Predicting Pathological Dental Wear: A Roadmap for Artificial Intelligence in Natural Teeth and Restorations
- 1Department of Conservative Dentistry and Prosthodontics, Faculty of Dentistry, Complutense University of Madrid, Madrid, Spain; Department of Research Analytics, Saveetha Dental College and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, India; Department of Prosthodontics, School of Dentistry, Shiraz University of Medical Sciences, Shiraz, Iran
Abstract
Artificial intelligence is transforming dental wear assessment, but clinically useful systems should forecast pathological progression rather than physiological wear associated with normal function and ageing. Current research follows 2 largely separate paths: models for natural teeth detect or grade existing wear and automate comparisons of serial intraoral scans, whereas restorative-material models predict laboratory wear under controlled tribological conditions. No clinically validated system currently forecasts patient-specific future wear across natural teeth, restorations, and antagonists. This perspective proposes a multimodal longitudinal framework combining serial surface geometry with substrate identity, restoration design, occlusal function, patient behaviour, and biological exposures. It defines clinically meaningful prediction targets and presents a staged roadmap for data harmonisation, external validation, clinical impact evaluation, and responsible implementation. Such systems could improve personalised recall, prevention, material selection, and timely intervention, although laboratory accuracy should not be interpreted as clinical certainty.
Related
- Predicting follow-up cognition using estimated structural and functional connectivity networks and artificial intelligence in multiple sclerosis
- Artificial intelligence for predicting chronicity, relapse, and zoonotic risk in brucellosis: toward a one health closed-loop decision-making framework
- Artificial Intelligence in Delirium Care: Predicting, Detecting, and Preventing Delirium in Older Hospitalized Adults.
- Multimodal Artificial Intelligence Predicts Pathological Response and Prognosis in HER2-Positive Early Breast Cancer Treated with Chemotherapy De-escalation Strategies: Analyses from PHERGain and PHERGain-2 Trials
- Artificial intelligence-enhanced electrocardiography for predicting mortality and major adverse cardiovascular events: A systematic review and narrative synthesis
BibTeX
@article{mosaddad2026predicting,
title = {{Predicting Pathological Dental Wear: A Roadmap for Artificial Intelligence in Natural Teeth and Restorations}},
author = {Seyed Ali Mosaddad},
journal = {International Dental Journal},
year = {2026},
month = oct,
doi = {10.1016/j.identj.2026.111250},
url = {https://doi.org/10.1016/j.identj.2026.111250},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting Pathological Dental Wear: A Roadmap for Artificial Intelligence in Natural Teeth and Restorations
AU - Seyed Ali Mosaddad
PY - 2026
DA - 2026/10/30
JO - International Dental Journal
DO - 10.1016/j.identj.2026.111250
UR - https://doi.org/10.1016/j.identj.2026.111250
AB - Artificial intelligence is transforming dental wear assessment, but clinically useful systems should forecast pathological progression rather than physiological wear associated with normal function and ageing. Current research follows 2 largely separate paths: models for natural teeth detect or grade existing wear and automate comparisons of serial intraoral scans, whereas restorative-material models predict laboratory wear under controlled tribological conditions. No clinically validated system currently forecasts patient-specific future wear across natural teeth, restorations, and antagonists. This perspective proposes a multimodal longitudinal framework combining serial surface geometry with substrate identity, restoration design, occlusal function, patient behaviour, and biological exposures. It defines clinically meaningful prediction targets and presents a staged roadmap for data harmonisation, external validation, clinical impact evaluation, and responsible implementation. Such systems could improve personalised recall, prevention, material selection, and timely intervention, although laboratory accuracy should not be interpreted as clinical certainty.
SN - 0020-6539
SN - 1875-595X
ER -