1 / 23

Part I: Introduction to SHARPn Normalization

Part I: Introduction to SHARPn Normalization. Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare. Data Normalization. Goals To conduct the science for realizing semantic interoperability and integration of diverse data sources

taryn
Download Presentation

Part I: Introduction to SHARPn Normalization

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. Part I: Introduction toSHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare

  2. Data Normalization • Goals • To conduct the science for realizing semantic interoperability and integration of diverse data sources • To develop tools and resources enabling the generation of normalized EMR data for secondary uses

  3. Data Normalization Target Value Sets Information Models Normalization Targets Tooling Raw EMR Data Normalized EMR Data Normalization Process

  4. Normalization Targets • Clinical Element Models • Intermountain Healthcare/GE Healthcare’s detailed clinical models • Terminology/value sets associated with the models • using standards where possible

  5. CEM Models • Different models for different use cases • “CORE” models

  6. “Core” Models CORE Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B CEM C CEM D

  7. “Core” Models Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B CEM C CEM D CORE Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B CEM C CEM D

  8. “Core” Models Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B Clinical Trial Lab CEM model CEMC attribute 1 attribute 2 attribute 3 attribute 4 CEMD CEMA CORE Lab CEM model CEM B attribute 1 attribute 2 attribute 3 attribute 4 CEM C CEM A CEM D CEM B CEM C CEM D

  9. “Core” Models Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B Clinical Trial Lab CEM model CEMC attribute 1 attribute 2 attribute 3 attribute 4 CEMD CEM A CORE Lab CEM model CEM B attribute 1 attribute 2 attribute 3 attribute 4 CEM C CEM A EMR Lab CEM model CEM D CEM B CEM C attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM D CEM B CEM C CEM D

  10. CEM Models • Different models for different use cases • “CORE” models • CORENotedDrug -> SecondaryUseNotedDrug • COREStandardLab -> SecondaryUseStandardLab (+ 6 data type-specific models) • COREPatient -> SecondaryUsePatient

  11. Generating XSDs Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM B CEM C CEM D

  12. Generating XSDs Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A SHARP “reference class” CEM B attribute 5 attribute 6 attribute 7 attribute 8 CEM E CEM C CEM F CEM D CEM G CEM H

  13. Generating XSDs Secondary Use Lab CEM model attribute 1 attribute 2 attribute 3 attribute 4 CEM A SHARP “reference class” CEM B attribute 5 attribute 6 attribute 7 attribute 8 CEM E CEM C CEM F CEM D CEM G Secondary Use Lab XSD CEM H attribute 1 . . . . . . . . . attribute 3 . . . . . . . . . attribute 5 . . . . . . . . . attribute 6 . . . . . . . . . attribute 7 . . . . . . . . . attribute 8 . . . . . . . . . COMPILE

  14. Terminology/Value Sets • Terminology value sets define the valid values used in the models • Terminology standards are used wherever possible

  15. Terminology/Value Sets • Terminology value sets define the valid values used in the models • Terminology standards are used wherever possible Secondary Use Patient CEM model administrativeGender attribute X attribute Y attribute Z Gender Value Set: HL7 AdminGender {M, F} Gender CEM CEM A CEM B CEM C

  16. CEM Request Site and Browser https://intermountainhealthcare.org/CEMrequests

  17. Normalization Process • Prepare Mapping • UIMA Pipeline to transform raw EMR data to normalized EMR data based on mappings

  18. Mappings • Two kinds of mappings needed: • Model Mappings • Terminology Mappings

  19. Model Mappings HL7 CEM Secondary Use Patient CEM model MSH PID 1 2 … OBR OBX 1 2 3 4 5 6 … attribute 1 attribute 2 attribute 3 attribute 4 Secondary Use Lab CEM model CEM A CEM B attribute 1 attribute 2 attribute 3 attribute 4 CEM A CEM C CEM B CEM D CEM C CEM D

  20. Model Mappings

  21. Terminology Mappings HL7 from Mayo CEM HL7 AdministrativeGender M = MALE F = FEMALE Local Gender Codes 1 = MALE 2 = FEMALE

  22. Terminology Mappings CEM Fields LocalCodeTargetCodeTargetCodeSystem Gender M M HL7 Gender Gender F F HL7 Gender Race 2 2106-3 CDC Race Race W 2106-3 CDC Race RouterMethodDevice ORAL PO HL7 Route DoseFreq BID &0800,173 229799001 SNOMED DoseFreq BID &0800,220 229799001 SNOMED DoseFreq DAILY &0830 69620002 SNOMED DoseFreq Q24HRS 396125000 SNOMED DoseFreq ONE TIME ORDER 422114001 SNOMED DoseUNIT Puff 415215001 SNOMED DoseUNIT TABLET 428673006 SNOMED DoseUNITtsp 415703001 SNOMED DoseUNIT CAPSULE (HA 415215001 SNOMED DoseUNIT patch 419702001 SNOMED DoseUNIT gr 258682000 SNOMED DoseUNIT mL 258773002 SNOMED

  23. Pipeline • Implement in UIMA (Unstructured Information Management Architecture) • Configurable • Data sources – HL7, CCD, CDA, and Table format • Model mappings (different EMR systems may have different formats) • Terminology mappings • Inference mappings – infer ingredients from clinical drugs

More Related