An intelligent processing method and system for urology diagnosis and treatment data

By calculating the deviation and sign similarity of urine test data, evaluating whether the urine test data is affected by the external environment, solving the problem of inaccurately distinguishing the source of data deviation in the prior art, and improving the accuracy of judging urine test data.

CN118762849BActive Publication Date: 2024-12-03SHANDONG UNIV QILU HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411237212.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-03
Estimated Expiration
2044-09-05

AI Technical Summary

Technical Problem

Existing methods cannot accurately determine whether the patient's urine test data is affected by the external environment and abnormalities, resulting in misjudgment of data deviations in the patient's own disease and environmental interference.

Method used

By obtaining the latest and historical urine test reports of the patient, calculating data deviation and sign similarity, selecting similar patients for environmental impact assessment, and determining whether urine test data is affected by the external environment.

Benefits of technology

Accurately distinguish the source of deviations in urine test data, eliminate the patient's own disease interference, and improve the accuracy of judgment results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118762849B_ABST
    Figure CN118762849B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of urology diagnosis and treatment data processing, and specifically to a method and system for intelligent processing of urology diagnosis and treatment data. The method first obtains the latest urine test reports and diagnosis and treatment recommendations as well as historical urine test reports of different patients, analyzes the difference in the test data of the same indicator in the latest urine test report and the historical urine test report of the patient, and obtains the data deviation; according to the difference in the test data of the same indicator in the historical urine test report between the target patient and other patients and the difference in the content of the diagnosis and treatment recommendations, obtains the similarity of physical signs, and selects similar patients, and evaluates whether the test data of the indicator in the latest urine test report of the target patient is affected by the external environment according to the difference in the data deviation of the same indicator in the latest urine test report between the target patient and similar patients and the similarity of physical signs. The present invention eliminates the factor that the patient suffers from related diseases, which interferes with the abnormal analysis of the test data due to the influence of the external environment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of urology diagnosis and treatment data processing, and in particular to an intelligent processing method and system for urology diagnosis and treatment data. Background Art

[0002] Urology is a medical science used to diagnose and treat the urinary system. By using clinical testing methods such as urine tests on patients, we can obtain test data on multiple indicators of patients, and use the test data to analyze the urinary system diseases of patients. Therefore, the accuracy of patients' urinary test data is of great significance for evaluating the health status of patients' urinary system and the effective treatment of diseases.

[0003] Since the patient's urine sample is easily affected by the external environment of the hospital, which may lead to abnormal test data, the relevant technology usually analyzes the degree of deviation of the diagnosis and treatment data of each indicator to determine whether the diagnosis and treatment data of each indicator is abnormal. However, the data deviation caused by the patient's urine test sample being affected by the external environment of the hospital is an abnormal phenomenon, while the data deviation caused by the patient himself suffering from related diseases is a normal phenomenon. As a result, the existing method cannot accurately determine whether the patient's test data is affected by the external environment and has abnormalities. Summary of the invention

[0004] In order to solve the technical problem that the existing methods cannot accurately determine whether the patient's test data is affected by the external environment and abnormal, the purpose of the present invention is to provide an intelligent processing method and system for urology diagnosis and treatment data. The technical solutions adopted are as follows:

[0005] The present invention proposes an intelligent processing method for urology diagnosis and treatment data, the method comprising:

[0006] Obtain the latest urine test report and diagnosis and treatment recommendations for different patients' current urine tests, and obtain historical urine test reports for each urine test of different patients within a preset historical time period, wherein both the latest urine test report and the historical urine test reports include the test date and test data of different indicators;

[0007] Taking any patient as the target patient and any indicator as the indicator to be tested, according to the difference of the test data of the indicator to be tested between the latest urine test report of the target patient and the historical urine test reports of each urine test and the difference of the test dates, obtaining the data deviation of the indicator to be tested in the latest urine test report of the target patient;

[0008] Patients other than the target patient are taken as reference patients, and the physical sign similarity between the target patient and each reference patient is obtained based on the difference in the test data of the same indicator between the historical urine test reports of the target patient and each reference patient, the difference in the test date, and the difference in the content information of the diagnosis and treatment recommendation between the target patient and each reference patient; based on the physical sign similarity, similar patients are selected from all reference patients; based on the difference in the data deviation of the indicator to be tested in the latest urine test report between the target patient and similar patients and the physical sign similarity, the environmental impact assessment value of the indicator to be tested in the latest urine test report of the target patient is obtained;

[0009] Based on the environmental impact assessment value, it is assessed whether the test data of the target patient's latest urine test report is affected by the external environment.

[0010] Furthermore, the data deviation of the target patient's latest urine test report includes:

[0011] Obtaining the difference in initial data of the target patient's latest urine test report and each historical urine test report of the target patient according to the difference in the test data of the target patient's latest urine test report and each historical urine test report of the target patient;

[0012] According to the difference in the test date between the latest urine test report of the target patient and each historical urine test report, the initial data difference is adjusted to obtain the real data difference of the indicator to be tested between the latest urine test report of the target patient and each historical urine test report;

[0013] The overall level of the real data difference of the indicator to be measured between the latest urine test report of the target patient and all the historical urine test reports is analyzed to obtain the data deviation of the indicator to be measured in the latest urine test report of the target patient.

[0014] Furthermore, the actual data difference of the target patient's latest urine test report and each historical urine test report includes:

[0015] Obtaining a first time interval between the target patient's latest urine test report and each historical urine test report according to the difference in the test date between the target patient's latest urine test report and each historical urine test report;

[0016] Performing negative correlation normalization processing on the first time interval to obtain a first confidence level between the latest urine test report of the target patient and each historical urine test report;

[0017] The initial data difference is weighted by using the first confidence level to obtain the real data difference of the indicator to be measured between the latest urine test report of the target patient and each historical urine test report.

[0018] Further, obtaining the similarity of physical signs between the target patient and each reference patient includes:

[0019] Any reference patient is used as the reference patient to be tested;

[0020] Obtaining a first physical sign similarity factor between the target patient and the reference patient to be tested based on the difference in the test data of the same indicator and the difference in the test date between the historical urine test reports of the target patient and the reference patient to be tested for the same urine test;

[0021] Obtaining a second physical sign similarity factor between the target patient and the reference patient to be tested according to the difference in content information of the diagnosis and treatment recommendation between the target patient and the reference patient to be tested;

[0022] The first physical sign similarity factor and the second physical sign similarity factor are integrated and normalized to obtain the physical sign similarity between the target patient and the reference patient to be tested.

[0023] Further, obtaining the first physical sign similarity factor between the target patient and the reference patient to be tested includes:

[0024] The two historical urine test reports of the same urine test of the target patient and the reference patient to be tested are used as one urine test report group;

[0025] According to the difference of the detection data of the same indicator between two historical urine test reports in each urine test report group, the data difference parameter of each indicator of each urine test report group is obtained; the data difference parameters of all indicators of each urine test report group are integrated to obtain the initial integrated difference value of each urine test report group;

[0026] According to the difference in the test date between the two historical urine test reports in each urine test report group, a second time interval of each urine test report group is obtained; and the second time interval is subjected to negative correlation normalization processing to obtain a second confidence level of each urine test report group;

[0027] Using the second confidence level, weighting the initial comprehensive difference value to obtain a true comprehensive difference value for each urine test report group;

[0028] The true comprehensive difference values ​​of all urine test report groups are integrated and normalized for negative correlation to obtain the first physical sign similarity factor between the target patient and the reference patient to be tested.

[0029] Further, obtaining the second physical sign similarity factor between the target patient and the reference patient to be tested includes:

[0030] Performing natural language processing on the diagnosis and treatment recommendations for the target patient and the reference patient to be tested, respectively, to obtain keywords in the diagnosis and treatment recommendations for the target patient and the reference patient to be tested and a word vector for each keyword;

[0031] Randomly select a keyword from the diagnosis and treatment recommendations for the target patient, and randomly select a keyword from the diagnosis and treatment recommendations for the reference patient to be tested, and use the two selected keywords as a keyword group;

[0032] The cosine similarity of the word vectors of the two keywords in each keyword group is used as the word similarity of each keyword group;

[0033] The overall level of the word similarity of all keyword groups is analyzed to obtain the second physical sign similarity factor between the target patient and the reference patient to be tested.

[0034] Furthermore, the similar patients selected from all reference patients based on the similarity of the physical signs include:

[0035] Select a preset number of reference patients corresponding to the largest physical sign similarities as similar patients.

[0036] Furthermore, the environmental impact assessment value of the indicator to be measured in the latest urine test report of the target patient is obtained, including:

[0037] Obtaining an initial deviation difference value of the indicator to be measured in the latest urine test report between the target patient and each similar patient according to the difference in the data deviation of the indicator to be measured in the latest urine test report between the target patient and each similar patient;

[0038] Using the similarity of the physical signs between the target patient and each similar patient, the initial deviation difference value is weighted to obtain the actual deviation difference value of the indicator to be measured in the latest urine test report between the target patient and each similar patient;

[0039] The overall level of the true deviation difference value of the target patient's target indicator in the latest urine test report is analyzed and normalized to obtain the environmental impact assessment value of the target patient's target indicator in the latest urine test report.

[0040] Furthermore, the step of evaluating whether the test data of the indicator to be tested in the latest urine test report of the target patient is affected by the external environment based on the environmental impact assessment value includes:

[0041] If the environmental impact assessment value is greater than a preset threshold, it is considered that the detection data of the target patient's latest urine test report's target indicator is affected by the external environment; otherwise, it is considered that the detection data of the target patient's latest urine test report's target indicator is not affected by the external environment.

[0042] The present invention also proposes an intelligent processing system for urological surgery diagnosis and treatment data, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any step of an intelligent processing method for urological surgery diagnosis and treatment data.

[0043] The present invention has the following beneficial effects:

[0044] The present invention takes into account that the existing methods cannot accurately determine whether the patient's test data is affected by the external environment and becomes abnormal. First, the latest urine test report and diagnosis and treatment recommendations of different patients' current urine tests are obtained, and the historical urine test reports of each urine test of different patients within a preset historical time period are obtained. Considering that when the test data of the target indicator to be tested is abnormal, the difference in the test data of the target indicator to be tested between the latest urine test report and the historical urine test report of the target patient is large, and the closer the test date of the historical urine test report is to the latest urine test report, the stronger the reference of the test data of the historical urine test report. Therefore, the deviation degree of the test data of the target indicator to be tested in the latest urine test report relative to the historical urine test report can be preliminarily reflected by the data deviation degree. Due to the interference of the external environment of the hospital and the target patient himself suffering from related diseases, When the target patient has a disease, these two situations will cause the detection data of the target patient's latest urine test report to deviate greatly from that of the historical urine test report. It is normal for the patient to have a deviation in the data when he / she suffers from related diseases. Therefore, the present invention selects patients with similar physical conditions to the target patient based on the similarity of physical signs. When the detection data of the target patient's latest urine test report is affected by the external environment, the difference in the data deviation of the target patient's latest urine test report with that of similar patients is large. Therefore, the environmental impact assessment value can be used to accurately determine whether the detection data of the target patient's latest urine test report is affected by the external environment and becomes abnormal, thereby eliminating the interference of the patient's own related diseases on the judgment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 work.

[0046] Figure 1 A flow chart of an intelligent processing method for urology diagnosis and treatment data provided by one embodiment of the present invention;

[0047] Figure 2 A flow chart of a method for obtaining the data deviation of a target patient's latest urine test report provided by one embodiment of the present invention;

[0048] Figure 3 A flow chart of a method for obtaining the similarity of physical signs between a target patient and each reference patient provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the intelligent processing method and system of urology diagnosis and treatment data proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of the intelligent processing method and system for urology diagnosis and treatment data provided by the present invention is described in detail below with reference to the accompanying drawings.

[0052] See also Figure 1 , which shows a flow chart of a method for intelligent processing of urology diagnosis and treatment data provided by an embodiment of the present invention, the method comprising:

[0053] Step S1: Obtain the latest urine test report and diagnosis and treatment recommendations for different patients' current urine tests, and obtain historical urine test reports for each urine test of different patients within a preset historical time period. Both the latest urine test report and the historical urine test report include the test date and test data of different indicators.

[0054] Urology is a medical science used to diagnose and treat the urinary system. By using clinical testing methods such as urine tests on patients, test data of multiple indicators of the patient can be obtained, and the urinary system diseases of the patient can be analyzed through the test data. Therefore, the accuracy of the patient's urine test data is of great significance for evaluating the health status of the patient's urinary system and the effective treatment of the disease. Since the patient's urine sample is easily affected by the external environment of the hospital, the test data may be abnormal. In the related technology, the degree of deviation of the diagnosis and treatment data of each indicator is usually analyzed to determine whether the diagnosis and treatment data of each indicator is abnormal. However, the deviation of the data caused by the patient's urine test sample being affected by the external environment of the hospital is an abnormal phenomenon, while the deviation of the data caused by the patient himself suffering from related diseases is a normal phenomenon, resulting in the inability of the existing method to accurately determine whether the patient's test data is affected by the external environment and abnormal. Therefore, an embodiment of the present invention proposes an intelligent processing method for urology diagnosis and treatment data to solve this problem.

[0055] Normally, after a hospital conducts a urine test on a patient, it will generate a urine test report, which contains the test date and test data of multiple indicators, such as pH, urobilinogen concentration, calcium ion concentration and urine specific gravity, etc. The patient's urine test report is stored in the medical database system. At the same time, during each urine test, the doctor will also give corresponding diagnosis and treatment recommendations based on the physical condition described by the patient, and store them in the medical database system together with the urine test report.

[0056] Therefore, the embodiment of the present invention first obtains the latest urine test report and diagnosis and treatment recommendations of different patients' current urine tests from the hospital's medical database system, and obtains the historical urine test reports of different patients for each urine test within a preset historical time period, wherein the number of patients is generally an integer between 100 and 200. In one embodiment of the present invention, the number of patients is set to 100. The number of patients can also be set by the implementer according to the specific implementation scenario, which is not limited here. At the same time, the embodiment of the present invention believes that the detection data of each indicator in the historical urine test report is verified data, so the detection data of each indicator in the historical urine test report is not affected by the external environment and abnormalities occur.

[0057] In one embodiment of the present invention, the preset historical time period is set to 1 year, and the specific value of the preset historical time period can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0058] Step S2: Take any patient as the target patient and any indicator as the indicator to be tested, and obtain the data deviation of the indicator to be tested in the latest urine test report of the target patient based on the difference in test data of the indicator to be tested between the latest urine test report of the target patient and the historical urine test reports of each urine test and the difference in test dates.

[0059] When the external environment interferes with the patient's urine sample, it will cause abnormal test data of certain indicators in the patient's latest urine test report. When the patient himself suffers from related diseases, it will also cause abnormal test data of certain indicators in the patient's latest urine test report. Both of these situations will cause a large difference in the test data of the same indicator between the patient's latest urine test report and the historical urine test report. In other words, when the test data of a certain indicator in the patient's latest urine test report is abnormal, the test data of a certain indicator in the latest urine test report will have a large deviation from the test data of the same indicator in the historical urine test report. Therefore, any patient can be taken as the target patient, any indicator can be taken as the indicator to be tested, and the latest urine test report of the target patient can be analyzed. The difference in the test data of the target patient's latest urine test report and the historical urine test report of each urine test is analyzed. Considering that the closer the test date of the historical urine test report is to the latest urine test report, the stronger the reference of the test data of the historical urine test report is, therefore, the difference in the test date between the target patient's latest urine test report and the historical urine test report of each urine test can be further combined, and the degree of deviation of the test data of the target patient's latest urine test report relative to the historical urine test report can be reflected through the obtained data deviation, which preliminarily reflects the possibility of abnormality in the test data of the target patient's latest urine test report. Subsequently, based on the degree of data deviation, it can be accurately analyzed whether the test data of the target patient's latest urine test report is affected by the external environment.

[0060] Preferably, in one embodiment of the present invention, the method for obtaining the data deviation of the indicator to be measured in the latest urine test report of the target patient specifically includes:

[0061] See also Figure 2 , which shows a flow chart of a method for obtaining the data deviation of a target patient's latest urine test report provided by an embodiment of the present invention.

[0062] Step S201: according to the difference of the detection data of the target indicator between the latest urine test report of the target patient and each historical urine test report, the difference of the initial data of the target indicator between the latest urine test report of the target patient and each historical urine test report is obtained.

[0063] Through the above analysis, it can be seen that when the test data of the target indicator in the latest urine test report of the target patient is abnormal, the difference in the test data of the target indicator between the latest urine test report of the target patient and the historical urine test report will be relatively large. Therefore, the difference in the test data of the target indicator between the latest urine test report of the target patient and each historical urine test report can be analyzed. The initial data difference degree obtained can preliminarily reflect the difference degree of the test data of the target indicator between the latest urine test report of the target patient and each historical urine test report. The initial data difference degree can be further adjusted later to improve the accuracy of the analysis result.

[0064] In one embodiment of the present invention, the absolute value of the difference in detection data of the indicator to be measured between the latest urine test report of the target patient and each historical urine test report can be used as the initial data difference of the indicator to be measured between the latest urine test report of the target patient and each historical urine test report, so as to analyze the difference between the two.

[0065] Step S202: According to the difference in test date between the latest urine test report of the target patient and each historical urine test report, the initial data difference is adjusted to obtain the real data difference of the target patient's latest urine test report and each historical urine test report.

[0066] Since the closer the test date of the historical urine test report is to the test date of the latest urine test report, the greater the reference value of the test data in the historical urine test report, the initial data difference can be adjusted according to the difference in test date between the target patient's latest urine test report and each historical urine test report, and the real data difference of the target patient's latest urine test report and each historical urine test report can be obtained. The real data difference can accurately reflect the difference in the test data of the target patient's latest urine test report and each historical urine test report.

[0067] Preferably, in one embodiment of the present invention, the method for obtaining the real data difference of the target patient's latest urine test report and each historical urine test report specifically includes:

[0068] According to the difference in detection date between the latest urine test report of the target patient and each historical urine test report, the first time interval between the latest urine test report of the target patient and each historical urine test report is obtained. The larger the first time interval, the farther the detection date of each historical urine test report is from the latest urine test report, and the smaller the confidence of the difference in detection data of the measured indicator between the two. Then, the first time interval is normalized by negative correlation to obtain the first confidence between the latest urine test report of the target patient and each historical urine test report.

[0069] In one embodiment of the present invention, the absolute value of the difference in detection date between the target patient's latest urine test report and each historical urine test report can be used as the first time interval between the target patient's latest urine test report and each historical urine test report to analyze the difference between the two.

[0070] In the embodiment of the present invention, the natural constant can be used A negative exponential function with base The normalization processing of negative correlation is realized in the form of a function, which is not limited here. The same method can also be used in subsequent steps to realize the normalization processing of negative correlation, where: Represents a normalization function. In one embodiment of the present invention, the normalization process may be specifically, for example, a maximum and minimum value normalization process, and the normalization in subsequent steps may adopt the maximum and minimum value normalization process. In other embodiments of the present invention, other normalization methods may be selected according to a specific range of numerical values, which will not be described in detail.

[0071] Then, the first confidence level can be used to weight the initial data difference to obtain the actual data difference of the indicator to be tested between the target patient's latest urine test report and each historical urine test report.

[0072] Step S203: Analyze the overall level of the difference in the real data of the target patient's latest urine test report and all the historical urine test reports to obtain the data deviation of the target patient's latest urine test report.

[0073] When the difference of the real data of the target patient's latest urine test report and each historical urine test report is relatively large, it means that the detection data of the target patient's latest urine test report has a large deviation from the historical urine test report. Therefore, the overall level of the difference of the real data of the target patient's latest urine test report and all historical urine test reports can be analyzed to obtain the data deviation of the target patient's latest urine test report.

[0074] In an embodiment of the present invention, the average value or median of the difference in real data of the indicator to be measured between the latest urine test report of the target patient and all historical urine test reports can be used as the data deviation of the indicator to be measured in the latest urine test report of the target patient, so as to realize the overall level analysis of the difference in real data of the indicator to be measured between the latest urine test report of the target patient and all historical urine test reports, which is not limited here.

[0075] The expression of the data deviation of the target patient's latest urine test report can be specifically, for example, as follows:

[0076]

[0077] in, Indicates the data deviation of the target patient's latest urine test report; Indicates the test date of the target patient's latest urine test report; The target patient The test date of the historical urine test report; Indicates the test data of the target patient's latest urine test report; The target patient The test data of the indicators to be tested in the historical urine test reports; represents the number of historical urine test reports of the target patient; Indicates the latest urine test report and the The first time interval between the historical urine test reports; Indicates the latest urine test report and the The first confidence level between historical urine test reports; Indicates the latest urine test report and the The difference in initial data of the indicators to be tested between historical urine test reports; Indicates the latest urine test report and the The difference in the actual data of the indicators to be tested between the historical urine test reports; Indicated by natural constant An exponential function with base .

[0078] The data deviation of the measured index in the latest urine test report of each patient can be obtained by the same method as above.

[0079] Step S3: Take patients other than the target patient as reference patients, and obtain the physical sign similarity between the target patient and each reference patient based on the difference in test data of the same indicator between the historical urine test reports of the target patient and each reference patient, the difference in test date, and the difference in content information of the diagnosis and treatment recommendations between the target patient and each reference patient; based on the physical sign similarity, select similar patients from all reference patients; obtain the environmental impact assessment value of the indicator to be tested in the latest urine test report of the target patient based on the difference in data deviation of the indicator to be tested in the latest urine test report between the target patient and the similar patients and the physical sign similarity.

[0080] Due to interference from the hospital's external environment and when the target patient suffers from related diseases, both situations will cause the test data of the target patient's latest urine test report to deviate significantly from historical urine test reports. It is normal for the target patient to have data deviations when suffering from related diseases. Therefore, only the data deviation obtained above cannot accurately assess whether the test data in the target patient's latest urine test report is affected by external environmental interference and becomes abnormal. It is easy to mistake the test data with large deviations caused by the target patient's own related diseases as abnormal data caused by external environmental interference, which requires further analysis.

[0081] Considering that when there is no interference from the external environment, for other patients with similar physical conditions or related diseases as the target patient, the similarity of the deviation of the test data of the tested indicators in the latest urine test report between them and the target patient is relatively high, and when the test data in the latest urine test report of the target patient is interfered by the external environment, this similarity of deviation will be broken, resulting in a larger difference, and the similarity between the physical conditions or related diseases between the target patient and the reference patient can be determined by the difference in the test data of the same indicator between the historical urine test reports of the target patient and the reference patient for the same urine test, as well as the content information of the diagnosis and treatment recommendations between the target patient and the reference patient. At the same time, considering that the closer the detection dates of the historical urine test reports of the target patient and the reference patient for the same urine test are, the higher the confidence of the difference analysis of the detection data of the same indicator between the historical urine test reports of the same urine test between the two patients, the difference in detection dates of the historical urine test reports of the same urine test between the target patient and each reference patient can be further combined, and the similarity of the physical condition between the target patient and each reference patient can be reflected by the obtained physical sign similarity. Subsequently, based on the physical sign similarity, patients with a physical condition similar to that of the target patient can be selected from the reference patients. At the same time, in the subsequent calculation process, the physical sign similarity can also be used as the confidence to improve the calculation accuracy.

[0082] Preferably, in one embodiment of the present invention, the method for obtaining the physical sign similarity between the target patient and each reference patient specifically includes:

[0083] See also Figure 3 , which shows a flow chart of a method for obtaining the physical sign similarity between a target patient and each reference patient provided by an embodiment of the present invention.

[0084] Step S301: Take any reference patient as the reference patient to be tested, and obtain the first physical sign similarity factor between the target patient and the reference patient to be tested based on the difference in test data of the same indicator between the historical urine test reports of the target patient and the reference patient to be tested and the difference in test dates.

[0085] First, an analysis is performed on any reference patient, and any reference patient is taken as the reference patient to be tested. The smaller the difference in the test data of the same indicator between the historical urine test reports of the target patient and the reference patient to be tested, the more similar the physical condition and related diseases between the target patient and the reference patient to be tested are. At the same time, the closer the test dates of the historical urine test reports of the same urine test between the target patient and the reference patient to be tested are, the higher the confidence level of the difference analysis of the test data of the same indicator between the historical urine test reports of the same urine test between the two. Therefore, the difference in the test data of the same indicator and the difference in the test date between the historical urine test reports of the same urine test between the target patient and the reference patient to be tested can be analyzed, and the first physical sign similarity factor obtained can be used to reflect the similarity in the physical condition and related diseases between the target patient and the reference patient to be tested, thereby providing a data basis for the subsequent calculation of physical sign similarity.

[0086] Preferably, in one embodiment of the present invention, the method for obtaining the first physical sign similarity factor between the target patient and the reference patient to be tested specifically includes:

[0087] First, the two historical urine test reports of the same urine test of the target patient and the reference patient to be tested are taken as a urine test report group.

[0088] Among them, for the two historical urine test reports in each urine test report group, one historical urine test report belongs to the target patient, and the other historical urine test report belongs to the reference patient to be tested.

[0089] Then, the urine test report groups are analyzed, and the data difference parameters of each indicator of each urine test report group are obtained according to the difference in the test data of the same indicator between the two historical urine test reports in each urine test report group. The smaller the data difference parameter, the smaller the difference in the test data of the same indicator of the two historical urine test reports in the urine test report group, which further indicates that the physical conditions represented by the same indicator of the target patient and the reference patient to be tested after the same urine test are more similar. Then, the data difference parameters of all indicators of each urine test report group are integrated to obtain the initial comprehensive difference value of each urine test report group. The smaller the initial comprehensive difference value, the more similar the physical conditions represented by each indicator of the target patient and the reference patient to be tested after the same urine test.

[0090] In one embodiment of the present invention, the absolute value of the difference in detection data of the same indicator between two historical urine test reports in each urine test report group can be used as the data difference parameter of each urine test report group for each indicator to analyze the difference between the two.

[0091] In an embodiment of the present invention, the accumulated value or the accumulated multiplied value of the data difference parameters of each urine test report group regarding all indicators can be used as the initial comprehensive difference value of each urine test report group to realize the integration of the data difference parameters of each urine test report group regarding all indicators, which is not limited here.

[0092] From the above analysis, it can be seen that the closer the test dates of the historical urine test reports of the same urine test of the target patient and the reference patient to be tested are, the higher the confidence of the difference analysis of the test data of the same indicator between the historical urine test reports of the same urine test of the two patients will be. Therefore, according to the difference in the test dates between the two historical urine test reports in each urine test report group, the second time interval of each urine test report group can be obtained, and the second time interval can be normalized by negative correlation to obtain the second confidence of each urine test report group. The initial comprehensive difference value is weighted by using the second confidence to obtain the true comprehensive difference value of each urine test report group. The smaller the true comprehensive difference value is, the more similar the physical conditions represented by each indicator of the target patient and the reference patient to be tested are after the same urine test.

[0093] In one embodiment of the present invention, the absolute value of the difference between the detection dates of two historical urine test reports in each urine test report group can be used as the second time interval of each urine test report group to analyze the difference between the two.

[0094] Then, the true comprehensive difference values ​​of all urine test report groups were integrated and normalized for negative correlation to obtain the first physical sign similarity factor between the target patient and the reference patient to be tested.

[0095] In the embodiment of the present invention, the integration of the true comprehensive difference values ​​of all urine test report groups can be achieved by calculating the cumulative value or cumulative multiplication value of the true comprehensive difference values ​​of all urine test report groups, which is not limited here.

[0096] The expression of the first physical sign similarity factor between the target patient and the reference patient to be tested can be specifically, for example, as follows:

[0097]

[0098]

[0099] in, represents the first physical sign similarity factor between the target patient and the reference patient to be tested; Indicates The true comprehensive difference value of each urine test report group; Indicates the minimum value of the number of historical urine test reports of the target patient and the number of historical urine test reports of the reference patient to be tested, that is, the number of urine test report groups. Considering that the number of historical urine test reports of the target patient and the reference patient to be tested is different, the minimum value of the number of historical urine test reports of the two is taken here; and Respectively represent The test dates of two historical urine test reports in a urine test report group; Indicates The second time interval of each urine test report group; Indicates The second confidence level of each urine test report group; and Respectively represent The first of two historical urine test reports in a urine test report group The detection data of each indicator; Indicates Urine test report group about Data difference parameters for each indicator; Indicates the number of indicators; Indicates The initial comprehensive difference value of each urine test report group; Indicated by natural constant An exponential function with base .

[0100] Step S302: obtaining a second physical sign similarity factor between the target patient and the reference patient to be tested according to the difference in content information of the diagnosis and treatment recommendation between the target patient and the reference patient to be tested.

[0101] Since the treatment recommendation contains the advice information given by the doctor based on the patient's physical condition, the content information of the treatment recommendation for patients with similar physical conditions is relatively similar. Therefore, the difference in the content information of the treatment recommendation between the target patient and the reference patient to be tested can be analyzed. The second physical sign similarity factor obtained can reflect the similarity of the physical condition and related diseases between the target patient and the reference patient to be tested, providing a data basis for the subsequent calculation of physical sign similarity.

[0102] Preferably, in one embodiment of the present invention, the method for obtaining the second physical sign similarity factor between the target patient and the reference patient to be tested specifically includes:

[0103] Since the information in the diagnosis and treatment recommendations is usually presented in text form, natural language processing is first performed on the diagnosis and treatment recommendations for the target patient and the reference patient to be tested, respectively, to obtain the keywords in the diagnosis and treatment recommendations for the target patient and the reference patient to be tested and the word vector of each keyword, wherein natural language processing is a technical means well known to technicians in this field and will not be elaborated here.

[0104] Then, randomly select a keyword from the diagnosis and treatment recommendations for the target patient, and randomly select a keyword from the diagnosis and treatment recommendations for the reference patient to be tested. The two selected keywords are used as a keyword group, and the cosine similarity of the word vectors of the two keywords in each keyword group is used as the word similarity of each keyword group. The greater the word similarity, the more similar the two keywords in the keyword group are. Among them, cosine similarity is an existing calculation method and will not be repeated here.

[0105] The greater the word similarity of each keyword group, the more similar the contents of the diagnosis and treatment recommendations for the target patient and the reference patient to be tested are, which further indicates that the physical conditions and related diseases of the two are more similar. Therefore, the overall level of word similarity of all keyword groups can be analyzed to obtain the second physical sign similarity factor between the target patient and the reference patient to be tested.

[0106] In an embodiment of the present invention, the average or median of the word similarities of all keyword groups can be used as the second physical sign similarity factor between the target patient and the reference patient to be tested to achieve an overall level of analysis of the word similarities of all keyword groups, which is not limited here.

[0107] The expression of the second physical sign similarity factor between the target patient and the reference patient to be tested can be specifically, for example, as follows:

[0108]

[0109] in, represents the similarity factor of the second physical sign between the target patient and the reference patient to be tested; Indicates the number of keyword groups; and Respectively represent The word vectors of the two keywords in the keyword group; Indicates The cosine similarity of the word vectors of the two keywords in the keyword group is calculated. Since the angle between the word vectors of each keyword obtained after natural language processing is less than 90 degrees, .

[0110] Step S303: The first physical sign similarity factor and the second physical sign similarity factor are integrated and normalized to obtain the physical sign similarity between the target patient and the reference patient to be tested.

[0111] From the above analysis, it can be seen that the larger the first sign similarity factor and the second sign similarity factor between the target patient and the reference patient to be tested, the more similar the physical condition and related diseases of the target patient and the reference patient to be tested are. Therefore, the first sign similarity factor and the second sign similarity factor can be combined and normalized to obtain the sign similarity between the target patient and the reference patient to be tested.

[0112] In the embodiment of the present invention, the integration of the first physical sign similarity factor and the second physical sign similarity factor can be achieved by calculating the sum or product of the two, which is not limited here.

[0113] The expression of the physical sign similarity between the target patient and the reference patient to be tested can be specifically, for example, as follows:

[0114]

[0115] in, Indicates the similarity of physical signs between the target patient and the reference patient to be tested; represents the first physical sign similarity factor between the target patient and the reference patient to be tested; represents the similarity factor of the second physical sign between the target patient and the reference patient to be tested; Represents the normalization function.

[0116] The same method as above can be used to obtain the physical sign similarity between the target patient and each reference patient, and then the physical sign similarity can be used to select patients with physical conditions similar to the target patient from all reference patients, namely similar patients.

[0117] Preferably, in one embodiment of the present invention, a preset number of reference patients corresponding to the largest physical sign similarities are selected as similar patients, wherein the value range of the preset number is an integer from 10 to 30. In one embodiment of the present invention, the preset number is set to 20. The specific value of the preset number can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0118] In other embodiments of the present invention, a threshold may be set and reference patients corresponding to physical sign similarities greater than the threshold may be regarded as similar patients.

[0119] From the above analysis, it can be seen that, considering that when there is no interference from the external environment, the similarity of the deviation of the detection data of the to-be-tested indicators in the latest urine test reports between similar patients and the target patient is higher, and when the detection data in the latest urine test report of the target patient is disturbed by the external environment, this similarity of deviation will be broken, resulting in a larger difference. Therefore, the difference in the data deviation of the to-be-tested indicators in the latest urine test reports between the target patient and similar patients can be analyzed. At the same time, the greater the similarity in physical signs between the target patient and similar patients, the more similar the physical condition and related diseases of the target patient and similar patients are, and the greater the confidence in the difference analysis of the data deviation of the to-be-tested indicators in the latest urine test reports between the target patient and similar patients. Therefore, the similarity in physical signs between the target patient and similar patients can be further combined, and the possibility of the detection data of the to-be-tested indicators in the latest urine test report of the target patient being affected by the external environment can be evaluated through the obtained environmental impact assessment value, so as to improve the accuracy of subsequent judgments.

[0120] Preferably, in one embodiment of the present invention, the method for obtaining the environmental impact assessment value of the indicator to be measured in the latest urine test report of the target patient specifically includes:

[0121] According to the difference in data deviation of the measured indicator in the latest urine test report between the target patient and each similar patient, the initial deviation difference value of the measured indicator in the latest urine test report between the target patient and each similar patient is obtained. The larger the initial deviation difference value, the greater the deviation of the test data of the measured indicator in the latest urine test report between the target patient and each similar patient, which further indicates that the test data of the measured indicator in the latest urine test report of the target patient is more likely to be interfered by the external environment.

[0122] In one embodiment of the present invention, the absolute value of the difference in data deviation of the measured indicator in the latest urine test report between the target patient and each similar patient can be used as the initial deviation difference value of the measured indicator in the latest urine test report between the target patient and each similar patient, so as to analyze the difference between the two.

[0123] Then, the physical sign similarity between the target patient and each similar patient is used as the confidence level, and the initial deviation difference value is weighted by the physical sign similarity to obtain the actual deviation difference value of the measured indicator in the latest urine test report between the target patient and each similar patient.

[0124] Finally, the overall level of the actual deviation difference values ​​of the measured indicators in the latest urine test reports between the target patient and all similar patients was analyzed and normalized to obtain the environmental impact assessment values ​​of the measured indicators in the latest urine test reports of the target patient.

[0125] In an embodiment of the present invention, the overall level analysis of the true deviation difference values ​​of the measured indicators in the latest urine test reports between the target patient and all similar patients can be achieved by calculating the average or median of the true deviation difference values ​​of the measured indicators in the latest urine test reports between the target patient and all similar patients, which is not limited here.

[0126] The expression of the environmental impact assessment value of the indicator to be measured in the latest urine test report of the target patient can be specifically, for example, as follows:

[0127]

[0128] in, Indicates the environmental impact assessment value of the indicator to be tested in the latest urine test report of the target patient; Indicates the target patient and Similarity of physical signs between similar patients; Indicates the data deviation of the target patient's latest urine test report; Indicates The data deviation of the measured indicators in the latest urine test reports of similar patients; represents the number of similar patients; Indicates the target patient and The initial deviation difference value of the measured index in the latest urine test report between similar patients; Indicates the target patient and The actual deviation difference value of the measured index in the latest urine test report between similar patients; Represents the normalization function.

[0129] Step S4: Based on the environmental impact assessment value, assess whether the test data of the target patient's latest urine test report is affected by the external environment.

[0130] The environmental impact assessment value obtained as mentioned above can accurately reflect the possibility that the test data of the target indicator in the latest urine test report of the target patient is affected by the external environment. The larger the environmental impact assessment value is, the more likely the test data of the target indicator in the latest urine test report of the target patient is affected by the external environment, causing a large deviation and abnormality in the test data, rather than the target patient himself suffering from related diseases, causing a large deviation and abnormality in the test data. Therefore, based on the environmental impact assessment value, whether the test data of the target indicator in the latest urine test report of the target patient is affected by the external environment can be accurately assessed.

[0131] Preferably, in one embodiment of the present invention, the method for evaluating whether the detection data of the target patient's latest urine test report is affected by the external environment specifically includes:

[0132] If the environmental impact assessment value is greater than the preset threshold, it is considered that the test data of the indicator to be tested in the target patient's latest urine test report is affected by the external environment. This means that during this urine test, the urine sample of the target patient was affected by the external environment, resulting in abnormal test data of the indicator to be tested. In this case, the target patient needs to be notified to undergo another urine test and re-obtain the test data of the indicator to be tested. Otherwise, it is considered that the test data of the indicator to be tested in the target patient's latest urine test report is not affected by the external environment.

[0133] In one embodiment of the present invention, the preset threshold is set to 0.8. The specific value of the preset threshold can also be set by the implementer according to the specific implementation scenario and is not limited here.

[0134] By using the same method as above, it is possible to accurately assess whether the test data of each indicator in each patient's latest urine test report is abnormal due to the influence of the external environment.

[0135] An embodiment of the present invention provides an intelligent processing system for urology diagnosis and treatment data, the system includes a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement the method described in steps S1 to S4.

[0136] In summary, the embodiment of the present invention first obtains the latest urine test report and diagnosis and treatment recommendations of different patients' current urine tests, and obtains historical urine test reports of different patients for each urine test within a preset historical time period, wherein both the latest urine test report and the historical urine test reports include the test date and the test data of different indicators; any one of the patients is taken as the target patient, and any indicator is taken as the indicator to be tested, and the data deviation of the indicator to be tested in the latest urine test report of the target patient is obtained according to the difference in the test data of the indicator to be tested between the latest urine test report of the target patient and the historical urine test reports of each urine test and the difference in the test date; other patients except the target patient are taken as reference patients, and the difference in the test date is obtained according to the difference in the test data of the indicator to be tested between the target patient and each reference patient. The similarity of physical signs between the target patient and each reference patient is obtained based on the differences in the test data of the same indicator between the historical urine test reports of the same urine test of the patient, the differences in the test dates, and the differences in the content information of the diagnosis and treatment recommendations between the target patient and each reference patient; based on the similarity of physical signs, similar patients are selected from all reference patients; based on the differences in the data deviations of the indicators to be tested in the latest urine test reports between the target patient and similar patients and the similarity of physical signs, the environmental impact assessment value of the indicators to be tested in the latest urine test report of the target patient is obtained; based on the environmental impact assessment value, whether the test data of the indicators to be tested in the latest urine test report of the target patient is affected by the external environment is evaluated.

[0137] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for intelligent processing of urology diagnosis and treatment data, characterized in that: The method comprises: Obtain the latest urine test report and diagnosis and treatment recommendations for different patients' current urine tests, and obtain historical urine test reports for each urine test of different patients within a preset historical time period, wherein both the latest urine test report and the historical urine test reports include the test date and test data of different indicators; Taking any patient as the target patient and any indicator as the indicator to be tested, according to the difference of the test data of the indicator to be tested between the latest urine test report of the target patient and the historical urine test reports of each urine test and the difference of the test dates, obtaining the data deviation of the indicator to be tested in the latest urine test report of the target patient; Patients other than the target patient are taken as reference patients, and the physical sign similarity between the target patient and each reference patient is obtained based on the difference in the test data of the same indicator between the historical urine test reports of the target patient and each reference patient, the difference in the test date, and the difference in the content information of the diagnosis and treatment recommendation between the target patient and each reference patient; based on the physical sign similarity, similar patients are selected from all reference patients; based on the difference in the data deviation of the indicator to be tested in the latest urine test report between the target patient and similar patients and the physical sign similarity, the environmental impact assessment value of the indicator to be tested in the latest urine test report of the target patient is obtained; Based on the environmental impact assessment value, assess whether the test data of the target patient's latest urine test report is affected by the external environment; The data deviation of the target patient's latest urine test report includes: Obtaining the initial data difference of the target patient's latest urine test report and each historical urine test report based on the difference of the test data of the target patient's latest urine test report and each historical urine test report; According to the difference in the test date between the latest urine test report of the target patient and each historical urine test report, the initial data difference is adjusted to obtain the real data difference of the indicator to be tested between the latest urine test report of the target patient and each historical urine test report; Analyze the overall level of the difference of the real data of the target patient's latest urine test report and all historical urine test reports to obtain the data deviation of the target patient's latest urine test report; The obtaining of the similarity of physical signs between the target patient and each reference patient comprises: Any reference patient is used as the reference patient to be tested; Obtaining a first physical sign similarity factor between the target patient and the reference patient to be tested based on the difference in the test data of the same indicator and the difference in the test date between the historical urine test reports of the target patient and the reference patient to be tested for the same urine test; Obtaining a second physical sign similarity factor between the target patient and the reference patient to be tested according to the difference in content information of the diagnosis and treatment recommendation between the target patient and the reference patient to be tested; The first physical sign similarity factor and the second physical sign similarity factor are integrated and normalized to obtain the physical sign similarity between the target patient and the reference patient to be tested; The environmental impact assessment value of the indicator to be tested in the latest urine test report of the target patient is obtained, including: Obtaining an initial deviation difference value of the indicator to be measured in the latest urine test report between the target patient and each similar patient according to the difference in the data deviation of the indicator to be measured in the latest urine test report between the target patient and each similar patient; Using the similarity of the physical signs between the target patient and each similar patient, the initial deviation difference value is weighted to obtain the actual deviation difference value of the indicator to be measured in the latest urine test report between the target patient and each similar patient; The overall level of the true deviation difference value of the target patient's target indicator in the latest urine test report is analyzed and normalized to obtain the environmental impact assessment value of the target patient's target indicator in the latest urine test report.

2. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: The actual data difference between the latest urine test report of the target patient and each historical urine test report includes: Obtaining a first time interval between the target patient's latest urine test report and each historical urine test report according to the difference in the test date between the target patient's latest urine test report and each historical urine test report; Performing negative correlation normalization processing on the first time interval to obtain a first confidence level between the latest urine test report of the target patient and each historical urine test report; The initial data difference is weighted by using the first confidence level to obtain the real data difference of the indicator to be measured between the latest urine test report of the target patient and each historical urine test report.

3. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: The obtaining of the first physical sign similarity factor between the target patient and the reference patient to be tested comprises: The two historical urine test reports of the same urine test of the target patient and the reference patient to be tested are used as one urine test report group; According to the difference of the detection data of the same indicator between two historical urine test reports in each urine test report group, the data difference parameter of each indicator of each urine test report group is obtained; the data difference parameters of all indicators of each urine test report group are integrated to obtain the initial integrated difference value of each urine test report group; According to the difference in the test date between the two historical urine test reports in each urine test report group, a second time interval of each urine test report group is obtained; and the second time interval is subjected to negative correlation normalization processing to obtain a second confidence level of each urine test report group; Using the second confidence level, weighting the initial comprehensive difference value to obtain a true comprehensive difference value for each urine test report group; The true comprehensive difference values ​​of all urine test report groups are integrated and normalized for negative correlation to obtain the first physical sign similarity factor between the target patient and the reference patient to be tested.

4. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: The obtaining of the second physical sign similarity factor between the target patient and the reference patient to be tested comprises: Performing natural language processing on the diagnosis and treatment recommendations for the target patient and the reference patient to be tested, respectively, to obtain keywords in the diagnosis and treatment recommendations for the target patient and the reference patient to be tested and a word vector for each keyword; Randomly select a keyword from the diagnosis and treatment recommendations for the target patient, and randomly select a keyword from the diagnosis and treatment recommendations for the reference patient to be tested, and use the two selected keywords as a keyword group; The cosine similarity of the word vectors of the two keywords in each keyword group is used as the word similarity of each keyword group; The overall level of the word similarity of all keyword groups is analyzed to obtain the second physical sign similarity factor between the target patient and the reference patient to be tested.

5. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: Based on the similarity of the physical signs, similar patients are selected from all reference patients, including: Select a preset number of reference patients corresponding to the largest physical sign similarities as similar patients.

6. The intelligent processing method for urology diagnosis and treatment data according to claim 1, characterized in that: The step of evaluating whether the test data of the target patient's latest urine test report is affected by the external environment based on the environmental impact assessment value includes: If the environmental impact assessment value is greater than a preset threshold, it is considered that the detection data of the target patient's latest urine test report's target indicator is affected by the external environment; otherwise, it is considered that the detection data of the target patient's latest urine test report's target indicator is not affected by the external environment.

7. An intelligent processing system for urology diagnosis and treatment data, the system 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 according to any one of claims 1 to 6 are implemented.