Infusion Pump Occlusion Detection Using Tubing Force Relaxation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing infusion pump systems face challenges in accurately detecting occlusions due to invasive sensors that risk contamination and non-invasive systems with degraded predictability under configuration changes, leading to potential under-infusion and life-threatening emergencies.
Innovation Solution
A fluid infusion pump system using a force measurement device and regression model to determine a time-decaying parameter, distinguishing between soft and hard occlusions by analyzing tubing force over time, and incorporating data filtering to provide robust infusion process assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive sensors are used for pressure measurement, then measurement precision is improved, but reliability deteriorates due to infection and contamination risks
Solution Approach 1:
The patent replaces the mechanical/invasive pressure sensor system with a non-invasive force measurement system. Instead of placing sensors inside the fluid path that risk contamination, the system uses external force sensors to measure the force exerted by the tubing on the pump mechanism, which is then converted to pressure information through mathematical modeling. This substitution eliminates the infection risk while maintaining measurement capability.
2Reliability
If non-invasive pressure measurement protocols are used, then reliability is improved by eliminating contamination risk, but measurement precision deteriorates due to degraded predictability under configuration changes
Solution Approach 1:
The patent addresses the predictability issue by dynamically adapting the mathematical model parameters based on actual system behavior. Instead of relying on fixed theoretical models that degrade under configuration changes, the system uses regression analysis and machine learning to continuously update the relationship between measured force and actual pressure, maintaining accuracy across different tubing configurations and pump settings.
Solution Approach 2:
The system incorporates feedback mechanisms where the measured force data is continuously compared against expected values based on the mathematical model. When deviations occur due to configuration changes, the system uses this feedback to adjust and refine the model parameters, ensuring sustained measurement precision across varying operating conditions.
3Measurement precision
If sophisticated averaging algorithms and machine learning algorithms are used, then measurement precision is improved for predicting occlusion, but device complexity increases
Solution Approach 1:
The patent extracts and isolates the specific mathematical relationship needed for occlusion detection from complex general-purpose machine learning algorithms. By focusing on the fundamental physical relationship between force and pressure in the tubing-pump system and modeling this specific interaction, the patent achieves accurate occlusion prediction without requiring sophisticated averaging algorithms, thereby reducing computational complexity while maintaining precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system reduces false positive and negative occlusion events, accurately models stress relaxation, and provides timely alerts, ensuring precise fluid pressure measurement and reducing the risk of under-infusion.
Implementation Method 1
determine a time-decaying parameter associated with a tubing force obtained by a sensor over time, the tubing force characterizing a force-time curve
Data Source
AI summary
An infusion pump for detection of a fluid condition in a flexible tubing is provided. The infusion pump includes a memory storing instructions, and a processor configured to execute the instructions to determine a time-decaying parameter associated with a tubing force obtained by a sensor over time, the tubing force characterizing a force-time curve, and determine a fluid pressure value for a fluid in the tube based at least in part on the time-decaying parameter. A machine implemented method for detecting a fluid condition in a flexible tube is also provided.