Show HN: GlycemicGPT – Open-source AI-powered diabetes management (github.com)

Do you find the analytics actually helps? I.e. a lot of this will depend on what you ate and whether or not you logged it?

And how do you deal with AI hallucinations?

Marvin

Monitoring and analytics is important, but it is a solved problem. A language model will only be able to hallucinate about the relationship between meals and glycemic response. At best it does no harm, at worst it can directly misinform.

The hardest to learn was that an unhealthy lifestyle resulted in a diabetes that was harder to manage. Too much carbs, not enough exercise, etc. After adjusting my lifestyle, it became quite easy.

The most pain, in my experience, comes from the discrepancy between the CGM - measured value and the prick-test value, even when accounting for time lag. I've used several CGMs and they've all been wildly off sometimes. I have a few T1D acquaintances who relied on their CGM alone and have significantly improved their HbA1c after accounting for that.

Maybe that information is useful to you.

On your work:

this is legit

it is appreciated

Hats off, I salute this, thank you

It's so helpful to offload some the thinking about the condition to ai, all these people moaning about 'muh safety' don't get it. T1D suffers have to think about it all day all the time. A person doesn't have their own blood glucose data in their head.

It's breaking the golden rule of these tools which is to have someone with enough knowledge to verify the accuracy of the data it spits out. Patient's famously don't. Hell, even the actual staff don't really understand or know how these tools work (or the ways in which you can/can't trust them).

But if someone dies because this thing hallucinates their reporting - would you feel any sense of culpability?

“GPL says no warranty”

“People need to double check LLM output”

“You’re holding it wrong”

I really don’t know if we, collectively as a civilization, should be willing to accept this kind of hand-waving when it comes to creating things like this. Sure, tools make mistakes or people misinterpret reports without the help of LLMs - but LLMs are just on a whole other level where the mistakes are just part of how these things work from a fundamental level.

I don’t even trust AI scribes at my doctors office to transcribe my appointment due to errors. There is no way in hell I would ever use something like this that could just straight up lie about something that kills me if I get it wrong.

How do you protect your life and the life of others using your software against potential lethal errors?

About the risks, managing type 1 diabetes is exhausting, and most people will still sanitycheck the output alongside the hundreds of treatment decisions they make every day. That doesn’t change the fact that tools like this can nudge you to notice and look into patterns or things that needs attention.

I'm a T1D myself and like to experiment with ChatGPT (or Opus). My experiences are mixed

LLMs are overly cautious when it comes to correcting with insulin. They regularly advise against correcting before going to bed, even if this means that my blood glucose remains above 140 mg/dl for the whole night.

I am following a low to medium carb diet (<100g a day). ChatGPT always nudges me to consume more carbohydrates, even though I have a TIR of 90% (70-150 mg/dl). Why would I change my diet if it currently works very well for me? Still, most LLMs seem to favor carbs for some reason.

I am using Fiasp as my fast acting insulin. Typically, I inject around 1 to 4 IUs of Fiasp. Its glucose-lowering effect typically lasts for roughly 2-3 hours. Therefore, I know that it is safe to re-inject after three hours without risking insulin stacking. But ChatGPT regularly advises against that and wants me to wait another 1-2 hours.

I am not against automating diabetes management. In fact, I really appreciate projects that help with that. But I don't consider LLMs to be helpful in this regard. Their combination of training data bias, liability aversion, lack of context, and one-size-fits-all thinking disqualifies them from such tasks.

As others have said, the analysis might be risky. I don’t want to trust interpretation to anyone but myself (bear my own risk) or my clinician. But just remembering to capture the data and making it easily time alignable and possible augmentable in the future would be useful.

But let me say one thing: I’ve been diabetic for more than 20 years. Ten years of management with finger pricks, three measurements a day, and insulin pens (thinking about it now, it feels completely insane that anyone could imagine managing this madness in such a primitive way). Then came years of CGM systems (I’m on my third one now, with different types of sensors, but that’s not the point).

I tinkered, automated, hacked things. But in the end I came to one conclusion: you need a competent specialist (someone who also understands that we tend to be a bit tech-obsessed) who, besides listening to you, actually imposes a strategy. We are the ones who need to adapt to the mainstream approach so we can speak the same language and have methods that are compatible with “everyone else.” No doctor will ever fully understand your custom system, and meanwhile the key to proper management is not in what you built.

Precise carb counting (without cheating yourself), correct boluses given at the right times, marking exercise, boredom and repetition, and being lucid about the effects of changes (agreed upon beforehand!) to CGM settings — changes that should only be made when you’re certain you’ve been a “good and precise patient.”

I’m saying this from the perspective of my own devastated situation. I now have an HbA1c of 5.8, but only after 20 years of smashing my head against the wall (and suffering incredible damage, many mistakes, and the classic “I’ve figured it all out myself” approach).

Stay strong.