Date of Award
Spring 4-21-2026
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Nursing
First Advisor
Aimee Woda
Second Advisor
Amber Young-Brice
Third Advisor
Jennifer Ohlendorf
Fourth Advisor
Kristina Thomas Dreifuerst
Abstract
This retrospective, descriptive study examined how clinical judgment was demonstrated across two immersive virtual reality simulation (IVRS) experiences in a cohort of Direct Entry Master of Science in Nursing (DEMSN) students using a generative large language model artificial intelligence, ChatGPT, for categorization of clinical judgment cognitive processes. The National Council of State Boards of Nursing (NCSBN) Clinical Judgment Measurement Model (CJMM) guided the study (NCSBN, 2022). Nurse expert-derived CJMM-aligned scoring rubrics were applied to deidentified, developer-generated IVRS performance reports, and ChatGPT categorized whether rubric actions were demonstrated and generated case-level, scored excel files. Total CJMM and cognitive component scores were summarized and converted to percentage scores to support comparisons across IVRS scenarios with different numbers of rubric actions. Within-student analyses examined change between IVRS scenario one and IVRS scenario two, and frequency analyses identified the most and least frequently demonstrated CJMM components. Findings indicated that change was CJMM component-specific and that demonstration patterns varied across students. ChatGPT showed strong utility by providing an efficient, consistent, and reliable method for CJMM-aligned categorization when used with locked rubrics and standardizes prompts. Continued research is needed to replicate findings across settings, refine CJMM rubric representation, examine IVRS scaffolding across additional exposures, and further evaluate AI-assisted scoring agreement and stability over time.