Artificial Intelligence Assisted Teaching of Structured Nursing Care According to ERAS Protocol

Overview

This study provides an original contribution to the literature by structuring nursing care for gyneco-oncology patients according to the ERAS protocol and delivering it through AI-assisted, case-based education. This randomized controlled, fully experimental study was conducted in the second semester of the 2024-2025 academic year with third-year students who had successfully completed the Obstetrics and Gynecology Nursing course at the Faculty of Health Sciences, Department of Nursing, at a state university located in western Turkey. Seventy students participated in the study and were assigned to either the AI-assisted case-based education group or the control group using block randomization. Data were collected using the ERAS Protocol Nursing Care Knowledge Test and the Multidimensional 21st Century Skills Scale. All statistical analyses were conducted using IBM SPSS Statistics (Version 27) and the PROCESS macro (Version 4.2) developed by Hayes. Descriptive statistics were used to summarize demographic variables and baseline characteristics. Group equivalence at baseline was assessed using independent samples t-tests for continuous variables and chi-square tests for categorical variables. Effect sizes were calculated using Cohen's d and Cramér's V, as appropriate. To examine the effect of the intervention on 21st-century skills, a mixed-design ANOVA was performed with time (pretest, posttest) as the within-subjects factor and group (intervention, control) as the between-subjects factor. Partial eta squared (η²) was reported as a measure of effect size for within- and between-subjects effects. An independent samples t-test was also used to compare posttest knowledge scores between the groups. To explore the mechanisms underlying the effect of the intervention on knowledge acquisition, mediation and moderation analyses were performed using PROCESS Models 4 and 1, respectively. In the mediation model, the change in 21st-century skills (posttest-pretest difference) was tested as a mediator. In the moderation model, academic achievement was examined as a moderator of the group-knowledge relationship. Both models controlled for academic achievement where applicable. Statistical significance was set at p \< .05, and 95% confidence intervals (CI) were reported for all relevant estimates.