Applications of artificial intelligence in the analysis of alveolar clefts: a scoping review

Abstract

Background Alveolar clefts are a prevalent clinical manifestation of cleft lip and palate (CLP), and are typically managed with secondary alveolar bone grafting (SABG) during mixed dentition. Nonetheless, considerable variability in the morphology and volume of the defect influences graft material choice and surgical timing, necessitating accurate imaging. Artificial intelligence (AI) can automate qualitative classification and quantitative measurement, yet its application in this field remains at an early stage of development. The purpose of this scoping review is to explore the application of AI in the analysis of alveolar clefts. Materials and methods This scoping review was conducted in adherence to the PRISMA-ScR guideline, and supplemented by the methodological approach proposed by Arksey and O’Malley and the Joanna Briggs Institute (JBI). A comprehensive electronic search was performed in four databases (PubMed, Web of Science, Scopus, ScienceDirect). The inclusion criteria were clinical trials and studies, journal articles, conference papers, case reports and book chapters assessing the application of AI in this field. A descriptive analysis was performed based on study objectives, samples, clinical designs, AI tools for analysis, and existing limitations. Results The initial electronic search in databases yielded 373 records, and after selection and removal, 10 published studies were included in the review eventually. This scoping review categorised the included studies into two main categories: qualitative classification, which included 2 articles, and quantitative measurement, which included 8 articles. Conclusions AI technology offers perspectives for addressing issues related to the qualitative and quantitative analysis of alveolar clefts. Preliminary studies have shown promising feasibility, with improved predictive accuracy and efficiency in individual studies. Though the generalisability of AI performance is still limited by small datasets and heavy reliance on data augmentation, these findings provide a foundation for future exploration. Clinical relevance Accurate evaluation of alveolar cleft morphology and graft volume is essential for planning and assessing secondary alveolar bone grafting, and also provides critical information for both pre- and postoperative orthodontic management. AI-assisted analysis may enhance measurement consistency and reduce manual burden, but further validation is required before clinical adoption.