Infusion Pump Dosing With Mobile-Computed Online and Offline Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated insulin delivery systems rely heavily on user inputs and have limited computational capabilities, especially when the infusion pump is not connected to external devices, leading to inefficiencies in determining optimal insulin doses.
Innovation Solution
A system that shifts computational load from the infusion pump to a mobile device, using an online dosing model when connected and an offline dosing model when disconnected, allowing the infusion pump to deliver insulin based on precomputed dosing functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computational load is performed on the infusion pump, then the pump can operate independently, but the pump's limited computational capabilities result in inefficiencies in determining optimal insulin doses
Solution Approach 1:
The patent extracts the complex computational functions from the infusion pump and relocates them to an external mobile device. The mobile device performs the computationally intensive tasks of determining optimal insulin doses using advanced algorithms and machine learning models, while the infusion pump retains only the essential function of delivering the calculated doses. This extraction resolves the contradiction by improving dosing efficiency through powerful external computation while maintaining the simplicity of the pump's computational architecture.
Solution Approach 2:
The patent introduces a mobile device as an intermediary between the user and the infusion pump. This intermediary handles the complex computational workload of calculating optimal insulin doses based on glucose data, pump settings, and algorithmic models. The mobile device communicates dose instructions to the pump, enabling efficient dosing determination without requiring the pump itself to possess advanced computational capabilities.
2Reliability
If the infusion pump operates in offline mode without connection to external devices, then it maintains independence, but it relies heavily on user inputs and has limited ability to determine optimal doses
Solution Approach 1:
The patent implements preliminary action by pre-computing and storing multiple dosing functions and algorithms in the mobile device before offline operation begins. These pre-computed dosing functions include machine learning models, algorithmic parameters, and dosing strategies that can be executed autonomously by the pump during offline periods. This allows the system to maintain high dosing accuracy without requiring continuous user input or external connectivity, as the computational work has already been performed in advance.
3Productivity
If the infusion pump uses simple dosing algorithms, then it maintains ease of operation, but it cannot provide optimized insulin delivery
Solution Approach 1:
The patent uses copying by transferring complex dosing algorithms and machine learning models from the mobile device to the infusion pump in the form of pre-computed dosing functions. These copied functions are simplified representations that can be executed on the pump's limited hardware, yet they embody the optimization intelligence of the more complex algorithms. This allows the pump to provide optimized insulin delivery without requiring the full complexity of the original algorithms to reside on the device.
Data Source
AI summary
A system for medicament infusion may include an infusion pump and a mobile device associated with a user. The mobile device is configured to determine an online dosing model and an offline model. The infusion pump is configured to determine an operation mode of the infusion pump based on a connection status between the mobile device and the infusion pump. The operation mode comprises an online mode when the infusion pump is connected to the mobile device and an offline mode when the infusion pump is not connected to the mobile device. The infusion pump is also configured to deliver a dose of medicament to the user based on the online dosing model or the offline dosing model, in accordance with a determination that the infusion pump is in an online mode or an offline mode.