Clinical Analytics

56 %
44 %
Information about Clinical Analytics

Published on October 15, 2014

Author: michaelobice



An Introductions to Clinical Analytics as a Sub-discipline in Health Informatics

1. An Overview of Clinical Analytics Michael O. Bice Health Informatics Consultant

2. Agenda • Clinical informatics as context for clinical analytics • Uniqueness of medical data mining • Define and describe the practice of clinical analytics • Challenges facing use of clinical analytics • Tools used to analyze clinical data • Use of clinical analytics in different healthcare settings • The future of clinical analytics

3. Domains of Clinical Informatics

4. Uniqueness of Medical Data Mining • Heterogeneity of medical data ▫ Raw medical data are voluminous and heterogeneous ▫ Medical data may be collected from various images, interviews with the patient, laboratory data, and the physician’s observations and interpretations ▫ All these components may bear upon the diagnosis, prognosis, and treatment of the patient, and cannot be ignored • Ethical, legal, and social issues ▫ Privacy and security considerations ▫ Fear of lawsuits ▫ Need to balance the expected benefits of research against any inconvenience or possible injury to the patient

5. Uniqueness of Medical Data Mining • Statistical philosophy: Methods of medical data mining must address ▫ The heterogeneity of data sources ▫ Data structures ▫ The pervasiveness of missing values • Special status of medicine ▫ Outcomes of medical care are life-or-death ▫ They apply to everybody ▫ Medicine is a necessity, not merely an optional luxury, pleasure, or convenience

6. Definition of Clinical Analytics (CA) • Clinical analytics encompasses the capture and use of discrete clinical data to identify and measure quality, patient safety, or service line efficiencies and improvements

7. Promise of Clinical Analytics • Through careful implementation of health analytics, hospitals can transform unwieldy amalgamations of data into information that can: ▫ Improve patient outcomes ▫ Increase safety ▫ Enhance operational efficiency ▫ Support public health efforts

8. Promise of Clinical Analytics • CA applications are designed to place: ▫ timely ▫ relevant ▫ actionable information • Into the hands of all users with a legitimate interest in it

9. Current Use of CA • Collecting and leveraging clinical and claims data to enhance patient care cost, safety and efficiency • Data is looked at on a variety of levels ▫ A specific patient ▫ Population-based, such as data specific to a particular physician or to a certain condition, such as diabetes or hypertension • Using rule sets from a wide variety of organizations ▫ Voluntary programs (the Leapfrog Group) ▫ Government sources (the Hospital Compare Database) ▫ Trade organizations (the Council of Teaching Hospitals or the Society for Thoracic Surgeons)

10. Current Use of CA • Much of the information that healthcare organizations ultimately choose to report is driven in one of three ways: ▫ Data that they are required to track by the government or other external organizations ▫ Data that healthcare organizations choose to look at that is driven by QA or cost containment opportunities ▫ Information that is required for recertification of professional staff

11. Types of CA Practitioners • Pharmacists with formal informatics training (e.g., Masters or Doctorate in Medical Informatics or Informatics fellowship) or extensive clinical informatics experience to develop and maintain pharmacy content • Physicians with informatics experience to translate clinical guidelines and study protocols into CDS interventions • Doctoral-level medical informaticians

12. Types of CA Practitioners • Registered nurses (RNs) with informatics training and experience • Dedicated software developers and project managers without a clinical background • Master’s in Health Informatics • Master’s in Health Administration with Concentration in Health Informatics

13. CA Continuum • Data extraction tools (Bottom of Hierarchy) ▫ Collect data from existing databases • Data warehouses and data marts • Formatting tools and techniques ▫ Used to "cleanse" the data and convert it to formats that can easily be understood

14. CA Continuum • Enterprise reporting and analytical tools ▫ Online analytic process (OLAP) engines and analytical application development tools are for professionals who analyze data and perform business forecasting, modeling and trend analysis • Human intelligence tools (Top of Hierarchy) ▫ Human expertise, opinions and observations

15. CA Challenges • Modern medicine generates, almost daily, huge amounts of heterogeneous data. Those who deal with such data understand that there is a widening gap between data collection and data comprehension. • In industry, data are typically viewed as a critical enterprise asset; medicine, in contrast, tends to view data as a byproduct of operations • Clinical analytics continues to be used primarily for retrospective analyses, rather than real-time clinical decision support.

16. CA Challenges • Organizational, not data or financial concerns, are holding back adoption. Primary obstacles to widespread analytics adoption include: ▫ Knowing how to use analytics to improve the business ▫ Management bandwidth due to competing priorities ▫ Lack of skills internally ▫ Ability to get the data ▫ Existing culture discourages info sharing

17. CA Challenges • Lack of use of tools to support the work of clinical analytics • Lack of money to hire additional appropriately trained clinical informaticians • Rapidly expanding regulatory reporting and compliance requirements along with increasing emphasis on quality measures • Healthcare provider organizations are struggling to understand how the government’s role in clinical analytics is going to evolve in the future

18. Inventory of Tools and Best Practices • A multidisciplinary team responsible for creating and maintaining the clinical content • An external repository of clinical content with web-based viewer that allows anyone to review it • An online, interactive, Internet-based tool to facilitate content development and collaboration

19. Inventory of Tools and Best Practices • An enterprise-wide tool to maintain the controlled clinical terminology concepts ▫ The availability of a robust, controlled clinical terminology(e.g., SNOMED for problems, LOINC for lab results and ICD-10 for billing diagnoses, etc.) ▫ Many controlled terminologies include some sort of semantic network that maintains various types of relationships among the clinical terms

20. Inventory of Tools and Best Practices • Niche vendors that specialize in the development of data warehouses or data mining to assist in this type of analysis (See www. • Use of data warehouses for clinical purposes is evolving ▫ According to data from the HIMSS Analytics™ Database, approximately 30% of U.S. hospitals presently use a clinical data warehouse ▫ Usage is more widespread among hospital systems and academic health centers

21. Case Studies (Duke UHS) • Leveraging enterprise data through computerized patient safety initiatives ▫ Integrated data warehouse ▫ Web-based safety dashboard ▫ Proactive detection and subsequent amelioration of Clostridium difficile colitis rates  Prevented 158 potential cases of nosocomially acquired C difficile colitis per year  Financial burden of C difficile colitis to range from $3669 to $7234 in additional hospital costs per infected patient, which by conservative analysis translates into a total savings of $578,968

22. Case Studies (Duke UHS) • Improving the business cycle: the Duke intensive care nursery ▫ Current and projected losses in the ICNursery ▫ Traditional cost-cutting not feasible ▫ Analysis suggested 4 areas for targeted improvement: MD documentation, medical record coding, revenue modeling, and 3rd party payments ▫ Current and retroactive profits recorded

23. Case Studies (Duke UHS) • Leveraging health analytics for emerging health issues ▫ Used its data warehouse to provide a highly refined estimate of patients likely to need H1N1 vaccine (Swine Flu)  Inpatient status  Diagnosis of chronic disease  High–risk mothers and children ▫ Timely and accurate information to the state and to better define DUHS strategy for vaccine administration

24. Case Studies (Beth Israel Deaconess Medical Center) • Challenge ▫ Need for a CDS tool capable of identifying the most appropriate imaging test for a specific patient  BIDPO physicians had the capability to select from 2,000 orderable radiological studies, many of which were state of the art technologies  The abundance of such options also resulted in potentially inappropriate testing, false positives, and potential risk to patients (e.g., contrast injections, interventional procedures, and radiation exposure)

25. Case Studies (Beth Israel Deaconess Medical Center) • Solution ▫ An advanced CDS system with computerized provider order entry (CPOE) and real-time insurer authorization ▫ Create a natural language ordering vocabulary ▫ A web-based, physician-designed user interface for Anvita Health’s imaging implementation was then seamlessly integrated into BIDMC’s existing EMR

26. Case Studies (Beth Israel Deaconess Medical Center) • Results ▫ CDS positively influenced up to 35% of all ordering decisions, and up to 10% of high-tech radiology decisions were changed ▫ CDS decreased inappropriate imaging, which reduced overall cost trends for the hospital, patients, and the health plan while increasing quality ▫ CDS identified testing contraindications (e.g., contrast dye use) in patients at high risk for adverse reactions

27. Future Considerations • Early stages of an information revolution in healthcare, as genomics, pharmacogenomics, and point-of-care decision support converge in a new era of personalized medicine • Active investment in health analytics, data integration, and data sharing are critical to creating efficiencies (Improve Signal to Noise ratio) • New approaches to data visualization and analysis are needed

28. Future Considerations CA is the next wave of HIT–converting paper to electronic impulses is a massive undertaking, but clearly not sufficient A widening gap between data collection and data comprehension – An industry that is drowning in data and starving for information and knowledge Conventional cost cutting may have run its course-need for finely grained systems analysis (Duke UHS example)

29. Future Considerations Moving CA from few large academic medical centers to general healthcare field (Few players dominate the CA discussions) Distinction between having information and knowledge – and acting on it, either individually or collectively Evolving discipline with significant upside potential

30. Pause and Reflect • Why study CA and why now? • What roles should the CEO, CFO and CIO play in bringing CA expertise into the organization? • How would you go about establishing CA capability in your hospital? • What skills and experience will you need to be CA “job ready” upon graduation?

Add a comment

Related presentations

Trabajo de democracia

Trabajo de democracia

October 23, 2014


Confrontando mitos mari

Confrontando mitos mari

November 6, 2014


Mitos y realidades de las sustancias psicoactivas

Mitos y realidades de las sustancias psicoactivas.

Confrontando mitos

Confrontando mitos

November 6, 2014

Confrontando mitos

Related pages

Clinical Analytics | ICIS

Clinical Analytics What is it? Clinical Analytics is an information system that provides up-to-date clinical information from ICIS in reports that drive ...
Read more

Clinical analytics 'next big thing' | Healthcare IT News

Clinical analytics and business intelligence tools have emerged as a top priority for hospital IT leaders who are moving towards accountable care adoption ...
Read more

Healthcare Analytics - Optum

Harness the power of your enterprise data. ... Creating a foundation for actionable analytics next. see all. request a presentation. Top Top Find a ...
Read more

Clinical analytics -

The next evolution: Analytics and population health management. Optum One supports and unites multiple tools to help decisionmakers identify their ...
Read more

The Many Types of Clinical Analytics (Module 3) | HIMSS

Retrospective Performance Measures and Predictive Analytics. Retrospective Performance Measures and Predictive Analytics; Regulatory Reporting, Compliance ...
Read more

Clinical Intelligence: The Big Data Analytics Revolution ...

Clinical Intelligence: The Big Data Analytics Revolution in Healthcare: A Framework for Clinical and Business Intelligence (English Edition) eBook: Peter ...
Read more

Health care analytics - Wikipedia

Health care analytics is a term used to describe the healthcare analysis activities that can be undertaken as a result of data collected from four areas ...
Read more

Keeping Up With Meaningful Use: Clinical Analytics Are Key

Wondering how you can continue to keep up with future meaningful use requirements? It turns out the clinical analytics will become increasingly critical...
Read more

Clinical Analytics Software | Predictive Analytics Suite ...

Clinical analytics solution to assist in cohort building, outcomes research and comparative effectiveness research. This enables hospitals and healthcare ...
Read more

How to Choose the Best Clinical Analytics Vendor: A Checklist

The clinical analytics market is a crowded and chaotic one, with many vendors lining up to claim they can help providers use their data to improve care and ...
Read more