Title
AI-driven prediction of irrigant penetration depth in root canal systems: An in vitro study
Authors
Meetkumar Dedania1, Prasangi Vijaya bhanu2, Priyal Shah3,*, Sadashiv Gopinath Daokar4, Chiranjan Guha5 & Vipin Arora6
Affiliation
1Department of Conservative Dentistry and Endodontics, K. M. Shah Dental College and Hospital, Sumandeep Vidyapeeth Deemed to be University, Piparia, Vadodara, Gujarat, India; 2Department of Conservative Dentistry and Endodontics, GSL dental college and hospital, Rajahmundry andhra Pradesh, India; 3Department of Conservative Dentistry and Endodontics, Siddhpur Dental College and Hospital, Dethali, Siddhpur, Gujarat, India; 4Department of Conservative Dentistry and Endodontics, CSMSS Dental College & Hospital, Kanchanwadi, Chhatrapati Sambhajinagar, Maharashtra, India; 5Department of Conservative Dentistry and Endodontics, Sanaka Institute of Dental Sciences, Kanksha, Malandighi, Durgapur, West Bengal, India; 6Department of Restorative Dental Sciences, Taif University, Saudi Arabia; *Corresponding author
Meetkumar Dedania - E-mail: meet97247da@gmail.com
Prasangi Vijaya bhanu - E-mail: prasangivijji@gmail.com
Priyal Shah - E-mail: priyalshah009@gmail.com
Sadashiv Gopinath Daokar - E-mail: drdaokar@gmail.com
Chiranjan Guha - E-mail: drguhu.chiru@gmail.com
Vipin Arora - E-mail: vipinendodontist@gmail.com
Article Type
Research Article
Date
Received July 1, 2026; Revised July 31, 2026; Accepted July 31, 2026, Published July 31, 2026
Abstract
Inadequate irrigant penetration into the apical and lateral extensions of root canal systems remains a major limitation of chemomechanical disinfection, particularly in curved and oval canals. Therefore, it is of interest to develop and validate artificial intelligence (AI) models to predict irrigant penetration depth using canal morphology, preparation size, activation method, irrigant viscosity, needle position and micro-computed tomography-derived anatomical variables from 120 extracted human mandibular premolars. Confocal imaging showed significantly greater penetration with passive ultrasonic activation (724.8 ± 105.7 µm) and laser activated irrigation (781.3 ± 112.4 µm) compared with conventional needle irrigation (412.6 ± 91.5 µm; p < 0.001). The gradient boosting model achieved the highest predictive performance (R² = 0.91, RMSE = 58.4 µm, MAE = 43.7 µm). Thus, data shows that AI based prediction accurately estimated irrigant penetration depth and it may facilitate personalized irrigation strategies based on canal anatomy and activation technique.
Keywords
Artificial intelligence (AI), endodontic irrigation, irrigant penetration, root canal morphology, machine learning (ML), passive ultrasonic irrigation
Citation
Dedania et al. Bioinformation 22(7): 4193-4198 (2026)
Edited by
Hiroj Bagde
ISSN
0973-2063
Publisher
License
This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.
