Decision-tree analysis for predicting first-time pass/fail rates for the NCLEX-RN in associate degree nursing students

24^th Global Nursing & Healthcare

March 01-02, 2017 Amsterdam, Netherlands

Hsiu Chin Chen

Utah Valley University, USA

Posters & Accepted Abstracts: J Nurs Care

Abstract :

Success in the nursing program is the first step to qualify for taking the National Council Licensure Examination-Registered Nurse (NCLEX-RN). The NCLEX-RN evaluates the knowl�¬edge and skills of nursing graduates for being new nurses. Pass�¬ing the NCLEX-RN in the United States is a critical outcome of the nursing program. Little evidence shows the use of decision-tree algorithms in identifying predictors and analyzing their associations with pass and fail rates for the NCLEX-RN�® in associate degree nursing students. This longitudinal and retrospec�¬tive cohort study investigated whether a decision-tree al�¬gorithm could be used to develop an accurate prediction model for the studentsâ�� passing or failing the NCLEX-RN. This study used archived data from 11 cohorts (N=453) of associ�¬ate degree nursing students in a selected program in the USA. Collected retrospective archived data included demographic information, pre-admission GPA, scores on the Test of Essential Academic Skills (TEAS) examination for entering into the nursing school, each semesterâ��s cumulative GPAs for nursing courses, ATIâ��s RN Comprehensive Predictor scores, and pass or fail for the first attempt on the NCLEX-RN. Any identifying information was removed before data entry and analysis. The Chi-Squared Automatic Interaction Detection (CHAID) analysis of the decision trees module was used to examine the effect of the collected predictors on passing/failing the NCLEX-RN. The CHAID is an analysis that can use a series of merging, splitting and stopping steps based on user-specified criteria to determine how independent variables best combine to explain the outcome in a given dependent variable. The actual percentage scores of Assessment Tech�¬nologies Institute�®â��s RN Comprehensive Predictor�® accu�¬rately identified students at risk of failing. The classification model correctly classified 92.7% of the students for passing. This study applied the decision-tree model to analyze a sequence database for developing a prediction model for early remediation in preparation for the NCLEX-RN.

Biography :

Email: chenhs@uvu.edu