70/100

Moderate evidence

ProblemPublished recordHealthProblem Space

Why aren't we using AI in eye clinics? A systematic review of barriers and solutions in AI-based fundus image diagnostics for ocular diseases

Truvace record
TRV-2026-1127raw data (JSON)
Version
v3Revised
First published
Evidence type
Systematic review or meta-analysis
Sources
1 sourcePeer-reviewed
sha256
82a1e549e90b…check it

Artificial intelligence (AI) has shown remarkable accuracy in the diagnosis of common ocular diseases such as diabetic retinopathy (DR), glaucoma, retinopathy of prematurity (ROP), and age-related macular degeneration (AMD), often matching or even outperforming expert clinicians. Despite these advancements, AI adoption in clinical settings remains limited due to key barriers. This systematic review evaluates 34 studies (2018-2025) highlighting AI's diagnostic performance (often >90% accuracy) while pointing out…

The problem

A systematic review of 34 studies shows eye-scan AI often tops 90% accuracy yet sees limited clinical adoption, which the review attributes to poor workflow integration, lack of transparency in decisions and weak generalizability.

Sources

1 on file
  1. Peer-reviewed2026-09-18

Cite this record

v3

Truvace Impact Record TRV-2026-1127, v3: “Why aren't we using AI in eye clinics? A systematic review of barriers and solutions in AI-based fundus image diagnostics for ocular diseases.” Truvace, 2026-11-05. /record/TRV-2026-1127 (accessed on the day you copy it). sha256 82a1e549e90bdcd0…

Change history

3 versions

Every change made to this record since it was first published, and why.

  1. Revisedv382a1e549e90b…

    Voice pass: plainer wording and study attribution; no facts or figures changed.

  2. Revisedv2333f0b27850c…

    Editorial pass: sharper headline; gain/problem restated as concrete outcomes.

  3. Publishedv1a88ccff32e49…

    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-2026-1127 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.