i2b2/NCBO Ontology Tools

Lori Phillips, MS

AUG meeting

July 24-25, 2012

Ontology migration example

A hospital has migrated from ICD-9 to ICD-10

Observation fact data is now a mix of legacy ICD-9 data and new ICD-10 data.

How can the i2b2 ontology adapt to handle this situation? ICD-10 ontology needs to be created in an i2b2 format Legacy ICD-9 terms need to be integrated into ICD-10 hierarchy

When two or more coding systems are mixed together, one will assume the master position of establishing the hierarchy, and the others are mapped into it at various levels.

Single integrated ontology can query for both ICD-9 and ICD-10 terms

Integrating ICD-9 terms into ICD-10 hierarchy

Why are hierarchies so important for i2b2?

Hierarchies form the basis of both the visualization of the terms and the query mechanism itself.

select * from metadata where c_fullname like ‘\Diagnoses\Respiratory system\Chronic obstructive

diseases\Emphysema\%’ and c_hlevel = 5

Hierarchies in queries

select patient_num from observation_fact where concept_cd IN (select concept_cd from concept_dimension where concept_path LIKE '\

Diagnoses\Respiratory system (460-519)\Chronic obstructive diseases (490-496)\(492) Emphysema\%')

NCBO BioPortal ICD-10

Building an ICD-10 Ontology with NCBO services

Pull data from NCBO via REST services. Reorganize information into i2b2 Metadata format

METADATA COLUMNDATA TYPE(ORACLE)

DATA TYPE(SQL)

C_HLEVEL INT INT

C_FULLNAME VARCHAR2(700) VARCHAR(700)

C_NAME VARCHAR2(2000) VARCHAR(2000)

C_SYNONYM_CD CHAR(1) CHAR(1)

C_VISUALATTRIBUTES CHAR(3) CHAR(3)

C_BASECODE VARCHAR2(50) VARCHAR(50)

C_METADATAXML CLOB TEXT

C_FACTTABLECOLUMN VARCHAR2(50) VARCHAR(50)

C_TABLENAME VARCHAR2(50) VARCHAR(50)

C_COLUMNNAME VARCHAR2(50) VARCHAR(50)

C_COLUMNDATATYPE VARCHAR2(50) VARCHAR(50)

C_OPERATOR VARCHAR2(10) VARCHAR(10)

C_DIMCODE VARCHAR2(700) VARCHAR(700)

C_TOOLTIP VARCHAR2(900) VARCHAR(900)

UPDATE_DATE DATE DATETIME

DOWNLOAD_DATE DATE DATETIME

IMPORT_DATE DATE DATETIME

SOURCESYSTEM_CD VARCHAR2(50) VARCHAR(50)

VALUETYPE_CD VARCHAR2(50) VARCHAR(50)

bioportal/concepts/46302/all<data> <pageNum>1</pageNum> <numPages>1832</numPages> <pageSize>50</pageSize> <numResultsPage>50</numResultsPage> <numResultsTotal>91590</numResultsTotal> <contents class="org.ncbo.stanford.bean.concept. ClassBeanResultListBean"> <classBeanResultList> <classBean> <id>0-ICD10CM</id> <fullId>http://purl.bioontology.org/

ontology/ICD10CM/0-ICD10CM</fullId> <label>ICD-10-CM TABULAR LIST of

DISEASES and INJURIES</label> <type>class</type> <relations> <entry> <string>ChildCount</string> <int>0</int> </entry> ……

NCBO Extraction workflow

NCBORESTXML

NCBORESTXML

Request to extract ontology

i2b2Metadata

ExtractionWorkflow

ICD-10

ExtractedData

Process

Extracted ICD-10 terms

What about my legacy ICD-9 data?

Ideally we would like an i2b2 ontology that integrates ICD-9 into ICD-10.

Mapping Tool

Tool to verify/(re)assign ontology mappings.

Navigating the Mapping Tool Tree

Displays terms mapped from one ontology within hierarchy of another

Mapped terms are displayed adjacent to terms they are mapped to and appear in bold

Adding a new mapping

ICD9:269.3, Mineral deficiency should appear for ICD10:E63 Other nutritional deficiencies

Copy term ICD9:269.3

Adding a new mapping

Paste onto ICD10:E63 Other nutritional deficiencies

Move or Unmap a mapping

ICD9:416.8 Other chronic pulmonary heart diseases appears in two places: the one attached to ICD10:I27.2 appears incorrect and can be unmapped.

Or it may be moved (drag and drop) up one level to ICD10:I27

The Unmapped Terms List

Free form list of terms to be mapped

Locate term you wish to map to in the hierarchy tree. Drag from table to term in the tree.

If you make a mistake you can either reassign the mapped term within the tree or unmap it from tree.

Unmap will cause it to reappear in the unmapped terms list if the term has no other mappings.

Finding the term to map to

Finding the term …

Finding the term …

Assigning an unmapped term

Drag from unmapped terms list

Drop onto term we are mapping to

Unmapping a term

Drag term from tree

Drop onto unmapped terms list

Search Unmapped Terms By Name

Search Unmapped Terms by Code

Mapped Terms Viewer

Search Mapped Terms By Code

Search Mapped Terms By Name

Merging Ontologies

Mapping tool provides a visualization of what the merged ontologies would look like

What if we could extract a single integrated metadata table from this?

Integration tool

Request to integrate

IntegrationWorkflow

ICD9 into ICD-10

ICD-10 merged with ICD9 terms

MapperCell

For each mapped ICD-9 term, compute ICD-10

hierarchy

Mapped ICD-9 terms

Integration of ICD-9 into ICD-10

i2b2 wiki: Community projects

Acknowlegements

NCBO/bioportal Nigam Shah, Stanford University Ray Fergerson, Stanford University Paul Alexander, Stanford University

i2b2 Janice Donahoe, Partners Alyssa Porter, Partners Nich Wattanasin, Partners