Methods Inf Med 2/2013 © Schattauer 2013
168 Focus Theme – Original Articles
Health Webscience
The Role of Taxonomies in Social
Media and the Semantic Web
for Health Education
A Study of SNOMED CT Terms in YouTube Health Video
Tags
S. Konstantinidis
1
; L. Fernandez-Luque
2
; P. Bamidis
3
; R. Karlsen
2,4
1
Aristotle University of Thessaloniki, Lab of Medical Informatics, Medical School, Thessaloniki, Greece;
2
Norut, Tromsø, Norway;
3
Aristotle University of Thessaloniki, Lab of Medical Informatics, Medical School, Thessaloniki, Greece;
4
University of Tromsø, Computer Science Department, Tromsø, Norway
Keywords
Heath video, tags, tag cloud, SNOMED CT,
terms, Medical thesauri, linked data, linked
medical data, educational metadata, learn-
ing/content management system
Summary
Background: An increasing amount of
health education resources for patients and
professionals are distributed via social media
channels. For example, thousands of health
education videos are disseminated via You-
Tube. Often, tags are assigned by the dis-
seminator. However, the lack of use of stan-
dardized terminologies in those tags and the
presence of misleading videos make it par-
ticularly hard to retrieve relevant videos.
Objectives: i) Identify the use of standard-
ized medical thesauri (SNOMED CT) in You-
Tube Health videos tags from preselected
YouTube Channels and demonstrate an infor-
mation technology (IT) architecture for treat-
ing the tags of these health (video) resources.
ii) Investigate the relative percentage of the
tags used that relate to SNOMED CT terms. As
such resources may play a key role in educat-
ing professionals and patients, the use of stan-
dardized vocabularies may facilitate the shar-
ing of such resources. iii) Demonstrate how
such resources may be properly exploited
within the new generation of semantically en-
riched content or learning management sys-
tems that allow for knowledge expansion
through the use of linked medical data and
numerous literature resources also described
through the same vocabularies.
Methods: We implemented a video portal in-
tegrating videos from 500 US Hospital chan-
nels. The portal integrated 4,307 YouTube
videos regarding surgery as described by
64,367 tags. BioPortal REST services were
used within our portal to match SNOMED CT
terms with YouTube tags by both exact match
and non-exact match. The whole architecture
was complemented with a mechanism to en-
rich the retrieved video resources with other
educational material residing in other reposi-
tories by following contemporary semantic
web advances, in the form of Linked Open
Data (LOD) principles.
Results: The average percentage of YouTube
tags that were expressed using SNOMED CT
terms was about 22.5%, while one third of
YouTube tags per video contained a SNOMED
CT term in a loose search; this analogy be-
came one tenth in the case of exact match.
Retrieved videos were then linked further to
other resources by using LOD compliant sys-
tems. Such results were exemplified in the
case of systems and technologies used in the
mEducator EC funded project.
Conclusion: YouTube Health videos can be
searched for and retrieved using SNOMED CT
terms with a high possibility of identifying
health videos that users want based on their
search criteria. Despite the fact that tagging
of this information with SNOMED CT terms
may vary, its availability and linked data ca-
pacity opens the door to new studies for per-
sonalized retrieval of content and linking
with other knowledge through linked medi-
cal data and semantic advances in (learning)
content management systems.
Correspondence to:
Panagiotis D. Bamidis
Lab of Medical Informatics
Medical School
Aristotle University of Thessaloniki,
PO Box 323
54124, Thessaloniki
Greece
E-mail: bamidis@med.auth.gr
Methods Inf Med 2013; 52: 168–179
doi: 10.3414/ME12-02-0005
received: March 4, 2012
accepted: February 3,2013
prepublished: February 28, 2013
For personal or educational use only. No other uses without permission. All rights reserved.
Downloaded from www.methods-online.com on 2014-09-12 | IP: 193.156.105.143