aceComparing Diagnostic Ability of Two Off-the-Shelf Large Language Models with That of Endodontists for Teeth Requiring Initial Root Canal Treatment: A Multicenter Retrospective Investigation
Introduction: Despite growing interest in large language models (LLMs) for endodontic diagnosis, prior studies have used simulated cases, examination formats, or small selected series. This multicenter retrospective study compared the diagnostic accuracy of ChatGPT-5.2 and Gemini 3.0 with that of calibrated endodontists across 645 teeth requiring initial root canal treatment. Methods: Cases were evaluated across four endpoints: pulpal diagnosis, periapical diagnosis, treatment planning, and case difficulty. Stan…
On individual endpoints such as pulpal or periapical diagnosis, both LLMs reached 74% to 88% accuracy on real root canal cases, which supports a role as adjunctive tools.
When the endpoints were combined, both models made at least one clinically relevant error in about half of cases, and performance dropped in low-prevalence categories.
Findings on minority categories are described as suggestive because of small subgroup sizes, and the study is retrospective.
Evidence
- Peer-reviewedJournal of Endodontics2026-10-13
How should this claim be treated?
Truvace Impact Record TRV-2026-1352, v1: “Comparing Diagnostic Ability of Two Off-the-Shelf Large Language Models with That of Endodontists for Teeth Requiring Initial Root Canal Treatment: A Multicenter Retrospective Investigation.” Truvace, 2026-10-14. /record/TRV-2026-1352 (accessed at citation time). sha256 f9bbbbd8445351fd…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1352 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.