Diagnosing Dyslexia – Earlier Intervention Through Technology


First aired in 1962, “The Jetsons” promised us a world of flying cars!

Technology has made a lot of promises to us over the years, with two of the big ones I commonly hear being:

  • Bringing “future technologies” to us sooner – think George Jetson and flying cars!
  • Processing large volumes of data for earlier intervention or diagnosis.

If we look honestly at many of the claims we hear, sometimes they don’t ever come to fruition and speaking candidly, I’m probably happy people are not in flying cars based off what I see on the roads on a daily basis! People struggle driving in two dimensions as it is, let alone introducing a third.

That said, I watched a couple of videos today from a Swedish company called Lexplore (previously known as Optolexia) that looks to have combined very clever technology (automatic eye tracking cameras, Azure cloud services, comprehensible reporting tools) to deliver a service for early diagnosis of dyslexia. For those unfamiliar with what dyslexia is, here’s one definition:

Dyslexia is a specific learning disability that is neurobiological in origin. It is characterized by difficulties with accurate and/or fluent word recognition and by poor spelling and decoding abilities. These difficulties typically result from a deficit in the phonological component of language that is often unexpected in relation to other cognitive abilities and the provision of effective classroom instruction. Secondary consequences may include problems in reading comprehension and reduced reading experience that can impede growth of vocabulary and background knowledge

What Lexplore have attempted to do is create a simple testing process for all readers that will track and measure their eye movement as they read. I was blown away by the visualization and accuracy of this tool – please do spend two minutes watching the following video:

Lexplore then use Artificial Intelligence (AI) to process the test results as explained on their website:

A computer model – using artificial intelligence (AI) – conducts the actual analysis. This statistical predictive method was designed by Lexplore to process huge amounts of data – amounts that could never be processed manually. The model has been “trained” on thousands of recorded eye movements and can identify children at risk of dyslexia – while also identifying those not at risk.

The reporting is presented at three levels:

  1. The individual
  2. The school level
  3. The district level
Eye Tracking

Screenshot from the video showing eye tracking across text.

I know people in my immediate family that have struggled with tracking when reading and often it is a difficult and expensive set of testing to get an accurate diagnosis around something like dyslexia which, when undiagnosed, can set students back significantly in their academic progress and adversely affect their attitude to learning and engagement at school. I first came across this technology on the following video case study from 2015 and see that in March 2017 Lexplore raised USD$5.6million in investment funding to take this eye tracking software to the USA. Here is the original Microsoft video case study when the company was still known as Optoloxia in 2015:

Given how quick this testing actually is, combined with the huge volume of existing data from other readers, this holds out that tantalizing opportunity within technology to be considered a “game changer.” It may help remove that element of “teacher judgement” that often occurs in schools (always with the best of intentions), but instead use real data from thousands of readers who have had their eyes tracked during reading, to far more accurately diagnose readers with dyslexic patterns of reading. With this, the next step is to provide the required support to them to ensure they don’t fall behind.

I am always keen to discuss what I've written and hear your ideas so leave a reply here...

%d bloggers like this: