Blood Glucose Data Imputation Between Sporadic Measurements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Individuals with diabetes face challenges in maintaining consistent blood glucose levels within recommended ranges, and existing blood glucose monitoring methods struggle to provide accurate predictions between sporadic measurements, making it difficult to implement effective lifestyle changes for better glycemic health.
Innovation Solution
A diabetes management platform that utilizes computational techniques such as Gaussian processes and Kalman filtering to impute blood glucose levels based on historical data, incorporating radial basis and periodic kernels to capture correlation and periodic patterns, enabling personalized and probabilistic estimation of glycemic health states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If blood glucose monitoring is performed sporadically, then measurement frequency is reduced and patient burden is decreased, but accuracy of glycemic state estimation deteriorates
Solution Approach 1:
The patent introduces an imputation model as an intermediary computational component that processes sporadic blood glucose measurements and generates continuous glycemic state estimates. This mediator fills the gaps between discrete measurements, allowing patients to monitor less frequently while maintaining accurate glycemic state assessment through statistical inference and pattern recognition algorithms.
Solution Approach 2:
The system creates virtual copies of blood glucose measurements through imputation, generating estimated glucose values at time points where actual measurements were not taken. These copied data points reconstruct the continuous glycemic profile from sparse sampling, enabling accurate estimation without requiring frequent physical measurements.
2Measurement precision
If continuous glucose monitoring is implemented, then glycemic state estimation accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the computational imputation functionality from complex continuous monitoring hardware and implements it as a separate software-based processing layer. This separates the measurement function (simple sporadic sampling) from the continuous estimation function (computational imputation), reducing hardware complexity while maintaining continuous glycemic state assessment through algorithmic processing of intermittent measurements.
3Reliability
If more blood glucose measurements are taken, then glycemic health management accuracy is improved, but loss of time and patient burden increase
Solution Approach 1:
The imputation model performs preliminary computational action by pre-calculating and storing the relationships between blood glucose measurements and glycemic state metrics. When new measurements are entered, the system rapidly retrieves and applies pre-computed imputation algorithms, avoiding time-consuming real-time calculations and enabling quick glycemic state assessment without requiring extensive measurement campaigns.
Data Source
AI summary
Introduced here are diabetes management platforms able to impute blood glucose level values for a subject whose glycemic health state is being monitored. These imputed values can be used to estimate the glycemic health state of the subject at a given point in time, identify appropriate recommendations for improving the glycemic health state, etc. More specifically, a diabetes management platform can initially acquire one or more explicit data values generated by a glucose monitoring device. The diabetes management platform can then design a statistical model for imputing data values based on the one or more explicit data values. The diabetes management platform may employ several different computational techniques for performing imputation.