The Clinical Efficacy and Diagnostic Accuracy of Artificial Intelligence Across Dental Specialties
A Comprehensive Systematic Review
DOI:
https://doi.org/10.5195/d3000.2026.1582Parole chiave:
Artificial Intelligence, Machine Learning, Diagnosis, Oral and Maxillofacial Surgery, Orthodontics, Prosthodontics, HealthcareAbstract
The integration of Artificial Intelligence (AI) into modern dentistry has already transformed diagnostic and treatment planning approaches; yet the impact of AI in day-to-day clinical practice remains disjointed across different disciplines. Although the laboratory findings of numerous controlled algorithmic validation trials are quite impressive, we must ask ourselves if the clinical applications of AI will indeed bring improvements to our patients' clinical outcomes as they are applied within the dynamic and unpredictable real-world conditions of dentistry. This comprehensive systematic review consolidates research assessing the diagnostic accuracy and clinical efficacy of AI throughout all specialties of dentistry - from oral and maxillofacial surgery to pedodontics to ascertain whether AI is currently an innovative new technology or an incremental advancement. The PubMed, Scopus, Web of Science, and IEEE Xplore literature databases were systematically searched for all prospective and retrospective studies on diagnostic accuracy and/or clinical application involving an AI tool versus a established clinical standard of care (from January 2020 to January 2026). Any peer-reviewed publication reporting new data from the use of clinical AI in direct patient care was considered eligible. Measures of diagnostic accuracy (including sensitivity, specificity, and area under the curve - AUC) along with data on AI-guided treatment planning accuracy and any patient-centered outcomes were extracted. Heterogeneity among the studies was assessed by calculating the value, defined as: low heterogeneity (I≤40%), moderate(40%<I<60%), and high(I>60%). Bias in each study was critically assessed using the QUADAS-2 tool, while clinical translation potential was assessed with the ROB-2 tool. The findings indicated considerable disparity in how the validation of AI applications in dentistry was reported. While many deep learning applications achieved impressive results for image-based diagnostics, specifically in radiology (pooled sensitivity=0.94; 95% CI, 0.89-0.97) and oral pathology (pooled AUC >0.90), the real-world clinical applications and surgical uses of AI have not been sufficiently investigated. Very few prospective clinical trials were found, and only 23% of included studies had prospective designs; nearly all studied enterprises exhibited external validity biases and did not detail the process by which AI was integrated into clinical workflows or its actual effects on patient health, leading to the limited analysis of patient-centered variables. Significant challenges exist in transitioning AI developed in laboratory settings into routine chair side clinical application, prompting the necessity for uniform methods to validate AI tools for responsible innovation. An accurate accounting of AI's real-world role in all facets of dentistry would aid clinicians, researchers, and policymakers in understanding AI's true value, informing sensible and evidence-based adoption rather than overzealous enthusiasm.
##submission.downloads##
Pubblicato
Fascicolo
Sezione
Licenza
Copyright (c) 2026 Ali Ahmed Khubrani, Khalid Alamri, Ahmed Abdurabu, Ahmed Abozor, Hussan Assiri, Mutea Aljamali, Abdulwahab Saad Alamri, Gamal Hafedh, Rawan Labani, Ibrahim Al Monjem, Samar Ahmad Omier, Saba Almassri, Areej Maher Alshalian
TQuesto lavoro è fornito con la licenza Creative Commons Attribuzione 4.0 Internazionale.
Authors who publish with this journal agree to the following terms:
- The Author retains copyright in the Work, where the term “Work” shall include all digital objects that may result in subsequent electronic publication or distribution.
- Upon acceptance of the Work, the author shall grant to the Publisher the right of first publication of the Work.
- The Author shall grant to the Publisher and its agents the nonexclusive perpetual right and license to publish, archive, and make accessible the Work in whole or in part in all forms of media now or hereafter known under a Creative Commons Attribution 4.0 International License or its equivalent, which, for the avoidance of doubt, allows others to copy, distribute, and transmit the Work under the following conditions:
- Attribution—other users must attribute the Work in the manner specified by the author as indicated on the journal Web site;
- The Author is able to enter into separate, additional contractual arrangements for the nonexclusive distribution of the journal's published version of the Work (e.g., post it to an institutional repository or publish it in a book), as long as there is provided in the document an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post online a prepublication manuscript (but not the Publisher’s final formatted PDF version of the Work) in institutional repositories or on their Websites prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work. Any such posting made before acceptance and publication of the Work shall be updated upon publication to include a reference to the Publisher-assigned DOI (Digital Object Identifier) and a link to the online abstract for the final published Work in the Journal.
- Upon Publisher’s request, the Author agrees to furnish promptly to Publisher, at the Author’s own expense, written evidence of the permissions, licenses, and consents for use of third-party material included within the Work, except as determined by Publisher to be covered by the principles of Fair Use.
- The Author represents and warrants that:
- the Work is the Author’s original work;
- the Author has not transferred, and will not transfer, exclusive rights in the Work to any third party;
- the Work is not pending review or under consideration by another publisher;
- the Work has not previously been published;
- the Work contains no misrepresentation or infringement of the Work or property of other authors or third parties; and
- the Work contains no libel, invasion of privacy, or other unlawful matter.
- The Author agrees to indemnify and hold Publisher harmless from Author’s breach of the representations and warranties contained in Paragraph 6 above, as well as any claim or proceeding relating to Publisher’s use and publication of any content contained in the Work, including third-party content.
Revised 7/16/2018. Revision Description: Removed outdated link.
