Hackaday Prize Entry: Seizure Detection By EEG

For those that suffer them, seizures are a dangerous thing. Outside the neurological effects, there is always the possibility of injury from the surrounding environment as well – consider the dangers of having a seizure near a busy road, or even simply a glass table. Some detection methods exist for seizure sufferers, but they are primarily based on detecting the jerking motion of the patient. [akhil2001us] thinks it’s possible to do better – by measuring brainwaves to detect the onset of seizures.

The build is centered around the Neurosky Mindwave headset. This is an off-the-shelf product designed specifically for capturing EEG data. It outputs raw brainwave data which is key for doing proper analysis. The project then uses an Arduino Mega to tie everything together, along with some Sparkfun Bluetooth modules to talk to a cell phone to send an SMS for help in the event of a seizure.

The real difficulty in a project like this comes from developing an algorithm that can reliably detect seizures, as well as a unit robust enough to work in the real world. It’s no use if your headset is detecting a seizure in progress, but the help message is never sent because a wire fell out of your breadboard. It’s considerations like this, combined with the threat of litigation, behind why medical devices are so rigorously engineered and certified. For a proof of concept, however, such concerns are not as important.

We’ve seen Mindwave builds before – brainwave research is an exciting field!

13 thoughts on “Hackaday Prize Entry: Seizure Detection By EEG

  1. The headset already has bluetooth capability so why does one need an external bluetooth module and Arduino to talk to a cell phone? Why not just go from headset to cell phone and let the cell phone do the analysis?

    Also, the device (please correct me if I am wrong) uses a single vector detection scheme so other regions of the brain whose electrical impulses are orthogonal to the detection direction will not be sensed. So this would mean that a partial seizure can be missed.

    In the case of a seizure being bad enough to cause fainting or brain damage (such as in status epilepticus), a pulse-ox may be better suited.

      1. Of course you can’t prevent brain damage with a pulse ox. There is nothing about prevention of anoxia in my text. If you are going to sit around and wait a couple of minutes while your patient is seizing then that is just wrong. Suffice it to say, don’t fall into the trap of relying on technology when some good common sense and physical exam will tell you otherwise.

  2. Here comes IoT for the brainwaves now too, eh?

    I applaud the effort and work. It will take a lot more leads and processor to do the job. Wright Brothers flew on a wing and a prayer from just kites though. Good idea. Definitely hacking!


  3. Great work and good luck defending yourself from all the sceptics, but there are more things to look at, like trying to do something to stop the seizures once you know it is coming. As somebody that has an untreatable brain tumor, I have some of my own designs that stops seizures. Havent had one in the 2 years now that I started using it, but I have s lot of other issues, that I can only treat with various electrical impulses after it occurs. Still looking for a predictave EMG to warn me when my breathing is about to seize, or my eyes are going to stop working. Lots of sceptics out there, including 90% of the medical profession. Heck, if Imlistened to the doctors and the sceptics, I would have died 3 years ago, but only by using my mind, reading as many research papers as possible, and experimenting on myself am I still alive.

    1. There are skeptics out there because some have put in a couple of years to try to solve the same problem so in bringing up valid issues they will hopefully reduce the chance of you wasting your own time/money only to stumble upon these issues yourself. Perhaps even some of the skeptics are the people that wrote the papers you are reading. You don’t have to take heart to what everyone says but you do at least need to listen and think about it.

      If 90% of medical profession are skeptical then perhaps it may be time to look at your re-evaluate your idea. To put it in general less than PC terms: “If everyone around you seems like an asshole, you’re the asshole”.

  4. Yes, the mindwave can detect seizures and other big events in brain, but has serious limitations.
    It outputs a 1saple/seconds, the bluetooth connection is weak, eats 1AAA battery per day and can’t be worn for long time else you get a sore earlobe.

    Considering these limitation is a nice entry EEG, very light and not invasive.

    I really don’t understand why an arduino is used as a middle man. The headset has an handy Android SDK with a working example(albeit the code isn’t that great, all the views are generated by the core activity, which is bad practice).

  5. My PhD thesis deals with EEG processing using Dicrete Wavelet Transform and Linear Discriminant Analysis for spike and seizure detection. I used several hours of EEG data to find correlated features to extract from the EEG signal. The algorithm I developed, calculates de DWT with 4 decomposition levels of 2 mother wavelet and calculates just 3 descriptors of each decomposition level. It detects spike with a very high accuracy. The best results were achieved using a EEG sample rate of 1KHz. It is a lot of data, and I think it is not a task for an Arduino. But it is doable for a good smatphone. Here is one of my articles: http://www.sciencedirect.com/science/article/pii/S0167865516303737

Leave a Reply

Please be kind and respectful to help make the comments section excellent. (Comment Policy)

This site uses Akismet to reduce spam. Learn how your comment data is processed.