Health care field is fertile ground for semantic tech

Domain may also fuel adoption in the National Information Exchange Model

The health care domain featured one of the earliest uses of semantic technology in the public sector -- and it could also fuel adoption in the National Information Exchange Model.

Back in 2004, the Situational Awareness and Preparedness for Public Health Incidents Using Reasoning Engines (SAPPHIRE) system rolled out with infrastructure based on semantic Web technologies. The University of Texas Health Science Center at Houston spearheaded the effort. Although SAPPHIRE is no longer funded, the center applies what it learned to other interoperability problems. In one project example, SAPPHIRE-based technology enables distributed data collection for disaster preparedness, noted Dr. Parsa Mirhaji, assistant professor of biomedical informatics at the center.


Related coverage:

Is government ready for the semantic Web?

It's all semantics: A glossary of machine-to-machine communications


As for NIEM, the health care community may end up being among the first groups that require greater use of semantics. Michael Daconta, CTO at Accelerated Information Management, said the federal government’s "meaningful use" directive, which focuses on the adoption of electronic health records, calls for decision support. That thrust will likely spark interest in semantic technologies.

“By its nature, decision support starts pushing you toward these technologies,” he said.

But some data integration efforts in health care don’t immediately plan to tap semantic technology. The National Institutes of Health’s National Database for Autism Research  (NDAR) and the Simons Foundation Autism Research Initiative are working to link autism research datasets using global unique identifiers (GUIDs). The project was described last year in the biomedical and health informatics journal Journal of the American Medical Informatics Association (JAMIA).

Matthew McAuliffe, chief of the Biomedical Imaging Research Services Section and NDAR project science manager at NIH, said semantic technology isn’t featuring in its GUID approach. McAuliffe, one of the authors of the JAMIA article, said he may consider NIEM, however.

NIEM, he said, “does look interesting and I plan on looking into it to see if there [is] any use for the model in NDAR.”

About the Author

John Moore is a freelance writer based in Syracuse, N.Y.

Reader Comments

Wed, Mar 23, 2011 David Loshin

I suspect that prior to employing electronic health records for decision support purposes we might consider the fact that there don't seem to be too many defined standards for persisting and then sharing the "structured data" insisted upon by the objectives. I have more to say about this in a longer note at http://bit.ly/gpeqvq - check it out there.

Wed, Mar 23, 2011 Richard Ordowich Princeton NJ

I suggest the National Cancer Institute's Data Standards registry and repository along with its governance framework is the best example of "semantics by design". NCI's DSR responds to the needs of a broadly based global community to facilitate the sharing of critical data.

This is a working example of what it takes to create a semantically rich environment for data. It’s not evident that this rigor has been applied to other data domains and until such time, the use of semantics will be limited to searches as provided by algorithms such as Google.

Sat, Mar 19, 2011 Jeremy Engdahl-Johnson New York, NY

Federal funding may be encouraging a move toward EHR, but there's more to it than just installing systems. How can healthcare data pooling lead to a better system? More at http://www.healthcaretownhall.com/?p=2193

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above