SlideShare a Scribd company logo
1 
Questionable Relationship 
Triples in the UMLS 
Huanying Gu, Gai Elhanan, Michael Halper, Zhe He 
Structural Analysis of Biomedical Ontologies Center (SABOC), 
New Jersey Institute of Technology, Newark, NJ
2 
Outline 
„ Background 
{ Biomedical terminologies and the UMLS 
{ Relationships in the UMLS 
„ Identify suspicious relationship triples 
„ Results 
„ Discussion
3 
Biomedical Terminologies 
„ What is biomedical terminology? 
{ A collection of concepts with attributes and 
relationships 
{ Used to encode drugs, diseases, diagnoses, 
findings, etc. 
„ The importance of biomedical terminologies 
{ Clinical practice, e.g. ICD10 use in diagnosis coding 
and billing 
{ Biomedical research 
{ Healthcare applications: EHR and EMR
4 
The Unified Medical Language System 
„ A system that integrates more than 150 
terminologies to enable interoperability between 
computerized systems in healthcare industry 
„ Designed and developed by United States 
National Library of Medicine
5 
Structure of the UMLS 
„ Two-level structure of the UMLS 
{ Metathesaurus (META): 
„ More than 2 million concepts 
„ Terms from sources are grouped into concepts 
„ More than 50 million relationships 
{ Semantic Network 
„ 133 semantic types 
„ Each concept in META is assigned to at least one 
semantic type
6 
Relationship in the META 
„ UMLS META relationship: 
{ Derived from the source 
{ Introduced during the integration 
„ 11 different relationship types (RELs): 
{ Hierarchical relationships 
„ Parent (PAR) and child (CHD) 
„ Broader (RB) and narrower (RN) 
{ Lateral (non-hierarchical) relationships 
„ e.g. SY (synonym)
7 
Problems of Relationship Triples 
„ Relationship in META is the foundation of concept 
definitions 
„ Problems of relationship triples: 
{ There exist multiple relationships between the 
same pair of concepts, they may be 
„ from the same source 
„ from different sources 
{ Multiple RELs between a pair of concepts may 
indicate problems
8 
Suspicious Relationship Triples 
„ Relationship triple 
{ Source concept – A 
{ Target concept – B 
{ Relationship – r 
{ (r, A, B) 
B 
r1 r2 
A
9 
Identify Suspicious Relationship Triples 
„ Our algorithm automatically identifies all 
suspicious relationship triples. 
„ They are in the following 4 cases 
{ Conflicting hierarchical RELs 
{ Redundant hierarchical RELs 
{ Mixed hierarchical/lateral RELs 
{ Multiple mutually exclusive lateral RELs
10 
Case 1: Conflicting Hierarchical RELs 
„ Two or more hierarchical RELs existing 
between two different concepts forming a 
hierarchical cycle where one or more RELs are 
incorrect. 
„ PAR and CHD 
„ PAR and RN 
„ RB and CHD 
„ RB and RN 
B 
A 
PAR 
(RB) 
CHD 
(RN)
11 
Example of Case 1 
Dermatologic 
disorder 
PAR 
UMLS_CODE 
C0037274 
Inverse_isa 
Dermatitis UMLS_CODE 
C0011603 
Dermatologic 
disorder 
UMLS_CODE 
C0037274 
Dermatitis UMLS_CODE 
C0011603 
conflicting hierarchical relationships 
CHD 
isa 
CHD 
isa
12 
Case 2: Redundant Hierarchical RELs 
„ A concept is PAR (CHD) and RB (RN) of 
another given concept at the same time 
{PAR and RB 
{CHD and RN 
B 
A 
CHD 
(RB) 
RN 
(PAR)
Case 3: Mixed Hierarchical/lateral RELs 
13 
„ Two different concepts A and B with one 
hierarchical relationship and one lateral 
relationship which are mutually exclusive and 
cannot occur in the same pair of concepts at the 
same time. 
B 
A 
PAR 
(CHD, RB, 
RN) 
Lateral 
REL
14 
Examples of Case 2 & 3 
Right suprascapular vein 
Structure of 
suprascapular vein 
Right external 
jugular vein 
PAR 
inverse_isa 
RB (Broader) 
inverse_isa 
PAR 
has_tributray 
RO (other semantic relation) 
has_tributary 
RB and PAR: redundant 
hierarchical relationships 
PAR and RO: 
mutually exclusive relationships
15 
Case 4: Multiple Lateral RELs 
„ Two different concepts A and B with two lateral 
relationships which are mutually exclusive. 
Mutual exclusivity can only be asserted by the 
relationship attributes qualifying both RELs 
B 
A 
Lateral 
REL 
Lateral 
REL
16 
Example for Case 4 
SLE glomerulonephritis 
syndrome, WHO class V 
Lupus Erythematosus, 
Systemic 
RO 
associated_with 
RL 
mapped_from 
SLE glomerulonephritis 
syndrome, WHO class V 
RO 
associated_with 
Lupus Erythematosus, 
Systemic 
UMLS_CODE 
C0268758 
UMLS_CODE 
C0024141
17 
2/21/2012 
Statistics 
„ Our methodology was applied to the UMLS 
2010AA release.
18 
Discussion 
„ Certain of REL triples can be attributed to the 
process of the source vocabulary integration. 
„ Questionable relationship triples may be an 
indicator of term ambiguity. 
„ Algorithmic approaches that can easily detect and 
classify such errors are important.
„ This work was partially supported by the National 
Library of Medicine, NIH R01 grant 
REFERENCES 
[1] O. Bodenreider, "The Unified Medical Language System (UMLS): integrating biomedical 
terminology." Nucleic Acids Res. 2004 Jan 1;32(Database issue):D267-70 
[2] O. Bodenreider, "Circular hierarchical relationships in the UMLS: Etiology, diagnosis, 
treatment, complications and prevention." AMIA Annu Symp Proc; 2001:57–61. 
[3] UMLS Reference Manual: www.nlm.nih.gov/research/umls/meta2.html. 
[4] H. Gu, Y. Perl, G. Elhanan, H. Min, L.Zhang, and Y. Peng, "Auditing concept categorizations 
in the UMLS." Artif Intell Med. 2004 May;31(1):29–44. 
[5] Y. Chen, H. Gu, Y. Perl, and J. Geller, "Structural group-based auditing of missing 
hierarchical relationships in UMLS." J Biomed Inform. 2009 Jun;42(3):452–67. 
[6] O. Bodenreider, S.J. Nelson, W.T. Hole, and H.F. Chang, "Beyond synonymy: exploiting the 
UMLS semantics in mapping vocabularies." Proc AMIA Symp. 1998:815–9. 
[7] F. Mougin and O. Bodenreider, "Approaches to eliminating cycles in the UMLS 
Metathesaurus: Naïve vs. formal." AMIA Annu Symp Proc; 2005:550–4. 
[8] M. Halper, C.P. Morrey, Y. Chen, G. Elhanan, G. Hripcsak, and Y. Perl, "Auditing 
Hierarchical Cycles to Locate Other Inconsistencies in the UMLS." AMIA Annu Symp 
Proc; 2011:529–33. 
19 
Acknowledgement and References
Thank you

More Related Content

Viewers also liked

Format & Design
Format & DesignFormat & Design
Format & Design
drtaichi
 
An Introduction to TACI
An Introduction to TACIAn Introduction to TACI
An Introduction to TACIMehdi Alamdar
 
Creating Flow States
Creating Flow StatesCreating Flow States
Creating Flow Statesdrtaichi
 
Penurunan mata uang IPS SMP
Penurunan mata uang IPS SMPPenurunan mata uang IPS SMP
Penurunan mata uang IPS SMP
lestaridiana28
 
Observing and Assessing Flow
Observing and Assessing FlowObserving and Assessing Flow
Observing and Assessing Flow
drtaichi
 

Viewers also liked (6)

Format & Design
Format & DesignFormat & Design
Format & Design
 
An Introduction to TACI
An Introduction to TACIAn Introduction to TACI
An Introduction to TACI
 
Creating Flow States
Creating Flow StatesCreating Flow States
Creating Flow States
 
Cv
CvCv
Cv
 
Penurunan mata uang IPS SMP
Penurunan mata uang IPS SMPPenurunan mata uang IPS SMP
Penurunan mata uang IPS SMP
 
Observing and Assessing Flow
Observing and Assessing FlowObserving and Assessing Flow
Observing and Assessing Flow
 

Similar to ZHE-BHI2012

Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
The Petrie-Flom Center for Health Law Policy, Biotechnology, and Bioethics
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
 
Gutell 119.plos_one_2017_7_e39383
Gutell 119.plos_one_2017_7_e39383Gutell 119.plos_one_2017_7_e39383
Gutell 119.plos_one_2017_7_e39383
Robin Gutell
 
Controlled vocabularies for medical and health research
Controlled vocabularies for medical and health researchControlled vocabularies for medical and health research
Controlled vocabularies for medical and health research
ARDC
 
Feb20 mayo-webinar-21feb2012
Feb20 mayo-webinar-21feb2012Feb20 mayo-webinar-21feb2012
Feb20 mayo-webinar-21feb2012
University of Minnesota, Duluth
 
Understanding medical concepts and codes through NLP methods
Understanding medical concepts and codes through NLP methodsUnderstanding medical concepts and codes through NLP methods
Understanding medical concepts and codes through NLP methods
Ashis Chanda
 
Ontology and the National Cancer Institute Thesaurus (2005)
Ontology and the National Cancer Institute Thesaurus (2005)Ontology and the National Cancer Institute Thesaurus (2005)
Ontology and the National Cancer Institute Thesaurus (2005)
Barry Smith
 
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
ijdms
 
O01821100103
O01821100103O01821100103
O01821100103
IOSR Journals
 
A review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word EmbeddingA review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word Embedding
Reza Sadeghi
 
Semantic Similarity Measures between Terms in the Biomedical Domain within f...
 Semantic Similarity Measures between Terms in the Biomedical Domain within f... Semantic Similarity Measures between Terms in the Biomedical Domain within f...
Semantic Similarity Measures between Terms in the Biomedical Domain within f...
Editor IJCATR
 
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
Allison McCoy
 
Debunk bullshit in statistics QN
Debunk bullshit in statistics QNDebunk bullshit in statistics QN
Debunk bullshit in statistics QN
Quan Nguyen
 
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge GraphsCombining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Paul Groth
 
www.ijerd.com
www.ijerd.comwww.ijerd.com
www.ijerd.com
IJERD Editor
 
Analyzing Compare and Contrast Essays: DNA Profiling
Analyzing Compare and Contrast Essays: DNA ProfilingAnalyzing Compare and Contrast Essays: DNA Profiling
Analyzing Compare and Contrast Essays: DNA Profiling
sarahelizabethfield
 
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...Chimezie Ogbuji
 
Zhe_2014JointSummits_v6
Zhe_2014JointSummits_v6Zhe_2014JointSummits_v6
Zhe_2014JointSummits_v6Zhe (Henry) He
 
The Monarch Initiative: From Model Organism to Precision Medicine
The Monarch Initiative: From Model Organism to Precision MedicineThe Monarch Initiative: From Model Organism to Precision Medicine
The Monarch Initiative: From Model Organism to Precision Medicine
mhaendel
 
Information extraction from EHR
Information extraction from EHRInformation extraction from EHR
Information extraction from EHR
Ashis Chanda
 

Similar to ZHE-BHI2012 (20)

Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
Isaac Kohane, "A Data Perspective on Autonomy, Human Rights, and the End of N...
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Gutell 119.plos_one_2017_7_e39383
Gutell 119.plos_one_2017_7_e39383Gutell 119.plos_one_2017_7_e39383
Gutell 119.plos_one_2017_7_e39383
 
Controlled vocabularies for medical and health research
Controlled vocabularies for medical and health researchControlled vocabularies for medical and health research
Controlled vocabularies for medical and health research
 
Feb20 mayo-webinar-21feb2012
Feb20 mayo-webinar-21feb2012Feb20 mayo-webinar-21feb2012
Feb20 mayo-webinar-21feb2012
 
Understanding medical concepts and codes through NLP methods
Understanding medical concepts and codes through NLP methodsUnderstanding medical concepts and codes through NLP methods
Understanding medical concepts and codes through NLP methods
 
Ontology and the National Cancer Institute Thesaurus (2005)
Ontology and the National Cancer Institute Thesaurus (2005)Ontology and the National Cancer Institute Thesaurus (2005)
Ontology and the National Cancer Institute Thesaurus (2005)
 
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
DESIGN METHODOLOGY FOR RELATIONAL DATABASES: ISSUES RELATED TO TERNARY RELATI...
 
O01821100103
O01821100103O01821100103
O01821100103
 
A review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word EmbeddingA review on Analyzing Multiple Medical Corpora Using Word Embedding
A review on Analyzing Multiple Medical Corpora Using Word Embedding
 
Semantic Similarity Measures between Terms in the Biomedical Domain within f...
 Semantic Similarity Measures between Terms in the Biomedical Domain within f... Semantic Similarity Measures between Terms in the Biomedical Domain within f...
Semantic Similarity Measures between Terms in the Biomedical Domain within f...
 
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
Comparative Analysis of Association Rule Mining, Crowdsourcing, and NDF-RT Kn...
 
Debunk bullshit in statistics QN
Debunk bullshit in statistics QNDebunk bullshit in statistics QN
Debunk bullshit in statistics QN
 
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge GraphsCombining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
Combining Explicit and Latent Web Semantics for Maintaining Knowledge Graphs
 
www.ijerd.com
www.ijerd.comwww.ijerd.com
www.ijerd.com
 
Analyzing Compare and Contrast Essays: DNA Profiling
Analyzing Compare and Contrast Essays: DNA ProfilingAnalyzing Compare and Contrast Essays: DNA Profiling
Analyzing Compare and Contrast Essays: DNA Profiling
 
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...
Integrating Large, Disparate, Biomedical Ontologies to Boost Organ Developmen...
 
Zhe_2014JointSummits_v6
Zhe_2014JointSummits_v6Zhe_2014JointSummits_v6
Zhe_2014JointSummits_v6
 
The Monarch Initiative: From Model Organism to Precision Medicine
The Monarch Initiative: From Model Organism to Precision MedicineThe Monarch Initiative: From Model Organism to Precision Medicine
The Monarch Initiative: From Model Organism to Precision Medicine
 
Information extraction from EHR
Information extraction from EHRInformation extraction from EHR
Information extraction from EHR
 

More from Zhe (Henry) He

AMIA2013-ZH-Family-v15
AMIA2013-ZH-Family-v15AMIA2013-ZH-Family-v15
AMIA2013-ZH-Family-v15Zhe (Henry) He
 

More from Zhe (Henry) He (7)

zhe_CRI2015_drug_v2
zhe_CRI2015_drug_v2zhe_CRI2015_drug_v2
zhe_CRI2015_drug_v2
 
zhe_CRI2015_NHANES
zhe_CRI2015_NHANESzhe_CRI2015_NHANES
zhe_CRI2015_NHANES
 
VDOS2013-Zhe-Slides
VDOS2013-Zhe-SlidesVDOS2013-Zhe-Slides
VDOS2013-Zhe-Slides
 
zhe_amia14_v7
zhe_amia14_v7zhe_amia14_v7
zhe_amia14_v7
 
MIXHS12-Zhe
MIXHS12-ZheMIXHS12-Zhe
MIXHS12-Zhe
 
AMIA2013-ZH-Family-v15
AMIA2013-ZH-Family-v15AMIA2013-ZH-Family-v15
AMIA2013-ZH-Family-v15
 
zhe_amia14_v7
zhe_amia14_v7zhe_amia14_v7
zhe_amia14_v7
 

ZHE-BHI2012

  • 1. 1 Questionable Relationship Triples in the UMLS Huanying Gu, Gai Elhanan, Michael Halper, Zhe He Structural Analysis of Biomedical Ontologies Center (SABOC), New Jersey Institute of Technology, Newark, NJ
  • 2. 2 Outline „ Background { Biomedical terminologies and the UMLS { Relationships in the UMLS „ Identify suspicious relationship triples „ Results „ Discussion
  • 3. 3 Biomedical Terminologies „ What is biomedical terminology? { A collection of concepts with attributes and relationships { Used to encode drugs, diseases, diagnoses, findings, etc. „ The importance of biomedical terminologies { Clinical practice, e.g. ICD10 use in diagnosis coding and billing { Biomedical research { Healthcare applications: EHR and EMR
  • 4. 4 The Unified Medical Language System „ A system that integrates more than 150 terminologies to enable interoperability between computerized systems in healthcare industry „ Designed and developed by United States National Library of Medicine
  • 5. 5 Structure of the UMLS „ Two-level structure of the UMLS { Metathesaurus (META): „ More than 2 million concepts „ Terms from sources are grouped into concepts „ More than 50 million relationships { Semantic Network „ 133 semantic types „ Each concept in META is assigned to at least one semantic type
  • 6. 6 Relationship in the META „ UMLS META relationship: { Derived from the source { Introduced during the integration „ 11 different relationship types (RELs): { Hierarchical relationships „ Parent (PAR) and child (CHD) „ Broader (RB) and narrower (RN) { Lateral (non-hierarchical) relationships „ e.g. SY (synonym)
  • 7. 7 Problems of Relationship Triples „ Relationship in META is the foundation of concept definitions „ Problems of relationship triples: { There exist multiple relationships between the same pair of concepts, they may be „ from the same source „ from different sources { Multiple RELs between a pair of concepts may indicate problems
  • 8. 8 Suspicious Relationship Triples „ Relationship triple { Source concept – A { Target concept – B { Relationship – r { (r, A, B) B r1 r2 A
  • 9. 9 Identify Suspicious Relationship Triples „ Our algorithm automatically identifies all suspicious relationship triples. „ They are in the following 4 cases { Conflicting hierarchical RELs { Redundant hierarchical RELs { Mixed hierarchical/lateral RELs { Multiple mutually exclusive lateral RELs
  • 10. 10 Case 1: Conflicting Hierarchical RELs „ Two or more hierarchical RELs existing between two different concepts forming a hierarchical cycle where one or more RELs are incorrect. „ PAR and CHD „ PAR and RN „ RB and CHD „ RB and RN B A PAR (RB) CHD (RN)
  • 11. 11 Example of Case 1 Dermatologic disorder PAR UMLS_CODE C0037274 Inverse_isa Dermatitis UMLS_CODE C0011603 Dermatologic disorder UMLS_CODE C0037274 Dermatitis UMLS_CODE C0011603 conflicting hierarchical relationships CHD isa CHD isa
  • 12. 12 Case 2: Redundant Hierarchical RELs „ A concept is PAR (CHD) and RB (RN) of another given concept at the same time {PAR and RB {CHD and RN B A CHD (RB) RN (PAR)
  • 13. Case 3: Mixed Hierarchical/lateral RELs 13 „ Two different concepts A and B with one hierarchical relationship and one lateral relationship which are mutually exclusive and cannot occur in the same pair of concepts at the same time. B A PAR (CHD, RB, RN) Lateral REL
  • 14. 14 Examples of Case 2 & 3 Right suprascapular vein Structure of suprascapular vein Right external jugular vein PAR inverse_isa RB (Broader) inverse_isa PAR has_tributray RO (other semantic relation) has_tributary RB and PAR: redundant hierarchical relationships PAR and RO: mutually exclusive relationships
  • 15. 15 Case 4: Multiple Lateral RELs „ Two different concepts A and B with two lateral relationships which are mutually exclusive. Mutual exclusivity can only be asserted by the relationship attributes qualifying both RELs B A Lateral REL Lateral REL
  • 16. 16 Example for Case 4 SLE glomerulonephritis syndrome, WHO class V Lupus Erythematosus, Systemic RO associated_with RL mapped_from SLE glomerulonephritis syndrome, WHO class V RO associated_with Lupus Erythematosus, Systemic UMLS_CODE C0268758 UMLS_CODE C0024141
  • 17. 17 2/21/2012 Statistics „ Our methodology was applied to the UMLS 2010AA release.
  • 18. 18 Discussion „ Certain of REL triples can be attributed to the process of the source vocabulary integration. „ Questionable relationship triples may be an indicator of term ambiguity. „ Algorithmic approaches that can easily detect and classify such errors are important.
  • 19. „ This work was partially supported by the National Library of Medicine, NIH R01 grant REFERENCES [1] O. Bodenreider, "The Unified Medical Language System (UMLS): integrating biomedical terminology." Nucleic Acids Res. 2004 Jan 1;32(Database issue):D267-70 [2] O. Bodenreider, "Circular hierarchical relationships in the UMLS: Etiology, diagnosis, treatment, complications and prevention." AMIA Annu Symp Proc; 2001:57–61. [3] UMLS Reference Manual: www.nlm.nih.gov/research/umls/meta2.html. [4] H. Gu, Y. Perl, G. Elhanan, H. Min, L.Zhang, and Y. Peng, "Auditing concept categorizations in the UMLS." Artif Intell Med. 2004 May;31(1):29–44. [5] Y. Chen, H. Gu, Y. Perl, and J. Geller, "Structural group-based auditing of missing hierarchical relationships in UMLS." J Biomed Inform. 2009 Jun;42(3):452–67. [6] O. Bodenreider, S.J. Nelson, W.T. Hole, and H.F. Chang, "Beyond synonymy: exploiting the UMLS semantics in mapping vocabularies." Proc AMIA Symp. 1998:815–9. [7] F. Mougin and O. Bodenreider, "Approaches to eliminating cycles in the UMLS Metathesaurus: Naïve vs. formal." AMIA Annu Symp Proc; 2005:550–4. [8] M. Halper, C.P. Morrey, Y. Chen, G. Elhanan, G. Hripcsak, and Y. Perl, "Auditing Hierarchical Cycles to Locate Other Inconsistencies in the UMLS." AMIA Annu Symp Proc; 2011:529–33. 19 Acknowledgement and References