Data analysis method and system for multiple PCR (Polymerase Chain Reaction) multi-target parallel amplification

Abstract

The invention relates to a data analysis method and system for multiple PCR multi-target parallel amplification, and relates to the field of biological detection.User features and respiratory tract features of a target user are collected and analyzed to obtain feature confidence, the features are utilized to predict multiple PCR detection results, error calculation is carried out on the results and an actual detection spectrum, and the accuracy of the results is improved. According to the multi-PCR multi-target parallel amplification data analysis method and system, the abnormal modes are detected in a classified mode in combination with the feature confidence coefficient, the actual detection spectrum is marked, the technical problems that multi-PCR multi-target parallel amplification data analysis is complex, errors are prone to occurring, and automatic and accurate analysis is difficult are solved, automatic and precise analysis of the multi-PCR multi-target parallel amplification data is achieved, the accuracy and efficiency of data analysis are effectively improved, and the data analysis efficiency is improved. Detection abnormity can be found in time, and the reliability and accuracy of clinical research are improved.

Description

Technical Field

[0001] The present invention relates to the field of biological detection, and in particular, to a data analysis method and system for parallel amplification of multiple targets by multiplex PCR. Background Art

[0002] In the field of molecular biology research, the multiplex polymerase chain reaction (MPCR) technology has become an important tool for simultaneously detecting multiple bacterial viruses or gene targets. The MPCR technology realizes the synchronous amplification of multiple targets by introducing multiple pairs of specific primers in a single PCR reaction, greatly improving the detection efficiency and throughput, and reducing the detection cost and time. Especially in the judgment of respiratory infections and the like, the MPCR technology can simultaneously detect multiple respiratory viruses, bacteria, etc., providing important support for biological research.

[0003] However, with the wide application of the MPCR technology, the complexity and challenge of its data analysis have become increasingly prominent. The data generated by the multiplex PCR reaction contains the amplification information of multiple targets. How to accurately and efficiently analyze these data and then extract useful biological information has become a hot topic and a difficult point in current research. The existing data analysis methods often rely on manual interpretation or simple threshold setting, which are difficult to handle complex multiplex PCR data and are prone to misjudgment or missed judgment. In addition, factors such as physiological differences between different users, sample quality, and changes in experimental conditions will also affect the MPCR detection results, further increasing the difficulty of data analysis. Summary of the Invention

[0004] Aiming at the technical problems in the prior art that the data analysis of parallel amplification of multiple targets by multiplex PCR is complex, error-prone and difficult to automatically and accurately analyze, the present invention provides a data analysis method and system for parallel amplification of multiple targets by multiplex PCR to solve.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a data analysis method for multiplex PCR multi-target parallel amplification. The method includes: collecting user characteristics and respiratory characteristics of a target user, and analyzing to obtain characteristic confidence levels; predicting the detection results after multiplex PCR detection according to multiple preset targets respectively based on the user characteristics and respiratory characteristics, to obtain a first predicted multiplex PCR detection spectrum and a second predicted multiplex PCR detection spectrum; collecting a detection sample of the target user, and performing multiplex PCR parallel amplification detection according to the multiple preset targets to obtain an actual multiplex PCR detection spectrum; calculating the errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a detection error margin, combining the characteristic confidence levels, classifying to obtain detection abnormal patterns, and annotating the actual multiplex PCR detection spectrum as the data analysis result.

[0007] In a second aspect, the present invention provides a data analysis system for multiplex PCR multi-target parallel amplification. The system includes: a characteristic collection module for collecting user characteristics and respiratory characteristics of a target user, and analyzing to obtain characteristic confidence levels; a detection spectrum acquisition module for predicting the detection results after multiplex PCR detection according to multiple preset targets respectively based on the user characteristics and respiratory characteristics, to obtain a first predicted multiplex PCR detection spectrum and a second predicted multiplex PCR detection spectrum; an amplification detection module for collecting a detection sample of the target user, and performing multiplex PCR parallel amplification detection according to the multiple preset targets to obtain an actual multiplex PCR detection spectrum; an error calculation module for calculating the errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a detection error margin, combining the characteristic confidence levels, classifying to obtain detection abnormal patterns, and annotating the actual multiplex PCR detection spectrum as the data analysis result.

[0008] The beneficial effects of the present invention are as follows: By collecting user characteristics and respiratory characteristics of a target user and analyzing to obtain characteristic confidence levels, using these characteristics to predict multiplex PCR detection results, then calculating the errors with the actual detection spectrum, combining the characteristic confidence levels to classify detection abnormal patterns and annotate the actual detection spectrum, it realizes the automated and precise analysis of multiplex PCR multi-target parallel amplification data, effectively improves the accuracy and efficiency of data analysis, helps to timely detect detection abnormalities, and enhances the reliability and accuracy of biological research. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a flowchart of a data analysis method for multiplex PCR multi-target parallel amplification provided by the present invention.

[0010] Figure 2Schematic structural diagram of a data analysis system for multiplex PCR multi-target parallel amplification provided by the present invention.

[0011] Explanation of reference numerals: Feature acquisition module 11, detection spectrum acquisition module 12, amplification detection module 13, error calculation module 14. Detailed implementation manners

[0012] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0015] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a data analysis method for multiplex PCR multi-target parallel amplification. The method includes: S10: Collect user characteristics and respiratory characteristics of the target user, and analyze to obtain feature confidence.

[0016] Exemplarily, multiplex PCR is a variant of polymerase chain reaction (PCR) that allows multiple different DNA targets to be amplified simultaneously in one reaction. Compared with traditional single-target PCR, multiplex PCR designs multiple pairs of specific primers that are respectively targeted at different DNA sequences, thereby achieving synchronous amplification of multiple targets in one reaction.

[0017] Among them, specific primers are primers specifically designed for different DNA sequences. Each pair of primers can accurately recognize and bind to a specific target DNA fragment, guiding the DNA amplification reaction, ensuring that in a single reaction of multiplex PCR, different primers amplify the corresponding target DNA sequences respectively, achieving synchronous amplification of multiple targets without non-specific binding to other irrelevant DNA sequences. For example, in a multiplex PCR experiment for detecting multiple viruses, the primers designed for specific gene fragments of each virus are specific primers, which only act on the genes of the corresponding virus and will not mistakenly bind to the DNA of other viruses or normal cells.

[0018] The multiplex PCR technique is widely used in the field of molecular biology research, especially in cases where multiple bacterial viruses or gene targets need to be detected simultaneously. For example, in the study of respiratory tract infections, multiplex PCR can simultaneously detect multiple respiratory viruses (such as influenza virus, respiratory syncytial virus) and bacteria (such as Streptococcus pneumoniae, Haemophilus influenzae), etc.

[0019] Parallel amplification of multiple targets is achieved by adding multiple pairs of specific primers to the PCR reaction system. These primers are respectively targeted at different DNA targets and need to be designed to ensure that they do not interfere with each other, that is, they do not form primer dimers or non-specific amplification. During the PCR reaction process, all primers bind to the template DNA simultaneously and are amplified under the action of DNA polymerase. Since each primer is only targeted at a specific DNA sequence, the amplification products are also specific, thus achieving parallel amplification of multiple targets.

[0020] The purpose of amplification is to increase the quantity of a specific DNA sequence to a detectable level. In molecular biology research, the content of target DNA sequences in many biological samples is extremely low, and direct detection often makes it difficult to obtain accurate results. Through PCR amplification, the quantity of the target DNA sequence can be amplified by millions or even billions of times, thus greatly improving the sensitivity and accuracy of detection. In multiplex PCR, amplification needs to process multiple targets simultaneously, and the content of each target may be very low. Only through amplification can it be ensured that each target can be accurately detected. The amplified DNA products can also be used for subsequent analyses, such as sequencing, cloning, expression, etc., providing rich materials for scientific research.

[0021] Preferably, in a data analysis method for multiplex PCR multi-target parallel amplification proposed in this solution, the user characteristics and respiratory characteristics of the target user are first collected. The target user refers to the specific research object for multiplex PCR multi-target parallel amplification. After determining the target user, their user characteristics are obtained. The user characteristics refer to the basic information of the target user, such as age, weight, etc. These characteristics are crucial for understanding the user's physiological state and possible influencing factors. At the same time, the respiratory characteristics of the target user are obtained. The respiratory characteristics refer to the characteristics related to the user's respiratory health status, which may include symptom descriptions, such as cough, fever, etc.

[0022] After obtaining the user characteristics and respiratory characteristics of the target user, by analyzing the occurrence rates of the user characteristics and respiratory characteristics in the user database, the reliability of these characteristics for the current detection, that is, the confidence level, is calculated. The higher the confidence level, the greater the contribution of these characteristics to the prediction result. The user database is continuously updated and stores a large amount of user characteristic data to calculate the occurrence rates of the characteristics.

[0023] Specifically, the occurrence frequencies of user characteristics, such as a specific age group or weight range, and respiratory characteristics, such as the physical properties of a specific sample, are respectively counted. The first occurrence rate and the second occurrence rate of the two in the database are obtained in sequence, and then the characteristic confidence level is calculated based on these occurrence rates. The characteristic confidence level, as an index to measure the reliability of the characteristic, reflects the stability and representativeness of the characteristic in the current analysis context, providing an important reference basis for predicting the multiplex PCR detection result. For example, if users in a certain age group frequently appear in the database and their respiratory characteristics show a certain regularity, the characteristic confidence level of this age group and related respiratory characteristics will be relatively high, indicating that these characteristics have higher credibility when predicting the multiplex PCR detection result.

[0024] S20: According to the user characteristics and respiratory characteristics, respectively predict the detection results after multiplex PCR detection according to multiple preset targets, and obtain the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum.

[0025] Optionally, after collecting the user characteristics and respiratory characteristics of the target user and analyzing to obtain the characteristic confidence level, use this characteristic information to respectively predict the detection results after multiplex PCR detection according to multiple preset targets.

[0026] Among them, multiple preset targets refer to multiple pre-set targets for multiplex PCR detection. These targets are the objects of detection, and the prediction network will predict the results after multiplex PCR detection according to these preset targets based on user characteristics and respiratory characteristics. For example, in actual detection, multiple preset targets may be set for different virus markers, and the prediction network predicts the amplification of these targets. If the physical properties of the sample indicate that it contains a high concentration of certain components, predictions may be made for the targets related to these components.

[0027] Specifically, call the multiplex PCR prediction channel configured on the cloud server. This channel incorporates a first multiplex PCR prediction network and a second multiplex PCR prediction network, both of which are constructed and trained through deep learning techniques. During the prediction process, the collected user characteristics, such as indicators reflecting individual physiological status like age and weight, and respiratory characteristics, such as factors that may affect the PCR reaction like the physical properties of the sample and environmental condition-related parameters, are used as input data and transmitted to the first multiplex PCR prediction network and the second multiplex PCR prediction network respectively.

[0028] The first multiplex PCR prediction network and the second multiplex PCR prediction network will predict the results after multiplex PCR detection according to the input characteristic information, combining the complex patterns and correlation relationships learned internally. The prediction output will obtain two prediction results, namely the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum. These two detection spectra respectively represent the estimations of the multiplex PCR detection results by different prediction networks, and they contain key information such as the amplification of each preset target and signal intensity.

[0029] For example, if the user characteristics show that the user is in a certain specific age group and the physical properties of the sample in the respiratory characteristics indicate that it may contain a high concentration of certain components, then the prediction network may predict that there will be a strong amplification signal for the targets related to these components in the multiplex PCR detection, which is thus reflected in the predicted multiplex PCR detection spectrum. These two prediction spectra provide a benchmark for subsequent comparative analysis with the actual detection results, helping to evaluate the accuracy and reliability of the detection.

[0030] S30: Collect the detection sample of the target user, perform multiplex PCR parallel amplification detection according to the multiple preset targets, and obtain the actual multiplex PCR detection spectrum.

[0031] Furthermore, after the collection and prediction analysis of the target user characteristics and respiratory characteristics are completed, enter the experimental operation stage, that is, collect the detection sample of the target user and perform multiplex PCR parallel amplification detection according to the preset multiple targets to obtain the actual multiplex PCR detection spectrum.

[0032] Specifically, as the material basis for subsequent analysis, the collection of test samples must follow strict operating specifications to ensure aseptic operation during the collection process and the integrity and representativeness of the samples. The sample types may cover biological fluids, tissue fragments, etc., and their selection is based on the experimental purpose and the characteristics of the preset targets. For example, when collecting biological fluid samples, special collection instruments need to be used and standard operating procedures need to be followed to avoid contamination.

[0033] Furthermore, based on the information of multiple preset targets, which are usually pre-selected according to research needs and may cover specific gene fragments, markers, and other DNA sequences with analytical value, multiplex PCR parallel amplification detection is carried out.

[0034] Using the multiplex PCR technique, specific primers for multiple preset targets are simultaneously added to the same reaction system. These primers are designed with precise base sequences to ensure that only the target sequences are specifically amplified in the PCR reaction. At the same time, the system also contains necessary components such as DNA polymerase and dNTPs to support the extension of DNA strands, aiming to ensure that they do not interfere with each other during the amplification process and can specifically recognize and amplify their corresponding target sequences.

[0035] Under the PCR reaction conditions, exponential amplification of the target DNA sequence is achieved through the thermal cycling process. The thermal cycler, as the key equipment for performing the PCR reaction, promotes the exponential amplification of the target DNA sequence by precisely controlling the temperature cycle, including three key steps: denaturation, annealing, and extension.

[0036] After the amplification is completed, high-precision detection equipment such as a fluorescence quantitative PCR instrument or a capillary electrophoresis instrument is used to detect and analyze the amplification products. These devices can accurately quantify the amplification of each target based on characteristic parameters such as fluorescence signal intensity or electrophoretic mobility. After integrating the detection data of each target, an actual multiplex PCR detection spectrum is constructed.

[0037] Among them, the actual multiplex PCR detection spectrum details the amplification of each preset target, including key parameters such as amplification efficiency and signal intensity, and is presented in a graphical or digital form, intuitively showing the amplification efficiency and relative content of each target, providing an experimental basis for subsequent comparative analysis with the predicted detection spectrum. For example, if a specific length of DNA sequence is included in the preset target, after parallel amplification by multiplex PCR, if the sequence is successfully amplified, a corresponding high-intensity fluorescence signal peak will appear in the actual multiplex PCR detection spectrum, and its position and intensity reflect the amplification efficiency and content of the target, providing an intuitive and quantitative result for data analysis.

[0038] S40: Calculate the error between the actual multiplex PCR detection spectrum and the first and second predicted multiplex PCR detection spectra to obtain the detection error margin. Combine the feature confidence level, classify to obtain the detection anomaly pattern, and label the actual multiplex PCR detection spectrum as the data analysis result.

[0039] Specifically, after obtaining the actual multiplex PCR detection spectrum, it is necessary to further calculate the error between it and the first and second predicted multiplex PCR detection spectra to quantify the deviation degree of the detection result. Among them, the error calculation is carried out by comparing the amplification signal intensity or relative content of each target in the actual detection spectrum with the predicted value of the corresponding target in the predicted spectrum, and statistical indicators such as mean square error (MSE) and absolute error are used for quantitative evaluation. The obtained result is the detection error margin, which reflects the difference between the actual detection result and the predicted value.

[0040] Furthermore, the calculated detection error margin is combined with the feature confidence level obtained from the analysis for analysis. The feature confidence level, as an indicator to measure the reliability of user features and respiratory tract features, directly affects the accuracy of the prediction result. Through preset classification rules or algorithm models, such as decision trees and support vector machines, the detection anomaly pattern is classified and identified based on the comprehensive consideration of the detection error margin and the feature confidence level. For example, when the detection error margin exceeds a certain threshold and the feature confidence level is low, it may be classified as a "high error and low confidence level anomaly pattern", indicating that there is a significant difference between the detection result and the predicted value, and the reliability of the feature information is insufficient; on the contrary, if the error margin is small and the confidence level is high, it is classified as a "normal detection pattern".

[0041] Finally, label the actual multiplex PCR detection spectrum according to the detected anomaly pattern obtained by classification. The labeling content may include key information such as the anomaly type and the degree of anomaly, thus forming a complete data analysis result. This result not only provides an important basis for subsequent data interpretation, but also provides a direction for optimizing the PCR reaction conditions and improving the detection accuracy. For example, if the labeling result shows that there is a "high error and low confidence level anomaly" for a certain target, it is necessary to further review the primer design, reaction conditions or sample processing process of this target to identify and correct potential error sources.

[0042] In summary, the data analysis process for multiplex PCR multi-target parallel amplification realizes the precise evaluation and labeling of the multiplex PCR detection result by collecting user features and respiratory tract features, predicting the multiplex PCR detection result, obtaining the actual detection spectrum, calculating the error and classifying the detection anomaly pattern, significantly improving the accuracy and reliability of the detection, and providing technical support for subsequent data interpretation and experimental optimization.

[0043] In a preferred embodiment, user characteristics and respiratory tract characteristics of a target user are collected, and characteristic confidence levels are analyzed and obtained, including: collecting user characteristics of the target user, where the user characteristics include age and weight; collecting respiratory tract characteristics of the target user, and the respiratory tract characteristics at least include sample physical properties, environmental parameters, and respiratory symptom indicators; analyzing and obtaining the characteristic confidence levels of the user characteristics and respiratory tract characteristics.

[0044] Specifically, in the preparation stage of multiplex PCR multi-target parallel amplification detection, it is necessary to systematically collect user characteristics and respiratory tract characteristics of the target user, and analyze and obtain characteristic confidence levels based on these characteristics to ensure the accuracy and reliability of subsequent detection and analysis.

[0045] Among them, the collection of the user characteristics focuses on two basic physiological indicators of age and weight. As a continuous variable, age reflects the life cycle stage of the user and may affect the natural content or metabolic rate of certain components in the body; weight, as an indicator to measure the physical size and substance content of the user, is indirectly related to the sample collection amount or the distribution of substances in the body. For example, under the same conditions, users with a larger weight may produce a larger amount of biological samples to be detected.

[0046] The collection of respiratory tract characteristics focuses on the characteristics directly related to the respiratory system, involving environmental parameters during sample collection, such as temperature and humidity. Although they are not directly used as user characteristics, they may affect the physical state of the sample. For example, the temperature, humidity, and air quality (dust concentration, microbial content) of the sampling environment may introduce external interference or affect the sample preservation quality; and the physical and chemical properties of the sample itself, such as viscosity, transparency, color, pH value, osmotic pressure, protein concentration, etc., reflect the apparent and chemical characteristics of the sample and may affect the PCR reaction efficiency. Respiratory symptom indicators, such as cough frequency, sputum nature, wheezing degree, body temperature, respiratory rate, abnormal lung auscultation, etc., assist in judging the type of infection or inflammation status. In addition, according to the actual situation, respiratory tract characteristics may also cover microbial indicators, such as Gram staining results, direct microscopic examination of flora distribution, etc., to provide a direction for multiplex PCR target selection; historical data related to the disease, such as previous respiratory infection types, previous records of positive detection targets, etc., assist in verifying the rationality of the current detection results.

[0047] After completing feature collection, by counting the occurrence frequencies of these features in a preset user database, the feature confidence levels of user features and respiratory tract features are analyzed and obtained. As a quantitative indicator for measuring the stability and representativeness of features, the feature confidence level directly reflects the reliability of features in the current analysis context. For example, if users in a certain age range and weight range frequently appear in the database and their respiratory tract features show certain regularity, the feature confidence level of this combined feature will be relatively high, indicating that these features have higher credibility in subsequent multiplex PCR multi-target parallel amplification detection analysis and providing strong support for the accurate interpretation of detection results.

[0048] In a preferred embodiment, the method further includes: retrieving the user features in the user database within a recently preset time range to obtain a first occurrence rate, where the user database updates and stores user features and respiratory tract features within the recently preset time range; retrieving the respiratory tract features in the user database to obtain a second occurrence rate; and calculating the feature confidence level based on the first occurrence rate and the second occurrence rate.

[0049] Specifically, to accurately evaluate the reliability of target user features and respiratory tract features, targeted retrieval and calculation need to be performed in the user database within a recently preset time range. The user database continuously updates and stores the feature information of all users within the recently preset time period, covering user features (such as indicators reflecting individual physiological states like age, weight, etc.) and respiratory tract features (such as physicochemical properties of samples, environmental parameters, etc., which may affect PCR reactions). The recently preset time range refers to a specific time interval set in advance, which can be set as the most recent week, month, or three months, etc. The data within this range is used for subsequent targeted retrieval and calculation to evaluate the reliability of target user features and respiratory tract features.

[0050] Retrieve the user features of the target user in the database. By counting the number of occurrences of these features in the database and dividing by the total number of records in the database, the first occurrence rate is calculated. As an indicator for measuring the universality and stability of user features, the first occurrence rate directly reflects the distribution of this feature in the target user group. For example, if users in a certain age range frequently appear in the database, the first occurrence rate of the age range feature will be relatively high, indicating that this feature has a high universality in the current user group.

[0051] Retrieve the respiratory tract features of the target user in the same database. Similarly, by counting the number of occurrences and calculating the proportion, the second occurrence rate is obtained. The second occurrence rate focuses on reflecting the distribution law of respiratory tract features in the target user group.

[0052] According to the first occurrence rate and the second occurrence rate, through a preset algorithm model, such as weighted average, multiplication model, etc., the feature confidence is calculated. As a quantitative index comprehensively measuring the reliability of user features and respiratory tract features, the calculation process of the feature confidence fully considers the occurrence frequencies of the two features and their potential impacts in data analysis. For example, if the age feature and the respiratory tract feature of a certain user both have a high occurrence rate in the database, then the feature confidence will be correspondingly increased, indicating that these features have higher credibility in the subsequent multiplex PCR multi-target parallel amplification detection analysis, providing a strong basis for the accurate interpretation of the detection results.

[0053] In a preferred embodiment, according to the user features and respiratory tract features, the detection results after multiplex PCR detection according to multiple preset targets are respectively predicted to obtain a first predicted multiplex PCR detection spectrum and a second predicted multiplex PCR detection spectrum, including: calling a multiplex PCR prediction channel configured on a cloud server, where the multiplex PCR prediction channel includes a first multiplex PCR prediction network and a second multiplex PCR prediction network; transmitting the user features and respiratory tract features to the cloud server and respectively inputting them into the first multiplex PCR prediction network and the second multiplex PCR prediction network in the multiplex PCR prediction channel, and predicting and outputting a first predicted multiplex PCR detection spectrum and a second predicted multiplex PCR detection spectrum for multiplex PCR detection according to multiple preset targets.

[0054] Preferably, to achieve accurate prediction of the detection results, it is necessary to call the multiplex PCR prediction channel configured on the cloud server. The multiplex PCR prediction channel, as the core analysis module, integrates a first multiplex PCR prediction network and a second multiplex PCR prediction network. Both of these networks are constructed based on deep learning algorithms and have been trained with a large amount of data, and have the ability to predict the results of multiplex PCR detection.

[0055] Specifically, the user features of the target user collected (such as indicators reflecting individual physiological states such as age and weight) and respiratory tract features (such as physicochemical properties of the sample, environmental parameters, etc., which may affect the PCR reaction) are used as input data and transmitted to the cloud server through a secure data transmission protocol. Subsequently, these feature data are respectively input into the first multiplex PCR prediction network and the second multiplex PCR prediction network in the multiplex PCR prediction channel.

[0056] Inside the prediction network, through a complex neural network structure and algorithm model, the input feature data is deeply analyzed and processed, simulating various variables and influencing factors in the multiplex PCR detection process, and then predicting and outputting the detection results after multiplex PCR detection according to multiple preset targets.

[0057] Among them, due to differences in network structure, training data, algorithm optimization, etc., the first multiplex PCR prediction network and the second multiplex PCR prediction network may output slightly different prediction results, and then obtain the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum respectively. These two predicted detection spectra detail the predicted amplification of each preset target, including key parameters such as amplification efficiency and signal intensity, providing an important basis for subsequent comparative analysis with the actual detection results. For example, if a certain target shows a high amplification efficiency in the first predicted multiplex PCR detection spectrum and a slightly lower amplification efficiency in the second predicted multiplex PCR detection spectrum, this may reflect the different understandings of the amplification of this target by different prediction networks, providing reference information from multiple perspectives for subsequent data interpretation.

[0058] In a preferred embodiment, the configuration steps of the multiplex PCR prediction channel include: according to the sample data of multiplex PCR detection according to multiple preset targets, collecting the sample user feature set and sample respiratory tract feature set of multiple sample users, and collecting the sample multiplex PCR detection spectrum set of the multiplex PCR detection; using deep learning to construct the first multiplex PCR prediction network and the second multiplex PCR prediction network; respectively using the sample user feature set and sample respiratory tract feature set as input training data, and using the sample multiplex PCR detection spectrum set as output supervision data to perform supervised training, verification and testing on the first multiplex PCR prediction network and the second multiplex PCR prediction network until convergence; configuring the converged first multiplex PCR prediction network and second multiplex PCR prediction network on the cloud server to obtain the multiplex PCR prediction channel.

[0059] Furthermore, the configuration of the multiplex PCR prediction channel aims to build a model that can accurately predict the results of multiplex PCR detection through deep learning technology. The specific configuration process needs to systematically collect the sample user feature set and sample respiratory tract feature set of multiple sample users according to the sample data of multiplex PCR detection according to multiple preset targets.

[0060] Among them, the sample user feature set covers indicators reflecting individual physiological states such as age and weight, and the sample respiratory tract feature set contains factors that may affect the PCR reaction such as the physicochemical properties and environmental parameters of the sample. At the same time, collect the sample multiplex PCR detection spectrum set obtained after multiplex PCR detection, which details the actual amplification of each preset target and serves as the supervision basis for subsequent model training.

[0061] Subsequently, deep learning techniques are adopted to construct a first multiplex PCR prediction network and a second multiplex PCR prediction network respectively. These two networks may differ in structure, such as the number of network layers, the number of neurons, or the choice of activation functions, etc., aiming to capture complex patterns in the data through different model architectures. Specific limitations are not set here and can be configured according to the actual situation.

[0062] In the model training stage, the sample user feature set and the sample respiratory tract feature set are used as input training data respectively, and the sample multiplex PCR detection spectrum set is used as output supervision data to conduct supervised training on the first multiplex PCR prediction network and the second multiplex PCR prediction network. During the training process, by continuously adjusting the network parameters, the model output gradually approaches the true multiplex PCR detection spectrum. At the same time, a validation set is used to validate the model, evaluate its generalization ability on new data, and a test set is used for the final test to ensure the stability and reliability of the model.

[0063] When the model reaches the convergence state during training, validation, and testing, it indicates that the model has learned the effective patterns in the data and can accurately predict the multiplex PCR detection results. Finally, the converged first multiplex PCR prediction network and the second multiplex PCR prediction network are deployed to the cloud server to construct a multiplex PCR prediction channel. The multiplex PCR prediction channel can receive user features and respiratory tract features as inputs and quickly output the predicted multiplex PCR detection spectrum, providing strong support for subsequent data analysis. For example, if the age and weight features of a sample user are input into the multiplex PCR prediction channel, the channel will use the trained model to predict the amplification of each target in the multiplex PCR detection of the user sample and output the corresponding predicted detection spectrum.

[0064] In a preferred embodiment, the error between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum is calculated to obtain the detection error magnitude, including: calculating the absolute error between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain the first detection spectrum error and the second detection spectrum error; calculating the detection error magnitude based on the first detection spectrum error and the second detection spectrum error.

[0065] Exemplarily, to evaluate the accuracy of the prediction results, it is necessary to calculate the error between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum, and then obtain the detection error magnitude.

[0066] First, for each preset target, calculate the absolute errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum, and the second predicted multiplex PCR detection spectrum respectively. The absolute error, as a quantitative index to measure the difference between the predicted value and the actual value, is obtained by calculating the absolute value of the difference between the amplification signal intensity or relative content of each target in the predicted spectrum and the corresponding target value in the actual spectrum. For example, if the amplification signal intensity of a certain target in the actual multiplex PCR detection spectrum is 100 units, while the predicted value in the first predicted multiplex PCR detection spectrum is 90 units, then the first detection spectrum error of this target is 10 units. Similarly, the second detection spectrum error of this target in the second predicted multiplex PCR detection spectrum can be calculated.

[0067] Subsequently, based on the obtained first detection spectrum error and second detection spectrum error, further calculate the detection error margin. The detection error margin, as an index comprehensively reflecting the prediction accuracy, can be obtained by calculating the average value, maximum value or other statistics of the first detection spectrum error and the second detection spectrum error, and the specific calculation method depends on the analysis requirements. For example, if the average value is used as the calculation method of the detection error margin, then sum the first detection spectrum errors and the second detection spectrum errors of all targets respectively and take the average to obtain two average error values. These two average error values together constitute the quantitative representation of the detection error margin, providing an important basis for subsequent data interpretation and model optimization. Through this process, the accuracy of the multiplex PCR prediction model can be systematically evaluated, providing strong support for improving the prediction algorithm and detecting accuracy.

[0068] In a preferred embodiment, in combination with the feature confidence, classify to obtain the detection abnormal pattern, and label the actual multiplex PCR detection spectrum as the data analysis result, including: when the detection error margin is greater than or equal to the preset error margin threshold, input the detection error margin and the feature confidence into the detection abnormal pattern classification channel configured in the cloud server, and obtain multiple classified detection abnormal patterns through classification output of multiple detection abnormal pattern classification branches; screen the classified detection abnormal pattern with the highest frequency of occurrence among the multiple classified detection abnormal patterns to obtain the detection abnormal pattern; use the detection abnormal pattern to label the actual multiplex PCR detection spectrum as the data analysis result.

[0069] Optionally, to accurately identify and label the abnormal situations in the detection process, a detection abnormal pattern classification channel is also configured on the cloud server, and then the detection error margin is comprehensively analyzed in combination with the feature confidence.

[0070] Specifically, when the calculated detection error margin is greater than or equal to the preset error margin threshold, it indicates that there is a significant difference between the actual multiplex PCR detection spectrum and the predicted spectrum. At this time, the detection error margin and the feature confidence level need to be further used as input data and transmitted to the detection anomaly mode classification channel configured in the cloud server for further analysis. Among them, the error margin threshold can be preset based on the actual situation.

[0071] The detection anomaly mode classification channel internally integrates multiple detection anomaly mode classification branches. Each branch is constructed based on a specific algorithm model or rule set, aiming to classify and analyze the input data from different perspectives. Through the parallel processing of multiple detection anomaly mode classification branches, the classification channel can output multiple classified detection anomaly modes, which reflect different possible anomaly types in the detection process.

[0072] Subsequently, screen the output multiple classified detection anomaly modes, count the occurrence frequencies of each mode in all classification results, and select the classified detection anomaly mode with the highest occurrence frequency as the final detection anomaly mode. This screening process is based on statistical principles and aims to determine the most likely one from multiple possible anomaly modes to improve the accuracy of anomaly recognition.

[0073] Finally, use the determined detection anomaly mode to label the actual multiplex PCR detection spectrum. The labeling content may include key information such as the anomaly type. This labeling result, as the final output of data analysis, not only provides an important basis for subsequent data interpretation but also provides a direction for optimizing PCR reaction conditions and improving the detection process.

[0074] In a preferred embodiment, the configuration steps of the detection anomaly mode classification channel include: according to the detection records of multiplex PCR detection, collect the sample feature confidence level set and the sample detection error margin set, and collect the anomaly types detected under different combinations of sample feature confidence levels and sample detection error margins, and label to obtain the sample anomaly mode set; perform N-fold partitioning on the sample feature confidence level set, the sample detection error margin set, and the sample anomaly mode set to obtain N sets of anomaly mode classification training data, where N is a positive integer; respectively use the N sets of anomaly mode classification training data to construct N detection anomaly mode classification branches to obtain the detection anomaly mode classification channel, which is configured in the cloud server.

[0075] Specifically, in the process of constructing the classification channel for abnormal patterns in multiplex PCR detection, it is necessary to systematically collect the sample feature confidence set, the sample detection error margin set, and the abnormal types detected under different combinations of sample feature confidence and sample detection error margin based on the detection records of multiplex PCR detection. Among them, the sample feature confidence set reflects the reliability degree of features in prediction, the sample detection error margin set quantifies the deviation between the actual detection and the prediction, and the abnormal types, such as false negatives and false positives, are the misclassification results that may occur in the detection process. By collecting and annotating these data, a sample abnormal pattern set is formed, which details the corresponding abnormal types under various combinations of feature confidence and detection error margin, providing a rich data basis for subsequent model training.

[0076] Subsequently, to improve the generalization ability and robustness of the model, the sample feature confidence set, the sample detection error margin set, and the sample abnormal pattern set are divided into N folds, that is, they are evenly divided into N non-overlapping subsets. Each time, N - 1 subsets are selected as training data, and the remaining 1 subset is used as validation data. This process is repeated N times to ensure that each data subset is used for both training and validation, thereby obtaining N sets of training data for abnormal pattern classification.

[0077] Next, these N sets of training data for abnormal pattern classification are used separately to independently construct N classification branches for detecting abnormal patterns. Each branch is constructed based on a specific algorithm model (such as decision tree, support vector machine, or neural network, etc.), aiming to learn the complex mapping relationship between feature confidence, detection error margin, and abnormal types from different perspectives. Through the parallel training of N branches, the model can capture the diversity and complexity in the data, improving the accuracy of abnormal pattern recognition.

[0078] Finally, these N trained classification branches for detecting abnormal patterns are integrated into a complete classification channel for detecting abnormal patterns and deployed to a cloud server. This channel can receive the feature confidence and detection error margin in actual detection as inputs and, through the collaborative work of internal branches, quickly output the corresponding abnormal types, providing strong support for the quality control and result interpretation of multiplex PCR detection. For example, if the feature confidence in a certain detection is low and the detection error margin is large, the classification channel may output abnormal types such as "false negative" or "false positive", prompting the detection personnel to further verify the detection process or sample processing steps.

[0079] The data analysis method for multiplex PCR multi-target parallel amplification provided by the embodiments of the present invention has at least the following technical effects:

[0080] 1. By calling the multiple PCR prediction channels configured on the cloud server and using the first multiple PCR prediction network and the second multiple PCR prediction network constructed by deep learning technology, the intelligent prediction of multiple PCR test results is realized. This prediction channel can comprehensively consider the user characteristics and respiratory characteristics of the target user and accurately output the first predicted multiple PCR test spectrum and the second predicted multiple PCR test spectrum. This kind of intelligent prediction not only improves the detection efficiency, but also enhances the reliability and accuracy of the prediction results through the setting of the dual prediction network, providing a basis for the subsequent detection error evaluation.

[0081] 2. After obtaining the actual multiple PCR test spectrum, the detection error range is further obtained by calculating the absolute error between it and the predicted spectrum. Combining with the feature confidence, a detection anomaly pattern classification channel is innovatively introduced. This channel can automatically classify and output multiple classified detection anomaly patterns based on the comprehensive analysis of the detection error range and the feature confidence. By screening the classified detection anomaly pattern with the highest frequency of occurrence, the abnormal situations in the detection process, such as false negatives and false positives, can be accurately identified, providing strong support for the accurate interpretation of the detection results.

[0082] 3. Making full use of the computing power of the cloud server, both the multiple PCR prediction channel and the detection anomaly pattern classification channel are deployed on the cloud server. This deployment method not only improves the speed and efficiency of data processing, but also realizes the centralized management and sharing of data. At the same time, by constructing multiple detection anomaly pattern classification branches through N-fold partitioning of sample data, the generalization ability and robustness of the model are further enhanced, ensuring that the detection anomaly patterns can be accurately identified under different combinations of sample feature confidence and detection error range. This efficient data processing and cloud server deployment strategy provides a strong guarantee for the large-scale application of multiple PCR multi-target parallel amplification detection.

[0083] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the data analysis method for multiple PCR multi-target parallel amplification provided in Embodiment 1, the present invention embodiment also provides a data analysis system for multiple PCR multi-target parallel amplification. The system includes: a feature acquisition module 11, configured to acquire the user characteristics and respiratory characteristics of the target user and analyze to obtain the feature confidence.

[0084] A detection spectrum acquisition module 12, configured to predict the detection results after multiple PCR detections according to multiple preset targets respectively based on the user characteristics and respiratory characteristics, and obtain the first predicted multiple PCR detection spectrum and the second predicted multiple PCR detection spectrum.

[0085] The amplification detection module 13 is used to collect the detection sample of the target user, perform multiplex PCR parallel amplification detection according to the multiple preset targets, and obtain the actual multiplex PCR detection spectrum.

[0086] The error calculation module 14 is used to calculate the errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum, obtain the detection error range, combine the feature confidence level, classify and obtain the detection abnormal mode, and label the actual multiplex PCR detection spectrum as the data analysis result.

[0087] Furthermore, the feature collection module 11 is further used to perform the following steps: collect the user features of the target user, where the user features include age and weight; collect the respiratory tract features of the target user; analyze and obtain the feature confidence levels of the user features and the respiratory tract features.

[0088] Furthermore, the feature collection module 11 is further used to perform the following steps: retrieve the user features in the user database within the most recent preset time range to obtain the first occurrence rate, where the user database updates and stores the user features and respiratory tract features within the most recent preset time range, and the respiratory tract features at least include sample physical properties, environmental parameters, and respiratory symptom indicators; retrieve the respiratory tract features in the user database to obtain the second occurrence rate; calculate and obtain the feature confidence level according to the first occurrence rate and the second occurrence rate.

[0089] Furthermore, the detection spectrum acquisition module 12 is further used to perform the following steps: call the multiplex PCR prediction channels configured on the cloud server, where the multiplex PCR prediction channels include a first multiplex PCR prediction network and a second multiplex PCR prediction network; transmit the user features and the respiratory tract features to the cloud server, and respectively input them into the first multiplex PCR prediction network and the second multiplex PCR prediction network in the multiplex PCR prediction channels, and predict and output the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum for multiplex PCR detection according to multiple preset targets.

[0090] Furthermore, the detection spectrum acquisition module 12 is further configured to perform the following steps: according to the sample data obtained by performing multiplex PCR detection according to multiple preset targets, collect the sample user feature sets and sample respiratory feature sets of multiple sample users, and collect the sample multiplex PCR detection spectrum sets of the multiplex PCR detections; use deep learning to construct a first multiplex PCR prediction network and a second multiplex PCR prediction network; respectively use the sample user feature sets and sample respiratory feature sets as input training data, and use the sample multiplex PCR detection spectrum sets as output supervision data to perform supervised training, verification, and testing on the first multiplex PCR prediction network and the second multiplex PCR prediction network until convergence; configure the converged first multiplex PCR prediction network and second multiplex PCR prediction network on the cloud server to obtain a multiplex PCR prediction channel.

[0091] Furthermore, the error calculation module 14 is further configured to perform the following steps: calculate the absolute errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a first detection spectrum error and a second detection spectrum error; calculate the detection error range according to the first detection spectrum error and the second detection spectrum error.

[0092] Furthermore, the error calculation module 14 is further configured to perform the following steps: when the detection error range is greater than or equal to a preset error range threshold, input the detection error range and the feature confidence into the detection anomaly mode classification channel configured on the cloud server, and obtain multiple classified detection anomaly modes through classification and output of multiple detection anomaly mode classification branches; screen the classified detection anomaly mode with the highest occurrence frequency among the multiple classified detection anomaly modes to obtain the detection anomaly mode; use the detection anomaly mode to label the actual multiplex PCR detection spectrum as the data analysis result.

[0093] Furthermore, the error calculation module 14 is further configured to perform the following steps: according to the detection records of multiplex PCR detections, collect the sample feature confidence set and the sample detection error range set, and collect the anomaly types detected under different combinations of sample feature confidence and sample detection error range, and label to obtain a sample anomaly mode set; perform N-fold partitioning on the sample feature confidence set, the sample detection error range set, and the sample anomaly mode set to obtain N pieces of anomaly mode classification training data, where N is a positive integer; respectively use the N pieces of anomaly mode classification training data to construct N detection anomaly mode classification branches to obtain a detection anomaly mode classification channel and configure it on the cloud server.

[0094] Through the foregoing detailed description of a data analysis method for multiplex PCR multi-target parallel amplification, those skilled in the art can clearly know a data analysis system for multiplex PCR multi-target parallel amplification in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, reference can be made to the description in the method section.

[0095] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data analysis method for multiplex PCR multi-target parallel amplification, characterized in that, The method includes: Collecting the user characteristics and respiratory tract characteristics of the target user, and analyzing to obtain the characteristic confidence level; According to the user characteristics and respiratory tract characteristics, respectively predicting the test results after multiplex PCR testing according to multiple preset targets, to obtain a first predicted multiplex PCR test spectrum and a second predicted multiplex PCR test spectrum; Collecting the test sample of the target user, and performing multiplex PCR parallel amplification testing according to the multiple preset targets to obtain an actual multiplex PCR test spectrum; Calculating the errors between the actual multiplex PCR test spectrum and the first predicted multiplex PCR test spectrum and the second predicted multiplex PCR test spectrum, to obtain the test error range, combining the characteristic confidence level, classifying to obtain the test abnormal pattern, and annotating the actual multiplex PCR test spectrum as the data analysis result.

2. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 1, wherein Collecting the user characteristics and respiratory tract characteristics of the target user, and analyzing to obtain the characteristic confidence level, including: Collecting the user characteristics of the target user, where the user characteristics include age and weight; Collecting the respiratory tract characteristics of the target user, and the respiratory tract characteristics at least include sample physical properties, environmental parameters and respiratory symptom indicators; Analyzing and obtaining the characteristic confidence level of the user characteristics and respiratory tract characteristics.

3. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 2, wherein Including: Retrieving the user characteristics in the user database within the most recent preset time range to obtain the first occurrence rate, where the user database updates and stores the user characteristics and respiratory tract characteristics within the most recent preset time range; Retrieving the respiratory tract characteristics in the user database to obtain the second occurrence rate; Calculating and obtaining the characteristic confidence level according to the first occurrence rate and the second occurrence rate.

4. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 1, characterized in that, According to the user characteristics and respiratory tract characteristics, respectively predicting the test results after multiplex PCR testing according to multiple preset targets, to obtain a first predicted multiplex PCR test spectrum and a second predicted multiplex PCR test spectrum, including: Invoking the multiplex PCR prediction channels configured on the cloud server, where the multiplex PCR prediction channels include a first multiplex PCR prediction network and a second multiplex PCR prediction network; Transmitting the user characteristics and respiratory tract characteristics to the cloud server, and respectively inputting them into the first multiplex PCR prediction network and the second multiplex PCR prediction network in the multiplex PCR prediction channels, and predicting and outputting to obtain a first predicted multiplex PCR test spectrum and a second predicted multiplex PCR test spectrum for multiplex PCR testing according to multiple preset targets.

5. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 4, wherein, The configuration steps of the multiplex PCR prediction channels include: According to the sample data of multiplex PCR testing according to multiple preset targets, collecting the sample user characteristic sets and sample respiratory tract characteristic sets of multiple sample users, and collecting the sample multiplex PCR test spectrum sets for multiplex PCR testing; Using deep learning to construct a first multiplex PCR prediction network and a second multiplex PCR prediction network; Respectively using the sample user characteristic sets and sample respiratory tract characteristic sets as input training data, and using the sample multiplex PCR test spectrum sets as output supervision data to perform supervised training, verification and testing on the first multiplex PCR prediction network and the second multiplex PCR prediction network until convergence; Configure the converged first multiplex PCR prediction network and the second multiplex PCR prediction network in a cloud server to obtain a multiplex PCR prediction channel.

6. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 1, wherein Calculate the errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a detection error margin, including: Calculate the absolute errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a first detection spectrum error and a second detection spectrum error; Calculate and obtain a detection error margin based on the first detection spectrum error and the second detection spectrum error.

7. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 1, wherein Combine the feature confidence to classify and obtain a detection anomaly pattern, and label the actual multiplex PCR detection spectrum as the data analysis result, including: When the detection error margin is greater than or equal to a preset error margin threshold, input the detection error margin and the feature confidence into a detection anomaly pattern classification channel configured in the cloud server, and output multiple classified detection anomaly patterns through multiple detection anomaly pattern classification branches; Screen the classified detection anomaly pattern with the highest occurrence frequency among the multiple classified detection anomaly patterns to obtain a detection anomaly pattern; Use the detection anomaly pattern to label the actual multiplex PCR detection spectrum as the data analysis result.

8. The data analysis method for multiplex PCR multi-target parallel amplification according to claim 7, characterized in that, The configuration steps of the detection anomaly pattern classification channel include: According to the detection records of multiplex PCR detection, collect a set of sample feature confidences and a set of sample detection error margins, and collect the abnormal types detected under different combinations of sample feature confidences and sample detection error margins, and label to obtain a set of sample anomaly patterns; Perform N-fold partitioning on the set of sample feature confidences, the set of sample detection error margins, and the set of sample anomaly patterns to obtain N sets of anomaly pattern classification training data, where N is a positive integer; Respectively use the N sets of anomaly pattern classification training data to construct N detection anomaly pattern classification branches to obtain a detection anomaly pattern classification channel and configure it in the cloud server.

9. A data analysis system for multiplex PCR multi-target parallel amplification, characterized in that, For implementing the data analysis method for multiplex PCR multi-target parallel amplification according to any one of claims 1-8, the system includes: A feature acquisition module for acquiring user features and respiratory tract features of a target user and analyzing to obtain a feature confidence; A detection spectrum acquisition module for respectively predicting the detection results after multiplex PCR detection according to multiple preset targets based on the user features and respiratory tract features to obtain a first predicted multiplex PCR detection spectrum and a second predicted multiplex PCR detection spectrum; An amplification detection module for collecting a detection sample of the target user and performing multiplex PCR parallel amplification detection according to the multiple preset targets to obtain an actual multiplex PCR detection spectrum; An error calculation module for calculating the errors between the actual multiplex PCR detection spectrum and the first predicted multiplex PCR detection spectrum and the second predicted multiplex PCR detection spectrum to obtain a detection error margin, combining the feature confidence to classify and obtain a detection anomaly pattern, and labeling the actual multiplex PCR detection spectrum as the data analysis result.

Images