Informatics for Integrating Biology and the Bedside (i2b2) Tutorial Introduction



welcome to the i2b2 basic tutorial training in this tutorial we are going to describe the IQ b2 data query tool first we are going to describe the i2b2 system and its data load process then we are going to guide you through the i2b2 interface we will then present two basic case scenarios to demonstrate how to use it what is i2b2 I 2 B 2 is an acronym for informatics for integrating biology and at the bedside I 2 B 2 is an NIH funded National Center for biomedical computing system developed is a scalable informatics framework designed for translational research I to be to was designed primarily for cohort identification allowing users to perform an enterprise-wide search on a de-identified repository to determine the existence of a set of patients meeting certain inclusion or exclusion criteria I to be – helps researchers overcome one of the greatest problems in population-based research rapidly compile large samples of well characterized patients qualified investigators may use the i2b2 web-based query tool to determine the aggregate total number of patients at participating hospitals who meet a given set of inclusion and exclusion criteria the University of Massachusetts Medical School uses the i2b2 software to store the clinical data on all patients served by the UMass Memorial HealthCare hospitals in ambulatory care offices the school data warehouse is known as my card my card is an acronym for Massachusetts integrated clinical academic research database the my card research data warehouse is a repository that integrates patient information from multiple sources that information is categorized as ontology z' my card ontology is include demographics icd-9 diagnosis CPT and ICD 9 coded procedures insurance medications laboratory results HCPCS vitals and biorepository samples investigators can perform an initial analysis on the de-identified cohort and if the results are promising they can request approval from the IRB for a fully identified extract clinical data sources include payer information IDX laboratories and hl7 messages providers and clinical information from the hospital systems all scripts and saurian are loaded into the my car data warehouse the data is loaded into a server installed in a restricted area designed primarily to protect patients data from unauthorized access all data is processed in the tied ETL server where the data is aggregated cleaned and standardized to create the i2b2 data trust the data is then mapped to the i2b2 ontology and de-identified to populate the my card I to be to data Mart a copy of the de-identified data Mart is loaded into a public server where users can access the data using the i2b2 query tool

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *