Artificial Intelligence for Working Length Determination in Endodontics: A Systematic Review and Meta-Analysis

Area of Science:

• Endodontics
• Dental Imaging
• Artificial Intelligence in Dentistry

Background:

• Accurate working-length determination is crucial for successful endodontic treatment.
• Current methods rely on radiographic or impedance-based inputs, with varying degrees of accuracy.
• Artificial intelligence (AI) offers potential for improved diagnostic performance.

Purpose of the Study:

• To systematically review and meta-analyze the performance of AI models for working-length determination.
• To compare AI-based methods against manual or conventional reference standards.
• To assess the certainty of evidence for AI in working-length determination.

Main Methods:

• Systematic review and meta-analysis of in vitro and ex vivo studies.
• Comprehensive search of seven electronic databases up to October 2025.
• Inclusion of five studies with over 1765 teeth or radiographic images.

Main Results:

• AI-based methods demonstrated higher odds of correct working length determination than expert assessment.
• Moderate to high risk of bias was observed, mainly due to internal validation and lab-based designs.
• Overall certainty of evidence for the primary outcome was rated low.

Conclusions:

• AI may enhance the consistency of working-length determination in controlled settings.
• Further well-designed clinical studies are essential for routine clinical implementation.
• Current evidence suggests potential but requires validation in real-world clinical scenarios.