Language
KR
EN
Open-source DIY APS is powerful,
but it requires complex setup and learning that patients must handle themselves.
An artificial pancreas is a system that uses technology to replace the role of a stopped pancreas.
The core lies in a Closed-loop structure where 'Measure (Sensor) - Decide (App) - Inject (Pump)' continuously circulates.
* The goal is for this entire process to be automated with minimal human intervention.
Connecting just any device won't work.
First, check the 'Golden Standard' combinations verified by the global community.
Galaxy S Series (Smartphone) + Dana-i (Pump) + Dexcom G6 (Sensor)
* This is the cleanest combination connecting via Bluetooth without additional communication equipment.
Brain of the System (Master)
iPhones (iOS) cannot use AndroidAPS due to background app execution restrictions.
Execution Organ (Actor)
Receives commands from the smartphone to inject insulin. Bluetooth support is key.
Detection Sensor (Sensor)
Transmits glucose values to the phone every 5 minutes. Developer app setup may be required instead of the official app.
For more detailed compatibility information, please check the AndroidAPS Official Documentation .
This is the highest barrier to entry. Due to regulations, you cannot download it from the App Store.
Patients must become 'developers' and build an app tailored to their phones.
Copy (Fork) the source code (AndroidAPS) shared by global developers to your Github account.
Just as cooking requires a kitchen, install Android Studio, a professional development program, on your PC.
Open the imported code in Android Studio and click the 'Generate Signed APK' button to create the app file (.apk).
Transfer the completed app file to your smartphone via USB and install it to finally see the icon.
Reality Check: Due to PC specs or Java version errors,
it takes an average of 3 days to 1 week for a non-major to complete this process alone.
The app won't work perfectly right after installation.
For safety, you must pass a verification process similar to a 'driving test'.
For user safety, the artificial pancreas has its automated injection features locked initially.
You must solve 11 stages of quizzes and prove your actual pump operation ability to unlock the next stage.
The AI needs reference values to make decisions. Much more precise values are required than at the hospital.
Physical limits must be set to prevent device malfunction or excessive injection.
How does the machine decide the insulin amount?
The key lies not in the present, but in 'predicting future glucose'.
"Insulin still active in the body"
It calculates the residual amount already injected but not yet effective to prevent over-injection (hypoglycemia).
"Food not yet digested"
It calculates how much material is left in the stomach that will raise glucose, preparing insulin in advance.
The DIY approach (Rule-based) relies solely on the formulas (ISF, IC) pre-entered by the user.
If variables not in the formula arise—such as 'menstrual cycle, stress, poor condition'—the prediction can be wrong.
This is exactly why a self-learning AI (GlucoUs) is needed.
Because in a 'rice-based culture' with a high proportion of carbs,
the traditional basal adjustment (AMA) method cannot control glucose spikes.
Like opening a faucet a bit more,
it gradually increases the 'basal rate'.
→ Slow response time
Like firing a machine gun,
it delivers 'super micro boluses' rapidly.
→ Instantly suppresses sharp spikes
If the settings aren't perfect, there's a high risk of hypoglycemia.
This is exactly why GlucoUs's AI is necessary.
| Category | Existing DIY (SMB) | GlucoUs (Next-Gen) |
|---|---|---|
| Operating Principle |
Rule-based "If glucose is X, blindly inject Y" |
RL-based (Reinforcement Learning) "In this situation, injecting Y is optimal" |
| Core Issue |
Relies on user-input values (ISF) If input is wrong, calculation is wrong |
AI learns on its own AI detects changes in the body |
| Meal Logging | Manual input (Scale required) | Camera photo (Auto volume calculation) |
We aren't just building a logging app.
We use technology to solve the biggest challenges in diabetes management: 'accurate meal measurement' and 'precise insulin control'.
"A single photo is enough."
Vision AI technology analyzes the volume and mass of food in 3D. No more taking out a scale before meals or stressing over estimating by eye.
"An algorithm that learns your body."
An AI based on Reinforcement Learning (RL) learns the user's glucose response patterns on its own, providing a precision insulin delivery algorithm optimized for the individual.
GlucoUs's journey towards a fully artificial pancreas
Foundation
Validation (NOW)
Expansion
Completion
We know the moment the joy of eating becomes a chore.
With GlucoUs, there is no complex coding. Just one camera shot
analyzes nutrients, and AI predicts your glucose.
* Currently recruiting beta testers