Skip to main content

Algorithm Spots COVID-19 Cases from Eye Images: Preprint

A small study shows artificial intelligence can pick out individuals with coronavirus infections, but ophthalmologists and AI experts say the approach is far from proven to be capable of distinguishing infections with SARS-CoV-2 from other ills.

Written byAnthony King
| 4 min read
covid-19 coronavirus sars-cov-2 pandemic eyes conjunctivitis artificial intelligence machine learning

Register for free to listen to this article
Listen with Speechify
0:00
4:00

ABOVE: Eye regions analyzed by the AI-based tool for screening potential coronavirus infections
YANWEI FU

Scientists describe a potential screening method for COVID-19 based on eye images analyzed by artificial intelligence. Scanning a set of images from several hundred individuals with and without COVID-19, the tool accurately diagnosed coronavirus infections more than 90 percent of the time, the developers reported in a preprint posted to medRxiv September 10.

“Our model is quite fast,” Yanwei Fu, a computer scientist at Fudan University in Shanghai, China, who led the study, tells The Scientist. “In less than a second it can check results.”

Currently, screening for coronavirus infection involves CT imaging of the lungs or analyzing samples from the nose or throat, both of which take time and require professional effort. A system based on a few images of the eyes that could triage or even diagnose people would save on both costs and ...

Interested in reading more?

Become a Member of

The Scientist Logo
Receive full access to more than 35 years of archives, as well as TS Digest, digital editions of The Scientist, feature stories, and much more!
Already a member?
Add The Scientist as a preferred source on Google

Add The Scientist as a preferred Google source to see more of our trusted coverage.

Meet the Author

  • anthony king

    Anthony King is a freelance science journalist based in Dublin, Ireland, who contributes to The Scientist. He reports on a variety of topics in chemical and biological sciences, as well as science policy and health. His articles have appeared in Nature, Science, Cell, Chemistry World, New Scientist, the Irish Times, EMBO Reports, Chemistry & Industry, and more. He is President of the Irish Science & Technology Journalists Association. 

    View Full Profile

Related Topics

November digest cover
November 2026

Chemistry Meets Arcade Combat in “Reaction Rumble” Game

Choose your fighter! Enter the arena as chemical elements and dole out moves inspired by real-world reactions in this educational browser-based game.

View this Issue
From Pilot to Practice: Advancing Regulatory Reliance

From Pilot to Precedent: A Year of Regulatory Innovation through PRISM and What it Means for Cloud Adoption in Regulatory Submissions

DNAnexus
Thumbnail

Make It Local, Make It Last: The Evolution of mRNA Protein Replacement Therapy

Improving Western Blot Analysis of Biofluid Samples

Improving Western Blot Analysis of Biofluid Samples

Bio-Rad
Reducing AAV Sample Consumption With Multiwavelength SV-AUC

Reducing AAV Sample Consumption With Multiwavelength SV-AUC

​Beckman Coulter

Products

Sino Biological Logo

Sino Biological Advances AI-Designed Molecule Validation with 4RISE™

Illustrated floating metabolites and molecules

Metabolon Verus™ Kit: Metabolomics Profiling Kit

Metabolon
Abstract image of circles and concentric lines on a blue and pink background.

MX Analytical and Precision Balances: Effortless Weighing and Secure Data Handling

Mettler
3D multicolored conceptual image of antibody molecules

Premium BsAb: LC-MS-Assisted Bispecific Antibody Production with >98% Heterodimer Purity

WuXi Biologics