Transcript Tailoring Health Information on the Web to the Needs of

Tailoring Health Information on
the Web to the Needs of the
Individual
The Role of Knowledge Representations and
Formal Vocabularies
Josette Jones, RNc, Licentiate Nursing,
Licentiate MIS
Gyda Bjornsdottir, RN, MSN
Patricia F. Brennan, RN, Ph.D, FAAN. FACMI
University of Wisconsin Madison
Purpose of the Study
Report on
 Indexing patient-specific web pages

Implication for information searching by
patients
Background and Significance

Capitalizing on the interactive technology
and health-oriented web sites to extend
discharge teaching

Issues in information searching
Entities Involved in Information
Searching

Set of indexed web documents

An information need formulated in a
query language

Matching mechanism
How are documents indexed?
How do we search for information?

Keyword indexing and searching


Controlled Vocabulary
Concept indexing and searching
Use of Knowledge
Representation Systems in
Indexing and Searching
Concept terms are derived from a Knowledge
Representation System (KRS)
A
KRS has :



Health
An underlying terminology,
A semantic (i.e the meaning of the term),
A restricted syntax (set of reasoning rules)
Care / Nursing KRS
How are Web Documents in
HeartCare Indexed?
Nurse-clinicians tagged web documents
with:
 Selected
concepts from Medical Language
Subject Heading (MeSH)
 Supplemented
with keywords reflecting
local clinical practice
Examples of Index Terms Used

MeSH concepts:
angina, cardiovascular diseases,
diabetes, hyperlypidemia, patientphysician relation, etc.

Keywords: lifting, driving, eating out,
menu planning, recipes, etc.
Reliability of the Judgment

Sample



54 patient-specific web pages
3 independent judges
Results

Same terms




Exact same terms
Additional terms by 1 or more
Same term by 2 judges
Different terms
69% (37 pages)
35%
34%
15% (8 pages)
16% (9 pages)
Search Function for Patients in
HeartCare
Design of Search Function

Use of controlled vocabulary (list of index
terms used)

Reformulation of the title of the web
document to better reflect the subject
matter
Use of Search Function
Sample

Patients enrolled in HeartCare

Time frame:
July 1, 1999 – February 11, 2000 (218 days)
Use of Search Function
Results
 Search sessions observed

N=137
Patients involved in searches
N= 37
Total searches initiated per patient range
from 1 to 21
Use of Search Function
Total searches



Accessed
Selection of keywords only
Browsing and/or retrieval of web pages
N= 137
65 (47.4%)
37 (27.0%)
35 (25.5%)
Use of Search Function
• Total terms used in searches:
41/71
• Most used terms:
appetite, driving, breast pain, behavior change, Aspirin,
diet, incisions
• Frequency of term selected during a search ranged
from 1 term (57 times) to 9 terms (1 time)
• Number of web documents viewed per selected
keyword ranged from 0 (63 times ) to 14 (1 time)
Discussion


Issues related to indexing

MeSH concepts not granular enough to describe the
content of all web documents

Ambiguity of language (e.g. synonymy, polysemy)
Issues related to searching

Terms used by nurses may not be significant/useful to
patients
The results discussed in this presentation
were collected from the experiences in
HeartCare (NLM/NINR Grant LM06249).
The support of the HeartCare team is
gratefully acknowledged.