Health Search and the Semantic Web

Reading time: 4 – 6 minutes

Before it gets too far behind us, I wanted to write briefly about the Health 2.0 Conference, which was held in San Francisco on October 22 and 23rd. The Health 2.0 Conference focuses on the application of Web 2.0 technologies to the fields of medicine and healthcare. Specifically, I wanted to comment on health search, the semantic web and the demonstration of the health 2.0 service iMedix.

Search engines today rely extensively on keywords. However, with health-related searches, context or meaning takes on great importance. Consider this: a study earlier this summer found that simply replacing the search term “vaccine safety” with “vaccine danger” replaced virtually all accurate search results (out of the first 20) with inaccurate results [1]. Granted, there are several limitations to the study (small sample size, controversial topic), but it nonetheless illustrates how a single keyword can dramatically alter search results.

Frequently, health search results are incomplete, inaccurate or altogether wrong. Indeed, although there is a large amount of reliable health information online, an equal or greater amount of misinformation also exists. Many health seekers have grown accustomed to repeatedly reviewing search results, revising the search criteria and searching again until they find the right keywords that return the desired information. Ultimately, health seekers are faced with determining which sources of information are reliable. One way to confront this issue is to discard the traditional search engine approach based on keywords and use Semantic Web technology.

Semantic Web: an extension of the World Wide Web in which the sematics or meaning of information and services on the Web is defined (i.e. the use of a set of formal rules to express the meaning of data, the properties of objects and the relationships that exist between them), making it possible for the information to be accessible to machines. In the Semantic Web model, data on the Internet contains contextual meaning; search engines can query contextual information to identify the websites related to the desired topic instead of simply returning sites that contain a given keyword(s).

One company embracing Semantic Web technology to improve health search is iMedix. As part of the series on Social Networks and Health, I recently reviewed iMedix at Highlight HEALTH 2.0:

Using medical semantic technology to translate health questions into a series of weighted medical terms, iMedix returns relevant search results from top-rated sources. iMedix CEO and cofounder Amir Leitersdorf presented a demo of the health 2.0 service at the Health 2.0 Conference. The fast-paced iMedix demo (presenters were only alloted 4 minutes for each presentation) provides a nice overview of what happens “behind the scenes” when a question is posted to the iMedix community.

For more articles on Web 2.0 in health and medicine, visit Highlight HEALTH 2.0.

Here’s some additional resources to learn more about the recent Health 2.0 Conference:

Additional Health 2.0 resources are listed in the Highlight HEALTH Web Directory.

References

  1. Kortum et al. The impact of inaccurate Internet health information in a secondary school learning environment. J Med Internet Res. 2008 Jun 30;10(2):e17.
    View abstract
About the Author

Walter Jessen, Ph.D. is a Data Scientist, Digital Biologist, and Knowledge Engineer. His primary focus is to build and support expert systems, including AI (artificial intelligence) and user-generated platforms, and to identify and develop methods to capture, organize, integrate, and make accessible company knowledge. His research interests include disease biology modeling and biomarker identification. He is also a Principal at Highlight Health Media, which publishes Highlight HEALTH, and lead writer at Highlight HEALTH.