Thursday, August 21, 2014
08:30 AM - 11:45 AM
|Level: ||Technical - Intermediate|
Interoperability of electronic healthcare information remains an enormous challenge in spite of the many standards and the "meaningful use" incentives that have been adopted over the years. The problem is complex but not unique to healthcare: information resides and continues to rapidly grow in a bewildering variety of vocabularies, formats and systems in thousands of organizations. This makes the interoperable exchange and integration of healthcare information exceedingly difficult. It inhibits access to complete and accurate patient data, undermines the key advantage of having patient data in electronic form, and drives up the already high cost of healthcare.
Last year's workshop on "RDF as a Universal Healthcare Exchange Language" explored the possibility of using RDF as a basis for semantic interoperability of healthcare information. It concluded with a group declaration known as the "Yosemite Manifesto", which has accumulated nearly 100 signatures from a wide variety of experts endorsing RDF as the "best available" candidate for achieving this goal of interoperability: http://YosemiteManifesto.org/
This year's workshop expands on these principles, presents updates on a variety of projects, and will announce the creation of the Yosemite Project, whose mission is to address the full problem of healthcare information interoperability and articulate a realistic roadmap for solving this problem through RDF and related Semantic Web standards.
Included in this workshop:
[8:30] RDF as a Universal Healthcare Exchange Language -- David Booth An introduction to the Yosemite Manifesto and the use of RDF as a universal healthcare exchange language.
[8:55] Why RDF? -- David Booth This session briefly explains why RDF is the "best available candidate" for use as a universal healthcare exchange language.
[9:10] The Ideal Medium for Health Data? A Dive into Lab Tests – Conor Dowling Lab tests and results have many dimensions from substances measured to timing to the condition of a patient. This presentation will show how RDF is the best medium to fully capture this highly nuanced data.
[9:30] Introduction and RDF Representation of Fast Healthcare Interoperability Resources (FHIR) for Clinical Data – Josh Mandel I'll provide a lightning tour of FHIR, an emerging clinical data standard, with a focus on its resource-oriented approach, and a discussion of how FHIR intersects with the Semantic Web. We'll look at how FHIR represents links between entities; how FHIR represents concepts from standards-based vocabularies; and how a set of FHIR instance data can be represented in RDF.
[9:45] Transformations for Integrating VA data with FHIR in RDF – Rafael Richards The VistA EHR has its own data model and vocabularies for representing healthcare data. This session describes how SPARQL Inference Notation (SPIN) can be used to translate VistA data to the data represented used by FHIR, an emerging interchange standard.
[10:30] Achieving Clinical Knowledge Convergence and Interoperability – Claude Nanjo In this presentation, we will discuss ways to expose clinical knowledge as OWL and RDF resources on the Web in order to promote greater convergence in the representation of health knowledge in the longer term. We will also explore how one might rally and coordinate the community to seed the Web with a core set of high-value resources and technologies that could greatly enhance health interoperability.
[10:50] Data-Driven Biomedical Research with Semantic Web Technologies – Michel Dumontier In this presentation, I will explore the use of Semantic Web technologies to reduce the overwhelming burden of integrating clinical data with public biomedical data, and enabling a new generation of translational research and their clinical application.
[11:15] The Yosemite Project: A Roadmap for Healthcare Information Interoperability -- David Booth This session announces the Yosemite Project, whose mission is to achieve semantic interoperability of all structured healthcare information through RDF as a common semantic foundation. It explains the rationale and technical strategy of the Yosemite Project, and describes how RDF and OWL address both prongs of semantic interoperability: facilitating standards convergence whenever possible and translation when necessary, through sharable data transformations. It concludes with a panel discussion of perspectives, remaining challenges and next steps.
David Booth is an independent consultant and senior software architect at both Hawaii Resource Group and Rancho BioSciences, using Semantic Web technology to make healthcare and biomedical data interoperable between diverse systems. He previously worked at KnowMED, using Semantic Web technology for healthcare quality-of-care and clinical outcomes measurement, and at PanGenX, applying Semantic Web technology to genomics in support of personalized medicine. Before that he worked on Cleveland Clinic's SemanticDB project, which uses RDF and other semantic technologies to perform cardiovascular research. Prior to that, he was a software architect at HP Software, where his primary focus was emerging technologies. He was a W3C Fellow from 2002 to 2005, where he worked on Web Services standards before becoming involved in Semantic Web technology. He has been programming for many years using a variety of programming languages and operating systems. He holds a PhD in Computer Science from UCLA.
Josh is a physician and software engineer interested in improving clinical care through information technology. After earning an S.B. in computer science and electrical engineering from the Massachusetts Institute of Technology and an M.D. from the Tufts University School of Medicine, he joined the faculty of the Boston Children's Hospital Informatics Program and Harvard Medical School, where he serves as lead architect of the SMART Project (http://smartplatforms.org). Josh has a special interest in tools and interfaces that support software developers who are new to the health domain.
Dr. Michel Dumontier is an Associate Professor of Medicine at Stanford University in the Stanford Center for Biomedical Informatics Research. His research focuses on methods to integrate large, heterogeneous clinical and biomedical data for discovery. His research interests include (1) developing novel therapeutics for rare and complex diseases, (2) elucidating the mechanism of drug-induced side-effects, and (3) optimizing multi-drug therapies to minimize undesirable side effects.
Claude Nanjo is a Software Architect at Cognitive Medical Systems. He is also an active contributor to a number of HL7 and S&I clinical modeling initiatives including Health eDecision (HeD), the Clinical Quality Framework (CQF), and Fast Health Interoperable Resources (FHIR). At both Cognitive Medical Systems and Zynx Health, Claude has been involved in a number of research projects exploring the intersection between Clinical Decision Support and the Semantic Web. Prior to joining Zynx Health, Claude was engaged in research developing machine learning solutions to mine information on the Web. Claude studied at the University of California where he obtained a B.S. in Biochemistry, a B.A. in History as well as a Masters degree in Public Health and African Area Studies.
Rafael Richards is a Physician Informatician in the Office of Informatics and Analytics at the Department of Veterans Affairs. Prior to this Dr. Richards was an Assistant Professor in the Division of Health Science Informatics and Department of Anesthesiology at Johns Hopkins University. Rafael's current interests and activities are in data standards, medical device data integration, and modernizing VA databases to enable enterprise data federation with Linked Data sources.
Prior to medicine, Rafael earned as B.S. Engineering from Swarthmore, M.S. Applied Mathematics from Lehigh University, and worked several years in industry in scientific software applications with IBM and in the UK office of Wolfram Research on Mathematica. Rafael is currently an invited expert in the Semantic Web in Healthcare and Lifesciences of W3C.
Conor Dowling is the CTO of Caregraf, which uses Semantic Web technologies to help health-care providers gather and analyze the information they create during the course of a patient’s care. He is a specialist in clinical-data analytics with a focus on how the definition of clinical know-how and institutions shapes the description of patient care.