EEG + CPAP

ironhands wrote:How many would be interested in tracking EEG data along with their respiratory data?

It wouldn't take "much" effort to incorporate dry EEG sensors into the headgear.

I've been thinking of working on my own sleep tracking software using a commercial grade EEG unit, but, it'd run me about $2k to buy the hardware($300) and software dev kit ($1500), so if people wouldn't want it, I'm not going to break my bank just to follow my own sleep states

Not me thanks. The regular nightly CPAP data is enough for me spend my valuable time on pretending to understand. There is a reason why an MD needs to read the hundreds and hundreds of pages of data generated in a true nocturnal EEG. Some other basic system would be no more than that sleep tracker getup they already sell at Best Buy, and likely as 'bout as worthless in terms of accuracy or validity, or usefulness vis a vis further tweaking pressure settings. Just my 2 cents...

hyperlexis wrote:

ironhands wrote:How many would be interested in tracking EEG data along with their respiratory data?

It wouldn't take "much" effort to incorporate dry EEG sensors into the headgear.

I've been thinking of working on my own sleep tracking software using a commercial grade EEG unit, but, it'd run me about $2k to buy the hardware($300) and software dev kit ($1500), so if people wouldn't want it, I'm not going to break my bank just to follow my own sleep states

Not me thanks. The regular nightly CPAP data is enough for me spend my valuable time on pretending to understand. There is a reason why an MD needs to read the hundreds and hundreds of pages of data generated in a true nocturnal EEG. Some other basic system would be no more than that sleep tracker getup they already sell at Best Buy, and likely as 'bout as worthless in terms of accuracy or validity, or usefulness vis a vis further tweaking pressure settings. Just my 2 cents...

As I said, it's not useful for clinical evaluation, obviously. The reason an MD needs to interpret the data (after the RPGST scores it) is looking for things to diagnose. You don't diagnose problems with a CPAP, it's used to treat. It would be very useful for determining how long a person spends in each sleep state, and the number of neurological arousals during sleep - which, when lined up with the graphs showing leaks, and apnea events, would show how severe they might be on your overall nightly sleep.

I see this as possible feedback tool for insomnia;
Of course, it would be most effective coupled with a coaching program (preferably OFF-line),
but similar to the "coaching" for Zeo. I found it a nuisance, but if I had insomnia . . .
Nothing like an interactive behavioral modification program; of course, just the
sleep hygiene notes should work somewhat by themselves, but for the really hard cases--feedback!

I am not sure when the Melon SDK will be available to developers, but updates are posted every few weeks at http://www.kickstarter.com/projects/806 ... re-your-fo# and people still do post questions to them there as well. Can't beat the $100 either.

BTW, the Emotive.com folks have a new model in the works called "Insight" - there are only 4 days left to "pre-order" for next year at $229 if interested in 5 electrodes. Only one person asked about sleeping with it that i noticed.

Also, before you start building your own headband check out this site too: http://openeeg.sourceforge.net/doc/ they share their projects there.

Chask

ironhands wrote:

TheChuckster wrote:My final engineering project at school was pretty much a DIY EEG with real-time data. There's documentation online at:

http://people.ece.cornell.edu/land/cour ... m55_mj294/

Well done for the $75 budget!

I'd like to get a price on the basic Neurosky chip for the basic amplification processes. Between that and a typical arduino, as you demonstrated, getting the data to the PC for under $100 is simple. From there it's just a matter of determining sleep states. That's just "simple" number crunching. I wonder why the big names haven't added this sort of feature to their headgear; the data would be useful to many, and they could jack the price up a few hundred dollars for <$20 in raw materials. They wouldn't need anything more than the amplifier, since there's already a microprocessor in the CPAP anyway.

Thanks!

CPAP manufacturers would restrict it so that only doctors can view the EEG data. The headstraps need a Zeo-like sensor so its a little more complicated. But yeah, ADC+amplifier as far as hardware goes, plus FFT (can even be post-processed). I'm pretty sure the ARM CPU at least in my S9 does not have an ADC. Why Neurosky? I guarantee all they are doing is a similar inst amp with secondary and maybe tertiary op-amp stages with filters. Take a look at the OpenEEG schematics.

Chask wrote:I am not sure when the Melon SDK will be available to developers, but updates are posted every few weeks at http://www.kickstarter.com/projects/806 ... re-your-fo# and people still do post questions to them there as well. Can't beat the $100 either.

BTW, the Emotive.com folks have a new model in the works called "Insight" - there are only 4 days left to "pre-order" for next year at $229 if interested in 5 electrodes. Only one person asked about sleeping with it that i noticed.

Also, before you start building your own headband check out this site too: http://openeeg.sourceforge.net/doc/ they share their projects there.

Chask

Unfortunately the emotiv units are really bulky. Very well constructed, and the data from them is pretty reliable from my understanding. The cost is also a little high for what most people would want to do. It'd be really nice to incorporate one with the oculus rift and the razer hydra though

TheChuckster wrote:

ironhands wrote:

TheChuckster wrote:My final engineering project at school was pretty much a DIY EEG with real-time data. There's documentation online at:

http://people.ece.cornell.edu/land/cour ... m55_mj294/

Well done for the $75 budget!

I'd like to get a price on the basic Neurosky chip for the basic amplification processes. Between that and a typical arduino, as you demonstrated, getting the data to the PC for under $100 is simple. From there it's just a matter of determining sleep states. That's just "simple" number crunching. I wonder why the big names haven't added this sort of feature to their headgear; the data would be useful to many, and they could jack the price up a few hundred dollars for <$20 in raw materials. They wouldn't need anything more than the amplifier, since there's already a microprocessor in the CPAP anyway.

Thanks!

CPAP manufacturers would restrict it so that only doctors can view the EEG data. The headstraps need a Zeo-like sensor so its a little more complicated. But yeah, ADC+amplifier as far as hardware goes, plus FFT (can even be post-processed). I'm pretty sure the ARM CPU at least in my S9 does not have an ADC. Why Neurosky? I guarantee all they are doing is a similar inst amp with secondary and maybe tertiary op-amp stages with filters. Take a look at the OpenEEG schematics.

Probably, but I'm sure there'd be a way to get the "professional" software version. I just like Neurosky because of the large scale mass production, same reason people like the Arduino, it's ready, it's available, and there's other resources. Haven't seen OpenEEG before, but that'd probably be a better solution as their are likely a lot more hobbyists than you'd find on Neurosky, since I don't think they make them available to the general public.


Just found this: https://www.olimex.com/Products/EEG/Ope ... e-hardware

Completely ready to go, $100, just needs electrodes to be mounted, and software developed. Seems there's a lot of code already available on sourceforge.

Lol, they also sell the completed electrodes. $140, and the BioEro freeware is pretty decent for tracking sleep, just not on a nightly basis for tracking or summary of stages.