Preprint System and Method to Determine ME/CFS and Long COVID Disease Severity Using a Wearable Sensor, 2024, Sun et al

Dolphin

Dolphin

Senior Member (Voting Rights)
https://arxiv.org/abs/2404.04345

[Submitted on 5 Apr 2024]
System and Method to Determine ME/CFS and Long COVID Disease Severity Using a Wearable Sensor

Yifei Sun, Suzanne D. Vernon, Shad Roundy

Objective:

We present a simple parameter, calculated from a single wearable sensor, that can be used to objectively measure disease severity in people with myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) or Long COVID. We call this parameter UpTime.

Methods:

Prior research has shown that the amount of time a person spends upright, defined as lower legs vertical with feet on the floor, correlates strongly with ME/CFS disease severity. We use a single commercial inertial measurement unit (IMU) attached to the ankle to calculate the percentage of time each day that a person spends upright (i.e., UpTime) and number of Steps/Day. As Long COVID shares symptoms with ME/CFS, we also apply this method to determine Long COVID disease severity. We performed a trial with 55 subjects broken into three cohorts, healthy controls, ME/CFS, and Long COVID. Subjects wore the IMU on their ankle for a period of 7 days. UpTime and Steps/Day were calculated each day and results compared between cohorts.

Results:

UpTime effectively distinguishes between healthy controls and subjects diagnosed with ME/CFS (p=0.00004) and between healthy controls and subjects diagnosed with Long COVID (p=0.01185). Steps/Day did distinguish between controls and subjects with ME/CFS (p=0.01) but did not distinguish between controls and subjects with Long COVID (p=0.3).

Conclusion:

UpTime is an objective measure of ME/CFS and Long COVID severity. UpTime can be used as an objective outcome measure in clinical research and treatment trials.

Significance:

Objective assessment of ME/CFS and Long COVID disease severity using UpTime could spur development of treatments by enabling the effect of those treatments to be easily measured.

https://twitter.com/user/status/1778436254062854405
Click to expand...
 
Last edited:
If they tied this data in with a food journal, they might find other correlations which might be helpful for improving quality of life (by avoiding problematic foods). The same holds true for computer time, social activities, etc. Those of us who are more severe might have trouble keeping detailed records, so any tools to reduce that burden would be helpful. We could use a wearable AI ... with a user-controlled setting for nagging.
 
Yeah, upright time or time spent lying down has been the best measure for MECFS disability in my experience. Ankle however is not the most ideal place. I remember spending lots of time sitting with my feet raised to the point that my lumbar spine got bent. That was only way I could get a relief from fatigue and ache, short of lying down. Better place would be the torso or upper arm for measuring time spent lying down.
 
I'm skeptical because I spend a lot of time sitting, which if I remember right, would not be counted as being upright by these researchers. I have to lie down to take rest breaks because even sitting becomes stressful over time. Still, my time upright is probably not far from that of a healthy but very sedentary person, despite still having significant limitations that just aren't captured by this kind of test.

My feeling is that this captures just one aspect of ME/CFS related disability.
 
Last edited:
Dolphin said:
System and Method to Determine ME/CFS and Long COVID Disease Severity Using a Wearable Sensor
Click to expand...
The title feels like something that comes in association with an attempt to patent the idea.

Jonathan Edwards said:
Seems a simple and sensible observation.

I would like to see more attention paid to patterns over time, rather than just amounts, of activity, but in a sense this suggests a pattern, which may be worth tracking over time.
Click to expand...

I've wondered if you could model PEM in activity measurements so you would recognize a level of activity that with some delay leads to a decrease in activity (or standing time). I had wondered if something like a Hawkes process (or there are more flexible neural net based versions) could be used to model this. The notion for a Hawkes transform, I believe, is that you model a process as having particular arrival rate (corrosponding to normal activity) then you have additional processes process that models an increase in arrival rates based on some event that then activate for a given (potentially random - as in sampled from a random distribution). Kind of the opposite from PEM but from what I remember looking at this a few years ago the neural hawkes process supported subtractive processes.

My point is if feels like there could be some interesting processing done on monitoring trace data to recognize certain patterns that we would expect and perhaps parameterize them for an individual.
 
I do think we need more work in this type of area in terms of monitoring to understand the dynamics of ME and also I wonder if this would be done as part of any sample collection (in terms of blood etc) as I think there is work looking at PEM and changes in some things measures - I heard Alain Moreau talk recently about some of his PEM work where he induces small amounts of PEM and looks for changes. If ME is based on a dynamic process then some measures will change according to activity so if you randomly sample without knowing activity/PEM levels then you could end up seeing something really quite random and unpredictable.
 
poetinsf said:
Yeah, upright time or time spent lying down has been the best measure for MECFS disability in my experience. Ankle however is not the most ideal place. I remember spending lots of time sitting with my feet raised to the point that my lumbar spine got bent. That was only way I could get a relief from fatigue and ache, short of lying down. Better place would be the torso or upper arm for measuring time spent lying down.
Click to expand...

I think a combination of upright time as measured here, time lying down and steps could be very useful.

I like this version of upright time with an ankle worn device because I think there is a specific problem with sitting feet on floor being much more problematic than sitting with legs horizontal. In my case that has been a noticeable change as my ME/CfS has become more severe.
 
Hoopoe said:
My feeling is that this captures just one aspect of ME/CFS related disability.
Click to expand...
Undoubtedly. But I think it would be asking too much of a single measure to capture everything, let alone everything in detail. As a broad measure of physical and orthostatic function this looks as good as anything we've seen to date.

That's assuming the readings are reasonably accurate. I'm still shocked at the very different readings I got from 3 different devices worn at the same time for step count and sleep, complete random inconsistency. It was a few years ago so hopefully the tech has improved.

But I wonder how such a position detecting device would handle a body position I spend quite a bit of time in, and I don't think I'm the only one. I'm talking about reclining either on a recliner chair or propped up in bed on pillows, with feet off the floor but knees pulled up (easier on the lower back than legs stretched straight out). In that position the ankles are at an angle at the borderline between feet up and feet down if you compare to the diagram in the paper. So would the device register that correctly as feet up or wrongly as feet down?

I've only skimmed the paper, maybe they explain it and I missed it?
 
Does someone wish to break this shocking discovery (joking) to the ME Association i.e. they could follow this protocol to monitor patients - they could also use patient reported outcomes and compare the results! In fact, if they did that they may actually get some useable data!

Haven't read the above study.
 
These are the 2 most comfortable positions when I'm upright. I think it pumps blood back up? I can't sit with my legs dangling for very long, it's very uncomfortable.
Screenshot 2024-04-12 073729.png
Screenshot 2024-04-12 073759.png
Click to expand...
 
Last edited by a moderator:
You must log in or register to reply here.
Back
Top Bottom