I solved my mystery fatigue with AI
metalearn.substack.com
metalearn.substack.com
For all of the writing about collecting data and using AI, she never explains what the AI did for her. Maybe it suggested trying iron supplements because her ferritin was slightly low on a blood test? I hope it explained that these blood tests can have transient highs and lows and that excess iron from supplements can have major negative health effects if not monitored.
For all of the lead up about using AI, there was never really a delivery where the AI was used to solve the mystery fatigue.
I’m glad this person is feeling better, but this post reminds me of those LinkedIn posts where someone is trying really hard to show their AI skills but used an example where the AI didn’t contribute to or accelerate the outcome.
Even for the part where she discovers she was in a caloric deficit and that carbs helped, the AI didn't seem to have a role:
> Figuring out what to track is an iterative process. At first, I logged only daily calories. But when I noticed that a small amount of carbs sometimes helped me recover faster mid-episode, I tracked carbs on the same spreadsheet.
The carb realization happened before tracking carbs. And why did it take a specialist to notice she was in a 300 calorie deficit? That seems like something that any AI process would trivially notice.
I don't know. This article is puzzling. I think using AI to analyze health records is interesting, but this article didn't really have anything supporting that other than to mention that she put everything into Claude on the side.
The only takeaway here is logging helps detect patterns, we already knew that.
I feel like this bit is more of a problem than many folks realize. I know that people see "frictionless" as a desirable trait, but for many of the things folks are using AI for these days, you're gonna want "push-back" sometimes. Especially in cases of health care and computer programming, there are times when the user is straight-up wrong about what they're trying to do, say, or believe, and the last thing you wanna hear when your life or job or the lives or jobs of others are on the line and you're about to make a huge mistake is "You're absolutely right! Let me get right on doing that for you!"
That’s the goal for doctors too. It would be great to get simple things off the system.
But I think the more realistic intermediate step is a trained person cheaper than a doctor - nurse, PA, etc - aided by AI. The current generation of agentic AI doesn’t seem to be there yet and is too agreeable from RL.
“you’re probably fine sleep it off combined with: drink more water, eat healthier, exercise more, sleep better, consume less alcohol and quit smoking/vaping” +/- “we’ll check some labs to make sure” is the correct answer for probably 95%+ of encounters so it’s not hard for an automated system to handle most simple things, even without AI.
See https://www.msn.com/en-us/health/other/this-state-is-testing...
Title: This state is testing out AI doctors—and actual doctors aren’t happy about it (Wall Street Journal)
New York state residents get the worst of it with the state bending over backwards to take away the people's rights.
Also, let's not confuse independence with AI. Independence is where I can do some extra bloodwork and diagnostics to satisfy my well-being. I don't need an AI limiting what I investigate either.
2. Doctors who depend on revenue from forced visits to renew prescriptions are grifters and not close to a majority. The profession obviously isn’t perfect but the vast majority of physicians I know would be happy to lighten their rosters.
With that said it can’t be a system that creates problems and dumps them back on physicians to fix, hence #1
Ultimately, it should be about personal freedom. This is not a contagious disease we're dealing with here.
> Ultimately, it should be about personal freedom. This is not a contagious disease we're dealing with here.
The state regulates health and medical devices for a reason. Look at what’s happening with all of these prescription mill apps these days which are still theoretically overseen by a licensed healthcare professional - plenty of medical errors and harm in the name of increasing access (a good thing, when done well). We’ll see criminal investigations within a year.
AI guiding a process is valuable even if it doesn’t replace all the parts of the process.
She said she started logging calories but recognized the carb connection before she logged carbs.
I kept waiting for the payoff where the AI led to something, but it never came.
Iron supplements are notorious for irritating the stomach, worsening gastritis and acid reflux. Even iron bisglycinate, while fully effective, is a significant stomach irritant. Ferric pyrophosphate might be safer, and I'm trying it now, but I have to take it twice a day because once wasn't sufficient.
With regard to addressing anemia, active B12 (hydroxo/methyl/adenosyl), methylfolate e.g. Quatrefolic, copper, and vitamin A also matter.
One can also simultaneously be low or suboptimal in many other vitamins and minerals unrelated to anemia, e.g. vitamin D. Fixing only one of them is no guarantee of a sustained solution.
With regard to blood tests, it can take many iterations of doing them to find anything useful. Doctors are ridiculous to work with in this regard, so I bypass them and get the tests myself. Doctors work for the insurance firm, not for you.
This is simply wrong when one considers that iron has many bodily functions outside of hemoglobin, such as acting as a cofactor in tyrosine hydroxylase for dopamine synthesis.
AI helped me figure out my symptoms were related to histamine issues. This was really hard to track down. I started to tune into chicken and eggs causing me issues, but (1) I wasn’t actually allergic (2) chicken and rice is a standard safe diet (3) chicken is low histamine itself, but can trigger histamine release . It was further complicated because a bunch of foods didn’t consistently trigger reactions.
It was only after I tracked a bunch of foods and tried a bunch of different remedies that Claude was able to track down the pattern. From there, I was able to understand what foods would trigger my issues.
Chronically:
* I my energy levels were dropping. * I had terrible brain fog. * My moods were less stable and I was often very irritable. I felt way less resilient to stress. * My joints were constantly hurting * GI symptoms comparable to IBS
Acutely, I would get flare ups between 2 to 48 hours after eating food that were essentially a mix of flu and allergic reaction symptoms (despite not having allergies to these foods). I felt feverish, dizzy, light-headed, joint pain, head aches, diarrhea, nausea. There were a few times that it knocked me out for 24+ hours.
Three's also this "bucket" theory that I resonate with. Symptoms can fluctuate according to how "full" your bucket is. If you have an empty bucket, you might be able to tolerate whatever triggers with limited reaction. If you have filled bucket and overflow it, your symptoms cascade horrendously.
This part actually made self-diagnosis extremely hard because the same food wouldn't consistently trigger issues. This is on top of triggers already feeling a bit random. Pizza, for example, is wildly hit-or-miss by brand. Despite it all being essentially the same ingredients, some of it, I tolerate incredibly well. Some of it, I flare up terribly. Even more confusing, the cheap/low quality places (like Little Ceasars) sit perfectly fine with me, but many "fresh" or "high quality" ones completely crash me.
I got an odd fatigue myself and went to the doctor for blood tests but nothing obvious came up. I'm guessing it's a post viral thing but there aren't really tests and it seems to be gradually getting better over a few years. Science could do with better understanding of that stuff.
If the article author saw this, you can reach at me, I will tell u the whole method and details, for free, for sure.
Because I think you were from China, too.