Influence of Artificial Intelligence-Driven Diagnostic Tools on Treatment Decision-Making in Early Childhood Caries: A Systematic Review of Accuracy and Clinical Outcomes.

Abstract

Early detection and accurate prediction of the risk of early childhood caries (ECC) are essential for effective prevention and management. This systematic review aims to assess the performance and applicability of machine learning algorithms in ECC prediction and detection. A comprehensive search was conducted to identify studies utilizing machine learning algorithms to predict or detect ECC. The included (n = 6) studies demonstrated high accuracy, sensitivity, specificity, and area under the receiver operating characteristic (AUC) values related to predicting and detecting ECC. The application of machine learning algorithms contributed to enhanced clinical decision-making, targeted preventive measures, and improved ECC management. The studies also highlighted the importance of considering multiple factors, including demographic, environmental, and genetic factors, when developing dental caries prediction models. Machine learning algorithms hold significant potential for ECC prediction and detection, having promising performance outcomes. Due to the heterogeneity of the studies, no meta-analysis could be performed. Moreover, further research is needed to explore the feasibility, acceptability, and effectiveness of integrating these algorithms into dental practice. This approach would ultimately contribute to enabling more effective and personalized dental caries management and improved oral health outcomes for diverse populations.