Selected for:

IINTS was selected to represent Belgium at the European Union Contest for Young Scientists.

IINTS-SDK

An open research platform to explore, test, and demystify the technology behind automated insulin delivery.

Understanding the "Recipe"

An algorithm is simply a recipe: a set of rules. In a standard pump, you set the rules (e.g., "deliver 2 units for this meal"). An automated insulin-delivery controller combines glucose data, trends, insulin-on-board and configured parameters to calculate a candidate action.

The "Black Box" Problem

Commercial pump algorithms are usually proprietary. While you see the outcome, the insulin being delivered, you often don't understand why the decision was made.

Hidden Logic: You lack insight into the actual decision-making process.
Trial & Risk: You cannot safely experiment with how the system reacts to stress or exercise.

IINTS-AF: The Research SDK

IINTS-AF is a comprehensive Software Development Kit (SDK). It provides an independent research framework that allows developers and academics to build, test, and evaluate AI algorithms within a controlled, seeded and reproducible research environment.

Data Registry

Global Data Access & Integration

Before an algorithm ever controls a real pump, it must be evaluated against diverse, real-world physiological data. The IINTS-AF SDK features a built-in Data Registry, allowing researchers to prepare, import, or benchmark supported datasets when researchers have access, including the Jaeb Center AIDE T1D, Tidepool Big Data Donation, and the OpenAPS Data Commons. Registered datasets include access, citation and provenance metadata. Local files can be validated through MDMP.

Data Checks You Can Audit

IINTS-AF uses MDMP (Medical & Machine Data Management Protocol) to certify every dataset used in simulation. MDMP records contract checks, fingerprints and optional signatures to improve traceability.

"Simulation is the first step toward safety."

OhioT1DM-Informed Research Sandbox

Live System Logic

The algorithm identifies trends in the glucose curve and simulates a corrective insulin response in the virtual environment.

Clinical Transparency

From "Black Box" to "Open Logic"

Two-layer research safety architecture

We do not believe in blind trust in AI. That is why the IINTS-AF SDK introduces a layered defense strategy:

Input validation

Incoming values are checked for numeric validity, configured glucose bounds and implausible rates of change. Invalid readings are rejected rather than silently corrected.

Independent supervision

Before a candidate insulin action affects the simulated patient, a separate deterministic component applies configured limits for glucose, trends, insulin-on-board, bolus size and recent insulin delivery.

These constraints support research experiments; they are not personalized clinical rules or proof of medical safety.

"Code shouldn't be a secret when it's managing a life."

Research Access

Take Control of Your Technology

IINTS-AF is a fully Open Source research platform designed to provide transparency into autonomous insulin delivery research. We believe you should be the master of your own technology through understanding.

Simulation

Processed OhioT1DM data can support forecast benchmarking and calibration audits when access conditions permit.

Edge AI

Optimized for the NVIDIA Jetson ecosystem. Run high-speed inference and 24/7 safety monitoring. The Independent Supervisor runs as a dedicated edge process, isolated from the AI inference layer.

Open Access

Apache-2.0 licensed, with legacy MIT notices where applicable, framework for independent medical tech research and study.

Join the Research

The IINTS-AF SDK is now a complete ecosystem for transparent, explainable, and safe research into autonomous insulin delivery. Download the latest version on PyPI or explore the source code on GitHub.

Explore on GitHub

SDK Experience

Built for Developers & Researchers

Getting started with medical AI research shouldn't take weeks. With IINTS-AF, it takes seconds.

One-Command Install

                            
                            pip install iints-sdk-python35
                        

Instantly set up the complete environment including safety engines and simulators.

Instant Data

                            
                            iints data fetch aide_t1d
                        

Built-in connectors for the world's leading T1D datasets.

Research Metrics

                            
                            iints evaluate --algo algorithms/example_algorithm.py --population 1000 --seed 42
                        

Stress-test an algorithm across virtual patients and report aggregate research metrics.

"IINTS-AF represents a shift toward explainable autonomous insulin delivery research, where human safety logic serves as the final authority over artificial intelligence."

Downloads

Get started with the IINTS-AF research platform.

Core SDK

Python framework for algorithmic research and simulation.

Download SDK

Desktop App

GUI for visual simulation and dataset management.

Download Beta