2. Introduction 2
Speaker Bios
Anand Rao is a Partner at Diamond Management & Technology Consultants. Anand has more than twenty
years of experience in using advanced techniques, such as predictive modeling, agent-based simulation,
and system dynamic techniques to analyze decision making situations. He has advised clients on a
number of different aspects of customer experience and value management; behavioral economics and
interventions; large scale transformation strategy, design, and execution. Anand is the lead proponent of
the Belief-Desire-Intention agent modeling paradigm and was recognized for his contribution in this field
with the Most Influential Paper Award for the decade by AAMAS in 2007. He has co-authored a number of
papers, has written four books on building intelligent systems and is a frequent speaker at conferences on
intelligent systems, behavioral economics, and advanced analytical techniques
(anand.rao@diamondconsultants.com and www.anand-rao.com)
Richard Findlay is a Practice Director in Diamond‟s Healthcare practice with over 25 years of experience
across the healthcare industry. He has focused on developing for clients business strategies that create
competitive advantage through the optimal use of Information Technology. His portfolio of expertise spans
the value chain of operations with a particular focus on informatics, sales and marketing, supply chain,
and clinical development. Within the industry Richard held senior executive positions with SmithKline
Beecham and Abbott Laboratories. He is recognized as a leading authority on the future of healthcare and
informatics frequently publishing and speaking at conferences on leading edge developments
(richard.findlay@diamondconsultants.com)
Amaresh has helped Fortune 500 companies in multiple industries to use bottoms-up data analytics in
strategic decision making. His work has focused on developing growth strategies, defining market entry
plans, understanding customer behavior to increase profitability, improve marketing efficiency, developing
operations strategy and streamlining distribution. Amaresh founded Diamond‟s Information and Analytics
practice and set up its delivery center in Mumbai, which he helps to manage. He is the editor of Diamond‟s
information analytics blog (www.diamondinfoanalytics.com) and has written white papers on customer
service, marketing segmentation and behavioral economics,. Amaresh holds a Masters degree in
Transportation Systems Engineering from the University of Texas at Austin
(amaresh.tripathy@diamondconsultants.com)
4. Market Context 4
Disruptive forces shaping Healthcare market
Rising Healthcare Costs Consumerism
• Employer costs • Consumer Directed
• Employee costs Health Plans
• Sicker population • Transparency
– Aging & Young
• New technology • Fear of Change
Technology Market Forces
• Data collection & • Convergence of
sharing value chain
• Informatics & Healthcare Market • New business
analysis models
• Presentation & • Changing
touchpoints industry
• Decision support structure
Economic Recession Government
& planning • Healthcare reform
• Employer bankruptcies
and cost reduction • Focus on interoperability,
• Payers losing group CPOE, and EHRs/ EMRs
business • Fiscal stimulus
• Reduced demand for
providers
• Consolidation
5. Market Context 5
Impact of Economic Recession
Payers Providers
• Stock market slide has hurt payer • Falloff in non-essential procedures
reserves • Rising bad debt
• Projected EPS growth ~5%, well • Focus on HMO operating model
below 2004-07 gains (S&P)
• Decline in group business
Suppliers
• Rx rates down
• Looking to consolidate for scale
• Restructuring to address new go to
market strategies
Consumers Employers
• Growing numbers of unemployed • Carry most of healthcare cost
and projected uninsured burden on top of other economic
• Unfunded retirement burden challenges
(Medicare and Social Security) • Pressure to reduce costs
6. Market Context 6
Increasing Government Activism
Executive Order Universal Health HSA Improvement Stimulus and
MMA
mandates Care Choice and and Expansion Act Budget
creates
requirements Access Act to allow increases limits Packages.
HSAs &
for technology, use of pre-tax dollars and flexibility in HIT spend $20B.
mandates
transparency for individual health use and funding of Pharma Pricing
eRecords
and incentives premiums HSAs restraints
2003 Healthcare Legislation Timeline 2010
Tax-Free
NIST will foster
Healthcare Tax Relief and
HIPAA the
Savings, Access, Health Care
establishes development of Protech Act
and Portability Act increases EMEDS
standards – a national in
Act increases flexibility and Act
compliance infrastructure Committee
financial limits for
by 2005 to share health
attractiveness of funding HSAs
data
HSAs
Source: Library of Congress – Thomas search.
7. Market Context 7
Greatest force for change in next 5 years is
Healthcare Reform
Reform is emerging in 2010.
Major alignments will result in:
a. Greater percentage of individual plans vs. group membership.
b. Greater interaction with government data bases and programs for all value
chain constituents.
Predictive modeling will need to assess
a. Legislation impact on member choices
b. Legislation choices for non member options
c. Impact and inference of “High Risk” pool
d. Payers new product opportunities
e. Payers need to re-segment the market place
f. Specifics around impacts of closing the “doughnut hole” for payers &
Pharma
8. Market Context 8
Reform will further impact business models to change
Integrated
„Holistic‟ Advice Integrated Hold Funds Alternative
Investment Portfolio & Process
& Financial Individual Platform and Manage Risk/ Capital
Advice Benefits Transactions
Planning Risk Mgmt Investments Markets
Mgmt
Back-office Risk
Adviser Distributor Risk Aggregator Manufacturer
Administrator Transferor
9. Market Context 9
Different types of value are added at each step
in the clinical information chain
Clinical Information Chain
Informatics Presentation Decision
Data
& & Support &
Collection
Analytics Touchpoints Planning
Collection, storage, Distilling large data Delivering the Driving behavioral
aggregation and sets to guide information back to change to improve
sharing from and to decisions for care and providers and patients health outcomes
multiple sources business operations conveniently and
coherently
11. Our Predictive Modeling Thesis 11
Diamond‟s Predictive Modeling Thesis
Strategic and Operational predictive modeling need different
tools and analysis approaches
Integration of multiple data sources, especially third party
data, provides better predictions
Statistical techniques are mature and normally not worth the
incremental investment dollar
Good data visualization leads to smarter decisions
Delivering the prediction at the point of decision making is
critical
Architecture is critical
Prototype, Pilot, Scale
12. Our Predictive Modeling Thesis 12
Strategic Vs. Operational Predictive Modeling Tools
Operational Decisions Strategic Decisions
Deterministic Learn drivers of
Predict equilibrium point stock & flow over time
Linear flows Feedback loops
Point solutions Systemic understanding
E.g., claims fraud, segmentation & E.g., Disease epidemiology, patient
targeting, efficacy of disease flow models, impact of public policy
management program reform
Analytical Techniques Simulation Techniques
Prediction e.g., Linear & Logistic Discrete-event Simulation
Regression Agent Based
Segmentation e.g., CHAID & Factor System Dynamics
Analysis Dynamic Systems
Optimization e.g., genetic algorithms
and linear programming
13. Our Predictive Modeling Thesis 13
Integrate Multiple Data Sources
Which data would you look for to predict dentist potential?
14. Our Predictive Modeling Thesis 14
Mature Statistical Techniques & Tools
1880s: Linear Regression proposed by Galton
1944: Logistic Regression proposed by Berkson
1954: Systems Dynamics developed by Forrester
1969: Backpropogration method in neural networks
1976: SAS Founded by Jim Goodnight
1993: R Open source statistical environment launched
15. Our Predictive Modeling Thesis 15
Good data visualization leads to smarter decisions
Dr. John Snow‟s Visualization at 40 Broad Street (1854)
Convinced city officials that cholera is a water borne disease
16. Our Predictive Modeling Thesis 16
40 Broad Street Water Pump
Photo Credit: Miles Dowsett (www.milesdowsett.com)
17. Our Predictive Modeling Thesis 17
Delivering predictions at the point of decision making
Order Forecasting at Grocery Store
Area Sales Managers
ASM can Override if he feels necessary
FORECAST
Inventory/ Forecast
Hole Count Handheld
Current Price Logic
Application
Start Over
two days
later Data Servers
Data checks
Next Day Delivery Place Order
Reduction in OOS from 14% to 4%
18. Our Predictive Modeling Thesis 18
Delivering predictions at the point of decision making
E-Prescription
Rx
RxHub Direct
Connections
Prescriber Health Plans
1. Select drug and connect to Payer to 2. Formulary/History brought to
determine eligibility 3. Once Rx written, provider
drug interactions are
checked
Rx Rx
RxHub
Prescriber Pharmacy
4. Send Rx to patient‟s pharmacy of 5. Renewal sent back to provider
choice
3.3% Increase in prescription of generic drugs when using an
e-prescription system with formulary decision support.
Source: Archives of Internal Medicine Dec 2008.
19. Our Predictive Modeling Thesis 19
Architecture is critical
Data
Analytical Visualization & Reporting
CRM, SFA, Mobile
Device Integration
Building Blocks
Aggregation
Engine Engine
Engine
Internal Data Predictive Mapping Lists & Scores
External Data Modeling Graphing Pivots
Syndicated Data Clustering &
Survey data Segmentation
Optimization
Tableau
Access SAS
Tools
MS Excel
Oracle SPSS
Mappoint
MS SQL R
Business Objects/Cognos
Source: Archives of Internal Medicine Dec 2008.
20. Our Predictive Modeling Thesis 20
Prototype, Pilot, Scale
Prototype Pilot Scale
Define problem and Choose pilot area Update tactical
hypotheses Pilot measurement elements based pilot
Identify datasets framework learnings
Develop model and Train and launch pilot Program integration
Tasks output Gather feedback on points for scaling the
Controlled pilot plan rollout process prototype
Ongoing
measurement plan
2 months 3 months 4 months
Duration
Source: Archives of Internal Medicine Dec 2008.
22. Strategic Applications 22
Strategic Vs. Operational Predictive Modeling Tools
Operational Decisions Strategic Decisions
Deterministic Learn drivers of
Predict equilibrium point stock & flow over time
Linear flows Feedback loops
Point solutions Systemic understanding
E.g., claims fraud, segmentation & E.g., Disease epidemiology, patient
targeting, efficacy of disease flow models, impact of public policy
management program reform
Analytical Techniques Simulation Techniques
Prediction e.g., Linear & Logistic Discrete-event Simulation
Regression Agent Based
Segmentation e.g., CHAID & Factor System Dynamics
Analysis Dynamic Systems
Optimization e.g., genetic algorithms
and linear programming
23. Strategic Applications 23
Applicability of Simulation Techniques
High Abstraction
Less Details Aggregates, Global Causal Dependencies, Feedback Dynamics,…
Macro Level
Strategic Level Agent Based System Dynamics
(AB) (SD)
• Active objects • Levels (aggregates)
• Individual behavior • Stock-and-Flow diagrams
rules • Feedback loops
“Discrete Event” • Direct or indirect
Middle Abstraction (DE) interaction
Medium Details • Entities (passive • Environment models
Meso Level objects)
Tactical Level • Flowcharts and/or
transport networks Dynamic Dynamics
• Resources
(DS)
• Physical state variables
• Block diagrams and/or
algebraic-differential
equations
Low Abstraction
Less Details Mainly discrete Mainly Continuous
Micro Level
Operational Level Individual objects, exact sized, distances, velocities, timings,…
Source: From System Dynamics and Discrete Event to Practical Agent Based Modeling: Reasons, Techniques,
Tools by Borshchev, A., and Filippov, A.
24. Strategic Applications 24
Application of Simulation Techniques in Healthcare
Patient Flow Model
– Within a Provider across multiple departments
– Across primary, secondary, and community healthcare
Disease epidemiology
– Heart disease, Diabetes, HIV, cervical cancer, chlamydia infection
– Dengue fever and drug-resistant pneumococcal infections
Substance abuse epidemiology
– Heroin addition, cocaine prevalence and tobacco reduction policy
Healthcare capacity and delivery
Interactions between public health capacity and disease epidemiology
28. Strategic Applications 28
Compressed Morbidity: Longer life and fewer disabled years
Life Expectancy at Age 85
9
Independent
8
Disabled
7
62%
Remaining Years
6
5 47%
34%
4
3
72% 66%
2 53% 38% 35%
1 77%
0
1935 1965 1982 1999 2015 2022
Source: The Aging Boom: Demographic Trends and Policy Implications, Department of Elder Affairs State of Florida (H) Committee on
Healthy Seniors, January 22, 2008 Charlie Crist Governor, State of Florida Statistics
29. Strategic Applications 29
Behind the Numbers: Compressed Morbidity
Incidence of chronic disease increases with age, however;
Improvements in disease management have reduced the
disabling effects of morbidity.
Therefore, even as there are increases in chronic disease
there are reductions in disability at advanced ages;
Leading to longer independent life-spans.
Source: The Aging Boom: Demographic Trends and Policy Implications, Department of Elder Affairs State of Florida (H) Committee on
Healthy Seniors, January 22, 2008 Charlie Crist Governor, State of Florida Statistics
30. Strategic Applications 30
Where we saw opportunity
Prototype Guiding Principles and Requirements
Patient Healthcare Intervention Spectrum
Proposed Intervention Current Intervention
Critical Intensive
Awareness Prevention Occurrence Self-care Primary-Care Hospitalization
Care Care
Guiding Principles Prototype Requirements
Meaningful and Measurable Multi-channel communication:
Simple and Easy to Use – Mobile via SMS
Social Networking – PC (Personal Or Computer @ Tele-Centre)
Community Involvement 6 months of execution for gathering data
Interactive Control group to evaluate efficiency & efficacy
Participation Incentives
32. Strategic Applications 32
How we approached the opportunity
Managed Gauteng Department of Health (GDoH) Prototype Overview
Preventative 1 3
SMS Medication Reminder doctor/health
: The
Medical Care care worker records the frequency at which the
SMS Location and Source of Educational
Material : When educational material
Using broadband as a patient should take medication. The system then becomes available, the system informs the
platform, managing patients subsequently reminds the patient at the requisite patient via SMS about the nearest locations
periodic intervals to ensure higher conformance where that material can be accessed.
more effectively and to the medicine schedule.
efficiently
:
Ecosystem Partners
• Blue IQ (orchestrator)
• GDoH (healthcare
expertise)
• Doctors, pharmacists,
2 4
patients (participants) SMS Nurse/Doctor Evaluation Reminder Collaborate via Social Networking
The doctor/health care worker records the : Portal : Patient, Doctors, Nurses, etc
frequency at which the patient should come for collaborate on a social networking
• Content providers, ISPs, evaluation. The system then subsequently portal to share information,
reminds the patient at appropriate intervals to concerns etc, and to post queries
ensure higher conformance to the visit and answers.
schedule.
Impact Rationale Key Performance Indicators
Key Performance Indicators
• Better Citizen Health • Diabetes is one of the most costly CDL • Patient Knowledge
• Improved Productivity • The direct and indirect economic impacts to citizens and • Capillary Blood Glucose Levels ( mmol/l)
• Efficient and Effective governments can be very high • HbA 1C %
Healthcare Service • 80% of diabetes can be well managed and easily controlled • Hospitalization rate
Delivery
• Body Mass Index
33. Strategic Applications 33
The SD Model as a candidate to help optimize Compressed
Morbidity
Stocks, flows and their causal relationships.
Structure as interacting feedback loops
Adoption
Rate
Potential Adopters
Adopters
+ +
B R Total
Population
+
+ Adoption from Adoption from
Advertising B Word of Mouth +
+ + -
Adoption
Advertising
Fraction
Effectiveness Contact
Rate
Bass Diffusion model in VenSim
34. Strategic Applications 34
Applying the basics of SD to the Diabetes Opportunity
Diagnosed
Incidence & Managed
Rate Adoption
Un- Diagnosed
Population diagnosed Managed
Diagnosis Death Rate
Rate Managed
Managed
Adoption
Diagnosed Diabetes
Un-managed Mortality
Death Rate
Un-managed
35. Strategic Applications 35
System Dynamics Economic Model Overview
One of the major findings of the prototype was a clearer understanding of
what it will cost to drive digital inclusion across Gauteng
Macro view of model and the four major sections Population & Internet
1
Adoption
• Inflow of diabetes patients
4
1 2 Diabetes patient lifecycle
• Lifecycle from
undiagnosed, through
diagnosis ending in
2 mortality
3 Four management activities
• Diet
3 • Exercise
• Self Management
• Clinic Management
4
4 Six major complications
• Visual complications
• Cardiovascular problems
• Amputations
• Neuropathy (Nerve)
• Nephropathy (Kidneys)
NOTE: Variables from Gauteng, South Africa and American diabetic sources combined with prototype-specific findings
36. Strategic Applications 36
Digital Inclusion:
Can the right app really bridge the digital divide?
One of the major findings of the prototype was a clearer understanding of
what it will cost to drive digital inclusion across Gauteng
Technology adoption shows
some departure from the
usual curve, with more
people in incent and
mandate category
Costs ~ ZAR1,100 per
person to adopt technology
It should cost ~ ZAR1.1 Bn
to make Gauteng fully
digitally included
37. Strategic Applications 37
Social Inclusion
Attempts were made to broaden social circles and consequently make the
participant‟s worlds a bigger place. Over 60% of registered users were
active in social media
Source of
Information No. of Respondents
Interactive
Media 52 patients mentioned online forum and
blogs as important sources of
Interactive
information. Therefore, we do see that
media
Traditional people are expressing interest in being
Media socially connected through ICT
201 patients mentioned Traditional mass
Doctors & Traditional
media (e.g. newspaper, TV, radio) as
Nurses Media
source of info for Diabetes
146 patients indicated that they still trust
Friends & Doctors &
doctors and nurses more and would go to
Family Nurses
them for any information
85 patients mentioned that they would
Friends &
reach their family members and friends
Family
for diabetes related info
38. Strategic Applications 38
Technology Adoption Overview
Patients showed a strong proclivity to adopt the Internet as a means of
education and information gathering
Segmentation
High usage of all three
technologies i.e. internet, mobile,
and Glucometer
Moderate users of all three
technologies
Intervention users who didn‟t use
Glucometer but used internet
and mobile device
Group who used Glucometer
and mobile device
Patients‟ response to simultaneous exposure to three
different technologies – Internet, Mobile, Medical Device
39. Strategic Applications 39
Service Health Findings
Relationship between higher website usage and improved health
conditions/awareness
40. Strategic Applications 40
Compliance is critical in managing Diabetes, here the pilot
excelled
Mobile Devices were pivotal in increasing the hospital appointment
compliance
Snapshot Appointment Compliance Data for July and August
41. Strategic Applications 41
Sizing the Opportunity through SD Modeling
Diabetes Complication Incidence with
NO INTERVENTION* INTERVENTION IMPACT
Complications Population Expense** ZAR
Ketoacidosis 17 34,636
Visual 442,484 1,252,053,618 ~R800 million
Amputations 14,202 89,303,542
Neuropathy 43,281 122,467,075 Estimated cost
Cardiovascular 101,779 277,326,773
savings of Diabetes
Nephropathy 7,252 20,520,972
TOTAL 609,015 1,761,706,616
hospitalizations for
Gauteng:
Diabetes Complication Incidence with
BROADBAND ACCESS & SERVICES
INTERVENTION* =
Complications Population Expense** ZAR
R524 Average Cost per
Ketoacidosis 8 16,520
Inpatient Day 1
Visual 211,778 599,246,177
Amputations
Neuropathy
6,813
20,501
42,839,276
58,010,938
x
Cardiovascular 89,599 244,140,486 ~1.5M Hospital Days
Nephropathy 6,384 18,065,331 Saved
TOTAL 335,083 962,318,728
Note: (*)Based on 6 year modeled impact; (**)Expenses were calculated using a unique average
length of stay for each complication
Source: 1Estimating the Cost of District Hospital Services, Joseph Wamukuo & Pamela Ntutela
42. Strategic Applications 42
Overview of Costs and Potential Benefits
This prototype illustrates the economic benefit per capita from just one
service. The ~$90/citizen cost of adoption could be spread over multiple
services to maximize the benefit.
~$90/citizen to deliver
~$230/citizen of and have services
realized benefit executed
- =
~$140/citizen for
just one critical
service*
* It is highly likely that one citizen will realize
benefit from multiple services
Source: ICT Enabled Preventive Intervention, Diamond Consultants
44. Strategic Applications 44
Modeling „Coping‟ Policies in UK Healthcare Systems
Model of UK Health and Social Care – NHS, Primary Care
Trusts, Local Government Social Services Directorates
System dynamics model of a typical health community
covering the whole patient pathway from primary care,
through hospitals and onward to post-hospital services
Incentives and penalties in one part of the chain can lead to
„coping‟ policies that can be counter-productive
Based on work carried out by Eric Wolstenholme and others
in UK (1999-2007)
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
45. Strategic Applications 45
Patient Flow across Primary Care, Hospitals, and Social Care
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
46. Strategic Applications 46
Situation – Delayed Hospital Discharges Rising
Delayed hospital
Delayed Hospital Discharges discharges started rising
rapidly
The government felt that
Social Services could do
much better at assessing
and placing older people
in post-hospital services
Fined Social Services for
delayed discharges
Problem started getting
worse – Why?
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
47. Strategic Applications 47
Flow of medical inpatients and capacity structure of Hospitals
and Post-Hospital services
When this structure was simulated over 3 years the results showed
significant accumulations in the “medical treatment backlog” and
“waiting discharge to post-hospital services” states, over those observed in practice –
even though they were not allowed in practice.
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
48. Strategic Applications 48
Medical Inpatient Model with four „Coping‟ Policies
Formal policies were being „overridden‟ by informal policies that had an
adverse impact on the overall flow of patients through the system
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
49. Strategic Applications 49
„Coping‟ Policies – Early Hospital Discharge
Informal Policy: Length of stay in
hospital for normal cases became
a managerial policy variable,
rather than a constant based on
patient need and condition
Positive Impact: Early discharge of
normal patients is an effective
option for hospitals to reduce their
medical treatment backlog
Negative Impact: Reduced length
of stays in hospital create
incomplete episodes of care and
this can result in increases in the
percentage of readmissions.
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
50. Strategic Applications 50
„Coping‟ Policies –
Overspill of Medical Patients to Surgical Beds
Informal Policy: Transfer of medical
patients to surgical beds whenever
referrals exceeded bed capacity
Positive Impact: Reduces
immediate medical treatment
backlog
Negative Impact: Medical patients
occupying surgical beds result in
cancellation of surgical procedures
and increase in elective surgical
wait times
Conditions of patients waiting will
deteriorate and cause medical
emergencies, and push the
medical treatment backlog
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
51. Strategic Applications 51
„Coping‟ Policies – Service Referral Rate
Informal Policy: With excessive
waiting for medical admission to
hospital, the referral threshold was
changed to reduce referrals
Positive Impact: Reduced
immediate medical treatment
backlog
Negative Impact: Pushes demand
further back upstream and
ultimately this has to be absorbed
by stocks outside the health and
social care system
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
52. Strategic Applications 52
„Coping‟ Policies – Insights
Insights: In an attempt to suppress demand and accelerate throughput,
coping mechanisms (fixes) are put into place that may do more harm
than good, by impacting people (inside and outside of the organization‟s
boundaries) in such a way that they do not get the care they need,
although the organizations existing metrics might not tell you that
Solution: Increasing the care package capacity within social services
was not only shown to be a cheaper solution than increasing hospital
capacity, but was demonstrated to be a win–win situation for both health
and social services
Source: Coping but not coping in health and social care: masking the reality of running organizations beyond safe design capacity;
Wolstenholme et.al. Vol 3. No. 4, System Dynamics Review, 2007
53. Strategic Applications 53
Summary
System Dynamics is an effective way of modeling healthcare policies at
the
– Patient level
– HMO, PPO, POS level
– National levels
It can model formal and informal policies and behaviors of all
stakeholders
Effective way of combining statistical data and qualitative information
Simulate behaviors and delayed feedbacks over time
55. Operational Applications 55
Strategic Vs. Operational Predictive Modeling Tools
Operational Decisions Strategic Decisions
Deterministic Learn drivers of
Predict equilibrium point stock & flow over time
Linear flows Feedback loops
Point solutions Systemic understanding
E.g., claims fraud, segmentation & E.g., Disease epidemiology, patient
targeting, efficacy of disease flow models, impact of public policy
management program reform
Analytical Techniques Simulation Techniques
Prediction e.g., Linear & Logistic Discrete-event Simulation
Regression Agent Based
Segmentation e.g., CHAID & Factor System Dynamics
Analysis Dynamic Systems
Optimization e.g., genetic algorithms
and linear programming
56. Operational Applications 56
DRIVE Platform : Accelerating Predictive Modeling Solutions
Diamond‟s DRIVE Platform
Visualization &
Data Aggregation Analytics
Reporting
Internal Data Predictive Modeling Graphing
External Data Clustering & Segmentation Mapping
Syndicated Data Optimization Lists & Scores
Survey data Pivots
Best of breed technology infrastructure
Complements Diamond‟s management consulting practice
Helps clients develop and test predictive modeling prototypes rapidly
57. Operational Applications 57
Example 1
Pharmaceutical major trying to move away from a retail detail
model to a more consultative model for marketing to physicians
(also relevant for payors and PBMs)
Identify patient population & physician group to target prescription drug
compliance and adherence program
Predict patient population and/or physicians who have patients who are
64. Operational Applications 64
Example 2
More RFPs but limited underwriting bandwidth. Need for underwriters to
focus on accounts with maximum likelihood to win and most profitable
Predict where to deploy the underwriting resources in the small
business segment of a payer
Identity opportunity and attractiveness of prospective clients and markets
70. Behavioral Economics in Healthcare 70
Estimates for Behavioral Economics to reduce costs are varied
The current "Information Overload and Accessibility" is resulting in
abdication from decisions to change for both:
– Patients
– Providers
Behavioral Economic structured interventions in the information based
decision tree can yield positive results
Many initiatives on individual therapeutic classes have demonstrated
success
– Diabetes
– Asthma
– Smoking
At Diamond we are in the process of refining a total HC model where
initial cost reductions from such programs can yield savings in the $1 to
2 billion range nationally
71. Behavioral Economics in Healthcare 71
Simple behavioral interventions can influence what people eat
and how much they eat
OBESITY BE Interventions
1. Placing candies three feet away from one‟s
31% desk reduced volume of chocolate consumption
by 5 to 6 chocolates a day (Self-control)
15% 2. Subjects provided with a bowl of M&Ms in 10
colors ate 77% more than people given a bowl
with only 7 colors (Visceral effects)
3. Food stamp benefits raise food expenditure
<20 yrs 20-74 yrs more than an equal amount in cash
(Mental Accounting)
1. Obesity causes at least 300,000 excess
deaths 4. Pre-ordered healthy-pack options encouraged
healthy eating by Food Stamp Beneficiaries in
2. Obesity in adults resulted in health care Connecticut and North Carolina (Defaults)
costs of $93 billion in 2002
5. Having more unhealthy choices reduces the
3. Lifetime costs related to diabetes, heart chances of health options being selected –
disease, high cholesterol, hypertension Salad, Hamburger, Cake vs Salad and
and stroke among obese are $10,000 Hamburger (Choice Relativity)
more than the non-obese
Source: Could Behavioral Economics Research help improve Diet Quality for Nutrition Assistance Program participants, USDA,
Economic Service, Diamond Analysis
72. Behavioral Economics in Healthcare 72
Diamond has used Agent Oriented Behavioral Modeling
on the Baby Boomer Segment
Diamond's market research on baby boomer health and wealth attitudes and
behaviors identified five significant clusters of consumers
Low Financial Confidence High Financial Confidence
High Health Consciousness Aspirants High Health Consciousness
Moderates 31% 24%
(56yrs/ (62yrs/
20% $50K) $98K)
(57yrs/
Affluent
Percent of
$31K)
population
Sophisticates
Avg. Age/ 15%
Avg. Income (66yrs/
$50K)
Retired Settlers
Survivors
10%
Low Financial Confidence (57yrs/ High Financial Confidence
$24K)
Low Health Consciousness Low Health Consciousness
Source: Diamond Retirement Study, 2008
73. Behavioral Economics in Healthcare 73
Agent Oriented Behavioral Modeling
The five segments are clearly differentiated in terms of their health consciousness
(e.g., regular exercise, health insurance cover, health risk during retirement)
Increasing Health Consciousness
Affluent
Survivors Moderates Aspirants Retired Settlers
% who exercise at least 3 hours a week
Sophisticates
49%
27% 29% 30%
15%
60% 84%
% who strongly agree that they have adequate health insurance 50%
17% 23%
% who ranked physical health as most at risk during retirement 63% 71%
42% 39%
26%
Source: Diamond Retirement Study, 2008
75. Summary 75
Summary
Changing healthcare landscape
Explosion of Information
Increase in computing power
Emergence of sophisticated tools and techniques
Opportunity to design and model new marketing and behavioral
interventions in healthcare
– DRIVE in Pharmaceuticals and Payer
– System Dynamics in Diabetes Intervention and Policy Formulation
– Behavioral Economics in healthcare