CONCERN Early Warning System: Nurse-Driven AI | Dr. Sarah Rossetti

Dr. Sarah C. Rossetti presents the CONCERN Early Warning System, a machine learning model that predicts patient deterioration from patterns in nursing surveillance documentation. Recorded September 29, 2026, as part of the NKBDS DIVE Journal Club webinar series. Read the trial: https://doi.org/10.1038/s41591-025-03... Rossetti SC, Dykes PC, Knaplund C, et al. Real-time surveillance system for patient deterioration: a pragmatic cluster-randomized controlled trial. Nat Med. 2025. When nurses sense that a patient is deteriorating, their documentation changes before the vital signs do. More frequent checks, additional notes, entries outside expected intervals. CONCERN treats that surveillance behavior as a measurable signal and uses it to flag patients at risk. In a multi-site pragmatic cluster-randomized trial across four hospitals, the system was associated with a 35.6% reduction in the instantaneous risk of in-hospital death and an 11.2% decrease in length of stay. ABOUT THE SPEAKER Sarah C. Rossetti, RN, PhD, FACMI, FAMIA, is an Associate Professor of Biomedical Informatics and Nursing at Columbia University and an experienced critical care nurse. She co-leads the CONCERN study, chairs AMIA's 25x5 Task Force to Reduce Documentation Burden, and is a recipient of the Presidential Early Career Award for Scientists and Engineers. MODERATORS Janet Northcote, PhD, RN, University of Florida Ragnhildur Bjarnadottir, MPH, PhD, RN, FAMIA, Mayo Clinic ABOUT NKBDS DIVE The Data, Informatics, and Visions Exchange (DIVE) Journal Club is a free webinar series from the Nursing Knowledge Big Data Science initiative, bringing researchers and practitioners together around emerging work in nursing data science and AI. Website: z.umn.edu/bigdata Contact: dive.jc.nkbds@gmail.com Next webinar: February 2027, with Dr. Stephen Motew, President and CEO of the UF Health clinical enterprise, on implementing AI at scale across a health system. 0:00 Welcome and introductions 2:42 Introducing Dr. Sarah Rossetti 4:02 CONCERN Early Warning System 12:55 Methods - Building the CONCERN model 18:54 Results - The Clinical Trial 26:43 Discussion - Implementation 38:36 Q&A 57:34 Closing