Generating executable knowledge for evidence-based medicine using natural language and semantic processing.

Tara Borlawsky, Carol Friedman, Yves A Lussier

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

With an increase in the prevalence of patients having multiple medical conditions, along with the increasing number of medical information sources, an intelligent approach is required to integrate the answers to physicians' patient-related questions into clinical practice in the shortest, most specific way possible. Cochrane Scientific Reviews are currently considered to be the "gold standard" for evidence-based medicine (EBM), because of their well-defined systematic approach to assessing the available medical information. In order to develop semantic approaches for enabling the reuse of these Reviews, a system for producing executable knowledge was designed using a natural language processing (NLP) system we developed (BioMedLEE), and semantic processing techniques. Though BioMedLEE was not designed for or trained over the Cochrane Reviews, this study shows that disease, therapy and drug concepts can be extracted and correlated with an overall recall of 80.3%, coding precision of 94.1%, and concept-concept relationship precision of 87.3%.

Original languageEnglish (US)
Pages (from-to)56-60
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
StatePublished - 2006
Externally publishedYes

Fingerprint

Natural Language Processing
Evidence-Based Medicine
Semantics
Physicians
Drug Therapy

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{fbc3aa24e23748e4a46b9c21434d5a69,
title = "Generating executable knowledge for evidence-based medicine using natural language and semantic processing.",
abstract = "With an increase in the prevalence of patients having multiple medical conditions, along with the increasing number of medical information sources, an intelligent approach is required to integrate the answers to physicians' patient-related questions into clinical practice in the shortest, most specific way possible. Cochrane Scientific Reviews are currently considered to be the {"}gold standard{"} for evidence-based medicine (EBM), because of their well-defined systematic approach to assessing the available medical information. In order to develop semantic approaches for enabling the reuse of these Reviews, a system for producing executable knowledge was designed using a natural language processing (NLP) system we developed (BioMedLEE), and semantic processing techniques. Though BioMedLEE was not designed for or trained over the Cochrane Reviews, this study shows that disease, therapy and drug concepts can be extracted and correlated with an overall recall of 80.3{\%}, coding precision of 94.1{\%}, and concept-concept relationship precision of 87.3{\%}.",
author = "Tara Borlawsky and Carol Friedman and Lussier, {Yves A}",
year = "2006",
language = "English (US)",
pages = "56--60",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Generating executable knowledge for evidence-based medicine using natural language and semantic processing.

AU - Borlawsky, Tara

AU - Friedman, Carol

AU - Lussier, Yves A

PY - 2006

Y1 - 2006

N2 - With an increase in the prevalence of patients having multiple medical conditions, along with the increasing number of medical information sources, an intelligent approach is required to integrate the answers to physicians' patient-related questions into clinical practice in the shortest, most specific way possible. Cochrane Scientific Reviews are currently considered to be the "gold standard" for evidence-based medicine (EBM), because of their well-defined systematic approach to assessing the available medical information. In order to develop semantic approaches for enabling the reuse of these Reviews, a system for producing executable knowledge was designed using a natural language processing (NLP) system we developed (BioMedLEE), and semantic processing techniques. Though BioMedLEE was not designed for or trained over the Cochrane Reviews, this study shows that disease, therapy and drug concepts can be extracted and correlated with an overall recall of 80.3%, coding precision of 94.1%, and concept-concept relationship precision of 87.3%.

AB - With an increase in the prevalence of patients having multiple medical conditions, along with the increasing number of medical information sources, an intelligent approach is required to integrate the answers to physicians' patient-related questions into clinical practice in the shortest, most specific way possible. Cochrane Scientific Reviews are currently considered to be the "gold standard" for evidence-based medicine (EBM), because of their well-defined systematic approach to assessing the available medical information. In order to develop semantic approaches for enabling the reuse of these Reviews, a system for producing executable knowledge was designed using a natural language processing (NLP) system we developed (BioMedLEE), and semantic processing techniques. Though BioMedLEE was not designed for or trained over the Cochrane Reviews, this study shows that disease, therapy and drug concepts can be extracted and correlated with an overall recall of 80.3%, coding precision of 94.1%, and concept-concept relationship precision of 87.3%.

UR - http://www.scopus.com/inward/record.url?scp=34748824128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34748824128&partnerID=8YFLogxK

M3 - Article

C2 - 17238302

AN - SCOPUS:34748824128

SP - 56

EP - 60

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -