Drug side effect extraction from clinical narratives of psychiatry and psychology patients

Sunghwan Sohn, Jean-Pierre Kocher, Christopher G. Chute, Guergana K. Savova

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

Objective: To extract physician-asserted drug side effects from electronic medical record clinical narratives. Materials and methods: Pattern matching rules were manually developed through examining keywords and expression patterns of side effects to discover an individual side effect and causative drug relationship. A combination of machine learning (C4.5) using side effect keyword features and pattern matching rules was used to extract sentences that contain side effect and causative drug pairs, enabling the system to discover most side effect occurrences. Our system was implemented as a module within the clinical Text Analysis and Knowledge Extraction System. Results: The system was tested in the domain of psychiatry and psychology. The rule-based system extracting side effects and causative drugs produced an F score of 0.80 (0.55 excluding allergy section). The hybrid system identifying side effect sentences had an F score of 0.75 (0.56 excluding allergy section) but covered more side effect and causative drug pairs than individual side effect extraction. Discussion: The rule-based system was able to identify most side effects expressed by clear indication words. More sophisticated semantic processing is required to handle complex side effect descriptions in the narrative. We demonstrated that our system can be trained to identify sentences with complex side effect descriptions that can be submitted to a human expert for further abstraction. Conclusion: Our system was able to extract most physician-asserted drug side effects. It can be used in either an automated mode for side effect extraction or semi-automated mode to identify side effect sentences that can significantly simplify abstraction by a human expert.

Original languageEnglish (US)
Pages (from-to)144-149
Number of pages6
JournalJournal of the American Medical Informatics Association
Volume18
Issue numberSUPPL. 1
DOIs
StatePublished - Dec 2011

Fingerprint

Drug-Related Side Effects and Adverse Reactions
Psychiatry
Psychology
Hypersensitivity
Physicians
Electronic Health Records
Semantics

ASJC Scopus subject areas

  • Health Informatics
  • Medicine(all)

Cite this

Drug side effect extraction from clinical narratives of psychiatry and psychology patients. / Sohn, Sunghwan; Kocher, Jean-Pierre; Chute, Christopher G.; Savova, Guergana K.

In: Journal of the American Medical Informatics Association, Vol. 18, No. SUPPL. 1, 12.2011, p. 144-149.

Research output: Contribution to journalArticle

@article{43ab6763dafa43f2a638b2dcde8d38c3,
title = "Drug side effect extraction from clinical narratives of psychiatry and psychology patients",
abstract = "Objective: To extract physician-asserted drug side effects from electronic medical record clinical narratives. Materials and methods: Pattern matching rules were manually developed through examining keywords and expression patterns of side effects to discover an individual side effect and causative drug relationship. A combination of machine learning (C4.5) using side effect keyword features and pattern matching rules was used to extract sentences that contain side effect and causative drug pairs, enabling the system to discover most side effect occurrences. Our system was implemented as a module within the clinical Text Analysis and Knowledge Extraction System. Results: The system was tested in the domain of psychiatry and psychology. The rule-based system extracting side effects and causative drugs produced an F score of 0.80 (0.55 excluding allergy section). The hybrid system identifying side effect sentences had an F score of 0.75 (0.56 excluding allergy section) but covered more side effect and causative drug pairs than individual side effect extraction. Discussion: The rule-based system was able to identify most side effects expressed by clear indication words. More sophisticated semantic processing is required to handle complex side effect descriptions in the narrative. We demonstrated that our system can be trained to identify sentences with complex side effect descriptions that can be submitted to a human expert for further abstraction. Conclusion: Our system was able to extract most physician-asserted drug side effects. It can be used in either an automated mode for side effect extraction or semi-automated mode to identify side effect sentences that can significantly simplify abstraction by a human expert.",
author = "Sunghwan Sohn and Jean-Pierre Kocher and Chute, {Christopher G.} and Savova, {Guergana K.}",
year = "2011",
month = "12",
doi = "10.1136/amiajnl-2011-000351",
language = "English (US)",
volume = "18",
pages = "144--149",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "SUPPL. 1",

}

TY - JOUR

T1 - Drug side effect extraction from clinical narratives of psychiatry and psychology patients

AU - Sohn, Sunghwan

AU - Kocher, Jean-Pierre

AU - Chute, Christopher G.

AU - Savova, Guergana K.

PY - 2011/12

Y1 - 2011/12

N2 - Objective: To extract physician-asserted drug side effects from electronic medical record clinical narratives. Materials and methods: Pattern matching rules were manually developed through examining keywords and expression patterns of side effects to discover an individual side effect and causative drug relationship. A combination of machine learning (C4.5) using side effect keyword features and pattern matching rules was used to extract sentences that contain side effect and causative drug pairs, enabling the system to discover most side effect occurrences. Our system was implemented as a module within the clinical Text Analysis and Knowledge Extraction System. Results: The system was tested in the domain of psychiatry and psychology. The rule-based system extracting side effects and causative drugs produced an F score of 0.80 (0.55 excluding allergy section). The hybrid system identifying side effect sentences had an F score of 0.75 (0.56 excluding allergy section) but covered more side effect and causative drug pairs than individual side effect extraction. Discussion: The rule-based system was able to identify most side effects expressed by clear indication words. More sophisticated semantic processing is required to handle complex side effect descriptions in the narrative. We demonstrated that our system can be trained to identify sentences with complex side effect descriptions that can be submitted to a human expert for further abstraction. Conclusion: Our system was able to extract most physician-asserted drug side effects. It can be used in either an automated mode for side effect extraction or semi-automated mode to identify side effect sentences that can significantly simplify abstraction by a human expert.

AB - Objective: To extract physician-asserted drug side effects from electronic medical record clinical narratives. Materials and methods: Pattern matching rules were manually developed through examining keywords and expression patterns of side effects to discover an individual side effect and causative drug relationship. A combination of machine learning (C4.5) using side effect keyword features and pattern matching rules was used to extract sentences that contain side effect and causative drug pairs, enabling the system to discover most side effect occurrences. Our system was implemented as a module within the clinical Text Analysis and Knowledge Extraction System. Results: The system was tested in the domain of psychiatry and psychology. The rule-based system extracting side effects and causative drugs produced an F score of 0.80 (0.55 excluding allergy section). The hybrid system identifying side effect sentences had an F score of 0.75 (0.56 excluding allergy section) but covered more side effect and causative drug pairs than individual side effect extraction. Discussion: The rule-based system was able to identify most side effects expressed by clear indication words. More sophisticated semantic processing is required to handle complex side effect descriptions in the narrative. We demonstrated that our system can be trained to identify sentences with complex side effect descriptions that can be submitted to a human expert for further abstraction. Conclusion: Our system was able to extract most physician-asserted drug side effects. It can be used in either an automated mode for side effect extraction or semi-automated mode to identify side effect sentences that can significantly simplify abstraction by a human expert.

UR - http://www.scopus.com/inward/record.url?scp=84863544591&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863544591&partnerID=8YFLogxK

U2 - 10.1136/amiajnl-2011-000351

DO - 10.1136/amiajnl-2011-000351

M3 - Article

C2 - 21946242

AN - SCOPUS:84863544591

VL - 18

SP - 144

EP - 149

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - SUPPL. 1

ER -