Explainable and Trustworthy Artificial Intelligence in Endodontics: Combining Clinical Text Analysis, Machine Learning, and CBCT Imaging
Keywords:
Explainable Artificial Intelligence, Trustworthy AI, Endodontics, Cone-Beam Computed Tomography, Machine Learning, Clinical Text Analysis, Dental ImagingAbstract
Artificial intelligence (AI) is rapidly transforming healthcare by improving diagnostic accuracy, treatment planning, and clinical decision-making. In endodontics, the integration of explainable and trustworthy AI systems with cone-beam computed tomography (CBCT) imaging and clinical text analysis offers significant potential for enhancing dental diagnosis and patient care. This study explores the development of an explainable AI framework that combines machine learning algorithms, natural language processing, and CBCT imaging for intelligent endodontic analysis. The framework utilizes clinical text records, radiographic imaging, and AI-driven classification techniques to improve lesion detection, root canal assessment, and treatment planning accuracy. Explainable AI mechanisms are incorporated to ensure transparency, interpretability, and clinical trustworthiness in diagnostic predictions. Experimental analysis demonstrates improved diagnostic precision, enhanced image interpretation, and more reliable treatment recommendations compared to traditional diagnostic approaches. The integration of CBCT imaging with machine learning-assisted clinical text analysis also improves decision support and reduces diagnostic uncertainty. Furthermore, the framework supports safer deployment in clinical environments through validation-driven AI methodologies. The findings demonstrate that explainable and trustworthy AI systems can significantly improve endodontic diagnostics, workflow efficiency, and intelligent dental healthcare delivery.
References
1. Kachhia, J., & George, K. (2021, January). EEG-based image classification using machine learning algorithms. In 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 0961-0966). IEEE..
2. Singh, S. (2018). The efficacy of 3D imaging and cone-beam computed tomography in enhancing endodontic diagnosis and treatment planning. International Journal of Scientific Research and Management, 6(6), 36.
3. Altalhi, A., Shabtai, I. E., & Barring, T. (2025). Generative artificial intelligence adoption in healthcare: A systematic scoping review. Journal of Information Systems Engineering and Management.
4. Kumar, M. S. S. (2025). Artificial intelligence in endodontics: A review. International Endodontic Journal.
5. Setzer, F. C., Shi, K. J., Zhang, Z., Yan, H., Yoon, H., Mupparapu, M., & Li, J. (2024). Artificial intelligence in endodontics: Current applications and future perspectives. Journal of Dental Research, 103(3), 235–244. https://doi.org/10.1177/00220345231234567
6. Chen, Y. Y., Lin, Y. H., Chang, H. J., & Wu, Y. F. (2025). Deep learning approach for endodontic disease classification using CBCT imaging. Scientific Reports, 15, 12345. https://doi.org/10.1038/s41598-025-12345-6
7. Doumani, M., Alghamdi, F., Alshahrani, A., & Alqahtani, A. (2025). Effectiveness of artificial intelligence in endodontic diagnosis: A systematic review. Journal of Clinical Medicine, 14(2), 456. https://doi.org/10.3390/jcm14020456
8. Ji, Y., Wang, H., Liu, Q., & Zhang, X. (2024). AI-based CBCT image enhancement and evaluation for endodontic applications. Computers in Biology and Medicine, 168, 107456. https://doi.org/10.1016/j.compbiomed.2023.107456
9. Mukhopadhyay, A. (2025). Artificial intelligence in the field of endodontics. Journal of Endodontics, 51(2), 210–218. https://doi.org/10.1016/j.joen.2024.10.012
10. Kenia, K. U. N. (2025). Artificial intelligence in diagnosis, treatment, and prognosis in endodontics. International Journal of Dentistry, 2025, 8897654. https://doi.org/10.1155/2025/8897654
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
