Translational research in Artificial Intelligence (AI) for healthcare has long been constrained by the lack of robust, diverse, and accessible data resources. The newly launched CRITICAL dataset addresses this challenge by providing an unprecedented resource to accelerate innovation in critical care and beyond. Funded by National Center for Advancing Translational Sciences (NCATS), and developed through a collaborative effort involving Clinical and Translational Science Award (CTSA) sites at Northwestern University, Tufts University, Washington University in St. Louis, and the University of Alabama at Birmingham, alongside the Massachusetts Institute of Technology, this dataset represents a major advancement in the field.
The CRITICAL dataset offers longitudinal data from approximately 400,000 critical care patients, making it the largest publicly shared, disease-independent benchmarking clinical dataset for critical care research. It provides comprehensive coverage of patient journeys, encompassing pre-ICU, ICU, and post-ICU encounters across both inpatient and outpatient settings. Moreover, it incorporates data from diverse populations across broad geographic regions, enabling the development of equitable and inclusive healthcare solutions.
Presenter
