Mobile Camera Test Strip Analysis for Plausible Color Readings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting analytes in bodily fluids using color formation reactions are prone to inaccuracies due to user-dependent handling errors and uncontrollable influences, leading to undetected color changes and incorrect analyte concentration measurements.
Innovation Solution
A determination method to establish a color expectation range for assessing the plausibility of color formation values by using a training set of optical test strips, which are either corrupted or non-corrupted, to determine a two-dimensional or three-dimensional color expectation range that accounts for proper handling and storage conditions, utilizing machine-learning algorithms to derive this range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If color formation reactions are used for analyte detection in bodily fluids, then the measurement can be performed with simple devices and methods, but user-dependent handling errors and uncontrollable influences cause inaccuracies in the color change evaluation
Solution Approach 1:
The system performs preliminary actions by capturing reference images of the test strip under known conditions before the actual measurement. These reference images are stored and used to compensate for variations in lighting, positioning, and device characteristics. This preliminary characterization of the measurement system allows subsequent measurements to be corrected for these systematic influences, improving accuracy without requiring complex real-time control.
Solution Approach 2:
The system implements feedback by comparing the measured color formation values against expected ranges derived from reference measurements. The evaluation unit uses this feedback to determine whether the color change is within plausible limits, and can request additional measurements or alert the user if the results fall outside expected ranges. This feedback mechanism helps identify and correct handling errors.
2Measurement precision
If multiple measurements are performed to account for handling errors and uncontrollable influences, then measurement accuracy improves, but the time required for analysis increases
Solution Approach 1:
The system performs preliminary measurements and stores reference data during device setup or initial use. These reference measurements characterize the specific device's response to known conditions. By having this reference data prepared in advance, the system can quickly compare subsequent measurements against these pre-established benchmarks without requiring time-consuming repeated measurements for each new sample.
Solution Approach 2:
The system creates a digital copy or model of the expected measurement outcomes based on reference data. Instead of performing multiple physical measurements on each sample, the system uses the stored reference images and color formation characteristics as a template for what valid results should look like. This allows rapid evaluation of new measurements by comparing them against the copied reference patterns.
3Reliability
If color reference values are used to compensate for lighting conditions and positioning variations, then measurement reliability improves, but the complexity of the evaluation system increases
Solution Approach 1:
The system uses a camera to create digital copies (images) of the test strip at different stages of the color formation process. These image copies are then processed using software algorithms that compare color values pixel-by-pixel or region-by-region. This approach to using digital copies and computational comparison is inherently more complex than simple optical filters but enables sophisticated compensation for lighting and positioning variations through image processing techniques.
Solution Approach 2:
The system replaces complex mechanical or optical compensation mechanisms with computational methods. Instead of using mechanical adjustments for lighting or positioning, the system uses software algorithms to mathematically correct for these variations by comparing measured values against reference data. This substitution of computational approaches for physical mechanisms increases software complexity but reduces mechanical 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 method enhances the accuracy of analyte concentration measurements by filtering out corrupted test strips and providing a reliable color expectation range, thereby reducing user-dependent errors and improving measurement precision.
Implementation Method 1
capturing, by using at least one mobile device (112) having at least one camera (114), a training set of images, the training set of images comprising images of at least one part of one or more of the reagent test regions (120)
Implementation Method 2
test elements and/or test strips comprising one or more test chemicals, which, in presence of the analyte to be detected, are capable of performing one or more detectable detection reactions, such as optically detectable detection reactions
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and devices for determining the concentration of at least one analyte in a bodily fluid A determination method of determining a color expectation range (132) for assessing the plausibility of a color formation value obtained in an analytical measurement based on a color formation reaction and a measurement method of performing an analytical measurement based on a color formation reaction by using a mobile device (112) having a camera (114) and a processor (130) are disclosed. Further disclosed are a determination system (110) for determining a color expectation range (132) for assessing the plausibility of a color formation value obtained in an analytical measurement based on a color formation reaction. The determination system comprises a training set of optical test strips (116) having a reagent test region (120). At least two of the training optical test strips are non-corrupted (122) and at least two are corrupted (124).