g a l e n slide no.: 1 g a l e n where we started building classifications with galen a look into...
TRANSCRIPT
Slide No.: 1 G A L E N
G A L E NG A L E NWhere we started
Building Classifications with GALEN
A look into the future…?
Key Questions
Slide No.: 2 G A L E N
GALEN-IN-USE PartnersGALEN-IN-USE Partners
University of Manchester, VAMP Health, UK
University of Nijmegen, Holland
EFCC and its affiliates: WCC, NOMESCO, CNR Rome, U St EtienneWCC, NOMESCO, CNR Rome, U St Etienne IASIST, IDGmbH, CMITD, STAKE, U LouvainIASIST, IDGmbH, CMITD, STAKE, U Louvain
University Hospital of Geneva, LNAT, Switzerland
OLE, RAMIT, Datasoft, Belgium
GSF Medis, U Hildesheim, Germany
CNR, Rome, Italy
SPRI, U Linköping, Sweden
VTT, Oulu Univ Hospital, Medici Data, Finland
Slide No.: 3 G A L E N
G A L E NG A L E NWhere we started
Slide No.: 4 G A L E N
Best Practice
Clinical Terminology
Data Entry
Clinical Record
Decision Support
Best Practice
GALEN Clinical
Terminology
Data Entry
Clinical Record
Decision Support
Slide No.: 5 G A L E N
enter search:
Choose terms from a coding Choose terms from a coding schemescheme
cystitis
Acute cystitis
Subacute cystitis, NOS
Follicular cystitis
Cystitis, NOS
Idiopathic cystitis
Chemical cystitis
Postoperative cystitis
Drug induced cystitis
Iatrogenic cystitis
Radiation cystitis
Chronic cholecystitis
Acute cholecystitis
Bacterial Cholecystitis
Cholecystitis, NOS
Bacterial cystitis
next pageetc
...picking liststoo long
Too Big
Too Small...not enoughclinical detail
Slide No.: 6 G A L E N
cystitis
chronic
severitysevere
onset
chronicity
mild
A new clinician-friendly option: A new clinician-friendly option: structured data entrystructured data entry
gradual
sub-acute
Assemble a phrase...
…from a set of useful pieces...
…displayed on the screen.
“moderately severe, acute cystitis of sudden onset”
acute
sudden
moderate
Slide No.: 7 G A L E N
Only one problem:Only one problem:
How can the computer know in advance what are the sensible pieces to display?
Traditional coding schemes do not have the information required
ICDRea
d
OPCSSNOMED
?cystitis
Slide No.: 8 G A L E N
What is cystitis combined with ‘acute and mild?
how would you likethe answer ?
A new resourceA new resource
... a resource that can cope with arbitrarily complex clinical concepts ...
Slide No.: 9 G A L E N
as an English phrase and as an ICD Code
<“mild, acute cystitis”, D595.0 >
... and cope with different natural languages and coding schemes.
A new resourceA new resource
Slide No.: 10 G A L E N
Computer knows ‘rules’ for:Computer knows ‘rules’ for:
how do you classify things? Fractures of femur, and of femoral neckFractures of femur, and of femoral neck
when are two things the same ? ‘‘Inflammation of Liver’ vs ‘Hepatitis’Inflammation of Liver’ vs ‘Hepatitis’
are there any illegal combinations? ‘‘fractured eyebrow causing donkey’fractured eyebrow causing donkey’
are any combinations redundant? ‘‘finger which is part of hand’finger which is part of hand’
Slide No.: 11 G A L E N
G A L E NG A L E NBuilding Classifications with GALEN
Slide No.: 12 G A L E N
Manual ClassificationsManual Classifications
Most medical ‘classifications’ are really ‘thesauri’ Thesauri have mixed hierarchiesThesauri have mixed hierarchies
– kind, part, cause, modified,...kind, part, cause, modified,...
heartheart
heart valveheart valveaortic valveaortic valve
cusp of aortic valvecusp of aortic valve
For interpretation by people OnlyOnly people can reorganise (and that isn’t easy or quick) people can reorganise (and that isn’t easy or quick)
Must read rubricsMust read rubrics Model of use implicit and fixedModel of use implicit and fixed
Slide No.: 13 G A L E N
‘‘Computed’ ClassificationsComputed’ Classifications
Strict hierarchies using ‘kind of’‘‘Disorder of heart’Disorder of heart’
‘‘Disorder of valve in heart’Disorder of valve in heart’‘‘Disorder of valve in left ventricle in heart’Disorder of valve in left ventricle in heart’
‘‘Disorder of cusp in valve in left ventricle in heart’Disorder of cusp in valve in left ventricle in heart’
Computable People can understand (but don’t have to)People can understand (but don’t have to) Computers can reorganiseComputers can reorganise
– because all meaning is explicit in formal expressionbecause all meaning is explicit in formal expression
G A L E N
Bridges from patient data to Bridges from patient data to classificationsclassifications
Coding &Classification
ICD-9 ICD-10
MeSH
ACRNEMA
ICPC
SNOMED Axes
UMLS
Clinical Applications
Medical Records
Data entry
Decision support
READ
OPCS
MEGA-TERM
G A L E N
Slide No.: 15 G A L E N
Added value of Computed Added value of Computed ClassificationsClassifications
Hide the complexity Let the computer do the workLet the computer do the work Small on the outside, huge on the insideSmall on the outside, huge on the inside
Reorganise classifications when needed
More complete, consistent and automatic indexing
Automatic cross mapping/merging
Quicker to update - worry about what, not where
‘Coherence without Uniformity’
G A L E N
Issues to considerIssues to consider
Can not prove result is complete or correct(but can’t do that with manual result either)
Initially expensive to build
Slide No.: 17 G A L E N
G A L E NG A L E N
A look into the future…?
Slide No.: 18 G A L E N
What will the classifications of What will the classifications of today look like in the future?today look like in the future?
They won’t exist
Each will be replaced by several different views on something else, each serving individually
the specific (conflicting) functions which were formerly tortured out of the one
classification
NOT a book
NOT a picking list
Slide No.: 19 G A L E N
What will these ‘views’ be What will these ‘views’ be like ?like ?
Each view is like a classification, but...
Multiaxial (very)
One, single clear purpose
Humans say what terms are included and what they mean
Computers decide how to arrange them
Not fixed in stone - malleable, customisable, localisable - but always coherent
Slide No.: 20 G A L E N
‘‘Views’ of what ?Views’ of what ?
‘Clinical Terminology’
Something clinicians use to record information about real, individual patients
Somebody else’s problem
..as long as the bridge to classification views exists
Slide No.: 21 G A L E N
G A L E NG A L E NKey Questions
Slide No.: 22 G A L E N
Key Questions Key Questions (for users of terminology systems)(for users of terminology systems) What do you want it to do?
Clinical systems are the endClinical systems are the end terminology the meansterminology the means
– Don’t get the cart before the horseDon’t get the cart before the horse
Can it do it? Can anything do it?Can anything do it? A universal coding scheme for everything is implausibleA universal coding scheme for everything is implausible Coherence without UniformityCoherence without Uniformity
Slide No.: 23 G A L E N
Key QuestionsKey Questions(for builders of terminology (for builders of terminology
systems)systems) Can it be built? implemented? maintained?
Quickly enough?Quickly enough? Are there short-term milestones and a migration pathway?Are there short-term milestones and a migration pathway?
Will it scale? Organisationally? Technically?Organisationally? Technically?
Can applications use it? Can we maintain them? Can vendors sell themCan we maintain them? Can vendors sell them
Slide No.: 24 G A L E N
WarningsWarnings
Be cautious of hype It’s not as easy as it looksIt’s not as easy as it looks Beware scalingBeware scaling It’s not how big it is that counts - it’s what you can do with itIt’s not how big it is that counts - it’s what you can do with it
Don’t reinvent the wheel
Simple to understand doesn’t mean simple to use
Coding systems are now software
Slide No.: 25 G A L E N
GALEN-IN-USEGALEN-IN-USEAdvanced terminological services to support
integrated clinical information systems
[email protected]://www.cs.man.ac.uk/mig/galen/