Faculty of Dentistry, Hasanuddin University, Indonesia
BibTex Citation Data :
@article{actodont31922, author = {Maqbool Noori and Erni Marlina and Andi Sri Permatasari and Fadhlil Ulum A. Rahman}, title = {Diagnostic Accuracy of Mobile Dental AI Applications for Early Oral Disease Detection: A Systematic Review}, journal = {Acta Odontologica Indonesia}, volume = {0}, number = {0}, year = {2026}, keywords = {Artificial intelligence, mobile health, diagnostic accuracy, oral health screening, diagnostic accuracy}, abstract = { Early detection of oral diseases, particularly dental caries, is critical for effective prevention and timely intervention. However, conventional diagnostic approaches are limited by subjectivity, inter-clinician variability, and unequal access to dental services. Recently, mobile-based artificial intelligence (AI) applications have emerged as potential tools to support early oral disease screening, especially in underserved and resource-limited settings. Despite increasing interest, evidence regarding their diagnostic accuracy and reliability remains fragmented. This systematic review aimed to evaluate the diagnostic accuracy and reliability of mobile-based artificial intelligence applications for early detection of oral diseases, with a primary focus on dental caries. A systematic review was conducted in accordance with PRISMA DTA guidelines. Electronic databases, including PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar, were searched for peer-reviewed studies published between 2015 and 2025. Eligible studies evaluated smartphone-based or mobile AI applications for dental caries detection and reported diagnostic performance metrics. Study selection, data extraction, and methodological quality assessment were performed using predefined criteria, with study quality assessed using the QUADAS-2 tool. Due to heterogeneity across studies, findings were synthesized narratively. Eighteen studies met the inclusion criteria. Mobile dental AI applications demonstrated moderate to high diagnostic accuracy, with reported sensitivity ranging from approximately 75% to over 95% and specificity from approximately 70% to 96%. AI-assisted systems showed performance comparable to professional dental assessment under controlled conditions, although most studies relied on internal validation. In conclusion, mobile based AI applications show promising diagnostic accuracy for early detection of dental caries and may serve as adjunctive screening tools in preventive oral healthcare. However, further large-scale studies with robust external validation are required before widespread clinical implementation.}, issn = {3090-7411}, pages = {36--48} doi = {10.14710/actodont.31922}, url = {https://ejournal2.undip.ac.id/index.php/actodont/article/view/31922} }
Refworks Citation Data :
Early detection of oral diseases, particularly dental caries, is critical for effective prevention and timely intervention. However, conventional diagnostic approaches are limited by subjectivity, inter-clinician variability, and unequal access to dental services. Recently, mobile-based artificial intelligence (AI) applications have emerged as potential tools to support early oral disease screening, especially in underserved and resource-limited settings. Despite increasing interest, evidence regarding their diagnostic accuracy and reliability remains fragmented.
This systematic review aimed to evaluate the diagnostic accuracy and reliability of mobile-based artificial intelligence applications for early detection of oral diseases, with a primary focus on dental caries.
A systematic review was conducted in accordance with PRISMA DTA guidelines. Electronic databases, including PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar, were searched for peer-reviewed studies published between 2015 and 2025. Eligible studies evaluated smartphone-based or mobile AI applications for dental caries detection and reported diagnostic performance metrics. Study selection, data extraction, and methodological quality assessment were performed using predefined criteria, with study quality assessed using the QUADAS-2 tool. Due to heterogeneity across studies, findings were synthesized narratively.
Eighteen studies met the inclusion criteria. Mobile dental AI applications demonstrated moderate to high diagnostic accuracy, with reported sensitivity ranging from approximately 75% to over 95% and specificity from approximately 70% to 96%. AI-assisted systems showed performance comparable to professional dental assessment under controlled conditions, although most studies relied on internal validation.
Article Metrics:
Last update:
Authors who publish in Acta Odontologica Indonesia retain full copyright ownership of their work. In keeping with the journal’s commitment to open access, all articles are published under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
This license permits anyone to access, use, share, adapt, remix, transform, and build upon the work for any non-commercial purpose, provided that appropriate credit is given to the original author(s), a link to the license is provided, and any changes to the work (if any) are clearly indicated.
Authors retain the right to reuse their published article in future scholarly works (such as books or conference presentations). All such uses must comply with the terms of the CC BY-NC license. Authors are encouraged to disseminate their work as widely as possible.
Readers and third parties may use the content in accordance with the CC BY-NC license. This includes the ability to reproduce, modify, and build upon the article for non-commercial purposes, as long as proper attribution is given.
