Your data on MRCVSonline
The nature of the services provided by Vision Media means that we might obtain certain information about you.
Please read our Data Protection and Privacy Policy for details.

In addition, (with your consent) some parts of our website may store a 'cookie' in your browser for the purposes of
functionality or performance monitoring.
Click here to manage your settings.
If you would like to forward this story on to a friend, simply fill in the form below and click send.

Your friend's email:
Your email:
Your name:
 
 
Send Cancel

Artificial intelligence to identify equine ocular disease
Artificial intelligence could lead to more horses getting an earlier diagnosis.
The tool can diagnose moon blindness in horses.

An artificial intelligence (AI) tool could be used to diagnose equine recurrent uveitus (ERU) in horses.

The inflammatory ocular disease, also known as ‘moon blindness’, can lead to blindness or loss of the affected eye.

ERU is one of the more common eye diseases in horses, and can have a major economic impact. A quick, correct diagnosis can minimise the lasting damage.

The research team created an AI tool, which was trained with photographs of diseases to identify the patterns which may lead to a diagnosis.

To assess the efficacy of their deep learning tool, researchers from the Ludwig-Maximilian-Universität München asked 150 veterinary surgeons to evaluate 40 photos of horses’ eyes. The pictures included a mixture of healthy eyes, eyes with ERU, and eyes with other diseases.

Equine veterinary surgeons completed the test with a 76 per cent success rate, meanwhile veterinary surgeons working in small animal or mixed practice identified the eye issues correctly 67 per cent of the time.

When the AI image analysis tool was given the same challenge, the probability of receiving the correct answer was 93 per cent.

The researchers say that, while the difference was not statistically significant, it proved that AI could reliably recognise ERU. This could support veterinary surgeons with the diagnosis of potential emergency cases.

This could lead to more horses getting an earlier diagnosis, increasing the likelihood of them receiving prompt treatment and saving affected eyes. It will also enable less experienced veterinary surgeons to differentiate between ERU and other opthalmic diseases.

The AI, deep learning tool is web-app based, and can be used through a smartphone device.

Professor Anna May, who led the research team, said: "It's not meant to replace veterinarians, but can help them reach the correct diagnosis.

“It is particularly valuable for less experienced professionals or for horse owners in regions where vets are few and far between,"

The full study can be found in the Equine Veterinary Journal.

Image © Shutterstock

Become a member or log in to add this story to your CPD history

FIVP launches CMA remedies survey

News Story 1
 FIVP has shared a survey, inviting those working in independent practice to share their views on the CMA's proposed remedies.

The Impact Assessment will help inform the group's response to the CMA, as it prepares to submit further evidence to the Inquiry Group. FIVP will also be attending a hearing in November.

Data will be anonymised and used solely for FIVP's response to the CMA. The survey will close on Friday, 31 October 2025. 

Click here for more...
News Shorts
CMA to host webinar exploring provisional decisions

The Competition and Markets Authority (CMA) is to host a webinar for veterinary professionals to explain the details of its provisional decisions, released on 15 October 2025.

The webinar will take place on Wednesday, 29 October 2025 from 1.00pm to 2.00pm.

Officials will discuss the changes which those in practice may need to make if the provisional remedies go ahead. They will also share what happens next with the investigation.

The CMA will be answering questions from the main parties of the investigation, as well as other questions submitted ahead of the webinar.

Attendees can register here before Wednesday, 29 October at 11am. Questions must be submitted before 10am on 27 October.

A recording of the webinar will be accessible after the event.