Method, device, electronic device and storage medium for mutual recognition of sex hormone test results
By conducting continuous time correlation analysis and regression adjustment of sex hormone test results data, the problem of differences in test results of different brands or models is solved, data quality and mutual recognition efficiency are improved, and mutual recognition of test results between medical platforms is achieved.
Patent Information
- Application Number
- CN202410245656.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-03-05
AI Technical Summary
The results of sex hormone testing for different brands or models vary, resulting in a decline in data quality and is difficult to effectively utilize in artificial intelligence technology, affecting the mutual recognition of test results between medical platforms.
By obtaining the sex hormone detection result data, statistical analysis of continuous time correlation was carried out, the target grouping time period was determined, the data group was divided, the standard curve was fitted, and the data was adjusted through regression analysis to achieve mutual recognition of the results.
The quality, efficiency and accuracy of test result data are improved, ensuring that test results can be mutually recognized between different medical platforms.
Smart Images

Figure CN118173278B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information processing technology, and in particular to a method, device, electronic device and storage medium for mutual recognition of sex hormone test results. Background Art
[0002] With the development of diagnostic medicine and the demand for evidence-based medicine, the test results of sex hormone testing projects are becoming more and more important. There are often certain differences in the test results between different brands or models, which will greatly affect the mutual recognition of test results between different medical platforms.
[0003] With the widespread application of artificial intelligence technology in the medical field, the importance of data quality has become increasingly prominent. However, since the test results of different brands or models are mixed together and piled up in large quantities, the quality of the data has been greatly reduced, making it impossible to effectively utilize historical test results and difficult to apply them in artificial intelligence technology, wasting a lot of data resources. Summary of the invention
[0004] In order to solve at least one of the technical problems existing in the above-mentioned related technologies, the embodiments of the present application propose a method, device, electronic device and storage medium for mutual recognition of sex hormone test results, which can greatly improve the data quality of the test result data, realize the mutual recognition of test results between different medical platforms, and improve the efficiency and accuracy of mutual recognition of test results.
[0005] On the one hand, the present application embodiment proposes a method for mutual recognition of sex hormone test results, the method comprising the following steps:
[0006] Obtain the test result data corresponding to the sex hormone test items;
[0007] According to a preset time scale set, a statistical analysis of continuous time association is performed on the test result data to determine multiple target grouping time periods;
[0008] Dividing the test result data according to each of the target grouping time periods to obtain a test result data group corresponding to each of the target grouping time periods;
[0009] According to the test result data, a test result standard curve is obtained by fitting;
[0010] According to the test result standard curve, regression analysis is performed on each of the test result data groups to determine the test result adjustment data corresponding to each of the test result data groups, and the test result adjustment data is used for result mutual recognition.
[0011] In some embodiments, the method further comprises the following steps:
[0012] The detection result adjustment data corresponding to each of the detection result data groups is used to train a deep learning model, and the deep learning model is used to perform detection result data analysis.
[0013] In some embodiments, the time scale set includes multiple time scales arranged in descending order, and the step of performing a statistical analysis of the continuous time association of the detection result data according to the preset time scale set to determine multiple clustering time points specifically includes:
[0014] Determine, according to each detection result data curve contained in the detection result data, curve feature node data corresponding to each detection result data curve;
[0015] Acquire a first time scale as the current time scale, and acquire each first grouping time node as the current grouping time node; the first grouping time node includes a start time node and an end time node corresponding to the detection result data;
[0016] According to the current time scale and each current grouping time node, each of the detection result data curves is divided to determine a plurality of curve data sets consisting of a plurality of the detection result data curves;
[0017] Integrate a plurality of target curve feature point data contained in each of the curve data sets to obtain a curve feature point data set corresponding to each of the curve data sets; the target curve feature point data is the curve feature node data corresponding to the detection result data curve in the curve data set;
[0018] Performing mean calculation and standard deviation calculation on each of the curve feature point data sets to obtain the mean and standard deviation corresponding to each of the curve feature point data sets;
[0019] Pairing the adjacent curve feature point data sets in each grouping time period into groups, and obtaining a plurality of curve feature data comparison groups corresponding to each grouping time period; the grouping time period is determined by each current grouping time node;
[0020] Comparatively analyzing the mean and standard deviation of each curve feature point data set in each curve feature data comparison group, and determining the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group;
[0021] When the mean fluctuation value corresponding to the curve feature data comparison group is not within a given first fluctuation threshold range, and the standard deviation fluctuation value corresponding to the curve feature data comparison group is not within a given second fluctuation threshold range, the curve feature data comparison group is determined as a target comparison group, and the data set division time node corresponding to the adjacent curve feature point data set in the target comparison group is determined as a second grouping time node;
[0022] When there are several target comparison groups, the second grouping time node corresponding to each target comparison group is added as the current grouping time node, a second time scale is obtained as the current time scale, and then the step of dividing each detection result data curve according to the current time scale and each current grouping time node to determine a plurality of curve data sets consisting of several detection result data curves is returned until there is no target comparison group; the second time scale is a time scale sequentially arranged after the current time scale in the time scale set;
[0023] When the target comparison group does not exist, the corresponding target grouping time periods are determined according to the current grouping time nodes; the target grouping time period is the time period between adjacent current grouping time nodes.
[0024] In some embodiments, the step of dividing each of the detection result data curves according to the current time scale and each of the current grouping time nodes to determine a plurality of curve data sets consisting of a plurality of the detection result data curves specifically includes:
[0025] According to each of the current grouping time nodes, a plurality of grouping time periods are determined; the grouping time period is a time period between adjacent current grouping time nodes;
[0026] According to each of the grouping time periods, a plurality of the test result data curves obtained in each of the grouping time periods are screened out from the test result data, and a pre-divided set of curve data corresponding to each of the grouping time periods is determined;
[0027] According to the current time scale, each of the curve data pre-divided sets is divided to obtain a plurality of the curve data sets corresponding to each of the curve data pre-divided sets.
[0028] In some embodiments, the step of performing comparative analysis on the mean and standard deviation of each curve feature point data set in each curve feature data comparison group to determine the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group specifically includes:
[0029] Performing difference calculation on the means of adjacent curve feature point data sets in the curve feature data comparison group to determine the mean fluctuation value;
[0030] The standard deviations of adjacent curve feature point data sets in the curve feature data comparison group are calculated to determine the standard deviation fluctuation value.
[0031] In some embodiments, the step of fitting and obtaining a test result standard curve according to the test result data specifically includes:
[0032] Obtain several preset key detection nodes;
[0033] Determine, according to each of the key detection nodes, key detection node data corresponding to each of the detection result data curves in the detection result data;
[0034] For the same key detection node, integrating the key detection node data corresponding to each detection result data curve to obtain a key node data set corresponding to the key detection node;
[0035] Calculating the mean of each of the key node data sets to determine the data mean corresponding to each of the key node data sets;
[0036] The test result standard curve is obtained by fitting according to the data mean corresponding to each of the key node data sets.
[0037] In some embodiments, the step of performing regression analysis on each of the test result data groups according to the test result standard curve, determining the test result adjustment data corresponding to each of the test result data groups, and using the test result adjustment data for result mutual recognition specifically includes:
[0038] According to the test result standard curve, regression analysis is performed on each of the test result data curves in the test result data group to determine the regression formula corresponding to each of the test result data curves;
[0039] According to the regression formula corresponding to each of the detection result data curves, data adjustment is performed on each of the detection result data curves to obtain the detection result adjustment data corresponding to each of the detection result data curves and the detection result adjustment data curve is obtained by fitting the detection result adjustment data.
[0040] On the other hand, the embodiment of the present application proposes a device for mutual recognition of sex hormone test results, the device comprising:
[0041] The first module is used to obtain the test result data corresponding to the sex hormone test items;
[0042] The second module is used to perform a statistical analysis of the continuous time association of the detection result data according to a preset time scale set to determine multiple target grouping time periods;
[0043] The third module is used to divide the test result data according to each target grouping time period to obtain a test result data group corresponding to each target grouping time period;
[0044] The fourth module is used to obtain a test result standard curve by fitting according to the test result data;
[0045] The fifth module is used to perform regression analysis on each of the test result data groups according to the test result standard curve, determine the test result adjustment data corresponding to each of the test result data groups, and use the test result adjustment data to perform result mutual recognition.
[0046] On the other hand, an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for mutual recognition of sex hormone test results described above is implemented.
[0047] On another aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for mutual recognition of sex hormone test results described above is implemented.
[0048] The present application provides a method, device, electronic device and storage medium for mutual recognition of sex hormone test results, which determines multiple target grouping time periods by performing statistical analysis of continuous time association on the test result data, divides the test result data according to each target grouping time period, obtains multiple test result data groups, and obtains a test result standard curve by fitting according to the test result data. According to the test result standard curve, each test result data group is subjected to regression analysis, and the test result adjustment data corresponding to each test result data group is determined, and the test result adjustment data is used for result mutual recognition. The present application can effectively utilize the test result data corresponding to the sex hormone test project, improve the data quality of the test result data, combine the regression analysis method, adjust the test result data, realize the mutual recognition of test results between different medical platforms, and improve the efficiency and accuracy of mutual recognition of test results. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 This is a flow chart of a method for mutual recognition of sex hormone test results provided in an embodiment of the present application;
[0050] Figure 2 This is a schematic diagram of dividing the test result data in an embodiment of the present application;
[0051] Figure 3 It is a structural schematic diagram of a device for mutual recognition of sex hormone test results provided in an embodiment of the present application;
[0052] Figure 4 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0054] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0056] Reference Figure 1 , Figure 1 This is an optional flow chart of a method for mutual recognition of sex hormone test results provided in an embodiment of the present application. The method may include but is not limited to steps S101 to S105:
[0057] Step S101, obtaining the test result data corresponding to the sex hormone test item;
[0058] Step S102, performing a statistical analysis of the continuous time association of the detection result data according to a preset time scale set, and determining a plurality of target grouping time periods;
[0059] Step S103, dividing the test result data according to each target grouping time period to obtain a test result data group corresponding to each target grouping time period;
[0060] Step S104, fitting and obtaining a standard curve of the test results according to the test result data;
[0061] Step S105, performing regression analysis on each test result data group according to the test result standard curve, determining the test result adjustment data corresponding to each test result data group, and using the test result adjustment data for result mutual recognition.
[0062] In step S101 of some embodiments, optionally, the medical records of all patients with natural cycles are screened through the electronic medical record system of assisted reproductive treatment, and then the result set of all sex hormone tests in all natural cycles corresponding to the patient is obtained from the medical record data, and the test result data corresponding to different sex hormone test items can be obtained.
[0063] In some embodiments, the above-mentioned time scale set includes multiple time scales arranged in descending order, and step S102 may include but is not limited to steps S201 to S210:
[0064] Step S201, determining curve feature node data corresponding to each detection result data curve contained in the detection result data;
[0065] Step S202, obtaining a first time scale as the current time scale, obtaining each first grouping time node as the current grouping time node; the first grouping time node includes a start time node and an end time node corresponding to the detection result data;
[0066] Step S203, dividing each test result data curve according to the current time scale and each current grouping time node, and determining a plurality of curve data sets consisting of a plurality of test result data curves;
[0067] Step S204, integrating multiple target curve feature point data contained in each curve data set to obtain a curve feature point data set corresponding to each curve data set; the target curve feature point data is the curve feature node data corresponding to the detection result data curve in the curve data set;
[0068] Step S205, performing mean calculation and standard deviation calculation on each curve feature point data set to obtain the mean and standard deviation corresponding to each curve feature point data set;
[0069] Step S206, pairing adjacent curve feature point data sets in each clustering time period into groups, and obtaining a plurality of curve feature data comparison groups corresponding to each clustering time period; the clustering time period is determined by each current clustering time node;
[0070] Step S207, performing comparative analysis on the mean and standard deviation of each curve feature point data set in each curve feature data comparison group, and determining the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group;
[0071] Step S208, when the mean fluctuation value corresponding to the curve feature data comparison group is not within the given first fluctuation threshold range, and the standard deviation fluctuation value corresponding to the curve feature data comparison group is not within the given second fluctuation threshold range, the curve feature data comparison group is determined as the target comparison group, and the data set division time node corresponding to the adjacent curve feature point data set in the target comparison group is determined as the second grouping time node;
[0072] Step S209, when there are several target comparison groups, the second grouping time node corresponding to each target comparison group is added as the current grouping time node, the second time scale is obtained as the current time scale, and then the step of dividing each test result data curve according to the current time scale and each current grouping time node to determine a plurality of curve data sets consisting of several test result data curves is returned until there is no target comparison group; the second time scale is a time scale sequentially arranged after the current time scale in the time scale set;
[0073] Step S210, when there is no target comparison group, determine the corresponding target grouping time periods according to the current grouping time nodes; the target grouping time period is the time period between adjacent current grouping time nodes.
[0074] In some embodiments, the detection result data is divided by using multiple time scales arranged in sequence in a time scale concentration, combined with clustering time nodes, so as to accurately obtain target clustering time nodes and realize intelligent result clustering of the detection result data.
[0075] In some embodiments, step S203 may include but is not limited to steps S301 to S303:
[0076] Step S301, determining a number of grouping time periods according to each current grouping time node; the grouping time period is the time period between adjacent current grouping time nodes;
[0077] Step S302, according to each grouping time period, a plurality of test result data curves obtained in each grouping time period are screened out from the test result data, and a pre-divided set of curve data corresponding to each grouping time period is determined;
[0078] Step S303: divide each curve data pre-division set according to the current time scale to obtain a plurality of curve data sets corresponding to each curve data pre-division set.
[0079] In some embodiments, the start time node corresponds to the data record start time of the detection result data curve generated earliest in the detection result data, and the end time node corresponds to the data record end time of the detection result data curve generated latest in the detection result data.
[0080] Reference Figure 2 , Figure 2 It is an optional schematic diagram for dividing the detection result data in an embodiment of the present application, wherein, assuming that the time scale set is {1 year, 6 months, 3 months, 1 month, 2 weeks}, the first grouping time node is the starting time node: X year Y month and the ending time node: X+5 year Y month, first obtain the first time scale as the current time scale, the first time scale is the starting time scale in the time scale set, that is, the first time scale is 1 year, obtain the first grouping time node as the current grouping time node, and divide each detection result data curve in the detection result data. The detection result data can be divided into 5 curve data sets: curve data set 1-curve data set 5. Assuming that a target comparison group is found later, and its corresponding second grouping time node is X+2 year Y month, then X+2 year Y month is added as the current grouping time node, then the current grouping time node includes X year Y month, X+2 year Y month and X+5 year Y month. After finding all the target comparison groups, the second time scale is obtained as the current time scale, and the second time scale is sequentially arranged after the current time scale in the time scale set. The time scale is 1 year, the second time scale is 6 months, the current time scale is updated to 6 months, and then the process returns to step S203. According to the current time scale: 6 months and the current clustering time nodes: X year Y month, X+2 year Y month and X+5 year Y month, each test result data curve in the test result data is divided to determine the clustering time period 1 from X year Y month to X+2 year Y month and the clustering time period 2 from X+2 year Y month to X+5 year Y month. The clustering time period 1 corresponds to the curve data pre-division set A, and the clustering time period 1 is divided into The group time period 2 corresponds to the curve data pre-division set B. Then, according to the current time scale, the curve data pre-division sets A and B are divided to obtain the curve data set 6-curve data set 10 corresponding to the group time period 1, and the curve data set 11-curve data set 16 corresponding to the group time period 2. Assuming that the target comparison group is not found in this division, the above step S210 is executed to determine that the corresponding target group time period 1 is from X year Y month to X+2 year Y month and the target group time period 2 is from X+2 year Y month to X+5 year Y month.
[0081] In step S201 of some embodiments, sex hormone detection items may include but are not limited to estradiol hormone detection, progesterone hormone detection, luteinizing hormone detection and follicle stimulating hormone detection. For different sex hormone detection items, the corresponding curve feature node data are also different.
[0082] For estradiol hormone testing, the highest peak value of the test result data curve can be taken as the curve characteristic node data; for luteinizing hormone testing and follicle stimulating hormone testing, the basic value near the peak value or the highest peak value can be taken as the curve characteristic node data. Optionally, based on the population basic value corresponding to luteinizing hormone or follicle stimulating hormone determined during the basic value detection, the basic value near the peak value corresponding to each test result data curve in the luteinizing hormone test or follicle stimulating hormone test can be determined through clinical comprehensive analysis; for progesterone hormone testing, some clinical conditions are combined for analysis. Since an early increase in progesterone will affect the cutoff value corresponding to the clinical pregnancy success rate, the data point of an early increase in progesterone in the test result data curve can be taken as the curve characteristic node data. The data point of an early increase in progesterone is the data point when the progesterone value in the follicular phase is greater than 0.6ng / ml.
[0083] In step S204 of some embodiments, it is assumed that the curve data set A includes detection result data curves 1 to 9, the curve feature node data of the detection result data curve 1 is Q1, the curve feature node data of the detection result data curve 2 is Q2, and so on, and then the curve feature node data of each detection result data curve is added to the corresponding curve feature point data set A, then the curve feature point data set A is {Q1, Q2, Q3, Q4, Q5, Q6, Q7, Q8, Q9}.
[0084] In step S207 of some embodiments, specifically, a difference calculation is performed on the means of adjacent curve feature point data sets in the curve feature data comparison group to determine the mean fluctuation value. Similarly, a difference calculation is performed on the standard deviations of adjacent curve feature point data sets in the curve feature data comparison group to determine the standard deviation fluctuation value.
[0085] Difference calculation is to make a difference. Assuming that the curve feature data comparison group has adjacent curve feature point data sets A and curve feature point data sets B, the mean value of the curve feature point data set A is X, and the mean value of the curve feature point data set B is Y, then the mean fluctuation value of the curve feature data comparison group is XY or YX.
[0086] In step S208 of some embodiments, the first fluctuation threshold range is a value range with the same upper and lower limits but different signs, and the second fluctuation threshold range is also a value range with the same upper and lower limits but different signs. It can be set according to actual needs. For example, the first fluctuation threshold range can be (-Q, Q), and the second fluctuation threshold range can be (-K, K).
[0087] When the mean fluctuation value corresponding to the curve feature data comparison group is not within the given first fluctuation threshold range, and the standard deviation fluctuation value corresponding to the curve feature data comparison group is not within the given second fluctuation threshold range, it means that the adjacent curve feature point data sets in the curve feature data comparison group have obvious differences and inconsistencies, and are obtained by testing using manufacturer equipment of different models or brands.
[0088] Optionally, assuming that there are clustering time period 1 and clustering time period 2, there are curve feature point data sets A to D in clustering time period 1, and there are curve feature point data sets E to G in clustering time period 2, then the curve feature data comparison group corresponding to clustering time period 1 includes curve feature data comparison group 1: curve feature point data set A and curve feature point data set B, curve feature data comparison group 2: curve feature point data set B and curve feature point data set C, and curve feature data comparison group 3: curve feature point data set C and curve feature point data set D, the curve feature data comparison group corresponding to clustering time period 2 includes curve feature data comparison group 4: curve feature point data set E and curve feature point data set F, and curve feature data comparison group 5: curve feature point data set F and curve feature point data set G. When the mean fluctuation value of curve feature data comparison group 1 is also not within the first fluctuation threshold range, and the standard deviation fluctuation value is not within the given second fluctuation threshold range, curve feature data comparison group 1 is determined as target comparison group 1, and so on.
[0089] In some embodiments, optionally, in the progesterone hormone detection project, the results can also be clustered in combination with clinical indicators, and the clinical indicator is the clinical pregnancy success rate. Since progesterone will increase prematurely in the follicular phase, affecting the clinical pregnancy success rate, resulting in a decrease in the clinical pregnancy success rate, therefore, when progesterone is greater than 0.6 ng / ml in the follicular phase, this situation is defined as progesterone increase, and the data node of progesterone increase in the test result data curve can be determined as the curve feature node, and the clinical pregnancy success rate of the relevant medical records corresponding to the progesterone increase node data (such as the above-mentioned curve feature node data) in the test result data curve in each curve data set is counted to obtain the corresponding subject clinical pregnancy success rate statistical curve and calculate the cutoff value according to the subject clinical pregnancy success rate statistical curve, and the cutoff value is used as the clustering indicator of each curve data set. When the cutoff values corresponding to the adjacent curve data sets in the curve feature data comparison group change significantly, that is, the difference is greater than a given threshold, the curve feature data comparison group is determined as the target comparison group, wherein the cutoff value is a medical test critical value, which is used to determine whether the test result is higher or lower than the clinical or analytical decision point. The cutoff value is a critical point set based on statistical analysis. If the test value is greater than the cutoff value, it is positive, and if it is less than the cutoff value, it is negative. Therefore, the cutoff value represents a limit of clinical testing.
[0090] In some embodiments, step S104 may include but is not limited to steps S401 to S405:
[0091] Step S401, obtaining a plurality of preset key detection nodes;
[0092] Step S402, determining key detection node data corresponding to each detection result data curve in the detection result data according to each key detection node;
[0093] Step S403, for the same key detection node, integrating the key detection node data corresponding to each detection result data curve to obtain a key node data set corresponding to the key detection node;
[0094] Step S404, performing mean calculation on each key node data set to determine the data mean corresponding to each key node data set;
[0095] Step S405, fitting to obtain a standard curve of the detection results according to the data mean corresponding to each key node data set.
[0096] In some embodiments, for different sex hormone detection items, combined with the hormone change rules and hormone curve characteristics, multiple corresponding key detection nodes are selected, the key detection node data corresponding to the key detection nodes of each detection result data curve are obtained, the key node data set is integrated to obtain the key node data set, the mean of the key node data set is calculated, the corresponding data mean is determined, and the detection result standard curve is obtained by fitting.
[0097] Assuming that key detection nodes 1 to 10 are determined, data acquisition and data integration are performed on each detection result data curve to obtain the corresponding key node data sets 1 to 10, and the data mean of each key node data set is calculated. Then, based on the data means 1 to 10 and the key detection nodes corresponding to each data mean, the above-mentioned detection result standard curve is fitted.
[0098] In step S105 of some embodiments, optionally, based on the test result standard curve, regression analysis is performed on each test result data curve in the test result data group to determine the regression formula corresponding to each test result data curve. Then, based on the regression formula corresponding to each test result data curve, data adjustment is performed on each test result data curve to obtain test result adjustment data corresponding to each test result data curve and obtain the test result adjustment data curve based on the test result adjustment data fitting. Based on this, all test result data can meet similar standards and realize mutual recognition of test results between different medical platforms.
[0099] In some embodiments, the above-mentioned method for mutual recognition of sex hormone test results may further include steps S501 to S503:
[0100] Step S501, obtaining manufacturer's product testing data;
[0101] Step S502, determining the manufacturer's product traceability information corresponding to each test result data group based on the manufacturer's product test data and each test result data group;
[0102] Step S503, using the detection result adjustment data corresponding to each detection result data group, training the deep learning model, and using the deep learning model to analyze the detection result data.
[0103] In steps S501 to S502 of some embodiments, the manufacturer's detection product data includes the manufacturer's instrument model and reagent updates, measurement value traceability information, switching time periods and laboratory comparison information. The manufacturer's detection product data is compared and analyzed with the target grouping time period and data mean corresponding to each test result data group, and the manufacturer's instrument brand and model used to obtain the test result data group can be matched to determine the manufacturer's detection product traceability information corresponding to each test result data group.
[0104] In step S503 of some embodiments, the test results can be used to adjust the data and perform independent artificial intelligence deep learning in combination with other clinical indicators, which can greatly improve the accuracy of the deep learning model used in clinical practice, and use the deep learning model to perform data analysis on various test result data to improve efficiency.
[0105] Reference Figure 3 , Figure 3 This is an optional structural diagram of a device for mutual recognition of sex hormone test results provided in an embodiment of the present application, the device comprising:
[0106] The first module is used to obtain the test result data corresponding to the sex hormone test items;
[0107] The second module is used to perform statistical analysis of the continuous time association of the test result data according to a preset time scale set to determine multiple target grouping time periods;
[0108] The third module is used to divide the test result data according to each target grouping time period to obtain the test result data group corresponding to each target grouping time period;
[0109] The fourth module is used to obtain a standard curve of the test results by fitting according to the test result data;
[0110] The fifth module is used to perform regression analysis on each test result data group according to the test result standard curve, determine the test result adjustment data corresponding to each test result data group, and use the test result adjustment data for result mutual recognition.
[0111] The specific implementation of the sex hormone test result mutual recognition device is basically the same as the specific implementation of the sex hormone test result mutual recognition method described above, and will not be repeated here.
[0112] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned method for mutual recognition of sex hormone test results when executing the computer program. The electronic device can be any smart terminal including a tablet computer.
[0113] See also Figure 4 , Figure 4 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0114] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;
[0115] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the method for mutual recognition of sex hormone detection results in the embodiment of this application;
[0116] Input / output interface 903, used to implement information input and output;
[0117] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);
[0118] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);
[0119] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .
[0120] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for mutual recognition of sex hormone test results is implemented.
[0121] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0122] A method, device, electronic device and storage medium for mutual recognition of sex hormone test results provided by the embodiments of the present application, which determines multiple target grouping time periods by performing statistical analysis of continuous time association on the test result data, divides the test result data according to each target grouping time period, obtains multiple test result data groups, and obtains a test result standard curve by fitting according to the test result data, performs regression analysis on each test result data group according to the test result standard curve, determines the test result adjustment data corresponding to each test result data group, and uses the test result adjustment data for result mutual recognition. The present application can effectively utilize the test result data corresponding to the sex hormone test project, improve the data quality of the test result data, combine the regression analysis method, adjust the test result data, realize the mutual recognition of test results between different medical platforms, and improve the efficiency and accuracy of mutual recognition of test results.
[0123] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0124] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0125] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A method for mutual recognition of sex hormone test results, It is characterized in that The method comprises the following steps: Obtain the test result data corresponding to the sex hormone test items; According to a preset time scale set, a statistical analysis of continuous time association is performed on the test result data to determine multiple target grouping time periods; Dividing the test result data according to each of the target grouping time periods to obtain a test result data group corresponding to each of the target grouping time periods; According to the test result data, a test result standard curve is obtained by fitting; According to the test result standard curve, regression analysis is performed on each of the test result data groups to determine the test result adjustment data corresponding to each of the test result data groups, and the test result adjustment data is used for result mutual recognition; The time scale set includes multiple time scales arranged in descending order. The step of performing a statistical analysis of continuous time association on the detection result data according to the preset time scale set to determine multiple target grouping time periods specifically includes: Determine, according to each detection result data curve contained in the detection result data, curve feature node data corresponding to each detection result data curve; Acquire a first time scale as the current time scale, and acquire each first grouping time node as the current grouping time node; the first grouping time node includes a start time node and an end time node corresponding to the detection result data; According to the current time scale and each current grouping time node, each of the detection result data curves is divided to determine a plurality of curve data sets consisting of a plurality of the detection result data curves; Integrate a plurality of target curve feature point data contained in each of the curve data sets to obtain a curve feature point data set corresponding to each of the curve data sets; the target curve feature point data is the curve feature node data corresponding to the detection result data curve in the curve data set; Performing mean calculation and standard deviation calculation on each of the curve feature point data sets to obtain the mean and standard deviation corresponding to each of the curve feature point data sets; Pairing the adjacent curve feature point data sets in each grouping time period into groups, and obtaining a plurality of curve feature data comparison groups corresponding to each grouping time period; the grouping time period is determined by each current grouping time node; Comparatively analyzing the mean and standard deviation of each curve feature point data set in each curve feature data comparison group, and determining the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group; When the mean fluctuation value corresponding to the curve feature data comparison group is not within a given first fluctuation threshold range, and the standard deviation fluctuation value corresponding to the curve feature data comparison group is not within a given second fluctuation threshold range, the curve feature data comparison group is determined as a target comparison group, and the data set division time node corresponding to the adjacent curve feature point data set in the target comparison group is determined as a second grouping time node; When there are several target comparison groups, the second grouping time node corresponding to each target comparison group is added as the current grouping time node, a second time scale is obtained as the current time scale, and then the step of dividing each detection result data curve according to the current time scale and each current grouping time node to determine a plurality of curve data sets consisting of several detection result data curves is returned until there is no target comparison group; the second time scale is a time scale sequentially arranged after the current time scale in the time scale set; When the target comparison group does not exist, the corresponding target grouping time periods are determined according to the current grouping time nodes; the target grouping time period is the time period between adjacent current grouping time nodes.
2. The method for mutual recognition of sex hormone test results according to claim 1, It is characterized in that The method further comprises the following steps: The detection result adjustment data corresponding to each of the detection result data groups is used to train a deep learning model, and the deep learning model is used to perform detection result data analysis.
3. The method for mutual recognition of sex hormone test results according to claim 1, It is characterized in that The step of dividing each of the detection result data curves according to the current time scale and each of the current grouping time nodes to determine a plurality of curve data sets consisting of a plurality of the detection result data curves specifically includes: According to each of the current grouping time nodes, a plurality of grouping time periods are determined; the grouping time period is a time period between adjacent current grouping time nodes; According to each of the grouping time periods, a plurality of the test result data curves obtained in each of the grouping time periods are screened out from the test result data, and a pre-divided set of curve data corresponding to each of the grouping time periods is determined; According to the current time scale, each of the curve data pre-divided sets is divided to obtain a plurality of the curve data sets corresponding to each of the curve data pre-divided sets.
4. The method for mutual recognition of sex hormone test results according to claim 1, It is characterized in that The step of comparing and analyzing the mean and standard deviation of each curve feature point data set in each curve feature data comparison group to determine the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group specifically includes: Performing difference calculation on the means of adjacent curve feature point data sets in the curve feature data comparison group to determine the mean fluctuation value; The standard deviations of adjacent curve feature point data sets in the curve feature data comparison group are calculated to determine the standard deviation fluctuation value.
5. The method for mutual recognition of sex hormone test results according to claim 1, It is characterized in that The step of fitting and obtaining a test result standard curve according to the test result data specifically includes: Obtain several preset key detection nodes; According to each of the key detection nodes, determine the key detection node data corresponding to each of the detection result data curves in the detection result data; For the same key detection node, integrating the key detection node data corresponding to each detection result data curve to obtain a key node data set corresponding to the key detection node; Calculating the mean of each of the key node data sets to determine the data mean corresponding to each of the key node data sets; The test result standard curve is obtained by fitting according to the data mean corresponding to each of the key node data sets.
6. The method for mutual recognition of sex hormone test results according to claim 1, It is characterized in that The step of performing regression analysis on each of the test result data groups according to the test result standard curve, determining the test result adjustment data corresponding to each of the test result data groups, and using the test result adjustment data for result mutual recognition specifically includes: According to the test result standard curve, regression analysis is performed on each of the test result data curves in the test result data group to determine the regression formula corresponding to each of the test result data curves; According to the regression formula corresponding to each of the detection result data curves, data adjustment is performed on each of the detection result data curves to obtain the detection result adjustment data corresponding to each of the detection result data curves and the detection result adjustment data curve is obtained by fitting the detection result adjustment data.
7. A device for mutual recognition of sex hormone test results, It is characterized in that The device comprises: The first module is used to obtain the test result data corresponding to the sex hormone test items; The second module is used to perform a statistical analysis of the continuous time association of the detection result data according to a preset time scale set to determine multiple target grouping time periods; the time scale set includes multiple time scales arranged in order from large to small, and the step of performing a statistical analysis of the continuous time association of the detection result data according to the preset time scale set to determine multiple target grouping time periods specifically includes: Determine, according to each detection result data curve contained in the detection result data, curve feature node data corresponding to each detection result data curve; Acquire a first time scale as the current time scale, and acquire each first grouping time node as the current grouping time node; the first grouping time node includes a start time node and an end time node corresponding to the detection result data; According to the current time scale and each current grouping time node, each of the detection result data curves is divided to determine a plurality of curve data sets consisting of a plurality of the detection result data curves; Integrate a plurality of target curve feature point data contained in each of the curve data sets to obtain a curve feature point data set corresponding to each of the curve data sets; the target curve feature point data is the curve feature node data corresponding to the detection result data curve in the curve data set; Performing mean calculation and standard deviation calculation on each of the curve feature point data sets to obtain the mean and standard deviation corresponding to each of the curve feature point data sets; Pairing the adjacent curve feature point data sets in each grouping time period into groups, and obtaining a plurality of curve feature data comparison groups corresponding to each grouping time period; the grouping time period is determined by each current grouping time node; Comparatively analyzing the mean and standard deviation of each curve feature point data set in each curve feature data comparison group, and determining the mean fluctuation value and standard deviation fluctuation value corresponding to each curve feature data comparison group; When the mean fluctuation value corresponding to the curve feature data comparison group is not within a given first fluctuation threshold range, and the standard deviation fluctuation value corresponding to the curve feature data comparison group is not within a given second fluctuation threshold range, the curve feature data comparison group is determined as a target comparison group, and the data set division time node corresponding to the adjacent curve feature point data set in the target comparison group is determined as a second grouping time node; When there are several target comparison groups, the second grouping time node corresponding to each target comparison group is added as the current grouping time node, a second time scale is obtained as the current time scale, and then the step of dividing each detection result data curve according to the current time scale and each current grouping time node to determine a plurality of curve data sets consisting of several detection result data curves is returned until there is no target comparison group; the second time scale is a time scale sequentially arranged after the current time scale in the time scale set; When the target comparison group does not exist, the corresponding target grouping time periods are determined according to the current grouping time nodes; the target grouping time period is the time period between adjacent current grouping time nodes; The third module is used to divide the test result data according to each target grouping time period to obtain a test result data group corresponding to each target grouping time period; The fourth module is used to obtain a test result standard curve by fitting according to the test result data; The fifth module is used to perform regression analysis on each of the test result data groups according to the test result standard curve, determine the test result adjustment data corresponding to each of the test result data groups, and use the test result adjustment data to perform result mutual recognition.
8. An electronic device, It is characterized in that The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method for mutual recognition of sex hormone test results as claimed in any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method for mutual recognition of sex hormone test results according to any one of claims 1 to 6 is implemented.
