Artificial Pancreas Feedback Framework for Post-Prandial Hyperglycemia
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing closed-loop blood glucose control systems for Type 1 diabetes patients face challenges in managing post-prandial hyperglycemia, with limited actionable feedback provided by state-of-the-art data analysis, leading to suboptimal glycemic control and high HbA1C levels.
Innovation Solution
A data science-driven framework that interprets Continuous Glucose Monitor and insulin pump records to provide actionable feedback by analyzing post-prandial and post-absorptive glucose dynamics, auto mode vs. sensor augmented pump performance, and CGM unavailability, enabling clinicians to adjust carb ratios, active insulin time, bolus delivery patterns, and basal rates for improved insulin management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If closed-loop control systems are used to automate insulin delivery, then time in range is maximized and hypoglycemic events are avoided, but post-prandial hyperglycemia persists and HbA1C levels remain high
Solution Approach 1:
The patent segments the analysis of glycemic control into distinct phases: post-prandial (PP) phase and post-absorptive (PA) phase. By dividing the 24-hour period into these functional segments, the system can identify specific patterns of hyperglycemia in each phase and provide targeted feedback. This segmentation allows clinicians to distinguish between PP hyperglycemia (indicating inadequate bolus insulin) and PAhyperglycemia (indicating other issues), thereby resolving the contradiction by addressing hyperglycemia management with phase-specific precision while maintaining overall glycemic control stability.
2Loss of information
If detailed CGM data is collected and analyzed, then glycemic patterns can be identified, but actionable feedback for clinicians remains limited
Solution Approach 1:
The patent implements a feedback mechanism that transforms detailed CGM data into actionable clinical feedback. The system analyzes CGM measurements, identifies PP and PA hyperglycemic patterns, and provides specific recommendations to clinicians about adjusting insulin therapy. This feedback loop converts raw data into meaningful insights, resolving the contradiction by ensuring that information is not only extracted but also translated into precise actionable guidance for improving glycemic control.
Solution Approach 2:
The patent introduces an intermediary analysis layer between raw CGM data and clinical decision-making. This intermediary system processes the detailed CGM data, segments it into PP and PA phases, identifies hyperglycemic patterns, and formulates actionable recommendations. This intermediary transformation ensures that rich information from CGM data is effectively converted into precise actionable feedback that clinicians can use to adjust therapy.
3Object-affected harmful factors
If conservative bolus insulin-carb ratios are used, then hypoglycemia is avoided, but post-prandial hyperglycemia increases
Solution Approach 1:
The patent applies dynamic adjustment of insulin therapy parameters based on observed glycemic patterns. Rather than using fixed conservative ratios, the system continuously monitors PP and PA glucose levels and provides feedback for adjusting carb ratios, active insulin times, and bolus delivery patterns. This dynamic approach allows the system to increase bolus insulin aggressiveness when PPhyperglycemia is detected while maintaining hypoglycemia avoidance, resolving the contradiction by making insulin therapy adaptive rather than static.
Solution Approach 2:
The patent utilizes parameter changes in insulin therapy settings based on phase-specific glycemic patterns. When PPhyperglycemia is identified, the system recommends increasing the aggressiveness of bolus insulin delivery (changing the carb ratio parameter). When PAhyperglycemia is detected, it suggests evaluating other parameters such as active insulin time or basal rates. These targeted parameter changes allow the system to address hyperglycemia in each phase without compromising hypoglycemia safety.
Data Source
AI summary
The present disclosure discloses a data science driven system and associated methodology framework for mining relevant knowledge from input/output traces of a closed-loop control system for glycemic control to aid in actionable feedback for Type 1 diabetes management. The framework takes Continuous Glucose Monitor (CGM) records and insulin pump records from a closed loop control (CLC) system and interprets the CGM records and insulin pump data to provide medically useful information, wherein the closed-loop control system is operable for operation in an “auto mode” (AP) and a “manual mode” (SAP).