How can federated FHIR systems handle patient identity and record linkage effectively? What are the challenges of managing patient data across distributed systems, and what strategies can be used to ensure accuracy and consistency? How do these approaches impact interoperability in healthcare?
In this webinar, experts explore the complexities of federated patient identity management and record linkage in FHIR. They discuss real-world solutions, best practices, and tools to address these challenges, offering valuable insights for healthcare organizations working towards seamless data integration.
How to manage longitudinal and consistent patient records, avoid duplicates and improve data quality? Link or merge patient data? What is federated FHIR?
Watch the video to hear from experts like Grahame Grieve, Dean Resnick, Thomas Myers, and Christopher Oakman who are making data federation work better in real life – and the lessons they've learned.
Grahame will discuss the issues involved in providing federating FHIR Servers that represent data from multiple source systems, and make clear the kind of challenges that implementers will have to deal with.
Grahame Grieve is HL7's Product Director for "FHIR" - the leading healthcare data exchange standard of the future. Grahame has a background in laboratory medicine, software vendor development, clinical research, open source development and has also conceived, developed and sold interoperability and clinical document solutions and products in the Australian market and around the world.
• Types of linkages and standard methods used for them
• Use of machine learning approaches within them
• Computing considerations for deployment
Mr. Resnick has been working on data analysis and statistical programming for at least several decades. For more than 10 years he worked at the U.S. Census Bureau in the administrative record area. During this period, he developed a SAS based record-linkage module for high-volume linkages that is still being used at the Bureau. At NORC, much of his work is focused on record linkage and he has developed (in collaboration with colleagues) a new SAS-based record linkage package that incorporates the E-M algorithm and several enhanced strategies for improving the quality of record linkage analyses.
Probabilistic record linking can be a powerful technique to identify similar pieces of data within a large dataset. In this talk, we will cover some record linking basics and then use the Fellegi-Sunter method to match some records using Clojure.
Chris Oakman is an open source developer, educator, and software engineer who has been programming for nearly 20 years. He is the author of many open source libraries including chessboard.js, the ClojureScript Cheatsheet, several Parinfer implementations, and more. In 2021 he taught a coding bootcamp class on ClojureScript and gave a presentation on Hospital Record Linking at Clojure/conj 2019. He lives in The Woodlands, TX and works at Treasury Prime.
• Real World Federation of Patient Record repositories
• Single Best Record Identification – Automatic and manual
• Use cases for hierarchical source longitudinal record Anonymization
Tom is currently the Global Vice President, Solution Consulting for Lyniate, and has more than 15+ years of experience in the HealthCare space with an emphasis on applying technical solutions to real-world clinical challenges ranging from radiology archive curation for AI/ML research training through complex interoperability solutions in the Cloud at a global scale.
Nikolay will host the event and generally create a welcoming environment for invited guests and speakers.
Nikolai is a CTO at Health Samurai and technical leader of the Aidbox FHIR Platform with more than 15 years of experience in healthcare IT. Since 2012, it has been actively contributing to the FHIR standard and popular open-source projects like Fhirbase and FHIR.js. Author of the FHIR-first development approach and regular speaker of FHIR events.
Aidbox is a developer-friendly FHIR platform where everything remains under your control. Build your enterprise-grade digital healthcare apps and systems using a habitual tech stack and suitable cloud infrastructure: Google, Azure, AWS, or on-premises.
// Read More
