[HN Gopher] Show HN: The App I Built to Help Manage My Diabetes
___________________________________________________________________
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
Author : yeatsy
Score : 176 points
Date : 2024-11-18 00:07 UTC (22 hours ago)
(HTM) web link (apps.apple.com)
(TXT) w3m dump (apps.apple.com)
| d416 wrote:
| For an app being in the early stages the feature list is solid.
| Good work! love these lovingly crafted apps
| chasing wrote:
| 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!
| Nk26 wrote:
| 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.
| OccamsMirror wrote:
| It's probably slightly worse than an educated guess?
| jrflowers wrote:
| 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.
| Nk26 wrote:
| 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.
| jrflowers wrote:
| 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/
| Nk26 wrote:
| 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.
| jrflowers wrote:
| 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.
| junikaefer wrote:
| 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.
| renewiltord wrote:
| 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.
| pimeys wrote:
| 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.
| je42 wrote:
| 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.
| jevogel wrote:
| 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.
| jrflowers wrote:
| Similarly, chatgpt can run a mile for you if you ask it
| to and then get up and run a mile.
| je42 wrote:
| 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
| nihzm wrote:
| 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.
| astura wrote:
| >Is that even possible?
|
| No.
| jcims wrote:
| 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!)
| soared wrote:
| 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
| didgeoridoo wrote:
| > GluCoPilot
|
| I'm dead I love it.
| didgeoridoo wrote:
| 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 :)
| leereeves wrote:
| Looks great. I'd love to try an Android version.
| pimeys wrote:
| 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/
| je42 wrote:
| 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)
| pimeys wrote:
| It is a life-saver. Learn it once, and it is the most
| important tool in your diabetic toolbox.
| tigerwash wrote:
| 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.
| kakoni wrote:
| 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.
| andrewchilds wrote:
| 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.
| xk_id wrote:
| 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.
| griomnib wrote:
| Therac-25
|
| https://en.wikipedia.org/wiki/Therac-25
| serial_dev wrote:
| 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
| system2 wrote:
| Question: Doesn't a carb-free (carnivor/true keto) diets
| eliminate diabetes?
| daydreamnation wrote:
| no. type one diabetics do not produce insulin. the immune
| system attacks insulin producing cells in the pancreas. there
| is no "elimination."
| junikaefer wrote:
| 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.
| hnuser435 wrote:
| It can help with type 2 diabetes. Look up Dr. Sarah Hallberg.
| bdcravens wrote:
| 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.
| hombre_fatal wrote:
| Don't get your intel from social media gurus.
| sph wrote:
| 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.
| andreareina wrote:
| 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.
| rcxdude wrote:
| 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).
| bdcravens wrote:
| Is there any concern about the similarity in name to the company
| Insulet (the maker of the Omnipod)?
| SushiHippie wrote:
| 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/
| yeatsy wrote:
| Thanks for pointing this out, forgot to update the Privacy
| Policy on the website.
| trialskid1986 wrote:
| 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
| nextworddev wrote:
| Beautiful charts - may I ask what library you are using?
| stringsandchars wrote:
| > 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
| nextworddev wrote:
| thanks! looks nice
| croes wrote:
| Does the App need GPT to run or was it just used to develop the
| app?
| asdev wrote:
| 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.
| windex wrote:
| 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?
| jermaustin1 wrote:
| 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.
| abdussamit wrote:
| How was the getting approved by Apple workflow? Historically
| speaking, they take a long time verifying your app. So just
| curious.
| kamens wrote:
| 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
| yeatsy wrote:
| Thanks so much ! Appreciate the kind words about Islet. It
| still has a long way to go !
| ainiriand wrote:
| 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.
| yeatsy wrote:
| 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.
| rubymamis wrote:
| This reply seems to be partly generated by chatGPT, which
| makes me nauseous...
| rasengan wrote:
| 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.
| lukko wrote:
| 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.
| Adirael wrote:
| 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.
| lukko wrote:
| 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.
| pimeys wrote:
| 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.
| bizzleDawg wrote:
| 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/
| ajith-joseph wrote:
| This is an incredible initiative, Joshua--combining personal
| experience with technology to tackle such a complex challenge is
| inspiring. I have a few questions and thoughts:
|
| 1) Data Security and Privacy: Since Islet uses ChatGPT for query
| translations and insights, how do you handle sensitive health
| data? Is everything processed locally, or is some data shared
| with external servers? Many users will likely have concerns about
| privacy, especially given the nature of medical information.
|
| 2) Accuracy and Reliability: How do you ensure that the insights
| provided by the app, powered by ChatGPT, are consistently
| accurate and reliable for users managing diabetes? For instance,
| if there's a delay in CGM data or inaccuracies in user-entered
| data, could the insights potentially lead to incorrect
| interpretations?
|
| 3) Long-term Vision: Are there plans to integrate real-time data
| syncing with devices like CGMs or insulin pumps to enhance
| automation? Perhaps features like predictive alerts for
| hypoglycemia or hyperglycemia based on activity patterns?
|
| 4) Community Input: Have you considered ways for users to share
| feedback or contribute to the app's development, perhaps through
| an open forum or beta program? This could foster a community
| around Islet and accelerate improvements.
|
| This feels like a tool with the potential to truly make a
| difference. Excited to see how it evolves and wishing you the
| best in your journey!
| ahaucnx wrote:
| 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.
| xivusr wrote:
| Congrats on shipping! Consider making it Mac compatible with
| catalyst or iPad app, seems like it would be useful on watchOS
| and macOS too.
| therahim wrote:
| 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.
___________________________________________________________________
(page generated 2024-11-18 23:02 UTC)