Deep learning for classifying the stages of periodontitis on dental images: a systematic review and meta-analysis

Abstract

Background The development of deep learning (DL) algorithms for use in dentistry is an emerging trend. Periodontitis is one of the most prevalent oral diseases, which has a notable impact on the life quality of patients. Therefore, it is crucial to classify periodontitis accurately and efficiently. This systematic review aimed to identify the application of DL for the classification of periodontitis and assess the accuracy of this approach. Methods A literature search up to November 2023 was implemented through EMBASE, PubMed, Web of Science, Scopus, and Google Scholar databases. Inclusion and exclusion criteria were used to screen eligible studies, and the quality of the studies was evaluated by the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology with the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies) tool. Random-effects inverse-variance model was used to perform the meta-analysis of a diagnostic test, with which pooled sensitivity, specificity, positive likelihood ratio (LR), negative LR, and diagnostic odds ratio (DOR) were calculated, and a summary receiver operating characteristic (SROC) plot was constructed. Results Thirteen studies were included in the meta-analysis. After excluding an outlier, the pooled sensitivity, specificity, positive LR, negative LR and DOR were 0.88 (95%CI 0.82–0.92), 0.82 (95%CI 0.72–0.89), 4.9 (95%CI 3.2–7.5), 0.15 (95%CI 0.10–0.22) and 33 (95%CI 19–59), respectively. The area under the SROC was 0.92 (95%CI 0.89–0.94). Conclusions The accuracy of DL-based classification of periodontitis is high, and this approach could be employed in the future to reduce the workload of dental professionals and enhance the consistency of classification.