Hypoglycemia Probability Tracking via Blood Glucose Scale Symmetrization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting hypoglycemia in diabetes patients are imperfect, particularly due to the asymmetry of the blood glucose measurement scale, leading to biased predictions towards hyperglycemia and poor accuracy in detecting severe hypoglycemic events.
Innovation Solution
A method and system that uses a bivariate probability distribution based on the Low Blood Glucose Index (LBGI) and Average Daily Risk Range (ADRR) from self-monitoring blood glucose data to track the probability of hypoglycemia, employing a mathematical transformation to symmetrize the blood glucose scale and a quadratic risk function to weight deviations, enabling early warning of impending hypoglycemic events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If traditional standard deviation and variability measures are used to predict hypoglycemia, then the calculation is simple and straightforward, but the prediction accuracy is poor and biased towards hyperglycemia
Solution Approach 1:
The patent transforms the blood glucose measurement scale using a mathematical function f(BG) that maps the asymmetric glucose range to a symmetric transformed scale. This parameter transformation allows the use of simple statistical measures like standard deviation on the transformed scale, which then accurately reflects hypoglycemia risk while maintaining calculation simplicity.
Solution Approach 2:
The patent explicitly addresses the asymmetry of the blood glucose scale by applying a transformation function that creates symmetry in the transformed values. The function is designed such that deviations below and above the target glucose level are weighted equally in the transformed space, eliminating the bias towardshyperglycemia while preserving the asymmetric nature of clinical significance.
2Ease of operation
If the blood glucose measurement scale is used directly without transformation, then the clinical interpretation is straightforward, but the statistical analysis is biased towardshyperglycemia
Solution Approach 1:
The patent introduces a transformed glucose scale as an intermediary representation between the original clinical measurements and the statistical analysis. The transformation function serves as a mediator that preserves clinical meaning while enabling unbiased statistical evaluation, allowing results to be interpreted in both transformed and original glucose units.
3Measurement precision
If intensive diabetes treatment is applied to improve glycemic control, then HbA1c levels decrease, but the risk of severe hypoglycemia increases
Solution Approach 1:
The patent calculates the Low BG Index and risk metrics from historical glucose data before severe hypoglycemic events occur. This preliminary assessment allows clinicians to identify patients at high risk and adjust treatment intensity before dangerous hypoglycemia occurs, enabling preventive action rather than reactive management.
Solution Approach 2:
The patent provides feedback about hypoglycemia risk based on analyzed glucose patterns. This feedback loop allows clinicians to monitor not just average glucose control but also the variability and risk of extreme low values, enabling balanced treatment decisions that maintain control while minimizing severe hypoglycemia risk.
Data Source
AI summary
A method, system and related computer program product for tracking the probability of hypoglycemia from routine self-monitoring of blood glucose (SMBG) data in patients with diabetes. A specific bivariate probability distribution of low BG events based jointly on the Low BG Index (LBGI) and the Average Daily Risk Range (ADRR) is used to predict hypoglycemia probability of occurrence from inputted SMBG data. The SMBG data is retrieved from a series of SMBG data of a patient available from the patient's glucose meter and allows tracking of the probability for future hypoglycemia over a predetermined duration, e.g., a 24 or 48 hour period. The tracking includes presentation of visual and/or numerical output, as we construction of hypoglycemia risk trajectories that would enable warning messages for crossing of predefined thresholds, such as 50% likelihood for upcoming hypoglycemia below 50 mg/dl.