Automation of traumatic brain injury diagnosis through an IoT-based embedded systems framework

Traumatic Brain Injury (TBI) is a prevalent cause of death and disability with over 3.8 million annual cases and 130 daily deaths in the United States alone. Whenever athletes suffer head trauma, concussion field tests that measure their perceptiveness and cognitive abilities are commonly administered. However, these tests have limited accuracy due to the lack of quantitative data basing the diagnosis, and often those administering concussion tests feel pressured to keep athletes playing in the game despite cognitive impairment. To solve this, an inexpensive diagnostic helmet targeting youth sports teams was created, providing quantitative data regarding how much head trauma an athlete has experienced. The helmet is connected to a web-based application system that stores real time data regarding the impact of the head injury, the region of the brain impacted, the time of injury, and speed at which the injury occurred, allowing for the design of more patient-tailored treatment plans. The device and web application were programmed using JavaScript, HTML, CSS, and the Node.js platform in the Intel Edison IoT IDE. Once the force sensitive resistors register an impact significant enough to cause a concussion based upon an algorithm that takes into consideration the player's height and weight, a text message is automatically sent to local paramedics through the Twilio API. This device therefore removes existing bias involved in diagnostics, allows doctors to more accurately handle injuries, and helps ensure player safety.