Cytokine detection data processing method, device, terminal and storage medium

By obtaining cytokine detection data and medical record information, determining the reference range of the detection items and normalizing it, the problem of inaccurate analysis and processing in the prior art is solved, and more accurate and comprehensive cytokine detection data analysis is achieved, enhancing the Clinical reference value.

CN118039176BActive Publication Date: 2024-11-05HEBEI PROVINCIAL CHILDRENS HOSPITAL (HEBEI PROVINCIAL FIFTH PEOPLES HOSPITAL HEBEI PROVINCIAL INST OF PEDIATRICS)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410247049.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-05
Publication Date
2024-11-05
Estimated Expiration
2044-03-05

AI Technical Summary

Technical Problem

The analysis and processing conclusions of cytokine detection data in the prior art are not accurate and comprehensive enough, and the actual clinical characteristics of the target object and the correlation between the detection items cannot be considered.

Method used

By obtaining the cytokine detection data and medical record information of the target object, determining the reference range of each detection item, normalizing the processing, and combining the medical record information to calculate the comprehensive abnormal scores to provide more accurate and comprehensive analysis and processing conclusions.

Benefits of technology

It improves the accuracy and comprehensiveness of the analysis and processing conclusions of cytokine detection data, enhances the clinical reference value, and can better reflect the current condition of the target object.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118039176B_ABST
    Figure CN118039176B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device, terminal and storage medium for processing cytokine detection data. The method includes: obtaining cytokine detection data and medical record information of a target object; determining reference ranges corresponding to each detection item in the cytokine detection data based on the medical record information; determining abnormal detection items based on the detection results of each detection item and the reference ranges corresponding to each detection item; normalizing the detection results of each detection item in the cytokine detection data based on the reference range to obtain normalized vector data of the detection results of each detection item; determining the comprehensive abnormal score of the cytokine detection data of the target object based on the normalized vector data of the detection results and the medical record information. The present invention can improve the scoring accuracy and comprehensiveness of cytokine detection data, and has greater reference value for clinical practice.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a method, device, terminal and storage medium for processing cytokine detection data. Background Art

[0002] Cytokines are a class of small molecule proteins with a wide range of biological activities that are synthesized and secreted by immune cells (such as monocytes, macrophages, T cells, B cells, NK cells, etc.) and certain non-immune cells (endothelial cells, epidermal cells, fibroblasts, etc.) upon stimulation. Cytokines generally regulate cell growth, differentiation and effects by binding to corresponding receptors, thereby regulating immune responses. As a sensitive indicator of inflammation, cytokine detection is an ideal monitoring indicator for precision medicine, personalized treatment and rational drug use. Timely and dynamic monitoring of the changing levels of cytokines in the target subjects and quantitative detection can help guide clinical evaluation of disease severity, efficacy and prognosis.

[0003] However, the current analysis and processing method for cytokine detection data is often to compare the test result value directly with the standard value range (from healthy people). The inventors of this application found that, on the one hand, this comparison result only means that the target object is abnormal compared with the cytokine detection data of healthy people, without considering the current actual clinical characteristics of the target object; on the other hand, this comparison result can only give the evaluation results of each single detection item, and fails to consider the correlation between each detection item, and gives a comprehensive evaluation result, which leads to the current analysis and processing conclusions of cytokine detection data being not accurate and comprehensive enough, and the clinical reference value is not high enough. Summary of the invention

[0004] The present invention provides a method, device, terminal and computer-readable storage medium for processing cytokine detection data to solve the problem that the analysis and processing conclusions of cytokine detection data in the prior art are not accurate and comprehensive enough.

[0005] In a first aspect, the present invention provides a method for processing cytokine detection data, comprising:

[0006] Acquire cytokine detection data of target subjects;

[0007] Obtain the target subject’s medical records;

[0008] Determine the reference range corresponding to each test item in the cytokine test data based on the medical record information;

[0009] Determine the abnormal test items based on the test results of each test item and the reference ranges corresponding to each test item;

[0010] Normalizing the test results of each test item in the cytokine test data based on the reference range to obtain normalized vector data of the test results of each test item;

[0011] The comprehensive abnormality score of the target subject's cytokine detection data is determined based on the normalized vector data of the detection results and the medical record information.

[0012] In a second aspect, the present invention provides a device for processing cytokine detection data, comprising:

[0013] A first acquisition unit, used to acquire cytokine detection data of a target object;

[0014] A second acquisition unit is used to acquire the medical record information of the target object;

[0015] A first determination unit, configured to determine reference ranges corresponding to respective detection items in the cytokine detection data based on the medical record information;

[0016] A second determination unit determines the detection abnormality item based on the detection result of each detection item and the reference range corresponding to each detection item;

[0017] A first processing unit is used to normalize the detection results of each detection item in the cytokine detection data based on the reference range to obtain normalized vector data of the detection results of each detection item;

[0018] The second processing unit is used to determine the comprehensive abnormality score of the target object's cytokine detection data based on the detection result normalized vector data and the medical record information.

[0019] In a third aspect, the present invention provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for processing cytokine detection data as described in the first aspect or any possible implementation of the first aspect are implemented.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for processing cytokine detection data as described in the first aspect or any possible implementation of the first aspect.

[0021] The present invention provides a method, device, terminal and storage medium for processing cytokine detection data, and determines the reference range corresponding to each detection item in the cytokine detection data through the medical record information of the target object. On the one hand, the detection abnormal items are determined based on the detection results of each detection item and the reference range corresponding to each detection item; on the other hand, the detection results of each detection item in the cytokine detection data are normalized based on the reference range to obtain the normalized vector data of the detection results of each detection item, and finally the analysis and processing conclusion of the target object cytokine detection data is determined based on the normalized vector data of the detection results and the medical record information. It can be seen that the processing method of cytokine detection data proposed in this application determines the reference range corresponding to each detection item in the cytokine detection data based on the medical record information, thereby taking into account the actual clinical characteristics of the target object at present, and at the same time determines the analysis and processing conclusion of the target object cytokine detection data based on the normalized vector data of the detection results and the medical record information, avoiding the influence of different magnitudes of the data of each detection item on the conclusion, and comprehensively analyzing and considering the correlation between multiple detection items, a comprehensive abnormal evaluation can be given. Therefore, the accuracy and comprehensiveness of the analysis and processing conclusion of the cytokine detection data are improved, and it has greater clinical reference value. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 This is an application scenario diagram of the method for processing cytokine detection data provided by an embodiment of the present invention;

[0024] Figure 2 is a flow chart of the implementation of the method for processing cytokine detection data provided by an embodiment of the present invention;

[0025] Figure 3 is a flow chart of the implementation of the method for processing cytokine detection data provided by an embodiment of the present invention;

[0026] Figure 4 is a schematic diagram of the structure of a device for processing cytokine detection data provided by an embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0029] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0030] Figure 1 This is an application scenario diagram of the method for processing cytokine detection data provided by an embodiment of the present invention. Figure 1 As shown, the processing terminal is used to execute the processing method of cytokine detection data provided by the embodiment of the present invention. The processing terminal obtains the cytokine detection data in the cytokine detection report, obtains the medical record information of the target object through the electronic medical record, and the processing terminal determines the reference range corresponding to each detection item in the cytokine detection data based on the medical record information. On the one hand, the detection abnormal items are determined based on the detection results of each detection item and the reference range corresponding to each detection item; because the reference range corresponding to each detection item is determined based on the medical record information of the target object, it is more referenceable than the reference range determined based on the healthy population in the related art; on the other hand, the processing terminal also performs detection of each detection item in the cytokine detection data based on the reference range. The results are normalized to obtain normalized vector data of the test results of each test item, and then the cytokine test results are evaluated based on the normalized vector data of the test results and the medical record information, and the comprehensive abnormal score of the cytokine test data of the target object is determined and output. It can be seen that the present invention determines the analysis and processing conclusion of the cytokine test data of the target object based on the normalized vector data of the test results and the medical record information, thereby avoiding the influence of the different magnitudes of the data of each test item on the conclusion. In addition, the comprehensive analysis takes into account the correlation between multiple test items and the actual current clinical characteristics of the target object, so that the comprehensive evaluation given has higher accuracy and comprehensiveness, which is conducive to providing better clinical reference value for medical personnel.

[0031] See also Figure 2 , which shows a flowchart of the implementation method of the cytokine detection data processing method provided by an embodiment of the present invention, which is described in detail as follows:

[0032] In step 201, cytokine detection data of a target object is obtained.

[0033] In the embodiment of the present invention, the cytokine detection data refers to the cytokine detection result data of the target object, which can be obtained by extracting data from the cytokine detection report of the target object. The target object refers to the person who performs the cytokine detection.

[0034] In one embodiment, the detection items in the above cytokine detection data may include: interleukin IL-1, interleukin IL-2, interleukin IL-4, interleukin IL-5, interleukin IL-6, interleukin IL-8, interleukin IL-10, interleukin IL-12, interleukin IL-17, tumor necrosis factor TNF-α, tumor necrosis factor TNF-β, interferon IFN-α and interferon IFN-γ.

[0035] In an embodiment of the present invention, the processing terminal obtains a cytokine detection report, and extracts cytokine detection data from the cytokine detection report, and the cytokine detection data includes the identification number or identification name of the target object, gender, and the detection results of each detection item. Exemplarily, the cytokine detection data of a target object may include: hospitalization number: 123456; name: Zhang San; gender: male; detection items: interleukin IL-1β is 4.46, interleukin IL-2 is 4.36, interleukin IL-4 is 2.21, interleukin IL-5 is 3.16, interleukin IL-6 is 428.99, interleukin IL-8 is 173.98, interleukin IL-10 is 18.1, interleukin IL-12 is 3.6, interleukin IL-17 is 3.51, interferon IFN-α is 4.53, and interferon IFN-γ is 4.1.

[0036] In practical applications, cytokines can be divided into interleukins, interferons, tumor necrosis factor superfamily, colony stimulating factors, chemokines, growth factors, etc. Interleukins (abbreviated as interleukins, abbreviated as IL) refer to lymphokines that interact between white blood cells or immune cells. They belong to the same category as blood cell growth factors. The two coordinate and interact with each other to complete the hematopoietic and immune regulation functions. Interleukins play an important role in transmitting information, activating and regulating immune cells, mediating T and B cell activation, proliferation and differentiation, and inflammatory responses.

[0037] Interferon (IFN) is a family of multifunctional cytokines with broad-spectrum antiviral, immunomodulatory, anti-angiogenic, anti-tumor, and anti-proliferative properties, mainly including α, β, and γ.

[0038] IFN-γ is not only a highly effective antiviral bioactive substance, but also a lymphokine with a wide range of effects. It regulates immune and inflammatory responses and can promote the activation, growth and differentiation of most cells. Immune regulation can mediate the host's defense function against pathogens and also play an important role in other physiological and pathological processes, such as metabolic syndrome, cardiovascular disease, tumorigenesis, etc.

[0039] Interferon (IFN) is a family of multifunctional cytokines with broad-spectrum antiviral, immunomodulatory, anti-angiogenic, anti-tumor, and anti-proliferative properties. There are mainly three types: α, β, and γ. Under natural conditions, interferon-α is a very important immune protective cytokine for humans to cope with viral infections. Interferon-α has broad-spectrum antiviral and immunomodulatory effects. Its broad-spectrum antiviral effect is not that interferon-α directly kills viruses, but that it stimulates cells to express a variety of antiviral proteins by binding to receptors on the surface of human cells, affecting cell metabolic processes, including degrading viral RNA, and inhibiting the synthesis of viral RNA and proteins. Since the effect of antiviral proteins is not directed at specific viruses, IFNα has a broad-spectrum antiviral activity. For cells that are not infected with viruses, interferon-α establishes an "antiviral state" by inducing cells to produce antiviral proteins, which can prevent cells from being infected by viruses.

[0040] It can be seen that different types of cytokines have different effects. For example, some have anti-inflammatory effects, some have pro-inflammatory effects, and some have both anti-inflammatory and pro-inflammatory effects. They just show different effects at different stages. In actual clinical practice, the patient's actual clinical symptoms are often not the result of a single cytokine, but the result of the combined action of various cytokines.

[0041] In step 202, the medical record information of the target object is obtained.

[0042] In the embodiment of the present invention, the medical record information of the target object refers to the target object's illness recorded by the medical staff when they interview the target object. The medical record information may also include other inspection and quarantine information. The content recorded in the medical record information may reflect the target object's physical condition in person, and may include the course of illness, time of illness, symptoms, etc. For example, if the target object has a fever symptom, the time when the fever started, the current body temperature, the historical body temperature, etc. The medical record information may be an electronic medical record, and the processing terminal obtains the target object's medical record information through the electronic medical record.

[0043] In step 203, reference ranges corresponding to respective detection items in the cytokine detection data are determined based on the medical record information.

[0044] When judging abnormalities in test results in related technologies, the reference range of healthy people is often used. In fact, if the target object is in the course of illness, some of its test results are bound to be abnormal. Patients can only think that the farther the test results are from the standard reference range, the more abnormal the test results are. In fact, human illness is a time process, and test items in different stages of the disease will show a certain degree of abnormal changes. If no abnormal changes are shown, it may be abnormal. Therefore, if there are corresponding reference ranges for test results at different stages of the disease based on the patient's disease course, such comparative conclusions will be more conducive to intuitively reflecting the current physical abnormalities of the target object.

[0045] In an embodiment of the present invention, the target object's current disease stage can be determined based on the target object's medical record information. Different disease stages are pre-set with different reference ranges for detection items (this data can be obtained based on expert experience or statistical analysis of massive historical data). The reference ranges corresponding to each detection item can be obtained based on the target object's current disease stage. For example, the course of disease can be divided into early, middle and late stages, and each detection item has a corresponding standard reference range in the three disease stages. In an embodiment of the present invention, the processing terminal can first obtain the target object's electronic medical record, extract the target object's medical record information from the electronic medical record, and then determine the target object's disease stage based on the medical record information, and finally determine the reference ranges corresponding to each detection item.

[0046] In one embodiment, the above step 203 may specifically include: extracting the disease stage characteristics of the target object based on the medical record information; and determining the reference ranges corresponding to each detection item based on the disease stage characteristics.

[0047] In this embodiment, medical personnel need to indicate the target subject's disease course stage in the target subject's medical record during the preliminary consultation, and the processing terminal identifies the disease course stage information and uses it as the disease stage feature to determine the reference range. In another embodiment, the target subject's disease cause and onset time may also be recorded in the medical record information, and the processing terminal automatically calculates the patient's disease course based on the target subject's disease cause, the date of detection, and the onset time.

[0048] In step 204, detection abnormal items are determined based on the detection results of each detection item and the reference ranges corresponding to each detection item.

[0049] In the embodiment of the present invention, after determining the reference ranges corresponding to the respective detection items, the actual detection results may be compared with the reference ranges, and the detection items whose detection results exceed the set thresholds of the reference ranges may be regarded as detection abnormalities.

[0050] In step 205, the detection results of each detection item in the cytokine detection data are normalized based on the reference range to obtain normalized vector data of the detection results of each detection item.

[0051] In the embodiment of the present invention, it is necessary to comprehensively analyze and consider the correlation between multiple detection items, and give a comprehensive abnormality evaluation. However, there are large differences in the magnitude of each detection item, which is conducive to the fact that some detection items have a dozen results, while some detection items have hundreds of results. It is necessary to normalize the results of each detection item to avoid excessive weights of high-level detection items, which affect the accuracy of the comprehensive evaluation results. In the related art, normalization is often performed based on the mean, variance, etc. of data statistics. The solution of the present invention is applied to the detection scenario, and the detection results of the detection items have corresponding reference ranges. The reference ranges corresponding to each detection item can be normalized to obtain normalized vector data of the detection results of each detection item.

[0052] For example, the test result value of a test item A is A 实际 , the reference range is (A min , A max ), can be based on the formula Calculate the normalized vector A of the detection item A g .

[0053] In step 206, the comprehensive abnormality score of the target subject's cytokine detection data is determined based on the detection result normalized vector data and the medical record information.

[0054] In an embodiment of the present invention, the normalized vector data of each test result is combined with relevant medical record information as input, and the cytokine detection data can be analyzed and processed using a trained deep recognition model to obtain a comprehensive abnormality score for the target object's cytokine detection data.

[0055] refer to Figure 3 , which shows that the embodiment of the present invention provides Figure 2 A flowchart of an implementation of step 206 in the embodiment shown is as follows: Figure 3 As shown, the implementation steps are as follows:

[0056] In step 2061, physiological index characteristics of the target object are extracted based on the medical record information;

[0057] In step 2062, sparse coding and feature embedding processing are performed on the physiological indicator features to obtain normalized vector data of the physiological indicator;

[0058] In step 2063, data fusion is performed on the normalized vector data of the detection result and the normalized vector data of the physiological index to obtain standardized vector data;

[0059] In step 2064, the standardized vector data is used as input, and a comprehensive evaluation is performed using the trained deep model to obtain a comprehensive abnormality score for the target object's cytokine detection data.

[0060] In this embodiment, the processing terminal can extract physiological index characteristics of the target object based on the medical record information, which may specifically include: whether the heart rate is abnormal, whether the consciousness is unclear, whether the patient has a high fever, whether the body temperature does not rise, and whether the patient is in shock. These indicators are associated with the cytokine detection results of the target object and can be used as input items to increase the accuracy of the comprehensive abnormal analysis of the cytokine detection results.

[0061] In practical applications, each item in the physiological indicator feature is unified into a binary classification of "yes" and "no", and "yes" and "no" represent abnormal and normal physical conditions, respectively. The unified data standard can help improve the training speed in the later stage and convert it into standardized vector data. The physiological indicator feature is a binary data. Sparse coding and feature embedding processing can be performed on it to obtain normalized vector data of physiological indicators. The normalized vector data of the test results and the normalized vector data of physiological indicators are fused to increase the data dimension, which is more conducive to improving the comprehensiveness and accuracy of judgment and analysis, and obtaining standardized vector data. Taking the standardized vector data as input and using the trained deep model for comprehensive evaluation, the comprehensive abnormality score of the target object's cytokine detection data can be obtained. The comprehensive abnormality score can correspond to different abnormality levels. For example, a comprehensive abnormality score of less than 5 points may mean that the target subject's condition is progressing normally, the prognosis is good, and the dosage can be appropriately reduced; a comprehensive abnormality score of greater than 5 points means that the target subject's condition is more serious than that of patients with the same course of disease, and may require attention in terms of nursing and medication; a comprehensive abnormality score of greater than 8 points means that the target subject's condition is very serious compared with patients with the same course of disease, and may require special attention in terms of nursing and medication.

[0062] In the embodiment of the present invention, the above-mentioned data fusion is a process of data dimensionality upgrading, which adds physiological index normalized vector data to the dimension of detection result normalized vector data, thereby improving the comprehensiveness and accuracy of judgment and analysis results.

[0063] In one embodiment, the above-mentioned data fusion of the normalized vector data of the detection result and the normalized vector data of the physiological index to obtain the standardized vector data can be specifically implemented based on the following steps:

[0064] Performing data fusion on the normalized vector data of the test results and the normalized vector data of the physiological indicators to obtain high-dimensional normalized vector data;

[0065] Determine the amount of information in each dimension of high-dimensional normalized vector data;

[0066] The high-dimensional normalized vector data is subjected to dimensionality reduction processing according to the amount of information, and data of a preset number of dimensions with a large amount of information is selected as the standardized vector data.

[0067] In an embodiment of the present invention, the step of data fusion is a process of data dimensionality upgrading. Although the accuracy of the data is improved after the dimensionality upgrade, it also brings about the problem of increased training workload. In this embodiment, for the high-dimensional normalized vector data obtained after the fusion, the information amount of the high-dimensional normalized vector data of each dimension can be determined by using the information entropy analysis method, and then the high-dimensional normalized vector data is subjected to dimensionality reduction processing according to the amount of information, and data of a preset number of dimensions with a larger amount of information is selected as the standardized vector data. For example, the dimensional data with an amount of information less than a certain threshold is cut off, and the dimensional data with an amount of information greater than a certain threshold is retained, thereby ensuring the accuracy and comprehensiveness of the information and helping to reduce the amount of training for the deep model.

[0068] In an embodiment of the present invention, the above-mentioned deep model is pre-trained and can output a deep neural network model of comprehensive anomaly score after analyzing and processing the input standardized vector data.

[0069] In one embodiment, the training process of the above-mentioned deep model may include:

[0070] Obtaining a cytokine detection data sample set;

[0071] Generate an error random number within a preset error range, and use the error random number to expand the historical data sample set to obtain an expanded data sample;

[0072] Divide the historical data sample set into N subsets;

[0073] Add a preset proportion of extended data samples to each subset, where the preset proportion is no greater than 10%;

[0074] One of the N subsets after adding samples is used as the validation set, and the remaining subsets are used as the training set to train the pre-built neural network model. This cycle is repeated N times until each subset has been used as the validation set in the training process. The model with the smallest loss function is taken as the trained model for each training.

[0075] The average of the N training output results is taken as the final output of the deep model.

[0076] This embodiment provides a training process for a deep model to ensure the accuracy of the deep model output. In addition, in the actual cytokine detection application environment, errors in the data collection process are inevitable; and, limited by external conditions such as detection and analysis equipment and test methods, laboratory test results will inevitably have errors. Therefore, even if each test has its corresponding quality control and clinical test operation specifications, it is obviously difficult to obtain completely accurate test results in the real world, and the detection accuracy is still within a certain range. However, a very small accuracy range may lead to erroneous estimation results, which undoubtedly causes the inaccuracy of cytokine detection results. This embodiment increases the generalization ability of the model to new data by increasing a certain proportion of error random numbers within the allowable error range in the training samples to generate extended samples to participate in the training process of the model, so that the model also has accurate analysis and processing capabilities for data with certain detection errors.

[0077] The present invention provides a method for processing cytokine detection data, which determines the reference range corresponding to each detection item in the cytokine detection data through the medical record information of the target object, on the one hand, determines the detection abnormal item based on the detection result of each detection item and the reference range corresponding to each detection item; on the other hand, the detection result of each detection item in the cytokine detection data is normalized based on the reference range to obtain the detection result normalized vector data of each detection item, and finally determines the analysis and processing conclusion of the target object cytokine detection data based on the detection result normalized vector data and the medical record information. It can be seen that the method for processing cytokine detection data proposed in this application determines the reference range corresponding to each detection item in the cytokine detection data based on the medical record information, thereby taking into account the actual clinical characteristics of the target object at present, and at the same time determines the analysis and processing conclusion of the target object cytokine detection data based on the detection result normalized vector data and the medical record information, avoiding the influence of different magnitudes of the data of each detection item on the conclusion, and comprehensively analyzing and considering the correlation between multiple detection items, a comprehensive abnormal evaluation can be given. Therefore, the accuracy and comprehensiveness of the analysis and processing conclusion of the cytokine detection data are improved, and it has greater clinical reference value.

[0078] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0079] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0080] Figure 4A schematic diagram of the structure of a device for processing cytokine detection data provided by an embodiment of the present invention is shown. For ease of description, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0081] like Figure 4 As shown, the cytokine detection data processing device 4 includes: a first acquisition unit 41, a second acquisition unit 42, a first determination unit 43, a second determination unit 44, a first processing unit 45 and a second processing unit 46.

[0082] A first acquisition unit 41 is used to acquire cytokine detection data of a target object;

[0083] A second acquisition unit 42 is used to acquire the medical record information of the target object;

[0084] A first determination unit 43 is used to determine the reference range corresponding to each detection item in the cytokine detection data based on the medical record information;

[0085] A second determination unit 44 determines the detection abnormal items based on the detection results of each detection item and the reference ranges corresponding to each detection item;

[0086] A first processing unit 45 is used to normalize the detection results of each detection item in the cytokine detection data based on the reference range to obtain normalized vector data of the detection results of each detection item;

[0087] The second processing unit 46 is used to determine the comprehensive abnormality score of the target subject's cytokine detection data based on the detection result normalized vector data and the medical record information.

[0088] In one possible implementation, the detection items in the cytokine detection data include: interleukin IL-1, interleukin IL-2, interleukin IL-4, interleukin IL-5, interleukin IL-6, interleukin IL-8, interleukin IL-10, interleukin IL-12, interleukin IL-17, tumor necrosis factor TNF-α, tumor necrosis factor TNF-β, interferon IFN-α and interferon IFN-β.

[0089] In a possible implementation, the processing device 4 may further include:

[0090] A disease stage feature extraction unit, used to extract disease stage features of a target object based on medical record information;

[0091] Correspondingly, the first determination unit 43 is specifically configured to determine the reference ranges corresponding to the respective detection items based on the disease stage characteristics.

[0092] In a possible implementation, the processing device 4 may further include:

[0093] A physiological index feature extraction unit, used to extract physiological index features of a target object based on medical record information;

[0094] A normalization processing unit, used for performing sparse coding and feature embedding processing on physiological index features to obtain normalized vector data of physiological indexes;

[0095] A standardized vector data processing unit is used to perform data fusion on the normalized vector data of the test results and the normalized vector data of the physiological indicators to obtain standardized vector data;

[0096] The second processing unit 46 is specifically configured to use the standardized vector data as input, perform comprehensive evaluation using the trained deep model, and obtain a comprehensive abnormality score for the target object's cytokine detection data.

[0097] In a possible implementation, the physiological indicator characteristics include: whether the heart rate is abnormal, whether the consciousness is unclear, whether there is a high fever, whether the body temperature does not rise, and whether there is shock.

[0098] In a possible implementation, the processing device 4 may further include:

[0099] A data fusion unit, used for fusing the normalized vector data of the detection result and the normalized vector data of the physiological index to obtain high-dimensional normalized vector data;

[0100] An information amount determination unit, used to determine the information amount of high-dimensional normalized vector data of each dimension;

[0101] The first processing unit 45 is specifically used to perform dimensionality reduction processing on the high-dimensional normalized vector data according to the amount of information, and select data of a preset number of dimensions with a larger amount of information as the standardized vector data.

[0102] In a possible implementation, the processing device 4 may further include:

[0103] The model training unit is used to obtain a cytokine detection data sample set; generate an error random number within a preset error range, and use the error random number to expand the historical data sample set to obtain an extended data sample; divide the historical data sample set into N subsets; add a preset proportion of extended data samples to each subset, wherein the preset proportion is not greater than 10%; use one of the N subsets after adding the samples as a validation set, and the remaining subsets as training sets to train the pre-constructed neural network model, repeating N times until each subset has been used as a validation set in the training process, and each training takes the model with the smallest loss function as the trained model; and the average value of the output results of N training times is used as the final output of the deep model.

[0104] The present invention provides a processing device for cytokine detection data, which determines the reference range corresponding to each detection item in the cytokine detection data through the medical record information of the target object. On the one hand, the detection abnormal items are determined based on the detection results of each detection item and the reference range corresponding to each detection item; on the other hand, the detection results of each detection item in the cytokine detection data are normalized based on the reference range to obtain the normalized vector data of the detection results of each detection item, and finally the analysis and processing conclusion of the target object cytokine detection data is determined based on the normalized vector data of the detection results and the medical record information. It can be seen that the processing method of cytokine detection data proposed in this application determines the reference range corresponding to each detection item in the cytokine detection data based on the medical record information, thereby taking into account the actual clinical characteristics of the target object at present, and at the same time determines the analysis and processing conclusion of the target object cytokine detection data based on the normalized vector data of the detection results and the medical record information, avoiding the influence of different magnitudes of the data of each detection item on the conclusion, and comprehensively analyzing and considering the correlation between multiple detection items, and can give a comprehensive abnormal evaluation. Therefore, the accuracy and comprehensiveness of the analysis and processing conclusion of the cytokine detection data are improved, and it has greater clinical reference value.

[0105] Figure 5 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 5 As shown, the terminal 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above-mentioned method for processing cytokine detection data are implemented, for example Figure 2 Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 4 The functions of the units 41 to 46 are shown.

[0106] Exemplarily, the computer program 52 may be divided into one or more modules / units, which are stored in the memory 51 and executed by the processor 50 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 52 in the terminal 5. For example, the computer program 52 may be divided into Figure 4 Modules / units 41 to 46 are shown.

[0107] The terminal 5 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 It is only an example of terminal 5 and does not constitute a limitation on terminal 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0108] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0109] The memory 51 may be an internal storage unit of the terminal 5, such as a hard disk or memory of the terminal 5. The memory 51 may also be an external storage device of the terminal 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 5. Further, the memory 51 may also include both an internal storage unit of the terminal 5 and an external storage device. The memory 51 is used to store the computer program and other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0110] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0113] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the processing method embodiment of each cytokine detection data can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0117] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for processing cytokine detection data, characterized in that: include: Acquire cytokine detection data of target subjects; Obtain the target's medical records; Determine the reference range corresponding to each test item in the cytokine test data based on the medical record information; Determine the abnormal test items based on the test results of each test item and the reference ranges corresponding to each test item; Normalizing the test results of each test item in the cytokine test data based on the reference range to obtain normalized vector data of the test results of each test item; Determine a comprehensive abnormality score of the target subject's cytokine test data based on the test result normalized vector data and medical record information; Determining the reference ranges corresponding to each test item in the cytokine test data based on the medical record information includes: Extracting the disease stage characteristics of the target object based on the medical record information; the medical record information includes the course of disease, the time of illness and the symptoms; Determine the reference range corresponding to each test item based on the characteristics of the disease stage; The method of determining the comprehensive abnormality score of the target object's cytokine detection data based on the normalized vector data of the detection result and the medical record information includes: Extract physiological index characteristics of target subjects based on medical record information; Perform sparse coding and feature embedding processing on physiological index features to obtain normalized vector data of physiological indexes; Performing data fusion on the normalized vector data of the test results and the normalized vector data of the physiological indicators to obtain standardized vector data; Using the standardized vector data as input, the trained deep model is used for comprehensive evaluation to obtain the comprehensive abnormality score of the target object's cytokine detection data; The physiological indicator characteristics include: whether the heart rate is abnormal, whether the consciousness is unclear, whether there is high fever, whether the body temperature does not rise, and whether there is shock.

2. The method for processing cytokine detection data according to claim 1, characterized in that: The various test items in the cytokine test data include: Interleukin IL-1, interleukin IL-2, interleukin IL-4, interleukin IL-5, interleukin IL-6, interleukin IL-8, interleukin IL-10, interleukin IL-12, interleukin IL-17, tumor necrosis factor TNF-α, tumor necrosis factor TNF-β, interferon IFN-α and interferon IFN-β.

3. The method for processing cytokine detection data according to claim 1, characterized in that: The step of fusing the normalized vector data of the test result and the normalized vector data of the physiological index to obtain the normalized vector data includes: Performing data fusion on the normalized vector data of the test results and the normalized vector data of the physiological indicators to obtain high-dimensional normalized vector data; Determine the amount of information in each dimension of high-dimensional normalized vector data; According to the amount of information, the high-dimensional normalized vector data is subjected to dimensionality reduction processing, and data of preset dimensions are selected in order from large to small in terms of the amount of information as the standardized vector data.

4. The method for processing cytokine detection data according to any one of claims 1 to 3, characterized in that: The training process of the deep model includes: Obtaining a cytokine detection data sample set; Generate an error random number within a preset error range, and use the error random number to expand the historical data sample set to obtain an expanded data sample; Divide the historical data sample set into N subsets; Add a preset proportion of extended data samples to each subset, where the preset proportion is no greater than 10%; One of the N subsets after adding samples is used as the validation set, and the remaining subsets are used as the training set to train the pre-built neural network model. This cycle is repeated N times until each subset has been used as the validation set in the training process. The model with the smallest loss function is taken as the trained model for each training. The average of the N training output results is taken as the final output of the deep model.

5. A device for processing cytokine detection data, characterized in that: include: A first acquisition unit, used to acquire cytokine detection data of a target object; A second acquisition unit is used to acquire the medical record information of the target object; A first determination unit, configured to determine reference ranges corresponding to respective detection items in the cytokine detection data based on the medical record information; A second determination unit, configured to determine the abnormal detection item based on the detection result of each detection item and the reference range corresponding to each detection item; A first processing unit is used to normalize the detection results of each detection item in the cytokine detection data based on the reference range to obtain normalized vector data of the detection results of each detection item; A second processing unit, configured to determine a comprehensive abnormality score of the target subject's cytokine detection data based on the detection result normalized vector data and the medical record information, wherein the comprehensive abnormality score includes a detection abnormality item and a comprehensive abnormality score; The first determining unit includes: Extracting the disease stage characteristics of the target object based on the medical record information; the medical record information includes the course of disease, the time of illness and the symptoms; Determine the reference range corresponding to each test item based on the characteristics of the disease stage; The second processing unit comprises: Extract physiological index characteristics of target subjects based on medical record information; Perform sparse coding and feature embedding processing on physiological index features to obtain normalized vector data of physiological indexes; Performing data fusion on the normalized vector data of the test results and the normalized vector data of the physiological indicators to obtain standardized vector data; Using the standardized vector data as input, the trained deep model is used for comprehensive evaluation to obtain the comprehensive abnormality score of the target object's cytokine detection data; The physiological indicator characteristics include: whether the heart rate is abnormal, whether the consciousness is unclear, whether there is high fever, whether the body temperature does not rise, and whether there is shock.

6. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for processing cytokine detection data as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for processing cytokine detection data as described in any one of claims 1 to 4 are implemented.