AI-Driven Decision Thresholds in Cariology: A Systematic Review of Lesion Stage Detection on Bitewing Radiographs

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.