Association of digital measures and self-reported fatigue: a remote observational study in healthy participants and participants with... 2023 Rao

Full title: Association of digital measures and self-reported fatigue: a remote observational study in healthy participants and participants with chronic inflammatory rheumatic disease

Background: Fatigue is a subjective, complex and multi-faceted phenomenon, commonly experienced as tiredness. However, pathological fatigue is a major debilitating symptom associated with overwhelming feelings of physical and mental exhaustion. It is a well-recognized manifestation in chronic inflammatory rheumatic diseases, such as Sjögren’s Syndrome and Systemic Lupus Erythematosus and an important predictor of patient’s health-related quality of life (HRQoL). Patient reported outcome questions are the key instruments to assess fatigue. To date, there is no consensus about reliable quantitative assessments of fatigue.

Method: Observational data for a period of one month were collected from 296 participants in the United States. Data comprised continuous multimodal digital data from Fitbit, including heart rate, physical activity and sleep features, and app-based daily and weekly questions covering various HRQoL factors including pain, mood, general physical activity and fatigue. Descriptive statistics and hierarchical clustering of digital data were used to describe behavioural phenotypes. Gradient boosting classifiers were trained to classify participant-reported weekly fatigue and daily tiredness from multi-sensor and other participant-reported data, and extract a set of key predictive features.

Results: Cluster analysis of Fitbit parameters highlighted multiple digital phenotypes, including sleep-affected, fatigued and healthy phenotypes. Features from participant-reported data and Fitbit data both contributed as key predictive features of weekly physical and mental fatigue and daily tiredness. Participant answers to pain and depressed mood-related daily questions contributed the most as top features for predicting physical and mental fatigue, respectively. To classify daily tiredness, participant answers to questions on pain, mood and ability to perform daily activities contributed the most. Features related to daily resting heart rate and step counts and bouts were overall the most important Fitbit features for the classification models.

Conclusion: These results demonstrate that multimodal digital data can be used to quantitatively and more frequently augment pathological and non-pathological participant-reported fatigue.

Open access, https://www.frontiersin.org/articles/10.3389/fdgth.2023.1099456/full

 

Off to a very poor start.

However I hope we see more attempts to objectify this, but the problem remains that there is nothing to calibrate this with. There needs to be a "ground truth" to validate answers, otherwise it's basically calibrating guesstimates with guesstimates. It's not calibrating how many Celsius degrees qualifies as "hot", it's calibrating one's perception of what is hot with another's, all of which change based on context.

Measurement is one of the hardest things to do in science. It took centuries to achieve this with the physical properties of nature, with rigorous experiments that were replicated independently. And now most of the standard measures are built on one another, steps that cannot be ignored. Astronomy and cosmology do the same, building a ladder of measurement that begins with parallax and works out from there to distances that can't be worked out this way.

Otherwise this is the same problem with AI: if you train a neural network with imprecise data, you are training a bad neural network. It doesn't magically work otherwise when it's people. It's possible to fix a subjective scale to an objective value, like the knobs on a stove, 5 means little, but it works out to a precise wattage, unknown to the user.

I said it recently, but I don't think it's possible to study subjective experience from a third party perspective. It's as pointless as alchemy was. Especially considering how activity usually follows an increase in energy, and not the other way around. But not always. It's not fixed, it's fuzzy, and not just because of perception.

 

Oh, I did not notice this. But it doesn't help clear up the confusion of using the same word for a different thing. Tiredness and pathological fatigue are indeed so very different, but here they are using the same root word. It's so often used precisely to cause confusion, the biopsychosocial model has really done nothing but throw huge wrenches in the machine of medicine.

I'm not sure what kind of reaction we'd get if we started using "pathological fatigue" instead of just fatigue. Probably some lecture about there being no pathology.

 

Oh, dang it.

Then again, modern astronomy did spring up out of astrology. It took centuries to get those measurements and it was mostly astrologers doing it for most of it. But really that's all astrology contributed, and mostly accidental.