Mobile Health Search Enhanced with Social Tags



Michael Zarro* Michael Zarro*, Drexel University, Philadelphia, United States

Track: Practice
Presentation Topic: Mobile & Tablet Health Applications
Presentation Type: Poster presentation
Submission Type: Single Presentation

Last modified: 2012-09-12
qrcode

If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL).

Abstract


Searching for health information is one of the most popular activities on the Internet. Health consumers frequently look online, most often starting with general search engines, before talking with doctors or forming health maintenance strategies. Yet, the complexity of health concepts, the “vocabulary gap” between health consumer and health-information provider, and the “scatter” of content across the Web make it difficult for the layperson to find comprehensive health information and ultimately make well-informed healthcare decisions. These barriers can have a serious impact on health outcomes. The purpose of this work is improving search technology and enhancing consumers’ ability to find useful health information using consumer vocabulary sources in a mobile environment.
Medical experts and health consumers often represent concepts differently on the lexical layer despite a strong overlap on the conceptual layer, limiting the effectiveness of keyword searches. Low overlap between social tags and Medical Subject Headings (MeSH) has been found when comparing annotations for medical resources, suggesting that combining medical terms and social tags creates a richer vocabulary for search and retrieval. Recent efforts like the Open Access Consumer Health Vocabulary (CHV), added to the Unified Medical Language System (UMLS) in 2011, help bridge the gap between expert and consumer vocabularies by mapping consumer terms to medical vocabularies. Social tags, the terms used by consumers to label websites in social media sites for organization and later retrieval, offer a practical addition to controlled health vocabularies. These tag sets are constantly updated and reflect emerging consumer expressions of health concepts.
Information is woven into the fabric of our society due in large part to the mobile Web. According Pew reports, overall 80% of US adults have looked online for health information, and 17% of Internet users have used their phone to look up health or medical information. There are thousands of apps available for iOS and Android devices, 9% of mobile phone owners have an app on their phones that help them track or manage their health. Leveraging the ‘always on’ information sources available with smart phones, we created a dynamic mobile health search app using a jQuery mobile JavaScript frontend connected to a datastore of content extracted from government health resources and trusted health sites, and external sources including: commercial search, social question answering, PubMed, and MedlinePlus search APIs. Development is informed by a previous user-study that utilized similar technologies in a desktop search prototype where searchers reported social tags and MeSH terms helpful when searching for health information. This work extends the technology in that study and focuses on mobile search.
The app uses health and medically related social tags for over 900 thousand URLs along with CHV terms as interactive search guides that when activated expand a user’s keyword search. Co-occurrence rankings are used to suggest highly similar tags the user may select to fully explore a medical concept. The primary focus is achieving high usability, while offering features that allow a user to expand their search with new terms.
Search engines function as important health information intermediaries, guiding searching and browsing behaviors as consumers try to find useful resources and learn about unfamiliar concepts. Interactive search systems enhanced by social tags and professionally created vocabularies are likely to improve retrieval of high quality health information resources. This work should help health consumers find high-quality information and ultimately achieve better health outcomes.




Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.