Explainable AI Models for Forensic Endodontics: Linking Root Canal Patterns to Individual Dental Identity

Abstract

Forensic endodontics relies on the unique anatomical features of teeth, particularly root canal morphology, to assist in individual identification. Recent advances in artificial intelligence (AI) offer powerful tools to analyze complex dental patterns; however, the “black-box” nature of many AI models limits their applicability in legal and forensic contexts. This study explores the development of explainable AI (XAI) models designed to link root canal configurations to individual dental identities. By integrating high-resolution dental imaging data with interpretable machine learning approaches, the proposed framework not only achieves accurate pattern recognition but also provides transparent insights into model decisions, enabling forensic practitioners to validate and justify identification outcomes. The findings demonstrate that XAI can bridge the gap between advanced computational analysis and forensic accountability, offering a robust, ethical, and legally defensible methodology for dental identification.