Clinical data set classification method, electronic equipment and storage medium

Abstract

The invention discloses a clinical data set classification method, electronic equipment and a storage medium, and relates to the technical field of data classification, and the method comprises the steps: pre-classifying all clinical data; analyzing the clinical data by using a clinical symptom analysis method to obtain clinical necessary symptoms and clinical secondary symptoms, establishing a symptom analysis table, obtaining misjudgeable symptoms of clinical symptoms, and classifying all the clinical data; the method is used for solving the problems that an existing classification method for clinical data sets cannot effectively solve the problem that after a doctor makes contact with a patient, corresponding clinical data cannot be obtained in time for reference on the basis of patient symptoms, or although the symptoms in the referenced clinical data are consistent with the patient symptoms, the disease causes are different from those of the patient; and thus, the problem that the patient cannot be judged in time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data classification, and in particular to a clinical data set classification method, electronic equipment and storage medium. Background Art

[0002] Clinical data sets are clinical case data collected and organized to support the research and application of clinical program analysis; clinical data sets contain various clinical data, such as basic information of patients, hospitalization records, drug treatment and laboratory test results, etc., which can support various types of clinical program analysis research; clinical data sets mainly include: safety analysis set, intention-to-treat analysis set and per-protocol analysis set; these classifications are mainly to meet the needs of different aspects of clinical trials, including evaluation of treatment effects, assessment of safety and maintaining the integrity of the study design.

[0003] Existing methods for classifying clinical data sets usually extract samples from clinical data and add different category labels to the clinical data, and then use the labeled clinical data and other clinical data for training, so as to improve the classification performance of clinical data; although this classification method can classify clinical data based on different clinical data categories, it cannot classify the clinical data after effectively processing the content of the clinical data, resulting in the inability of doctors to obtain corresponding clinical data for reference based on the patient's symptoms in a timely manner after contacting the patient, or the symptoms in the referenced clinical data are consistent with the patient's symptoms but the cause is different from the patient, which leads to the problem that the patient cannot be judged in a timely manner. For example, in the patent application with publication number CN110400610A, a method based on A small sample clinical data classification method and system based on multi-channel random forests. This solution is to train the classifier by using labeled amplification data and clinical data to form a training data set, thereby improving its classification performance for clinical samples. Other improvements in the classification of clinical data sets usually classify different clinical data sets for different clinical trials, and the classification results are usually related to the medication used in the clinical trials. This still cannot effectively solve the problem that after doctors contact patients, they cannot obtain corresponding clinical data for reference based on the patient's symptoms in a timely manner, or the symptoms in the reference clinical data are consistent with the patient's symptoms but the cause is different from that of the patient, which leads to the inability to make timely judgments on the patient. In view of this, it is necessary to improve the existing classification methods for clinical data sets. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by proposing a clinical data set classification method, an electronic device and a storage medium, so as to solve the problem that the existing classification method for clinical data sets cannot effectively solve the problem that after the doctor contacts the patient, the corresponding clinical data cannot be obtained in time for reference based on the patient's symptoms, or the symptoms in the reference clinical data are consistent with the patient's symptoms but the cause is different from that of the patient, which leads to the inability to make a timely judgment on the patient.

[0005] To achieve the above objectives, in a first aspect, the present application provides a clinical data set classification method, comprising the following steps:

[0006] Acquire clinical data to be classified, and pre-classify all clinical data based on the departments to which the clinical data corresponds, wherein the pre-classification is used to record the departments to which the clinical data corresponds as the source departments of the clinical data;

[0007] Analyze the clinical data using the clinical symptom analysis method, record the symptoms of the patients in the clinical data as clinical symptoms, and obtain the clinically necessary symptoms and clinically minor symptoms in the clinical data based on the analysis results;

[0008] Establish a symptom analysis table to obtain the misdiagnosed symptoms of clinical diseases based on the clinically necessary symptoms and clinically minor symptoms of clinical data;

[0009] All clinical conditions are analyzed for misdiagnosed conditions, and all clinical data are classified based on the analysis results.

[0010] Furthermore, the clinical symptom analysis method includes:

[0011] The analysis number is set for all clinical data, and the analysis number of all clinical data is initially 0; for any clinical data with an analysis number of 0, the department where the clinical data is located is recorded as the clinical department;

[0012] All clinical data corresponding to the clinical departments are recorded as analysis data FX1 to analysis data FX n ; For any analysis data FX n1 , based on text extraction to obtain analytical data FX n1 All patient symptoms in the clinical condition LB1 to clinical condition LB k ; Where n is the type of clinical data and k is the type of patient symptoms.

[0013] Furthermore, the clinical symptom analysis method also includes:

[0014] Establish a plane rectangular coordinate system, recorded as the disease differentiation coordinate system, where the unit of the Y axis of the disease differentiation coordinate system is quantity, and the coordinates to the right of the origin in the X axis are filled in clinical disease LB1 to clinical disease LBk ; Extract patient symptoms from all analysis data FX, for any clinical condition LB k1 , obtain LB containing clinical symptoms k1 The number of analysis data is recorded as p1, and the point in the disease analysis coordinate system (clinical disease LB k1 , p1) is recorded as the disease point BZ k1 ;

[0015] Obtain the symptom points BZ corresponding to all clinical symptoms LB, and record the straight line fitted by all symptom points BZ as the symptom straight line, where the horizontal coordinates of the leftmost point and the rightmost point of the symptom straight line are clinical symptom LB1 and clinical symptom LB respectively. k ; Draw a straight line parallel to the X-axis from the midpoint of the symptom line and record it as the span dividing line.

[0016] Furthermore, the clinical symptom analysis method also includes:

[0017] The disease point BZ with the largest ordinate and the smallest ordinate among all the disease points BZ are recorded as the peak point and the valley point respectively; the line connecting the peak point and the valley point is recorded as the disease span line; the disease span line is translated so that the valley point coincides with the origin of the coordinate system, and the sine of the angle less than 90 degrees between the disease span line and the X-axis is recorded as the span line sine value.

[0018] Furthermore, the clinical symptom analysis method also includes:

[0019] The value of the peak point divided by n is recorded as the peak ratio; when the peak ratio is greater than or equal to the cross-line sine value, the horizontal coordinate of the valley point is marked as the clinical data FX n1 The necessary clinical symptoms are marked as clinical data FX. n1 Clinical minor symptoms;

[0020] When the peak ratio is less than the sine value of the span line, the horizontal coordinates of all symptom points BZ between the span dividing line and the X-axis are marked as clinical data FX. n1 The clinically necessary symptoms are recorded as secondary points, and the horizontal coordinates of all the symptom points BZ that are not recorded as clinically necessary symptoms are marked as secondary points, and the horizontal coordinates of the secondary points are marked as clinical data FX n1 Clinical minor symptoms;

[0021] Obtain clinically necessary symptoms and clinically minor symptoms corresponding to all analysis data FX. When any analysis data FX obtains clinically necessary symptoms and clinically minor symptoms, adjust the analysis number of the analysis data FX to 1.

[0022] Furthermore, the clinical symptom analysis method also includes:

[0023] When the analysis number of all clinical data is 1, all different clinical symptoms LB corresponding to all clinical data are obtained and put into set A;

[0024] A table of T rows × R columns is established, which is recorded as a misjudgment analysis table, wherein the top row of the misjudgment analysis table is filled with all clinical symptoms LB in set A from left to right except the first cell, and the leftmost column of the misjudgment analysis table is filled with all clinical data from top to bottom except the first cell;

[0025] Get two markings that can be made in the table and record them as γ1 and γ2 respectively;

[0026] In the misjudgment analysis table: for any clinical data, the grid where the row where the clinical data is located intersects with the column where all the clinically necessary symptoms of the clinical data are located is marked as γ1; the grid where the row where the clinical data is located intersects with the column where all the clinically minor symptoms of the clinical data are located is marked as γ2; based on the clinically necessary symptoms and clinically minor symptoms corresponding to all clinical data, mark the rows where all clinical data are located;

[0027] In the misjudgment analysis table after marking with γ1 and γ2: for any clinical symptom LB, the misjudgment analysis algorithm is used to obtain the misjudgment analysis coefficient corresponding to the clinical symptom LB. The misjudgment analysis algorithm is: Among them, F is the misjudgment analysis coefficient, f1 is the number of grids marked as γ1 in the column where the clinical condition LB is located, and f2 is the number of grids marked as γ2 in the column where the clinical condition LB is located.

[0028] Furthermore, the clinical symptom analysis method also includes:

[0029] Obtain the misjudgment analysis coefficients corresponding to all clinical symptoms LB; record the clinical symptoms LB with a misjudgment analysis coefficient of 1 as the main influencing symptom, record the clinical symptoms LB with a misjudgment analysis coefficient of 0 as the secondary influencing symptom, and record the clinical symptoms LB with a misjudgment analysis coefficient less than 1 and greater than 0 as the mixed influencing symptom;

[0030] When the number of cells marked as γ1 in the column where the main influencing symptom is located is 1, the main influencing symptom is recorded as the only symptom; when the number of cells marked as γ2 in the column where the secondary influencing symptom is located is 1, the secondary influencing symptom is recorded as the only symptom;

[0031] The number of main influencing symptoms that are not recorded as the only symptom is recorded as A1, the number of secondary influencing symptoms that are not recorded as the only symptom is recorded as A2, and the number of mixed influencing symptoms is recorded as A0; the value of A1 divided by A0 is recorded as the main judgment value, and the value of A2 divided by A0 is recorded as the secondary judgment value;

[0032] For any mixed-effect disease, the value obtained by dividing the number of grids marked as γ1 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the primary self-judgment value, and the value obtained by dividing the number of grids marked as γ2 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the secondary self-judgment value;

[0033] When the primary self-judgment value was greater than or equal to the primary judgment value or the secondary self-judgment value was greater than or equal to the secondary judgment value, the mixed-effect disease was recorded as a misjudged disease;

[0034] All major effect conditions that were not recorded as the only condition and minor effect conditions were recorded as misclassified conditions.

[0035] Furthermore, all clinical symptoms that may be misdiagnosed are analyzed, and all clinical data are classified based on the analysis results, including:

[0036] For any clinical data, when there is no misjudged disease in the clinical disease LB corresponding to the clinical data, the clinical data is classified as a non-misjudged disease type;

[0037] When there are misdiagnosed diseases in the clinical disease LB corresponding to the clinical data and they are all major influencing diseases, the clinical data are classified as the major disease misdiagnosis type;

[0038] When there are misdiagnosed diseases in the clinical disease LB corresponding to the clinical data and they are all secondary impact diseases, the clinical data is classified as a secondary disease misdiagnosis type;

[0039] When there are misdiagnosed symptoms and mixed-effect symptoms in the clinical symptoms LB corresponding to the clinical data, the clinical data are classified into the primary and secondary symptom misdiagnosis type.

[0040] In a second aspect, the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0041] In a third aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0042] Beneficial effects of the present invention: The present invention first obtains clinical data to be classified, and pre-classifies all clinical data based on the departments corresponding to the clinical data. The pre-classification is used to record the departments corresponding to the clinical data as the source departments of the clinical data; then the clinical data are analyzed using a clinical symptom analysis method, the symptoms of the patients in the clinical data are recorded as clinical symptoms, and the clinically necessary symptoms and clinically minor symptoms in the clinical data are obtained based on the analysis results. The advantage of this is that the clinical symptoms that can represent the clinical data and the clinical symptoms that will generally appear in other clinical data, i.e., clinically necessary symptoms and clinically minor symptoms, can be effectively obtained from all clinical symptoms corresponding to each clinical data, so that the differences between each clinical data can be obtained, which is helpful for doctors to effectively obtain clinical data that matches the patient's symptoms when using the clinical data for reference, and prevent the problem of delayed treatment or wrong treatment;

[0043] The present invention also establishes a symptom analysis table to obtain the misdiagnosed symptoms of clinical symptoms based on the clinically necessary symptoms and clinical minor symptoms of the clinical data, and finally analyzes the misdiagnosed symptoms of all clinical symptoms, and classifies all clinical data based on the analysis results. The advantage of this is that by obtaining the misdiagnosed symptoms of clinical symptoms and classifying the clinical data based on the misdiagnosed symptoms, it can ensure that the classified clinical data can help doctors judge whether there is a possibility of misdiagnosis while assisting doctors in diagnosis and treatment, thereby reducing the frequency of misdiagnosis by doctors and effectively treating patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a principle block diagram of the method of the present invention;

[0045] Figure 2 A schematic diagram of a coordinate system for distinguishing diseases of the present invention;

[0046] Figure 3 It is a schematic diagram of obtaining the cross-line sine value of the present invention;

[0047] Figure 4 It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1, first aspect, please refer to Figure 1As shown, the present application provides a clinical data set classification method, comprising the following steps:

[0050] Step S1, obtaining clinical data to be classified, pre-classifying all clinical data based on the departments corresponding to the clinical data, and pre-classifying is used to record the departments corresponding to the clinical data as the source departments of the clinical data; in the specific implementation process, considering that patients give priority to choosing the department to be treated when visiting a doctor, the pre-classification in this embodiment adopts recording the department corresponding to the clinical data as the source department of the clinical data, so as to preliminarily classify the clinical data based on the source departments of all clinical data, and the source departments may include: gastroenterology, urology, otolaryngology, pediatrics, surgery and other departments in the hospital. In the specific implementation, the clinical data can be pre-classified according to the actual classification needs, such as based on the classification criteria such as the site of the patient's injury in the clinical data, the time of the patient's medical treatment in the clinical data, and the frequency of the patient's symptoms in the clinical data;

[0051] Step S2, using a clinical symptom analysis method to analyze the clinical data, recording the patient's symptoms in the clinical data as clinical symptoms, and obtaining clinically necessary symptoms and clinically minor symptoms in the clinical data based on the analysis results; establishing a symptom analysis table, and obtaining misdiagnosed symptoms of clinical symptoms based on the clinically necessary symptoms and clinically minor symptoms of the clinical data;

[0052] The clinical symptom analysis method includes: step S201, setting an analysis number for all clinical data, and the analysis number of all clinical data is initially 0; for any clinical data with an analysis number of 0, the department where the clinical data is located is recorded as the clinical department;

[0053] Step S202: record all clinical data corresponding to the clinical departments as analysis data FX1 to analysis data FX2. n ; For any analysis data FX n1 , based on text extraction to obtain analytical data FX n1 All patient symptoms in the clinical condition LB1 to clinical condition LB k ;; Where n is the type of clinical data, and k is the type of patient symptoms; in a specific implementation process, for example, in a data processing, all patient symptoms in an analysis data FX obtained include: dizziness, nausea, stomachache, and limb weakness, then the value of k is 4, and clinical symptoms LB1 to clinical symptoms LB4 are dizziness, nausea, stomachache, and limb weakness, respectively;

[0054] In the specific implementation process, the "patient symptoms" in the analysis data FX or the patient symptoms filled in by the doctor can be identified through text extraction, and the text extraction can be trained according to the content composition of the actual analysis data FX before extraction to ensure the validity of the obtained patient symptoms;

[0055] Step S203, establish a plane rectangular coordinate system, recorded as the disease differentiation coordinate system, wherein the unit of the Y axis of the disease differentiation coordinate system is quantity, and the coordinates to the right of the origin in the X axis are filled in clinical disease LB1 to clinical disease LB k ; Extract patient symptoms from all analysis data FX, for any clinical condition LB k1 , obtain LB containing clinical symptoms k1 The number of analysis data is recorded as p1, and the point in the disease analysis coordinate system (clinical disease LB k1 , p1) is recorded as the disease point BZ k1 ;

[0056] In the specific implementation process, for example, the disease differentiation coordinate system obtained in a data processing is as follows Figure 2 As shown, the value of k is 5, all the symptom points BZ are BZ1 to BZ5, LB1 to LB5 are clinical symptoms LB1 to clinical symptoms LB5, and through analysis, the symptom line is LL1, the midpoint of the line LL1 is DD1, the span dividing line is LL2, the peak point is point BZ2, and the valley point is point BZ4; after stripping the peak point and the valley point, please refer to Figure 3 As shown, the disease span line is LL3, the angle between the disease span line and the X-axis is less than 90 degrees, and the span line sine value is The peak ratio is calculated to be 1, and the peak ratio is greater than The abscissa LB4 of BZ4 is recorded as the clinically necessary symptom of the clinical data FX, and LB1, LB2, LB3 and LB5 are recorded as the clinically minor symptoms of the clinical data FX;

[0057] Step S204, obtaining the symptom points BZ corresponding to all clinical symptoms LB, and recording the straight line fitted by all symptom points BZ as the symptom straight line, wherein the horizontal coordinates of the leftmost point and the rightmost point of the symptom straight line are clinical symptom LB1 and clinical symptom LB respectively. k ; Draw a straight line parallel to the X-axis from the midpoint of the symptom line and record it as the span dividing line;

[0058] Step S205, the disease point BZ with the largest ordinate and the smallest ordinate among all the disease points BZ are recorded as the peak point and the valley point respectively; the line connecting the peak point and the valley point is recorded as the disease span line; the disease span line is translated so that the valley point coincides with the origin of the coordinates, and the sine of the angle between the disease span line and the X-axis that is less than 90 degrees is recorded as the span line sine value;

[0059] Step S206, the value of dividing the ordinate of the peak point by n is recorded as the peak proportion value; when the peak proportion value is greater than or equal to the cross-line sine value, the horizontal coordinate of the valley point is marked as the clinical data FX n1The necessary clinical symptoms are marked as clinical data FX. n1 Clinical minor symptoms;

[0060] Step S207: When the peak ratio is less than the span sine value, the horizontal coordinates of all the symptom points BZ between the span dividing line and the X-axis are marked as clinical data FX. n1 The clinically necessary symptoms are recorded as secondary points, and the horizontal coordinates of all the symptom points BZ that are not recorded as clinically necessary symptoms are marked as secondary points, and the horizontal coordinates of the secondary points are marked as clinical data FX n1 Clinical minor symptoms;

[0061] In the specific implementation process, by obtaining clinically necessary symptoms and clinically minor symptoms, the differences between each clinical data can be obtained, which helps doctors to effectively obtain clinical data that matches the patient's condition when using clinical data for reference, thereby preventing delayed treatment or erroneous treatment.

[0062] Step S208, obtaining clinically necessary symptoms and clinically minor symptoms corresponding to all analysis data FX, and when any analysis data FX obtains clinically necessary symptoms and clinically minor symptoms, adjusting the analysis number of the analysis data FX to 1;

[0063] Step S209, when the analysis number of all clinical data is 1, all different clinical symptoms LB corresponding to all clinical data are obtained and put into set A;

[0064] Step S210, establish a table of T rows × R columns, recorded as a misjudgment analysis table, wherein the top row of the misjudgment analysis table is filled with all clinical symptoms LB in set A from left to right except the first cell, and the leftmost column of the misjudgment analysis table is filled with all clinical data from top to bottom except the first cell. In specific implementation, the value of T is the number of all clinical data plus 1, and the value of R is the number of all clinical symptoms LB plus 1. For example, the misjudgment analysis table constructed in one analysis is as follows: Figure 1 : As shown in the misjudgment analysis table;

[0065] Figure 1 : Misjudgment analysis table

[0066] Clinical symptoms LB1 Clinical symptoms LB2 Clinical symptoms LB3 Clinical symptoms LB4 Clinical Data 1 <![CDATA[γ2]]> <![CDATA[γ2]]> <![CDATA[γ1]]> Clinical Data 2 <![CDATA[γ2]]> <![CDATA[γ2]]> <![CDATA[γ1]]> Clinical Data 3 <![CDATA[γ2]]> <![CDATA[γ2]]> <![CDATA[γ1]]> <![CDATA[γ2]]>

[0067] Step S211, obtaining two marks that can be performed in the table, and recording them as γ1 and γ2 respectively;

[0068] Step S212, in the misjudgment analysis table: for any clinical data, mark the grid where the row where the clinical data is located intersects with the column where all the clinical necessary symptoms of the clinical data are located as γ1; mark the grid where the row where the clinical data is located intersects with the column where all the clinical minor symptoms of the clinical data are located as γ2; based on the clinical necessary symptoms and clinical minor symptoms corresponding to all the clinical data, mark the rows where all the clinical data are located;

[0069] Step S213, in the misjudgment analysis table after being marked with γ1 and γ2: for any clinical symptom LB, a misjudgment analysis algorithm is used to obtain a misjudgment analysis coefficient corresponding to the clinical symptom LB, and the misjudgment analysis algorithm is: Among them, F is the misjudgment analysis coefficient, f1 is the number of grids marked as γ1 in the column where the clinical condition LB is located, and f2 is the number of grids marked as γ2 in the column where the clinical condition LB is located;

[0070] In the specific implementation process, for example, during a data processing, the number of grids marked as γ1 in the column where the clinical symptom LB is located is 2, and the number of grids marked as γ2 in the column where the clinical symptom LB is located is 1. Then, by calculation, the misjudgment analysis coefficient is about 0.67, and the clinical symptom LB is recorded as a mixed influence symptom;

[0071] Step S214, obtaining the misjudgment analysis coefficients corresponding to all clinical symptoms LB; recording the clinical symptoms LB with a misjudgment analysis coefficient of 1 as the main influencing symptom, recording the clinical symptoms LB with a misjudgment analysis coefficient of 0 as the secondary influencing symptom, and recording the clinical symptoms LB with a misjudgment analysis coefficient less than 1 and greater than 0 as the mixed influencing symptom;

[0072] Step S215, when the number of grids marked as γ1 in the column where the main influencing symptom is located is 1, the main influencing symptom is recorded as the only symptom; when the number of grids marked as γ2 in the column where the secondary influencing symptom is located is 1, the secondary influencing symptom is recorded as the only symptom;

[0073] Step S216, record the number of main influencing symptoms that are not recorded as the only symptom as A1, record the number of secondary influencing symptoms that are not recorded as the only symptom as A2, and record the number of mixed influencing symptoms as A0; record the value of A1 divided by A0 as the main judgment value, and record the value of A2 divided by A0 as the secondary judgment value;

[0074] Step S217, for any mixed-effect disease, the value obtained by dividing the number of grids marked as γ1 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the primary self-judgment value, and the value obtained by dividing the number of grids marked as γ2 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the secondary self-judgment value;

[0075] In summary of the specific implementation process, for example, when A1 is 3, A2 is 1, and A0 is 5 in a data processing, the main judgment value is 0.6 and the secondary judgment value is 0.2 through calculation; the main self-judgment value and the secondary self-judgment value of the mixed-effect disease are 0.2 and 0.3 respectively, and through analysis, it can be obtained that the mixed-effect disease is recorded as a misjudged disease. When the mixed-effect disease is recorded as a misjudged disease, it means that the mixed-effect disease may be misdiagnosed as other diseases due to its main clinical disease or secondary clinical disease, so that the patient cannot be treated in time;

[0076] Step S218, when the primary self-judgment value is greater than or equal to the primary judgment value or the secondary self-judgment value is greater than or equal to the secondary judgment value, the mixed-influence disease is recorded as a misjudged disease;

[0077] Step S219: All major influencing symptoms and minor influencing symptoms that are not recorded as the only symptom are recorded as misdiagnosed symptoms.

[0078] Step S3, analyzing the misdiagnosed symptoms of all clinical symptoms, and classifying all clinical data based on the analysis results; Step S3 includes:

[0079] Step S301, for any clinical data, when there is no misjudged disease in the clinical disease LB corresponding to the clinical data, classify the clinical data into a non-misjudged disease type;

[0080] Step S302, when there are misdiagnosed symptoms in the clinical symptoms LB corresponding to the clinical data and they are all major influencing symptoms, the clinical data is classified as a major symptom misdiagnosis type;

[0081] Step S303, when there are misdiagnosed symptoms in the clinical symptoms LB corresponding to the clinical data and they are all secondary affecting symptoms, the clinical data is classified as a secondary symptom misdiagnosis type;

[0082] Step S304: when there are misdiagnosed symptoms and mixed influencing symptoms in the clinical symptoms LB corresponding to the clinical data, the clinical data is classified into the primary and secondary misdiagnosis types; in the specific implementation process, for example, in one data processing, it is obtained that there are misdiagnosed symptoms in all clinical symptoms LB corresponding to the clinical data, and all clinical symptoms LB are primary influencing symptoms, then the clinical data is classified as the primary misdiagnosis type;

[0083] In this embodiment, the clinical data classified as the type of symptoms that cannot be misdiagnosed are data that can directly judge the symptoms based on the patient's symptoms, while the clinical data classified as the major symptom misdiagnosis type, the minor symptom misdiagnosis type, and the primary and secondary symptom misdiagnosis type are data that may be misdiagnosed due to the patient's symptoms. This helps doctors judge whether there is a possibility of misdiagnosis when using clinical data for reference, thereby reducing the frequency of misdiagnosis by doctors and providing effective treatment for patients.

[0084] Example 2, please refer to Figure 4 As shown, Figure 4 The structural diagram of an electronic device is illustrated, and the electronic device may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor may call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a clinical data set classification method are executed to achieve the following functions: firstly, clinical data to be classified are obtained, and all clinical data are pre-classified based on the departments corresponding to the clinical data, and the pre-classification is used to record the departments corresponding to the clinical data as the source departments of the clinical data; then, the clinical data are analyzed using a clinical symptom analysis method, and the symptoms of the patients in the clinical data are recorded as clinical symptoms, and the clinical necessary symptoms and clinical minor symptoms in the clinical data are obtained based on the analysis results, and the misjudged symptoms of the clinical symptoms are obtained based on the clinical necessary symptoms and clinical minor symptoms of the clinical data by establishing a symptom analysis table, and finally, the misjudged symptoms of all clinical symptoms are analyzed, and all clinical data are classified based on the analysis results.

[0085] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0086] Embodiment 3. The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a clinical data set classification method provided by the above methods, the method including: first, obtaining clinical data to be classified, pre-classifying all clinical data based on the department corresponding to the clinical data, and the pre-classification is used to record the department corresponding to the clinical data as the source department of the clinical data; then using the clinical symptom analysis method to analyze the clinical data, recording the symptoms of the patients in the clinical data as clinical symptoms, and obtaining clinically necessary symptoms and clinically minor symptoms in the clinical data based on the analysis results, and also by establishing a symptom analysis table, obtaining the misjudged symptoms of the clinical symptoms based on the clinically necessary symptoms and clinically minor symptoms of the clinical data; finally, analyzing the misjudged symptoms of all clinical symptoms, and classifying all clinical data based on the analysis results.

[0087] Embodiment 4, the present application also provides a computer-readable storage medium, the present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above clinical data set classification method are executed to achieve the following functions: first, the clinical data to be classified are obtained, and all clinical data are pre-classified based on the department corresponding to the clinical data, and the pre-classification is used to record the department corresponding to the clinical data as the source department of the clinical data; then, the clinical data is analyzed using a clinical symptom analysis method, and the symptoms of the patients in the clinical data are recorded as clinical symptoms, and clinically necessary symptoms and clinically minor symptoms in the clinical data are obtained based on the analysis results, and by establishing a symptom analysis table, the misjudged symptoms of the clinical symptoms are obtained based on the clinically necessary symptoms and clinically minor symptoms of the clinical data; finally, the misjudged symptoms of all clinical symptoms are analyzed, and all clinical data are classified based on the analysis results.

[0088] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0089] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A clinical data set classification method, characterized in that: The steps include: Acquire clinical data to be classified, and pre-classify all clinical data based on the departments to which the clinical data corresponds, wherein the pre-classification is used to record the departments to which the clinical data corresponds as the source departments of the clinical data; Analyze the clinical data using the clinical symptom analysis method, record the symptoms of the patients in the clinical data as clinical symptoms, and obtain the clinically necessary symptoms and clinically minor symptoms in the clinical data based on the analysis results; Establish a symptom analysis table to obtain the misdiagnosed symptoms of clinical diseases based on the clinically necessary symptoms and clinically minor symptoms of clinical data; All clinical conditions are analyzed for misdiagnosed conditions, and all clinical data are classified based on the analysis results.

2. A clinical data set classification method according to claim 1, characterized in that: Clinical symptom analysis includes: The analysis number is set for all clinical data, and the analysis number of all clinical data is initially 0; for any clinical data with an analysis number of 0, the department where the clinical data is located is recorded as the clinical department; All clinical data corresponding to the clinical departments are recorded as analysis data FX1 to analysis data FX n ; For any analysis data FX n1 , based on text extraction to obtain analytical data FX n1 All patient symptoms in the clinical condition LB1 to clinical condition LB k ; Where n is the type of clinical data and k is the type of patient symptoms.

3. A clinical data set classification method according to claim 2, characterized in that: Clinical symptom analysis also includes: Establish a plane rectangular coordinate system, recorded as the disease differentiation coordinate system, where the unit of the Y axis of the disease differentiation coordinate system is quantity, and the coordinates to the right of the origin in the X axis are filled in clinical disease LB1 to clinical disease LB k ; Extract patient symptoms from all analysis data FX, for any clinical condition LB k1 , obtain LB containing clinical symptoms k1 The number of analysis data is recorded as p1, and the point in the disease analysis coordinate system (clinical disease LB k1 , p1) is recorded as the disease point BZ k1 ; Obtain the symptom points BZ corresponding to all clinical symptoms LB, and record the straight line fitted by all symptom points BZ as the symptom straight line, where the horizontal coordinates of the leftmost point and the rightmost point of the symptom straight line are clinical symptom LB1 and clinical symptom LB respectively. k ; Draw a straight line parallel to the X-axis from the midpoint of the symptom line and record it as the span dividing line.

4. A clinical data set classification method according to claim 3, characterized in that: Clinical symptom analysis also includes: The disease point BZ with the largest ordinate and the smallest ordinate among all the disease points BZ are recorded as the peak point and the valley point respectively; the line connecting the peak point and the valley point is recorded as the disease span line; the disease span line is translated so that the valley point coincides with the origin of the coordinate system, and the sine of the angle less than 90 degrees between the disease span line and the X-axis is recorded as the span line sine value.

5. A clinical data set classification method according to claim 4, characterized in that: Clinical symptom analysis also includes: The value of the peak point divided by n is recorded as the peak ratio; when the peak ratio is greater than or equal to the cross-line sine value, the horizontal coordinate of the valley point is marked as the clinical data FX n1 The necessary clinical symptoms are marked as clinical data FX. n1 Clinical minor symptoms; When the peak ratio is less than the sine value of the span line, the horizontal coordinates of all symptom points BZ between the span dividing line and the X-axis are marked as clinical data FX. n1 The clinically necessary symptoms are recorded as secondary points, and the horizontal coordinates of all the symptom points BZ that are not recorded as clinically necessary symptoms are marked as secondary points, and the horizontal coordinates of the secondary points are marked as clinical data FX n1 Clinical minor symptoms; Obtain clinically necessary symptoms and clinically minor symptoms corresponding to all analysis data FX. When any analysis data FX obtains clinically necessary symptoms and clinically minor symptoms, adjust the analysis number of the analysis data FX to 1.

6. A clinical data set classification method according to claim 5, characterized in that: Clinical symptom analysis also includes: When the analysis number of all clinical data is 1, all different clinical symptoms LB corresponding to all clinical data are obtained and put into set A; A table of T rows × R columns is established, which is recorded as a misjudgment analysis table, wherein the top row of the misjudgment analysis table is filled with all clinical symptoms LB in set A from left to right except the first cell, and the leftmost column of the misjudgment analysis table is filled with all clinical data from top to bottom except the first cell; Get two markings that can be made in the table and record them as γ1 and γ2 respectively; In the misjudgment analysis table: for any clinical data, the grid where the row where the clinical data is located intersects with the column where all the clinically necessary symptoms of the clinical data are located is marked as γ1; the grid where the row where the clinical data is located intersects with the column where all the clinically minor symptoms of the clinical data are located is marked as γ2; based on the clinically necessary symptoms and clinically minor symptoms corresponding to all clinical data, mark the rows where all clinical data are located; In the misjudgment analysis table after marking with γ1 and γ2: for any clinical symptom LB, the misjudgment analysis algorithm is used to obtain the misjudgment analysis coefficient corresponding to the clinical symptom LB. The misjudgment analysis algorithm is: Among them, F is the misjudgment analysis coefficient, f1 is the number of grids marked as γ1 in the column where the clinical condition LB is located, and f2 is the number of grids marked as γ2 in the column where the clinical condition LB is located.

7. A clinical data set classification method according to claim 6, characterized in that: Clinical symptom analysis also includes: Obtain the misjudgment analysis coefficients corresponding to all clinical symptoms LB; record the clinical symptoms LB with a misjudgment analysis coefficient of 1 as the main influencing symptom, record the clinical symptoms LB with a misjudgment analysis coefficient of 0 as the secondary influencing symptom, and record the clinical symptoms LB with a misjudgment analysis coefficient less than 1 and greater than 0 as the mixed influencing symptom; When the number of cells marked as γ1 in the column where the main influencing symptom is located is 1, the main influencing symptom is recorded as the only symptom; when the number of cells marked as γ2 in the column where the secondary influencing symptom is located is 1, the secondary influencing symptom is recorded as the only symptom; The number of main influencing symptoms that are not recorded as the only symptom is recorded as A1, the number of secondary influencing symptoms that are not recorded as the only symptom is recorded as A2, and the number of mixed influencing symptoms is recorded as A0; the value of A1 divided by A0 is recorded as the main judgment value, and the value of A2 divided by A0 is recorded as the secondary judgment value; For any mixed-effect disease, the value obtained by dividing the number of grids marked as γ1 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the primary self-judgment value, and the value obtained by dividing the number of grids marked as γ2 in the column where the mixed-effect disease is located by the number of all marked grids in the column where the mixed-effect disease is located is recorded as the secondary self-judgment value; When the primary self-judgment value was greater than or equal to the primary judgment value or the secondary self-judgment value was greater than or equal to the secondary judgment value, the mixed-effect disease was recorded as a misjudged disease; All major effect conditions that were not recorded as the only condition and minor effect conditions were recorded as misclassified conditions.

8. A clinical data set classification method according to claim 1, characterized in that: Analyze all clinical symptoms that may be misdiagnosed, and classify all clinical data based on the analysis results, including: For any clinical data, when there is no misjudged disease in the clinical disease LB corresponding to the clinical data, the clinical data is classified as a non-misjudged disease type; When there are misdiagnosed diseases in the clinical disease LB corresponding to the clinical data and they are all major influencing diseases, the clinical data are classified as the major disease misdiagnosis type; When there are misdiagnosed diseases in the clinical disease LB corresponding to the clinical data and they are all secondary impact diseases, the clinical data is classified as a secondary disease misdiagnosis type; When there are misdiagnosed symptoms and mixed-effect symptoms in the clinical symptoms LB corresponding to the clinical data, the clinical data are classified into the primary and secondary symptom misdiagnosis type.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images