Basal Rate Titration Model Using Timestamped Glucose Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current insulin titration methods are not robust enough to achieve target glucose levels with minimal glucose measurements, often leading to suboptimal insulin doses and inadequate glycaemic control.
Innovation Solution
A system and method that utilize timestamped autonomous glucose measurements and insulin medicament records to calculate a glycaemic risk measure and insulin sensitivity factor, enabling the generation of a basal rate titration schedule and a fasting blood glucose profile model to predict and maintain optimal fasting blood glucose levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional insulin titration methods are used, then patients can receive insulin treatment, but the titration is not robust enough to achieve target glucose levels with minimal glucose measurements
Solution Approach 1:
The system performs preliminary intensive glucose monitoring during a starter period to collect sufficient data before transitioning to less frequent measurements. This preliminary data collection enables the model to be trained and validated, allowing accurate predictions with fewer subsequent measurements.
Solution Approach 2:
The system continuously compares predicted glucose levels with actual measurements to validate and refine the insulin sensitivity factor and glucose profile model. This feedback mechanism ensures the model remains accurate while reducing the frequency of required measurements.
2Reliability
If frequent glucose measurements are performed, then target glucose levels can be monitored accurately, but the burden on patients increases and productivity decreases
Solution Approach 1:
The measurement frequency is dynamically adjusted based on the patient's needs and the model's confidence. During the starter period, measurements are intensive, but once the model is validated, the frequency is reduced to maintain reliability while improving patient productivity.
Solution Approach 2:
The system automates the titration process by having the insulin pump automatically adjust basal rates based on the validated model, reducing the need for manual patient intervention and frequent measurements while maintaining reliable glycaemic control.
3Measurement precision
If intensive glucose monitoring is implemented during the starter period, then robust insulin sensitivity factor calculation is achieved, but the device complexity and data processing requirements increase
Solution Approach 1:
The complex data processing and model validation functions are extracted from the insulin pump to an external computing device or server. The pump only needs to collect and transmit data, while the intensive computational tasks are performed externally, reducing the pump's complexity.
Solution Approach 2:
A software intermediary layer is introduced that handles the complex data processing, model training, and validation tasks. This intermediary sits between the simple data collection hardware and the decision-making algorithms, managing the complexity externally.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
Systems and methods for treating a subject are provided. A first dataset comprising timestamped autonomous glucose measurements of the subject over a first time course is obtained. A second dataset, associated with a standing insulin regimen for the subject over the first time course and comprising insulin medicament records, is also obtained. Each record comprises a timestamped administration event including an amount and type of insulin medicament administered into the subject by an insulin delivery device. The first and second datasets serve to calculate a glycaemic risk measure and an insulin sensitivity factor of the subject during the first time course, which are used to obtain a basal rate titration schedule and a fasting blood glucose profile model over a subsequent second time course for the subject. The model predicts the fasting blood glucose level of the subject based upon amounts of insulin medicament administered into the subject.