SHARPn Data Normalization

November 18, 2013

Data-driven Healthcare

Big Data

Knowledge

Research P

ract

ice

Analytics

Domain Pragmatics

Experts

A framework for clinical data reuse

Replicate Replicate

Query

Production Systems

Production Databases

Enterprise Repository/Data Warehouse

Workgroup Datamarts

Query Query

Workflow or goal specific

Data AnalyticsNLP and Data Normalization

SHARPn 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 portable and scalable secondary uses

Data Normalization

Information Models

Target Value Sets

Raw EMR Data

Tooling

Normalized EMR Data

Normalization Targets

Normalization Process

Normalization Targets

Clinical Element Models– Based on Intermountain Healthcare/GE

Healthcare’s detailed clinical modelsTerminology/value sets associated with

the models– Using standards where possible

Normalization Process

Configuration of Model (Syntactic) and Terminology (Semantic) Mapping

UIMA Pipeline to transform raw EMR data to normalized EMR data based on mappings

Four Subprojects

Clinical Information Modeling Value Sets Management End-to-End Pipeline Normalized Data Representation and

Store

Secondary Use Clinical Element Models

GenericStatement GenericComponent

Core CEMs

SecondaryUse CEMs

Links

AdministrativeGender, …Severity, Status

Embracing the fact that data may not be able to be normalized and enabling bottom-up and top-down

http://www.clinicalelement.com

Status of Secondary Use CEMs

Model specification is finalCEM Browser is in productionManuscript is in preparation

Future:

Secondary Use CEMs and CEM Browser will be maintained through Clinical Information Modeling Initiative (CIMI)

SecondaryUseNotedDrug – Output (1/2)

SecondaryUseNotedDrug – Output (2/2)

NLP in data normalization

A large amount of clinical information is in clinical narratives, NLP is a critical component in data normalization

cTAKES has been wrapped into the data normalization pipeline to normalize data in clinical narratives

End-to-end DN framework

Data Normalization version 2

http://sourceforge.net/p/sharpn/datan/code/HEAD/tree/

DN activities after SHARPn (1) – Clinical Information Model Initiatives

DN activities after SHARPn (2) – Open Health Natural Language Processing

(OHNLP)

Use of the Data Normalization information model as the base to define a Common Type System to capture basic clinical information models

Use of the Data Normalization pipeline to improve interoperability of various clinical information models

DN activities after SHARPn (3) – Clinical decision support and phenotyping

The use of NLP and Big Data for Late Binding Data Normalization

Practical implementation of Late Binding Data Normalization and Drools for real-time clinical decision support