AUTHOR=Mohammad Norhasmira , Ahmad Rohana , Kurniawan Arofi , Mohd Yusof Mohd Yusmiaidil Putera TITLE=Applications of contemporary artificial intelligence technology in forensic odontology as primary forensic identifier: A scoping review JOURNAL=Frontiers in Artificial Intelligence VOLUME=Volume 5 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.1049584 DOI=10.3389/frai.2022.1049584 ISSN=2624-8212 ABSTRACT=Background: Forensic odontology (FO) may require a visual or clinical method during identification. Sometimes it may require forensic experts to refer to the existing technique to identify individuals, for example, by using the atlas to estimate the dental age. However, the existing technology can be a complicated procedure for a large-scale incident requiring a more significant number of forensic identifications, particularly during mass disasters. This has driven many experts to perform automation in their current practice to improve efficiency. Objective: This article aims to evaluate current artificial intelligence (AI) applications and discuss their performance concerning the algorithm architecture used in FO. Methods: This study summarizes the findings of 25 research papers published between 2010 and June 2022 using the Arksey and O'Malley framework, updated by the Joanna Briggs Institute Framework for Scoping Reviews methodology, highlighting the research trend of AI-based methods in FO. In addition, a literature search was conducted on Web of Science (WoS), Scopus, Google Scholar, and PubMed, and the results were evaluated based on their content and significance. Results: The potential application of the AI-based methods in FO can be categorized into four: (1) human bite marks, (2) gender determination, (3) age estimation and (4) dental comparison. It is evident that this powerful tool can solve humanity’s problems by giving an adequate number of datasets, the appropriate implementation of algorithm architecture and the proper assigning of hyperparameter that enables the model to perform the prediction at a very high performance. Conclusion: The reviewed articles demonstrate that machine learning (ML) techniques are dependable for studies involving continuous features, such as morphometric parameters, which require fewer training datasets for the ML model to be trained with promising results. As a result, large datasets may be necessary to train the network, as it must learn as many features as possible to make an accurate prediction. In the meantime, this method's capacity to automatically learn task-specific feature representations has made it a major success in forensic odontology.