Jennifer Zaino
SemanticWeb.com Contributor

Just as President Obama has set his sights on using technology to improve health care, the European Union also sees value in using technology in its efforts toward electronic medical record interoperability.

In January, the SemanticHealth project, a support action funded by the Union’s 6th R&D Framework Programme, published its semantic interoperability research and deployment roadmap for electronic health record systems. The goals of the long term road map are fairly ambitious: “identify key steps towards realizing semantic interoperability across the whole health value system, thereby focusing on the needs of patient care, biomedical and clinical research as well as of public health through the re-use of primary health data.”

The challenges at the heart of the electronic health record interoperability agenda are achieving not only regional and national levels of interoperability, but interoperability across the entire EU – the latter being a challenge the report’s authors admit could take decades before being fully resolved. Semantic interoperability is defined by the report as addressing issues of how to best facilitate the coding, transmission and use of meaning across health services, among all parties in the chain from providers to patients to researchers.

That last is interesting, as society often thinks of e-health records as a way for providers to better collaborate about patient care. But patient information in aggregate can be used by public health officials or researchers to help drive quality assurance or policy recommendations, among other things. Moreover, linking patient data to existing research findings may lead to “the discovery of new knowledge from semantically coherent EHR repositories,” the report states.

What does full semantic interoperability look like — accounting for differences in language that might otherwise impede patient care across European countries’ borders? The report presents an interesting picture. When interoperability is available at the technical and syntactical level, a patient from Ireland who falls ill in Spain may benefit from having his doctors there receive existing electronic records from his physician at home, but that benefit is curtailed if no one at the Spanish hospital speaks English. Attaining partial semantic interoperability, where some fragments of data such as allergies, past diagnosis and so on are encoded using international coding schemes, means that a hospital information system can automatically detect, interpret and present that data such that an attending physician in Spain could make sense of it, whether or not he speaks the language the original documents were written in.

At the highest level, semantic interoperability across heterogeneous hospital electronic record systems means that the Spanish hospital information system is able to automatically access, interpret and present all necessary medical information about the patient to the physician at the point of care, stymied neither by language nor technological differences. Additionally, the data (anonymous, of course) could then become part of aggregate health records information. Speeding the collection of and access to this aggregated data, nationally and across borders, should help to lower the costs of providing health care, especially as it relates to quickly identifying the outbreak of epidemics or other major health problems.

“Interoperability requires agreement on meanings and labels for those meanings – on ontologies and lexicons, which together we label as terminologies,” the report notes. “The primary goal of ontologies and terminologies for interoperability is to enable the faithful exchange of meaning between machines and between machines and people.”

Work on terminologies, the report concludes, should begin where there is general consensus on content and need, such as adverse drug reactions. In fact, attaining semantic interoperability at the highest level may not even be practical, with the report suggesting that the focus be placed on specific areas of clinical practice that are known to be of high patient safety risk, and in priority areas for which the evidence is strongest for a gap to be bridged between current and good practice. These include: New medication prescriptions requiring information on concurrent medication and details of known allergies and conditions; reminders and prompts for overdue or overlooked health care actions and interventions; the use of clinical guidelines and other forms of evidence to determine the optimal management strategy for a given patient; and care coordination, ensuring that a high-level view can be taken of distributed care to protect against duplication, delay and incompatible interventions.

Interestingly enough, though, the report notes that technical standardization is no longer the most prominent issue in delivering on this vision of semantic interoperability. Indeed, over-spending on semantic interoperability technology may result in unwieldy and ultimately higher cost, lower-return approaches.

Similarly, lack of active policy interventions can be equally hazardous, leading to a state of market lock-in where health care providers wind up reliant on specific niche systems that are difficult to integrate and impede innovation. Most importantly, however, is the bedrock of human trust that has to be the foundation of these efforts — the idea that patient information must be confidential, secure, and accessible only by trusted parties. Without that, semantic health record interoperability will never get close to being realized.

SemTechBiz is Less Than 2 Weeks Away

The Semantic Tech & Business Conference (SemTechBiz) is coming to San Francisco on June 3-7! Join us for case studies, innovative panels, tutorials, and keynotes that will provide you with practical advice, hands-on guidance, and breakthrough approaches to solving business problems with semantic technology. Passes go up $200 at the door. Sign up now and save !