part i: introduction to sharpn normalization hongfang liu, phd, mayo clinic tom oniki, phd,...
DESCRIPTION
Data Normalization Information Models Target Value Sets Raw EMR Data Tooling Normalized EMR Data Normalization Targets Normalization ProcessTRANSCRIPT
![Page 1: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/1.jpg)
Part I: Introduction toSHARPn Normalization
Hongfang Liu, PhD, Mayo ClinicTom Oniki, PhD, Intermountain Healthcare
![Page 2: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/2.jpg)
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
![Page 3: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/3.jpg)
Data Normalization
Information Models
Target Value Sets
Raw EMR Data
Tooling
Normalized EMR Data
Normalization Targets
Normalization Process
![Page 4: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/4.jpg)
Normalization Targets
Clinical Element Models– Intermountain Healthcare/GE Healthcare’s
detailed clinical modelsTerminology/value sets associated with
the models– using standards where possible
![Page 5: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/5.jpg)
CEM Models
Different models for different use cases“CORE” models
![Page 6: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/6.jpg)
“Core” Models
CORELab CEM modelattribute 1
attribute 2
attribute 3
attribute 4
CEM A
CEM C
CEM B
CEM D
![Page 7: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/7.jpg)
“Core” Models
CORELab CEM modelattribute 1
attribute 2
attribute 3
attribute 4
Secondary Use Lab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
CEM A
CEM C
CEM B
CEM D
![Page 8: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/8.jpg)
“Core” Models
CORELab CEM modelattribute 1
attribute 2
attribute 3
attribute 4
Secondary Use Lab CEM model
CEM A
CEMC
CEM B
CEMD
attribute 1
attribute 2
attribute 3
attribute 4
Clinical TrialLab CEM model
CEMA
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4CEM A
CEM C
CEM B
CEM D
![Page 9: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/9.jpg)
“Core” Models
CORELab CEM modelattribute 1
attribute 2
attribute 3
attribute 4
Secondary Use Lab CEM model
CEM A
CEMC
CEM B
CEMD
attribute 1
attribute 2
attribute 3
attribute 4
Clinical TrialLab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4CEM A
CEM C
CEM B
CEM D
EMRLab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
![Page 10: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/10.jpg)
CEM Models
Different models for different use cases“CORE” models
– CORENotedDrug -> SecondaryUseNotedDrug
– COREStandardLab -> SecondaryUseStandardLab (+ 6 data type-specific models)
– COREPatient -> SecondaryUsePatient
![Page 11: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/11.jpg)
Generating XSDsSecondary Use Lab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
![Page 12: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/12.jpg)
Generating XSDsSecondary Use Lab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
SHARP“reference class”
attribute 5
attribute 6
attribute 7
attribute 8
CEM E
CEM G
CEM F
CEM H
![Page 13: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/13.jpg)
Generating XSDsSecondary Use Lab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
SHARP“reference class”
attribute 5
attribute 6
attribute 7
attribute 8
CEM E
CEM G
CEM F
CEM H
COMPILE
Secondary Use Lab XSDattribute 1. . . . . . . . .attribute 3. . . . . . . . .attribute 5. . . . . . . . .attribute 6. . . . . . . . .attribute 7. . . . . . . . .attribute 8. . . . . . . . .
![Page 14: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/14.jpg)
Terminology/Value SetsTerminology value sets define the valid values used
in the modelsTerminology standards are used wherever possible
![Page 15: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/15.jpg)
Terminology/Value SetsTerminology value sets define the valid values used
in the modelsTerminology standards are used wherever possible
Secondary UsePatient CEM model
CEM B
CEM A
CEM C
administrativeGender
attribute X
attribute Y
attribute Z
Gender CEM GenderValue Set:
HL7AdminGender
{M, F}
![Page 16: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/16.jpg)
CEM Request Site and Browser
https://intermountainhealthcare.org/CEMrequests
![Page 17: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/17.jpg)
Normalization Process
Prepare Mapping UIMA Pipeline to transform raw EMR data
to normalized EMR data based on mappings
![Page 18: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/18.jpg)
Mappings
Two kinds of mappings needed:– Model Mappings– Terminology Mappings
![Page 19: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/19.jpg)
Model MappingsHL7 CEM
Secondary Use Patient CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
MSHPID
12…
OBROBX
123456…
Secondary Use Lab CEM model
CEM A
CEM C
CEM B
CEM D
attribute 1
attribute 2
attribute 3
attribute 4
![Page 20: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/20.jpg)
Model Mappings
![Page 21: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/21.jpg)
Terminology Mappings
HL7 from Mayo CEM
Local Gender Codes1 = MALE2 = FEMALE
HL7 AdministrativeGenderM = MALEF = FEMALE
![Page 22: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/22.jpg)
Terminology MappingsCEM Fields LocalCode TargetCode TargetCodeSystemGender M M HL7 GenderGender F F HL7 GenderRace 2 2106-3 CDC RaceRace W 2106-3 CDC RaceRouterMethodDevice ORAL PO HL7 Route DoseFreq BID &0800,173 229799001 SNOMED DoseFreq BID &0800,220 229799001 SNOMEDDoseFreq DAILY &0830 69620002 SNOMEDDoseFreq Q24HRS 396125000 SNOMEDDoseFreq ONE TIME ORDER 422114001 SNOMEDDoseUNIT Puff 415215001 SNOMEDDoseUNIT TABLET 428673006 SNOMEDDoseUNIT tsp 415703001 SNOMEDDoseUNIT CAPSULE (HA 415215001 SNOMEDDoseUNIT patch 419702001 SNOMEDDoseUNIT gr 258682000 SNOMEDDoseUNIT mL 258773002 SNOMED
![Page 23: Part I: Introduction to SHARPn Normalization Hongfang Liu, PhD, Mayo Clinic Tom Oniki, PhD, Intermountain Healthcare](https://reader035.vdocuments.net/reader035/viewer/2022062317/5a4d1af87f8b9ab059982863/html5/thumbnails/23.jpg)
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