Review Machine learning and multi-omics in precision medicine for ME/CFS, 2025, Huang....Armstrong

Utsikt said:
Interesting idea! Although my typing speed and posting frequency isn’t always tied to current «local» health, and it would be difficult to isolate the ME-effect from other factors. Others have also pointed out how up time increases during PEM due to e.g. brainfog and forgetting things, yet it decreases when you getting sicker long term. Maybe AI would still be able to pick out a reliable pattern across multiple variables.
Click to expand...

Trish said:
Interesting idea. Typing speed also depends on what I'm typing about.
Factors affecting my typing speed and number of corrections I need to make include
- fatiguablity - gets slower if I go on too long - both cognitive and physical.
- what else I've done that week, day, hour and how close to crashed I am
- the subject matter and whether it requires a lot of thought or I'm just rambling or copy typing
- whether I'm touch typing on my laptop or one finger typing on my phone.
- mistake rate increases markedly as I fatigue, if pushing when crashed, understanding the words on the screen and being able to spell them deteriorates
- overall quantity of typing may not directly relate to state of health - also depends on whether there's anything I want to say, and what else I'm doing

So it's a complex picture, but I think could be useful. Perhaps it needs to be narrowed down to something like assessing typing speed and error rate on a set task. Combining and or correlating it with steps, time with feet on the floor, resting heart rate, HRV might be interesting.
Click to expand...

NelliePledge said:
My posts definitely tend to get longer and more wordy when I’ve got to my limits. I often struggle to realise this until I stop typing and realise I’ve been rambling. It takes quite a bit of concentration to keep to the point.
Click to expand...

Yes it would be a way to observe some of the exertion that isn't just walking (step count) or being upright (up time). I think at the very least it would be interesting data to monitor to see if it is useful.

Most continuous data collection devices are flawed but their value comes from being able to repeatedly provide the same data for hundreds to thousands of times, you can then build an average and look at things like variability, you'd look at these factors before and after treatment.
 
There appears to be a lot of confusion around the language we used, that sounds like we failed to communicate in a simple way and will do better in the future. Yes a student wrote the draft but we all reviewed and edited the writing as well as peer-reviewers. So this isn't a reflection of the student but the group and me.

The intention of the review was to discuss the benefits of this type of research in ME/CFS and why it should be explored more. We're disappointed that the writing is distracting from that goal.

I'm happy to see the critiques by the way, thank you for taking the time, especially @Hutan. I want to respond to each but am a bit time poor at the moment, will try get back to them.
 
Last edited:
MelbME said:
The intention of the review was to discuss the benefits of this type of research in ME/CFS and why it should be explored more. We're disappointed that the writing is distracting from that goal.
Click to expand...

My last take is that it feels like the writers were trying to justify the use of AI, and therefore might have chosen descriptions and phrases about ME/CFS that mesh well with how they want to talk about AI.

Creating the «perfect» problem for the tool, rather than picking the right tool for the problem? But that isn’t needed, AI is a good fit regardless due to its ability to deal with lots of data and spotting trends and patterns.

That being said, I’m very excited to see what can be done with AI!
 
The paper seems to get more assured and more useful as it goes on, as it gets into the actual tools and how they have been applied rather than talking about ME/CFS. I feel as though I'm getting to the good bits, but sadly am running out of steam to finish reading it right now.

I agree with @Utsikt that these tools are very useful, the work with big data is very important.
 
MelbME said:
We were just listing all the types of information that can be collected to interpret understanding of an individual or a disease. It wasn't targeted at something specific to ME.

Relevant information to ME could be hiding in places we don't suspect. But just to give an example, there are phone apps that can monitor user behaviour. You could track how slowly someone types words, how often they make posts on a forum, how often they use the device, etc. We have played around with the idea that this could be an objective marker or a factor in a suite of objective behaviour markers (perhaps tied to step tracking or up time). From speaking large biotech companies, an objective outcome measure for clinical trials is a major hurdle for them to get involved in this area of disease. So yeah, this is an example of why that type of data could be relevant to specifically ME.

Purpose of the paper was to summarize existing efforts and to highlight how this type of work is a good fit for a complex diseases like ME/CFS. I typically get my PhD students to do a review article of some kind for their benefit and to provide a nice summary for others interested in the topic.
Click to expand...

This thinking is clear and good to hear.

The point about the objective outcome measure being a major hurdle is useful insight.

I'm currently for various reasons thinking about new phone/watch (to find phone when I lose it) and it's brought up the question I've carparked for too many years of the various tracker apps because of compatibility/what could be used on what equipment. Of course (for the same reasons it got carparked for so long) my bandwidth on this has been along the line of snippets and trying to parasite other people's feedback. But I was intrigued that visible was using an arm band vs watches obviously using wrist and so on.

I've been as someone at the bottom end of severe, and bobbled in severe for quite a few years now hoping circumstances would become more amenable to health, intrigued to notice the 'lying down' thing.

And also really conscious of it because I've had this so long I feel like I need to be putting bits out there into the world no matter how awful I feel because the 'better times' don't come, and lack of understanding of how bad more severe is perpetuates this issue. Plus you want to exist somehow. So contact with the world, whether by laptop on good days or phone by hook or crook on other days is important. But what angle you are needing to be at really affects that.

I've noticed that when I'm feeling awful I need to lie so flat my body is looking for some inverting disappear into the ground position that doesn't exist. And when 'more well day' then I can spend a bit more time more sat up. The in-betweens have been interesting though as there is a lot of spectrum there (that you don't know/predict until you've got your good or bad position) and I think the amount of soft but supportive (and almost 'cuddling' with eg pillows) stuff under me ie how well I've nailed getting the pillow mound right makes a difference there in being able to tolerate a bit more angle in hip-shoulder because I'm so not having to engage any muscle the rest of the body is related and I've definitely struggled with holding my head (and have to have extra pillows either side for that as for some reason each cheek needs a rest frequently)

I mention this because of these different monitors and the question of which part of the body do you tie them to. My arm if it was looking at angle might be useless because I get such exhausted arms that when flat on my back I have to have pillows under them, but also have to do the same when not. And when completely 'lie flat' I'm as likely to need to be prone as on back. Plus I'm very sensitive to any rubbing or things not soft.

But if tech gets there then a t-shirt or vest (with a back that comes up to the back of the neck) seems the location. A stretchy soft, cotton-modal vest if tech could be embedded without creating rub (and would know front from back as it is worn) that can have angle programmed. And maybe looks at muscles around this area (so if at 30 degree and well propped all the way from hip to top of head these relax). I'm sort of taking inspiration from the old school 'how it was made' on CGI for eg lord of the rings type things but assuming things have moved on.

Something like a vest could perhaps pick up on the breathing issues I notice sometimes too.
 
Trish said:
Interesting idea. Typing speed also depends on what I'm typing about.
Factors affecting my typing speed and number of corrections I need to make include
- fatiguablity - gets slower if I go on too long - both cognitive and physical.
- what else I've done that week, day, hour and how close to crashed I am
- the subject matter and whether it requires a lot of thought or I'm just rambling or copy typing
- whether I'm touch typing on my laptop or one finger typing on my phone.
- mistake rate increases markedly as I fatigue, if pushing when crashed, understanding the words on the screen and being able to spell them deteriorates
- overall quantity of typing may not directly relate to state of health - also depends on whether there's anything I want to say, and what else I'm doing

So it's a complex picture, but I think could be useful. Perhaps it needs to be narrowed down to something like assessing typing speed and error rate on a set task. Combining and or correlating it with steps, time with feet on the floor, resting heart rate, HRV might be interesting.
Click to expand...
agreed

this has just reminded me that even many years ago I used to have to re-read paragraphs as I realised depsite having spent the requisite time aping looking at them nothing had gone in. These days that can be infinite, particularly strangely if it is a book or form vs eg this forum.

I have definitely however noticed of recent years that watching TV/film I just miss chunks and either have to rewind back, sometimes quite a few times or just go with the flow of watching but not watching and then having to catch that episode later and often out of sequence. Hence one reason I often stick with things I've already watched many times unless having a good point and it doesn't matter if it takes it out of me paying attention.

I'd be intrigued to find out my results on the touch typing but I suspect there are lots of other factors to control for. As long as I don't have to do grammar or punctuation or spelling then just typing as I think is often less exertion than talking these days. But my goodness if I'm having a bad day and need to reply to a short email or text with a direct question at a specific timeframe then it often isnt doable. So there is something huge about context.
 
MelbME said:
Yes it would be a way to observe some of the exertion that isn't just walking (step count) or being upright (up time). I think at the very least it would be interesting data to monitor to see if it is useful.
Click to expand...

Hi, Chris - From my perspective, typing speed and accuracy are very valuable measurements to look into. I am a writer and like probably Every other writer in the world I was working on a book during 2020. This happened to be the year that I deteriorated From mild to severe (due to GET essentially). Over the course of that year, my typing speed and accuracy got worse from draft to draft of my novella, to the point where I was noticably messing up and stopping more and more mid flow. Also I was not noticing a lot of mistakes in word choice or spelling/grammar that would previously have been very obvious to me, or that I would never have made previously, until I reviewed the printed drafts days later. There was a very strong correlation with typing inaccuracies and my ME getting worse.

On a related note, I am also a musician and my playing speed on guitar was noticeably reduced when I developed mild ME, even when my overall technique improved quite a bit. I was struggling with accurately playing fast licks that I would have easily played a few years previously. It wasn't only the speed but the frequency of errors in playing the wrong note etc. I would practice a lot and get more accurate with playing with a metronome slowed down, but when I tried to speed things up again I would keep making mistakes. This went way beyond the usual experience of playing things wrong enough times until you get them right. It took a lot longer to learn things and I simply could not play fast for as long or as fluidly as I could previously. It was quite perplexing as I was and undiagnosed at the time.

I was 26 when I got ME, and 29 during 2020 so I highly doubt it was natural aging related slowing down. Now of course I struggle to play and type at all. And am very uncoordinated and inaccurate when I do either!

So for these reasons I think this is a really valuable area to explore for researchers. Obviously thats all my n=1 experience though.
 
Last edited by a moderator:
You must log in or register to reply here.
Back
Top Bottom