Pulse Oximeter Pathlength Correction for Accurate SpO2 Readings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical monitoring devices, such as pulse oximeters, face errors in oxygen saturation readings due to physiological factors like skin pigmentation, thickness, and abnormalities, leading to inaccurate blood oxygen saturation (SpO2) values.
Innovation Solution
A medical monitoring system that includes a sensor with a memory storing a sensor identifier, weight, and bias, and a monitor with processing circuitry to select coefficients based on the sensor identifier, input these to a neural network, and adjust oxygen saturation values using correction factors to generate a corrected SpO2 value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional pulse oximetry is used to measure oxygen saturation, then the measurement process is simple and quick, but the accuracy is reduced due to pathlength errors from skin variations
Solution Approach 1:
The system performs preliminary characterization of the sensor and patient tissue properties before the actual oxygen saturation measurement. The sensor identifier is read and used to select appropriate coefficients, and the neural network is pre-trained with pathlength correction data. This preliminary preparation enables accurate correction during the measurement process without adding significant complexity to the overall system.
Solution Approach 2:
The patent introduces a neural network as an intermediary component that processes the relationship between sensor characteristics, tissue properties, and oxygen saturation measurements. The neural network acts as a mediator that translates raw sensor data into corrected oxygen saturation values by accounting for pathlength errors, thereby improving measurement accuracy without requiring direct complex interactions between all system components.
2Measurement precision
If correction factors are applied to account for skin variations, then measurement accuracy is improved, but the computational complexity increases
Solution Approach 1:
The neural network is pre-trained offline with extensive pathlength correction data covering various skin types and sensor characteristics. This preliminary training phase separates the complex computational work from the real-time measurement process, allowing the system to apply pre-computed correction factors during actual use with minimal computational overhead.
Solution Approach 2:
The system changes the parameter space by using sensor identifiers as discrete inputs to select appropriate correction coefficients. Instead of continuously processing all possible tissue variation parameters, the system discretizes the problem by categorizing sensors and selecting pre-determined correction factors based on sensor type and measured optical properties, thereby reducing real-time computational complexity.
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 improves the accuracy of oxygen saturation readings by accounting for pathlength errors caused by skin variations, enabling precise health monitoring and management.
Implementation Method 1
inputting, via the processor, the coefficient, the weight and bias, or any combination thereof to a neural network to output a correction factor
Implementation Method 2
physiological factors affecting light absorption and scattering
Implementation Method 3
physiological factors affecting light absorption and scattering
Data Source
AI summary
A medical monitoring system including a sensor and a monitor. The sensor includes a sensor memory that stores a sensor identifier, a weight and bias, or any combination thereof. The monitor includes a port to communicatively couple to the sensor to receive a sensor signal, the sensor identifier, the weight and bias, or any combination thereof, a display, and monitor processing circuitry. The monitor processing circuitry to select a coefficient based on the sensor identifier, input the coefficient, the sensor signal, the weight and bias, or any combination thereof to a neural network to output a correction factor, and adjust a physiological parameter based on the correction factor.