Transcript Pipeline Proof of Concept

Initial Prototype
for Clinical Data
Normalization and High
Throughput Phenotyping
SHARPn F2F
June 30,2011
Purpose
 Demonstrate a proof of concept solution, based on
new tools, technology, models and methods.
 The prototype demonstrates:
– The ability to push unsolicited data using NwHIN exchange
protocols
– Conversion and normalization of HL7 2.x lab messages to XML
clinical element model (CEM) instances
– Conversion and normalization of HL7 2.x medication orders to
CEMs.
– Extraction of medication CEM instances from narrative clinical
documents using NLP processing
– Persistence of CEM instances in a light weight SQL database
– Phenotype processing across the CEM database utilizing the Drools
rules engine
High Level Architecture Diagram
6a
Mayo
EDT System
5
1
IHC
(Backend CDR
Systems)
2
Mirth
Connect
3
4
IHC
NwHIN
Aurion
Gateway
SHARP
NwHIN
Aurion
Gateway
Firewall
7
6
Mirth
Connect
UIMA
Pipeline
8
9
Firewall
10
SHARP Processing Sequence
CEM
Instance
Database
1. Use Data from IHC (De-Identified) HL7 2.x messages
2. Send data into Mirth Connect on the IHC side
3. Create NwHIN Document Submission (XDR) message using HL7 2.x message as payload
4. Send Document Submission (XDR) message from Mirth to IHC NwHIN Aurion Gateway
5. Send XDR message from IHC Aurion Gateway to SHARP NwHIN Aurion Gateway
6. Send XDR message from SHARP NwHIN Aurion to Mirth Connect
6a. Send Mayo HL7 2.x Lab Messages & Clinical Documents to Mirth Connect
7. Process HL7 2.x messages and/or clinical documents in the UIMA Pipelines, to
normalize and transform into Clinical Element Model (CEM) instances
8. Send the resulting XML instance of Clinical Element Model (CEM) to Mirth Connect
9. Persist Clinical Element Model (CEM) instances to MySql database.
10. Perform phenotype processing on the CEM instance database.
Mirth Connect
 Enables information flow and transformation
 Mirth channel receives message from some source,
transforms it, and routes it to one or more
destinations
 Product is open source
 NwHIN with Aurion/CONNECT can be source or
destination of a channel
 Used to store CEM Instances to the database
 Can be used to route data to other locations or
databases
High level flow - Mayo
CDA for Meds
cTAKES
cTAKES
cTAKES
cTAKES
(NLP)
SharpDb
CEM
Mayo EDT
HL7 for labs
Mayo EDT
Tabular
data
Custom
Custom
UIMA
Configurable
UIMA
pipeline
UIMA
pipeline
pipeline
AdminDiagnosis
processor
Mirth
CEM
CEM
Medication to CEM - Mayo data
cTAKES UIMA Annotators (NLP)
CDA
CDAInitializer
Sentence
Annotator
Tokenizer
Annotator
POS
Tagger
Chunker
Context
Dependent
Tokenizer
Dictionary
Lookup
Annotator
LVG
Drug
Mention
Annotator
Patient count – 10000
CDA document count - 360452
CEM count for medication – 3442000
SharpDb
Mirth
Drug
CEM
CAS
Consumer
IHC-Medication,
Mayo, IHC LAB to CEM
New UIMA Process Nodes
HL7
Meds
HL7
Labs
HL7
Initializer
HL7
Initializer
Mayo
LOINC
resource
IHC
RXNORM
resource
Drug
CEM
CAS
Consumer
IHC-GCN
TORXNORM
Annotator
GenericLABAnnotator
SharpDb
LAB
CEM
CAS
Consumer
IHC
LOINC
resource
Mirth
SharpDB a CEM Instance Database
Phenotyping (Drools)
Clinical
Element
Database
Data Access
Layer
Business Logic
Transformation
Layer
Transform physical representation
 Normalized logical representation
(Fact Model)
Inference/
workflow
Engine (Drools)
Service for
Creating Output
(File, Database,
etc)
List of
Diabetic
Patients
Completed Work
 Installation of informatics “SHARP” Cloud system at Mayo
 Installation and configuration of tools on IHC side and
SHARP Cloud
 “Tracer Message” processing
– Used to test communication throughout system
– Successful transfer using NwHIN/Aurion of test message
between IHC & Mayo
 30 de-id IHC patients through pipeline/Drools end-to-end
– 134 Thousand CEMS generated
 Extraction and message generation for 10,000 patients
 Processing of 10,000 patients Meds, Labs, Billing data
– 15 Million CEMS generated
 Conversion to selected CEM models via UIMA framework
 Persisted from CEM to MySQL
Completed Work (Cont.)
 Produced New XML Schemas for CEM Models
– Standard lab panel
– Ambulatory medication order
– Administrative diagnosis
These three models were used
for the prototype experiment.
CEM Search Tool:
http://intermountainhealthcare.org/cem
Excerpt of Lab CEM instance
Completed Work (Cont.)
• Mirth Enhancements
– Implemented NwHIN XDR connector capability
– Implemented UIMA connector capability
– Created NwHIN Aurion XDR adapter
• Channels Created
Sample XDR Channel
Channel that receives HL7 2.x message, places the message as
the payload of an XDR message and sends it to a remote NwHIN
gateway
ReceiveXDRMessage
Receives an XDR message from Mirth and extracts the HL7 2.x
message
CemAdminDxtoDatabase
Receives an XML instance of the administrative diagnosis CEM
and persists it to the database
CemLabToDatabase
Receives an XML instance of a standard lab panel CEM and
persists it to the database
CemMedicationToDatabas
e
Receives an XML instance of a medication CEM and persists it to
the database
Dual Security Certificate Exchange
Intermountain Healthcare
Mirth
Aurion
Gateway
IHC Proxy
Internet
SHARP/Mayo Cloud
SHARP
Proxy
SHARP Aurion
Gateway
Mirth
Thank You!
Calvin Beebe
Christopher Chute
Craig Parker
Cui Tao
Cyndalynn Tilley
David Mead
Dingcheng Li
Donna Ihrke
Gerald Bortis
Guergana Savova
James Masanz
Jeff Ferraro
John Holman
Jon Teichrow
Kevin Bruce
Kyle Marchant
Les Westberg
Margarita Sordo
Mat Bockol
Michael Turk
Mitch Dempsey
Nathan Davis
Pei Chen
Sean Murphy
Sridhar Dwarkanath
Stan Huff
Susan Welch
Tim Peters
Tom Oniki
Vinod Kaggal