Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Disease Surveillance Monitoring and Reacting to Outbreaks (like Ebola) with an Enterprise Data Warehouse

7,299 views

Published on

The current options for monitoring data to help identify disease outbreaks like Ebola are not great. These are: 1) Monitoring chief complaint/reason for admission data in ADT data streams. Although this is a real-time approach, the data is not codified and would require some degree of NLP. 2) Monitoring coded data collected in EHRs. The most precise option available, but the data is not available until after the patient encounter is closed, which would be too late in most cases. And 3) Monitoring billing data. This approach has the same problems as the two listed above, but it’s better than nothing in the absence of an EMR. All of these weaknesses can be solved with the use of a data warehouse.

Published in: Healthcare, Data & Analytics
  • Hello! Get Your Professional Job-Winning Resume Here - Check our website! https://vk.cc/818RFv
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here

Disease Surveillance Monitoring and Reacting to Outbreaks (like Ebola) with an Enterprise Data Warehouse

  1. 1. Disease Surveillance Monitoring and Reacting to Outbreaks (like Ebola) with an Enterprise Data Warehouse Dale Sanders Senior VP
  2. 2. Disease Surveillance in Healthcare You don’t have to look much past today’s headlines to understand the importance of disease surveillance among healthcare providers. Here’s a summary of the current options available for monitoring healthcare data that could help identify disease outbreaks. Monitoring billing data. © 2014 Health Catalyst www.healthcatalyst.com Monitoring chief complaint /reason for admission data in Admit, Discharge, and Transfer (ADT) data streams. Monitoring coded data collected in Electronic Health Records (EHRs). Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  3. 3. © 2014 Health Catalyst www.healthcatalyst.com Data Quality and Data Profiles One of the key concepts underlying the discussion is data quality. Poor data quality translates into poor outcomes for decision-making, imprecise decision-making, and imprecise responses to a situation. Data Quality = Completeness x Validity Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  4. 4. © 2014 Health Catalyst www.healthcatalyst.com Data Quality and Data Profiles The higher your data quality, the more precise your understanding of the situation at hand, and the more precise your decisions and reaction can be to a situation. Just like photographs of a higher resolution show more granular detail, data “completeness” shows more detail and is critical to the patient diagnosis and treatment. Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  5. 5. © 2014 Health Catalyst www.healthcatalyst.com Data Quality and Data Profiles Data “Validity” is a little more difficult to describe, but in short, it relates to the context of the situation in which accurate data is collected. It assumes the treatment team is inputting accurate data into the system. It also depends on the timeliness of the data. Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  6. 6. © 2014 Health Catalyst www.healthcatalyst.com Data Quality and Data Profiles In addition to Data Quality, the other key concept is the notion of a “Data Profile” for a patient and disease type. A simple data profile for a patient is pretty straightforward—name, gender, age, height, weight, address—those are the basics of a first pass at a data profile. Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  7. 7. © 2014 Health Catalyst www.healthcatalyst.com Data Quality and Data Profiles Diseases also have a data profile, based upon commonly acknowledged symptoms and, hopefully, very discrete lab results or other diagnostics, such as those from imaging. Using a set of Boolean logical determinations, based on complete and valid data, we can immediately see opportunities for computer-assisted treatment decision-making. Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  8. 8. Every healthcare system in the U.S. should possess a generalized data-profile-alerting enterprise data warehouse, that could also feed analytic output to the EHR at the point of care, as well as any number of other downstream data consumers, such as state and federal governments. © 2014 Health Catalyst www.healthcatalyst.com Data Profile Alert Engine engine, fed by an Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  9. 9. © 2014 Health Catalyst www.healthcatalyst.com Data Profile Alert Engine Diagram of Conceptual Architecture: Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  10. 10. Disease Surveillance in the Near-Term Option 1 Monitoring ADT messages: This option would use the chief complaint/reason for admission data in an ADT message. Advantage: This option is real-time, upon presentation of the patient at a healthcare facility. Disadvantage: Lacks codified, computable data in the data stream, thus requiring some form of natural language processing. © 2014 Health Catalyst www.healthcatalyst.com Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  11. 11. Disease Surveillance in the Near-Term Option 2 Analyzing Coded EHR and Other Clinical Data: Monitors coded data (SNOMED or ICD) for diagnosis, labs tests and results, and diagnostic imaging. Advantage: The most precise option available however it is unlikely to ever be a real-time option due to the inherent nature of healthcare delivery. Disadvantage: Timeliness of treatment data will lag the decision making process too late for effective decision making. © 2014 Health Catalyst www.healthcatalyst.com Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  12. 12. Disease Surveillance in the Near-Term Option 3 Analyzing Coded Data From Billing Systems: This has all the problems of option 2 and more. It’s not unusual for revenue cycle processes and systems to take over 30 days to drop a bill. But, in the absence of an EMR, this data is certainly better than nothing for profiling. © 2014 Health Catalyst www.healthcatalyst.com Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  13. 13. Options are not great right now, but with a well-designed and flexible data warehouse, at least healthcare delivery organizations have the beginnings of an option that can improve in precision as we integrate more and more data, increasing the completeness and resolution of the picture for syndromic surveillance. © 2014 Health Catalyst www.healthcatalyst.com Conclusion Disease Surveillance Needs a Data Warehouse Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  14. 14. Link to original article for a more in-depth discussion. Disease Surveillance: Monitoring and Reacting to Outbreaks (like Ebola) with an Enterprise Data Warehouse Predictive Analytics: It’s the Intervention That Matters (webinar, slides, or transcript) Dale Sanders, Senior Vice President and David Crockett, PhD, Senior Director of Research and Predictive Analytics © 2014 Health Catalyst www.healthcatalyst.com More about this topic The Power of Maps to Improve Predictive Analytics in Healthcare David Crockett, PhD, Senior Director of Research and Predictive Analytics Defining Predictive Analytics in Healthcare A primer on predictive analytics and what it means for healthcare Three Problems with Comparative Analytics, Predictive Analytics, and NLP Dale Sanders, Senior Vice President In Healthcare Predictive Analytics, Big Data is Sometimes a Big Mess David K. Crockett, Ph.D., Senior Director of Research and Predictive Analytics Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  15. 15. © 2014 Health Catalyst www.healthcatalyst.com For more information: Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.
  16. 16. Other Clinical Quality Improvement Resources Dale Sanders has been one of the most influential leaders in healthcare analytics and data warehousing since his earliest days in the industry, starting at Intermountain Healthcare from 1997-2005, where he was the chief architect for the enterprise data warehouse (EDW) and regional director of medical informatics at LDS Hospital. In 2001, he founded the Healthcare Data Warehousing Association. From 2005-2009, he was the CIO for Northwestern University’s physicians’ group and the chief architect of the Northwestern Medical EDW. From 2009-2012, he served as the CIO for the national health system of the Cayman Islands where he helped lead the implementation of new care delivery processes that are now associated with accountable care in the US. Prior to his healthcare experience, Dale had a diverse 14-year career that included duties as a CIO on Looking Glass airborne command posts in the US Air Force; IT support for the Reagan/Gorbachev summits; nuclear threat assessment for the National Security Agency and START Treaty; chief architect for the Intel Corp’s Integrated Logistics Data Warehouse; and co-founder of Information Technology International. As a systems engineer at TRW, Dale and his team developed the largest Oracle data warehouse in the world at that time (1995), using an innovative design principle now known as a late binding architecture. He holds a BS degree in chemistry and minor in biology from Ft. Lewis College, Durango Colorado, and is a graduate of the US Air Force Information Systems Engineering program. © 2014 Health Catalyst www.healthcatalyst.com Click to read additional information at www.healthcatalyst.com Proprietary. Feel free to share but we would appreciate a Health Catalyst citation.

×