Artificial Intelligence can detect vision problems in young children

The World Health Organization (WHO) estimates that there are 19 million children in the world with vision problems, of which 70 to 80 percent can be prevented or cured with an early diagnosis.

In most cases they remain undiagnosed for years. The Aragon Health Research Institute of the University of Zaragoza, the technology manufacturer Huawei and DIVE Medical, work on the co-development of Track AI, a system based on Artificial Intelligence designed to detect and diagnose early signs of visual impairment in children.

It is not science fiction

We had already highlighted the progress of the DIVE software to monitor and track the look of each eye while the child is looking for stimuli, designed to test different aspects of visual function.

In Babies and more A device developed by ophthalmologists at the University of Zaragoza lets you know how babies see

Now, one step is taken further. The data that is being collected throughout the world of the look pattern of children, is processed in a Huawei P30 smartphone, enhanced with Artificial Intelligence, in order to indicate possible indicators of visual problems.

As explained by its developers, "Everything is specified in a portable device, affordable and easy to use to identify these problems in children as soon as possible".

This is really important since, in most situations, children under four are not able to clearly explain their symptoms, which often means that they are not treated quickly and before the problem is aggravated. This is stated by Dr. Victoria Pueyo, a pediatric ophthalmologist at DIVE Medical:

"Early diagnosis is vital. All pathologies associated with low vision problems leave minor sequelae if detected before three or four years of age."

This project, in which they have been working for years, according to the ophthalmologist, aims "Implement this technology worldwide and with our multiethnic approach to address all types of visual impairment."

In Babies and more Spanish children under seven are more nearsighted by the use of screens

How does it work?

Project photo, courtesy of Huawei

Children with visual impairment have different look patterns compared to children with normal vision. DIVE software can accurately collect data on the position of the gaze during a scientifically designed visual stimulus.

The interpretation of this data can be a challenge for non-specialized health workers. However, using Artificial Intelligence (AI), computers can be trained to identify abnormal look patterns, in order to perform easier screening tests and assisted diagnoses. In this way, it is possible to speed up the process, from diagnosis to problem management.

The Track AI device, built in the smartphone, does not require WI-FI and receives real-time data to speed up diagnostics. Thus, can be used worldwide, from an ophthalmologist in a UK hospital to a doctor from a village in a remote area of ​​Africa.

The development of an AI-based system requires the collection of data from thousands of children, and research centers are currently collecting it in five countries on three continents (China, Mexico, United Arab Emirates, Spain and the United Kingdom).

Once a large amount of data has been incorporated, neural networks will be trained and a prototype device will be tested later this year. The objective is to implement it in 2020, which will help health professionals diagnose and treat eye conditions at an early stage.

Photos | iStock

In Baby and More | Strabismus in the newborn: my baby deflects the eyes, is it normal ?, My son has a stye: why it comes out and what to do if it appears

Video: Artificial Intelligence: The Common Sense Problem (May 2024).