Eur Arch Paediatr Dent. 2026 Jun 23. doi: 10.1007/s40368-026-01241-8. Online ahead of print.
ABSTRACT
PURPOSE: Paediatric dental anxiety remains a significant challenge in clinical practice, often impacting co-operation and treatment outcomes. This randomised controlled trial compares the anxiety-reducing effects of AI-based self-modelling versus standard video modelling.
METHODS: A single-blind, parallel-arm randomised controlled trial was conducted on 80 children aged 6-12 years requiring restorative dental treatment. Participants were randomised into two groups. Dental fear and anxiety were assessed using CFSS-DS and MCDASf, along with pulse and heart rate monitoring. Data were collected pre- and post-intervention by a blinded assessor and statistically analysed.
RESULTS: Both groups showed significant within-group reductions in dental fear and anxiety (p < 0.001); however, no statistically significant between-group difference was observed for the primary outcome (CFSS-DS). The AI-based personalised video self-modelling app group demonstrated a greater reduction in heart rate (7.65 vs. 2.18 bpm), with a significant between-group difference (p < 0.001; Cohen’s d = 0.89), indicating reduced short-term physiological arousal rather than overall superiority of the intervention and specific anxiety parameters, particularly related to injections and dental examinations. Intergroup analysis revealed a large effect size for heart rate (Cohen’s d = 0.89) and moderate-to-large effects for selected anxiety items with some item-level differences observed. However, overall CFSS-DS score differences between groups were not statistically significant.
CONCLUSION: Both interventions were effective in reducing dental fear and anxiety. However, no superiority was demonstrated for the primary psychological outcome. The AI-based personalised intervention showed greater reduction in physiological arousal (heart rate), suggesting potential benefits in short-term anxiety modulation.
PMID:42334822 | DOI:10.1007/s40368-026-01241-8
