Dystech creates first dyslexia and motor dysgraphia screening app
In June, Australian startup and AWS EdStart Member Dystech, launched the world’s first screening app for dyslexia and motor dysgraphia. Dyslexia and dysgraphia impact between 10-20 percent of individuals worldwide. With this release, Dystech has the opportunity to change lives and accelerate testing for millions of individuals around globe. Dystech uses artificial intelligence (AI) and machine learning (ML) to create an app that transforms how education and healthcare organizations screen for this disorder.
Dyslexia is a neurological disorder that inhibits the brain from recognizing and processing letters, which often results in poor reading and handwriting. Traditionally, testing for dyslexia is done in person, and can be an emotionally exhausting, potentially expensive, and invasive process. Now, caretakers can download the Dyscreen app, fill out a short survey, then have the child read aloud words as they appear on screen. Shortly after completing the screening, users receive a comprehensive report on their likelihood of dyslexia.
Prior to launching the dyslexia screen app, Dystech launched a screening app for motor dysgraphia, a disorder of written expression that impairs writing and fine motor skills. Students or caretakers download the app, take a photo of their handwritten text, and within minutes receive a comprehensive assessment with 95.6 percent accuracy.
Dystech’s solutions remove barriers for testing and alleviate the challenges of time, expense, and physical location by providing a quick and accurate reading at home. In Australia, testing costs over $1400 USD and takes over four hours on average. With Dystech, all testing is under $20 USD and takes less than 10 minutes, resulting in a faster, cheaper diagnosis than scheduling a traditional appointment with a doctor.
How Dystech works
Using datasets of handwritten text pictures and audio recordings (from traditional learners and dyslexic/dysographic learners), Dystech applies machine learning techniques to order and analyze the differences.
To accelerate their machine learning techniques, Dystech uses Amazon Elastic Compute Cloud (Amazon EC2) P3 instances to deliver high performance computing in the cloud. Amazon EC2 P3 instances have been proven to reduce machine learning training times from days to minutes, as well as increase the number of simulations completed for high performance computing by three to four times.
Amazon EC2 P3 instances work seamlessly together with Amazon SageMaker to provide a powerful and intuitive complete machine learning solution. Amazon SageMaker is a fully managed machine learning platform that enables you to quickly and easily build, train, and deploy machine learning models. Amazon EC2 P3 instances can be integrated with AWS Deep Learning Amazon Machine Images (AMIs) that are pre-installed with popular deep learning frameworks. This makes it faster and easier to get started with machine learning training and inference.
According to Hugo Richard, chief executive officer and co-founder of Dystech, who is also dyslexic and dysgraphic, “Without AWS, I don’t believe we could have had the agility to manipulate our data the way we did. Machine learning requires us to be very agile in the way we prepare our data and AWS provides a great way to prepare and train data.”
As a team of passionate academics, entrepreneurs, and professionals, Dystech is dedicated to building an assessment system that globally empowers parents, teachers, and therapists to assess children with dyslexia and dysgraphia quickly, to take early action to improve their lives.
“As an organization that employs people with disabilities, we see firsthand the importance of Dystech’s work on improving understanding of and support for people with dyslexia,” said Elena Kelareva, chief executive officer of GippsTech.
Learn more about how AWS EdStart Members around the world benefit from technical training, networking, and mentorship by visiting the AWS EdStart website. Stay up-to-date on all AWS EdStart news and events by joining the AWS EdStart newsletter mailing list.