Embedded Dose Optimization for Low-Power Drug Delivery Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional wearable drug delivery devices face limitations in computational power and memory, making it difficult to implement complex medication delivery algorithms that require high computational and power consumption, especially in disposable, small-scale electronics.

Innovation Solution

A simplified computational model is used to approximate the solution to the optimization problem, allowing for reduced computational cost and power consumption by performing a stepwise exploration across all possible search spaces, enabling the medication delivery algorithm to be executed onboard the wearable device.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a complex optimization algorithm is used to calculate medication delivery, then the accuracy and effectiveness of drug dosage calculation is improved, but the computational cost and power consumption increase significantly

Engineering Contradiction:
Improveaccuracy of drug dosage calculationVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by using a simplified optimization algorithm that performs only the necessary computational steps to achieve clinically acceptable accuracy. Instead of computing the exact optimal solution, the system uses a reduced-order model that captures the essential dynamics while omitting computationally intensive details, thereby achieving sufficient precision for medical decisions with dramatically lower power consumption.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the parameters of the optimization algorithm by reducing the complexity of the mathematical model. The system transforms the full-order optimization problem into a reduced-order problem by adjusting model parameters and computational resolution, enabling the algorithm to run on low-power embedded processors while maintaining clinically valid dosage calculations.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If a complex optimization algorithm is used to calculate medication delivery, then the accuracy and effectiveness of drug dosage calculation is improved, but the processing capability requirements increase

Engineering Contradiction:
Improveaccuracy of drug dosage calculationVSAvoidprocessing capability requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies partial action by implementing a simplified optimization algorithm that performs only the necessary computational steps. The system uses a reduced-order mathematical model that captures essential physiological dynamics while omitting computationally intensive details, enabling accurate dosage calculations to run on low-power embedded processors rather than requiring complex high-performance computing hardware.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent extracts the essential computational requirements from the full optimization algorithm. By separating and removing unnecessary computational complexity while retaining the core optimization logic, the system achieves sufficient accuracy for clinical use with minimal processing power requirements, making the algorithm suitable for wearable and implantable devices.

Inventive Principle:
Principle #2Taking out (Extraction)

3Reliability

If the medication delivery algorithm is executed onboard the wearable device, then the responsiveness and reliability of drug delivery is improved, but the computational cost and power consumption increase

Engineering Contradiction:
Improvereliability of drug deliveryVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by implementing a simplified optimization algorithm that performs only the necessary computational steps for reliable drug delivery. The reduced-order model maintains the essential feedback control capabilities needed for safe and effective insulin delivery while using minimal computational resources, enabling onboard execution without requiring high power consumption.

Inventive Principle:
Principle #16Partial or excessive action

4Use of energy by moving object

If a simplified computational model is used to approximate the optimization solution, then the computational cost and power consumption are reduced, but the accuracy of the solution may be compromised

Engineering Contradiction:
Improvepower consumptionVSAvoidaccuracy of optimization solution
Core Design Contradiction:
Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The patent changes the parameters of the computational model to achieve an optimal balance between accuracy and efficiency. By adjusting model complexity parameters and computational resolution, the system achieves clinically acceptable accuracy while using minimal processing power, making the approximation sufficient for medical decision-making.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent substitutes the complex mechanical computational system with a simplified mathematical model. Instead of using full-order physical and computational models that require extensive calculations, the system replaces them with reduced-order mathematical representations that capture essential dynamics with minimal computational effort, achieving sufficient precision for clinical use.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12409270B2Optimizing embedded formulations for drug delivery
Publication Date: 2025.09.09 INSULET CORP
  • US12409270B2 patent drawing
  • US12409270B2 patent drawing
  • US12409270B2 patent drawing

AI summary

Disclosed herein is a method for execution by a drug delivery device for determining an optimal dose of a liquid drug for current cycle of a medication delivery algorithm, the method utilizing a stepwise evaluation of a model and a cost function across a coarse search space consisting of coarse discrete quantities of the drug and a refined search space consisting of refined discrete quantities of the drug.