2E: The NEIA Tool: Comparing Human and AI Performance in NCLEX-Style Item Review

Wednesday, September 23 | 3:00 p.m. – 3:45 p.m. 

The NEIA Scoring Tool provides a validated framework for evaluating NCLEX-style exam items across 14 subcategories. This study established content validity via Delphi process and compared human faculty versus AI performance applying the rubric. AI models demonstrated higher reliability (ICC=0.71) and agreement with experts (70%) than individual faculty (ICC=0.32, 47%). Findings support a suggested hybrid AI-faculty workflow for assessment quality assurance.

Presenter: 

Rachel Simms, PhD, DNP, RN, FNP-BC | MGH Institute of Health Professions