One of our team members is an undergraduate intern at Boston Children's Hospital in the epilepsy center. Sudden unexpected death in epilepsy (SUDEP) is the most prevalent cause of epilepsy related deaths, most often causing respiratory arrest during sleep. The American Epilepsy Society estimates that as many as 42,000 deaths are caused by seizures each year. SUDEP accounts for 8-17% of the total deaths in people with epilepsy according to a study by New York Methodist Hospital. A Harvard-MIT study indicates a strong correlation between skin conductance and generalized tonic-clonic seizures, which indicate a higher risk of SUDEP. Traditional seizure monitoring technologies fail to provide any effective means to assist in the prevention of epilepsy related deaths.

What it does

Seisir is designed to detect life-threatening seizures, and then trigger text notifications to a caretaker for help or signal an implantable device that could release medication. Although still in development, our current version of Seisir intakes data from a custom built biosensor that identifies changes in skin conductance as well as a six-axis accelerometer and gyroscope. Data is processed in real time locally on an Arduino 101 board powered by Intel. Data is uploaded to a secure server and can be accessed via a mobile Android device. In cases where Seisir detects a high likelihood of seizure activity, the program contacts a caretaker or medical staff via text, or could signal an implantable device. Seisir has a strong potential to save lives by notifying others in emergency cases.

How we built it

Our current program utilizes a combination of technologies starting with the an Arduino 101 board powered by Intel. The program connects the android device via Bluetooth with a mobile application to obtain various sensor data. This data is then passed through the app to the cloud. Our program identifies seizure activity from the sensor data originally recorded by custom biosensors. The cloud system, android app and Arduino board all monitor for abnormal activity, specifically moments when seizure activity is identified. Upon receiving a seizure alert, the android app notifies emergency contacts via a traditional text message.

We intend to improve the accuracy of our machine-learning platform by creating a research database wherein healthcare providers can manually mark seizure activity as well, minimizing any false detection rate.

Challenges we ran into

Since the Seizure platform requires integrating a combination of multiple different technologies, devices and programming languages. This cross compatibility created the majority of our implementation challenges.

Accomplishments that we're proud of

We successfully developed a custom biosensor using only wires, resistors and code that can successfully detect changes in skin conductance, a major factor in identifying seizure activity.

What we learned

We learned how to implement and code on an Arduino 101 board and connect biosensors. We believe that Seisir demonstrates that the Arduino board could spearhead significant clinical advancements.

What's next for Seisir - Epilepsy Detection and Treatment Device

It is our hope that the Intel technologies behind Seisir have the opportunity to be used in a research setting that is clinically relevant to seizures and other epileptiform activity. Since one of our team members interns within the neurology department at Boston Children's Hospital and works with epilepsy patients on a daily basis, it is our hope that the Seisir / Intel combination platform have the opportunity to be tested within a clinical setting.

Share this project: