Abstract
BACKGROUND: There is a high prevalence of short video addiction (SVA) among Chinese nursing students. This study was aimed at establishing a risk prediction model for SVA among this population. METHODS: Two rounds of cross-sectional survey were performed, with 620 nursing students from Jinzhou included in T1 (July 2024) survey to perform model establishment and internal validation, and 293 nursing students from Guangzhou included in T2 (February, 2025) survey to perform external validation. Participants were invited to complete a panel of questionnaires to measure SVA using the Short Video Addiction Scale (SVAS) and 22 candidate SVA predictors. A visual nomogram was plotted and its performance was evaluated using area under the receiver operating characteristics curve (AUC), calibration curve and decision curve analysis (DCA). A sex-based subgroup analysis was also conducted. RESULTS: A 31.3% SVA prevalence was revealed among Chinese nursing students. Academic stress, social interaction anxiety, sleep disorders, depressive symptoms, anxiety symptoms, and whether from a single-parent family were identified as significant factors for SVA nomogram construction. The nomogram performed well in the training cohort, internal validation cohort, and external validation cohort as evidenced by the AUC (0.809, 0.831, and 0.839, respectively), calibration curves and DCA curves. Subgroup analysis showed that this model performed well in both male and female nursing students. CONCLUSION: Our present study developed a predictive nomogram for SVA among Chinese nursing students via integration of six salient predictors, including academic stress, social interaction anxiety, sleep disorders, depressive symptoms, anxiety symptoms, and whether from a single-parent family. This nomogram is potentially useful for universities and educators in identifying nursing students more likely to develop SVA and in developing tailored preventive interventions to reduce the prevalence of this condition.