Artificial Intelligence for Detecting Periodontitis: Systematic Literature Review

Background: The determination of the diagnosis of inflammatory periodontitis is generally based on clinical examination, which is then strengthened by radiographic examination. Still, the inequality of assessment of clinical conditions, along with limitations of radiographic interpretation, makes determining the diagnosis of the periodontal disease difficult. The use of artificial intelligence as a digital system approach is believed to reduce costs, time, the need for medical services, and medical errors that may occur due to human factors. Objective: This systematic review study is to analyze the use of dental and panoramic radiographs combined with the use of artificial intelligence in establishing the diagnosis of periodontitis based on the parameters of periodontal disease severity according to the 2017 American Academy of Periodontology/European Federation of Periodontology Workshop (pocket depth, clinical attachment loss (CAL) and the pattern and level of alveolar bone damage that occurs). Methods: Journal searches for articles published in English were carried out through the PubMed and Scopus databases in the 2011-2021 period, using the search terms periodontitis, periodontal disease, food impaction, trauma occlusion, periapical radiograph, panoramic, machine learning, artificial intelligence, and periodontal bone loss, after going through article selection, two suitable articles were obtained. Results: Two studies fell into the analyzed category. Both list periodontal bone loss as a parameter that marks periodontitis, and the use of panoramic photos in detecting this parameter assisted by Convolutional Neural Networks as artificial intelligence. Conclusion: The use of panoramic radiographs and Convolutional Neural Networks as artificial intelligence that serves as a tool to detect periodontal bone damage has almost the same results as experienced clinicians In order for this method to be developed in the future to help clinicians establish the diagnosis, more clinical and image data will be required.