Data-driven method to enhance craniofacial and oral phenotype vocabularies

Rashmi Mishra, Andrea Burke, Bonnie Gitman, Payal Verma, Mark Engelstad, Melissa A. Haendel, Ilias Alevizos, William A. Gahl, Michael T. Collins, Janice S. Lee, Murat Sincan

Research output: Contribution to journalArticle

Abstract

Background: A significant amount of clinical information captured as free-text narratives could be better used for several applications, such as clinical decision support, ontology development, evidence-based practice, and research. The Human Phenotype Ontology (HPO) is specifically used for semantic comparisons for diagnostic purposes. All these functions require quality coverage of the domain of interest. The authors used natural language processing to capture craniofacial and oral phenotype signatures from electronic health records and then used these signatures for evaluation of existing oral phenotype ontology coverage. Methods: The authors applied a text-processing pipeline based on the clinical Text Analysis and Knowledge Extraction System to annotate the clinical notes with Unified Medical Language System codes. The authors extracted the disease or disorder phenotype terms, which were then compared with HPO terms and their synonyms. Results: The authors retrieved 2,153 deidentified clinical notes from 558 patients. Finally, 2,416 unique diseases or disorders phenotype terms were extracted, which included 210 craniofacial or oral phenotype terms. Twenty-six of these phenotypes were not found in the HPO. Conclusions: The authors demonstrated that natural language processing tools could extract relevant phenotype terms from clinical narratives, which could help identify gaps in existing ontologies and enhance craniofacial and dental phenotyping vocabularies. Practical Implications: The expansion of terms in the dental, oral, and craniofacial domains in the HPO is particularly important as the dental community moves toward electronic health records.

Original languageEnglish (US)
Pages (from-to)933-939.e2
JournalJournal of the American Dental Association
Volume150
Issue number11
DOIs
StatePublished - Nov 2019

Fingerprint

Vocabulary
Phenotype
Natural Language Processing
Tooth
Electronic Health Records
Unified Medical Language System
Clinical Decision Support Systems
Evidence-Based Practice
Semantics

Keywords

  • craniofacial and oral phenotypes
  • evidence-based dentistry
  • Natural language processing
  • ontology

ASJC Scopus subject areas

  • Dentistry(all)

Cite this

Data-driven method to enhance craniofacial and oral phenotype vocabularies. / Mishra, Rashmi; Burke, Andrea; Gitman, Bonnie; Verma, Payal; Engelstad, Mark; Haendel, Melissa A.; Alevizos, Ilias; Gahl, William A.; Collins, Michael T.; Lee, Janice S.; Sincan, Murat.

In: Journal of the American Dental Association, Vol. 150, No. 11, 11.2019, p. 933-939.e2.

Research output: Contribution to journalArticle

Mishra, R, Burke, A, Gitman, B, Verma, P, Engelstad, M, Haendel, MA, Alevizos, I, Gahl, WA, Collins, MT, Lee, JS & Sincan, M 2019, 'Data-driven method to enhance craniofacial and oral phenotype vocabularies', Journal of the American Dental Association, vol. 150, no. 11, pp. 933-939.e2. https://doi.org/10.1016/j.adaj.2019.05.029
Mishra, Rashmi ; Burke, Andrea ; Gitman, Bonnie ; Verma, Payal ; Engelstad, Mark ; Haendel, Melissa A. ; Alevizos, Ilias ; Gahl, William A. ; Collins, Michael T. ; Lee, Janice S. ; Sincan, Murat. / Data-driven method to enhance craniofacial and oral phenotype vocabularies. In: Journal of the American Dental Association. 2019 ; Vol. 150, No. 11. pp. 933-939.e2.
@article{ab1bebdbac98494bb6c6e9e2aeaa350c,
title = "Data-driven method to enhance craniofacial and oral phenotype vocabularies",
abstract = "Background: A significant amount of clinical information captured as free-text narratives could be better used for several applications, such as clinical decision support, ontology development, evidence-based practice, and research. The Human Phenotype Ontology (HPO) is specifically used for semantic comparisons for diagnostic purposes. All these functions require quality coverage of the domain of interest. The authors used natural language processing to capture craniofacial and oral phenotype signatures from electronic health records and then used these signatures for evaluation of existing oral phenotype ontology coverage. Methods: The authors applied a text-processing pipeline based on the clinical Text Analysis and Knowledge Extraction System to annotate the clinical notes with Unified Medical Language System codes. The authors extracted the disease or disorder phenotype terms, which were then compared with HPO terms and their synonyms. Results: The authors retrieved 2,153 deidentified clinical notes from 558 patients. Finally, 2,416 unique diseases or disorders phenotype terms were extracted, which included 210 craniofacial or oral phenotype terms. Twenty-six of these phenotypes were not found in the HPO. Conclusions: The authors demonstrated that natural language processing tools could extract relevant phenotype terms from clinical narratives, which could help identify gaps in existing ontologies and enhance craniofacial and dental phenotyping vocabularies. Practical Implications: The expansion of terms in the dental, oral, and craniofacial domains in the HPO is particularly important as the dental community moves toward electronic health records.",
keywords = "craniofacial and oral phenotypes, evidence-based dentistry, Natural language processing, ontology",
author = "Rashmi Mishra and Andrea Burke and Bonnie Gitman and Payal Verma and Mark Engelstad and Haendel, {Melissa A.} and Ilias Alevizos and Gahl, {William A.} and Collins, {Michael T.} and Lee, {Janice S.} and Murat Sincan",
year = "2019",
month = "11",
doi = "10.1016/j.adaj.2019.05.029",
language = "English (US)",
volume = "150",
pages = "933--939.e2",
journal = "Journal of the American Dental Association",
issn = "0002-8177",
publisher = "American Dental Association",
number = "11",

}

TY - JOUR

T1 - Data-driven method to enhance craniofacial and oral phenotype vocabularies

AU - Mishra, Rashmi

AU - Burke, Andrea

AU - Gitman, Bonnie

AU - Verma, Payal

AU - Engelstad, Mark

AU - Haendel, Melissa A.

AU - Alevizos, Ilias

AU - Gahl, William A.

AU - Collins, Michael T.

AU - Lee, Janice S.

AU - Sincan, Murat

PY - 2019/11

Y1 - 2019/11

N2 - Background: A significant amount of clinical information captured as free-text narratives could be better used for several applications, such as clinical decision support, ontology development, evidence-based practice, and research. The Human Phenotype Ontology (HPO) is specifically used for semantic comparisons for diagnostic purposes. All these functions require quality coverage of the domain of interest. The authors used natural language processing to capture craniofacial and oral phenotype signatures from electronic health records and then used these signatures for evaluation of existing oral phenotype ontology coverage. Methods: The authors applied a text-processing pipeline based on the clinical Text Analysis and Knowledge Extraction System to annotate the clinical notes with Unified Medical Language System codes. The authors extracted the disease or disorder phenotype terms, which were then compared with HPO terms and their synonyms. Results: The authors retrieved 2,153 deidentified clinical notes from 558 patients. Finally, 2,416 unique diseases or disorders phenotype terms were extracted, which included 210 craniofacial or oral phenotype terms. Twenty-six of these phenotypes were not found in the HPO. Conclusions: The authors demonstrated that natural language processing tools could extract relevant phenotype terms from clinical narratives, which could help identify gaps in existing ontologies and enhance craniofacial and dental phenotyping vocabularies. Practical Implications: The expansion of terms in the dental, oral, and craniofacial domains in the HPO is particularly important as the dental community moves toward electronic health records.

AB - Background: A significant amount of clinical information captured as free-text narratives could be better used for several applications, such as clinical decision support, ontology development, evidence-based practice, and research. The Human Phenotype Ontology (HPO) is specifically used for semantic comparisons for diagnostic purposes. All these functions require quality coverage of the domain of interest. The authors used natural language processing to capture craniofacial and oral phenotype signatures from electronic health records and then used these signatures for evaluation of existing oral phenotype ontology coverage. Methods: The authors applied a text-processing pipeline based on the clinical Text Analysis and Knowledge Extraction System to annotate the clinical notes with Unified Medical Language System codes. The authors extracted the disease or disorder phenotype terms, which were then compared with HPO terms and their synonyms. Results: The authors retrieved 2,153 deidentified clinical notes from 558 patients. Finally, 2,416 unique diseases or disorders phenotype terms were extracted, which included 210 craniofacial or oral phenotype terms. Twenty-six of these phenotypes were not found in the HPO. Conclusions: The authors demonstrated that natural language processing tools could extract relevant phenotype terms from clinical narratives, which could help identify gaps in existing ontologies and enhance craniofacial and dental phenotyping vocabularies. Practical Implications: The expansion of terms in the dental, oral, and craniofacial domains in the HPO is particularly important as the dental community moves toward electronic health records.

KW - craniofacial and oral phenotypes

KW - evidence-based dentistry

KW - Natural language processing

KW - ontology

UR - http://www.scopus.com/inward/record.url?scp=85073630645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073630645&partnerID=8YFLogxK

U2 - 10.1016/j.adaj.2019.05.029

DO - 10.1016/j.adaj.2019.05.029

M3 - Article

C2 - 31668172

AN - SCOPUS:85073630645

VL - 150

SP - 933-939.e2

JO - Journal of the American Dental Association

JF - Journal of the American Dental Association

SN - 0002-8177

IS - 11

ER -