A test paper test analysis method and system for medical tests

Abstract

The present invention discloses a test strip test analysis method and system for medical inspection, which relates to the technical field of medical inspection, and includes collecting spectral signals, filtering and multi-dimensional feature optimization of data; constructing a deep feature decomposition model and a multi-objective optimization prediction model; dynamically correcting test strip data, and generating a visual report according to the detection result. The test strip test analysis method for medical inspection provided by the present invention performs high-precision scanning on the surface of the test strip to obtain optical feature information, improves the sensitivity of the test strip detection to low-concentration target substances, decomposes the collected multi-dimensional spectral data into different feature signals, combines with a dynamic optimization model, comprehensively analyzes the characteristics of each target substance in the sample, improves the adaptability of the detection system, and improves the usability and ease of use of the detection result by automatically correcting the optical deviation and environmental noise during the collection process. The present invention achieves better effects in terms of sensitivity, adaptability and usability.

Description

Technical Field

[0001] The present invention relates to the technical field of medical testing, and specifically provides a test strip testing and analysis method and system for medical testing. Background Art

[0002] In recent years, the medical testing technology has developed rapidly. Especially in the field of biomarker detection and quantitative analysis, test strip detection has been widely used due to its advantages of low cost, convenient operation, and rapid result output. From the early visual colorimetric method, to the later simple optical colorimetric detection, and to the current multi-spectral analysis and computer-aided digital detection technology applied, the test strip detection technology has experienced a leapfrog development from qualitative analysis to semi-quantitative analysis. The introduction of optical detection technology has significantly improved the sensitivity and accuracy of test strip detection. At the same time, the automated analysis system combined with machine learning models has further improved the detection efficiency. However, in the face of the multi-target analysis requirements in complex biological samples, such as the detection of multiple co-existing biomarkers or low-concentration target substances, the existing technology still has certain limitations in terms of accuracy, resolution, and adaptability, and cannot fully meet the growing needs of precision medicine.

[0003] Although the test strip detection technology has been widely used in the medical field, the current mainstream methods still have many deficiencies. First of all, the traditional colorimetric method has a high dependence on the color change on the surface of the test strip. This method is not only easily interfered by environmental light, but also often results in inaccurate results due to the cross-interference of different biomarkers in complex samples. Secondly, most of the existing optical detection methods focus on single-band or simple optical feature extraction, and it is difficult to comprehensively reflect the multi-dimensional spectral characteristics of the test strip reaction area, resulting in insufficient sensitivity in the detection of low-concentration target substances. In addition, the existing technology generally lacks the ability of dynamic calibration and multi-target optimization of detection data. For example, in the case of multiple co-existing biomarkers, it is difficult for traditional analysis methods to achieve high-precision qualitative and quantitative analysis simultaneously. Finally, the interpretation of test results often relies on manual experience, lacking intelligent automated analysis tools, which not only increases the risk of subjective errors, but also is difficult to meet the needs of high-throughput detection. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing test strip testing and analysis methods have insufficient detection sensitivity, high sensitivity to ambient light, difficulty in coping with cross-interference of multiple biomarkers, and how to achieve the optimization of high sensitivity, high precision, and intelligent detection.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A test paper test analysis method for medical tests, including collecting spectral signals, filtering and multi-dimensional feature optimization of the data; constructing a deep feature decomposition model and a multi-objective optimization prediction model; dynamically correcting the test paper data and generating a visualization report according to the test results.

[0007] As a preferred embodiment of the test paper test analysis method for medical tests of the present invention, wherein: the collecting of spectral signals includes collecting reflection, absorption, and scattering signals on the surface of the test paper through a high-precision optical scanning device within different wavelength ranges, capturing color changes, light absorption intensity, and scattering characteristics on the test paper by scanning the reaction area on the test paper surface. During the collection process, the interference of environmental light conditions, the self-bias of the scanning device, and the optical property differences of the test paper material are controlled and corrected in real time, and the characteristic differences between different spectral bands are analyzed. The spectral signal collection is expressed as:

[0008]

[0009] I(λ,t)=R(λ)e -α(λ)t +S(λ)sin(βλt)

[0010] wherein, I(λ,t) is the optical signal intensity of the reaction area of the test paper at wavelength λ and time t, R(λ) is the reflection spectral intensity at wavelength λ, α(λ) is the light absorption coefficient at wavelength λ, t is the reaction time, S(λ) is the scattering spectral intensity at, β is the coupling coefficient in the scattering characteristics, D(λ,t) is the normalized optical signal intensity under the conditions of wavelength λ and time t, G(λ,t) is the interference intensity of the environmental background light, and t1 and t2 are respectively the start and end points of the time interval for optical signal collection.

[0011] As a preferred embodiment of the test paper test analysis method for medical tests of the present invention, wherein: the filtering and multi-dimensional feature optimization of the data includes, after collecting the preliminary spectral data, optimizing through data processing, removing the interference signals caused by equipment noise, environmental light changes, and non-target components in the sample, and extracting the most representative feature signals for the target substance from the original data through multi-dimensional feature analysis. During the process, the reaction time, the characteristics of different spectral bands, and the potential complexity in the sample are considered. The data filtering and multi-dimensional feature optimization are expressed as:

[0012]

[0013] wherein, is the preliminary intensity calculation value of the feature signal in the i-th scan, N is the number of data feature dimensions, F j is the signal weight of the j-th dimension, H jis the intensity of the signal in the j-th dimension, T j is the response time value of the j-th signal, δ is the time compensation coefficient, γ is the time sensitivity adjustment coefficient, Y i is the normalized signal quality factor, M(λ) is the spectral noise signal function, dλ is the differential element in the integration, representing the infinitesimal change in the wavelength variable λ during the integration process, λ min and λ max are the minimum and maximum values of the spectral wavelength range, respectively.

[0014] As a preferred scheme of the test paper test analysis method for medical tests described in the present invention, wherein: the deep feature decomposition model includes the spectral signal detected by the test paper passing through the feature decomposition model, decomposing the complex spectral signal into components that are easy to analyze. The characteristic components reflect the dynamic behavior of the target substance reaction and reveal the characteristics of different reaction stages. By comprehensively analyzing the error distribution of the multi-dimensional spectral signals during the decomposition process, the feature extraction results are optimized. The deep feature decomposition model is expressed as:

[0015]

[0016] wherein, F h (x, y) is the value after calculating the gradient and second derivative of the two-dimensional feature signal, F(x, y) is the two-dimensional feature distribution function of the test paper reaction area, x and y are the spatial coordinates of the reaction area, P k is the normalized feature decomposition value, x1 and x2 are the starting and ending points of the spatial range of the feature distribution respectively, E i is the error value in the i-th dimension, W i is the weight of the error in the i-th dimension, and m is the total number of error dimensions.

[0017] As a preferred scheme of the test paper test analysis method for medical tests described in the present invention, wherein: the multi-objective optimization prediction model includes comprehensively analyzing multiple parameters and constructing a model for predicting the state of the target substance. The prediction model integrates the various variables in the test paper detection, dynamically adjusts the weights, and the output result reflects the characteristics of the target substance and is adjusted according to the detection conditions and background situations of different samples. Through the multi-objective optimization model, the complex chemical reaction process in the test paper detection is predicted, expressed as:

[0018]

[0019] wherein, Z t is the intermediate calculated value adjusted based on time, T p is the time variable of the p-th reaction, θ is the dynamic adjustment index of time, φ p is the phase difference of the p-th reaction signal, Z is the normalized optimized prediction value, U qis the mean of the q-th signal feature, κ q is the attenuation coefficient of the q-th signal feature.

[0020] As a preferred solution of the test paper test analysis method for medical tests according to the present invention, wherein: the dynamic correction of the test paper data includes eliminating various equipment errors and environmental interferences during the test paper detection process. The dynamic calibration monitors the detection conditions in real time, and compares the actually collected multi-dimensional spectral signals with the preset calibration reference data to automatically adjust the detection parameters. By adjusting the sensitivity of the detection equipment and the weight of signal processing to correct the deviation, the dynamic calibration is expressed as:

[0021]

[0022] where C x is the intermediate signal value of the dynamic calibration, K is the amplitude constant of the oscillation signal, ω is the frequency of the oscillation signal, L is the amplitude constant of the attenuation signal, η is the exponential attenuation coefficient of the signal, C is the dynamic calibration factor, N k is the k-th noise factor, and n is the total number of noise factors.

[0023] As a preferred solution of the test paper test analysis method for medical tests according to the present invention, wherein: the generation of the visualization report according to the detection result includes, after completing the detection analysis, quantitatively analyzing the characteristics of the detection signal and generating a score in combination with the specific background information of the sample. The score output is expressed as:

[0024]

[0025] where S x is the score signal value of the intermediate calculation, R(t) is the calibrated signal intensity, ρ is the growth rate of the time signal, T(t) is the noise signal of time, γ is the signal phase adjustment coefficient, S is the output score value, V i is the variance of the i-th signal feature, and o is the total dimension number of the signal features.

[0026] Another object of the present invention is to provide a test paper test analysis system for medical tests, which can construct a deep feature decomposition model and a multi-objective optimization prediction model through a model construction module for high-precision analysis of the collected and processed data, and solves the problem that it is difficult to effectively separate the characteristic signals of the target substance in the case of coexistence of multiple markers at present, and it is easy to have cross-interference.

[0027] As a preferred solution of the test strip test analysis system for medical tests described in the present invention, it includes an acquisition and processing module, a model construction module, and a dynamic correction module; the acquisition and processing module is used to acquire spectral signals and filter and optimize multi-dimensional features of the data; the model construction module is used to construct a deep feature decomposition model and a multi-objective optimization prediction model; the dynamic correction module is used to dynamically correct the test strip data and generate a visualization report according to the detection result.

[0028] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the test strip test analysis method for medical tests are implemented.

[0029] A computer-readable storage medium stores a computer program. It is characterized in that when the computer program is executed by a processor, the steps of the test strip test analysis method for medical tests are implemented.

[0030] The beneficial effects of the present invention: The test strip test analysis method for medical tests provided by the present invention performs high-precision scanning on the surface of the test strip to obtain multi-band optical characteristic information including reflected light, absorbed light, and scattered light, improves the sensitivity of the test strip detection to low-concentration target substances, and enhances the resolution ability of multi-object characteristics in complex biological samples. Through the deep feature decomposition model, the acquired multi-dimensional spectral data is decomposed into different feature signals, and combined with the dynamic optimization model, the characteristics of each target substance in the sample are comprehensively analyzed, improving the adaptability of the detection system. By automatically correcting the optical deviation and environmental noise during the acquisition process, the usability and ease of use of the detection result are improved. The present invention achieves better effects in terms of sensitivity, adaptability, and usability. Description of the Drawings

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0032] Figure 1 It is the overall flowchart of a test strip test analysis method for medical tests provided by the first embodiment of the present invention.

[0033] Figure 2 It is the overall module diagram of a test strip test analysis system for medical tests provided by the third embodiment of the present invention. Detailed Embodiments

[0034] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0035] Embodiment 1

[0036] Referring to Figure 1 , an embodiment of the present invention provides a test paper test analysis method for medical testing, including:

[0037] S1: Collect spectral signals and filter and optimize the data for multi-dimensional features.

[0038] Furthermore, collecting spectral signals includes using a high-precision optical scanning device.

[0039] It should be noted that the reflection, absorption, and scattering signals on the surface of the test paper are collected within different wavelength ranges. By scanning the reaction area on the surface of the test paper, the color changes, light absorption intensity, and scattering characteristics on the test paper are captured. During the collection process, the interference of environmental light conditions, the self-deviation of the scanning device, and the optical property differences of the test paper material are controlled and corrected in real time, and the characteristic differences between different spectral bands are analyzed. The spectral signal collection is expressed as:

[0040]

[0041] I(λ,t) = R(λ)e -α(λ)t + S(λ)sin(βλt)

[0042] where I(λ,t) is the optical signal intensity of the reaction area of the test paper at wavelength λ and time t, R(λ) is the reflection spectral intensity at wavelength λ, α(λ) is the light absorption coefficient at wavelength λ, t is the reaction time, S(λ) is the scattering spectral intensity at, β is the coupling coefficient in the scattering characteristics, D(λ,t) is the normalized optical signal intensity under the conditions of wavelength λ and time t, G(λ,t) is the interference intensity of the environmental background light, and t1 and t2 are respectively the start and end points of the time interval for optical signal collection.

[0043] It should also be noted that during the test strip detection process, the optical scanning device scans the surface of the test strip through a multi-band light source to capture the optical reaction signals in the target area. The optical reaction signals include multi-dimensional characteristics such as the intensity of reflected light, absorption at specific wavelengths, and the angular distribution of scattered light. Through a high-resolution sensor, the changes of these characteristic signals in different wavelengths, time, and spatial regions can be collected in real time. To eliminate the interference caused by ambient light, the device ensures that the collected signals truly reflect the chemical characteristics of the reaction area of the test strip by setting a mechanism for dynamically adjusting the light source intensity and noise shielding. The collection process can capture weak color changes or optical characteristics, enhancing the detection ability for low-concentration target substances.

[0044] Furthermore, filtering and multi-dimensional feature optimization of the data are carried out after collecting the preliminary spectral data.

[0045] It should be noted that through data processing for optimization, the interference signals caused by device noise, ambient light changes, and non-target components in the sample are removed, and through multi-dimensional feature analysis, the characteristic signals most representative of the reaction of the target substance are extracted from the original data. During the process, the reaction time, characteristics of different spectral bands, and potential complexity in the sample are considered. The data filtering and multi-dimensional feature optimization are expressed as:

[0046]

[0047] Among them, is the preliminary intensity calculation value of the characteristic signal in the i-th scan, N is the number of data feature dimensions, F j is the signal weight of the j-th dimension, H j is the intensity of the signal in the j-th dimension, T j is the reaction time value of the j-th signal, δ is the time compensation coefficient, γ is the time sensitivity adjustment coefficient, Y i [[ID=X]]is the normalized signal quality factor, M(λ) is the spectral noise signal function, dλ is the differential element in the integral, representing the infinitesimal change of the wavelength variable λ during the integration process, λ min and λ max are respectively the minimum and maximum values of the spectral wavelength range.

[0048] It should also be noted that the collected original spectral signals may contain interference factors such as ambient light, device noise, and reflection of the test strip substrate. It is necessary to perform quality filtering on the spectral signals through data preprocessing. According to the characteristics of different spectral bands, an appropriate filtering mechanism is applied to remove background noise, and at the same time, the signals directly related to the target reaction characteristics are separated. The signals are normalized to reduce the deviation caused by differences in test strip batches or detection environments. Through the feature extraction algorithm, the core features closely related to the reaction characteristics of the target substance are extracted from the multi-band signals. The optimization process improves the resolution and sensitivity of the signals.

[0049] S2: Construct a deep feature decomposition model and a multi-objective optimization prediction model.

[0050] Furthermore, the deep feature decomposition model includes the spectral signals detected by the test strip passing through the feature decomposition model.

[0051] It should be noted that the complex spectral signals are decomposed into components that are easy to analyze. The characteristic components reflect the dynamic behavior of the target substance reaction and reveal the characteristics of different reaction stages. By comprehensively analyzing the error distribution of the multi-dimensional spectral signals during the decomposition process, the feature extraction results are optimized. The deep feature decomposition model is expressed as:

[0052]

[0053] where, F h (x, y) is the value of the two-dimensional feature signal after gradient and second derivative calculations, F(x, y) is the two-dimensional feature distribution function of the test strip reaction area, x and y are the spatial coordinates of the reaction area, P k is the normalized feature decomposition value, x1 and x2 are the starting and ending points of the spatial range of the feature distribution respectively, E i is the error value of the i-th dimension, W i is the weight of the error of the i-th dimension, and m is the total number of error dimensions.

[0054] It should also be noted that the spectral signals contain multi-dimensional complex data, and these data need to be decomposed to extract key information. The complex signals are separated into single feature signals that are easy to analyze by feature decomposition, such as the change in absorbance peak or reflectance at a specific wavelength. When decomposing the signals, the interaction between different dimensions also needs to be considered, such as the coupling relationship between time dynamic changes and spectral characteristics. At the same time, to ensure the accuracy of the decomposition results, the error distribution in the signals is modeled, such as the signal deviation caused by device optical deviation or sample characteristic differences. Through the decomposed feature signals, the chemical reaction characteristics of the target substance can be accurately identified.

[0055] Furthermore, the multi-objective optimization prediction model includes comprehensive analysis of multiple parameters.

[0056] It should be noted that a model for predicting the state of the target substance is constructed. The prediction model integrates various variables in the test strip detection, dynamically adjusts the weights, and the output result reflects the characteristics of the target substance. It is adjusted according to the detection conditions and background of different samples. Through the multi-objective optimization model, the complex chemical reaction process in the test strip detection is predicted, which is expressed as:

[0057]

[0058] Among them, Z t is the intermediate calculated value adjusted based on time, T p is the time variable of the p-th reaction, θ is the dynamic adjustment index of time, φ p is the phase difference of the p-th reaction signal, Z is the optimized prediction value after normalization, U q is the mean value of the q-th signal feature, κ q is the attenuation coefficient of the q-th signal feature.

[0059] It should also be noted that the goal of test strip detection is not only to identify the presence of the target substance, but also to simultaneously detect multiple components or analyze their concentration changes. By constructing a multi-objective optimization model, the characteristic signals of different target substances are comprehensively analyzed. This model can adapt to the situation where multiple markers coexist in complex samples, and at the same time optimize the recognition and quantification results of each target. The model realizes the enhancement of weak signals and the suppression of strong interference signals by dynamically adjusting the weights of different features. Combining with the time dynamic characteristics of the sample, the model can predict the completion state of the chemical reaction and the final concentration of the target substance, improving the accuracy and adaptability of the detection, and at the same time reducing the errors caused by cross-interference.

[0060] S3: Dynamically correct the test strip data and generate a visualization report according to the detection results.

[0061] Furthermore, dynamically correcting the test strip data includes eliminating various equipment errors and environmental interferences in the test strip detection process.

[0062] It should be noted that dynamic calibration monitors the detection conditions in real time and compares the actually collected multi-dimensional spectral signals with the preset calibration reference data to automatically adjust the detection parameters. By adjusting the sensitivity of the detection equipment and the weight correction deviation of signal processing, the dynamic calibration is expressed as:

[0063]

[0064] Among them, C x is the intermediate signal value of dynamic calibration, K is the amplitude constant of the oscillation signal, ω is the frequency of the oscillation signal, L is the amplitude constant of the attenuation signal, η is the exponential attenuation coefficient of the signal, C is the dynamic calibration factor, Nk is the k-th noise factor, and n is the total number of noise factors.

[0065] Furthermore, generating a visualization report according to the detection result includes, after completing the detection and analysis, quantitatively analyzing the characteristics of the detection signal, and generating a score in combination with the specific background information of the sample. The score output is expressed as:

[0066]

[0067] Among them, S x is the score signal value of the intermediate calculation, R(t) is the calibrated signal intensity, ρ is the growth rate of the time signal, T(t) is the noise signal of time, γ is the signal phase adjustment coefficient, S is the output score value, V i is the variance of the i-th signal feature, and o is the total dimension number of the signal features.

[0068] Embodiment 2

[0069] An embodiment of the present invention provides a test strip test analysis method for medical tests. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0070] Multiple groups of tests are carried out, covering different environmental conditions and sample types. 6 groups of samples are selected for the test, and each group of samples contains target substances with different concentrations, simulating a real medical detection scenario. The test equipment includes an optical scanner, a data processing platform, and a dynamic calibration system. Among them, the optical scanner supports multi-band spectral acquisition (including reflection, scattering, and absorption signals), and the data processing platform integrates a deep feature decomposition model and a multi-objective optimization prediction algorithm.

[0071] During the test process, first, spectral scanning is performed on each group of samples, and the original signal is collected through multi-dimensional optical technology in the reaction area, and the reflected light intensity and environmental noise level are recorded. Subsequently, the collected data is input into the data integration platform, and the target feature peak is extracted by using the feature decomposition model and the noise is filtered. On this basis, the characteristics of the target substance are dynamically fitted by using the multi-objective optimization algorithm to generate a predicted concentration. To ensure the accuracy of the result, the test combines the dynamic calibration technology to adjust the deviation introduced by environmental light, equipment error, and test strip batch difference in real time. Finally, a detection report is generated according to the calibration result, and key parameters such as the precision rate and the degree of environmental interference are recorded.

[0072] As shown in Table 1, after dynamic calibration, the signal intensity of each sample is significantly improved, and the interference of environmental noise on the detection result is reduced compared with the initial signal intensity. The calibrated signal intensity of sample A is optimized from 12.5W / m 2 to 11.3W / m 2 , and the background noise level is from 1.2W / m2 Reduced to a negligible range. The calibrated signal not only enhances the detectability of target features but also improves the precision of detecting low-concentration target substances (such as sample F, 4.7 mg / L), reaching 98.3%. From the precision data, the average precision of each sample detection exceeds 97.9%, significantly higher than that of traditional detection methods (usually 90% - 93%). In addition, the degree of environmental light interference is effectively controlled, and the maximum interference value is only 0.8%, demonstrating the adaptability of the method of the present invention to environmental light changes.

[0073] Table 1 Experimental data table

[0074]

[0075] Example 3

[0076] Refer to Figure 2 , which is an embodiment of the present invention, provides a test paper test analysis system for medical tests, including: a collection and processing module, a model construction module, and a dynamic correction module.

[0077] Among them, the collection and processing module is used to collect spectral signals, filter data, and optimize multi-dimensional features; the model construction module is used to construct a deep feature decomposition model and a multi-objective optimization prediction model; the dynamic correction module is used to dynamically correct test paper data and generate a visual report according to the detection results.

[0078] If the function is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. As used in this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0080] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing as necessary, and then stored in a computer memory.

[0081] It should be understood that the various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A test paper test analysis method for medical tests, characterized in that, Including: Collect spectral signals, filter the data, and optimize multi-dimensional features; Construct a deep feature decomposition model and a multi-objective optimization prediction model; Dynamically correct the test strip data and generate a visualization report according to the detection results; The filtering and multi-dimensional feature optimization of the data includes, after collecting preliminary spectral data, optimizing through data processing, removing interference signals caused by device noise, environmental light changes, and non-target components in the sample, and through multi-dimensional feature analysis, extracting the most representative feature signals for the target substance from the original data. During the process, reaction time, characteristics of different spectral bands, and potential complexity in the sample are considered. The data filtering and multi-dimensional feature optimization are expressed as: Among them, is the preliminary intensity calculation value of the characteristic signal in the i-th scan, N is the number of data characteristic dimensions, F j is the signal weight of the j-th dimension, H j is the intensity of the signal in the j-th dimension, T j is the response time value of the j-th signal, δ is the time compensation coefficient, γ is the time sensitivity adjustment coefficient, Y i is the normalized signal quality factor, M(λ) is the spectral noise signal function, dλ is the differential element in the integral, representing the infinitesimal change of the wavelength variable λ in the integration process, λ min and λ max are the minimum and maximum values of the spectral wavelength range, respectively; The deep feature decomposition model includes that the spectral signals detected by the test strip are decomposed by the feature decomposition model into components that are easy to analyze. The feature components reflect the dynamic behavior of the target substance reaction and reveal the characteristics of different reaction stages. By comprehensively analyzing the error distribution of multi-dimensional spectral signals during the decomposition process, the feature extraction results are optimized. The deep feature decomposition model is expressed as: Among them, F h (x, y) is the value of the two-dimensional feature signal after gradient and second derivative calculations, F(x, y) is the two-dimensional feature distribution function of the test paper reaction area, x and y are the spatial coordinates of the reaction area, P k is the normalized eigenvalue decomposition value, x1 and x2 are the starting and ending points of the spatial range of the feature distribution respectively, E i is the error value of the i-th dimension, W i is the weight of the error of the i-th dimension, and m is the total number of error dimensions; The multi-objective optimization prediction model includes comprehensively analyzing multiple parameters and constructing a model to predict the state of the target substance. The prediction model integrates various variables in the test strip detection, dynamically adjusts the weights, and the output result reflects the characteristics of the target substance and is adjusted according to the detection conditions and background situations of different samples. Through the multi-objective optimization model, the complex chemical reaction process in the test strip detection is predicted, expressed as: Among them, Z t is the intermediate calculated value adjusted based on time, T p is the time variable of the p-th reaction, θ is the dynamic adjustment exponent of time, φ p is the phase difference of the p-th reaction signal, Z is the optimized prediction value after normalization, U q is the mean value of the q-th signal feature, κ q is the attenuation coefficient of the q-th signal feature; The dynamic correction of the test strip data includes eliminating various device errors and environmental interferences during the test strip detection process. The dynamic calibration monitors the detection conditions in real time and compares the actually collected multi-dimensional spectral signals with the preset calibration reference data to automatically adjust the detection parameters. By adjusting the sensitivity of the detection device and the weight of signal processing to correct the deviation, the dynamic calibration is expressed as: Among them, C x is the intermediate signal value for dynamic calibration, K is the amplitude constant of the oscillation signal, ω is the frequency of the oscillation signal, L is the amplitude constant of the attenuation signal, η is the exponential attenuation coefficient of the signal, C is the dynamic calibration factor, N k is the k-th noise factor, and n is the total number of noise factors.

2. The test strip test analysis method for medical tests according to claim 1, characterized in that: The collection of spectral signals includes collecting the reflection, absorption, and scattering signals on the surface of the test strip through a high-precision optical scanning device within different wavelength ranges. By scanning the reaction area on the surface of the test strip, capturing the color changes, light absorption intensity, and scattering characteristics on the test strip. During the collection process, the interferences of environmental light conditions, the self-deviation of the scanning device, and the optical property differences of the test strip material are controlled and corrected in real time, and the characteristic differences between different spectral bands are analyzed. The spectral signal collection is expressed as: I(λ,t) = R(λ)e -α(λ)t + S(λ)sin(βλt) Where, I(λ,t) is the optical signal intensity of the reaction area of the test strip at wavelength λ and time t, R(λ) is the reflection spectral intensity at wavelength λ, α(λ) is the light absorption coefficient at wavelength λ, t is the reaction time, S(λ) is the scattering spectral intensity at, β is the coupling coefficient in the scattering characteristics, D(λ,t) is the normalized optical signal intensity under the conditions of wavelength λ and time t, G(λ,t) is the interference intensity of the environmental background light, and t1 and t2 are respectively the start and end points of the time interval for optical signal collection.

3. The test strip test analysis method for medical tests according to claim 2, characterized in that: The generation of the visualization report according to the detection result includes, after the completion of the detection analysis, quantitatively analyzing the characteristics of the detection signal and generating a score in combination with the specific background information of the sample, and the score output is expressed as: Among them, S x is the scoring signal value for intermediate calculation, R(t) is the calibrated signal strength, ρ is the growth rate of the time signal, T(t) is the time noise signal, γ is the signal phase adjustment coefficient, S is the output scoring value, V i is the variance of the i-th signal feature, and o is the total number of dimensions of the signal feature.

4. A system adopting the test strip test analysis method for medical tests as described in any one of claims 1 to 3, characterized in that: It includes a collection and processing module, a model construction module, and a dynamic correction module; The collection and processing module is used to collect spectral signals and filter and optimize multi-dimensional features of the data; The model construction module is used to construct a deep feature decomposition model and a multi-objective optimization prediction model; The dynamic correction module is used to dynamically correct the test strip data and generate a visualization report according to the detection result.

5. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the test strip test analysis method for medical tests described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the test strip test analysis method for medical tests described in any one of claims 1 to 3.

Images