Method, device and medium for mutual recognition of clinical test results based on technical traceability

Abstract

The application discloses a kind of based on technical traceability clinical test result mutual recognition method, equipment and medium;Method includes the following steps: establishing traceability data management platform, and the clinical test result obtained by a plurality of different methodological detection is input into traceability data management platform;According to the clinical test result in traceability data management platform, establish standard test curve, simultaneously generate the mapping relationship of each methodological and standard test curve;Determine the risk value of each methodological to each traceability node;According to the determined risk value, new traceability node is formed and is recorded as label information in the corresponding clinical test result of traceability data management platform;Output clinical test result with traceability node.This application can effectively integrate the contribution value of various methodological, eliminate the bias generated by too much dependence on a method;At the same time, the detection process of other methodological is early warned, so that the clinical test result of other methodological can be expected.

Description

Technical Field

[0001] This invention relates to the field of information traceability technology, specifically to a method, device, and medium for mutual recognition of clinical test results based on technical traceability. Background Technology

[0002] The current mechanism for mutual recognition of medical test results mainly relies on a unified concentration benchmark and standardized methodology: First, the concentration of the standard is determined as a comparison benchmark through traceability methods. Then, standard methodologies (such as mass spectrometry) are used to detect the results and obtain the concentration value. Finally, all other methodologies are required to be calibrated to the benchmark concentration, thereby achieving mutual recognition of test results across different methods and platforms.

[0003] However, this mutual recognition mechanism has certain drawbacks: First, it results in significant resource waste, as each manufacturer has already compared the reagents with the traceability method at the time of manufacture, making secondary calibration using another set of standards meaningless. Second, the method has limited technical reliability; since the relationship between concentration and response curves in nature is not ideally linear, the results of different methodologies will inevitably deviate due to differences in calculation methods, antibody specificity, and various interfering factors. The validity of one methodology cannot be used to negate the validity of others. Third, there is serious conceptual confusion; biological activity depends on the binding of spatial structural sites, reflecting the quantity of specific functional structures, not simply the concentration of substances. Clinical diagnosis and artificial intelligence training scenarios truly require activity data; therefore, relying solely on traceability of standard substances to determine results is insufficient. The accuracy of the results is neither convincing nor clinically applicable. Furthermore, this mechanism is not friendly to clinical practice; forced calibration will mask the original performance characteristics of each methodology, making it impossible for clinicians to assess the initial risks of the test, thus increasing diagnostic and treatment uncertainty. At the same time, there is a lack of early warning for cross-methodological differences. When a specific methodology is interfered with and false positives / false negatives occur, the calibrated "mutually recognized" values ​​will mask the risks, causing hidden dangers to be overlooked. Finally, this scheme also creates conflict of interest. It negates the value of other methodologies with a single standard methodology, which itself may not represent the optimal clinical choice, but forces other medical institutions to redevelop antibodies and reconstruct curves in pursuit of consistency, which is costly and difficult to achieve. In essence, it creates an opposition with all other methodology suppliers and is not feasible overall.

[0004] Based on the above problems, the existing mechanism for mutual recognition of medical test results urgently needs improvement. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, device and medium for mutual recognition of clinical test results based on technical traceability.

[0006] The first aspect of this invention provides a method for mutual recognition of clinical test results based on technical traceability, comprising the following steps: Establish a traceability data management platform and input clinical test results obtained by various methodologies into the traceability data management platform. Each clinical test result contains multiple tag information as traceability nodes. Based on the clinical test results in the traceability data management platform, a standard test curve is established, and a mapping relationship between each methodology and the standard test curve is generated. Determine the risk value of each methodology for each tracing node; New traceability nodes are generated based on the determined risk values ​​and recorded as tag information in the corresponding clinical test results on the traceability data management platform. Output clinical test results with traceability nodes.

[0007] Furthermore, the methodology refers to the technical path used when testing the sample; the traceability node includes sample information, testing instrument information, testing reagent information, and testing methodology information. The source tracing node is determined through the following steps: Obtain the source node rules through a preset rule base; The source tracing node rules are used to perform text matching on clinical test results to filter out the target text that matches the results. Establish a traceability node as a label for clinical test results based on the target text.

[0008] Furthermore, the establishment of a standard test curve based on the clinical test results in the traceability data management platform specifically includes the following steps: Prepare standard test samples; The standard test samples are tested using different methodologies, and the clinical test results obtained from the different methodologies are summarized to form a standard dataset. Curve fitting was performed based on the standard dataset, using the concentration of the standard test sample and the mean of the clinical test results as references to obtain the standard test curve.

[0009] Furthermore, the generation of the mapping relationship between each methodology and the standard test curve specifically includes the following steps: The deviation curve is obtained by calculating the deviation between the clinical test results obtained by each methodology in the standard dataset and the standard test curve. The deviation curve serves as a mapping relationship between the clinical test results and the corresponding methodology and the standard test curve.

[0010] Furthermore, determining the risk value of each methodology for each tracing node specifically includes the following steps: Identify the target tracing nodes and prepare tracing samples based on the target tracing nodes; Different methodologies were used to test the traced samples, resulting in multiple sets of clinical test results for the traced samples. The clinical test results of the source samples were transformed using the mapping relationships corresponding to different methodologies, and the transformation results were obtained and a transformation dataset was established. The risk value for each methodology at each tracing node is calculated based on the transformed dataset.

[0011] Furthermore, the calculation of the risk value for each methodology for each source tracing node based on the transformed dataset specifically includes the following steps: Determine the range of risk benchmark values; For each transformation result in the transformation dataset, count the number of other transformation results in the transformation dataset that fall within the range of the risk benchmark value centered on that transformation result. The ratio of the number of transformation results within the risk benchmark range to the total number of transformation results in the transformation dataset is used as the risk value of the methodology corresponding to the transformation result for the target tracing node.

[0012] Furthermore, the calculation of the risk value for each methodology for each source tracing node based on the transformed dataset specifically includes the following steps: Calculate the overall mean of the transformation results in the transformed dataset; The deviation of each transformation result in the transformed dataset from the overall mean is taken as the risk value of the corresponding methodology for the target tracing node.

[0013] Furthermore, the process of mining new tracing nodes based on the determined risk values ​​specifically includes the following steps: The source node to be explored is identified as the target source node; Methodologies with risk values ​​higher than a preset risk difference threshold are selected from the target traceability nodes and used as the target methodologies. Find clinical test results that were detected using the target methodology and whose labels contain the target source node, and use these results as mining results. Then, summarize the mining results into a mining dataset. Feature analysis was performed on the source nodes other than the target source node in the mining results of the data set, and multiple common features were extracted; The extracted common features are then validated a second time, and the common features that pass the second validation are used as new tracing nodes.

[0014] Another aspect of the present invention discloses an electronic device, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the above-described method for mutual recognition of clinical test results based on technical traceability.

[0015] In another aspect, the present invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the above-described method for mutual recognition of clinical test results based on technical traceability.

[0016] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0017] The embodiments of the present invention have the following beneficial effects: The present invention provides a method, device and medium for mutual recognition of clinical test results based on technical traceability. By integrating standard test curves obtained from various samples, instruments, reagents and methodologies, it can effectively integrate the contribution values ​​of various methodologies and eliminate the bias caused by over-reliance on a certain method. The clinical test results with traceability nodes can provide risk warnings for the testing processes of other methodologies, making the clinical test results of other methodologies predictable and providing reliable data support for doctors' treatment recommendations.

[0018] Additional aspects and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description or may be learned by practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the basic steps of a method for mutual recognition of clinical test results based on technical traceability according to the present invention; Figure 2 This is a schematic diagram of the steps for establishing a standard test curve in a clinical test result mutual recognition method based on technical traceability according to the present invention; Figure 3 This is a schematic diagram of the steps for determining the risk value of each methodology for each traceability node in a clinical test result mutual recognition method based on technical traceability according to the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device according to the present invention; Figure 5 This is a schematic diagram of a computer-readable storage medium structure according to the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] The current mechanism for mutual recognition of medical test results mainly follows the following process: 1. Use standard samples with fixed values ​​as the basis for concentration traceability; 2. Concentration detection is performed using standardized comparison methodologies (such as mass spectrometry); 3. All other testing methodologies must be calibrated to the above-mentioned reference concentrations to achieve mutual recognition of test results.

[0023] However, this process suffers from significant technical deficiencies and implementation difficulties, specifically in the following aspects: 1. Repetitive consumption of resources: The traceability method comparison has been calibrated before the reagent leaves the factory. Repeatedly using another set of standard substances for verification does not generate new value and is a redundant process. 2. Limitations of technical implementation: Due to the natural variation between biological sample concentration and response curve, and the influence of multiple technical factors such as calculation methods, differences in antibody specificity, and interfering substances, the detection results of different methodologies will inevitably differ, and the effectiveness of other methodologies cannot be negated by a single methodology. 3. Unclear Conceptual Definition: Biological activity and the concentration of the detected substance belong to different categories. Biological activity reflects the number of binding sites in the spatial structure, rather than the concentration of the substance itself. Clinical diagnosis and treatment, as well as artificial intelligence model training, require reliance on biological activity, not simply on the concentration of the substance. Therefore, relying solely on the traceability of standard substances to determine the accuracy of results lacks scientific basis and clinical applicability. 4. Insufficient clinical applicability: Mandatory calibration may mask the performance characteristics and accuracy of the original methodology, making it impossible for clinicians to assess the initial risk of the test, thereby increasing diagnostic and treatment uncertainty; 5. Lack of methodological discrepancy early warning mechanism: When a specific method is interfered with and false positives / false negatives occur, the mutually recognized values ​​after mandatory calibration may mask the actual risks and cause clinical misjudgment; 6. Conflict of Interests and Technologies: Using a single standard methodology to negate the clinical value of other methodologies, even though that standard methodology may not represent optimal clinical accuracy. To achieve calibration consistency, other methodologies often require the redevelopment of antibodies and the reconstruction of standard curves, which is costly and technically challenging. This leads to conflict between the protocol and most methodology manufacturers, making it difficult to implement.

[0024] In an attempt to address or minimize the aforementioned problems, embodiments of the present invention provide a method, device, and medium for mutual recognition of clinical test results based on technical traceability.

[0025] The first embodiment of the present invention provides a method for mutual recognition of clinical test results based on technical traceability, such as... Figure 1 As shown, it includes the following steps: S1. Establish a traceability data management platform and input clinical test results obtained by various methodologies into the traceability data management platform. Each clinical test result contains multiple label information as traceability nodes. S2. Based on the clinical test results in the traceability data management platform, establish standard test curves and generate the mapping relationship between each methodology and the standard test curve; S3. Determine the risk value of each methodology for each tracing node; S4. New traceability nodes are generated based on the determined risk values ​​and recorded as label information in the corresponding clinical test results on the traceability data management platform; S5. Output clinical test results with traceability nodes.

[0026] The embodiments of this invention, by integrating standard test curves obtained from various samples, instruments, reagents, and methodologies, can effectively synthesize the contribution values ​​of various methodologies and eliminate bias caused by over-reliance on a single method. The clinical test results provided with traceability nodes can provide risk warnings for the testing processes of other methodologies, making the clinical test results of other methodologies predictable and providing reliable data support for doctors' treatment recommendations.

[0027] The implementation process of each step of this invention is described in detail below: S1. Establish a traceability data management platform and input clinical test results obtained from various methodologies into the traceability data management platform.

[0028] In this embodiment of the invention, a traceability data management platform for mutual recognition of clinical test results is jointly established by connecting with medical entities such as hospitals, clinics, testing instrument manufacturers, and reagent manufacturers.

[0029] Because different medical entities use different testing technologies (e.g., different sample collection and culture environments, different brands and functions of testing instruments, different components of testing reagents, etc.), there are certain obstacles to the mutual recognition of clinical test results across entities. Therefore, this embodiment of the invention expresses the testing technology path in the form of a testing methodology, and achieves mutual recognition of test results between different medical entities by establishing a traceability data management platform. Specifically, the traceability data management platform communicates with various hospitals, clinics, testing instrument manufacturers, and reagent manufacturers through different interfaces, allowing each medical entity to upload or download the corresponding clinical test results.

[0030] In this embodiment of the invention, when the traceability data management platform receives clinical test results uploaded by a medical entity, it automatically marks the clinical test results with traceability nodes. Traceability nodes include sample information, instrument information, reagent information, and methodology information. Sample information includes the sample's physical properties (e.g., sample purity), processing conditions (e.g., storage environment), type (e.g., type of body fluid, source of body fluid), and clinical background (e.g., sampling time, sampling site). Instrument information includes instrument identity (e.g., brand, model), status (e.g., years of use, calibration time), and parameters (e.g., software version, detection channels). Reagent information includes reagent identity (e.g., brand, components, version) and status (e.g., opening date, current stability). Methodology information refers to the specific technical path used by the corresponding medical entity to generate the clinical test results (e.g., type of sample, instrument, reagent, specific testing environment, testing duration, etc.). By marking the source nodes of clinical test results, the source nodes themselves can be used as characteristics of the clinical test results, which helps with subsequent commonality analysis and mutual recognition of test results.

[0031] Preferably, in this embodiment of the invention, the marking of source nodes is performed by text matching, specifically including the following steps: S1-1. The source node is determined through the following steps: S1-2. Obtain the source node rules through the preset rule base; S1-3. Use source node rules to perform text matching on clinical test results and filter out the target text that matches the results; S1-4. Establish a traceability node as a label for clinical test results based on the target text.

[0032] In some embodiments, neural networks such as BERT (Bidirectional Encoder Representations from Transformers) and LSTM (Long Short-Term Memory) can also be used for semantic recognition to complete the labeling of source nodes.

[0033] S2. Based on the clinical test results in the traceability data management platform, establish standard test curves and generate the mapping relationship between each methodology and the standard test curve.

[0034] Preferably, such as Figure 2 As shown, step S2 involves establishing a standard test curve based on the clinical test results from the traceability data management platform, specifically including the following steps: S2-1. Prepare standard test samples; S2-2. Test the standard test samples using different methodologies, and summarize the clinical test results obtained from the different methodologies to form a standard dataset; S2-3. Perform curve fitting based on the standard dataset, using the concentration of the standard test sample and the mean of the clinical test results as references to obtain the standard test curve.

[0035] In this embodiment of the invention, the standard test samples are prepared using standards or quality control samples of known concentrations free from matrix interference. Preferably, non-clinical samples (such as those obtained through purely industrial production) are used in the preparation of the standard test samples to avoid contamination of the standard test curves by clinical interference factors.

[0036] After the standard test samples are prepared, this embodiment of the invention uses different methodologies to test them. Preferably, the standard test samples can be distributed to various medical entities for testing. Since different medical entities use different methodologies, and these medical entities themselves are also the recipients of mutual recognition of test results, distributing the standard test samples to various medical entities for testing can effectively realize the testing process of different methodologies, and also make the standard test curve adaptable to the usage needs of each medical entity. After the testing is completed, each medical entity uploads the clinical test results to the traceability data management platform through the corresponding interface. The traceability data management platform summarizes the clinical test results uploaded by each medical entity to form a standard dataset.

[0037] After establishing a standard dataset, this embodiment of the invention obtains a standard test curve through curve fitting. Preferably, a reference system can be established with known, objective substance concentrations as the horizontal axis and the technical consensus values ​​of all participating methodologies as the vertical axis, and the standard test curve can be plotted accordingly. The horizontal axis is used for comparison of known concentration values ​​of non-patient-derived standards / quality control materials. Since the standard test samples are uniformly prepared or procured, their concentrations are assigned using authoritative methods (such as international standard substances, gravimetric preparation, etc.), providing an objective, material benchmark. Therefore, it can provide a stable, realistic, and traceable concentration scale for the entire standard test curve, ensuring the accuracy of the curve at different concentration levels. The vertical axis represents the mean of the effective raw results after cleaning and reliability assessment of all methodologies after testing the standard test sample. It represents the collective consensus or technical democratization result of all methodologies on "how much detection signal the standard test sample concentration should correspond to" under current technical conditions. It can be used as a technical standard.

[0038] Preferably, in this embodiment of the invention, the standard verification curve is iteratively updated as the number of traceability nodes increases. The updating of the standard verification curve reflects the impact of new methodologies or overall technological advancements on the standard verification curve, ensuring that the standard verification curve is not static. Simultaneously, this embodiment of the invention establishes a consensus value for the vertical axis through multiple methodologies, which also avoids imposing the bias of one methodology on the entire result mutual recognition system, making the standard verification curve more equitable.

[0039] Preferably, step S2, which generates the mapping relationship between each methodology and the standard test curve, specifically includes the following steps: S2-4. Calculate the deviation between the clinical test results obtained by each methodology in the standard dataset and the standard test curve to obtain the deviation curve; S2-5. The deviation curve serves as a mapping relationship between the clinical test results and the corresponding methodology and the standard test curve.

[0040] In this embodiment of the invention, after establishing the standard test curve, a mapping relationship between each methodology and the standard test curve is further established. For example, a mathematical formula or algorithm for conversion can be derived through mathematical analysis (such as linear regression, piecewise linear fitting, etc.). This formula may be a simple coefficient or a more complex function, serving as the mapping relationship between the corresponding methodology and the standard test curve. Thus, when different medical entities upload new clinical test results using the corresponding methodology, the clinical test results can be converted into clinical test results of the standard test sample based on this mapping relationship, thereby achieving mutual recognition of results between different medical entities.

[0041] S3. Determine the risk value of each methodology for each tracing node.

[0042] Preferably, such as Figure 3 As shown, in step S3, the risk value of each methodology for each tracing node is determined, which specifically includes the following steps: S3-1. Determine the target tracing nodes and prepare tracing samples based on the target tracing nodes; S3-2. Different methodologies were used to test the traced samples to obtain multiple sets of clinical test results for the traced samples; S3-3. Use the mapping relationships corresponding to different methodologies to transform the clinical test results of their respective source samples, obtain the transformation results, and establish a transformation dataset; S3-4. Calculate the risk value of each methodology for each source node based on the transformed dataset.

[0043] In this embodiment of the invention, the risk value is used to quantify the degree of risk of a certain methodology detecting a clinical sample with certain characteristics (i.e., the clinical test report of the clinical sample is marked with a specific traceability node). Due to the lag in traceability node rules, clinical test reports submitted using a specific methodology in a specific clinical context may contain some previously unidentified features. In this case, the risk value can be used to update the traceability node rules in a timely manner to effectively identify and screen newly classified features, thus maintaining the reliability of the traceability data management platform of this invention.

[0044] In a preferred embodiment, step S3-4 calculates the risk value of each methodology for each source tracing node based on the transformed dataset, specifically including the following steps: S3-4-a1. Determine the range of risk benchmark values; S3-4-a2. Taking each transformation result in the transformation dataset as the center, count the number of other transformation results in the transformation dataset that fall within the range of the risk benchmark value centered on that transformation result; S3-4-a3. The ratio of the number of transformation results within the risk benchmark range to the number of transformation results in the transformation dataset is taken as the risk value of the methodology corresponding to the transformation result for the target tracing node.

[0045] The hazard value calculation method used in this embodiment determines the hazard value of the methodology for the target traceability node through a clinically acceptable consistency assessment. Since different methodologies exhibit varying cross-reactivity to different clinical samples, the resulting differences may be non-linear and unpredictable. Therefore, this embodiment of the invention uses a consistency assessment method to determine whether the clinical test results of the methodology for the target traceability node are subject to a specific interference, and attempts to reorganize this interference into a new traceability node in step S4.

[0046] In a preferred embodiment, step S3-4 calculates the risk value of each methodology for each source tracing node based on the transformed dataset, specifically including the following steps: S3-4-b1. Calculate the overall mean of the transformation results in the transformed dataset; S3-4-b2. The deviation of each transformation result in the transformed dataset from the overall mean is taken as the risk value of the corresponding methodology for the target tracing node.

[0047] In another embodiment, the risk value of the corresponding methodology to the target traceability node can also be determined by calculating the deviation magnitude of a single transformation result from the overall mean. Risk value calculation based on the overall deviation magnitude is primarily applicable to clinical test results where the results are continuous numerical values ​​and clinical diagnosis is sensitive to linear changes. This allows the deviation of the methodology from the target traceability node to provide reliable guidance for physicians' clinical diagnosis through quantitative numerical analysis.

[0048] Preferably, the two risk value calculation methods in steps S3-4 can be used in combination, with the consistency assessment method promoting the discovery of traceability nodes, and the overall deviation magnitude calculation method serving as the data basis for clinical diagnosis.

[0049] S4. New traceability nodes are generated based on the determined risk values ​​and recorded as tag information in the corresponding clinical test results of the traceability data management platform.

[0050] In step S4, new source nodes are generated based on the determined risk values, which specifically includes the following steps: S4-1. Determine the source node to be excavated as the target source node; S4-2. Select methodologies whose risk values ​​are higher than a preset risk difference threshold from the target traceability nodes, and use them as target methodologies; S4-3. Find clinical test results that were detected using the target methodology and whose labels contain the target source node, and use these results as mining results. Then, summarize the mining results into a mining dataset. S4-4. Perform feature analysis on the source nodes other than the target source node in the mining results of the mining dataset, and extract multiple common features; S4-5. Perform secondary verification on the extracted common features, and use the common features that pass the secondary verification as new tracing nodes.

[0051] In this embodiment of the invention, common features of target tracing nodes are extracted through feature analysis. After determining the target tracing nodes, the corresponding target methodologies are obtained through risk value screening. Based on the target methodologies and target tracing nodes, the clinical test results that need to be mined are further determined and summarized into a mining dataset. Then, characteristic analysis is performed on the mining dataset to obtain common features. The feature analysis process preferably uses a deep learning model, such as a graph neural network, graph attention network, or other graph neural networks. Graph neural networks can establish a heterogeneous graph by treating target tracing nodes and target methodologies as entities and risk values ​​as relationships. Then, through multi-layer propagation, the most relevant feature nodes are identified and output as common features.

[0052] After obtaining common characteristics, professional medical personnel conduct secondary verification of these characteristics. For example, they can be extended to various medical entities and feedback can be collected. Common characteristics that pass the secondary verification can be used as new traceability nodes, thereby enriching and updating the traceability nodes.

[0053] S5. Output clinical test results with traceability nodes.

[0054] When used clinically, the traceability data management platform of this invention outputs clinical test results with traceability nodes to doctors. These results can be output in report form, including the original test data, traceability nodes (brand, methodology, reagents, etc.), conversion values ​​to standard test curves, and the risk level corresponding to the traceability node. Since clinical test results have a certain time sensitivity and may gradually deviate from valid values ​​as standard test curves and traceability nodes are updated, in some embodiments, a traceability code can be added to the clinical test results. This code allows for the recalculation and display of conversion values ​​and mutual recognition risk levels, dynamically adapting to market and clinical needs.

[0055] In summary, the embodiments of the present invention, by integrating standard test curves obtained from various samples, instruments, reagents, and methodologies, can effectively integrate the contribution values ​​of various methodologies and eliminate bias caused by over-reliance on a single method. The clinical test results provided with traceability nodes can provide risk warnings for the testing processes of other methodologies, making the clinical test results of other methodologies predictable and providing reliable data support for doctors' treatment recommendations.

[0056] Figure 4This is a schematic diagram of the electronic device proposed in the second embodiment of the present invention. In this embodiment, the memory stores program instructions for implementing the method for mutual recognition of clinical test results based on technical traceability in any of the above embodiments. The processor executes the program instructions stored in the memory to perform mutual recognition of clinical test results based on technical traceability. The processor may also be referred to as a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0057] The methods described in the first embodiment of the present invention are applicable to the embodiments of the present electronic device. The specific functions implemented by the embodiments of the present electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0058] Figure 5 This is a schematic diagram of the structure of a computer-readable storage medium according to the third embodiment of the present invention. The computer-readable storage medium of the fourth embodiment of the present invention stores program instructions capable of implementing the above-described method for mutual recognition of clinical test results based on technical traceability. These program instructions can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0059] The methods described in the first embodiment of the present invention are applicable to the computer-readable storage medium embodiment. The specific functions implemented by the computer-readable storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0060] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the method for mutual recognition of clinical test results based on technical traceability provided in the above embodiment.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0062] Those skilled in the art will understand that modules in the device of the embodiments of the present invention can be adaptively modified and placed in one or more devices different from those embodiments. Modules, units, or components in the embodiments of the present invention can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the corresponding claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the corresponding claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0063] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0064] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0065] Furthermore, the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. In particular, for embodiments such as apparatus and devices, since they are basically similar to the method embodiments, the relevant parts can be referred to the description of the method embodiments. The apparatus, devices, and other embodiments described above are merely illustrative, and the modules, units, etc., described as separate components may or may not be physically separate, that is, they may be located in one place or distributed in multiple places, such as nodes in a system network. Specifically, some or all of the modules and units can be selected according to actual needs to achieve the purpose of the above-described embodiment solutions. Those skilled in the art can understand and implement this without creative effort.

[0066] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0067] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0068] Furthermore, the terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this invention can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this invention, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly specified in the embodiments.

[0069] In embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of the present invention may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0070] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention. Other embodiments of the present invention will readily conceive of by considering the specification and practicing the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

Claims

1. A method for mutual recognition of clinical test results based on technical traceability, characterized in that, Includes the following steps: Establish a traceability data management platform and input clinical test results obtained by various methodologies into the traceability data management platform. Each clinical test result contains multiple tag information as traceability nodes. Based on the clinical test results in the traceability data management platform, a standard test curve is established, and a mapping relationship between each methodology and the standard test curve is generated. Determine the risk value of each methodology for each tracing node; New traceability nodes are generated based on the determined risk values ​​and recorded as tag information in the corresponding clinical test results on the traceability data management platform. Output clinical test results with traceability nodes.

2. The method for mutual recognition of clinical test results based on technical traceability according to claim 1, characterized in that, The methodology refers to the technical path used when testing the sample; the traceability node includes sample information, testing instrument information, testing reagent information, and testing methodology information. The source tracing node is determined through the following steps: Obtain the source node rules through a preset rule base; The source tracing node rules are used to perform text matching on clinical test results to filter out the target text that matches the results. Establish a traceability node as a label for clinical test results based on the target text.

3. The method for mutual recognition of clinical test results based on technical traceability according to claim 1, characterized in that, The establishment of a standard test curve based on clinical test results from the traceability data management platform includes the following steps: Prepare standard test samples; The standard test samples are tested using different methodologies, and the clinical test results obtained from the different methodologies are summarized to form a standard dataset. Curve fitting was performed based on the standard dataset, using the concentration of the standard test sample and the mean of the clinical test results as references to obtain the standard test curve.

4. The method for mutual recognition of clinical test results based on technical traceability according to claim 1, characterized in that, The process of generating the mapping relationship between each methodology and the standard test curve specifically includes the following steps: The deviation curve is obtained by calculating the deviation between the clinical test results obtained by each methodology in the standard dataset and the standard test curve. The deviation curve serves as a mapping relationship between the clinical test results and the corresponding methodology and the standard test curve.

5. The method for mutual recognition of clinical test results based on technical traceability according to claim 1, characterized in that, Determining the risk value of each methodology for each tracing node specifically includes the following steps: Identify the target tracing nodes and prepare tracing samples based on the target tracing nodes; Different methodologies were used to test the traced samples, resulting in multiple sets of clinical test results for the traced samples. The clinical test results of the source samples were transformed using the mapping relationships corresponding to different methodologies, and the transformation results were obtained and a transformation dataset was established. The risk value for each methodology at each tracing node is calculated based on the transformed dataset.

6. A method for mutual recognition of clinical test results based on technical traceability according to claim 5, characterized in that, The calculation of the risk value for each methodology for each source tracing node based on the transformed dataset specifically includes the following steps: Determine the range of risk benchmark values; For each transformation result in the transformation dataset, count the number of other transformation results in the transformation dataset that fall within the range of the risk benchmark value centered on that transformation result. The ratio of the number of transformation results within the risk benchmark range to the total number of transformation results in the transformation dataset is used as the risk value of the methodology corresponding to the transformation result for the target tracing node.

7. A method for mutual recognition of clinical test results based on technical traceability according to claim 5, characterized in that, The calculation of the risk value for each methodology for each source tracing node based on the transformed dataset specifically includes the following steps: Calculate the overall mean of the transformation results in the transformed dataset; The deviation of each transformation result in the transformed dataset from the overall mean is taken as the risk value of the corresponding methodology for the target tracing node.

8. A method for mutual recognition of clinical test results based on technical traceability according to claim 1, characterized in that, The process of generating new source nodes based on the determined risk values ​​specifically includes the following steps: The source node to be explored is identified as the target source node; Methodologies with risk values ​​higher than a preset risk difference threshold are selected from the target traceability nodes and used as the target methodologies. Find clinical test results that were detected using the target methodology and whose labels contain the target source node, and use these results as mining results. Then, summarize the mining results into a mining dataset. Feature analysis was performed on the source nodes other than the target source node in the mining results of the data set, and multiple common features were extracted; The extracted common features are then validated a second time, and the common features that pass the second validation are used as new tracing nodes.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement a method for mutual recognition of clinical test results based on technical traceability as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement a method for mutual recognition of clinical test results based on technical traceability as described in any one of claims 1-8.

Images