SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
Making the Most
of Predictive Analytics
Presented by JJ Schmidt, Senior Vice President
Administrative Details:
• All participants will be muted during the call.
• If you need to step away from your phone during the webinar, 
please hang up and dial back in when you can rejoin us.  Please do 
not place the call on hold.
• If you would like to ask a question during the webinar, please type 
your question in the question box on your screen.
• To minimize the toolbar, just click the red arrow.
• As the flow of the presentation permits, the presenter will address 
questions during the presentation.
• There will be a Question and Answer session at the end of the main 
presentation.
• A copy of the presentation and a recording of the webinar will be 
available on the Resources section of our website 
(www.yorkrsg.com) and will be sent to all participants.   
2
Making the Most
of Predictive Analytics
Presented by JJ Schmidt, Senior Vice President
PREDICTIVE ANALYTICS | AGENDA
What we will cover
– Definitions
– How predictive analytics work
– Analytics
– What can analytics do
– Why predictive analytics is an important topic
– Key considerations
– The three A’s of analytics
– Case study
– Practical implications
– Key takeaways
– Questions
4
Not everything that can be 
counted counts, and not 
everything that counts can be 
counted.
‐ Albert Einstein
5
PREDICTIVE ANALYTICS
Definitions
– Predictive analytics
– Predictive modeling
– Data mining
– Big data
– Data warehouse
– Algorithms
6
PREDICTIVE ANALYTICS | DEFINITIONS
Analytics in everyday life:
– Soccer moms
– NASCAR dads
– Amazon, Google, Online/Catalog Retailers, Banks & Credit
Cards
– What might be some typical types of claimants or
accidents/injuries that we “know” will be those claims that will
be bad
7
PREDICTIVE ANALYTICS | ANALYTICS IN EVERYDAY LIFE
How do predictive analytics work?
– Use your claim and managed care data
– Create specific algorithms
– Review data looking for patterns, issues or targets
– Gain insights on claims and patient populations
– Influence claim progression by alerting to the use of
specific actions
– Change or improve clinical pathways for injured
workers
8
PREDICTIVE ANALYTICS | HOW DO PREDICTIVE ANALYTICS WORK?
Analytics
– Analytics can be transformative
– “Past performance is not necessarily indicative of future
results”
– Analytics in everyday life
• Netflix, Amazon, Facebook, Google
– Data is everywhere
• Transactions
• Spending
– Sometimes analytics are not the answer
• Timing is an issue? Before you have all of the information?
• A decision maker can add unique perspective – clinical
issues
9
PREDICTIVE ANALYTICS | ANALYTICS
What can predictive analytics do?
– Improve decision making
– Predict or anticipate changes
– Manage risk
– Reduce claim costs
– Reduce claim durations
– Improve operational efficiency and effectiveness
– Help resources to work together
10
PREDICTIVE ANALYTICS | WHAT CAN PREDICTIVE ANALYTICS DO?
Why are predictive analytics important?
– Understand claims and improve outcomes
• Analytics can help to better understand the dynamics of a
claim at a specific point in time
• Analytics can help to improve claim performance metrics
such as costs or durations
• Analytics can help to better understand what processes
are, and also are not, working on claim administration
• Analytics can help to improve the efficacy of specific claim
related services such as case management, peer review
or utilization review
• Analytics can allow for claim professionals to individualize
claim strategies to distinguish between injured workers
who will or will not benefit from specific treatment plans
11
PREDICTIVE ANALYTICS | WHY ARE PREDICTIVE ANALYTICS IMPORTANT?
Key considerations
– Tie analytics to specific objective targets
• Improved claim durations
• Lower claim or medical costs
• Improved return to work
– Leverage existing information technology and data
• Better insight into claim current and future status
• Earlier or faster execution of specific activities
• Increased and enhanced value of information
technology investments
12
PREDICTIVE ANALYTICS | KEY CONSIDERATIONS
Key considerations
– Make the program adaptive
• Learn from the results – positive and negative
– Create new insights
– Look for changes
• Learn from the process – what works and what does not add
value
– Feedback from staff
– How does this fit into strategy and objectives?
• Focus on the specific metrics and indicators that impact
results
• Review and examine the program continuously
13
PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
• Key considerations
– Data
• Structure
• Unique
• Integration
• Quality
• Access
• Privacy
• Governance
14
PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
Key considerations
– Challenges
• Systems and information technology
• Data – quality and input
• Organizational and customer acceptance
• Process consistency
15
PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
The three A’s of analytics
– Alert
• Notification
• Something has happened
• Something is happening
• Something could happen based on prior experience
• Who does it go to as an alert?
• What does it tell them?
• What is the benefit?
16
PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
The three A’s of analytics
– Action
• Process
• How do I review the information?
• What do I need to do now?
• What is my timeframe?
• Who do I need to involve?
• Feedback
• Process improvement
• Alert evaluation
17
PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
The three A’s of analytics
– Accountable
• Consistency and quality
• What is expected?
• What if I do not follow guidelines?
• Who monitors what I do – or do not do?
• Continuous improvement
• Program feedback
18
PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
• Case Study – Predictive Analytics
– Start with regression analysis
– Identify common factors on outlier claims
– Develop data plan
– Develop algorithms
– Results
• Two year study focusing on impacts to back claims
• Statistically significant reductions in
– Total average claim costs
– Total average medical costs
– Number of disability days
– Number of days claim open to close
19
PREDICTIVE ANALYTICS | CASE STUDY
Practical Uses
– Pharmacy
• Physician dispensing
• Medication uses or combinations
20
PREDICTIVE ANALYTICS | PRACTICAL USES
• Key takeaways
– Make decisions
• More accurately
• More consistently
• More timely
– Data is an asset – we collect it and we need to use it
– Data can be a tool to guide and assist in decision making
• Past
– What happened?
– Why and how did it happen?
• Present
– What is happening now?
– What should we do next?
• Future
– What has the potential to happen?
– What are the best or worst outcomes?
– How do we plan?
21
PREDICTIVE ANALYTICS | KEY TAKEAWAYS
• Resources for additional knowledge
– Books
• Big Data @ Work – Thomas Davenport
• Keeping Up with the Quants – Thomas Davenport
• Data Science for Business – Foster Provost & Tom Fawcett
– Articles
• “Big Data for Skeptics” by Adi Ignatius.  Harvard Business 
Review
• “A Predictive Analytics Primer” by Thomas Davenport.  
Harvard Business Review
• “Big Data in Healthcare”  Health Affairs July 2014
• “A Decision Support Tool for Predicting Patients at Risk of 
Readmission”  Decision Sciences October 2014
22
PREDICTIVE ANALYTICS | RESOURCES
23
PREDICTIVE ANALYTICS | QUESTIONS
jj.schmidt@wellcomp.com
(954) 665-7140
Join Us for our Next Webinars
Feb. 2:  How to Build an Effective Return to Work Program
March 3:  Opt Out and Workers’ Compensation –
Is This The Right Option for You?
Register at york‐webinars@yorkrsg.com

Weitere ähnliche Inhalte

Was ist angesagt?

Data Analytics and the Small Audit Department: How to Implement for Big Gains
Data Analytics and the Small Audit Department: How to Implement for Big GainsData Analytics and the Small Audit Department: How to Implement for Big Gains
Data Analytics and the Small Audit Department: How to Implement for Big GainsCaseWare IDEA
 
Actuaries and Examiners Talk Numbers: Go Figure!
Actuaries and Examiners Talk Numbers:  Go Figure!Actuaries and Examiners Talk Numbers:  Go Figure!
Actuaries and Examiners Talk Numbers: Go Figure!Sedgwick
 
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...Summarized version of Key Performance Indicators (KPIs) for Security Operatio...
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...MaryamAlHumam
 
How to Measure the Relevance and Accuracy of OHS Information
How to Measure the Relevance and Accuracy of OHS InformationHow to Measure the Relevance and Accuracy of OHS Information
How to Measure the Relevance and Accuracy of OHS Informationdanieljohn810
 
1530 track 3 gunther_using our laptop
1530 track 3 gunther_using our laptop1530 track 3 gunther_using our laptop
1530 track 3 gunther_using our laptopRising Media, Inc.
 
1555 track 1 huang_using his mac
1555 track 1 huang_using his mac1555 track 1 huang_using his mac
1555 track 1 huang_using his macRising Media, Inc.
 
Project Management in Health and Human Services
Project Management in Health and Human ServicesProject Management in Health and Human Services
Project Management in Health and Human ServicesBrandon Olson
 
An Introduction to Monitoring & Evaluation
An Introduction to Monitoring & EvaluationAn Introduction to Monitoring & Evaluation
An Introduction to Monitoring & EvaluationRobin Beveridge
 
Prescriptive analytics
Prescriptive analyticsPrescriptive analytics
Prescriptive analyticsIpsita Kulari
 
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...TRI, the risk-based monitoring company
 
Mental Health Business Architecture
Mental Health Business ArchitectureMental Health Business Architecture
Mental Health Business ArchitectureDonna Kelly
 
A Supplier perspective on Health Technology Assessment.
A Supplier perspective on Health Technology Assessment.A Supplier perspective on Health Technology Assessment.
A Supplier perspective on Health Technology Assessment.HTAi Bilbao 2012
 
Closing the regulatory policy cycle through ex post evaluation
Closing the regulatory policy cycle through ex post evaluationClosing the regulatory policy cycle through ex post evaluation
Closing the regulatory policy cycle through ex post evaluationOECD Governance
 
Healthcare Management for Change
Healthcare Management  for ChangeHealthcare Management  for Change
Healthcare Management for ChangeRavi Kumudesh
 
Difference between supervision and monitoring by sajjad awan
Difference between supervision and monitoring by sajjad awanDifference between supervision and monitoring by sajjad awan
Difference between supervision and monitoring by sajjad awanMalik Sajjad Ahmad Awan
 
Implementation, Change Management and the Application of Healthcare Analytics
Implementation, Change Management and the Application of Healthcare AnalyticsImplementation, Change Management and the Application of Healthcare Analytics
Implementation, Change Management and the Application of Healthcare AnalyticsJ. Bryan Bennett, MBA, CPA, LSSGB
 
Ms 94 2018 solved assignment
Ms 94 2018 solved assignmentMs 94 2018 solved assignment
Ms 94 2018 solved assignmentPramodShaw6
 

Was ist angesagt? (20)

Data Analytics and the Small Audit Department: How to Implement for Big Gains
Data Analytics and the Small Audit Department: How to Implement for Big GainsData Analytics and the Small Audit Department: How to Implement for Big Gains
Data Analytics and the Small Audit Department: How to Implement for Big Gains
 
Actuaries and Examiners Talk Numbers: Go Figure!
Actuaries and Examiners Talk Numbers:  Go Figure!Actuaries and Examiners Talk Numbers:  Go Figure!
Actuaries and Examiners Talk Numbers: Go Figure!
 
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...Summarized version of Key Performance Indicators (KPIs) for Security Operatio...
Summarized version of Key Performance Indicators (KPIs) for Security Operatio...
 
How to Measure the Relevance and Accuracy of OHS Information
How to Measure the Relevance and Accuracy of OHS InformationHow to Measure the Relevance and Accuracy of OHS Information
How to Measure the Relevance and Accuracy of OHS Information
 
1530 track 3 gunther_using our laptop
1530 track 3 gunther_using our laptop1530 track 3 gunther_using our laptop
1530 track 3 gunther_using our laptop
 
1555 track 1 huang_using his mac
1555 track 1 huang_using his mac1555 track 1 huang_using his mac
1555 track 1 huang_using his mac
 
Forecasting
ForecastingForecasting
Forecasting
 
Project Management in Health and Human Services
Project Management in Health and Human ServicesProject Management in Health and Human Services
Project Management in Health and Human Services
 
Healthcare And Project Management 1
Healthcare And Project Management 1Healthcare And Project Management 1
Healthcare And Project Management 1
 
An Introduction to Monitoring & Evaluation
An Introduction to Monitoring & EvaluationAn Introduction to Monitoring & Evaluation
An Introduction to Monitoring & Evaluation
 
Prescriptive analytics
Prescriptive analyticsPrescriptive analytics
Prescriptive analytics
 
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...
RbM Webinar Slides- A Practical Guide for Getting Your RBM Program Up and Run...
 
Mental Health Business Architecture
Mental Health Business ArchitectureMental Health Business Architecture
Mental Health Business Architecture
 
Business Analytics
Business AnalyticsBusiness Analytics
Business Analytics
 
A Supplier perspective on Health Technology Assessment.
A Supplier perspective on Health Technology Assessment.A Supplier perspective on Health Technology Assessment.
A Supplier perspective on Health Technology Assessment.
 
Closing the regulatory policy cycle through ex post evaluation
Closing the regulatory policy cycle through ex post evaluationClosing the regulatory policy cycle through ex post evaluation
Closing the regulatory policy cycle through ex post evaluation
 
Healthcare Management for Change
Healthcare Management  for ChangeHealthcare Management  for Change
Healthcare Management for Change
 
Difference between supervision and monitoring by sajjad awan
Difference between supervision and monitoring by sajjad awanDifference between supervision and monitoring by sajjad awan
Difference between supervision and monitoring by sajjad awan
 
Implementation, Change Management and the Application of Healthcare Analytics
Implementation, Change Management and the Application of Healthcare AnalyticsImplementation, Change Management and the Application of Healthcare Analytics
Implementation, Change Management and the Application of Healthcare Analytics
 
Ms 94 2018 solved assignment
Ms 94 2018 solved assignmentMs 94 2018 solved assignment
Ms 94 2018 solved assignment
 

Andere mochten auch

Mmx maio 2013 - português - v2
Mmx   maio 2013 - português - v2Mmx   maio 2013 - português - v2
Mmx maio 2013 - português - v2mmxriweb
 
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politique
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politiqueArticle dans L'informaticien décembre 2015 : DigitaleBox le crm de la politique
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politiqueDigitaleBox
 
Album de Selección 1-1 / Reinier y Osbeidy
Album de Selección 1-1 / Reinier y OsbeidyAlbum de Selección 1-1 / Reinier y Osbeidy
Album de Selección 1-1 / Reinier y Osbeidydmaudiovisuales
 
Conseguir mas seguidores en twitter
Conseguir mas seguidores en twitterConseguir mas seguidores en twitter
Conseguir mas seguidores en twitterHisocial
 
FENÓMENOS DE TRANSPORTE
FENÓMENOS DE TRANSPORTEFENÓMENOS DE TRANSPORTE
FENÓMENOS DE TRANSPORTEAndres Hincapie
 
Pulses: The Common Yet Mysterious Food
Pulses: The Common Yet Mysterious FoodPulses: The Common Yet Mysterious Food
Pulses: The Common Yet Mysterious FoodCambro Manufacturing
 
Caso de Sucesso WK - Ybera - Cosméticos
Caso de Sucesso WK - Ybera - CosméticosCaso de Sucesso WK - Ybera - Cosméticos
Caso de Sucesso WK - Ybera - CosméticosWK Sistemas
 
Tweeting as uea chemistry
Tweeting as uea chemistryTweeting as uea chemistry
Tweeting as uea chemistrySimon Lancaster
 

Andere mochten auch (20)

Mmx maio 2013 - português - v2
Mmx   maio 2013 - português - v2Mmx   maio 2013 - português - v2
Mmx maio 2013 - português - v2
 
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politique
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politiqueArticle dans L'informaticien décembre 2015 : DigitaleBox le crm de la politique
Article dans L'informaticien décembre 2015 : DigitaleBox le crm de la politique
 
Yle
YleYle
Yle
 
Invertebrats 2
Invertebrats 2Invertebrats 2
Invertebrats 2
 
Impresionismo 1
Impresionismo 1Impresionismo 1
Impresionismo 1
 
Content page
Content pageContent page
Content page
 
Action jam april 2013
Action jam april 2013Action jam april 2013
Action jam april 2013
 
Ergonomics
ErgonomicsErgonomics
Ergonomics
 
Gli aracnidi
Gli aracnidiGli aracnidi
Gli aracnidi
 
Tecnologia 9a
Tecnologia 9aTecnologia 9a
Tecnologia 9a
 
Original Brief.
Original Brief.Original Brief.
Original Brief.
 
Album de Selección 1-1 / Reinier y Osbeidy
Album de Selección 1-1 / Reinier y OsbeidyAlbum de Selección 1-1 / Reinier y Osbeidy
Album de Selección 1-1 / Reinier y Osbeidy
 
Conseguir mas seguidores en twitter
Conseguir mas seguidores en twitterConseguir mas seguidores en twitter
Conseguir mas seguidores en twitter
 
FENÓMENOS DE TRANSPORTE
FENÓMENOS DE TRANSPORTEFENÓMENOS DE TRANSPORTE
FENÓMENOS DE TRANSPORTE
 
Pulses: The Common Yet Mysterious Food
Pulses: The Common Yet Mysterious FoodPulses: The Common Yet Mysterious Food
Pulses: The Common Yet Mysterious Food
 
Umbanda sem medo 3
Umbanda sem medo 3Umbanda sem medo 3
Umbanda sem medo 3
 
Umbanda sem medo 2
Umbanda sem medo 2Umbanda sem medo 2
Umbanda sem medo 2
 
Borajet
BorajetBorajet
Borajet
 
Caso de Sucesso WK - Ybera - Cosméticos
Caso de Sucesso WK - Ybera - CosméticosCaso de Sucesso WK - Ybera - Cosméticos
Caso de Sucesso WK - Ybera - Cosméticos
 
Tweeting as uea chemistry
Tweeting as uea chemistryTweeting as uea chemistry
Tweeting as uea chemistry
 

Ähnlich wie Analytics-Webinar-FINAL

Introduction to Policy Evaluation
Introduction to Policy EvaluationIntroduction to Policy Evaluation
Introduction to Policy EvaluationpasicUganda
 
2015 ISACA NACACS - Audit as Controls Factory
2015 ISACA NACACS - Audit as Controls Factory2015 ISACA NACACS - Audit as Controls Factory
2015 ISACA NACACS - Audit as Controls FactoryNathan Anderson
 
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...Health IT Conference – iHT2
 
Data Analytics Strategy
Data Analytics StrategyData Analytics Strategy
Data Analytics StrategyeHealthCareers
 
Leading an improvement project
Leading an improvement projectLeading an improvement project
Leading an improvement projectChris Jacob
 
Game Changing Quality Strategies that Drive Organizational Excellence
Game Changing Quality Strategies that Drive Organizational ExcellenceGame Changing Quality Strategies that Drive Organizational Excellence
Game Changing Quality Strategies that Drive Organizational Excellencekushshah
 
Shing Lee MedicReS World Congress 2015
Shing Lee MedicReS World Congress 2015Shing Lee MedicReS World Congress 2015
Shing Lee MedicReS World Congress 2015MedicReS
 
Financial Metrics That Mean to Nonprofits
Financial Metrics That Mean to NonprofitsFinancial Metrics That Mean to Nonprofits
Financial Metrics That Mean to NonprofitsIntacct Corporation
 
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...Frank Wang
 
Qi toolkit oct 2020
Qi toolkit oct 2020 Qi toolkit oct 2020
Qi toolkit oct 2020 JosephCope3
 
How to Determine the Root Cause Analysis Techniques in a Management System?
How to Determine the Root Cause Analysis Techniques in a Management System?How to Determine the Root Cause Analysis Techniques in a Management System?
How to Determine the Root Cause Analysis Techniques in a Management System?PECB
 
Automating Phase One Clinical Trials
Automating Phase One Clinical TrialsAutomating Phase One Clinical Trials
Automating Phase One Clinical TrialsPerficient
 
The Data Maze: Navigating the Complexities of Data Governance
The Data Maze: Navigating the Complexities of Data GovernanceThe Data Maze: Navigating the Complexities of Data Governance
The Data Maze: Navigating the Complexities of Data GovernanceHealth Catalyst
 
Seven Parts of an Effective Injury and Illness Prevention Plan
Seven Parts of an Effective Injury and Illness Prevention PlanSeven Parts of an Effective Injury and Illness Prevention Plan
Seven Parts of an Effective Injury and Illness Prevention PlanKPADealerWebinars
 
Redefining Workflows with Lean and Simulation
Redefining Workflows with Lean and SimulationRedefining Workflows with Lean and Simulation
Redefining Workflows with Lean and SimulationSIMUL8 Corporation
 
Chapter 2 Analyzing the Business Case .pptx
Chapter 2 Analyzing the Business Case .pptxChapter 2 Analyzing the Business Case .pptx
Chapter 2 Analyzing the Business Case .pptxAxmedMaxamuudYoonis
 
Importance of M&E
Importance of M&EImportance of M&E
Importance of M&Eclearsateam
 

Ähnlich wie Analytics-Webinar-FINAL (20)

Introduction to Policy Evaluation
Introduction to Policy EvaluationIntroduction to Policy Evaluation
Introduction to Policy Evaluation
 
2015 ISACA NACACS - Audit as Controls Factory
2015 ISACA NACACS - Audit as Controls Factory2015 ISACA NACACS - Audit as Controls Factory
2015 ISACA NACACS - Audit as Controls Factory
 
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...
iHT² Health IT Summit Atlanta - Case Study “Analytics Strategies to Improve Q...
 
Data Analytics Strategy
Data Analytics StrategyData Analytics Strategy
Data Analytics Strategy
 
Leading an improvement project
Leading an improvement projectLeading an improvement project
Leading an improvement project
 
Game Changing Quality Strategies that Drive Organizational Excellence
Game Changing Quality Strategies that Drive Organizational ExcellenceGame Changing Quality Strategies that Drive Organizational Excellence
Game Changing Quality Strategies that Drive Organizational Excellence
 
Shing Lee MedicReS World Congress 2015
Shing Lee MedicReS World Congress 2015Shing Lee MedicReS World Congress 2015
Shing Lee MedicReS World Congress 2015
 
Financial Metrics That Mean to Nonprofits
Financial Metrics That Mean to NonprofitsFinancial Metrics That Mean to Nonprofits
Financial Metrics That Mean to Nonprofits
 
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...
Drive Healthcare Transformation with a Strategic Analytics Framework and Impl...
 
Quality management and process improvement layton
Quality management and process improvement   laytonQuality management and process improvement   layton
Quality management and process improvement layton
 
Qi toolkit oct 2020
Qi toolkit oct 2020 Qi toolkit oct 2020
Qi toolkit oct 2020
 
How to Determine the Root Cause Analysis Techniques in a Management System?
How to Determine the Root Cause Analysis Techniques in a Management System?How to Determine the Root Cause Analysis Techniques in a Management System?
How to Determine the Root Cause Analysis Techniques in a Management System?
 
Gp commissioning kinetik
Gp commissioning  kinetikGp commissioning  kinetik
Gp commissioning kinetik
 
Automating Phase One Clinical Trials
Automating Phase One Clinical TrialsAutomating Phase One Clinical Trials
Automating Phase One Clinical Trials
 
The Data Maze: Navigating the Complexities of Data Governance
The Data Maze: Navigating the Complexities of Data GovernanceThe Data Maze: Navigating the Complexities of Data Governance
The Data Maze: Navigating the Complexities of Data Governance
 
Seven Parts of an Effective Injury and Illness Prevention Plan
Seven Parts of an Effective Injury and Illness Prevention PlanSeven Parts of an Effective Injury and Illness Prevention Plan
Seven Parts of an Effective Injury and Illness Prevention Plan
 
Redefining Workflows with Lean and Simulation
Redefining Workflows with Lean and SimulationRedefining Workflows with Lean and Simulation
Redefining Workflows with Lean and Simulation
 
Chapter 2 Analyzing the Business Case .pptx
Chapter 2 Analyzing the Business Case .pptxChapter 2 Analyzing the Business Case .pptx
Chapter 2 Analyzing the Business Case .pptx
 
Importance of M&E
Importance of M&EImportance of M&E
Importance of M&E
 
M & E Presentation DSK.ppt
M & E Presentation DSK.pptM & E Presentation DSK.ppt
M & E Presentation DSK.ppt
 

Analytics-Webinar-FINAL

  • 1. Making the Most of Predictive Analytics Presented by JJ Schmidt, Senior Vice President
  • 2. Administrative Details: • All participants will be muted during the call. • If you need to step away from your phone during the webinar,  please hang up and dial back in when you can rejoin us.  Please do  not place the call on hold. • If you would like to ask a question during the webinar, please type  your question in the question box on your screen. • To minimize the toolbar, just click the red arrow. • As the flow of the presentation permits, the presenter will address  questions during the presentation. • There will be a Question and Answer session at the end of the main  presentation. • A copy of the presentation and a recording of the webinar will be  available on the Resources section of our website  (www.yorkrsg.com) and will be sent to all participants.    2
  • 3. Making the Most of Predictive Analytics Presented by JJ Schmidt, Senior Vice President
  • 4. PREDICTIVE ANALYTICS | AGENDA What we will cover – Definitions – How predictive analytics work – Analytics – What can analytics do – Why predictive analytics is an important topic – Key considerations – The three A’s of analytics – Case study – Practical implications – Key takeaways – Questions 4
  • 6. Definitions – Predictive analytics – Predictive modeling – Data mining – Big data – Data warehouse – Algorithms 6 PREDICTIVE ANALYTICS | DEFINITIONS
  • 7. Analytics in everyday life: – Soccer moms – NASCAR dads – Amazon, Google, Online/Catalog Retailers, Banks & Credit Cards – What might be some typical types of claimants or accidents/injuries that we “know” will be those claims that will be bad 7 PREDICTIVE ANALYTICS | ANALYTICS IN EVERYDAY LIFE
  • 8. How do predictive analytics work? – Use your claim and managed care data – Create specific algorithms – Review data looking for patterns, issues or targets – Gain insights on claims and patient populations – Influence claim progression by alerting to the use of specific actions – Change or improve clinical pathways for injured workers 8 PREDICTIVE ANALYTICS | HOW DO PREDICTIVE ANALYTICS WORK?
  • 9. Analytics – Analytics can be transformative – “Past performance is not necessarily indicative of future results” – Analytics in everyday life • Netflix, Amazon, Facebook, Google – Data is everywhere • Transactions • Spending – Sometimes analytics are not the answer • Timing is an issue? Before you have all of the information? • A decision maker can add unique perspective – clinical issues 9 PREDICTIVE ANALYTICS | ANALYTICS
  • 10. What can predictive analytics do? – Improve decision making – Predict or anticipate changes – Manage risk – Reduce claim costs – Reduce claim durations – Improve operational efficiency and effectiveness – Help resources to work together 10 PREDICTIVE ANALYTICS | WHAT CAN PREDICTIVE ANALYTICS DO?
  • 11. Why are predictive analytics important? – Understand claims and improve outcomes • Analytics can help to better understand the dynamics of a claim at a specific point in time • Analytics can help to improve claim performance metrics such as costs or durations • Analytics can help to better understand what processes are, and also are not, working on claim administration • Analytics can help to improve the efficacy of specific claim related services such as case management, peer review or utilization review • Analytics can allow for claim professionals to individualize claim strategies to distinguish between injured workers who will or will not benefit from specific treatment plans 11 PREDICTIVE ANALYTICS | WHY ARE PREDICTIVE ANALYTICS IMPORTANT?
  • 12. Key considerations – Tie analytics to specific objective targets • Improved claim durations • Lower claim or medical costs • Improved return to work – Leverage existing information technology and data • Better insight into claim current and future status • Earlier or faster execution of specific activities • Increased and enhanced value of information technology investments 12 PREDICTIVE ANALYTICS | KEY CONSIDERATIONS
  • 13. Key considerations – Make the program adaptive • Learn from the results – positive and negative – Create new insights – Look for changes • Learn from the process – what works and what does not add value – Feedback from staff – How does this fit into strategy and objectives? • Focus on the specific metrics and indicators that impact results • Review and examine the program continuously 13 PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
  • 14. • Key considerations – Data • Structure • Unique • Integration • Quality • Access • Privacy • Governance 14 PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
  • 15. Key considerations – Challenges • Systems and information technology • Data – quality and input • Organizational and customer acceptance • Process consistency 15 PREDICTIVE ANALYTICS | KEY CONSIDERATIONS CONTINUED
  • 16. The three A’s of analytics – Alert • Notification • Something has happened • Something is happening • Something could happen based on prior experience • Who does it go to as an alert? • What does it tell them? • What is the benefit? 16 PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
  • 17. The three A’s of analytics – Action • Process • How do I review the information? • What do I need to do now? • What is my timeframe? • Who do I need to involve? • Feedback • Process improvement • Alert evaluation 17 PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
  • 18. The three A’s of analytics – Accountable • Consistency and quality • What is expected? • What if I do not follow guidelines? • Who monitors what I do – or do not do? • Continuous improvement • Program feedback 18 PREDICTIVE ANALYTICS | THE THREE A’S OF ANALYTICS
  • 19. • Case Study – Predictive Analytics – Start with regression analysis – Identify common factors on outlier claims – Develop data plan – Develop algorithms – Results • Two year study focusing on impacts to back claims • Statistically significant reductions in – Total average claim costs – Total average medical costs – Number of disability days – Number of days claim open to close 19 PREDICTIVE ANALYTICS | CASE STUDY
  • 20. Practical Uses – Pharmacy • Physician dispensing • Medication uses or combinations 20 PREDICTIVE ANALYTICS | PRACTICAL USES
  • 21. • Key takeaways – Make decisions • More accurately • More consistently • More timely – Data is an asset – we collect it and we need to use it – Data can be a tool to guide and assist in decision making • Past – What happened? – Why and how did it happen? • Present – What is happening now? – What should we do next? • Future – What has the potential to happen? – What are the best or worst outcomes? – How do we plan? 21 PREDICTIVE ANALYTICS | KEY TAKEAWAYS
  • 22. • Resources for additional knowledge – Books • Big Data @ Work – Thomas Davenport • Keeping Up with the Quants – Thomas Davenport • Data Science for Business – Foster Provost & Tom Fawcett – Articles • “Big Data for Skeptics” by Adi Ignatius.  Harvard Business  Review • “A Predictive Analytics Primer” by Thomas Davenport.   Harvard Business Review • “Big Data in Healthcare”  Health Affairs July 2014 • “A Decision Support Tool for Predicting Patients at Risk of  Readmission”  Decision Sciences October 2014 22 PREDICTIVE ANALYTICS | RESOURCES
  • 23. 23 PREDICTIVE ANALYTICS | QUESTIONS jj.schmidt@wellcomp.com (954) 665-7140
  • 24. Join Us for our Next Webinars Feb. 2:  How to Build an Effective Return to Work Program March 3:  Opt Out and Workers’ Compensation – Is This The Right Option for You? Register at york‐webinars@yorkrsg.com