185
Show HN: The App I Built to Help Manage My Diabetes
Hi HN,
I’m Joshua, a student, and I’m excited (and a little nervous) to share something deeply personal that I’ve been working on: Islet, my diabetes management app powered by GPT-4o-mini. It’s now on the App Store, but I want to be upfront—it’s still very much in its early stages, with a lot more to go.
I was diagnosed with Type 1 diabetes while rowing competitively, and that moment changed everything. It wasn’t just the practical challenges of managing insulin, carb counts, and blood sugars; it fundamentally shifted how I see myself and the world. It forced me to slow down, prioritise my health, and take control in ways I never had to before. My outlook on life became more focused on resilience, adaptability, and finding solutions to problems that truly matter.
This app started as a pet project over the summer, a way to see what I could create using ChatGPT and explore the potential of LLMs to help with real-world challenges. At first, it was just about making my own diabetes management easier—understanding patterns in blood sugars, planning meals, and adjusting routines. But as I worked on it, I realised it could do more.
Right now, Islet offers personalised meal suggestions, tracks activity, and provides basic insights based on the data you enter. It’s far from complete. Even so, the process of building Islet has already taught me so much about how powerful AI can be in creating personal, meaningful tools.
This project is deeply tied to how my diagnosis changed me. It’s about more than managing diabetes, it’s about showing how anyone, even a student experimenting over the summer, can use AI to potentially solve real, personal problems. I believe tools like LLMs have the power to democratise solutions for all, making life just a bit easier for all of us.
If you’re curious, you can check it out here: https://apps.apple.com/gb/app/islet-diabetes/id6453168642. I’d love to hear your thoughts what works, what doesn’t, and what features you think would make it better. Your input could help shape the next steps for Islet.
Thanks for reading !
joshua
This is amazing, my daughter has been on pump therapy for almost eight years now and just now starting to feel like she has any control at all.
I downloaded the app, just to check it out, and the one thing that just struck me right off the bat is the permissions. Read is fine, it’s the write permissions, particularly glucose level and insulin delivery. I don’t know the full app ecosystem, and if it would be possible for your app to interfere with the insulin delivery settings on her pump.
if you have a website or anything that discusses how the application operates and what the permissions are used for it definitely check it out.
Ultimately though this looks like a great tool!
(Also really digging the company name!)
It’s not explained so I have no idea where AI is involved, which makes this all the more alarming. I would seriously ask anyone considering the use of computer generated information in healthcare to do some soul searching and ask themselves if literally people’s lives are worth prolonging this bubble.
I would be wary to put AI functionality in my app, especially if it is a medical or health app.
It looks like the intentions are good, but it reminds me of some indie hacker with zero AI (apart from wrapper apps) or therapist background offered “therapist AI”.
Some people don’t understand how much garbage AI outputs, and these people might not be skeptical enough when it comes to taking medical advice from gpt
Therac-25
https://en.wikipedia.org/wiki/Therac-25
Hey, I'm a doctor and work in a similar area. I really like the name and well done on shipping. You can tell the app is made by a patient who suffers from the condition, which is amazing.
I would be really careful in this area though, especially using ChatGPT to generate suggestions. This to me this does venture into medical device territory, based on the intended use. Check the guidelines here https://www.gov.uk/government/publications/medical-devices-s... - UK specific, but will be similar for FDA.
Honestly, I would seek proper consultancy advice, remove any suggestions / recommendations for now, and just have it as a data-logging platform. The disclaimer unfortunately will not stand up.
Congratulations on getting this far - I really hope you continue on this path, just make sure you are on firm ground.
I don't know, I understand the advice and I guess that's probably one of the reasons Loop (https://loopkit.github.io/loopdocs/) is not on the App Store. If they had turned their project into another data-logging platform we wouldn't have commercial closed loop systems.
Thanks for the link. Yep - exactly, they took a leap, but importantly didn't release a full product / package on the App Store, or charge for features. This falls much more into a grey area, but is clearly DIY, and demonstrates demand/need for the commercial / regulated systems.
Especially when the problematic features are charged for, it gives the recommendations / suggestions an air of legitimacy which could be dangerous.
A lot of the research from Loop and AndroidAPS is used in commercial closed loop platforms; many of the people working for these open source utilities also work for medical companies.
So you either get lucky and your doctor can prescribe you a commercial loop, or you compile one from source.
I came here to say the same as the parent comment - it's an amazing achievement, but you may well have built a medical device which needs certification in order to be on the market in the territories you want to use it in.
I work (freelance) with a consultancy [1] that helps specifically with software-as-a-medical-device (SaMD). My email is in my profile if you want to chat about what might be the best way forward.
[1]: https://www.hardianhealth.com/
Curious where AI added value for you here? I can see the obvious use cases like photo recognition of meals for tracking, but wondering if there's anything more unique.
Congrats on the launch, Joshua! Super impressive work. I built a management app for T1D kids+parents, so I know how much work goes into a project like this. Happy to chat and share what I learned from my own attempt at this if that might be helpful.
I would like to know more about what kind of data is powered by ChatGTP, what kind of data is sent there because it states on-device.
I am not sure how ChatGPT can give any advice (if it is even given in the app) about insulin or glucose.
Hey, Thanks for asking.
The Islet app is designed as a knowledge base that logs crucial data, including insulin dosages, meals, and physical activities. It aims to provide users with insights into how these factors interact to impact their blood sugar levels. Here's a breakdown of how ChatGPT integrates into the app and what data is involved:
What kind of data powers ChatGPT in Islet?
The ChatGPT component in Islet acts as a translation and query layer rather than the sole knowledge source. Islet’s knowledge base aggregates and organises the user’s logged data, such as:
- Glucose Levels: Derived from CGM (Continuous Glucose Monitor) data. This Data is currently on a 3hr delay in the app.
- Insulin Dosages: Logged by the user to capture the timing, type, and amount of insulin administered.
- Meals: Users can log meals in detail, including macronutrient composition, portion sizes, and timing.
- Activities: Logs include exercise type, intensity, and duration, as physical activity significantly impacts glucose regulation.
Does ChatGPT provide advice?
While the app itself does not directly provide medical advice, the ChatGPT integration facilitates better use of the logged data by enabling the user to ask targeted questions. For example:
- "How has my blood sugar been affected by pasta meals over the past two weeks?"
- "What impact does my 30-minute cycling routine typically have on my glucose levels?"
- "Are there patterns between my evening meals and morning glucose levels?"
Purpose of the App
The primary purpose of Islet is to empower users with a system that captures and organises their diabetes-related data into a knowledge base. The ChatGPT layer makes querying this knowledge base intuitive by translating user questions into actionable insights, offering:
1. Pattern Analysis: It helps users understand trends by analysing recurring meals and activities regimens and their effects on blood sugar levels.
2. Education: Users gain a better understanding of their unique responses to different scenarios, supporting informed decisions in their diabetes management.
By focusing on personalised, data-driven insights rather than generic advice, Islet ensures that the ChatGPT integration remains a helpful tool for exploring user-specific trends.
This reply seems to be partly generated by chatGPT, which makes me nauseous…
[dead]
Congratulations on shipping but using LLM for health decisions is highly risky given the risk of hallucinations.
Something to consider and probably add some kind of warning about.
I was founding engineer at a start-up tackling similar problems, albeit using 2014-2022 tech. Email me off-list and I’d be happy to talk through some experiences!
Congratulations on shipping! This looks incredibly polished for an initial release from a solo developer. And as others have said, great name!
As a T1D dad it's great to see work like this, not least because it should raise the expectations of what we should expect from well funded engineering teams within the established players.
Right now it's not a great fit for my use case, in that one phone follows my 9 year old around, but the bulk of management happens on other phones on distinct accounts.
I agree with @jcims point about the permissions, greedily allowing write permissions to those data items up front feels like a real point of friction, I'd much prefer to see that done lazily at the point the user is enabling a feature that needs it.
As a fellow indie iOS hacker working on a personal project, I’d love to know more about how you built it! Assuming SwiftUI? Any UI libraries or dependencies? Any learning resources you found particularly helpful?
Congrats on shipping, I’m hopefully a month or so away myself :)
I’m not in the target market, but most people have no idea what gpt-40-mini is so while it might make sense to list it in the HN title it probably doesn’t make sense to use that term in the dashboard. AI likely makes more sense, or just machine learning
I wish thyroid disorders were easier to measure as well, just like Blood Sugar is. Does anyone know of proxies to actual blood tests for thyroid level management?
As a person with Hashimoto's and struggle with Hashi flares that last a few weeks at a time, I've been working on a PWA that helps me track various things. It is "modular" and lets you track anything you want, so mine is set up to track medicine, food/diet, stress level, exercise, and I can export the text-log and email it to whoever I want.
I was daily driving it for a few weeks just to see if I wanted to do anything with it, but a flair up and life got in the way.
I have no real plan to release it, but I might add the PWA to github and maybe let other's actually run with it.
Hi Joshua,
I am so sorry to hear about your diagnosis, it happened in our family and it changed our lives. I will definitely try your app because I am curious if AI can improve diabetes management. Does the app support both mmol/L and mg/dL? Have you had any limitations with iOS? Do you have an Android version in mind? Thanks for your efforts
Does the photo recognition attempt to carb count what it sees? Is that even possible? My son is a T1D and he still struggles with carb counting.
It is absolutely not possible to carb-count through photo recognition in a way that is reliable enough for a diabetic to safely use to make treatment decisions.
Indeed, around 2019 I was reading many computer vision papers for volume estimation and came across a few that tried to estimate the weight of the meals from pictures using the size of known objects (cutlery beside the plate). The idea was good but they were very far from accurate and not robust at all, and that was just for the weight, not even carb counting. I know CV is a fast moving field but I wouldn't bet that the tech has improved enough to be anywhere near medically safe.
I meant more in a general way, like a piece of pizza is usually around X carbs. We have apps that make the guess a bit easier but it's almost always a guess. I was thinking could this look at a photo and know there's a sweet potato, a piece of chicken and some corn and give a basic idea.
The answer is still Absolutely Not, especially since all food can involve a treatment decision for people with type 1 diabetes.
Pizza is a good example of why not. Slices come in very different sizes, sauces have very different carb content, so do crusts, and toppings.
Edit: for example this pizza(1) is 31g per slice and this pizza(2) is 73g per slice. The difference is very meaningful and the “general idea” given by photo recognition would likely be wrong to the point of dangerous for a diabetic in both cases.
If you’re looking for software that can make a guess simply for the sake of generating a number to write down and not be used in any way, a random number generator would be safer since the risk of output being misconstrued as actual information is much lower.
1 https://www.costcobusinessdelivery.com/kirkland-signature-ca...
2 https://sbarro.is/product/bbq/
Yep. And the issue with pizza is the amount of fat that comes with the carbs. This quite often (depending on the position of the moon) gives you some of the carbs when you eat it to your blood, and the rest will come after several hours. What you want to do is to inject a bit of insulin before eating, then after two or three hours more while measuring your glucose levels.
Of course if you eat a Neapolitan pizza with not that much of cheese everything changes again. And YMMV, I'm just talking about my experiences.
Not only fat plays a role with pizza, but also the amount of protein in it. When having pizza we usually add protein to the carbs. 50% immediately bolus. Other 50% spread over 3-4 hours, and let AAPS dose the insulin.
What do you use then to make these decisions? If you use your eyes, app, nutrition label or Chatgpt, you would still have the same variables. You're still making the decision based on averages, and best guesses.
I use nutrition labels. I have absolutely no idea whatsoever why anyone would lump nutrition labels in with your eyes or chatgpt.
The people that make the label make the food. They know what they put in it. Because they made it. They wrote down what they put in it for you to read and make decisions off of. The difference is categorical.
I cook myself and i know which and how much ingredients i use and how much carbs they contain. Either from a food label or in general (like 100g of cooked potatoes contain about 16g carbs).
Then I calculate how much my serving contains.
Depending on what you eat, what type of diabetes you have and how it’s treated you may have to consider the amount of protein and fat as well (they slow digestion and cause a delayed rise in blood sugar levels). If you have an insulin pump you may want to program a delayed insulin dose to handle that.
Sounds complicated? It is, but only during the first weeks. You quickly learn the carbs content of the food you frequently eat and learn to estimate how much is on your plate. Like, two units for a bun. There are also great nutrition apps out there that help a lot.
Personally, I take a representative sample and then use a calorimeter to test it. Anyone who doesn't do this is being grossly irresponsible and will only have themselves to blame when they eat so dangerously. I recommend a CK 5E-C5808J but you have to ensure a trained professional is helping you. Otherwise, you might as well not eat at all.
Yeah, you can try this on the ChatGPT app. Take a picture and ask ChatGPT to give you the nutrition info, then do your own calculations based on weight and the USDA database and see how it compares.
Similarly, chatgpt can run a mile for you if you ask it to and then get up and run a mile.
However, if you dont have carb info, the alternative is to judge yourself. Your own model may be better than gpts model, though. I would use GPTs output and at least look at it on a case by case basis
It's probably slightly worse than an educated guess?
>Is that even possible?
No.
How was the getting approved by Apple workflow? Historically speaking, they take a long time verifying your app. So just curious.
As a new diagnose T1D I love this!
I signed up for the free week trial to test out some of the AI features. When I asked it to analyze my week the numbers weren’t very accurate compared to my graphs inside the app.
If you need help troubleshooting I’d be more than happy to help
fellow t1d + engineer + competitive rower (20 years ago...sigh) here.
props on shipping an incredible personal project! if you ever want to geek out about diabetes tech, DM me on X @kamens
scott hanselman would probably also love to chat about your project
Thanks so much ! Appreciate the kind words about Islet. It still has a long way to go !
Does the App need GPT to run or was it just used to develop the app?
Congrats on shipping! Consider making it Mac compatible with catalyst or iPad app, seems like it would be useful on watchOS and macOS too.
Looks great. I'd love to try an Android version.
There's been one for years already. Instead of sending your data to ChatGPT, it uses multiple scientific models to calculate your insulin resistance, basal dose and can give you an accurate amount of insulin to dose based on the number of carbs you input. What the Android app can do and iOS makes very hard is to control your pump and close the loop. It is illegal to distribute health apps in binary form if they control your pump, but very much legal in source code form. Try it out:
https://androidaps.readthedocs.io/en/latest/
This is a life-changing app. It lowered my A1c values from around 8% to 5.5%. What is so special with Android is how easy it is to side-load apps, so you can compile AndroidAPS by yourself and keep using it. In Apple ecosystem you need the developer subscription and you also need to reinstall the app every now and then. There is still the Loop app if any iOS users want to try, but this complication from Apple has just pushed me to Android ecosystem for the past decade already.
https://loopkit.github.io/loopdocs/
There is also iAPS, the AAPS-version but for Apple Devices; also take a look at Trio.
https://iaps.readthedocs.io/en/main/
https://docs.diy-trio.org/
But I like using Loop/LoopKit due its simple interface.
I didn't know about trio. Is there someone who has experience in both AndroidAPS and trio? My son would like to switch to Apple ecosystem but aaps keeps him in android.
My son (13) and I are also using AAPS for roughly 3 years now. The app does not look styled, however after taking the initial hurdle to find our way around in the app, it is greatly appreciated. Integrates nicely with Xdrip ( anf others)
It is a life-saver. Learn it once, and it is the most important tool in your diabetic toolbox.
> GluCoPilot
I’m dead I love it.
For an app being in the early stages the feature list is solid. Good work! love these lovingly crafted apps
Is there any concern about the similarity in name to the company Insulet (the maker of the Omnipod)?
First up - awesome work.
Having been through the year long build of a similar app for another health condition here’s some thoughts focusing on the GenAI side of things:
- What’s the source of the responses? Is this a RAG system or straight-to-LLM?? We have an ever-growing huge repo of domain expert written content which is the source for our RAG system. It’s far easier to control potential misinformation with a well set up RAG and some tight prompting/guardrails.
- What verification do you have that the responses are correct? We have a group of 50 highly experienced experts in the field who constantly vet the responses to our synthetic set questions and it was eye opening how often our “looks good to me” analysis was off at the beginning.
- The main reason for this questions was that your responses are going to be wrong sometimes, what legal protection do you have? Disclaimers, terms of use at absolute minimum. Who is liable if the answer is wrong? Just presume someone is going to be very upset if your response gives them bunk info.
Either way - great work.
Beautiful charts - may I ask what library you are using?
> what library you are using?
Not the OP but these look like they are Apple's own SwiftUI Charts framework:
https://developer.apple.com/documentation/charts
thanks! looks nice
Hey Joshua, Amazing work with the app and a sad welcome to the pancreatically challenged club from a long term member!
I love the app and feel we could have quite some similarities, I too undertook the effort to create a solo-diabetes app for the community, called "Diabetes Cockpit" - i think yours looks much prettier though <3
Would love to connect and have a coffee - tried the contact on the website but its not implemented yet i think ;P
So maybe you just get in touch via schusterlich@gmail.com if you are up for it, i would be happy!
Really good work! Best, Lukas
If your app uses GPT-4o-mini you should probably update your Privacy Policy, as it states that everything stays on device and nothing is shared with third partys
https://anthropometric.godaddysites.com/
Thanks for pointing this out, forgot to update the Privacy Policy on the website.
[dead]
[flagged]
This comment looks so much ChatGPT / Gemini generated.
I'm not against using it but it feels inappropriate for hacker news discussions and I am not really sure it adds value.
Question: Doesn't a carb-free (carnivor/true keto) diets eliminate diabetes?
High blood sugar is a symptom of the underlying pathology—the lack of insulin in T1, low sensitivity to insulin in T2 (itself typically but not always secondary to other factors such as visceral obesity). Low carbohydrate intake can manage the deleterious effects of T2, but it is not a cure.
Depends on the type. For instance, my diabetes is caused by scarring of the pancreas due to another medical condition, and no diet can undo that.
No, muscles and the liver constantly release glucose into the bloodstream. Type 1 diabetics can’t produce any insulin and would end up in hyperglycemia.
https://dornsife.usc.edu/news/stories/a-diet-that-mimics-fas...
no. type one diabetics do not produce insulin. the immune system attacks insulin producing cells in the pancreas. there is no "elimination."
No. Though low-carb diets are generally a good idea for those suffering from diabetes, it doesn't eliminate it, and in fact one of the most life-threatening situations a T1 diabetic can be in (hypoglycemia) needs to be addressed by giving them as close to pure sugar as you can manage (and the person themselves might be too out of it to manage on their own - advanced hypoglycemia impairs brain function).
See sources below. The answer is… No! All food requires insulin. This is true for type-1-diabetics and non-diabetics. Fat and protein require insulin, but via a “post-bolus” instead of a “pre-bolus”. Another issue is fat and protein cause insulin resistance.
Here’s a link to an insulin calculator for fat and protein: https://drlogy.com/calculator/warsaw-method
Sources: “The effect of fat and protein was additive, with blood glucose concentrations increasing by 5.4 mmol/L (97.2 mg/dl) at 5 h, the sum of the individual incremental increases for protein and fat” https://diabetesjournals.org/care/article/38/6/1008/37384/Im...
“Meal composition impacts postprandial glucose excursions. Education on the impact of high-fat and high-protein meals and the adjustment of insulin dosing is necessary.” Source: ADA Standards of Care in Diabetes—2024 https://diabetesjournals.org/care/article/47/Supplement_1/S2...
“Match mealtime insulin doses to carbohydrate intake and, additionally, to fat and protein intake.” Source: ADA Standards of Care in Diabetes—2024 https://diabetesjournals.org/care/article/47/Supplement_1/S1...
“Insulin dosing based on carbohydrate plus fat/protein counting reduces the postprandial glucose levels” Source: Pediatric Diabetes Volume 13, Issue 7 p. 540-544 https://pubmed.ncbi.nlm.nih.gov/22765260/
“research and the use of continuous glucose monitoring have shown that other nutritional properties of food, including fat, protein, and glycemic index significantly affect postprandial glucose excursions” https://diabetesjournals.org/care/article/38/6/1008/37384/Im...
https://dornsife.usc.edu/news/stories/a-diet-that-mimics-fas...
Don't get your intel from social media gurus.
That applies to vegan militants as well. It is well researched now that low-carb puts T2 diabetes in remission, and calling it bro science won't invalidate it.
It can help with type 2 diabetes. Look up Dr. Sarah Hallberg.