96 PD Predictive Modeling: Now What? Moderator: Kara L. Clark, FSA, MAAA



Similar documents
Creating signal from noise:

Transformational Data-Driven Solutions for Healthcare

Session 42 PD, Predictive Analytics for Actuaries: Building an Effective Predictive Analytics Team. Moderator: Courtney Nashan

A predictive analytics platform powered by non-medical staff reduces cost of care among high-utilizing Medicare fee-for-service beneficiaries

Predictive analytics: Poised to drive population health. White Paper

Predictive Modeling for Workers Compensation Claims

An Optum Company. The Journey: From Healthcare To Health

Presenters. How to Maximize Technology to Improve Care and Reduce Cost 9/17/2015

Big Data and Healthcare Payers WHITE PAPER

An Introduction to Advanced Analytics and Data Mining

Extracting Value from Health Care Big Data with Predictive Analytics

Identifying High-Risk Medicare Beneficiaries with Predictive Analytics

IBM Business Analytics for Higher Education IBM Corporation

Data Warehousing and Data Mining in Business Applications

Session 121 PD, Medicare Advantage Risk Score Basics. Moderator: Christine Sue Bach, ASA, FCA, MAAA

PREDICTIVE ANALYTICS DEMYSTIFIED

WHITE PAPER. Payment Integrity Trends: What s A Code Worth. A White Paper by Equian

Infogix Healthcare e book

ElegantJ BI. White Paper. The Competitive Advantage of Business Intelligence (BI) Forecasting and Predictive Analysis

Session 190 PD, Model Risk Management and Controls Moderator: Chad R. Runchey, FSA, MAAA

Welcome to the Era of Big Data and Predictive Analytics in Higher Education

Accountable Care Organizations: Medicare MSSP & Pioneer Options

Not all NLP is Created Equal:

How Big Is Big Data Adoption? Survey Results. Survey Results Big Data Company Strategy... 6

Tapping the benefits of business analytics and optimization

How To Analyze Health Data

Big Data Text Mining and Visualization. Anton Heijs

Leveraging EHR to Improve Patient Safety: A Davies Story

Three proven methods to achieve a higher ROI from data mining

Text Analytics. A business guide

Value of. Clinical and Business Data Analytics for. Healthcare Payers NOUS INFOSYSTEMS LEVERAGING INTELLECT

Better planning and forecasting with IBM Predictive Analytics

Voice of the Customer: How to Move Beyond Listening to Action Merging Text Analytics with Data Mining and Predictive Analytics

Self-Service Big Data Analytics for Line of Business

High-Performance Business Analytics: SAS and IBM Netezza Data Warehouse Appliances

IBM's Fraud and Abuse, Analytics and Management Solution

New York DISCOs: Managed care plans for people with developmental disabilities - Critical factors for financial viability

SOA Annual Symposium Shanghai. November 5-6, Shanghai, China. Session 4b: Health Insurance Market in China. Jesse Song

MedInsight Healthcare Analytics Brief: Population Health Management Concepts

Electronic Medical Records Programs

Analyzing Big Data: The Path to Competitive Advantage

TACKLING POPULATION HEALTH MANAGEMENT with Worksite Wellness & Community Outreach

Next presentation starting soon Business Analytics using Big Data to gain competitive advantage

A Population Based Risk Algorithm for the Development of Type 2 Diabetes: in the United States

PALANTIR HEALTH. Maximizing data assets to improve quality, risk, and compliance. 100 Hamilton Ave, Suite 300 Palo Alto, California 94301

Data Mining for Successful Healthcare Organizations

A Glimpse at the Future of Predictive Analytics in Healthcare

Interactive data analytics drive insights

Predictive Modeling and Big Data

Text Mining for Business Intelligence

KPMG Unlocks Hidden Value in Client Information with Smartlogic Semaphore

How To Use Predictive Analytics To Improve Health Care

Voice. listen, understand and respond. enherent. wish, choice, or opinion. openly or formally expressed. May Merriam Webster.

Turning Big Data into More Effective Customer Experiences. Experience the Difference with Lily Enterprise

ACCOUNTABLE CARE ANALYTICS: DEVELOPING A TRUSTED 360 DEGREE VIEW OF THE PATIENT

and Analytic s i n Consu m e r P r oducts

Profit from Big Data flow. Hospital Revenue Leakage: Minimizing missing charges in hospital systems

Big Data 101: Harvest Real Value & Avoid Hollow Hype

How Organisations Are Using Data Mining Techniques To Gain a Competitive Advantage John Spooner SAS UK

Big Data-Challenges and Opportunities

Big Data: How can it enhance your strategy?

Big Data Analytics in Health Care

Response to Serving the Medi Cal SPD Population in Alameda County

Big Data Analytics in Healthcare In pursuit of the Triple Aim with Analytics. David Wiggin, Director, Industry Marketing, Teradata 20 November, 2014

Benefit Design and ACOs: How Will Private Employers and Health Plans Proceed?

Predicting & Preventing Banking Customer Churn by Unlocking Big Data

Risk adjustment and shared savings agreements

The Business Value of Predictive Analytics

Session 35 PD, Predictive Modeling for Actuaries: Integrating Predictive Analytics in Assumption Setting Moderator: David Wang, FSA, FIA, MAAA

The Definitive Guide to Data Blending. White Paper

Enterprise Analytics Strategic Planning

Global Headquarters: 5 Speen Street Framingham, MA USA P F

PREDICTIVE ANALYTICS FOR THE HEALTHCARE INDUSTRY

CoolaData Predictive Analytics

Business Analytics and Data Warehousing in Higher Education

Harnessing the power of advanced analytics with IBM Netezza

RISK ADJUSTMENT ARRIVES FOR COMMERCIAL HEALTH INSURANCE

Transcription:

96 PD Predictive Modeling: Now What? Moderator: Kara L. Clark, FSA, MAAA Presenters: Philip Fiero Syed Muzayan Mehmud, ASA, FCA, MAAA Prashant Ratnakar Nayak, ASA, MAAA

TM Advanced Predictive Modelling Phil Fiero, Vice President, Predilytics Inc. June 2014 Prepared for:

Who is Predilytics? Predilytics is a healthcare analytics company that generates insight from big data to: Improve quality of care Coordinate care Attract and retain members Manage reimbursement and shared savings Reduce costs We use the latest machine learning technology and computer science to identify and predict opportunities at both the population and individual member level. This approach enables use of our expansive non-clinical data on over 225M lives and our customers structured and unstructured clinical and financial data to optimize the power and economics of predictive modeling at the individual level. Predilytics serves health, services, and risk bearing entities: Health plans Health systems Providers Health services Medical device Manufacturers At both the member and provider level CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 2

The ideas that drive new analytic approaches... Use all available data to improve population and individual health 95% 1 of the data wake we all leave annually is not in the healthcare system Individual behavior is best predicted by socio-economic and lifestyle characteristics and consumer activities, not typically found in EMR and Claims Data Machine learning and advance computer science are required to convert massive amounts of data into actionable insights, by optimizing identification of targeted events at the actionable cohort Individual insight, population impact by deploying interventions with highest probability of success SOURCE: IDC; US Bureau of Labor Statistics; McKinsey Global Institute analysis, May 2011 Big data: The next frontier for innovation, competition, and productivity CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 3

Expansive use of data: Demographic, administrative, operational, clinical Incorporate data in any format, structured or unstructured Mental Health Rx Member Enrollment Details CMS Files MOR/MMR Admissions Claim History Provider Office Visits Labs Approach maximizes data intake to drive highest order prospective models Required Highly recommended Recommend EMR/Clinical Including Notes Data Inputs External Data HRA Call Center Logs & Details Census Voting Consumer Social CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 4

Unstructured data mining and linguistic analysis Can provide more accurate and predictive model results Claims and membership data often represent the majority of model input data However, specific words and word pairs in the comment fields can increase the predictive lift of the models (natural language engine) Examples of data with free text that can be mined: HRA data Sales force notes Clinical visits Call center notes EXAMPLE: Presence of the words: SON or DAUGHTER maps to the concept of family involvement and changing situation ANALYSIS: When a son (or daughter or other family member) becomes involved, it may be an early indication that the parent is experiencing health issues it can also be an early flag for disenrollment or exploring health plan changes CONFIDENTIAL COPYRIGHT, 2013 PREDILYTICS, INC. ALL RIGHTS RESERVED 5

Illustrative external data sources: Public, consumer, financial, social media Matched holistic view of over 220M people Public Healthcare Medicare, Medicaid Population Stats Healthcare Providers, Cost, Quality AHRQ, NIH, CDC Health Outcomes Consumer Consumer Behavior / Purchasing Ethnicity Social Security / Death Records Voter Registration Legal / Regulatory Financial Consumer spending Credit risk Public records Real estate indicators Social Media Facebook Activity Foursquare Check-in Twitter Activity Google Services, ETC. CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 6

Machine Learning background Machine learning is a technology in which software evaluates a data set and combinations of data sets millions of times to learn and predict data relationships Machine learning is capable of exploring more data, faster and more thoroughly than traditional statistical techniques Predictive patterns in the data are discovered and retained The software builds on previous learnings and highly predictive equations evolve Genetic Algorithms (GAs) are a form of machine learning that are highly effective in spotting subtle patterns in data sets. GA modeling technology and the output are transparent and more actionable Traditional modeling relies on statistical analyses of data, in particular various forms of regression, which carry with it certain limitations that are not found in iterative based learning models These patented algorithms have been consistently used in the financial services and marketing industries for enhanced business success CONFIDENTIAL COPYRIGHT, 2013 PREDILYTICS, INC. ALL RIGHTS RESERVED 7

Genetic Algorithms (GA) Generation One Model 1 Model 2 Model 3 Model 4 Model 5 Model 6 Generation Two Model 7 Model 8 Model 9 Model 10 Model 11 Model 12 Generation (n) Model 13 Model 14 Model 15 Model 16 Model 17 Model 18 Model (n) Fitness Accuracy Scale Low High 125 models per generation in 10 seconds 10,000 generations performed 1.25 Million equations evaluated with learning past to next generation CONFIDENTIAL COPYRIGHT, 2013 PREDILYTICS, INC. ALL RIGHTS RESERVED 8

Applying analytics to allocate resources Current Served Populations Historical experience indicates 1/3 of population at risk of not recertifying With predictive analytics at-risk individuals can be identified increase probability of failure to recertify to 90% likelihood Improve business performance by appropriately allocating resources to targeted cohort New Populations Integration of consumer behavior, social claiming can identify risk in unknown populations Failure to recertify risk COPYRIGHT 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 9

Sample Outputs: Creating member target lists Predilytics Prospective Member List Operationalize established models to Analytic Warehouse. Design, review, and develop member extracts. Generation, validation, and delivery of member extracts in the pre-determined format. Integrate directly into client operations systems and processes COPYRIGHT, 2013 PREDILYTICS, INC. ALL RIGHTS RESERVED 10

Sample Outputs: Key model drivers Purpose: Identify the top clinical and non-clinical drivers at a member level in order to support intervention operations. This methodology allows end users (providers, case managers, etc.) of to understand key risk drivers in a comprehensive and actionable way. Key drivers may include, but are not limited to, existing/pre-existing conditions, demographic, consumer, utilization, and financial attributes at a member/risk level. This information facilitates identification of the appropriate intervention at a member level, as well as provides an area of focus for those at the point-of-care. Member CHF Hosp. Risk Decile Key Driver 1 Key Driver 2 Key Driver 3 Person A.92 1 2-IP-HCC85-CHF GAP-CCSPx44-Lipid Profile Person B.81 2 1-EM-HCC22-Morbid Obesity Poor LDL-C Control GAP-Annual EM Visit Person C.97 1 History-CABG GAP-GC3- Ace inhibitors GAP-GC3- Beta- Adrenergic Blockers 2-Visits-Cardiologist- Last 30 days COPYRIGHT, 2013 PREDILYTICS, INC. ALL RIGHTS RESERVED 11

Case Studies CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 23

Big Data Machine Learning Healthcare Analytics Delivering patented machine learning healthcare data analytics to generate meaningful insight to solve healthcare industry challenges CONFIDENTIAL COPYRIGHT, 2014 PREDILYTICS, INC. ALL RIGHTS RESERVED 13

#96: Predictive Modeling Now What? Syed M. Mehmud Director and Senior Consulting Actuary Wakely Consulting Group syedm@wakely.com

Risk Score Optimization Continuing from session 33 A brief re-cap 2

Risk Score Optimization WNRAR Project Wakely Consulting Group 3

Risk Score Optimization 3R Predictive Analytics Where do we go from here? 4