Nudge theory proposes using subtle interventions to encourage individuals to make better decisions. The aim of this study was to evaluate the effectiveness of the Nudge theory in plaque control and assess caries experience among third-grade primary schoolchildren with refugee and immigrant backgrounds in Mashhad, Iran. Moreover, Afghan and Iranian schoolchildren were compared to assess differences in oral health outcomes. A quasi-experimental field trial was conducted in three public primary schools, comprising 309 participants approximately 9 years old. Interventions were randomly assigned to three schools: School I Messages based on Social Norms (MSN), School II Messages based on Fear of Negative Outcome (MFNO), and School III control group (C). MSN and MFNO received customized motivational video clips at baseline, while C only received Oral hygiene instruction (OHI). All participants received OHI, a brush, and toothpaste. Baseline plaque index (PI) and caries experience in primary and permanent dentition (dmft/DMFT) were recorded. PI was reassessed at two weeks, two months, and six months post-intervention. All data were subjected to statistical analysis. The mean PI decreased significantly in all three groups at the two-week follow-up (p < 0.01). The PI improvements declined over a six-month follow-up period in all groups, and the mean PI difference after six months compared to the pre-intervention was significant only in MSN and MFNO (p < 0.01), while C reverted almost to the pre-study level. Schoolchildren with at least one filled tooth or Iranian nationality showed a greater PI reduction (p < 0.01, p = 0.05). The overall mean ± SD dmft and DMFT were 4.24 ± 2.11 and 1.70 ± 1.24, respectively. Among all the examined participants, 32 (10.40%) individuals were caries-free. The mean dmft was statistically significantly higher in Afghan children than in Iranians (p = 0.01). MSN was more effective on PI reduction in the short term, while MFNO was more long-lasting. Using the Nudge theory via visual aids was more effective in motivating children to perform better oral self-care than solely traditional OHI.

Introduction: This systematic review evaluates the stage-specific diagnostic accuracy of artificial intelligence (AI) models for caries detection and compares their performance with human examiners. Methods: Following PRISMA 2020 guidelines, four databases (PubMed/Scopus/Embase/ Web of Science) were searched up to October 2025. Nineteen studies using bitewing radiographs and reporting at least one diagnostic metric stratified by lesion stage (E1–D3, or equivalent) were included. Data extraction included model architecture, dataset characteristics, annotation, and stage-specific outcomes. Risk of bias was assessed using QUADAS-AI. Due to heterogeneity in staging systems (binary, ICDAS, ICCMS) and reported metrics, a narrative synthesis was conducted. Results: AI models, especially YOLO variants, U-Net architectures, and ResNet classifiers, demonstrated consistently high sensitivity for early enamel lesions, often outperforming human examiners. Across the 19 included studies, 17 reported stage-specific outcomes for enamel and 18 for dentin lesions, with 10 studies providing direct AI–human comparisons. For moderate and advanced dentin lesions, AI performance was comparable or superior, with strong F1-scores, high AUC, and low false-negative rates, although specificity was less consistently reported. QUADAS AI identified a high risk of bias in at least one domain in 14 studies due to patient selection, insufficient blinding, and limited external validation. Conclusion: AI systems show promise as adjunctive tools for stage specific caries detection on bitewing radiographs. They may support identification of early enamel lesions, although performance remains variable. Evidence certainty was limited by heterogeneity and methodological bias. Standardized reporting, external validation, and unified lesion depth criteria are required before clinical integration.