Intelligent POCT detection method and system based on 5G and microfluidic technology

Abstract

The invention discloses an intelligent POCT detection method and system based on 5G and a microfluidic technology. The method comprises the following steps: acquiring initial data of a sample collected in real time by adopting a microfluidic technology in combination with an integrated sensor; preprocessing the initial data, and converting the preprocessed data to obtain converted data; constructing a mathematical model between the sample characteristic change and the target analyte concentration according to the converted data; analyzing a frequency domain corresponding to the time sequence signal of the initial data, and determining a high-frequency component and a low-frequency component in the frequency domain in combination with a set threshold value; calculating the change condition of the sample characteristics according to the high-frequency component and the low-frequency component by using the mathematical model, and deducing the abnormal condition or pathogen type existing in the sample to obtain a deducing result; and sending the inference result by using a 5G technology. By implementing the method provided by the invention, the real-time performance, the accuracy and the overall performance of POCT detection can be improved.

Description

Technical Field

[0001] The present invention relates to a POCT detection method, and more specifically to an intelligent POCT detection method and system based on 5G and microfluidic technology. Background Art

[0002] With the increase in medical and health needs, POCT (Point-of-Care Testing) technology, as a fast, convenient and on-site testing technology, has been widely used in clinical diagnosis, disease screening and health monitoring.

[0003] However, traditional POCT devices have certain limitations in sample processing speed, data transmission efficiency, and result accuracy. Specifically, traditional POCT devices may not be able to produce results quickly, which limits their ability to respond immediately in field applications. Due to the lack of efficient communication protocols or infrastructure support, traditional POCT devices have slow data upload and download speeds, affecting the real-time and interactivity in application scenarios such as telemedicine. Some POCT tests may require a high sample volume or be not sensitive enough to the identification of specific biomarkers, resulting in inaccurate test results. Limited by the development of technology and materials science, some POCT devices provide limited quantitative analysis capabilities and are difficult to meet the high-precision standards required for clinical diagnosis. Moreover, existing POCT technologies often fail to fully utilize multi-source information fusion and advanced data analysis methods to optimize detection performance.

[0004] Therefore, it is necessary to provide a new method to improve the real-time, accuracy and overall performance of POCT detection. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide an intelligent POCT detection method and system based on 5G and microfluidic technology.

[0006] To achieve the above objectives, the present invention adopts the following technical solutions: an intelligent POCT detection method based on 5G and microfluidics technology, comprising:

[0007] Microfluidics technology combined with integrated sensors is used to obtain initial data of samples collected in real time;

[0008] Preprocessing the initial data, and converting the preprocessed data to obtain converted data;

[0009] constructing a mathematical model between sample characteristic changes and target analyte concentrations based on the converted data;

[0010] Analyze the frequency domain corresponding to the time series signal of the initial data, and determine the high-frequency components and low-frequency components in the frequency domain in combination with a set threshold;

[0011] Utilizing the mathematical model to calculate changes in sample characteristics based on the high-frequency components and the low-frequency components, and inferring abnormal conditions or pathogen types present in the sample to obtain inference results;

[0012] The inference result is sent using 5G technology.

[0013] The further technical solution is: the use of microfluidic technology combined with integrated sensors to obtain the initial data of samples collected in real time includes:

[0014] The sample is introduced into a microfluidic system, and relevant data is collected in real time using an integrated sensor to obtain initial data;

[0015] The initial data includes the concentration information of the target substance, the flow rate of the sample liquid, and the equipment operating environment parameters.

[0016] A further technical solution is: preprocessing the initial data and converting the preprocessed data to obtain converted data, including:

[0017] Preprocessing the concentration information of the target substance and the flow rate of the sample liquid according to the equipment environment operating parameters to obtain preprocessed data;

[0018] The time domain signal corresponding to the preprocessed data is converted into a frequency domain signal using a Fourier transform algorithm to obtain the converted data.

[0019] A further technical solution is: analyzing the frequency domain corresponding to the time series signal of the initial data, and determining the high-frequency component and the low-frequency component in the frequency domain in combination with a set threshold, including:

[0020] Identify high-frequency components and low-frequency components according to the frequency domain data and the initial data in combination with a set threshold, and determine weight coefficients corresponding to the high-frequency components and the low-frequency components;

[0021] The step of identifying high-frequency components and low-frequency components according to the frequency domain data and the initial data in combination with a set threshold, and determining weight coefficients corresponding to the high-frequency components and the low-frequency components, includes:

[0022] Perform spectrum analysis on the frequency domain data, identify high-frequency components and low-frequency components based on sample feature changes, target analyte concentrations, and set thresholds;

[0023] The proportions of the high-frequency component and the low-frequency component in the total are calculated to obtain the weight coefficients corresponding to the high-frequency component and the low-frequency component.

[0024] A further technical solution is: using the mathematical model to calculate the change of sample characteristics according to the high-frequency components and the low-frequency components, and inferring the abnormal conditions or pathogen types present in the sample to obtain an inference result, including:

[0025] Calculate sample fluctuations based on the frequency data corresponding to the high-frequency components and the low-frequency components;

[0026] Calculate the comprehensive sample irregularity according to the sample fluctuation and the weight coefficients corresponding to the high-frequency component and the low-frequency component to obtain the sample irregularity;

[0027] The abnormal conditions or pathogen types encountered by the sample are identified based on the sample fluctuations and the irregularity of the sample, and the specific features are classified into specific pathological states to obtain inference results.

[0028] A further technical solution is: identifying the abnormality or pathogen type encountered by the sample according to the sample fluctuation and the irregularity of the sample, and classifying the specific features into a specific pathological state to obtain an inference result, including:

[0029] Obtain data of standard samples under the same conditions as the current samples but without the influence of the test substance as a reference;

[0030] Calculate the specific change value between the preprocessed data and the standard sample data to obtain a change vector;

[0031] The change vector, the sample fluctuation, and the sample irregularity quantification are input into an analysis model to determine the abnormality or pathogen type encountered by the sample and classify the specific features into a specific pathological state.

[0032] Its further technical solution is: the mathematical model is C(t)=f(S(t),P(t))+b·V(t)+c· Wherein, C(t) represents the concentration of the target substance, S(t) is the transmission speed of the sample, P(t) is the equipment pressure, V(t) is the liquid flow rate, b and c are influence coefficients, which are used to quantify the influence of the flow rate and its rate of change on the concentration change; f(S(t), P(t)) in the mathematical model represents the influence of the sample transmission speed and the equipment pressure on the concentration of the target substance.

[0033] The present invention also provides an intelligent POCT detection system based on 5G and microfluidic technology, including:

[0034] An initial data acquisition unit, used to acquire initial data of samples collected in real time by using microfluidics technology combined with integrated sensors;

[0035] A preprocessing unit, used for preprocessing the initial data and converting the preprocessed data to obtain converted data;

[0036] A mathematical model building unit, used to build a mathematical model between sample characteristic changes and target analyte concentrations based on the converted data;

[0037] An analysis unit, used for analyzing the frequency domain corresponding to the time series signal of the initial data, and determining the high-frequency component and the low-frequency component in the frequency domain in combination with a set threshold;

[0038] An inference unit, used to calculate the change of sample characteristics according to the high-frequency components and the low-frequency components using the mathematical model, and to infer the abnormality or pathogen type present in the sample to obtain an inference result;

[0039] A sending unit is used to send the inference result using 5G technology.

[0040] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0041] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0042] The beneficial effects of the present invention compared with the prior art are: the present invention collects sample data in real time through microfluidic technology and integrated sensors, thereby improving the real-time and automation of the detection process. The initial data is preprocessed and converted to ensure data quality and consistency, providing an accurate basis for subsequent analysis. By establishing a mathematical model, the changes in sample characteristics are associated with the concentration of the target analyte, thereby improving the accuracy and reliability of the test results. The time series signal is analyzed in the frequency domain, and the changes in the sample are identified by combining the high and low frequency components, thereby effectively discovering potential anomalies or pathogens. Combined with 5G technology to achieve fast data transmission and real-time inference, the test results can be transmitted to relevant personnel in a timely manner, enhancing the overall detection performance and response speed.

[0043] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0045] Figure 1 A schematic diagram of a process of an intelligent POCT detection method based on 5G and microfluidics technology provided in an embodiment of the present invention;

[0046] Figure 2 A schematic block diagram of an intelligent POCT detection system based on 5G and microfluidic technology provided in an embodiment of the present invention;

[0047] Figure 3 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] See also Figure 1 , Figure 1A schematic flow chart of an intelligent POCT detection method based on 5G and microfluidic technology provided in an embodiment of the present invention. The intelligent POCT detection method based on 5G and microfluidic technology is applied to a server. The server interacts with the microfluidic system and the display terminal for data. The method of this embodiment is mainly to solve the limitations of traditional POCT equipment in sample processing speed, data transmission efficiency and result accuracy. By combining microfluidic technology and 5G communication technology, it aims to achieve faster detection speed, higher data transmission rate, more accurate results, and more efficient multi-source information fusion and advanced data analysis capabilities; specifically, by manipulating trace amounts of liquid using a microfluidic chip, rapid mixing, separation, reaction and other operations of the sample can be achieved, greatly improving the speed and efficiency of sample processing while reducing the required sample volume. Integrated sensors are used to monitor sample changes in real time and obtain initial data. These sensors can be electrochemical, optical or other types of sensors that can provide information about changes in sample characteristics. The collected initial data is cleaned and formatted as necessary and converted into a form suitable for further analysis. A relationship between changes in sample characteristics and target analyte concentrations is established so that information about pathogen types or abnormal conditions can be inferred from the data. Convert time series signals to the frequency domain to identify different components (such as high-frequency and low-frequency components) to better understand the changing patterns of sample characteristics over time. 5G technology ensures high-speed data transmission, making telemedicine and immediate response possible, greatly improving the application scenarios and practicality of POCT; it is particularly suitable for scenarios where quick judgment results are required, such as emergency rooms, ambulances, medical institutions in remote areas, and on-site quarantine points. In addition, it is also suitable for situations where remote monitoring of patient health is required.

[0053] Figure 1 Schematic diagram of the process of the intelligent POCT detection method based on 5G and microfluidics technology provided by the embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110 to S160.

[0054] S110, using microfluidic technology combined with integrated sensors to obtain initial data of samples collected in real time.

[0055] In this embodiment, the sample is introduced into a microfluidic system, and an integrated sensor is used to collect relevant data in real time to obtain initial data; wherein the initial data includes concentration information of the target substance, sample liquid flow rate, and equipment operating environment parameters.

[0056] In this embodiment, microfluidics uses a micrometer-level channel network to control the flow of liquids, can accurately manipulate extremely small amounts of liquids, and can integrate multiple functions on a chip, such as mixing, separation, reaction, etc. This not only reduces the consumption of samples and reagents, but also improves the degree of automation of experiments.

[0057] Integrated sensors refer to the combination of multiple sensing elements to monitor multiple physical or chemical parameters simultaneously. For example, in this embodiment, it can obtain the concentration information of the target substance, the flow rate of the sample liquid, and the parameters of the device operating environment in real time. These data are crucial for subsequent data analysis.

[0058] Specifically, the sample to be tested is added to a specially designed microfluidic chip. The channels inside the microfluidic system guide the flow of the sample. At the same time, the integrated sensor begins to collect various relevant information in real time, including but not limited to the concentration information of the target substance, the flow rate of the sample liquid, and the equipment operating environment parameters; wherein the target substance refers to the specific component that needs to be detected or analyzed, which can be a certain chemical substance, biological molecule (such as DNA, protein), cell or other specific particles. Concentration information refers to the content level of these target substances in the sample, usually expressed in mass per unit volume (such as mg / L) or molar number (such as μM); equipment operating environment parameters include but are not limited to factors such as temperature, humidity, pressure, etc. that may affect the experimental results. In some cases, other factors such as pH value and light intensity may also be involved.

[0059] The small size of the microfluidic chip allows the POCT device to be smaller and lighter as a whole, making it easier to carry and operate, and is particularly suitable for on-site testing in remote areas or emergency situations. Various types of sensors are installed at key nodes, such as biosensors at the entrance, pressure sensors at the exit, and temperature sensors around the entire channel; multiple functional modules are integrated on one platform, reducing external connection components and enhancing the stability and reliability of the system.

[0060] S120: preprocessing the initial data, and converting the preprocessed data to obtain converted data.

[0061] In one embodiment, the above-mentioned step S120 may include steps S121 - S122 .

[0062] S121 . Preprocess the concentration information of the target substance and the flow rate of the sample liquid according to the equipment environment operating parameters to obtain preprocessed data.

[0063] In this embodiment, this stage mainly solves the problem of data deviation caused by changes in the operating environment of the device (such as temperature, humidity, pressure, etc.). By adjusting these parameters, the target substance concentration and flow rate under actual conditions can be more accurately reflected. Specifically, the operating environment parameters of the device (such as temperature, humidity, pressure) are analyzed, and the target substance concentration information and the sample liquid flow rate are adjusted accordingly to eliminate the influence of environmental factors on the measurement results.

[0064] Effective data preprocessing using equipment operating environment parameters is a key step to ensure the accuracy of measurement results and the stability of system behavior characteristics. In this embodiment, for temperature-sensitive sensors (such as enzyme activity detection), calibration curves or lookup tables at different temperatures are established. In the preprocessing stage, the sensor readings are adjusted according to the current temperature to compensate for the effects of temperature changes. For pH-sensitive chemical reactions, the variation of sensor responses under different pH conditions is determined experimentally, and then the corresponding correction strategy is formulated.

[0065] If there are substances in the environment that may interfere with sensor readings (such as dissolved gases, suspended particles, etc.), physical or chemical methods can be used to remove these impurities, or special algorithms can be developed to identify and eliminate their effects. For electromagnetic interference problems, hardware shielding measures are taken and combined with software algorithms to suppress noise, such as using filters to reduce high-frequency interference signals.

[0066] Considering the influence of temperature and pressure on liquid viscosity, an appropriate correction factor is introduced when calculating the flow rate of the sample liquid to ensure that the flow rate measurement reflects the actual situation. Among them, the correction factor can be formulated by self-learning historical data; when the actual environmental conditions deviate from the design standards of the flow meter, the flow meter is recalibrated according to the new environmental parameters to ensure that its accuracy is not affected.

[0067] S122. Use a Fourier transform algorithm to convert the time domain signal corresponding to the preprocessed data into a frequency domain signal to obtain converted data.

[0068] In this embodiment, the Fourier transform algorithm is applied to convert the preprocessed time domain signal (i.e., data that changes with time) into a frequency domain signal. This step can help identify time-independent characteristics hidden in the original data, such as frequency components, thereby enhancing the ability of data analysis.

[0069] This step, through the preprocessing step, reduces the impact of external environmental changes on the measurement results and improves the quality and credibility of the data. Using Fourier transform, we can examine the data from a new perspective and discover features that are not easily perceived in the time domain, thereby supporting more accurate analysis.

[0070] S130, constructing a mathematical model between sample characteristic changes and target analyte concentrations according to the converted data.

[0071] In this embodiment, the mathematical model is Wherein, C(t) represents the concentration of the target substance, S(t) is the transmission speed of the sample, P(t) is the equipment pressure, V(t) is the liquid flow rate, b and c are influence coefficients, which are used to quantify the influence of the flow rate and its rate of change on the concentration change; f(S(t), P(t)) in the mathematical model represents the influence of the sample transmission speed and the equipment pressure on the concentration of the target substance.

[0072] In this embodiment, the sample transmission speed S(t) and the device pressure P(t) are the main influencing factors, while the liquid flow velocity V(t) and its change rate are taken into consideration. It will also affect the concentration. Therefore, it can be assumed that there is a function f(S(t), P(t)() to describe the effect of transport speed and pressure on concentration, and the other two coefficients b and c quantify the influence of flow velocity and its rate of change on concentration change.

[0073] Determining the influence coefficients b and c in a mathematical model usually involves multiple steps, including experimental design, data collection, selection of parameter estimation methods, and model validation. The following is a detailed process:

[0074] In order to accurately capture the liquid flow velocity V(t) and its rate of change The effect on the concentration of the target substance C(t) requires a series of carefully designed experimental conditions to ensure that all possible combinations of variables are covered. For example, the sample transfer speed S(t) and the equipment pressure P(t) can be changed, and the liquid flow rate and its changes under different conditions can be recorded at the same time.

[0075] Under each set condition, high-precision sensors are used to monitor and record in real time the concentration of the target substance C(t), sample transfer speed S(t), equipment pressure P(t), liquid flow rate V(t) and the rate of change of flow rate And other key parameters.

[0076] Based on the obtained data set, appropriate statistical or machine learning methods are used to estimate the unknown parameters b and c in the model. Commonly used methods include but are not limited to the following:

[0077] If we assume that b and c are linearly related, we can directly apply the least squares method or other forms of linear regression algorithms to solve for these two parameters by fitting the known data points.

[0078] When there is a complex (such as nonlinear) relationship between b and c, you can consider using nonlinear optimization techniques such as gradient descent and genetic algorithms to find the optimal solution.

[0079] For more complex systems, parameter estimation can also be performed with the help of advanced machine learning models such as neural networks and support vector machines. These models can automatically learn the mapping relationship between input features and outputs during training, and adjust internal parameters accordingly to minimize prediction errors.

[0080] The collected data is divided into a training set and a test set. After training the model with the training set and calculating the values ​​of b and c, the performance of the model is evaluated on the test set to ensure that it has good generalization ability.

[0081] Check the sensitivity of the model to parameters b and c, that is, whether small changes in the values ​​of these parameters will lead to significantly different output results. This helps to understand the stability and reliability of the model.

[0082] Based on the results of the above verification process, appropriate adjustments should be made to the original assumptions or model structure if necessary until the parameter configuration that best reflects the actual situation is found.

[0083] Once the best estimates of b and c are determined, they can be applied to real-time data analysis to help infer changes in sample characteristics and identify potential abnormal conditions or pathogen types. As more new data accumulates, parameters b and c are regularly re-evaluated and updated to ensure that the model is always in the best state and adapts to changing practical application scenarios.

[0084] In addition, for f(S(t), P(t)), we first define the range of variation of S(t) and P(t), which should cover all situations that may be encountered in actual operations.

[0085] Using statistical experimental design methods, such as full factorial design, fractional factorial design or response surface methodology, a series of experimental condition combinations are planned to systematically explore the effects of S(t) and P(t) on C(t).

[0086] In each experiment, try to keep other conditions except S(t) and P(t) consistent, such as environmental factors such as temperature and humidity, and liquid flow rate V(t), to reduce the impact of external interference on the results.

[0087] Use accurate sensors to record the values ​​of C(t), S(t) and P(t) in real time to ensure the quality and accuracy of the data. Repeat each experimental condition at least three times to calculate the average value and standard deviation to improve data reliability.

[0088] Based on theoretical knowledge and the results of preliminary data analysis, choose an appropriate mathematical expression to represent f(S(t), P(t)). For example, if it is believed that there is a linear relationship between the two, it can be assumed that f(S(t), P(t)) = a 1 S(t)+a 2 P(t); if it is a nonlinear relationship, f(S(t), P(t)) is determined by fitting. The parameters of the selected model are estimated based on the experimental data set using methods such as least squares, maximum likelihood estimation or machine learning algorithms to obtain a specific a 1 and a 2 value.

[0089] Use part of the data as a training set for model training and the other part as a validation set to evaluate model performance. Use techniques such as cross-validation to check the fit between the model predictions and actual observations. Use new data sets independent of the modeling process to further test the generalization ability and stability of the model.

[0090] Analyze the sensitivity of the model to different input parameters and identify which parameters have a greater impact on the output, thereby guiding the focus of subsequent research. Perform statistical tests on key assumptions in the model, such as linear assumptions, additive effects, etc., and consider introducing interaction terms or other advanced features when necessary. Based on the problems found during the verification process, continuously adjust the model structure and parameters until you find the form that best reflects the actual situation.

[0091] Once the model has been fully validated and deemed reliable, it can be applied to actual production and monitoring environments. As more new data accumulates, the performance of the model is regularly re-evaluated and parameter configurations are updated in a timely manner to ensure its long-term effectiveness.

[0092] S140, analyzing the frequency domain corresponding to the time series signal of the initial data, and determining the high-frequency components and low-frequency components in the frequency domain in combination with a set threshold.

[0093] In this embodiment, the high-frequency component and the low-frequency component are identified according to the frequency domain data and the initial data in combination with a set threshold, and the weight coefficients corresponding to the high-frequency component and the low-frequency component are determined.

[0094] In this embodiment, high-frequency components refer to components with higher frequencies, which usually correspond to parts of the data that change or oscillate rapidly. In the intelligent POCT detection method, high-frequency components may represent instantaneous fluctuations, short-term changes, or rapid reaction events in the sample, such as instantaneous concentration changes caused by biochemical reactions, turbulence effects in sample flow, or other forms of rapid disturbances. For medical diagnosis, high-frequency components can provide information about the presence or absence of pathogens and their activity, or reveal the presence of certain acute pathological states.

[0095] Low-frequency components refer to components with lower frequencies, which usually correspond to slower changes or stable states in the data. In the intelligent POCT detection method, low-frequency components may reflect the long-term trend, gradual changes or stable baseline levels of sample characteristics, such as the continuous increase or decrease in the concentration of the target analyte, the gradual change in the sample flow rate, etc. Low-frequency components help to understand the overall behavior and background information of the sample, can be used to evaluate the development process of chronic diseases or monitor the effect of treatment, and can serve as one of the foundations for establishing mathematical models.

[0096] By identifying and distinguishing high-frequency and low-frequency components, this method can more carefully analyze the changes in sample characteristics and the biological mechanisms behind them. For example, after the initial data is preprocessed and converted into frequency domain signals, the set threshold is combined to determine which are high-frequency components and which are low-frequency components. Then, the constructed mathematical model is used to calculate the changes in sample characteristics based on these components, thereby inferring the abnormalities or pathogen types present in the sample.

[0097] In short, the high-frequency components and low-frequency components each carry information about different aspects of the sample, working together to achieve more accurate diagnostic results. This method not only improves the detection accuracy, but also enhances the system's anti-interference ability and adaptability, providing strong support for instant detection.

[0098] In one embodiment, the above-mentioned step S140 may include steps S141 - S142 .

[0099] S141. Perform spectrum analysis on the frequency domain data, and identify high-frequency components and low-frequency components based on sample feature changes, target analyte concentration, and a set threshold.

[0100] In this embodiment, a spectrum graph is generated based on the data in the frequency domain to show the amplitude at different frequencies. Characteristic frequency components related to the target analyte are identified from the spectrum graph. For example, peaks of certain specific frequencies may correspond to vibration modes or reaction rates that are unique to the target substance. The spectrum differences between known samples (positive control, negative control) and unknown samples are compared to determine which frequency component changes are associated with the concentration of the target analyte. If the sample characteristics change over time, such as due to reaction progress or environmental factors, the spectrum analysis model needs to be dynamically updated to adapt to these changes.

[0101] Based on laboratory validation experiments or historical data, one or more thresholds are set for each characteristic frequency to distinguish between fluctuations within the normal range and abnormal conditions. When a frequency component exceeds the preset threshold, an alarm is triggered or the presence of a specific concentration of the target analyte is confirmed.

[0102] According to the results of spectrum analysis, the frequency components are divided into high-frequency parts (usually related to fast-changing processes) and low-frequency parts (more inclined to reflect slow-changing processes). The importance of these two types of information may vary for different application scenarios.

[0103] S142, calculating the proportions of the high-frequency component and the low-frequency component in the total respectively, to obtain the weight coefficient corresponding to the high-frequency component and the weight coefficient corresponding to the low-frequency component.

[0104] In order to quantify the importance of high-frequency components and low-frequency components, the proportion of each in the entire signal is calculated. These proportions are used as weight coefficients (w 1 , w 2 ), which is used to indicate the degree to which high-frequency and low-frequency components contribute to the total signal. The weight coefficient can help understand the impact of different frequency components on the overall signal, thereby better explaining and predicting the relationship between sample feature changes and target analyte concentrations.

[0105] By distinguishing and weighting high-frequency and low-frequency components, the subtle relationship between changes in sample characteristics and the concentration of target analytes can be captured more accurately, thereby improving the accuracy of diagnostic results. In practical applications, external factors such as temperature fluctuations and equipment noise may introduce additional frequency components. By reasonably setting thresholds and accurately identifying high-frequency and low-frequency components, these interferences can be effectively filtered out to ensure the stability of the detection system. After understanding the respective roles of high-frequency and low-frequency components, the detection strategy can be adjusted according to the specific situation, such as increasing attention to specific frequency ranges, or reducing unnecessary monitoring items, so as to save energy and time. According to the characteristics and weights of high-frequency and low-frequency components, a more reliable basis can be provided for inferring abnormal conditions or pathogen types in samples, which will help achieve early warning and precision medicine.

[0106] S150, using the mathematical model to calculate changes in sample characteristics according to the high-frequency components and the low-frequency components, and inferring abnormal conditions or pathogen types present in the sample to obtain inference results.

[0107] In this embodiment, the inference result refers to whether there is any abnormality in the sample, and if there is an abnormality, the possible pathogen type will also be given.

[0108] In one embodiment, the above-mentioned step S150 may include steps S151 - S153 .

[0109] S151. Calculate sample fluctuations based on frequency data corresponding to high-frequency components and low-frequency components.

[0110] In this embodiment, the sample fluctuation includes information brought about by changes in high-frequency component and low-frequency component signals.

[0111] In this step, we mainly focus on the information brought by the signal changes in different frequency ranges in the sample:

[0112] High-frequency components: This part reflects the rapidly changing characteristics in the sample, which is usually associated with acute infection or rapidly multiplying pathogens. For example, in a POCT testing environment, this can be a sudden increase in the number of viral particles or a sharp change in bacterial metabolic activity. In order to quantify these rapidly changing characteristics, the root mean square (RMS) corresponding to the high-frequency component is calculated. The root mean square value is a statistical measure that effectively represents the average level of signal strength or amplitude. By calculating the RMS of the high-frequency component, the presence and intensity of acute or sudden events in the sample can be assessed.

[0113] Low-frequency components: In contrast, low-frequency components tend to reflect chronic changes or long-term effects in the sample, such as chronic inflammation or persistent pathogen infection. In order to capture the trend of such long-term changes, we calculate the cumulative value of the low-frequency component. The cumulative value can be obtained by accumulating all measurement points in a specific time period to depict the overall trend or state change of the sample over time.

[0114] S152. Calculate the comprehensive sample irregularity according to the sample fluctuation and the weight coefficients corresponding to the high-frequency component and the low-frequency component to obtain the sample irregularity.

[0115] In this embodiment, the comprehensive sample irregularity refers to an indicator generated by integrating the information of high-frequency and low-frequency components to reflect the overall health status or pathological status of the sample.

[0116] Specifically, a weighted summation method is used, in which different weights are assigned to features in each frequency range. These weights are selected based on their importance for diagnosis and how they best reflect the behavior patterns of potential pathogens. For example, if the acute stage of a certain type of pathogen is particularly critical for its diagnosis, high-frequency components will be given higher weights; conversely, if it is a chronic disease, the weight of low-frequency components will be greater. The final comprehensive sample irregularity is a numerical indicator used to determine whether the sample deviates from the normal healthy state.

[0117] S153. Identify the abnormal conditions or pathogen types encountered by the sample based on the sample fluctuations and the irregularity of the sample, and classify the specific features into specific pathological states to obtain inference results.

[0118] In one embodiment, the above-mentioned step S153 may include steps S1531 - S1533 .

[0119] S1531. Obtain standard sample data under the same conditions as the current sample but not affected by the test substance as a reference.

[0120] In this embodiment, a set of standard sample data under the same conditions as the current sample to be tested is obtained, and these data should not be affected by any test substance to ensure that they represent a "normal" state. For example, in medical testing, blood, urine or other body fluid samples from healthy individuals are selected as references. The selection of standard samples should match the environmental conditions (such as temperature, humidity, collection time, etc.) of the sample to be tested as much as possible to reduce the impact of external variables on the results. These standard samples will be used as the basis for subsequent comparisons.

[0121] S1532. Calculate specific change values ​​between the preprocessed data and the standard sample data to obtain a change vector.

[0122] In this embodiment, the pre-processed sample data to be tested and the standard sample data are obtained, and the next step is to calculate the difference between the two, that is, the change value. Specifically, for each feature dimension i, the sample feature value X is calculated. test (i) and the corresponding standard sample eigenvalue X reference (i) The difference between i =X test (i)-X reference (i) , thus forming a change vector ΔX containing all feature differences. This change vector directly reflects the degree of deviation of the sample to be tested relative to the standard sample, providing an important quantitative basis for subsequent analysis.

[0123] S1533. Quantify the change vector, the sample fluctuation, and the sample irregularity into an analysis model to determine the abnormality or pathogen type encountered by the sample and classify the specific features into a specific pathological state.

[0124] The previously obtained change vector and sample fluctuation σ test , and the irregularity quantification index Complexity are integrated into a feature vector F input =(ΔX,σ test, Complexity), and input it into a pre-trained analysis model. The task of the model is to evaluate the input feature vector to determine whether there is an abnormal condition or a specific type of pathogen infection, and to classify the specific features into known pathological states. Specifically, if a sample is detected as abnormal, the model will classify the sample into different pathogen types (such as bacteria, viruses, fungi, etc.) or specific pathological states (such as acute diseases, chronic diseases, etc.) based on feature matching; it can also be based on the output of the model, combined with known pathological states, to infer the possible abnormal types or pathogens that may appear in the sample to be tested. For example, if the difference value is large and the fluctuation frequency is abnormally high, it may indicate a viral infection; if the feature value changes greatly and there is no obvious periodicity, it may be a manifestation of an acute disease.

[0125] For the analysis model, it is trained in the following way:

[0126] First, a large number of labeled data sets need to be collected. These data should include samples of various known pathological states or pathogen types. Each sample must undergo detailed feature extraction and preprocessing to ensure that it meets the requirements of the model input. In addition, the true label of each sample (that is, the actual category to which it belongs) needs to be recorded for supervised learning.

[0127] Before actual training, the feature vectors need to be further optimized. This may involve feature selection (selecting features that best distinguish different classes), feature combination (creating new features to enhance the performance of the model), or applying dimensionality reduction techniques (such as principal component analysis PCA) to simplify the problem space without losing important information.

[0128] Depending on the nature of the problem and the type of data available, you can choose a suitable machine learning algorithm or deep learning architecture. Common choices include but are not limited to support vector machines (SVM), random forests (RF), K nearest neighbors (KNN), neural networks (NN), and deep learning models such as convolutional neural networks (CNN) or recurrent neural networks (RNN). Each model has its own unique advantages and disadvantages and is suitable for different types of data and tasks.

[0129] The selected model is trained using a labeled dataset. During this process, the model continuously adjusts its internal parameters to minimize the error between the predicted output and the true label. Cross-validation is often used to evaluate model performance and prevent overfitting. After training, the model should be able to make accurate predictions on new data that it has not seen.

[0130] After training, use an independent test set to perform a final evaluation of the model to check its generalization ability. If you find that the model performs poorly, you can return to the previous steps to make adjustments, such as changing the model structure, adding more data, or improving feature engineering. Until you get satisfactory performance.

[0131] In this embodiment, the inference result includes not only whether the sample is abnormal, possible pathogen type or pathological state (such as "suspected viral infection", "bacterial infection", "no abnormality", etc.), but also clinical suggestions, such as: if pathogens or abnormalities are detected, further examinations (such as PCR testing, blood culture, etc.) are recommended. If no abnormalities are detected, continue to observe or conduct regular health checks.

[0132] By analyzing both high-frequency and low-frequency components simultaneously, the system can not only capture acute events (such as sudden outbreaks of infection), but also detect chronic changes (such as chronic inflammation or infection). Such multi-dimensional analysis improves the accuracy and reliability of detection. Sensitive monitoring of high-frequency components enables the system to capture changes in signals in the early stages of the disease, thereby achieving early warning, which is critical for rapid response to acute diseases. Taking into account each individual's historical health records and personal differences, this approach provides each patient with a personalized health management plan rather than a one-size-fits-all approach.

[0133] Optimize resource allocation: Predicting the development of a disease in advance can help medical institutions better plan resources, arrange inspections, treatments and other activities reasonably, and improve the efficiency of medical services. By comparing standard sample data, abnormalities in actual samples can be more clearly identified, increasing the credibility of diagnosis and helping to eliminate the possibility of misdiagnosis. The entire process is highly dependent on data analysis and mathematical models, which reduces the need for human intervention, improves the speed and consistency of diagnosis, and also reduces costs.

[0134] In addition, it is also possible to extract features from the preprocessed data; retrieve the historical data of the sample, and extract the sample fluctuations, sample irregularities and features corresponding to the historical data to obtain historical information; input the historical information and the features, the sample fluctuations and the sample irregularities into a development trend prediction model to perform development trend prediction to obtain a prediction result; match the prediction result with a known pathological state model stored in a database to obtain a corresponding specific pathological state to form an inference result.

[0135] Specifically, when analyzing the preprocessed data, it is first necessary to extract meaningful features from the data. These features can be statistics calculated directly from the original data (such as mean, variance), or new features obtained through complex algorithm transformation (such as obtaining frequency domain features through Fourier transform, or using wavelet transform to capture multi-scale characteristics). The goal of feature extraction is to convert the original data into a set of numerical values ​​or vectors that can best describe the properties of the sample so that it can be analyzed more effectively in subsequent steps. Next, the system will call up the historical data of the current sample. The importance of this step is that it allows us to understand the currently observed data in the context of a time series, rather than just looking at a single measurement result in isolation. By analyzing historical data, we can extract the trends and patterns of the sample over time, such as its fluctuations (i.e. the magnitude of the data changes) and irregularity (a measure of the randomness and complexity of the data distribution). This long-term perspective helps to identify subtle changes or trends that may be overlooked by a single measurement. Once you have the characteristics of the current sample and its historical information, the next step is to input all this information into a specially designed development trend prediction model. The task of this model is to make predictions about future data points, that is, to estimate what might happen in the future if the current trend continues. To achieve this, the prediction model is usually built based on machine learning or deep learning technology, and is trained on a large amount of similar data to learn the development laws of different types of samples. The input to the model includes not only the latest features and current fluctuations, irregularities and other information, but also the historical information mentioned earlier to ensure that the prediction is as accurate as possible. Finally, based on the results output by the prediction model, the system searches the database for the closest known pathological state model. This is a matching process, the purpose of which is to find the pathological pattern that is most similar to the predicted result, so as to infer the specific pathological state corresponding to the current sample. The key to this step is to have a comprehensive and accurately annotated pathological state database, which contains typical data manifestations under various disease states. When the best match is found, the system will form an inference result to tell the user which pathological state the current sample is most likely to belong to, and provide corresponding explanations and supporting information.

[0136] By combining real-time data with historical data for comprehensive analysis, early signs or changing trends of diseases can be captured more accurately, helping doctors make more accurate diagnoses. Using development trend prediction models, potential health risks can be warned before symptoms become apparent, making preventive treatment possible. Taking into account each individual's historical health records, this approach can provide each patient with a personalized health management plan instead of a one-size-fits-all approach.

[0137] S160. Send the inference result using 5G technology.

[0138] In this embodiment, using 5G technology to send inference results can greatly improve the efficiency, response speed and accessibility of medical services. 5G network, with its high bandwidth, low latency and large number of connections, is very suitable for real-time transmission of large amounts of data, including but not limited to high-definition medical images, video streams and complex analysis results. Before transmission, the inference results need to be encrypted before being transmitted to the display terminal.

[0139] The above-mentioned intelligent POCT detection method based on 5G and microfluidic technology collects sample data in real time through microfluidic technology and integrated sensors, which improves the real-time and automation of the detection process. The initial data is preprocessed and converted to ensure data quality and consistency, providing an accurate basis for subsequent analysis. By establishing a mathematical model, the changes in sample characteristics are associated with the concentration of the target analyte, which improves the accuracy and reliability of the test results. The time series signal is analyzed in the frequency domain, and the changes in the sample are identified by combining high and low frequency components, so as to effectively detect potential abnormalities or pathogens. Combined with 5G technology to achieve fast data transmission and real-time inference, the test results can be transmitted to relevant personnel in a timely manner, enhancing the overall detection performance and response speed.

[0140] Figure 2 FIG. 3 is a schematic block diagram of an intelligent POCT detection system 300 based on 5G and microfluidics technology provided by an embodiment of the present invention. Figure 2 As shown, corresponding to the above intelligent POCT detection method based on 5G and microfluidic technology, the present invention also provides an intelligent POCT detection system 300 based on 5G and microfluidic technology. The intelligent POCT detection system 300 based on 5G and microfluidic technology includes a unit for executing the above intelligent POCT detection method based on 5G and microfluidic technology, and the system can be configured in a server. Specifically, please refer to Figure 2 The intelligent POCT detection system 300 based on 5G and microfluidic technology includes an initial data acquisition unit 301, a preprocessing unit 302, a mathematical model construction unit 303, an analysis unit 304, an inference unit 305 and a sending unit 306.

[0141] The initial data acquisition unit 301 is used to adopt microfluidic technology combined with integrated sensors to obtain the initial data of the sample collected in real time; the preprocessing unit 302 is used to preprocess the initial data and convert the preprocessed data to obtain the converted data; the mathematical model construction unit 303 is used to construct a mathematical model between the sample characteristic change and the target analyte concentration according to the converted data; the analysis unit 304 is used to analyze the frequency domain corresponding to the time series signal of the initial data, and determine the high-frequency component and the low-frequency component in the frequency domain in combination with the set threshold; the inference unit 305 is used to use the mathematical model to calculate the change of the sample characteristic according to the high-frequency component and the low-frequency component, and infer the abnormality or pathogen type existing in the sample to obtain the inference result; the sending unit 306 is used to send the inference result using 5G technology.

[0142] In one embodiment, the initial data acquisition unit 301 is used to:

[0143] The sample is introduced into a microfluidic system, and an integrated sensor is used to collect relevant data in real time to obtain initial data; wherein the initial data includes concentration information of the target substance, sample liquid flow rate, and equipment operating environment parameters.

[0144] In one embodiment, the pre-processing unit 302 is used to:

[0145] The concentration information of the target substance and the flow velocity of the sample liquid are preprocessed according to the equipment environment operating parameters to obtain preprocessed data; and the time domain signal corresponding to the preprocessed data is converted into a frequency domain signal using a Fourier transform algorithm to obtain converted data.

[0146] In one embodiment, the analysis unit 304 is used to:

[0147] According to the frequency domain data and the initial data combined with the set threshold, the high-frequency component and the low-frequency component are identified, and the weight coefficients corresponding to the high-frequency component and the low-frequency component are determined; the high-frequency component and the low-frequency component are identified according to the frequency domain data and the initial data combined with the set threshold, and the weight coefficients corresponding to the high-frequency component and the low-frequency component are determined, including: performing spectral analysis on the frequency domain data, combining sample characteristic changes, target analyte concentration and the set threshold, identifying the high-frequency component and the low-frequency component; calculating the proportion of the high-frequency component and the low-frequency component in the total, respectively, to obtain the weight coefficient corresponding to the high-frequency component and the weight coefficient corresponding to the low component.

[0148] In one embodiment, the inference unit 305 is used to calculate the sample fluctuation according to the frequency data corresponding to the high-frequency component and the low-frequency component; calculate the comprehensive sample irregularity according to the sample fluctuation combined with the weight coefficients corresponding to the high-frequency component and the low-frequency component to obtain the sample irregularity; identify the abnormal condition or pathogen type encountered by the sample according to the sample fluctuation and the sample irregularity, and classify the specific characteristics into a specific pathological state to obtain an inference result.

[0149] In one embodiment, the inference unit 305 is further configured to:

[0150] Obtain standard sample data under the same conditions as the current sample but not affected by the test substance as a reference; calculate specific change values ​​between the preprocessed data and the standard sample data to obtain a change vector; input the change vector, the sample fluctuation and the sample irregularity into the analysis model to determine the abnormal situation or pathogen type encountered by the sample, and classify the specific characteristics into a specific pathological state.

[0151] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned intelligent POCT detection system 300 based on 5G and microfluidic technology and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0152] The above-mentioned intelligent POCT detection system 300 based on 5G and microfluidics technology can be implemented in the form of a computer program, which can be used in Figure 3 Runs on the computer device shown.

[0153] See also Figure 3 , Figure 3 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0154] See also Figure 3 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0155] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, which, when executed, can enable the processor 502 to execute an intelligent POCT detection method based on 5G and microfluidics technology.

[0156] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0157] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an intelligent POCT detection method based on 5G and microfluidic technology.

[0158] The network interface 505 is used to communicate with other devices over the network. Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps:

[0160] Microfluidic technology is used in combination with integrated sensors to obtain initial data of samples collected in real time; the initial data is preprocessed, and the preprocessed data is converted to obtain converted data; a mathematical model between sample characteristic changes and target analyte concentrations is constructed based on the converted data; the frequency domain corresponding to the time series signal of the initial data is analyzed, and the high-frequency components and low-frequency components in the frequency domain are determined in combination with a set threshold; the mathematical model is used to calculate changes in sample characteristics based on the high-frequency components and low-frequency components, and to infer abnormal conditions or pathogen types present in the sample to obtain inference results; and the inference results are sent using 5G technology.

[0161] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0162] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0163] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps:

[0164] Microfluidic technology is used in combination with integrated sensors to obtain initial data of samples collected in real time; the initial data is preprocessed, and the preprocessed data is converted to obtain converted data; a mathematical model between sample characteristic changes and target analyte concentrations is constructed based on the converted data; the frequency domain corresponding to the time series signal of the initial data is analyzed, and the high-frequency components and low-frequency components in the frequency domain are determined in combination with a set threshold; the mathematical model is used to calculate changes in sample characteristics based on the high-frequency components and low-frequency components, and to infer abnormal conditions or pathogen types present in the sample to obtain inference results; and the inference results are sent using 5G technology.

[0165] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0166] It should be noted that the functions or steps that can be implemented by the above-mentioned storage medium or computer device can refer to the relevant description in the aforementioned method embodiment. In order to avoid repetition, they will not be described one by one here.

[0167] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0168] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0169] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the system of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a terminal, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0171] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent POCT detection method based on 5G and microfluidic technology, characterized in that: include: Microfluidics technology combined with integrated sensors is used to obtain initial data of samples collected in real time; Preprocessing the initial data, and converting the preprocessed data to obtain converted data; constructing a mathematical model between sample characteristic changes and target analyte concentrations based on the converted data; Analyze the frequency domain corresponding to the time series signal of the initial data, and determine the high-frequency components and low-frequency components in the frequency domain in combination with a set threshold; Utilizing the mathematical model to calculate changes in sample characteristics based on the high-frequency components and the low-frequency components, and inferring abnormal conditions or pathogen types present in the sample to obtain inference results; The inference result is sent using 5G technology.

2. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 1 is characterized in that: The method of using microfluidics technology combined with integrated sensors to obtain initial data of samples collected in real time includes: The sample is introduced into a microfluidic system, and relevant data is collected in real time using an integrated sensor to obtain initial data; The initial data includes the concentration information of the target substance, the flow rate of the sample liquid, and the equipment operating environment parameters.

3. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 1 is characterized in that: The preprocessing of the initial data and converting the preprocessed data to obtain converted data includes: Preprocessing the concentration information of the target substance and the flow rate of the sample liquid according to the equipment environment operating parameters to obtain preprocessed data; The time domain signal corresponding to the preprocessed data is converted into a frequency domain signal using a Fourier transform algorithm to obtain the converted data.

4. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 1 is characterized in that: The analyzing the frequency domain corresponding to the time series signal of the initial data and determining the high-frequency component and the low-frequency component in the frequency domain in combination with the set threshold value includes: Identify high-frequency components and low-frequency components according to the frequency domain data and the initial data in combination with a set threshold, and determine weight coefficients corresponding to the high-frequency components and the low-frequency components; The step of identifying high-frequency components and low-frequency components according to the frequency domain data and the initial data in combination with a set threshold, and determining weight coefficients corresponding to the high-frequency components and the low-frequency components, includes: Perform spectrum analysis on the frequency domain data, identify high-frequency components and low-frequency components based on sample feature changes, target analyte concentrations, and set thresholds; The proportions of the high-frequency component and the low-frequency component in the total are calculated to obtain the weight coefficients corresponding to the high-frequency component and the low-frequency component.

5. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 4 is characterized in that: The use of the mathematical model to calculate the change of the sample characteristics according to the high-frequency components and the low-frequency components, and inferring the abnormal conditions or pathogen types present in the sample to obtain the inference results, includes: Calculate sample fluctuations based on frequency data corresponding to high-frequency components and low-frequency components; Calculate the comprehensive sample irregularity according to the sample fluctuation and the weight coefficients corresponding to the high-frequency component and the low-frequency component to obtain the sample irregularity; The abnormal conditions or pathogen types encountered by the sample are identified based on the sample fluctuations and the irregularity of the sample, and the specific features are classified into specific pathological states to obtain inference results.

6. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 5, characterized in that: The identifying of abnormal conditions or pathogen types encountered by the sample according to the sample fluctuation and the irregularity of the sample, and classifying specific features into specific pathological states to obtain inference results, includes: Obtain data of standard samples under the same conditions as the current samples but without the influence of the test substance as a reference; Calculate the specific change value between the preprocessed data and the standard sample data to obtain a change vector; The change vector, the sample fluctuation, and the sample irregularity quantification are input into an analysis model to determine the abnormality or pathogen type encountered by the sample and classify the specific features into a specific pathological state.

7. The intelligent POCT detection method based on 5G and microfluidic technology according to claim 1 is characterized in that: The mathematical model is Wherein, C(t) represents the concentration of the target substance, S(t) is the transmission speed of the sample, P(t) is the equipment pressure, V(t) is the liquid flow rate, b and c are influence coefficients, which are used to quantify the influence of the flow rate and its rate of change on the concentration change; f(S(t), P(t)) in the mathematical model represents the influence of the sample transmission speed and the equipment pressure on the concentration of the target substance.

8. Intelligent POCT detection system based on 5G and microfluidic technology, characterized by: include: An initial data acquisition unit, used to acquire initial data of samples collected in real time by using microfluidics technology combined with integrated sensors; A preprocessing unit, used for preprocessing the initial data and converting the preprocessed data to obtain converted data; A mathematical model building unit, used to build a mathematical model between sample characteristic changes and target analyte concentrations based on the converted data; An analysis unit, used for analyzing the frequency domain corresponding to the time series signal of the initial data, and determining the high-frequency component and the low-frequency component in the frequency domain in combination with a set threshold; An inference unit, used to calculate the change of sample characteristics according to the high-frequency components and the low-frequency components using the mathematical model, and to infer the abnormality or pathogen type present in the sample to obtain an inference result; A sending unit is used to send the inference result using 5G technology.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images