Glucose Monitoring System Using Probability Analysis for Insulin Dosing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current glucose monitoring systems for diabetes management do not effectively alert individuals when the probability of needing an insulin dose exceeds a threshold, leading to potential hypoglycemic or hyperglycemic events.
Innovation Solution
A system and method that analyze continuous glucose monitoring data to determine a probability analysis tool, comparing measured glucose values to threshold probabilities to trigger alerts and calculate insulin bolus doses, including a bolus calculator for determining safe insulin doses and preventing insulin stacking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If continuous glucose monitoring data is analyzed using probability analysis tools to determine insulin dosage requirements, then the accuracy of diabetes management decisions is improved, but the computational complexity and time required for analysis increases
Solution Approach 1:
The patent transforms the complex probability analysis problem into a more manageable form by changing parameters - using standardized statistical parameters (mean, standard deviation) and transforming glucose data into probability scores that can be compared against threshold values. This parameter transformation maintains analytical accuracy while simplifying the computational approach.
Solution Approach 2:
The analysis process is segmented into distinct computational stages: data collection, probability calculation, threshold comparison, and alert generation. By dividing the complex probability analysis into these discrete segments, the system manages computational complexity while maintaining overall accuracy in insulin dosage determination.
2Reliability
If probability threshold analysis is implemented to alert users when insulin dosage is needed, then the reliability of diabetes management alerts is improved, but the response time and computational overhead increase
Solution Approach 1:
The system performs preliminary calculations by continuously maintaining running statistics (mean and standard deviation) of glucose data as it is collected. This preliminary action allows the probability analysis to be performed rapidly when new data arrives, improving response time while maintaining reliable alert generation based on pre-computed statistical parameters.
Solution Approach 2:
The system implements continuous feedback by constantly comparing new glucose measurements against the probability thresholds and updating the running statistics. This real-time feedback mechanism ensures reliable alert generation while maintaining efficient response times through iterative refinement of the probability model.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems are disclosed analyzing a glucose level of a person having diabetes. The method, in at least one example, comprises receiving into a computing device a plurality of measured glucose values from a continuous glucose monitoring system coupled to a person having diabetes, analyzing the plurality of measured glucose values with a probability analysis tool on the computing device to determine a glucose threshold (g lc ), and a boundary (g ρ ) glucose value at a probability threshold where the person having diabetes requires at least a predetermined insulin dose, and comparing, with the computing device, the boundary glucose value (g ρ ) to the glucose threshold (g lc ), wherein if the boundary glucose value (g ρ ) is greater than the glucose threshold (g lc ) then the computing device performs an alert on a user interface.