The problem Detection of Dyslexia using ML solves

Dyslexia is a learning disorder that involves difficulty reading due to problems identifying speech sounds and learning how they relate to letters and words (decoding). Signs of dyslexia can be difficult to recognize before child enters school, but some early clues may indicate a problem. For kids who have dyslexia, the brain has a hard time connecting letters to the sounds they make, and then blending those sounds into words. So to someone with dyslexia, the word "cat" might read as "tac." Because of these mix-ups, reading can be a slow and difficult process. Severity varies, but the condition often becomes apparent as a child starts learning to read. When dyslexia goes undiagnosed and untreated, childhood reading difficulties continue into adulthood. So, the aim of our model is to detect dyslexia in kids. For this, we created a survey and quiz and the answers given by the kids were the basis of forming a database and using that database, we created an ML model to predict whether the child has severe dyslexia, mild dyslexia or no dyslexia at all. The early and faster diagnosis of dyslexia can improve help the child over come problems such as not being able to reach their his or her potential, can prevent them from having low self esteem and anxiety issues significantly, as it can promote timely clinical treatment. Through our website, people can detect whether their kids have dyslexia or not by themselves and consult the doctor accordingly. A lot of time and money can be saved.

Challenges we ran into

We ran into quite a few issues while building this model:

1. We wanted to deploy the model using streamlit but we encountered login error as we could not connect to the database server so we dropped the idea
2. We even tried to store HTML survey and quiz data to SQL using PHPMYADMIN but again we were'nt able to connect with the server so we had to drop that idea as well.
   So we decided that instead of deploying the model we'll just upload it on github and show it's working