Artificial Intelligence (AI) and CPAP, APAP machines
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Right...
_________________
Machine: ResMed AirSense™ 10 AutoSet™ CPAP Machine with HumidAir™ Heated Humidifier |
Mask: Eson™ 2 Nasal CPAP Mask with Headgear |
- chunkyfrog
- Posts: 34545
- Joined: Mon Jul 12, 2010 5:10 pm
- Location: Nowhere special--this year in particular.
Re: Artificial Intelligence (AI) and CPAP, APAP machines
I don't really trust people who choose palindromes as their usernames.
Illogical, I know--but I never claimed to be 100% rational.
As for TED talks, not everything that is in a presentation is brilliant, or even practical.
Some BS actually gets by . . .
(Ted, are you REALLY paying attention?)
Illogical, I know--but I never claimed to be 100% rational.
As for TED talks, not everything that is in a presentation is brilliant, or even practical.
Some BS actually gets by . . .
(Ted, are you REALLY paying attention?)
_________________
Mask: AirFit™ P10 For Her Nasal Pillow CPAP Mask with Headgear |
Additional Comments: Airsense 10 Autoset for Her |
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Probably less then what I've seen in the last responses here, but thanks for your valuable input - especially on palindromes, which is absolutely fascinating.chunkyfrog wrote:...Some BS actually gets by.
Should we one day become forum-friends :hug:, I'll overcome my natural shyness and share my batrachian phobias with you.
_________________
Machine: ResMed AirSense™ 10 AutoSet™ CPAP Machine with HumidAir™ Heated Humidifier |
Mask: Eson™ 2 Nasal CPAP Mask with Headgear |
Re: Artificial Intelligence (AI) and CPAP, APAP machines
i think you have over estimated what AI can do
I have followed this for 40 years or so
the problem is one size fits nobody
the A I would have to learn each patients specific needs
essentially that is what the algorithms in AVS and to some extent other types try to do
the problem is that people are not constant
so the best approach is the simple feedback servo control theory approach
the problem is we dont know what a given person might need
and the ability to learn it by trial and error is not a good approach
the other problem is ross ashby law of requisite variety
there are many feedback paths and we cant control all of them directly
so whatever we come up with will be a compromise and the best that we can do
AI is not going to be a magic cure
I have followed this for 40 years or so
the problem is one size fits nobody
the A I would have to learn each patients specific needs
essentially that is what the algorithms in AVS and to some extent other types try to do
the problem is that people are not constant
so the best approach is the simple feedback servo control theory approach
the problem is we dont know what a given person might need
and the ability to learn it by trial and error is not a good approach
the other problem is ross ashby law of requisite variety
there are many feedback paths and we cant control all of them directly
so whatever we come up with will be a compromise and the best that we can do
AI is not going to be a magic cure
sleepy1235 wrote:The general press and the technical press is full of information about Artificial Intelligence (AI). I am sure everyone has heard of self-driving cars, robots used in warehouses, robots used to do delivery in hospital etc.
The big thing they talk about now days is Deep Learning and software to do it.
It occurs to me that AI would be great for APAP machines. The software could learn from your sleep and optimize the APAP, or should I call it an AIPAP, to reduce events. In fact it might continuously learn to eliminate events. Deep Learning develops models and decision making models can be very complex and made more complex as AI learns. Also, an AI system could adjust as a person or their environment changes over time.
I read that doctors have to optimize control factors for APAP. That they try different settings and then see how it works over a month or so. There are just a few factors they have to adjust. Some times the factors drive a pressure increase that wakes the sleeper. AI could develop complex models which would be optimal and could have many factors and have very complex curves of increasing pressure preventing an event but not waking the patient.
I think the goal with AI might possibly be zero events for every evening. Since AI learns from failures as well as success it might be as the level gets very low it will stall out in improvement, unless perhaps there can be identified a "near" event to further optimization.
There are papers for using AI for Apnea in diagnosis, but I am not seeing the use of AI for running the APAP.
To have a new technology the first step is to imagine it and why it is necessary.
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Guest... thank you for your information (really), but in CPAP terms, the broad-sense definition of "titration" is... trial and error, this last being mostly human-induced, as we do tell the machines what they must execute. Given all the variables and factors that patients bring into the equation, that's all we have currently, and it's not a lot. Proof of this are the very weak statistics of the therapy: poor compliance rate, % of undiagnosed population, very poor "formal" support (mostly), etc etc. There is clearly a gap, which some us try to fill by taking ownership of our "ailment" with the help of tools like forums, with the help of compassionate sleep techs here and there...
My proposition is that like it has already done in many complex domains, AI could help fine-tune and speed up CPAP titration. Just that would be a huge improvement. Burn me at the stake
My proposition is that like it has already done in many complex domains, AI could help fine-tune and speed up CPAP titration. Just that would be a huge improvement. Burn me at the stake
_________________
Machine: ResMed AirSense™ 10 AutoSet™ CPAP Machine with HumidAir™ Heated Humidifier |
Mask: Eson™ 2 Nasal CPAP Mask with Headgear |
- chunkyfrog
- Posts: 34545
- Joined: Mon Jul 12, 2010 5:10 pm
- Location: Nowhere special--this year in particular.
Re: Artificial Intelligence (AI) and CPAP, APAP machines
The thing we must remember is that medicine is largely driven by MONEY,
and any use of AI is likely to be used solely to save it or make more.
Not necessarily a scenario for the utopia we've been hoping for.
and any use of AI is likely to be used solely to save it or make more.
Not necessarily a scenario for the utopia we've been hoping for.
_________________
Mask: AirFit™ P10 For Her Nasal Pillow CPAP Mask with Headgear |
Additional Comments: Airsense 10 Autoset for Her |
- chunkyfrog
- Posts: 34545
- Joined: Mon Jul 12, 2010 5:10 pm
- Location: Nowhere special--this year in particular.
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Old thread, but to address the recent reanimation:
Beware--this might be spam.
Not clicking on anything with "singapore" in its title.
I was not born yesterday.
Beware--this might be spam.
Not clicking on anything with "singapore" in its title.
I was not born yesterday.
_________________
Mask: AirFit™ P10 For Her Nasal Pillow CPAP Mask with Headgear |
Additional Comments: Airsense 10 Autoset for Her |
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Maybe we can get AI to teach Nano Bots to rebuild our body shortcomings. Jim
Use data to optimize your xPAP treatment!
"The art of medicine consists in amusing the patient while nature cures the disease." Voltaire
"The art of medicine consists in amusing the patient while nature cures the disease." Voltaire
Re: Artificial Intelligence (AI) and CPAP, APAP machines
Yes, control Windshield Wiper control box, $6,000 to replace the old way of intermittent WS Wiper control old way cost $60 seldom broke, what a bargain, as are the Ign controller, they replaced the points or magnetic pulse sensor that replaced it or the ECM computer. We are throwing $100 bills at Ten cent fixes, all we get for it is higher prices and less reliable systems, that's progress, sounds like the Government.jim22 wrote: ↑Sun Mar 05, 2017 7:40 pmI write software for airplanes for a living. We are not allowed to use "self modifying code", which is pretty close to what AI would be. I suppose based on the language used, maybe it would only be data that changed, but the bottom line is that it would be somewhat unpredictable how the machine would behave. Now the machine has physical limits, like it cannot physically create enough pressure to cause real harm. It could, however reduce the pressure below a breathable level, but in that case the masks provide a safety backup vent to prevent harm. To be useful, I think an AI based machine would need access to more information than a basic cpap machine has. If it could know sleeping position, sleep stage including being awake, and who knows what else, it might be able to learn what pressure settings work for different conditions. The advantage is that the machine could set itself up over time in ways that are too complicated and varied for one time sleep studies. I also think that it would not require a separate or expensive update to the processors used in the equipment we have now. There are quite powerful processors that are inexpensive and self contained. We use them to run our cars every day.
Jim
If we built a Pinto today it would cost $23,000, not $1,695, and it would burn twice as fast.

It would have No American Parts.
Use data to optimize your xPAP treatment!
"The art of medicine consists in amusing the patient while nature cures the disease." Voltaire
"The art of medicine consists in amusing the patient while nature cures the disease." Voltaire