Query Health: Distributed Population Queries Update & Demo from ONC’s Office of Standards & Interoperability Rich Elmore Coordinator, Query Health

Provide a look at how Query Health is progressing How do the different parts of the Query Health solution fit together? How might a distributed query work in a real technical environment? Objectives

Vision Enable a learning health system to understand population measures of health, performance, disease and quality, while respecting patient privacy, to improve patient and population health and reduce costs.

Distributed queries unambiguously define a population from a larger set Questions about disease outbreaks, prevention activities, health research, quality measures, etc.

Distributed Query Networks Voluntary, No Central Planning Community of participants that voluntarily agree to interact with each other. There will be many networks; requestors and responders may participate in multiple networks. RequestorsParticipating Responders Query

New York City / New York State Pilot Dr. Michael Buck, Primary Care Information Project 5

Aggregated DataPatient Data Query & Results Reviewer Query & Results Reviewer Data Source How would a distributed query work? Information Requester 5. Sends Query Results to Information Requestor Firewall 3. Distribute Query to Data Sources 1. EHR / Clinical Record (Patient Data) 1. EHR / Clinical Record (Patient Data) 2. Query Health Data Model Note: All patient level data stays behind the firewall. Translate patient data 4. Execute Query, format & return Results Responding Organization

Type II Diabetes Expanded Analysis Example Result Set 7 Example Result Set Query Result for Provider X (where X is each reporting provider): GenderAge RangeZip CodeSetting Encounter Type RaceEthnicity Insurance Coverage For specified time frame: (MM-DD-YYYY - MM-DD-YYYY) TotalMaleFemale< ≥ InpatientOutpatientED….. Numerator Counts Risk Score HbA1c > 9.0% Blood Pressure ≥ 140/90 mm Hg LDL ≥ 130 mg/dl Microalbumin > 30 microgram/mg Creatine BMI ≥ 25 kg/m^2 Smoking Status Foot Examination Eye Examination Medication - Statin Medication - Asprin Medication - Ace Inhibitor/ARB Denominator Counts Diagnosis of Diabetes Type I Type II And all Risks Scores And Hb A1c Result And BP Reading And LDL Result And Microalbumin And BMI And Medications

NYS DOH NYC PCIP Information Requestors Data Sources Axolotl RHIO Inter- systems RHIO eCW EHR Sends Query to Data Sources Distributes Query Results to Information Requestor New York City / New York State Pilot Sends Query to Data Sources Distributes Query Results to Information Requestor

Query Health Technical Approach and Proposed Standards 9

Vocabulary & Code Sets Develop modular, testable portfolio of Query Health standards and specifications that can adopted by the industry, and support key HITECH and govt. priorities Content Structure Queries & Responses Privacy & Security Foundation: Distributed Query Solutions SNOMED-CT Clinical Element Data Dictionary i2b2 The Results New QRDA 2 & 3 The Results New QRDA 2 & 3 PopMedNet LOINC ICD-10 RxNorm 10 Query Health Standards and Reference Implementation Stack Reference Implementation Stack The Question New HQMF The Question New HQMF Query Envelope Privacy Policy Enablement hQuery

The Query New HQMF Health Quality Measure Format HQMF newly modified to support the needs for dynamic population queries: – More executable – Simplified Advantages for query – Avoids “yet another standard” – Secure (vs procedural approach) – Works across diverse platforms Benefits – Speed and Cost

The Query Envelope Query agnostic Content agnostic Metadata facilitates privacy guidance from HIT Policy Committee RESTful interface specification

The Data Clinical Element Data Dictionary 13 – Demographic – Patient Contact Information – Payer Information – Healthcare Provider – Allergies & Adverse Reactions – Encounter – Surgery – Diagnosis – Medication – Procedure – Immunization – Advance Directive – Vital Signs – Physical Exam – Family History – Social History – Order – Result – Medical Equipment – Care Setting – Enrollment – Facility ONC S&I Framework deliverable Standards independent UML representation underway

The Results New QRDA Quality Reporting Document Architecture – Category I – Patient Level – Category II – Patient Populations – Category III – Population Measures Query Health will use new definitions of Categories II and III – Not yet specified and balloted – Needs implementation guide – Needs to align with eMeasures

Query Health How it works together 15

The path to critical mass 16 Today, distributed queries are generally limited to – Organizations with large IT & research budgets – Some exceptions (e.g., NYC PCIP, MDPHNet) Missing: Primary Care, FQHCs, CAHs, HIEs, etc… In other words, most places where clinical care is delivered and recorded Path to critical mass depends on – Query Health Standards – Health IT vendor participation Health IT vendors AllscriptsAmazing Charts AZZLYCerner dbMotionClinicalWorks EpiceRECORDS IBEZAInterSystems MedicityMicrosoft National Health Data Systems NextGenRelayHealth Siemens Check back - more to come at QueryHealth.org Health IT vendors AllscriptsAmazing Charts AZZLYCerner dbMotionClinicalWorks EpiceRECORDS IBEZAInterSystems MedicityMicrosoft National Health Data Systems NextGenRelayHealth Siemens Check back - more to come at QueryHealth.org

The Way Ahead for Query Health

Demonstrations 18

Demonstration Distributed Query Execution What you’ll see – Life cycle of a Distributed Query (1 requestor, 2 data providers) – Policy Enablement Layer (control of queries execution and results by data providers) – RESTful interface – Query Envelope metadata for work flow integration and policy enforcement – Integration of hQuery (Query execution) and PopMedNet (policy enablement) – Open source components Presenting – Marc Hadley, MITRE Corporation – Rob Rosen, Lincoln Peak 19

Demonstration Query Language What you’ll see – Query Composition using i2B2 query builder – Query representation of i2B2 using internal formats and ontologies – Translation of composed Query to new HQMF – Translation of new HQMF to SQL – Open source components Presenting – Shawn Murphy, Partners Healthcare – Keith Boone, GE Healthcare 20

Query Health Recap