Using apple watch ECG data for heart rate variability monitoring and stress prediction: A pilot study, 2022, Velmovitsky et al

[SNT Gatchaman]

Using apple watch ECG data for heart rate variability monitoring and stress prediction: A pilot study
Velmovitsky PE, Alencar P, Leatherdale ST, Cowan D, Morita PP

Stress is an increasingly prevalent mental health condition that can have serious effects on human health. The development of stress prediction tools would greatly benefit public health by allowing policy initiatives and early stress-reducing interventions. The advent of mobile health technologies including smartphones and smartwatches has made it possible to collect objective, real-time, and continuous health data.

We sought to pilot the collection of heart rate variability data from the Apple Watch electrocardiograph (ECG) sensor and apply machine learning techniques to develop a stress prediction tool. Random Forest (RF) and Support Vector Machines (SVM) were used to model stress based on ECG measurements and stress questionnaire data collected from 33 study participants. Data were stratified into socio-demographic classes to further explore our prediction model. Overall, the RF model performed slightly better than SVM, with results having an accuracy within the low end of state-of-the-art. Our models showed specificity in their capacity to assess "no stress" states but were less successful at capturing "stress" states.

Overall, the results presented here suggest that, with further development and refinement, Apple Watch ECG sensor data could be used to develop a stress prediction tool. A wearable device capable of continuous, real-time stress monitoring would enable individuals to respond early to changes in their mental health. Furthermore, large-scale data collection from such devices would inform public health initiatives and policies.

Link | PDF

 

[SNT Gatchaman]

As someone commented on a computer forum: "People can't tell how stressed they are themselves? Must be nice."

 

[SNT Gatchaman]

Furthermore, large-scale data collection from such devices would inform public health initiatives and policies.

We literally have an ongoing global pandemic, with a disease that is conservatively now the third leading cause of death, causing substantial amounts of excess death in all countries, unheard of childhood hospitalisation, health systems' collapse, and with financial and insurance institutions publishing robust data on the massive employment impact.

<crickets>

 

[Kitty]

Or maybe just give the grant straight to the patients, because they'd be a whole lot less stressed if they could afford to live somewhere that wasn't a damp, crumbling wreck and their kids had enough to eat.

 

[rvallee]

Aside from the wrongness of describing stress as a mental health condition, the word is used both to mean the stressor and the response to stress so it makes it very confusing, if they validate with self-reported questionnaires that rely on patients assessing their level of stress, whatever that means to each individual, then there is no need for that additional instrument.

I really fail to see any benefit to this. The very concept of stress is not just ambiguous and vague, it sometimes exactly match backwards between individuals. What some people find "stressful" is enjoyable, or exhilarating, to some. It pretty much means different things to different people.

This seems again the obsession with giving numbers to arbitrary concepts on the premise that it makes them objective, which is an massive conceptual error.

This is very, very vague and generic:

1. I felt that I was using a lot of nervous energy;
2. I found it hard to wind down;
3. I found myself getting agitated;
4. I found it difficult to relax;
5. I tended to over-react to situations;
6. I was intolerant of anything that kept me from getting on with what I was doing;
7. I felt that I was rather touchy;
8. Right now, I am …

Questions 1–7 have the options: “Not at all”, “To some degree”, “To a considerable degree”, and “Very much”, while Question 8 has “Stressed Out”, “Definitely stressed”, “A little stressed”, “Feeling good”, and “Feeling great”. The questions were displayed to the user in a random order each time the questionnaire is filled.

This is again validating unvalidated concepts turned into fake numbers with other unvalidated concepts turned into fake numbers. This is completely useless, it has no relation to real things.

Pseudoscience with technology is still pseudoscience. This is like all the CBT apps, they're just as useless in medicine in app form or not. You could probably use those "mood" rocks that change color with temperature and it would be just as useful and scientific.

In the end it's clear that where stress is used it means exertion. People don't have unlimited energy and the immune system has a cost, too. This is no different than how some people aren't really good at physical activity while others are borderline machines, people are different and there's nothing wrong with that.

 

[Woolie]

Pseudoscience with technology is still pseudoscience.

Agree, this is super dumb.

As @rvallee says, this study confuses two very different things:
- the normal, transient ECG changes that occur when we want to perform well in a task or situation (a very good thing!).
- the long-term response to sustained mental or physical performance pressure that consistently exceeds our resources (not such a great thing).

They may also be confusing the second thing with other types of mental and mood states that are "bad", but have little to do with stress, such as generalised anxiety - or even normal everyday life distress (failure, disappointment, heartbreak, etc.).