Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

msn.com

Post reply on HN
Print view View original

141–150 of 240 posts

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#141

Post by vidarh »

cthalupa wrote: post #134
vidarh wrote: post #131

Earlier quoted context omitted.

It doesn't help when doctors are often unaware of outliers affecting the test results. E.g. I've had a number of doctors freak out over my eGFR (kidney function) test results because the default test they use is affected by body mass and diet, and made even worse by e.g. preworkout supplements with creatine. None of my doctors have been aware of this, and I've had to explain it to them.

I've not seen evidence that creatine actually has significant impact on eGFR. Anecdotally, mine does not budge even on 5g a day. Meta-analysis show minimal impact, e.g. https://pmc.ncbi.nlm.nih.gov/articles/PMC12590749/ Muscle mass obviously does, though. cystatin c is a better market if your body composition differs from the "average"

I did end up taking a cystatin c test privately to be able to prove to my GP that the results he freaked out over were nonsense. I'm in the UK, and for whatever reason the NHS just doesn't typically do them for basic kidney function - presumably cost, but they were dirt cheap to do privately so...

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#142

Post by mr_toad »

ignoramous wrote: post #25
brandonb wrote: post #8

Earlier quoted context omitted.

FWIW, Apple has published validation data showing the Apple Watch's estimate is within 1.2 ml/kg/min of a lab-measured Vo2Max. Behind the scenes, it's using a pretty cool algorithm that combines deep learning with physiological ODEs: https://www.empirical.health/blog/how-apple-watch-cardio-fit...

The paper itself: https://www.apple.com/healthcare/docs/site/Using_Apple_Watch... Seems like Apple's 95% accuracy estimate for VO2 max holds up. Thirty participants wore an Apple Watch for 5-10 days to generate a VO2 max estimate. Subsequently, they underwent a maximal exercise treadmill test in accordance with the modified Åstrand protocol. The agreement between measurements from Apple Watch and indirect calorimetry…

That’s saying that they’re 95% confident that the mean measurement is lower than the treadmill estimate, not that the watch is 95% accurate. In other words they’re confident that the watch underestimates VO2 max.

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#143

Post by smallerfish »

theshrike79 wrote: post #94
chrisfosterelli wrote: post #20

Health metrics are absolutely tarnished by a lack of proper context. Unsurprisingly, it turns out that you can't reliably take a concept as broad as health and reduce it to a number. We see the same arguments over and over with body fat percentages, vo2 max estimates, BMI, lactate thresholds, resting heart rate, HRV, and more. These are all useful metrics, but it's important to consider them in the proper context tha…

Measuring metrics is easy, it's the algorithm on the backend that matters. There's a reason why Oura rings are expensive and it's not the hardware - you can get similar stuff for 50€ on Aliexpress. But none of them predicted my Covid infection days in advance. Oura did. A device like the Apple Watch that's on you 24/7 is good with TRENDS, not absolute measurements. It can tell you if your heart rate, blood oxygen or…

> But none of them predicted my Covid infection days in advance. Oura did.

It actually warned you, or retrospectively looking at the metrics you could see that there was a pattern in advance of symptoms? (If the latter, same here with my Garmin watch - precipitous HRV decline in the 7 days before symptoms. But no actual warning.)

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#144

Post by theshrike79 »

yolo3000 wrote: post #103
theshrike79 wrote: post #94

Earlier quoted context omitted.

Measuring metrics is easy, it's the algorithm on the backend that matters. There's a reason why Oura rings are expensive and it's not the hardware - you can get similar stuff for 50€ on Aliexpress. But none of them predicted my Covid infection days in advance. Oura did. A device like the Apple Watch that's on you 24/7 is good with TRENDS, not absolute measurements. It can tell you if your heart rate, blood oxygen or…

I'm curious how the ring detected it in advance? I also discovered my Covid when I looked at my Garmin watch and my resting heart rate was 100, until then I had thought I had too much sun that day.

Some of the metrics were out of whack, I think my average body temp was up along with my resting heart rate both asleep and awake.

It somehow takes all that and gave me a "you might be sick" notification.

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#146

Post by theshrike79 »

smallerfish wrote: post #143
theshrike79 wrote: post #94

Earlier quoted context omitted.

Measuring metrics is easy, it's the algorithm on the backend that matters. There's a reason why Oura rings are expensive and it's not the hardware - you can get similar stuff for 50€ on Aliexpress. But none of them predicted my Covid infection days in advance. Oura did. A device like the Apple Watch that's on you 24/7 is good with TRENDS, not absolute measurements. It can tell you if your heart rate, blood oxygen or…

> But none of them predicted my Covid infection days in advance. Oura did. It actually warned you, or retrospectively looking at the metrics you could see that there was a pattern in advance of symptoms? (If the latter, same here with my Garmin watch - precipitous HRV decline in the 7 days before symptoms. But no actual warning.)

It actually told me, they've been doing this for a while: https://ouraring.com/blog/early-covid-symptoms/

Of course it didn't tell me "you have COVID19-B variant C" - but it did tell me I'm probably sick and should seek care.

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#147

Post by mr_toad »

alpineman wrote: post #106

My wife is a doctor and there is a general trend at the moment of everyone thinking their intelligence in one area (say programming) carries over into other areas such as medicine, particularly with new tools such as ChatGPT. Imagine if as a dev someone came to you and told you everything that is wrong with your tech stack because they copy pasted some console errors into ChatGPT. There's a reason doctors need to spe…

> general trend at the moment

“A little knowledge is a dangerous thing” is not new, it’s a quote/observation that goes back hundreds of years.

> Imagine if as a dev someone came to you and told you everything that is wrong with your tech stack because they copy pasted some console errors into ChatGPT.

You mean the PHB? They don’t need ChatGPT for that, they can cite Gartner.

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#148

Post by XorNot »

tclancy wrote: post #129
FeteCommuniste wrote: post #124

Earlier quoted context omitted.

> The most notorious of which is BMI; it is practically a category error to infer someone's health or risk by individual BMI, and yet doing so remains widespread amongst people that are supposed to know better. BMI works fine for people who aren't very muscular, which is the great majority of people. Waist to height ratio might be more informative for people with higher muscle mass.

I dunno, basing life decisions off a metric that has a fudge factor built into it to make the regression work feels sub-optimal to me.

BMI underestimates in most cases and your body fat is higher then the chart would predict.

When people say "oh BMI isn't accurate" it means you are more overweight then it suggests unless you are literally an extreme body builder.

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#149

Post by harvey9 »

vidarh wrote: post #141
cthalupa wrote: post #134

Earlier quoted context omitted.

I've not seen evidence that creatine actually has significant impact on eGFR. Anecdotally, mine does not budge even on 5g a day. Meta-analysis show minimal impact, e.g. https://pmc.ncbi.nlm.nih.gov/articles/PMC12590749/ Muscle mass obviously does, though. cystatin c is a better market if your body composition differs from the "average"

I did end up taking a cystatin c test privately to be able to prove to my GP that the results he freaked out over were nonsense. I'm in the UK, and for whatever reason the NHS just doesn't typically do them for basic kidney function - presumably cost, but they were dirt cheap to do privately so...

NICE guidelines. "Evidence on the specific eGFR equations or ethnicity adjustments seen by the committee was not from UK studies so may not be applicable to UK black, Asian and minority ethnic groups. None of the studies included children and young people. The committee was also concerned about the value of P30 as a measure of accuracy (P30 is the probability that the measured value is within 30% of the true value), the broad range of P30 values found across equations and the relative value or accuracy of ethnicity adjustments to eGFR equations in different ethnic groups. The committee agreed that adding an ethnicity adjustment to eGFR equations for different ethnicities may not be valid or accurate...."

https://www.nice.org.uk/guidance/ng203/chapter/rationale-and...

Re: I let ChatGPT analyze a decade of my Apple Watch data, then I called my doctor

#150

Post by mr_toad »

siliconc0w wrote: post #43

The problem is that false positives can be incredibly expensive in money, time, pain, and anxiety. Most people cannot afford (and healthcare system cannot handle) thousands of dollars in tests to disprove every AI hunch. And tests are rarely consequence free. This is effectively a negative externality of these AI health products and society is picking up the tab.

This is why certain types of cancer tests are usually only performed on people over a certain age. If you test young people the false positives outnumber the true positives.
Post reply on HN