A Path to Real-World Evidence in Critical Care Using Open-Source Data Harmonization Tools

Area of Science:

• Critical care medicine
• Health informatics
• Data science

Background:

• The COVID-19 pandemic underscored the necessity of real-world data (RWD) for timely clinical, research, and policy applications in critical care.
• Analyzing RWD is increasingly vital for informing policymakers and regulators, but extracting high-quality data from electronic health records (EHRs) demands significant infrastructure and resources.

Purpose of the Study:

• To customize publicly available tools for harmonizing RWD from EHRs, covering data quality assessment, de-identification, and generation of data science-ready datasets.
• To make these harmonized RWD accessible to clinicians and researchers via the CURE ID platform.

Main Methods:

• Customization of existing public tools to support the entire RWD harmonization pipeline from EHRs.
• Implementation of data quality assessments and de-identification procedures.
• Integration of processed RWD into the CURE ID platform for accessibility.

Main Results:

• Successful customization of tools enabling the generation of robust, data science-ready RWD from EHRs.
• Establishment of a collaborative process involving the National Center for Advancing Translational Sciences (NCATS) and the Food and Drug Administration (FDA).
• Facilitation of access to challenging clinical case reports and repurposed treatments through the CURE ID platform.

Conclusions:

• The collaborative effort successfully created a system for generating and disseminating high-quality RWD from EHRs for critical care.
• This initiative enhances the utility of RWD for clinical decision-making, research, and policy development, with potential for broader impact.
• Future directions include expanding the scope and utility of the CURE ID platform and the underlying RWD infrastructure.