Related Experiment Video
Updated: May 27, 2026
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Explainable Artificial Intelligence in Dentistry: A Systematic Review of Its Trust and Translation
Sermporn Thaweesapphithak1, Vivat Thongchotchat2, Hamid Alinejad-Rokny3
1Center of Excellence in Precision Medicine and Digital Health, Department of Physiology, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand; Department of Oral Biomedical Sciences, International College of Dentistry, Walailak University, Bangkok, Thailand.
Introduction And Aims:
Explainable artificial intelligence (XAI) is a set of methods and processes that make the decisions of artificial intelligence (AI) models understandable to those who are not conversant with the technology. This "black box" nature of complex AI models appears to be a primary barrier to their clinical adoption in health sciences, including dentistry. XAI is being touted as a solution to build clinician trust. This review critically assesses whether current dental XAI research is methodologically rigorous enough to substantiate claims of enhanced trustworthiness.
Methods:
This systematic review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines, searching PubMed, IEEE Xplore, medRxiv, and Ovid for dental XAI studies (2015-2025). We assessed the risk of bias and applicability using QUADAS-2 and PROBAST.
Results:
Nineteen of the 100 identified studies met the inclusion criteria. Although these studies used diverse XAI techniques, including image-based saliency methods (eg, Grad-CAM), feature attribution approaches (eg, SHAP), and local approximation methods (eg, LIME) across various dental specialties, quality assessment exposed significant limitations. Most (14 of 19) exhibited a high risk of bias, driven by small retrospective datasets, lack of external validation, and weak reference standards. Interestingly, only 1 study has evaluated the impact of XAI on human understanding.
Conclusion:
Current dental XAI research remains in a proof-of-concept phase, characterised by technical demonstrations based on low-quality evidence. The field has not yet substantiated claims that XAI enhances clinical trust or decision-making. To bridge this gap, future work must prioritise methodological rigour, external validation, and, most importantly, human-centred evaluations with dental professionals to measure the true impact of explainability on clinical workflows and patient care.
Clinical Relevance:
Current dental XAI lacks the evidence quality required for clinical reliance. Practitioners should exercise caution, as these tools have not been proven to actually improve diagnostic accuracy or trust in daily practice. Until validated in real-world settings, XAI remains experimental technology rather than a standard of care.
