‘Nurses-in-the-loop’: Narrative Note Extraction, Assessment and Consensus

Presentation Time: 08:36 AM - 08:48 AM

Abstract Keywords: Nursing Informatics, Artificial Intelligence, Natural Language Processing, Human-computer Interaction, Information Extraction
Working Group: Nursing Informatics Working Group
Primary Track: Applications
Programmatic Theme: Clinical Informatics

This study describes a 'nurses-in-the-loop' methodology for selecting narrative nursing notes to train artificial intelligence (AI) systems. Expert nurses evaluated notes from adult falls and neonatal intensive care unit patients using a modified quality instrument across four iterative rounds. The process, involving two academic medical centers, identified 393 salient notes for natural language processing model development. The study highlights the importance of nursing expertise and understanding documentation nuances for effective AI integration with nursing data.

Speaker(s):
Kimberly Powell, PhD, RN, FAMIA
University of Missouri - Columbia

Author(s):
Julie Vignato, PhD, RN, RNC-LRN, CNE - University of Iowa College of Nursing; Anna Krupp, PhD, MSHP, RN - University of Iowa, College of Nursing; Jaewon Bae, PhD, RN - University of Iowa; Jemmie Hoang, BS, RN - University of Iowa; Baris Karacan, BS, MS - University of Illinois, Chicago; Karen Dunn Lopez, PhD, MPH, RN, FAAN - University of Iowa College of Nursing;