A Low-Cost Artificial Pancreas System With Integrated Machine Inference
ISEF · 2022 Biomedical Engineering
Overview
Insulin pumps on the market today are expensive and are computationally limited in calculating and providing accurate dose regimens for type 1 diabetics. In this work, four academic disciplines--Biology, Mechanical Engineering, Electronic Engineering, and Computer Science--are integrated to demonstrate a low cost, open source solution that solves the fundamental problems of today's devices, and does so in a way that can mimic the functions of a biological pancreas. The integration and use of these four academic disciplines are essential in creating the mechanical pumping system, the integration to the human circulatory system, control electronics for the hardware, as well as a neural network computational model to optimize battery usage and to efficiently predict when blood glucose levels will rise. This work shows a functioning prototype as well as a predictive computational model derived from a simulated patient dataset.
Awards (1)
- Drexel University: Full tuition scholarship
Competition history
- ISEF 2022
Resources
Related projects
ISEF · 2019
An Improved Inexpensive Closed-Loop Insulin Pump for Automatic Management of Types 1 and 2 Diabetes
ISEF · 2018
A Low Cost, Closed Loop Insulin Pump for Better Management of Types 1 and 2 Diabetes Mellitus
ISEF · 2022
Creating a Low-Cost Non-Invasive Blood Glucose Monitoring and Automatic Insulin Injection System With an Artificial Neural Network and Raspberry Pi
ISEF · 2023
Optimizing Glycemic Control in Type 1 Diabetic Patients Using a Deep Learning-Based Artificial Pancreas With a Secure Glucagon and Insulin Delivery System
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair