AtaxiaV

Version 1 - 2019

Evaluation System of Ataxia on Internet Web Browser

Dysmetria is a reduction in the ability to control the movement path, speed, and force that may cause serious impairment of motor functions. AtaxiaV is a tool for quantitatively evaluating the exercise control ability of patients by scientifically measuring and analyzing movement distance anomaly.  To this end, we proposed and implemented an algorithm that can quantitatively measure the severity of ataxia of the upper limbs by using the coordinates from tests such as diagonals, circles, rectangles, triangles, and targets on the touch screen, and analyzing the movement paths and motility using them.  

AtaxiaV

Version 2 - 2020

Evaluation System of Ataxia in 3D Environment using OpenCV​

AtaxiaV version 1, developed in a two-dimensional experimental environment, is currently being patent pending. AtaxiaV version 2, which can be tested in a 3D experimental environment, is in progress. We hope that our project will help patients suffering from Ataxia and doctors treat the patients. 

AtaxiaV

Version 3 - 2022

Diagnosis and Treatment for Patients with Ataxia

Version 3 was designed with a focus on rehabilitation, but it also has tests to help diagnose ataxia. While researching cases of patients with ataxia, we discovered that accurate diagnosis for children was crucial. There are currently no tools made specifically for child patients' rehabilitation treatment, which is an issue because the universal treatment methods can cause children to become bored and make it difficult to continue. 

So, we developed a 3D game using Unity and the Leap Motion Controller that works as both an evaluation system and rehabilitation exercise system so that patients with Ataxia, especially children, can continuously participate in testing and rehabilitation treatment. Our program requires relatively simple equipment and does not require a professional assistant or other special requirements. Since it is so easily accessible, it will enable extensive data collection. It is expected to help more accurately diagnose the types of ataxia through machine learning.