1 / 31

The Analytic System: Finding Patterns in the Data

The Analytic System: Finding Patterns in the Data. John L. Haughom, MD June 2014. Healthcare: The Way It Should Be. Part One – Forces Driving Transformation Chapter One – Forces Defining and Shaping the Current State of U.S. Healthcare

hamish-cummings
Download Presentation

The Analytic System: Finding Patterns in the Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. The Analytic System:Finding Patterns in the Data John L. Haughom, MD June 2014

  2. Healthcare: The Way It Should Be Part One– Forces Driving Transformation • Chapter One – Forces Defining and Shaping the Current State of U.S. Healthcare • Chapter Two – Present and Future Challenges Facing U.S. Healthcare Part Two– Laying the Foundation for Improvement and Sustainable Change • What will it take to successfully ride the transformational wave? Part Three– Looking into the Future • What will it take to successfully ride the transformational wave? Available for FREE download at: http://www.healthcatalyst.com/ebooks/healthcare-transformation-healthcare-a-better-way/

  3. Implementing an Effective System of Production in Healthcare Analyticsystem Scalable and sustainable outcomes Deploymentsystem Contentsystem

  4. Analytic System Components

  5. Late-Binding™ Data Warehouse Metadata: EDW Atlassecurity and auditing FINANCIAL SOURCES (e.g. EPSi, Peoplesoft, Lawson) DEPARTMENTAL SOURCES (e.g. Apollo) Common, linkable Vocabulary FinancialSource Marts DepartmentalSource Marts Readmissions AdministrativeSource Marts PatientSource Marts PATIENT SATISFACTION SOURCES (e.g. NRC Picker, Press Ganey) ADMINISTRATIVE SOURCES (e.g. API Time Tracking) Diabetes Sepsis EMR Source Marts HRSource Mart EMR SOURCE Human Resources (e.g. PeopleSoft) More transformation Less transformation

  6. Population Health Management Clinical Integration hierarchy - care process families Outpatient Inpatient SNF Home Health Hospice Home ClinicCare Hyperlipidemia Acute Myocardial Infarction(AMI) Cardiac Rehab CoronaryAtherosclerosis Percutaneous Intervention(PCI) Ischemic Heart Disease care process family Coronary Artery Bypass Graft (CABG)

  7. Population Health Management Clinical Integration hierarchy - clinical programs Inpatient SNF Home Health Hospice Home ClinicCare Outpatient Cardiovascular clinical program Heart Rhythm Disorders care process family Ischemic Heart Diseasecare process family Heart Failurecare process family Vascular Disorders care process family

  8. Clinical Integration hierarchy Clinical programs – ordering of care CV W&C GI Neuro Sciences Musculo-skeletal General Med Resp-iratory Primary Care Surgery Oncology Peds Spec Mental Health care process families e.g., Heart Failure care process families e.g., Pregnancy care process families e.g., Lower GI Disorders care process families e.g., Obstructive Lung Disorders care process families e.g., Spine Disorders care process families e.g., Joint Replace-ment care process families e.g., Infectious Disease care process families e.g., Diabetes care process families e.g., Urologic Disorders care process families e.g., Breast Cancer care process families e.g., Peds CV Surg care process families e.g., Depression

  9. Linking the three systemsClinical Integration hierarchy

  10. Top 32 care process families account for 80% of the opportunity Inpatient per case KPA Top 10 care process families account for over 40% of the opportunity Percent of total resources consumed Care process families by resources consumed (high to low)

  11. Frequency distribution with control limits Centerline Lower control limit Upper control limit 99% Within specifications Defect Defect Number of times observed (Number, rate, percentage, proportion) Spread 0.5% 0.5% 2.33 std. devs. 2.33 std. devs. Value observed

  12. The Causes of Variation

  13. A Clinical Example Frequency distributions and control limits are common in healthcare

  14. Statistical process control chart(How a process behaves over time) Clinical process XYZ Title Assignable (special cause) variation Upper control limit Random (common cause) variation Centerline Values Observed Lower control limit The further a point moves off the center line the higher the probability it is not random variation and the greater the probability you can identify an assignable cause. Time

  15. Uses of control charts Unstable process Stable process Process improvement worse Control limits Quality Improvement Assignable variation suggesting an unstable process Random variation suggesting a stable process Process capability better Time

  16. Approach to improvement Punish the outliers 1 box = 100 cases in a year Focus on minimum standard metric Mean # of cases # of Cases Poor outcomes Excellent outcomes Poor outcomes Excellent outcomes • Current condition • Significant volume • Significant variation Option 1: Punish the outliers

  17. Approach to improvement Focus on better care 1 box = 100 cases in a year Focus on best practice care process model Mean # of Cases # of Cases Poor outcomes Excellent outcomes Poor outcomes Excellent outcomes Option 2: Identify best practice “Narrow the curve and shift it to the right” • Current condition • Significant volume • Significant variation

  18. Improvement Approach - Prioritization High 3 1 # of Cases # of Cases Variability 4 2 Poor outcomes Excellent outcomes Poor outcomes Excellent outcomes # of Cases # of Cases Poor outcomes Excellent outcomes Poor outcomes Excellent outcomes Low Low High Resource consumption 18

  19. A Demonstration • Demonstrating the power of modern analytics… • …Finding Meaningful Patterns in your data

  20. What Does Health Catalyst Do? • Enterprise Data Warehouse “single source of truth” • Library of data acquisition adapters • Metadata repository • Auditing and access control • Supports a variety of analytic applications • Health Catalyst • Client developed Platform

  21. What Does Health Catalyst Do? • Reports & Dashboards • Ad-hoc query • Registries • Quality measures • Population health • Data mining • Clinical improvement • Workflow analysis • Modeling and predictive analytics Applications Platform

  22. What Does Health Catalyst Do? • Installation • Configuration • Data Architecture • Improvement • Project Management • Clinical Improvement • “Lean” Process Improvement Services Applications Platform

  23. Application Families Foundational Applications Discovery Applications Advanced Applications Encourage broad use of the data warehouse by presenting dashboards, reports, and basic registries across clinical and departmental areas. Allow users to discover patterns and trends within the data that inform prioritization, inspire new hypotheses, and define populations for management. Provide deep insights into evidence-based metrics that drive improvement in quality and cost reduction through managing populations, workflows, and patient injury prevention.

  24. Demos Foundational Applications Discovery Applications Advanced Applications` EDIT—Executive Dashboard Integration Tool (Key Performance Indicator editable collage from all app categories) CAFE—Comparative Analytics Framework and Exchange—across Healthcare Systems and National Benchmarks Key Process Analysis (KPA) Population Suitese.g., Ischemic Heart Disease Population Explorer Cohort Builder Patient Satisfaction Explorer Population Modules e.g., CABG, Stent, AMI Comorbidity Analyzer General Ledger Explorer Regulatory Explorer Readmission Explorer Workflow / Operational Suites e.g., Acute Medical Attribution Modeler Practice Management Explorer Suite Workflow/Operational Modules e.g., ICU, MedSurg, Emergency ACO Explorer Suite Patient Flow Explorer Readmission Predictor Financial Management Explorer Patient Injury Prevention Suites e.g., Infection Prevention Payment Model Analyzer Labor Management Explorer Metric Correlation Analyzer Patient Injury Prevention Modules e.g., CAUTI, CLABSI, SSI Patient Flight Plan Predictor Rev Cycle Explorer

  25. Demos: How Analytics Drive Improvement & Savings Demo 1: Key Process Analysis (KPA).Identify areas of greatest opportunityfor quality improvement and savings Demo 2: Population Explorer. Identify potential risk by understanding relative size of disease populations and risk profiles Demo 3: Heart Failure.Achieving quality improvement and cost reductions by directing targeted interventions to high-risk patients Demo 4: Community Care.Monitoring high-risk patientsin primary care to prevent expensive acute treatment

  26. KPA: Measuring Opportunity Using provider variation to calculate the potential financial impact of improving and standardizing care processes Mean Cost per Case = $10,000 Dr. J. 15 Cases $15,000 Avg. Cost Per Case Total Opportunity = $75,000 Total Opportunity = $1,200,000 Total Opportunity = $175,000 Total Opportunity = $500,000 $4,000 x 25 cases = $100,000 opportunity $5,000 x 15 cases = $75,000 opportunity Cost Per Case, Vascular Procedures

  27. Poll Questions • Does your organization effectively engage front line clinicians in improvement projects where they routinely analyze care processes to eliminate inappropriate variation and improve processes over time? • 91 Respondents • 5 – Definitely – 19% • 4 – 22% • 3 – 26% • 2 – 25% • 1 – Not at all – 8%

  28. Demos: How Analytics Drive Shared Savings Demo 1: Key Process Analysis (KPA).Identify areas of greatest opportunity for quality improvement and savings Demo 2: Population Explorer. Identify potential risk by understanding relative size of disease populations and risk profiles Demo 3: Heart Failure.Achieving quality improvement and cost reductions by directing targeted interventions to high-risk patients Demo 4: Community Care.Monitoring high-risk patients in primary care to prevent expensive acute treatment

  29. In Summary… • A good Analytic System that unlocks your data, automates its distribution and makes it easy to see important patterns in the data is necessary to support meaningful and sustainable improvement. • The data model on which your EDW is based matters. • A Clinical Integration Hierarchy can help you organize how you think about and manage health care delivery. • Differentiating random variation from assignable or “special cause” variation is important in healthcare and in improvement. • Good use of your data can help guide you in an effort to maximize improvement and valuefor the investment.

  30. Poll Question • Using our discussion of an Analytic System as a guide, on a Scale of 1-5, how effective is your organization’s analytical strategy and capability? • 78 Respondents • 5 – Very Effective – 9% • 4 – 15% • 3 – 35% • 2 – 25% • 1 – Very Limited – 15%

  31. Thank You Upcoming Educational Opportunities • Late-Binding Data Warehousing: An Update on the Fastest Growing Trend in Healthcare Analytics • Date: July 10th • Presenter: Dale Sanders, Senior Vice President, Health Catalyst • Register at http://healthcatalyst.com/ • Healthcare Analytics Summit • Join top healthcare professionals for a high-powered analytics summit using analytics to drive an engaging experience with renowned leaders who are on the cutting edge of healthcare using data-driven methods to improve care and reduce costs. • Date: September 24th-25th • Location: Salt Lake City, Utah • Save the Date: http://www.healthcatalyst.com/news/healthcare-analytics-summit-2014 For Information Contact: John.Haughom@healthcatalyst.com

More Related