Glucose Forecasting Interface for Insulin Bolus Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing insulin infusion systems face challenges in managing blood glucose levels due to variations in insulin response and user activities, requiring manual estimation of carbohydrate intake for bolus dosages, which can lead to therapy inefficiencies and increased patient workload.
Innovation Solution
A patient monitoring system with a graphical user interface that forecasts glucose levels and allows users to adjust predicted activities and events, dynamically updating forecasts based on user input, and provides recommendations for insulin bolus amounts to maintain desired glucose levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual estimation of carbohydrate intake is used to determine bolus dosage, then the user can control insulin delivery, but the patient workload increases and therapy effectiveness decreases due to manual errors
Solution Approach 1:
The system automatically detects meals through sensors and algorithms, eliminating the need for manual carbohydrate counting. The glucose monitor self-adjusts bolus recommendations based on detected glucose patterns and meal indicators, allowing the system to serve itself rather than requiring constant patient input.
Solution Approach 2:
The system continuously monitors glucose levels and uses this feedback to automatically adjust bolus dosage recommendations. The closed-loop control mechanism processes real-time glucose data, insulin absorption models, and meal detection signals to generate optimized bolus suggestions, creating a continuous feedback cycle that improves therapy effectiveness while reducing patient burden.
2Reliability
If automated insulin delivery adjustments are implemented, then therapy effectiveness improves, but system complexity increases
Solution Approach 1:
The glucose monitor serves multiple functions: it acts as a continuous glucose sensor, a meal detector, an insulin absorption model calculator, and a bolus recommendation engine. By consolidating these functions into a single device rather than requiring separate systems, the patent reduces overall system complexity while maintaining automated therapy effectiveness.
Solution Approach 2:
The patent combines meal detection algorithms, glucose sensing, and bolus calculation into an integrated system. The sensor data, meal indicators, and insulin models are merged into a unified control algorithm that generates bolus recommendations, simplifying the architecture compared to separate independent systems for each function.
3Manufacturing precision
If personalized activity planning is provided, then glucose control improves, but the computational requirements and processing time increase
Solution Approach 1:
The system pre-calculates activity factors and their expected impact on glucose levels based on historical data and physiological models. By preparing these calculations in advance rather than computing them in real-time during glucose management, the system achieves personalized precision without excessive processing delays during critical decision moments.
Solution Approach 2:
The system focuses computational resources on the most impactful activity factors and time periods, rather than equally processing all possible variables. By prioritizing calculations for activities with the greatest expected glucose impact and using simplified models for less critical parameters, the system achieves sufficient precision while reducing overall computational burden and processing time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Infusion devices and related medical devices, patient data management systems, and methods are provided for monitoring a physiological condition of a patient. A method of managing a physiological condition of a patient using infusion of a fluid to influence the physiological condition of the patient involves obtaining a cost function representative of a desired performance for a bolus of the fluid to be delivered, obtaining a value for the physiological condition of the patient at a time corresponding to the bolus, determining a prediction for the physiological condition of the patient after the time corresponding to the bolus based at least in part on the value for the physiological condition using a prediction model, identifying a recommended amount of fluid to be associated with the bolus input to the prediction model that minimizes a cost associated with the prediction using the cost function, and providing indication of the recommended amount of fluid for the bolus.