Searching and Analyzing Unstructured and Structured Data at Scale with MetiStream Ember and Elastic
In this video, we show you how MetiStream Ember and Elastic can be used together to empower users with the ability to easily search and analyze structured and unstructured healthcare data, like doctors' notes, which have traditionally posed challenges to healthcare organizations' analytics efforts. Using the MIMIC III dataset, we'll demonstrate how Ember's clinical NLP engine can be used to extract clinical concepts and terms from unstructured text in multi-year backlogs at scale to fill in gaps in structured data and provide a fuller view of reality. Once processed, data is opened up for intuitive search by clinical ontologies such as ICD 9 / 10, SNOMED, CPT, LOINC, and RxNorm, surfacing insights many times faster and more consistently than manual chart review can support.
Register to Watch
You'll also receive an email with related content
Michael is a seasoned professional in the data technology space with experience in database operations and disaster recovery. Michael is now a Solution Architect at Elastic where he works with customers on architecting real-time data ingest, search, and analytics solutions using the Elastic Stack.
Nathan Salmon is MetiStream's Chief Architect and visionary for Ember, an intuitive machine learning solution leveraging Elastic, FHIR and Spark. He brings deep domain expertise in healthcare from his early career at Cerner and extensive experience in big data technologies such as Spark, Kafka, Solr and HBase. Nathan has architected and implemented streaming, search, analytics and storage solutions for companies such as Cerner, Rush University Medical Center, Global Wireless Solutions, Evariant and Bose Corporation. As a contributor to Open Source projects such as Samza and Impala and a regular speaker at many technology meetups, he is passionate about Open Source and regularly gives back to the community. Nathan is also an amateur ping-pong champ, avid musician and can share jokes in Japanese.