Automated Oxygen Control System for Preterm Infants
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for automatically controlling inspired oxygen delivery in preterm infants are imprecise, leading to excessive time outside target oxygen saturation ranges, and fail to account for individual variations in oxygenation responses and changing system gains over time.
Innovation Solution
A computer-implemented method and apparatus that generates output inspired oxygen concentration values by receiving oxygen saturation signals, using immediate, accumulation, and predictive control values, with non-linear compensation weighting based on the predetermined relationship between partial pressure of arterial oxygen and oxygen saturation, to maintain oxygen saturation within a target range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated control of FiO2 is implemented, then time in target SpO2 range increases, but system complexity increases
Solution Approach 1:
The controller dynamically adapts its response characteristics by adjusting gain coefficients based on the current SpO2 level relative to the target range. The system transitions between different control modes (proportional, integral, derivative) with varying weights depending on whether SpO2 is below, within, or above the target range, making the control system flexible and responsive to changing patient conditions
Solution Approach 2:
The system changes control parameters (gain coefficients: KP, KI, KD) based on the SpO2 error magnitude and direction. Different parameter sets are applied depending on the clinical situation (hypoxia, target range, hyperoxia), allowing the same hardware to deliver context-appropriate control actions without manual reconfiguration
2Ease of operation
If uniform automated control response is applied, then ease of operation improves, but adaptability to individual patients deteriorates
Solution Approach 1:
The control system applies different control strategies to different SpO2 conditions locally. When SpO2 is below target, aggressive corrective action is taken; when within target, maintenance mode operates; when above target, conservative adjustment is applied. This localized control quality matches the clinical priorities for each oxygenation state
Solution Approach 2:
The system dynamically adjusts its control characteristics based on real-time SpO2 measurements, transitioning between control modes as the patient's oxygenation status changes. This dynamic adaptation allows a single automated system to provide personalized control for each patient without requiring manual configuration
3Device complexity
If manual adjustment of FiO2 is performed, then device complexity is reduced, but manufacturing precision of SpO2 control deteriorates
Solution Approach 1:
The system continuously monitors SpO2 and FiO2 measurements and uses this feedback to automatically adjust the oxygen delivery. The closed-loop control compares actual SpO2 with target range and modifies FiO2 accordingly, achieving precision that would be difficult to maintain with manual adjustment alone
Solution Approach 2:
The control system performs self-adjustment based on the measured SpO2 and the control algorithm. The system serves itself by automatically detecting deviations from target and correcting FiO2 without requiring continuous manual intervention, thereby achieving precise control with reduced operational complexity
4Measurement precision
If non-linear compensation weighting is applied to accumulation control values, then SpO2 targeting effectiveness improves, but device complexity increases
Solution Approach 1:
The system applies non-linear compensation by modifying the accumulation control value based on the current SpO2 level. When SpO2 is far from target, different weighting is applied compared to when SpO2 is near target. This parameter transformation improves the accuracy of SpO2 targeting by accounting for the non-linear relationship between FiO2 changes and SpO2 response
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided herein is a method for automatically controlling inspired oxygen delivery, including: receiving signals representing a plurality of input oxygen saturation (SpO2) values for a patient; generating control values based on the input SpO2 values and a target SpO2 value; and generating output inspired oxygen concentration (FiO2) values based on the control values and reference inspired oxygen concentration (rFiO2) values; wherein the control values include: immediate control values, generated based on the input SpO2 values, the target SpO2 value, and an immediate gain coefficient; accumulation control values, generated based on the input SpO2 values, the target SpO2 value, and an accumulation gain coefficient; and predictive control values, generated based on the input SpO2 values, the target SpO2 value, and a predictive gain coefficient; wherein the immediate gain coefficient is determined based on the rFiO2 value; and wherein a non- linear compensation weighting is applied to the accumulation control value based on a predetermined non-linear relationship between partial pressure of arterial oxygen (PaO2) and SpO2.