healthcare information analytics
TRANSCRIPT
Healthcare Information Analytics
Frank F. Wang, MBA, MSPrincipal, FFW Consulting
Adjunct Faculty, Department of Management, University of New Haven
Linkedin: http://www.linkedin.com/in/frankfangwang
Email: [email protected]
Session 1
Class Introduction
Class Introduction
4
Let us get to know each other: • Who you are• What you are doing (occupation)• What your career aspiration is• Why you are enrolled in the program and why you
are taking this class• What you hope to accomplish in the class
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Syllabus Review
Course Materials
• Required Textbook: Healthcare Analytics for Quality and Performance Improvement by Trevor Strome (ISBN: 978-1-118-51969-1), available for purchase at the University of Bookstore.
• Additional ebooks, papers, slides and datasets will be posted in Blackboard.
• Software required to install on your personal computers for completing individual and group assignments: Microsoft Office 365, downloadable free of charge via Microsoft; SPSS downloadable free of charge via IBM. Review instructions under Technology tab, Hardware and Software section.
• HIMSS Analytics Database• Many online resources and datasets.• Also, Visit the “Analytics Primer” section on Trevor Strome’s blog
–http://HealthcareAnalytics.info/AnalyticsPrimer/
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 6
Other House-keeping Items
• The Center for Learning Resources (CLR) is back and ready to help you with complimentary:
· Tutoring· Supplemental Instruction (SI)· Workshops· Software Learning Assistance
• University of New Haven Enrollment Policy• Withdraw• Incomplete
• Bookmark Highline Excel 2016 website for portions of our online classes https://people.highline.edu/mgirvin/AllClasses/218_2016/218Excel2016.htm
• Download Microsoft Power Query and Power BI from https://www.microsoft.com/en-us/download/details.aspx?id=39379 and install them on your computer
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 7
Current Healthcare Challenges
Current Healthcare System Challenges
9
Healthcare organizations are under immense pressure to:
– Improve quality and patient safety– Ensure patient satisfaction– Adopt new technologies– Demonstrate outcomes– Remain sustainable and competitive
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Current Healthcare System Challenges• US Healthcare costs have been risen.
10HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Current Healthcare System Challenges
• And are expected to continue to rise.
11HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Current Healthcare System Challenges
• We spent much more than other countries.
12HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Current Healthcare System Challenges
• And yet, our quality of care does not stand out (OECD 2015).
13HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Quality of careTop third performers. Middle third performers. Bottom third performers.
Note: Countries are listed in alphabetical order. The number in the cell indicates the position of each country among all countries for which data is available. For the indicators of avoidable hospital admissions and case-fatality rates, the top performers are countries with the lowest rates.
IndicatorAsthma and COPD hospital admission
Diabetes hospital admission
Case-fatality for Case-fatality for AMI (admission- ischemic stroke based) (admission-based)
Cervical cancer survival
Breast cancer survival
Colorectal cancer survival
Australia 29 17 1 20 11 5 3Austria 28 29 27 8 19 19 7Belgium 16 20 19 20 16 12 4Canada 18 10 11 26 12 8 13Chile 6 27 31 16 25 23 n.a.Czech Rep. 12 23 11 22 13 22 21Denmark 26 14 7 17 5 11 18Estonia 27 n.a. 28 29 8 25 22Finland 10 15 9 4 6 4 7France 7 21 17 13 n.a. n.a. n.a.[…]
United KingdomUnited States
22 5 20 19 22 21 2025 24 5 3 21 2 9
Healthcare Information Systems
15
The Evolution of Hospital Information Systems 1960s
HEALTHCARE DRIVERS IT DRIVERS RESULTING HITMedicare/Medicaid • Expensive mainframes
• Expensive storageShared hospital accounting systems
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
16
The Evolution of Hospital Information Systems 1970s
HEALTHCARE DRIVERS IT DRIVERS RESULTING HIT• Hospital-wide
communications (ADT, OC, Bed Control)
• Broadened admin systems
• Departmental systems processing
• Smaller computers• Improved terminals and
connectivity
• Expanded financial and administrative systems (PA, GA, HR, MM,OP/POB)
• Results review• Selected clinical
department automation (Lab, MR,RX)
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
17
The Evolution of Hospital Information Systems 1980s
HEALTHCARE DRIVERS IT DRIVERS RESULTING HIT• DRGs • Networking
• Personal computers• Cheaper storage• Independent software
applications
• Integrated financial and clinical (limited) systems
• Managed care financial and administrative systems
• Departmental imaging (limited systems)
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
18
The Evolution of Hospital Information Systems 1990s
HEALTHCARE DRIVERS IT DRIVERS RESULTING HIT• Competition,
consolidation• Integrated hospital,
provider, and managed care offering
• Broadened distributed computers
• Cheaper hardware and storage
• Expanded clinical departmental solutions
• Increased IDN-like integration
• Emergence of integrated EMR offerings
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
19
The Evolution of Hospital Information Systems 2000s
HEALTHCARE DRIVERS IT DRIVERS RESULTING HIT• More integration• Beginnings of outcomes-
based reimbursement
• More of everything• Mobility• Emerging cloud computers
• Emerging, broad-based clinical decision support
• Broad operational departmental systems with EMR integration
• Emerging data warehousing and analytics solutions
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
Patient Centered Systems
20
• Clinical Systems• E-prescribing• Medication Management• Inpatient computerized provider order entry
(COPE)• Electronic Medical Record (EMR) …
• Hospital Department Information Systems• Emergency• Radiology• Ambulatory care …
• Others
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
Business-centered and Hospital Operation Systems
21
• Admission, Discharge and Transfer• E-prescribing• Medication Management• Inpatient computerized provider order entry
(COPE)• Electronic Medical Record (EMR) …
• Enterprise Resource Management• Emergency• Radiology• Ambulatory care …
• Revenue-cycle Management
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Landscape of Information System Architecture in a Typical US Healthcare Provider
22HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
US EMR Adoption Model according to HIMSS Analytics
23
US EMR Adoption Model according to HIMSS Analytics
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 24
25
HEALTH INFORMATION EXCHANGE (HIE)
Collaborate regionally and cross- border with other statesOffer clear guidance and flexible access to consumers, employers, payers pharmas
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
26
Health Information Exchange
Singular• Houses data from many clinical data sources
in a secure central structure
Enabling
• Enables key functions that reduces costs (reduced repeated testing, reduced risk of adverse events) and improves coordination of care
Payer
• Some HIE use cases have focus on sending ADTs (admissions, discharges, transfers) and discharge summaries to the health plans in lieu of manual processing
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
27
DATA: A Fortuitous Byproduct of Healthcare IT Implementation
• The most commonly implemented systems were designed to automate clinical and adminstrative transactions.
• This resulted in readily available digitized data from multiple systems.
• Early innovators articulated that improving operational performance would require health systems to merge and then analyze this data.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
• Regulatory mandates
• Lack of consensus on standards
Current State of Health Data: Culture, Organization, Process, People and Technology
• Reluctance to share
• Disparate data
• Proprietary data
• Multiple owners
• Large volumes
• Different in allied health industries
• New types of data (genomic, molecular)
• Legacy data
• Privacy/security
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 28
Introduction to Healthcare Analytics
What is Analytics?
Everything is vague to a degree you do not realize till you have tried to make it precise.
Bertrand RussellHCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 30
31
Data, Information, Knowledge, Wisdom Hierarchy
Data• Symbols, facts, measurements
Information• Data processed to be useful• Provides the “who, what, when, where”
Knowledge • Application of data and information• Provides the “how”
Wisdom • Evaluated understanding• Provides the “why”
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
32
Turning Data into Wisdom – Healthcare Example
We have 35,000 individuals in our population with diabetes.
The patients cost us $7,000 this year, a 15% increase over last year.
The national prevalence rate for diabetes is 8.3%; ours is 12%.
Hypertension is a major co-morbidity for diabetes.
Assign patient-level risk scores using a statistical model to predict which diabetics will be hospitalized next year.
Efficiently allocate care management resources to help reduce avoidable hospitalizations for at-risk patients.
Wisdom
• actionable info
5
Knowledge
• goals• targets
4
Information
• Bench-marks
• trends
3
Secondary Data
• averages• rates
2
Primary Data
• counts• sums
1
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
33
Data Management and Information Management
Data• Generate• Collect• Organize• Validate• Analyze• Store• Integrate
Information• Disseminate• Communicate• Present• Utilize• Transmit• Safeguard
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
What Is Analytics
34
• Analytics is the “data, statistical, and quantitative analysis, explanatory and predictive models, and fact-based management to drive decisions and actions.”(1)
• Analytics are often applied to study data using statistical analysis in order to discover and understand historical patterns within the data with an eye to predicting and improving operational performance in the future. (2)
• Analytics refers to the skills, technologies, applications and practices for continuous iterative exploration and investigation of past performance to gain insight and drive organizational planning. (3)
1.
2.
3.
Davenport TH. Harris JG. Competing on Analytics. Harvard Business School Press. 2007.
http://en.wikipedia.org/wiki/Analytics
http://www.docstoc.com/docs/7486045/Next-Generation-Business-Analytics-Technology-Trends
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
HCAD 6035: Health Information Analytics
35
• Not a programming class
• Not a data science class
• Not a management class
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Gartner’s Four Types of Analytics
36
• Descriptive – What is happening now based on incoming data. To mine the analytics, you typically use a real-time dashboard and/or email reports.
• Diagnostic – A look at past performance to determine what happened and why. The result of the analysis is often an analytic dashboard.
•Predictive – An analysis of likely scenarios of what might happen using simulation and modeling to identify trends and portend outcomes taken. The deliverables are usually a predictive forecast.
• Prescriptive – This type of analysis reveals what actions should be taken. This is the most valuable kind of analysis and usually results in rules and recommendations for next steps. It helps organizations to optimize clinical, financial and other outcomes.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Gartner Analytic Ascendancy Model
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 37
Gartner Analytic Model Healthcare Examples
Type of Analytics
Question Answered
General Business Example
Healthcare Example
Descriptive Analytics
What Happened?
How many cars did we sell last year?
How many patients were diagnosed with HBP last year?
Diagnostic Analytics
Why Did It Happen?
Why did we only sell x cars last year?
Why did these patients develop HBP?
Predictive Analytics
What Will Happen?
If I run x advertising programs, how many cars can we sell?
What are the chances Mr. Jones’ HBP will result in a stroke?
Prescriptive Analytics
How Can We Make it Happen?
What do we need to do to sell x number of cars?
Mr. Jones should be put on x medication to prevent his HBP from resulting in a stroke.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 38
Health Analytics
39
• Healthcare organizations require better insight into their operations and accountability for their performance.
• Healthcare organizations must allow for creative use of available data and analytic tools to foster decision making – in real time and near the point of care.
• To keep up with pace of change, analytics development needs to adopt an agile approach which values innovation and experimentation.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Health Analytics
40
• Healthcare decisions becoming more evidence-based and data-driven
• Healthcare organizations are methodologies that encourage and support innovation (i.e., Lean, Six Sigma)
• Multidisciplinary teams are increasingly involved in quality and performance improvement initiatives
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
Objectives of Healthcare Analytics
• The fundamental objective of healthcare analytics is to help peopleto make and execute rational decisions, defined as being:
Data-driven Transparent
Verifiable Robust
41
Source:Rahul Saxena and Anand Srinivasan, Business Analytics: A Practitioner’s Guide, International Series in Operations Research & Management (New York: Springer Science+Business Media, 2013), 9.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Objective: Data Driven
42
• Clinical and administrative decisions must be based on the best possible evidence that is generated from extensive research and data analysis.– Much “evidence” on which decisions are based is not held
to these standards.
• Analytics in healthcare can help ensure that all decisions are made based on the best possible evidence derived from accurate and verified sources of information rather than gut instinct or because a process or procedure has always been done that way.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
43
Being Data Driven
• Data as a driver of organizational strategy and leadership isn’t just a recent trending topic.
• The world of finance and insurance have always been data rich and data dependent.
• What’s not easy to detect is the pragmatic insight a health-care organization needs to become data driven.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
44
Advantages of Being Data Driven
• Use data to support the mission, thus ensuring its continuity and supporting the culture.
• If your mission is to care for patients, you want data that is in the best interest of patients.
Being Data Driven
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
• Data illuminates opportunities for process improvement.
• Help to avoid duplication of effort, unnecessary costs, and repeat performances of poor prior performance.
Being Data Driven• A data-driven organization
realizes fewer disruptions of operations, such as those that can arise from organizational inertia and internal politics.
Being Data Driven
45
Advantages of Being Data Driven
• If medicine were not data driven, and clinicians (people) routinely ignored the evidence showing the benefits of the treatments they prescribe, we’d be back in the days of the Health Jolting Chair and Dr. Bonker’s Egyptian Oil.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
• Leaders in a data-driven organization depend on the insights of data, rather than just their own expertise and opinion, to drive the business.
• Organizations runs best when its employees know where they have been, where they are, and where they are headed.
46
Who or what are we
monitoring?
What are our goals?
What are we measuring?
How will we achieve them?
Data and Technology
Organization, Culture and
Process
Regularly return to these fundamentals
The Five Questions of Health Analytics
People
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Objective: Transparent
47
• Information silos are still a reality in healthcare due to the belief by some that withholding information from other departments or programs best maintains autonomy and control.
• Healthcare analytics can help break down silos based on program, department, or even facility by promoting the sharing of accurate, timely, and accessible information.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Objective: Verifiable
• Consistent and verifiable decision making involves a validated decision-making model that links the proposed options from which to choose to the decision criteria and associated methodology for selecting the best available option.
• With this approach, the selected option can be tested and verified, based on the available data and decision making model, to be as good as or better than other alternatives.
48HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Objective: Robust
49
• Healthcare is a dynamic environment; decisions must often be madequickly and without perfect data on which to base them.
• Decision-making models must be robust enough to perform in non-optimal conditions.– They must accommodate biases that might be introduced as
a result of missing data, calculation errors, failure to consider all available options, and other issues.
• Robust models can benefit from a feedback loop in which improvements to the model are made based on its observed performance.
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
Data Analytics Essentials for Today’s Healthcare Organization Copyright © 2015 Trevor Strome
Healthcare Analytics and the Information Value Chain
Performance Objectives
Quality Goals
Improvement Approach
Data
Business Processes
Analytics
What DID Happen
What IS Happening
What Will Happen
Decisions & Actions
Outcomes Evaluation
Healthcare analytics is the system of tools, techniques, and people required to consistently and reliably generate accurate, validated, and trustworthy business and clinical insight.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 50
51
Healthcare Analytics SystemAnalytics Use Cases B
usiness Context & “Voice Of The Patient”
Privacy and Security Policies
Data Governance & Stewardship
Improvement & Management Methodology
Quality & Performance Improvement.
Clinical Decisions Support
Research, Administration,& Planning
Risk Assessment & Fraud Detection
Population Health Management
Meaningful Use
Analytic Tools
Query Dashboards Reports / BI
Alerts Predictive Geospatial
Simulation Visualization
Security
Access Audit
Data Stores
Data Warehouse Data Mart RDBMS
Cloud
Integration
ETL Virtualization BPM
Data Cleansing Data Profiling
Data Sources
EMR Labs Radiology
Finance HR Claims
Social Media Devices Genomics
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Healthcare Analytics Architecture
Sources of Data
52
• Human-generated data
• Web and social media data
• Machine-to-machine data
• Transaction data
• Biometric data
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Data Integration
53
• Data integration is the combination of technical and business processes used to combine data from disparate sources into meaningful and valuable information1.– A complete data integration solution encompasses discovery,
cleansing, monitoring, transforming and delivery of data from a variety of sources.
• Data integration (DI) is a family of techniques and best practices thatrepurpose data by transforming it as it’s moved2.– ETL (extract, transform, and load) is the most common form
of DI found in data warehousing.
1.
2.
www.ibm.com/software/data/integration/
https://tdwi.org/articles/2011/05/18/data-integration-and-data-warehousing-defined.aspx
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Data Stores
Source: https://tdwi.org/articles/2011/05/18/data-integration-and-data-warehousing-defined.aspx
54
• At the highest level, designing a data warehouse involves creating,manipulating, and mapping models.– These models are conceptual, logical, and physical (data)
representations of the business and end-user information needs.
• Creating a data warehouse requires designers to map data between source and target models, capturing the details of the transformation in a metadata repository.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Data Storage and Management Models
55
• Transactional Database– The database used directly by applications for data storage
and optimized for application use– Typically not analysis-friendly and provide limited analytic
capability• Operational Data Store
– Brings multiple sources of data together to enable more efficient reporting and analysis
• Data Warehouse– A repository of an organization’s electronically stored
data designed to facilitate analysis and reporting.(1)
• Data Mart– A collection of subject areas organized for decision
support based on the needs of a given business unit. (1)
Inmon, B. “Data Mart Does Not Equal Data Warehouse”. DM Direct, Nov 1999.1.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Security, Privacy, and Access
Source:http://s3.amazonaws.com/rdcms-himss/files/production/public/HIMSSorg/Content/files/CPRIToolkit/version6/v7/D03_Security_Primer(3).pdf
56
• Information security is achieved by implementing policies andprocedures as well as physical and technical measures that deliver:– Confidentiality: the protection of information from
unauthorized access or disclosure.– Integrity: the protection of information from unauthorized
change(deliberate or accidental).
– Availability: the use of information as intended by ensuring that the information and other required resources are accessible for use whenever needed including during emergencies and disasters.
• Access to data is based on the individual’s role and is provided on aneed-to-know basis.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Common Analytical Tools
57
Analytical Application Description
Business Intelligence • Provides a healthcare organization with reports and graphs used by management, decision-makers, and QI teams to analyze and understand to analyze clinical, business, and administrative trends and issues.
Statistical • Used for deeper statistical analysis not available in “standard” business intelligence or reporting packages.
Visualization • Used for developing interactive, dynamic data visualizations that aid with analysis
Data Profiling • Specific data analysis tools that help to understand and improve the quality of an HCO’s data.
Data Mining • Enables the analysis of large data sets to uncover unknown or unsuspected relationships.
Text Mining • Analysis of unstructured, text-based data to extract high-quality information.
Online Analytical Processing • Allows analysts to interactively explore data by drilling-down, rolling up, or “slicing and dicing” data.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
58
ACADEMIC
STATE
SOURCEDATA CONTENT
SOURCE SYSTEMANALYTICS
CUSTOMIZED DATA MARTS
DATAANALYSIS
OTHERS
HR
FINANCIAL
CLINICAL
SUPPLIES
INTE
RN
AL
EX
TER
NA
L
ACADEMIC
STATE
OTHERS
HR
FINANCIAL
CLINICAL
SUPPLIES
RESEASRCH REGISTRIES
QlikView
Microsoft Access/ODBC
Web applications
Excel
SAS, SPSS
Et al
OPERATIONAL EVENTS
CLINICAL EVENTS
COMPLIANCE AND PAYER MEASURES
DISEASE REGISTRIES
MATERIALS MANAGEMENT
Data Privacy and Information Governance
Enterprise Data Architecture of an Health Analytic System
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Integration and TransformationCapture Consumption
Analytics in Action – Example Use Cases
59
• Clinical Decision Support
• Population Health Management
• Process & Quality Improvement
• Administration & Planning
• Risk Assessment & Fraud Prevention
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Clinical Decision Support (CDS)
60
• CDS ranges from providing suggestions and evidence regarding the management of a single patient to helping manage an entire unit or department during a surge in patients.
• Goal of CDS is disseminating timely, actionable information and insight to clinical providers at the point of care when that information is required and is the most useful.
Copyright © 2016 Frank F. WangHCAD 6635 Health Information Analytics
Clinical Decision Support (CDS)
• Provide insight into particular patients– Possible diagnosis given
ambiguous symptoms, incomplete history, or other missing data
– Likely outcomes (i.e., admission, long-stay) given past history of patient (and of similar patients)
• Provide insight into “near-future” of the ED
• Alert staff and management when undesirable conditions are likely to occur (i.e., offload delays, excessive wait times)
• Provide sufficient warning to take preventive action
61HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Population Health Management
62
• Analytics can help coordinate care delivery across a population ofpatients to improve clinical and financial outcomes– through disease management– case management– demand management
• Analytics helps HCOs achieve these improvements by– identifying patient subpopulations– risk-stratifying the subpopulations (that is, identifying
which patients are at highest risk of poor outcomes)– using clinical decision support tools and best evidence to
manage patients’ and populations’ care in the best way possible.
– tracking of patients to determine overall compliance and outcomes.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
The 8 Building Blocks of Successful Accountable HealthcareP
ay fo
r Rep
ortin
gP
ay fo
r Out
com
es
EHR/PMS/E-Prescribing 2. Automating and Integrating Fragmented Stakeholders
InformationExchange
(HIE)3. Sharing Clinical, Operations and Financial Information
Aggregation &Analytics 4. Aggregating Siloed Data and Gaining Insight
DecisionSupport 5. Transforming collected data into clinical knowledge
HealthcarePortals and
Medical Homes6. Making clinical information accessible and “team-based” care possible
OutcomesMeasurement &
Reporting7. Establishing Core Measures and Reporting Outcomes
RiskSharing 8. Enabling Population Based Management and Risk Sharing
Models
ConvergedMedical
Infrastructure1. Establishing Standardized and Optimized IT Platforms
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 63
9
Enterprise Data Architecture Of Population Health Management
Data Integration &
Transformation
Dashboards & Analytic ViewsContract Measures
PerformanceSummary
Baseline Expenditure Provider
Profile
Data A
ccess –Navigation &
Security
Reports
Capture Integration and Transformation Consumption
Extensible Data Architecture
Provider
Standard Data Models
Patient
Location
Claim
Reference
Other Master Data
Encounter
Patient Panel Analytics
Targeted Populations& Outcomes
Baseline Expenditures& Costs
Accountability Models
Financial Reconciliation
Population Health Management
Health System
EMR
Billing
MPI
Provider Master
Coding
Payers
Members
Claims
• Data Enrichment • Data Profiling, Data Quality (DQ) management • Metadata layer, Controlled Vocabulary• Data Warehouse & Data Store• Data MartHCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 64
• Standard and Ad hoc Reporting• Data Discovery & Data Mining• Text Analytics• Statistical Analysis
Trevor Strome
Process and Quality Improvement
• Provide superior analysis of baseline data
• Identify bottlenecks and other causes of poor quality and performance.
• Guide selection of improvement initiatives that are most likely to have an impact and be successful
• Monitoring ongoing performance of processes and workflows– ensure that improvements are sustained in the
long term.
27HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Administration and Planning
66
• Analytics can help healthcare administrators optimize current (andpredict future) resource allocation requirements.
• Such resources include:• Staffing levels and scheduling• Bed requirements (type and number)• Service availability
– Diagnostic– Consulting– Allied Health
• Analytics can also assist in case-costing and efficient financialmanagement
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Improving Clinical Workflow
• Throughput analytics monitors ED workflow and improves triage efficiencies.
67HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Payer Risk Analysis and Fraud Prevention
68
• Healthcare data analytics help reduce submissions of improper,erroneous or fraudulent claims– computer algorithms analyze large volumes of data, scanning for
patterns and other clues in the data that might indicate fraudulent activity and other irregularities.
• Once a manual, painstaking, and imprecise process, this is now an automated, immensely more efficient process, saving healthcare systems billions of dollars.– Centers for Medicare and Medicaid Services (CMS) achieved
$4 billion in recoveries
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang
Cost Containment Findings
Provider #
Count Provider Name Specialty Total $
1 4836 Bing, Mark Family Practice $160,833
2 4342 Yahoo, Charles Psychiatry $143,490
3 2732 East End Urgent Care URGENT Family Practice $90,479
4 2602 Place, First MD General Practice $63,892
5 1724 Swat, Edward MD Anesthesiology $56,696
6 4312 Smith, Gregory E DPM Podiatry $54,597
7 3836 Man, Super G DPM Podiatry $49,796
8 1615 Riley, James R MD Plastic Surgery $37,970
9 3243 Avian, Bird DPM Podiatry $37,327
10 2513 Copper, Metal H DPM Podiatry $32,668
Identifying and eliminating un-necessary procedures
Necessity
• Is the procedure necessary
Savings
• How large is the potential saving and what is the estimated cost/benefit ratio?
Nail Debridement
• Nail debridement clinical guidelines. Only 2 of 5 are directly tied to a disease • Relief of pain• Treatment of infection (bacterial, fungal and viral)• Temporary removal of an anatomic deformity …• Exposure of subungal condition …• Prophylactic measure to prevent further problems …
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 69
Fraud and Abuse Detection
Provider #
Count Provider Name Specialty Total $
1 4836 Bing, Mark Family Practice $160,833
2 4342 Yahoo, Charles Psychiatry $143,490
3 2732 East End Urgent Care URGENT
Family Practice $90,479
4 2602 Place, First MD General Practice $63,892
5 1724 Swat, Edward MD Anesthesiology $56,696
6 4312 Smith, Gregory E DPM
Podiatry $54,597
7 3836 Man, Super G DPM Podiatry $49,796
8 1615 Riley, James R MD Plastic Surgery $37,970
9 3243 Avian, Bird DPM Podiatry $37,327
10 2513 Copper, Metal H DPM Podiatry $32,668
Provider1
• Charges significantly higher than his peers
Provider 2
• Specialized in psychiatry, and is not generally associated with nail debridement
Provider 5
• Practiced in a specialty that is not generally associated with the nail debridement procedure
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 70
Fraud and Abuse (F&A) Detection by Profiling Providers
Ranking Top 5 Codes by Quantity for Provider: GR0000000 – ABC Medical Group, Inc
6 Months of Service xx/xx-yy/yy, Paid in Months xx/xx-yy/yy
GR0000000Qty Rank and % Compared to
OB/GYN Groups6 Month Peer
Averages
Code Code DescTotal Dollars
Paid
Total Qty Adj Rank
% of Total Qty
Total #
Provs
Peer Avg Dollars
Paid
Peer Avg Qty
81025-TC Urine pregnancy test $12,560.60 2,710 #1 or 19% 65 $1,022.93 220
Z9752Family planning counseling (15 minutes) $33,086.45 1,735 #1 or 21% 55 $2,778.90 149
Z6410Perinatal education, individual, each 15 minutes $9,511.71 1,131 #9 or 3% 91 $3,657.38 435
Z6204
Follow-up antepartum nutrition assessment, treatment and/or intervention; individual, each 15 minutes $7,569.00 900 #5 or 4% 96 $2,074.14 247
Z1034 Antepartum follow-up visit $48,625.92 804 #16 or 2% 195 $11,996.08 203
Outlier detection based on profiling provide data.
HCAD 6635 Health Information Analytics Copyright © 2016 Frank F. Wang 71