Can tracker readings predict daily health for PWME?

[TracyD]

For me, the answer is no.

Here's a blog post about my many, failed efforts to create a statistical model to predict my daily health using tracker data.

And here's the gist:
How well can the tracker data that’s available to me upon waking foretell my health status, as a person with ME/CFS (PWME), for the rest of the day? Over the past few years, I have applied a plethora of machine learning techniques to answer this question. The goal was to create an app to automatically predict PWME’s daily health each morning.

The result is disappointing: the best method will accurately predict whether my daily health will be ‘bad’ or ‘not bad’ only 57 percent of the time. Flipping a coin would result in 50 percent accuracy, so this is an improvement of only 7 percent.

I still believe that resting heart rate (RHR) and heart rate variability (HRV) generally change along with my health status, so what went wrong? My observation is that many other factors also influence these measurements, masking the relationship that I’m trying to model. The good-ish news is that a person likely can do a better job of taking these contingencies into account, making this a case when human learning probably outperforms machine learning.

 

[Rondo]

Thank you for posting this Tracy. I think you are right. Personally, I have pretty recently started using the Visible tracker and app. This platform also uses HR and HRV. It’s true that the morning check in doesn’t always seem very good at predicting how my day will go.. The developers do state that it won’t be in all situations.
However I still find it overall quite helpful because it shows me when I’ve over exerted myself and holds me accountable for taking a break. I still need to pay close attention to how I am feeling, but I am finding it useful in learning how to pace myself.

 

[ZeroGravitas]

Interesting blog. I've been tracking HRV, RHR, stability, etc, via Fitbit, Garmin, Visible, Phone apps, plus logging a lot of subjective metrics to a sheet. And yeah, the correlation between how I'm doing and the data from the trackers isn't significant, for me.

RHR does trend up with better function, I think being low on norepinephrine (and other catechols)... Except during acute infection, which has a very strong negative correlation, that overall throws my 2 years of eg Fitbit data into zero correlation territory... I'm aiming to post about this on Twitter, etc. Provisional (part 1) blog post here.

 

[TracyD]

Interesting blog. I've been tracking HRV, RHR, stability, etc, via Fitbit, Garmin, Visible, Phone apps, plus logging a lot of subjective metrics to a sheet. And yeah, the correlation between how I'm doing and the data from the trackers isn't significant, for me.

RHR does trend up with better function, I think being low on norepinephrine (and other catechols)... Except during acute infection, which has a very strong negative correlation, that overall throws my 2 years of eg Fitbit data into zero correlation territory... I'm aiming to post about this on Twitter, etc. Provisional (part 1) blog post here.

The annotated graphs on your blog post are great. I might try doing the same, for my own enlightenment.