Soojin Park, MD: No relevant financial relationship(s) to disclose.
The Speaker in this session will discuss tools and approaches for large-scale data extraction and harmonization from clinical ICU databases. Examples such as MIMIC and the CHoRUS Bridge2AI datasets will be utilized.
In this session, the speaker will provide a overview of various tools and techniques used to gain a better understanding of data and extract valuable insights from clinical ICU databases. The speaker will delve into the example of the Bridge2AI CHoRUS (Collaborative Hospital Repository Uniting Standards). CHoRUS is a newly developed data enclave that contains de-identified electronic health records, waveforms, and imaging of patients admitted to the ICU, making it a valuable resource for researchers and healthcare professionals.
The speaker will showcase the data elements in the CHoRUS dataset including vital signs, laboratory results, medications, waveforms, and imaging. The speaker will highlight approaches to extract trustworthy information from datasets of this type such as robust and fair machine learning algorithms.
