Terminology Tools: State of the Art and Practical Lessons James J. Cimino Department of Medical...

37
Terminology Tools: State of the Art and Practical Lessons James J. Cimino Department of Medical Informatics Columbia University New York, New York, USA
  • date post

    21-Dec-2015
  • Category

    Documents

  • view

    218
  • download

    0

Transcript of Terminology Tools: State of the Art and Practical Lessons James J. Cimino Department of Medical...

Terminology Tools: State of the Art and Practical Lessons

James J. Cimino

Department of Medical Informatics

Columbia University

New York, New York, USA

Overview

• Knowledge-based terminologies– what are they?– tools needed for management and use

• Literature review of terminology tools

• Experience at Columbia

Knowledge-Based Terminologies

• Concept-based

• Terms

• Synonyms

• Multiple hierarchies

• Semantic relationships

• Inheritance

Knowledge-Based Tools

• Browsers - a prerequisite• Editors

– Collect requisite knowledge– Require referential integrity– Automated classification– Propagate inherited information– Manage change

• Servers– Term look-up– Answer questions about terms– Class-based queries

Literature Review• Browsers

– MicroMeSH: Lowe et al., SCAMC 1989– UMLS: Tuttle et al., SCAMC 1991 and 1992

• Editors– CMT: Mays et al., SCAMC 1996– CMT: Campbell et al., SCAMC 1996, Methods 1998

• Servers– Meta-1: Sherertz et al., SCAMC 1989– VOSER: Rocha et al., CBR, 1994– Galen: Rector et al., Methods 1995– MED: Forman et al., SCAMC 1995– InterMED: Gennari et al., SCAMC 1995– UMLS: Many others

Terminology Requirements

• OMG RFP for terminology services

• 3M Health System Responded

• Chute et al. (SCAMC 1999) simplified

Experience with Terminology Tools

• Medical Entities Dictionary• MED Editor/Server Architecture• KEE MED Editor• MUMPS MED Editor• Unix shared memory server• Qrymed• Accessmed• Web MED browser• Mainframe environment• Web MED Editor

Experience with Terminology Tools

• Medical Entities Dictionary

CPMC Medical Entities Dictionary

• Concept-based (60,000)

• Multiple hierarchy (85,000)

• Synonyms (149,000)

• Translations (103,000)

• Semantic links (114,000)

• Attributes (136,000)

MED StructureMedicalEntity

PlasmaGlucose

LaboratorySpecimen

PlasmaSpecimen

AnatomicSubstance

Plasma Substance

Sampled

Part of

Has S

pecimen

Substance Measured

LaboratoryProcedure

CHEM-7

LaboratoryTest

Event

DiagnosticProcedure

Substance

BioactiveSubstance

Glucose

Chemical

Carbo-hydrate

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture

MED Editor/Server ArchitectureMED

MUMPS Globals

Datatree

MUMPS

MED Editor Functions

MED Editor Update Programs

medlog

medlog

MED Server

Query Functions

Command Line

Interface

MED Browser

Translation Tables

Unix

IBMUnix

UnixUnix

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server

Unix Shared Memory Server

ShMMED

MS AccesMED db

MedLEENLP

MEDlib

MLMcompiler

Dxplainbutton

Medlinebutton

MLMcomposition

tool

Integratedresults

design tool

Web MEDbrowser

accessMED

rpc MEDlib

qrymed

MEDbrowser

MEDviewer

Lab uploadextract

Radiologybuploadextract

Bloodbanupload

Integratedresultsreview

ICU resultsdisplay

dop

Data engine

pse

WebCIS

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed

Qrymed Functions-allslts: lists all the slots, with their names.-scd: returns the slotcode with string x as its name.-snm: returns the name of slotcode x.-srecip: returns the reciprocal of slotcode x.-stype: returns the type for slotcode x.-cd: returns the medcode with string x as its name (exact match).-find: lists medcodes that have string x in their names (pattern match).-nm: returns the name for medcode x.-pnm: returns the print name for medcode x.-par: lists the parents of medcode x.-child: lists the children of medcode x.-anc: lists the ancestors of medcode x.-desc: lists the descendants of medcode x.-ianc: lists the ancestors of medcode x (including x).-idesc: lists the descendants of medcode x (including x).-slts: lists the slots of medcode x.-sltsval: lists the slots, with their values, for medcode x.-isval: lists the medcodes which have value y in slotcode x.-val: returns the value(s) of slotcode x for medcode y.

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed• Accessmed

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed• Accessmed• Web MED browser

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed• Accessmed• Web MED browser• Mainframe environment

MED in DB2 on Mainframe

1234

Entities

10 Name 20 UMLS 30 Part-of

40 Specimen

Slots

1 102 102 202 30

Entity-Slots

1 10 Entity2 10 C00012 40 12342 50 mg/dl

Entity/Slot/Values1 11 21 32 3

Ancestry

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed• Accessmed• Web MED browser• Mainframe environment• Web MED Editor

Experience with Terminology Tools

• Medical Entities Dictionary• KEE MED Editor• MUMPS MED Editor• MED Editor/Server Architecture• Unix shared memory server• Qrymed• Accessmed• Web MED browser• Mainframe environment• Web MED Editor

Terminology Requirements for Controlled Data Entry (Chute, 1999)

• Word normalization• Word completion• Target terminology specification• Spelling correction• Lexical matching• Term completion• Semantic locality• Term composition • Term decomposition

Other Queries For Data Entry• Keyword synonyms• Class-based queries

– “Get me all the terms in class X”– “Is this term in class X?”– Class X may or may not include term X

• Class-restricted queries– “Get term from class X matching string Y”– Useful for data entry

• Semantic queries

Next Steps

• Further Web editor development

• Change management

• Multieditor environment

• Server-enable applications

Conclusions

• Knowledge-based terminologies are here to stay

• Sophisticated tools are needed

• Terminology-enabled applications need servers

• Server specifications can be simplified for specific purposes

• Class-based, class-restricted, and semantic queries are useful