Dynamic generation of a health topics overview from consumer health information documents

Trudi Miller, Gondy Augusta Leroy

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Online health information use is increasing, but can be too difficult for consumers. We created a system that dynamically generates a health topics overview for consumer health web pages that organises the information into four consumer-preferred categories while displaying topic prevalence through visualisation. It accesses both a consumer health vocabulary and the Unified Medical Language System (UMLS). We evaluated its ability by calculating precision, recall, and F-score for phrase extraction and categorisation. We tested pages from three different consumer web sites. Overall, precision is 82%, recall is 75%, and F-score is 78%, and precision between sites did not significantly differ.

Original languageEnglish (US)
Pages (from-to)395-414
Number of pages20
JournalInternational Journal of Biomedical Engineering and Technology
Volume1
Issue number4
DOIs
StatePublished - 2008
Externally publishedYes

Fingerprint

Health
Websites
Information use
Visualization

Keywords

  • Consumer health informatics
  • Information systems
  • Information technology
  • Natural language processing
  • Text visualisation
  • UMLS
  • Unified Medical Language System

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

@article{56dbb4855d1c4d02ad265ec978cf9d70,
title = "Dynamic generation of a health topics overview from consumer health information documents",
abstract = "Online health information use is increasing, but can be too difficult for consumers. We created a system that dynamically generates a health topics overview for consumer health web pages that organises the information into four consumer-preferred categories while displaying topic prevalence through visualisation. It accesses both a consumer health vocabulary and the Unified Medical Language System (UMLS). We evaluated its ability by calculating precision, recall, and F-score for phrase extraction and categorisation. We tested pages from three different consumer web sites. Overall, precision is 82{\%}, recall is 75{\%}, and F-score is 78{\%}, and precision between sites did not significantly differ.",
keywords = "Consumer health informatics, Information systems, Information technology, Natural language processing, Text visualisation, UMLS, Unified Medical Language System",
author = "Trudi Miller and Leroy, {Gondy Augusta}",
year = "2008",
doi = "10.1504/IJBET.2008.020069",
language = "English (US)",
volume = "1",
pages = "395--414",
journal = "International Journal of Biomedical Engineering and Technology",
issn = "1752-6418",
publisher = "Inderscience Enterprises Ltd",
number = "4",

}

TY - JOUR

T1 - Dynamic generation of a health topics overview from consumer health information documents

AU - Miller, Trudi

AU - Leroy, Gondy Augusta

PY - 2008

Y1 - 2008

N2 - Online health information use is increasing, but can be too difficult for consumers. We created a system that dynamically generates a health topics overview for consumer health web pages that organises the information into four consumer-preferred categories while displaying topic prevalence through visualisation. It accesses both a consumer health vocabulary and the Unified Medical Language System (UMLS). We evaluated its ability by calculating precision, recall, and F-score for phrase extraction and categorisation. We tested pages from three different consumer web sites. Overall, precision is 82%, recall is 75%, and F-score is 78%, and precision between sites did not significantly differ.

AB - Online health information use is increasing, but can be too difficult for consumers. We created a system that dynamically generates a health topics overview for consumer health web pages that organises the information into four consumer-preferred categories while displaying topic prevalence through visualisation. It accesses both a consumer health vocabulary and the Unified Medical Language System (UMLS). We evaluated its ability by calculating precision, recall, and F-score for phrase extraction and categorisation. We tested pages from three different consumer web sites. Overall, precision is 82%, recall is 75%, and F-score is 78%, and precision between sites did not significantly differ.

KW - Consumer health informatics

KW - Information systems

KW - Information technology

KW - Natural language processing

KW - Text visualisation

KW - UMLS

KW - Unified Medical Language System

UR - http://www.scopus.com/inward/record.url?scp=78649891971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649891971&partnerID=8YFLogxK

U2 - 10.1504/IJBET.2008.020069

DO - 10.1504/IJBET.2008.020069

M3 - Article

AN - SCOPUS:78649891971

VL - 1

SP - 395

EP - 414

JO - International Journal of Biomedical Engineering and Technology

JF - International Journal of Biomedical Engineering and Technology

SN - 1752-6418

IS - 4

ER -