost 23,237,422
5,631 per FTE
5,631 per FTE
5,631 per FTE
5,631 per FTE
Direct
Indirect
Direct
Indirect
13,761,278
9,476,144
13,761,278
9,476,144
3,334 / FTE
2,296 / FTE
3,334 / FTE
2,296 / FTE
59.2
40.8
59.2
40.8
Inpatient
Pharmacy
Presenteeism
STD
Inpatient
Pharmacy
Presenteeism
STD
Turnover
Turnover
Professional/
Work
Professional/
Work
376
804
318
220
376
804
318
220
74
74
Outpatient
Comp
Outpatient
Comp
6.7
14.3
5.7
3.9
6.7
14.3
5.7
3.9
Sick Leave
Sick Leave
1.3
1.3
2,154
82
2,154
82
FMLA
LTD
FMLA
LTD
1,322
1,322
38.3
1.5
38.3
1.5
274
4
274
4
23.5
23.5
4.9
0.1
4.9
0.1
17
Top 20 Cost Drivers
18
History

• Identifying Members for Case Management
• Referrals from
• Internal Sources
• External Sources
• An internally developed ICD9 Trigger list
• The ICD9 Trigger list included Asthma, Diabetes,
  High Risk OB, AIDs, Cancer, CHF, COPD etc
• Case managers workload
• 103/CM/Month
• PM implementation validation revealed missed
  opportunities for case management

19
Next Generation Care ManagementTriage Guidelines
20
Lifestyle/Health Counseling for Healthy and
Worried Well

• Information on disease/condition
• Web resources
• Pamphlets
• Telephonic health library
• Encouragement to take more active
  role/accountability

21
Care Coordinationfor Chronically Ill

• Telephonic coordination with members and their
  providers
• Ensures appropriate treatments and
  pharmaceuticals
• Five different programs included in this model

22
Care Coordination Programs

• Pharmacy Care Management
• Emergency Room (ER) Visits Mgmt.
• Transition of Care
• Condition Specific Care Coordination
• Disease Management

23
Catastrophic Case Management

• Directed to members with
• Terminal illness
• Major trauma
• Cognitive/physical disability
• High-risk condition
• Complicated care needs
• Systematic process of assessing, planning,
  coordinating, implementing, and evaluation of care

24
Next Generation Care ManagementImplementation

• Predictive Modeling Using
• DCG
• ETG
• Rolling 12 Months DCG Explanation Prospective
  Model
• ETG Cost to Supplement DCG Prediction

25
Next Generation Care ManagementProcess
Enhancements

• Developed SQL database containing DCG and ETG
  information
• Improved processes/workflow
• Easy and continuous access
• Better documentation

26
Next Generation Care ManagementProcess
Enhancements
27
Next Generation Care ManagementProcess
Enhancements
28
Care Management Staff Feedback

• Under prediction at all risk levels
• Use pharmacy data for prediction
• NDCs
• Prediction of utilization
• Provide information to help prioritize members
  for interventions
• Evidence-based guideline gaps

29
MEDai RNC

• Forecasted cost
• Overall
• Pharmacy

• ER and IP LOS prediction

• Gaps in care

30
Improving the Information Shared with Care
Management Staff

• Enhancing SQL database with RNC information
• ETG Low/Med/High Amount
• MEDai forecasted costs (total and Rx)
• ER and IP LOS prediction
• Impact index
• Care management history
• Active PCP
• - Risk drivers - Latest Rx data
  
• - Gaps in Care - Risk History

31
(No Transcript)
32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)
37
Developing a Stratification Index (SI)

• Why?
• 1) To reliably identify higher cost, highly
  impactable members
• 2) To enhance prioritization of members for
  nurse-intervention management
• How?
• Use predictive output from MEDai
• Select key MEDai measures to construct a
  composite score
• Use the composite score as an index to stratify
  members
• Focus on members with the highest index
  scores

38
Chronic Impact Break Down by SI Score
39
Acute Impact Break Down by SI Score
40
Chronic Gaps Break Down by SI Score
41
Preventative Gaps Break Down by SI Score
42
NGCM Risk Levels Break Down by SI Score
43
Mover Identification

• Movers are members who are likely to make the
  transition from low or moderate to high risk
• Movers can be identified by comparing current
  vs. forecasted NGCM risk level
• if a members current cost is less than 1,000
  (Risk Level I) and is predicted to cost more than
  25,000 (Risk Level V)
• Do movers have higher index scores?

44
Index Scores for Movers
Current Risk Level Forecasted Risk Level Frequency Mean Index Score
I II 430,312 4.52
I III 11,370 9.87
I IV 451 12.75
I V 2 11.00
II III 96,352 10.26
II IV 7,737 13.03
II V 51 13.04
III IV 22,492 13.47
III V 225 13.95
IV V 2,142 14.85
45
Distribution of Index Scores
Commercial LOB 10/2005
High Scores gt11 (10.2)
Moderate Scores 6-10 (18.4)
Low Scores lt5 (71.4)
46
How Do We Measure Care Management (CM) Impact?

• Basic research problem measuring what would have
  happened vs. what actually happened
• Methodologies
• Randomized Control Group
• Population-Based Pre-Post Methodology
• Predictive Modeling
• Control Group Matching
• Combination

47
Predictive Modeling
48
Predictive Modeling w/Adjustments










49
Conclusions of DM Evaluations

• A statistically valid predictive model should be
  incorporated in lieu of randomized control group
• Adjustments (inflation factors, inaccuracy of
  predictive models, etc.) should be made to the
  model information

50
Conclusions

• More scientific/standardized approach
• Able to touch more lives efficiently
• Well accepted by our case managers
• NGCM has helped
• Streamline our processes
• Better manage case managers case load
• Provide Peace of Mind to our members and clients