Health Records using UMLS Concept Graphs Laura Plaza and Alberto Díaz Universidad Complutense de Madrid When facing complex and untypical cases physicians need ID: 784113
Download The PPT/PDF document "Retrieval of Similar Electronic" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Retrieval
of Similar
Electronic Health Records using UMLS Concept Graphs
Laura Plaza and Alberto DíazUniversidad Complutense de Madrid
Slide2When
facing complex and untypical cases, physicians
need to refer to similar previous casesThe adoption EHR by office-based physicians and hospitals is increasingBut still the time required
to find them can be prohibitive
if no
effective access is provided
Motivation
Given
a
reference
record,
retrieve
others from the clinical database that are similar to the reference one
Retrieval of Similar Electronic Health Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)
2
Slide3A
mix of highly structured information + idiosyncratic
narrative textUnique sublanguage characteristics: Verbless sentences, punctuation, spelling errors.Synonyms and homonymsNeologismsAcronyms and abbreviations
When two HR can be considered as similar?
A
Different
IR
Task
Retrieval
of Similar
Electronic
Health Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)3
Slide4Two
EHR are Similar if…
Same
symptom or sign
(e.g. fever or 5 kg weight loss
)
Same
diagnosis (e.g. bacterial pneumonia)Same test or procedure (e.g. cerebral NMR or
endoscopy biopsy)
Same medicament (e.g. clopidogrel)
But … absent criteria are not relevant for the task!!!
Retrieval of Similar Electronic Health Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)4
Slide5UMLS
consists of three main components: the Specialist Lexicon, the Metathesaurus and the Semantic Network
We use MetaMap to translate free-form text to Metathesaurus conceptsAdvantages:Broad coveragePerforms word sense disambiguation Numerous entries for acronyms and abbreviationsEtc. Using UMLS
for Concept
Annotation
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept Graphs (Plaza and Díaz, 2010)5
Slide6A
four-step graph-based method :Extraction of UMLS
conceptsNegation detectionSemantic graph-based representationRanking similar EHR Our
Proposal
CLINICAL HISTORY:
Eleven
years
old
with
ALL,
bone narrow transplant on Jan.2, now with 3 day history
of cough.IMPRESSION: No focal pneumonia. Likely chronic changes
at
the
left
lung
base.
Mild
anterior
wedging
of
the
thoracic
vertebral
bodies
.
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs
(Plaza and Díaz, 2010)
6
Slide7We
use MetaMap to extract the UMLS concepts
from the Metathesaurus and their semantic types from the Semantic NetworkBut, according to the expert, not all concepts are relevant to the task
Thus, the expert mapped these
criteria to
semantic types and only concepts
from
those types are considered
Our
Proposal
: Extracting UMLS ConceptsRetrieval of Similar Electronic
Health Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)7
Slide8Our
Proposal: Extracting UMLS Concepts
Category
UMLS Semantic Types
Symptoms
and Signs
Sign
or
Symptom
FindingDiseases
Disease or SyndromePathologic Function
Procedures
Therapeutic or Preventive Procedure
Diagnosis Procedure
Body
Parts
Body Location or Region
Body Part, Organ, or Organ Component
Medicaments
Pharmacologic substance
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs
(Plaza and Díaz, 2010)
8
Slide9According
to the expert, absent
or negated criteria (e.g. On admission, the patient had no internal bleeding) are not relevant for the taskThus, negated UMLS concepts are ignored
Negations in medical records usually appears in a reduced
number of forms
, easy to identify using
a simple lexical scanner
from
regular expressions
Our
Proposal:
Negation DetectionRetrieval of Similar Electronic Health
Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)9
Slide10Our
Proposal: Negation Detection
Lexical Pattern
Examples
no|without
| rule out +
concept
+
(
or
concept)*No pneumonia Without fever or coughno|without|rule out + adj + concept
+ (or concept)*No significant hydronephrosisRule out cardiac abnormality
no|without
+
noun
+ of +
concept
+
(or
concept
)*
No signs of tuberculosis
Without evidence of hydroureter
evaluate for + (
noun
|
adj
)?
+
concept
+
(or
concept
)*
Evaluate for foreign body
Evaluate for abnormalities
lack
of|absence
of + (
noun
|
adj
)?
+
concept
+ (or
concept
)*
Lack of
kyphosis
Absence of heart murmur
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs
(Plaza and Díaz, 2010)
10
Slide11First, the concepts are retrieved from the UMLS Metathesaurus along with their complete hierarchy of hypernyms (
is-a relations).Second, all concept hierarchies for each category are merged, building a unique graph for each category in the EHR
Finally, each concept is assigned a weight, using the Jaccard similarity coefficient, attaching greater importance to specific concepts than to general ones Our Proposal: Semantic
Graph Representation
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs (Plaza and Díaz, 2010)11
Slide12Our
Proposal: Semantic Graph Representation
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs (Plaza and Díaz, 2010)
121/52/53/54/55/5
Slide13We
compute the similarity among the
reference EHR and all records in the database, and rank themGiven two graphs, A and B, so that the similarity of A to B has to be measured:First, each concept of A which is not in B assigns a score equal to 0, while each concept of A which is also in B assigns a score equal to its weight in the graph A Next, the sum of the scores for all concepts in A is computed.
Finally, this result is normalized in the interval [0, maximum similarity].
Our
Proposal
:
Ranking Similar
EHR
Retrieval
of Similar Electronic Health Records Using UMLS Concept Graphs (Plaza and Díaz, 2010)
13
Slide14Our
Proposal: Ranking Similar EHR
Retrieval
of Similar
Electronic
Health
Records
Using UMLS Concept Graphs (Plaza and Díaz, 2010)
14
Finding by site
Clinical finding
Disease
Bacterial
pneumonia
Infectious
disease
Disorder by
body site
Pneumonia due
to
Streptococcus
Mycoplasma
pneumonia
Respiratory
finding
Functional finding
of respiratory tract
Coughing
Clinical finding
Disorder by
body site
Finding by site
1/11
2/11
3/11
8/11
9/11
10/11
3/5
4/5
5/5
Bacterial
pneumonia
Pneumococcal
pneumonia
11/11
Pneumonia due to
anaerobic
bacteria
Pneumonia due
to
pleuropneumonia
Graph A
Graph B
...
...
Virus Diseases
Slide15Test
collection: 50 radiology reports from
the CMC-NLP 2007 Challenge corpusQuery collection: a subset of 20 reports from the test collectionTwo hospital physicians were asked to select, for each report in the query collection, the most similar reports within the test collectionThere is a substantial agreement between judges (Kappa test, k=0.7980)Precision and Recall of our method are compared with those obtained by a term-based approach Experiments
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs
(Plaza and Díaz, 2010)15
Slide16Results
Retrieval of Similar Electronic
Health Records Using
UMLS Concept
Graphs (Plaza and Díaz, 2010)
16
Graph-based method
Term-based Method
Precision
Recall
F-score
Precision
RecallF-scoreUnion-5 0.530
0.765
0.626
0.470
0.708
0.564
Intersection-5
0.420
0.884
0.569
0.340
0.729
0.463
Union-3
0.717
0.676
0.696
0.467
0.476
0.471
Intersection-3
0.600
0.788
0.681
0.333
0.487
0.395
Graph-based method
Term-based
Method
Precision
F-score
Precision
F-score
Union
0.707
0.692
0.594
0.632
Intersection
0.745
0.742
0.503
0.598
Slide17The method achieves relatively high precision and recall which are also well balanced
UMLS occasionally fails to recover relevant concepts especially when expressed in their shortened forms
Another impairment to concept identification comes from the spelling errors in the clinical recordsFuture work will test the method on a different evaluation collection which will present longer medical records structured in different sections Conclusion and Future Work
Retrieval
of Similar
Electronic
Health
Records
Using
UMLS Concept
Graphs
(Plaza and Díaz, 2010)17