Experiences and methods for observing, testing and tracking cognitive fatigueability and PEM - discussion thread

Speech. Word-finding difficulties, errors or slowness in speech, more "er"s and pauses, and perhaps tangentiality or a lower level of coherency as well.

I'm not sure if speech-to-text is good enough to measure the error rate here, yet, and I doubt there's an open-source system that will measure the timings between words to determine if they're atypical. ASR systems are obviously improving, though - I think OpenAI released a new one, Whisper, recently?

 

Here's another possibility: typing patterns. I'd bet that if I typed a paragraph or two and inter-keystroke timing was measured you'd get a correlation with how I was feeling on that particular day. (If you wanted to observe usual activity, rather than keep asking the user to type a sample paragraph, you'd need a kernel-mode driver or a DLL injected into every process that receives textual input on Windows. I've written such software in the distant past, albeit for a completely different purpose.)

 

For me, getting easily irritated, stressed, or emotional means pem is starting soon.

 

Also if I’m not in PEM it’s pretty easy for me to recall what I did in the past 10 mins. If I’m approaching PEM, I will have a blank.

 

You could track how the user's speed, error rate etc changes over the course of working on the same task (document/web form/etc) - does it worsen over time, and by how much? Are they fatiguing quickly, or slowly? You could also try to do this a bit more intelligently by tracking the user's activity at the time in an attempt to avoid task-specific differences: for instance, you could track data entered into web forms separately from typing into Microsoft Word.

There are possible non-cognitive ones too: the one I thought of straight away was gait analysis. I know I often feel less steady, and more prone to dizziness and vertigo, around PEM episodes. I'm not sure if the cameras on mobile devices and modern computers are good enough to operationalise this in an app, though. Several years ago there were attempts to commercialise gait analysis as a form of biometric authentication, so the technology definitely exists.

 

Yep, I'm totally hitting backspace much more frequently when I'm very fatigued.

This seems potentially useful. A keylogger that captures each button press and the time between. It might return something like this:

P - 7 ms
D - 5 ms
BACKSPACE - 3 ms
U - 6 ms
P - 5 ms
P - 2 ms
Y - 4 ms

Though practically, there's a huge privacy issue with this if its logging everything you type. It'd probably have to be made open-source and work completely locally (not send any data to another computer) to be trustworthy.

I think there are devices you can connect between a keyboard and computer to catch all the buttons you press.

 

You could measure all kinds of variables. Backspace use, yes, and inter-word as well as inter-keystroke timings (the time it takes to find a suitable word). Spelling & grammar error rates relative to a baseline. Mouse movement patterns. As for privacy - as long as you don't store the text on disk or send it over the network - just do the analysis and zeroise the memory that contains the analysed text. In order to work out whether any of this would be useful you'd need a small trial with a group of cooperating ME patients: measure absolutely every statistical & timing property you can think of, see which ones correlate with visual analogue scales / questionnaires.

Another few "fatigue/PEM detection" ideas (cognitive & non-cognitive):

- Eye-movement tracking. Frequency of eye movements, blink rate, etc, may correlate with inattention or fatigue (?)

- Breathing patterns may change as exertion becomes harder, and there are probably various measurable physiological correlates of that.

- HR relative to recumbancy time and step count. I think in some patients postural tachycardia may be worsened during episodes of PEM, so tracking how HR responds not only to going from supine to standing & sitting to standing but also by how much it increases based on the number of steps taken compared to a baseline. (I know some patients are already tracking their sitting/standing HRs & step counts but I'm thinking more about the relationship between the two.) I'd guess that data would be accessible through some smartwatch/wearable APIs.

ETA: I wonder if there are subtle movements - or lack thereof - associated with fatigue or PEM that could be picked up by a wearable's accelerometer?

 

Blurry vision is my first indicator and when my equilibrium starts to shift. It's not what I would describe as PEM, but I know I need to lie down soon.

 

Anything that needs rhythm (walking, playing music), balance (walking, moving from standing to sitting), spatial relationships (going through a doorway), and grip force calculation (picking up a plate) will show that I'm off.

Also having to make up nouns and adjectives because the real ones have disappeared behind the brick wall. Eg, reducing people to helpless giggles by describing the window in a tin whistle as the music hole.

I don't know whether facial expressions would work for me, as mine are very contrived due to autism. I had to learn to do them as deliberately as the way children learn to pronounce a sentence in another language.

Skin tone probably would, though, it's how colleagues at work used to know. It might only be because I have the fairest skin type humans are issued with and my colouring changes a lot during conversation. When I'm in PEM it apparently doesn't, it just looks grey.

 

Oh! Ability to sing on key. When I'm in a good period, I'm not winning any awards but it's mostly the correct pitch. When I'm in a rough patch, I feel bad for anyone within earshot.

 

While I relate to many symptoms above, my wife has other experiences. Could we consider starting multiple threads on the lesser symptoms occasionally to bring out the differences or commonality between sufferers? For instance the International criteria lists poor breathing / breathlessness, what does that mean for us as individuals and our experience? I could add IBS or allergy, night sweats, urine urgency, poor temperature control. While many of this non exhaustive list gets mentioned in passing I cannot see patient experience in a list per minor symptoms. Not sure if it should be public, but it’s very reassuring to read others have the same experience.