Kaiser Permanente Standards Summit September 7-8 , 2011 Stanley M. Huff, MD

1. Detailed Clinical Models, Coded Terminology, and an “App Store” for Health Care UHIMSS and UHIMA Annual Spring Conference May 18, 2012 Stanley M Huff, MD Chief Medical Informatics Officer Kaiser Permanente Standards Summit September 7-8 , 2011 Stanley M. Huff, MD

2. an integrated health system Intermountain Healthcare

3. Four ideas • patientslikeme • Learning Healthcare System • Data capture as part of clinical care • Billing and quality measures based on clinical charting • An “App Store” for healthcare

4. patientslikeme • Institute of Medicine meeting • James Heywood • Brother Stephen with ALS • "It is simply no longer possible to believe much of the clinical research that is published, or to rely on the judgment of trusted physicians or authoritative medical guidelines. I take no pleasure in this conclusion, which I reached slowly and reluctantly over my two decades as an editor of The New England Journal of Medicine.” Marcia Angell, MD

5. patientslikeme steps • Step 1: Create/update and share your health profile • Step 2: Find support from others like you and compare experiences • Step 3: Learn from aggregated community Treatment and Symptom Reports • Step 4: Take profile to your doctor to have an improved treatment conversation • Step 5: Play an integral part in your own health care

6. A Learning Health System (LHS) “… one in which progress in science, informatics, and care culture align to generate new knowledge as an ongoing, natural by-product of the care experience, and seamlessly refine and deliver best practices for continuous improvement in health and health care.” (Institute of Medicine)

7. Federal Agencies Beacon Community A Learning Health System for the Nation Pharmaceutical Firm State Public Health Community Practice Governance Patient Engagement Trust Analysis Dissemination IntegratedDelivery System Health Information Organization 7 Health Center Network

8. The Right Way, and the Wrong Way • Medication ordering/ePrescribing • Nearly 100% use, because it has value to the clinician • Problem list application • ~30% use • Not yet connected to order sets or measures or automatic billing

9. What we hope to do • Capture problems at the point of care from clinicians • Using coded clinical terminology (SNOMED CT) • Drive clinical processes from the problems • Order sets • Protocols • Denominator for measures • Derive billing codes and MU measures based rules and logic applied to clinical data

10. Homer Warner and HELP The first version of the HELP (Health Evaluation through Logical Processing) system was built in 1967 From its inception, the HELP system was built primarily to provide advanced decision support Dr. Homer Warner

11. Patient

12. Core Assumptions ‘The complexity of modern medicine exceeds the inherent limitations of the unaided human mind.’ ~ David M. Eddy, MD, Ph.D. ‘... man is not perfectible. There are limits to man’s capabilities as an information processor that assure the occurrence of random errors in his activities.’ ~ Clement J. McDonald, MD

13. Clinical System Approach Intermountain can only provide the highest quality, lowest cost health care with the use of advanced clinical decision support systems integrated into frontline workflow

14. Adverse Drug Events • Rates today (2008-9) at about 230 per year • Generates >$1 million per year in net cost reductions at LDS Hospital alone

15. Well newborn bilirubin testing

17. Newborns w/ hyperbilirubinemia

18. Decision Support Modules • Antibiotic Assistant • Ventilator weaning • ARDS protocols • Nosocomial infection monitoring • MRSA monitoring and control • Prevention of Deep Venous Thrombosis • Infectious disease reporting to public health • Diabetic care • Pre-op antibiotics • ICU glucose protocols • Ventilator disconnect • Infusion pump errors • Lab alerts • Blood ordering • Order sets • Patient worksheets • Post MI discharge meds

19. Current Status • Intermountain can’t create all of the executable knowledge that it needs • Each vendor builds every application, and creates its own executable knowledge (rules, alerts, reminders, protocols, order sets, quality measures), etc. • Even different installations from the same vendor often can’t use knowledge created by other customers

20. Strategic Goals • Minimum goal: Be able to share applications, reports, alerts, protocols, and decision support with ALL customers of our current partner • Maximum goal: Be able to share applications, reports, alerts, protocols, and decision support with anyone in the WORLD

21. VA Order Entry COS VA Order Services Order Entry API (adapted from Harold Solbrig) Application Update Medication Order Interface Service Update PharmacyOrder WHERE orderNumber = “4674” … MUMPS Database Data

22. Dept of Defense COS VA Order Services Order Entry API – Different Client, Same Service (adapted from Harold Solbrig) Application Update Medication Order Interface Service Update PharmacyOrder WHERE orderNumber = “4674” … MUMPS Database Data

23. Dept of Defense GE Services Order Entry API – Different Server, Same Client (adapted from Harold Solbrig) Application Update Medication Order COS Interface Update PharmacyOrder WHERE orderNumber = “4674” … Service GE Repository Oracle Tables Data

24. COS Order Entry API (adapted from Harold Solbrig) . . . Application Interface Service Data

25. From Ben Adida and Josh Mandel

26. Standard set of detailed clinical data models coupled with… Standard coded terminology Standard API’s (Application Programmer Interfaces) for healthcare related services Open sharing of models, coded terms, and API’s Sharing of decision support modules and knowledge What Is Needed to Create a New Paradigm?

27. What are detailed clinical models?Why do we need them?

28. A diagram of a simple clinical model Clinical Element Model for Systolic Blood Pressure SystolicBP SystolicBPObs 138 mmHg data quals BodyLocation BodyLocation Right Arm data PatientPosition PatientPosition Sitting data

29. Estimated Auto Manual What if there is no model? Site #1 70 % 37 Hct, manual: 70 % 35 Hct, auto : Site #2 70 % 37 Hct :

30. Patient Identifier Patient Identifier Date and Time Date and Time Observation Type Observation Type Method Observation Value Observation Value Units Units 123456789 123456789 7/4/2005 7/4/2005 Hct Hct, manual manual 37 37 % % 123456789 123456789 7/19/2005 7/19/2005 Hct Hct, auto auto 35 35 % % Relational database implications If the patient’s hematocrit is <= 35 then ….

31. What do we model? • All data in the patient’s EMR, including: • Allergies • Problem lists • Laboratory results • Medication and diagnostic orders • Medication administration • Physical exam and clinical measurements • Signs, symptoms, diagnoses • Clinical documents • Procedures • Family history, medical history and review of symptoms

32. Model Source Expression (CDL) model BloodPressurePanel is panel { key code(BloodPressurePanel_KEY_ECID); statement SystolicBloodPressureMeas systolicBloodPressureMeas optional systolicBloodPressureMeas.methodDevice.conduct(methodDevice) systolicBloodPressureMeas.bodyLocationPrecoord.conduct(bodyLocationPrecoord) systolicBloodPressureMeas.bodyPosition.conduct(bodyPosition) systolicBloodPressureMeas.relativeTemporalContext.conduct(relativeTemporalContext) systolicBloodPressureMeas.subject.conduct(subject) systolicBloodPressureMeas.observed.conduct(observed) systolicBloodPressureMeas.reportedReceived.conduct(reportedReceived) systolicBloodPressureMeas.verified.conduct(verified); statement DiastolicBloodPressureMeas diastolicBloodPressureMeas optional …. statement MeanArterialPressureMeas meanArterialPressureMeas optional …. qualifier MethodDevice methodDevice optional; md.code.domain(BloodPressureMeasurementDevice_DOMAIN_ECID); qualifier BodyLocationPrecoord bodyLocationPrecoord optional; blp.code.domain(BloodPressureBodyLocationPrecoord_DOMAIN_ECID); modifier Subject subject optional; attribution Observed observed optional; attribution ReportedReceived reportedReceived optional; attribution Verified verified optional; }

33. Number of models created - 4384 Laboratory models – 2933 Evaluations – 210 Measurements – 353 Assertions – 143 Procedures – 87 Qualifiers, Modifiers, and Components Statuses – 26 Date/times – 27 Others – 400+ Browser and download site http://intermountainhealthcare.org/CEM/Pages/LicenseAgreement.aspx Model Subtypes Created

34. Clinical modeling activities • Netherlands/ISO Standard • CEN 13606 • United Kingdom – NHS • Singapore • Sweden • Australia • openEHR Foundation • Canada • US Veterans Administration • US Department of Defense • Intermountain Healthcare • Mayo Clinic • HL7 • Version 3 RIM, message templates • TermInfo • CDA plus Templates • Detailed Clinical Models • greenCDA • Tolven • NIH/NCI – Common Data Elements, CaBIG • CDISC SHARE • Korea

35. Clinical Information Modeling Initiative • Shared repository of detailed clinical information models • Using a single formalism • Based on a common set of base data types • With formal bindings of the models to standard coded terminologies • Repository is open and models are free for use at no cost

36. Questions?