Simulating expert clinical comprehension

Adapting latent semantic analysis to accurately extract clinical concepts from psychiatric narrative

Trevor Cohen, Brett Blatter, Vimla Patel

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Cognitive studies reveal that less-than-expert clinicians are less able to recognize meaningful patterns of data in clinical narratives. Accordingly, psychiatric residents early in training fail to attend to information that is relevant to diagnosis and the assessment of dangerousness. This manuscript presents cognitively motivated methodology for the simulation of expert ability to organize relevant findings supporting intermediate diagnostic hypotheses. Latent Semantic Analysis is used to generate a semantic space from which meaningful associations between psychiatric terms are derived. Diagnostically meaningful clusters are modeled as geometric structures within this space and compared to elements of psychiatric narrative text using semantic distance measures. A learning algorithm is defined that alters components of these geometric structures in response to labeled training data. Extraction and classification of relevant text segments is evaluated against expert annotation, with system-rater agreement approximating rater-rater agreement. A range of biomedical informatics applications for these methods are suggested.

Original languageEnglish (US)
Pages (from-to)1070-1087
Number of pages18
JournalJournal of Biomedical Informatics
Volume41
Issue number6
DOIs
StatePublished - Dec 1 2008
Externally publishedYes

Fingerprint

Semantics
Psychiatry
Dangerous Behavior
Informatics
Aptitude
Learning algorithms
Learning

Keywords

  • Cognition
  • Conceptual spaces
  • Expertise
  • Information extraction
  • Latent semantic analysis
  • Natural language processing
  • Text comprehension

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Simulating expert clinical comprehension : Adapting latent semantic analysis to accurately extract clinical concepts from psychiatric narrative. / Cohen, Trevor; Blatter, Brett; Patel, Vimla.

In: Journal of Biomedical Informatics, Vol. 41, No. 6, 01.12.2008, p. 1070-1087.

Research output: Contribution to journalArticle

@article{d5ca8bec37d0429d8bbf6ded3e7e05d7,
title = "Simulating expert clinical comprehension: Adapting latent semantic analysis to accurately extract clinical concepts from psychiatric narrative",
abstract = "Cognitive studies reveal that less-than-expert clinicians are less able to recognize meaningful patterns of data in clinical narratives. Accordingly, psychiatric residents early in training fail to attend to information that is relevant to diagnosis and the assessment of dangerousness. This manuscript presents cognitively motivated methodology for the simulation of expert ability to organize relevant findings supporting intermediate diagnostic hypotheses. Latent Semantic Analysis is used to generate a semantic space from which meaningful associations between psychiatric terms are derived. Diagnostically meaningful clusters are modeled as geometric structures within this space and compared to elements of psychiatric narrative text using semantic distance measures. A learning algorithm is defined that alters components of these geometric structures in response to labeled training data. Extraction and classification of relevant text segments is evaluated against expert annotation, with system-rater agreement approximating rater-rater agreement. A range of biomedical informatics applications for these methods are suggested.",
keywords = "Cognition, Conceptual spaces, Expertise, Information extraction, Latent semantic analysis, Natural language processing, Text comprehension",
author = "Trevor Cohen and Brett Blatter and Vimla Patel",
year = "2008",
month = "12",
day = "1",
doi = "10.1016/j.jbi.2008.03.008",
language = "English (US)",
volume = "41",
pages = "1070--1087",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "6",

}

TY - JOUR

T1 - Simulating expert clinical comprehension

T2 - Adapting latent semantic analysis to accurately extract clinical concepts from psychiatric narrative

AU - Cohen, Trevor

AU - Blatter, Brett

AU - Patel, Vimla

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Cognitive studies reveal that less-than-expert clinicians are less able to recognize meaningful patterns of data in clinical narratives. Accordingly, psychiatric residents early in training fail to attend to information that is relevant to diagnosis and the assessment of dangerousness. This manuscript presents cognitively motivated methodology for the simulation of expert ability to organize relevant findings supporting intermediate diagnostic hypotheses. Latent Semantic Analysis is used to generate a semantic space from which meaningful associations between psychiatric terms are derived. Diagnostically meaningful clusters are modeled as geometric structures within this space and compared to elements of psychiatric narrative text using semantic distance measures. A learning algorithm is defined that alters components of these geometric structures in response to labeled training data. Extraction and classification of relevant text segments is evaluated against expert annotation, with system-rater agreement approximating rater-rater agreement. A range of biomedical informatics applications for these methods are suggested.

AB - Cognitive studies reveal that less-than-expert clinicians are less able to recognize meaningful patterns of data in clinical narratives. Accordingly, psychiatric residents early in training fail to attend to information that is relevant to diagnosis and the assessment of dangerousness. This manuscript presents cognitively motivated methodology for the simulation of expert ability to organize relevant findings supporting intermediate diagnostic hypotheses. Latent Semantic Analysis is used to generate a semantic space from which meaningful associations between psychiatric terms are derived. Diagnostically meaningful clusters are modeled as geometric structures within this space and compared to elements of psychiatric narrative text using semantic distance measures. A learning algorithm is defined that alters components of these geometric structures in response to labeled training data. Extraction and classification of relevant text segments is evaluated against expert annotation, with system-rater agreement approximating rater-rater agreement. A range of biomedical informatics applications for these methods are suggested.

KW - Cognition

KW - Conceptual spaces

KW - Expertise

KW - Information extraction

KW - Latent semantic analysis

KW - Natural language processing

KW - Text comprehension

UR - http://www.scopus.com/inward/record.url?scp=55549086149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55549086149&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2008.03.008

DO - 10.1016/j.jbi.2008.03.008

M3 - Article

VL - 41

SP - 1070

EP - 1087

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 6

ER -