Opinions/Experience re the ZEO?

General Discussion on any topic relating to CPAP and/or Sleep Apnea.

Opinions/Experience re the ZEO?

I purchased a Zeo and believe it is a great product with useful data output.
23
28%
I purchased a Zeo and think it is just so-so.
8
10%
I purchased a Zeo and don't like it.
5
6%
I am considering purchasing a Zeo.
24
29%
I have no interest in purchasing a Zeo.
11
13%
I don't know what a Zeo is.
11
13%
 
Total votes: 82

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Mon Apr 16, 2012 10:47 am

Quote from MaxDarkside:
If I use the Zeo information as an input to my analysis, the accuracy of the unit no longer matters, just as long as it is repeatable (consistent reading under same conditions)
...however...
If I use the Zeo directly as a performance measure, then it must be both accurate and repeatable.

As I use the Zeo as an input, technically, I don't care how accurate it is.
How can accuracy not matter if Zeo reported good sleep when you had bad sleep, and/or if Zeo reported bad sleep when you had good sleep? It seems like unaccurate results would cause your sleep habits to get worse, not better.
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 11:15 am

edm_msu wrote:Quote from MaxDarkside:
If I use the Zeo information as an input to my analysis, the accuracy of the unit no longer matters, just as long as it is repeatable (consistent reading under same conditions)
...however...
If I use the Zeo directly as a performance measure, then it must be both accurate and repeatable.

As I use the Zeo as an input, technically, I don't care how accurate it is.
How can accuracy not matter if Zeo reported good sleep when you had bad sleep, and/or if Zeo reported bad sleep when you had good sleep? It seems like unaccurate results would cause your sleep habits to get worse, not better.
Ed M.
Hi Ed,
The answer is above; "If I use the Zeo directly as a performance measure, then it must be both accurate and repeatable." However, if I use it as an INPUT to analysis, whereby I "chompulate" it and extract it's information to predict some other performance measure, it merely needs to be repeatable.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Mon Apr 16, 2012 11:25 am

MaxDarkside,
I did not word my post properly.

How can accuracy not matter if the Zeo OUTPUT reported good sleep when you had bad sleep, and/or if Zeo OUTPUT reported bad sleep when you had good sleep? The OUTPUT of Zeo is used as the INPUT of your analysis. It seems like unaccurate Zeo OUTPUT that you used as your INPUT would cause your sleep habits to get worse, not better.

Thanks,
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 11:33 am

edm_msu wrote:How can accuracy not matter if the Zeo OUTPUT reported good sleep when you had bad sleep, and/or if Zeo OUTPUT reported bad sleep when you had good sleep? The OUTPUT of Zeo is used as the INPUT of your analysis. It seems like unaccurate Zeo OUTPUT that you used as your INPUT would cause your sleep habits to get worse, not better.
If you are using the Zeo as measuring how good your sleep is, then you are using it as a performance measure and in that case it needs to be accurate and repeatable.
However, if it is used as an input to mathematical analysis, it merely needs to be repeatable (same output for same conditions).

You are CORRECT on the first part.
It seems paradoxical, that last part, but it is not. It's true (30 years in the biz).

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Mon Apr 16, 2012 11:49 am

If you are using the Zeo as measuring how good your sleep is, then you are using it as a performance measure and in that case it needs to be accurate and repeatable.
However, if it is used as an input to mathematical analysis, it merely needs to be repeatable (same output for same conditions).

You are CORRECT on the first part.
It seems paradoxical, that last part, but it is not. It's true (30 years in the biz).

II still don't get it. I'll exaggerate. Lets say that the Zeo is hooked up to someone who had an absolutely perfect night of sleep. The OUTPUT of Zeo showed a completelty horrible night of sleep. This completely unaccurate INPUT would be analyzed. As a result, the sleep would need to be "improved" since it was horrible. After many nights of trial and error, the Zeo is hooked up to the same person who had an absolutely horrible night of sleep. The OUTPUT of Zeo showed a completelty perfect night of sleep. The end result is that the repeatable and unaccurate Zeo OUTPUT caused the sleep quality to become much worse.
Am I missing something here?
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter
Last edited by edm_msu on Mon Apr 16, 2012 12:09 pm, edited 2 times in total.

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 12:04 pm

edm_msu wrote:I still don't get it. I'll exaggerate. Lets say that the Zeo is hooked up to someone who had an absolutely perfect night of sleep. The OUTPUT of Zeo showed a completelty horrible night of sleep. This completely unaccurate INPUT would be analyzed. As a result, the sleep would need to be "improved" since it was horrible. After many nights of trial and error, the Zeo is hooked up to the same person who had an absolutely horrible night of sleep. The OUTPUT of Zeo showed a completelty perfect night of sleep. The end result is that the repeatable and unaccurate Zeo OUTPUT caused the sleep quality to become much worse.
Am I missing something here?
Since in your hypothetical case you know that the persons had horrible and perfect nights sleep, the analytics would reverse the Zeo's output when using it as an input to the analytics. Then, since I require that to be repeatable, if the Zeo again showed a horrid night sleep, the analytics would know that means a good night's sleep and vis versa. If I used the Zeo brain waves as an input, it does not matter if Delta is 30% or 20%, just as long as it is consistent, right or wrong. If the Sleep Score was 99 when in fact it should have been 88, it does not matter as long as it is consistent when I'm using it as an input to analytics.

In commercial applications, pressures, temperatures, flow rates, etc. in manufacturing do not have to be correct in order to predict product quality, just consistent. They can even be very noisy (somewhat inconsistent). The analytics filters out the noise, and maps those conditions to product quality, even reversing their effect if necessary.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Mon Apr 16, 2012 1:03 pm

MaxDarkside,
You are assuming that the vice-versa output is known so it can be accounted for. Something like that could happen if a DC voltage input was reversed. As always, judgement is needed to verify that things make sense. I was using that to make a point. Your point is understood.
From your experience, how repeatable is the Zeo output?
Thanks,
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 1:14 pm

edm_msu wrote:You are assuming that the vice-versa output is known so it can be accounted for.
Not only did you stipulate that, I also make independent measures of how I feel (qualitative) and how I perform (quantitative). I can then try to map Zeo (and a bunch of other info) to these "knowns". So it is not an assumption in my case.
As always, judgement is needed to verify that things make sense.
Clearly so.
From your experience, how repeatable is the Zeo output?
Not fully sure yet, but repeatable enough to be useful. The correlations of metrics of sleep and performance are "soft" I'm finding. Much like marketing data analytics, which I do as well, the relationship between a person's feelings about a product and the product's features are "fuzzy" as is their "likelihood to buy". We humans are very "fuzzy" critters.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 1:26 pm

Let me show you how "fuzzy" it is. Below is a (not very good quality) picture of my Zeo Sleep Score vs. my response time doing a "whack a mole" image clicking test. The bottom axis is Sleep Score, the vertical axis is response time. Response time lower means faster, means better. You can see that as my Zeo sleep score gets higher (more to the right) that my response time goes faster (lower). So, this makes sense, but it is a VERY fuzzy relationship, but it is there. There is "noise" in both measures and this discards all other factors that impact my response time, ergo I could only just a wee bit estimate my performance from the Zeo Sleep score.

Apologies for the lack of quality in the image, but I reduced it so it would not fill the screen like a monster, but it gives you an idea of what I'm saying.

Image

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 2:00 pm

Now, let's presume that the Zeo Sleep Score is consistently backwards. Can I still get an equally good (albeit rough) estimate of my performance from it. Yup, as long as it was consistently backwards the analytical software would merely reverse the relationship between the Zeo sleep score to my response time. No problem.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Mon Apr 16, 2012 2:24 pm

One more comment in a row, before I get accused of "over-posting"

The closer to a physical measurement about your sleep the more consistent your results will likely be. If you think about it, there's a lot of assumptions between the current in your skin and a Sleep Score.

Skin Electrical =>(Assumptions about frequencies) => brain waves => (assumptions about wave characteristics and relationships) => Sleep Stage => (assumptions about noise filtering) => 30 second sleep stage => (assumptions about Deep, REM, Wake on Sleep Quality) => Sleep Score.

Wow.

Now, granted, analyzing the skin's electrical is a bit much, even for me, but that is nearest the truth in all this. I can with Zeo's raw skin signal, tell which direction my eyes move, left or right, and you can see "Spindles" and "complexes" of various sorts, which you cannot see in the brain waves, or sleep stages or the sleep score. Information is shed as you go through that chain, summarizing more and more, in the end, characterizing a WHOLE LOT of information into a single number. A single number therefore cannot possibly truly, fully characterize your sleep, and thus my advice (an others') to not try to maximize something so simplistic.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Tue Apr 17, 2012 1:05 am

By looking at how "fuzzy" or how much your data jumps around in the chart, I think that there should be multiple (maybe 10) nights data for every change in sleep habits. This gives a chance for the data to average out. The result could be way off if only one night of data was used.
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Tue Apr 17, 2012 7:36 am

edm_msu wrote:By looking at how "fuzzy" or how much your data jumps around in the chart, I think that there should be multiple (maybe 10) nights data for every change in sleep habits. This gives a chance for the data to average out. The result could be way off if only one night of data was used.
Correcto! I suggest measuring (at least looking at) how much your data "jumps around" (also known as variance or "standard deviation") without making any changes, night to night, and the longer you measure, the better understanding what the average is and the spread of the data. Statisticians suggest by rule of thumb (they call it the rule of large numbers) 30 samples (nights), but we generally don't have that much patience. 3 nights is a minimum to quantify the mean and variance, but that likely is not enough. Your "maybe 10" would be good, tho it probably on the edge of trying the patience for some people, not wanting to wait. Then make a change and record your data for some number of nights (3-30, probably 5-10 is enough). Then compare the shift in the mean of the measurement to the variance (jumping around). If the mean changes a little compared to how much the data is jumping around, then the change you made is not very significant, the shift in the mean could be due to just the jumping around. If the mean moves up or down by as much as the jumping around, you have an "aha!" moment. If you immediately see the result move more than the amount it varies night-to-night, you can suspect you have made a real change, but measure a few more nights to make sure.

This is why the veterans here say you need to make a change and see what happens "over a few nights", no less than 3 nights, better if it could be a week or more.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
MaxDarkside
Posts: 1199
Joined: Sun Dec 18, 2011 4:21 pm
Location: Minneapolis, MN

Re: Opinions/Experience re the ZEO?

Post by MaxDarkside » Tue Apr 17, 2012 8:30 am

My narrative above presumes a change has an immediate effect, but some changes have an accumulative effect, that is, it takes some days for the change's effect to accumulate and come to "full power". In those cases you have to measure for even more nights. However, unfortunately, few of us know which changes are immediate vs. accumulative. A mask change on leaks we would presume would be immediate. Changes in diet or sleep quality might take some days to shift, or even start shifting after making the change. It's not simple. Life isn't simple. Sigh.

_________________
Mask: Quattro™ FX Full Face CPAP Mask with Headgear
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: CMS-50E Oximeter, Zeo Bedside, Software: Comm'l grade AI analytics server & tools & SleepyHead
Do or Die... Sleep Apnea killed me, but I came back. Click for my story
Please visit my My Apnea Analytics blog. Maybe we can help each other.
54 yrs, 6' 1", 160->172 lbs

User avatar
edm_msu
Posts: 198
Joined: Thu Mar 15, 2012 10:45 am
Location: USA, Michigan

Re: Opinions/Experience re the ZEO?

Post by edm_msu » Tue Apr 17, 2012 11:06 am

MaxDarkside,

Good point about someone's patience vs accuracy. I'm an engineer that works for a company that requires people to Cover Their Butt. So I automatically and always consider accuracy only, without considering the required time. There are times where I could use good judgement but don't because I don't have the data to back me up. So I'll fully test even though I already know what the answer is. BTW: I am not being singled out on this.

Anyways, people who are using Zeo do not have to Cover Their Butt. They only answer to themselves and only need to make the correct decision. So probably five nights data would do this, as you suggested.
Ed M.

_________________
Humidifier: S9™ Series H5i™ Heated Humidifier with Climate Control
Additional Comments: Like SleepyHead software better. CMS-50F Oximeter