Development of a prediction model for early diagnosis of not passing the national council of licensure examination for registered associate degree nurses.

Passing the national licensure examination for registered nurses (NCLEX-RN) in the US is a critical outcome of the nursing program. Research has been conducted to identify which nursing students are at risk for not passing the NCLEX-RN test. The purpose of this study was to investigate whether any of several student covariates can be used to accurately identify associate in science in nursing (ASN) students that are at-risk for failing the NCLEX-RN test. Covariates included in the study were demographics, students' pre-admission grade point average (GPA), the scores of test of essential skills (TEAS), and the assessment technologies institute® (ATI)'s comprehensive scores for a pre-RN examination test. Chi-squared automatic interaction detection, or CHAID analysis, was used to develop the model. One covariate, ATI comprehensive test scores, was found to accurately identify all at-risk ASN students. The model explained that students identified as "at-risk" had a failure rate nearly two-and-a-half times as high as the general population.