70/100

Moderate evidence

GainPublished recordHealthGood Space

AI-Assisted Ni Classification in Nasopharyngeal NBI: Multicenter Validation and Reader Study

Truvace record
TRV-2026-3035raw data (JSON)
Version
v1Published
First published
Evidence type
Controlled or validated comparison
Sources
1 sourcePeer-reviewed
sha256
1b970fe5cdf7…check it

To develop and validate an artificial intelligence (AI) system for standardized Ni classification of nasopharyngeal narrow-band imaging (NBI) and to evaluate whether AI assistance improves physician diagnostic consistency and biopsy-related decision making in a reader-study setting. In this multicenter diagnostic study, 5404 high-quality nasopharyngeal NBI images were retrospectively collected. Lesion segmentation and five-class Ni classification networks were trained independently. Performance was evaluated in…

The gain

In a randomized crossover study of 12 physicians reading 200 nasopharyngeal images, AI assistance cut potentially unnecessary biopsy decisions from 21.6% to 10.3% for junior physicians and from 13.7% to 8.0% for senior physicians.

What this doesn’t fix

The effect on biopsy decisions was measured in a reader-study setting using 200 images from one centre, CHSZCAMS, and the authors call only for further evaluation as a second-reader tool.

Sources

1 on file
  1. The Laryngoscopedoi:10.1002/lary.71067
    Peer-reviewed2026-11-17

Cite this record

v1

Truvace Impact Record TRV-2026-3035, v1: “AI-Assisted Ni Classification in Nasopharyngeal NBI: Multicenter Validation and Reader Study.” Truvace, 2026-11-18. /record/TRV-2026-3035 (accessed on the day you copy it). sha256 1b970fe5cdf77c83…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv11b970fe5cdf7…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-3035 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.