Traditional Chinese medicine reproductive endocrine disease diagnosis auxiliary system based on clinical knowledge map

Abstract

The invention belongs to the technical field of disease auxiliary diagnosis, and particularly relates to a traditional Chinese medicine reproductive endocrine disease diagnosis auxiliary system based on a clinical knowledge graph. Disease environment information collection of a patient is increased when the reproductive knowledge graph is constructed by integrating medical records of the reproductive disease patient, and correlation analysis is carried out aiming at the disease environment; the method comprises the following steps: inputting a disease symptom of a patient to identify a risk disease environment, creating a search platform based on a reproductive knowledge graph, judging whether the matching is successful or not by matching the input disease symptom of the patient with the reproductive knowledge graph, and outputting an optimal treatment path matched with the symptom of the patient when the matching is successful; and when the matching fails, the disease environment information of the patient is input to be matched with the reproductive knowledge graph, and then the potential reproductive disease of the patient is output, so that the capability of the reproductive knowledge graph in the aspects of early warning and preventive intervention is improved, and the application value of the reproductive knowledge graph for auxiliary diagnosis is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of disease auxiliary diagnosis, and specifically is a TCM reproductive endocrine disease diagnosis auxiliary system based on clinical knowledge graph. Background Art

[0002] With rising public health awareness, women are paying significantly more attention to their health. In particular, factors such as modern society's fast-paced lifestyles, high-stress environments, environmental pollution, and changes in dietary patterns can adversely affect women's health, leading to an increasing incidence of certain reproductive endocrine diseases. Traditional Chinese Medicine (TCM), with its unique herbal remedies and other non-invasive treatments, is becoming a popular option for the diagnosis and treatment of reproductive endocrine diseases.

[0003] In the current medical environment, to improve the accuracy and efficiency of Traditional Chinese Medicine (TCM) diagnosis and treatment, especially given the relative lack of experience among TCM experts, the industry generally adopts the approach of building clinical knowledge graphs to assist TCM diagnosis. Traditional TCM diagnosis primarily relies on the physician's experience and a comprehensive analysis of the patient's four diagnostic methods (inspection, auscultation, inquiry, and palpation), rarely utilizing modern medical examination methods. By establishing a knowledge graph encompassing multiple aspects of information, including symptom characteristics and treatment plans, clinicians can be provided with a systematic reference tool to help them better understand the condition, select appropriate treatments, and potentially shorten treatment cycles.

[0004] When currently using clinical knowledge graphs to diagnose reproductive diseases, most systems primarily focus on the patient's symptoms and treatment options, often overlooking the patient's environment (such as diet, sleep quality, exercise habits, and living conditions). In fact, the occurrence and progression of reproductive endocrine disorders are closely related to these lifestyle and environmental factors. This one-sided focus prevents existing knowledge graphs from fully capturing the risk factors that influence disease development, limiting their ability to provide early warning and preventive intervention. This leaves doctors with limited symptomatic treatment options after clear symptoms appear, making it difficult to predict potential health risks in advance. Summary of the Invention

[0005] In view of this, the present invention aims to propose a TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph. By adding the collection and aggregation of patient disease environment information and identifying risky disease environments when constructing the reproductive knowledge graph, the depth of disease auxiliary diagnosis using the reproductive knowledge graph is deepened, effectively solving the problems raised in the above background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: a Chinese medicine reproductive endocrine disease diagnosis auxiliary system based on clinical knowledge graph, including the following modules: a reproductive knowledge graph construction module, which is used to integrate patient medical information from different hospitals to form a reproductive medical data set, and construct a reproductive knowledge graph from it.

[0007] The disease data description statistics module is used to extract the symptoms, pathogenesis and treatment paths of various reproductive diseases from the constructed reproductive knowledge graph.

[0008] The disease-causing environment association analysis module is used to conduct disease-causing environment association analysis based on the disease-causing environment of various reproductive diseases to identify risky disease-causing environments.

[0009] The treatment effect analysis module is used to analyze the treatment effects of various reproductive diseases according to the corresponding treatment paths of patients, so as to select the optimal treatment path.

[0010] The auxiliary diagnosis module is used to create a search platform based on the reproductive knowledge graph. By inputting the patient's symptoms and matching them with the reproductive knowledge graph, it is judged whether the match is successful. When the match is successful, the preferred treatment path matching the patient's symptoms is output. When the match fails, the patient's onset environment information is input and matched with the reproductive knowledge graph, and then the patient's potential reproductive diseases are output.

[0011] One of the improvements to the above technical solutions is to construct a reproductive knowledge graph, referring to the following process:

[0012] The medical information of each patient was retrieved from the reproductive medical treatment data set, and the symptoms, onset environment, type of reproductive disease, and treatment path were extracted from it.

[0013] The reproductive disease types of each patient were classified into the same disease type to form patient groups of each reproductive disease.

[0014] The onset symptoms of each patient in the patient groups of various reproductive diseases are compared and then duplicated to form a set of onset symptoms of various reproductive diseases.

[0015] The onset environment of each patient in the patient group of each reproductive disease is formed into an onset environment set of each reproductive disease, and the occurrence frequency of the same onset environment is marked in the set.

[0016] The treatment pathway of each patient in the patient group of each type of reproductive disease is formed into a treatment pathway set of each type of reproductive disease.

[0017] The symptom sets, pathogenesis sets and treatment path sets of various reproductive diseases are taken as knowledge items of various reproductive diseases.

[0018] A node is created for each reproductive disease and assigned an identifier and attributes. Edges connecting the nodes are created based on the relationships in the knowledge items. Attribute information is added to the nodes and edges. The nodes and edges thus created constitute the reproductive knowledge graph.

[0019] An improvement to one of the above technical solutions is that the pathogenesis environment association analysis also includes an evaluation of whether there is a pathogenesis environment association. The specific operation is as follows: the pathogenesis environment set of various reproductive diseases is retrieved from the reproductive knowledge graph, and the frequency of occurrence of different pathogenesis environment information in the marked pathogenesis environment parameters is extracted.

[0020] The occurrence frequencies of different pathogenic environment information in each pathogenic environment parameter were compared, and the maximum and minimum occurrence frequencies were extracted. The difference between the maximum and minimum occurrence frequencies was divided by the maximum occurrence frequency to obtain the repetition difference of each pathogenic environment parameter.

[0021] The recurrence difference of each pathogenic environment parameter is compared with the set critical difference. If the recurrence difference of all pathogenic environments is less than the critical difference, it is judged that there is no pathogenic environment correlation; otherwise, it is judged that there is a pathogenic environment correlation.

[0022] An improvement of one of the above technical solutions is that the process of identifying the risk environment is as follows:

[0023] When judging whether there is a pathogenic environment association, the pathogenic environment parameters that appear repeatedly and reach the critical difference will be recorded as effective pathogenic environment parameters.

[0024] The occurrence frequencies of different pathogenic environment information in the effective pathogenic environment parameters are compared, and the pathogenic environment information with the highest occurrence frequency is selected as the risk pathogenic environment.

[0025] One improvement of the above technical solution is that the treatment effect analysis refers to the following process:

[0026] A set of treatment pathways for various reproductive diseases is retrieved from the reproductive knowledge graph, and the treatment stages of each treatment pathway are marked. The treatment duration and symptom indicators of each treatment stage are also extracted.

[0027] The symptom indicators of each treatment stage are compared with those of the previous treatment stage to calculate the degree of improvement of the symptoms in each treatment stage.

[0028] Substitute the improvement degree of each treatment stage and the treatment duration into the formula The treatment effect coefficient Q of each treatment stage is obtained, where η represents the improvement degree of the symptoms in the treatment stage, and t represents the treatment duration of the treatment stage.

[0029] The improvement rate of the treatment effect of each treatment stage on the treatment path is calculated by subtracting the treatment effect coefficient of the previous treatment stage from the treatment effect coefficient of the previous treatment stage.

[0030] The therapeutic effect representation value of the treatment path is obtained by accumulating the therapeutic effect improvement rate of each treatment stage on the treatment path.

[0031] An improvement of one of the above technical solutions is that the screening of the preferred treatment pathway is performed as follows:

[0032] Patients with the same treatment path in the treatment path set of various reproductive diseases are classified to obtain a number of patients corresponding to each treatment path, and the number of patients with each treatment path is counted.

[0033] The standard deviation of the treatment effect characterization values ​​of each patient in the same treatment pathway is calculated and compared with the set limit standard deviation. If the standard deviation of the treatment effect characterization values ​​of patients in a treatment pathway is less than or equal to the limit standard deviation, the average value of the treatment effect characterization values ​​of each patient in the treatment pathway is taken as the typical treatment effect characterization value of the treatment pathway; otherwise, the minimum value of the treatment effect characterization values ​​of each patient in the treatment pathway is taken as the typical treatment effect characterization value of the treatment pathway.

[0034] Substitute the typical treatment effect representation value of each treatment path and the number of patients into the evaluation formula Get the selection value of each treatment path Where i represents the treatment pathway number, i=1,2,......,n, Q 典型 i represents the typical treatment effect representation value of the i-th treatment path, x i Indicates the number of patients for which the i-th treatment path exists.

[0035] The selection values ​​of various treatment paths are compared, and the treatment path with the greatest selection value is selected as the preferred treatment path.

[0036] Compared to existing technologies, the present invention offers the following benefits: In constructing a reproductive knowledge graph, the present invention systematically integrates patient medical records and incorporates data on environmental factors at the time of illness, thereby conducting in-depth correlation analysis of this information to identify risk environments associated with disease onset. A search platform based on this enhanced knowledge graph matches patient symptoms or onset environmental information to provide possible symptom indications and optimal treatment path recommendations, enhancing both early warning capabilities and the effectiveness of preventive interventions, significantly increasing the value and accuracy of knowledge graph-assisted diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work.

[0038] Figure 1 This is a schematic diagram of the connection of various modules of the system of the present invention.

[0039] Figure 2 Schematic diagram of the construction of the reproductive knowledge graph in the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0041] See also Figure 1 As shown, the present invention proposes a TCM reproductive endocrine disease diagnosis auxiliary system based on clinical knowledge graph, including a reproductive knowledge graph construction module, a disease data description and statistics module, a disease environment association analysis module, a treatment effect analysis module and an auxiliary diagnosis module, wherein the reproductive knowledge graph construction module is connected to the disease data description and statistics module, the disease data description and statistics module is respectively connected to the disease environment association analysis module and the treatment effect analysis module, and the disease environment association analysis module and the treatment effect analysis module are respectively connected to the auxiliary diagnosis module.

[0042] The reproductive knowledge graph construction module is used to integrate patient medical information from different hospitals to form a reproductive medical data set, and construct a reproductive knowledge graph from it.

[0043] Applied to the above scheme, the reproductive knowledge graph is constructed by referring to the following process: the medical information of each patient is retrieved from the reproductive medical treatment dataset, and the symptoms, onset environment, types of reproductive diseases, and treatment pathways are extracted from it.

[0044] It should be noted that when constructing the reproductive knowledge graph, the patient's medical information retrieved is mainly obtained by retrieving the patient's medical records, and then extracting the medical information from the medical records. The symptoms of the disease refer to the physical discomfort or abnormal conditions described by the patient when seeking medical treatment. For example, irregular bleeding, lower abdominal pain, abnormal leucorrhea, etc. The disease environment usually refers to the external conditions or background that may affect the occurrence of the disease. In the field of reproduction, this can include living habits (such as eating habits, exercise frequency), living environment (such as sanitary conditions of residence), etc. The disease environment can be obtained by asking the patient about his daily living habits. The type of reproductive disease refers to the specific disease name or diagnosis result, such as uterine fibroids, ovarian cysts, cervicitis, etc. The treatment pathway refers to the phased treatment measures taken for a specific disease, which may include drug therapy, physical therapy, etc.

[0045] The reproductive disease types of each patient were classified into the same disease type to form patient groups of each reproductive disease.

[0046] The onset symptoms of each patient in the patient group of each reproductive disease are compared and then duplicated to form a set of onset symptoms of each reproductive disease. This ensures that the key symptoms of each reproductive disease are accurately identified and summarized.

[0047] The disease-causing environments of each patient in each reproductive disease group were combined into a set of disease-causing environments for each category, and the frequency of occurrence of the same disease-causing environment in the set was marked. This frequency-marked data provided an intuitive understanding of the prevalence of each environmental factor, providing a foundation for further analysis.

[0048] The treatment pathway of each patient in the patient group of each type of reproductive disease is formed into a treatment pathway set of each type of reproductive disease.

[0049] The symptom sets, pathogenesis sets and treatment path sets of various reproductive diseases are taken as knowledge items of various reproductive diseases.

[0050] Create a node for each reproductive disease and assign it an identifier and attributes (such as the type of reproductive disease). Create edges connecting the nodes based on the relationships in the knowledge items, and add attribute information to the nodes and edges. The nodes and edges thus created constitute the reproductive knowledge graph. Figure 2 shown.

[0051] It should be added that the constructed reproductive knowledge graph can be intuitively displayed using visualization tools.

[0052] The disease data description statistics module is used to extract the symptoms, pathogenesis and treatment paths of various reproductive diseases from the constructed reproductive knowledge graph.

[0053] The pathogenesis environment association analysis module is used to perform pathogenesis environment association analysis based on the pathogenesis environment of various reproductive diseases to identify risk pathogenesis environments.

[0054] In the implementation method of the above scheme, it is necessary to judge whether there is a pathogenic environment association before conducting pathogenic environment association analysis. The specific operation is as follows: retrieve the pathogenic environment set of various reproductive diseases from the reproductive knowledge graph, and extract the frequency of occurrence of different pathogenic environment information in the marked pathogenic environment parameters.

[0055] The frequency of occurrence of different pathogenic environmental information within each pathogenic environmental parameter is compared, and the maximum and minimum frequencies are extracted. The difference between the maximum and minimum frequencies is then divided by the maximum frequency to obtain the recurrence difference of each pathogenic environmental parameter. Calculating the difference can quantify the distribution differences between different pathogenic environmental information and help identify which environmental factors show significant differences among patient groups.

[0056] The recurrence difference of each pathogenesis environment parameter is compared with the set critical difference. For example, the critical difference is 0.6. If the recurrence difference of all pathogenesis environments is less than the critical difference, it is judged that there is no pathogenesis environment correlation. Otherwise, it is judged that there is a pathogenesis environment correlation.

[0057] It needs to be understood that the occurrence of diseases in the reproductive field is often related to the patient's living environment. This is because a variety of life and environmental factors can directly or indirectly affect women's reproductive health. Specifically, eating habits: an unhealthy diet (such as a high-fat, high-sugar, low-fiber diet) may lead to obesity, which in turn increases the risk of polycystic ovary syndrome, endometriosis and other diseases. Exercise habits: Lack of exercise can lead to weight gain and metabolic disorders, and increase the risk of endocrine disorder-related diseases. On the contrary, excessive exercise may lead to menstrual disorders and ovulation problems, affecting fertility. Work and rest habits: staying up late for a long time and lack of sleep will interfere with the body's biological clock, leading to hormone imbalances, affecting the menstrual cycle and ovarian function, and increasing the risk of reproductive diseases.

[0058] The recurrence difference of the above-mentioned pathogenic environment parameters can be understood as a measure of the frequency or pattern of disease occurrence under certain environmental conditions, and by setting a threshold (i.e., critical difference) to determine whether the environmental conditions may be associated with the disease.

[0059] When the recurrence variability of all pathogenic environment parameters is less than the critical variability, this means that the incidence of the disease under the environmental conditions has not changed much in different observations or experiments, or is relatively stable and has no obvious increasing trend. In this case, researchers may conclude that there is no direct causal relationship between this particular environmental condition and the disease being studied, or that its effect is very weak. On the contrary, if the recurrence variability of certain pathogenic environment parameters exceeds the critical variability, this indicates that the incidence of the disease under the environmental conditions has large fluctuations at different time points or in different samples, which may suggest that this environmental condition has a certain impact on the occurrence of the disease.

[0060] However, it is worth noting that the above explanation only applies to the context of scientific research and data analysis. In actual clinical practice, doctors will not rely solely on such statistical data to make diagnosis or treatment decisions.

[0061] In a further implementation of the above scheme, the risky pathogenic environment is identified as follows: when judging whether there is a pathogenic environment association, the pathogenic environment parameters that appear repeatedly and have a difference reaching a critical difference are recorded as valid pathogenic environment parameters.

[0062] The frequencies of occurrence of different pathogenic environment information within the valid pathogenic environment parameters are compared, and the pathogenic environment information with the highest frequency of occurrence is selected as the risk pathogenic environment. Selecting the pathogenic environment information with the highest frequency of occurrence as the risk factor conforms to the "majority principle," that is, the most common environmental factor is more likely to be the true risk factor.

[0063] The treatment effect analysis module is used to analyze the treatment effects of various reproductive diseases according to the treatment paths of the patients, so as to select the preferred treatment path.

[0064] Preferably, treatment efficacy analysis involves the following process: extracting a set of treatment pathways for various reproductive conditions from the reproductive knowledge graph, labeling the treatment stages for each pathway, and extracting the treatment duration and symptom indicators for each treatment stage. By labeling treatment stages, the unstructured treatment process can be converted into structured data, facilitating subsequent quantitative analysis.

[0065] Compare the symptom indicators of each treatment stage with those of the previous treatment stage to calculate the symptom improvement of each treatment stage.

[0066] Substitute the improvement degree of each treatment stage and the treatment duration into the formula The treatment effect coefficient Q for each treatment phase is obtained, where η represents the degree of improvement in the treatment phase and t represents the treatment duration. Including treatment duration allows for a comprehensive assessment of the efficiency of each treatment phase, taking into account not only the degree of improvement but also the time cost.

[0067] The improvement rate of the treatment effect of each treatment stage on the treatment path is calculated by subtracting the treatment effect coefficient of the previous treatment stage from the treatment effect coefficient of the previous treatment stage.

[0068] The therapeutic effect representation value of the treatment path is obtained by accumulating the therapeutic effect improvement rate of each treatment stage on the treatment path.

[0069] What you need to know is that by calculating the treatment effect improvement rate, you can capture the improvement of each treatment stage relative to the previous node, reflect the dynamic changes in the treatment process, and use the treatment effect coefficient of the previous node as the denominator, so that the improvement rate value is between 0 and 1, which is convenient for subsequent cumulative calculations. The cumulative method can reflect the cumulative improvement effect of each node in the treatment process and help identify the most effective treatment path.

[0070] More preferably, the preferred treatment pathway is screened as follows: patients with the same treatment pathway within the treatment pathway set for each reproductive condition are grouped to obtain a number of patients corresponding to each treatment pathway, and the number of patients with each treatment pathway is counted. This allows understanding the frequency and prevalence of the treatment pathway, providing a basis for subsequent evaluation.

[0071] The standard deviation of the treatment effect characterization values ​​of each patient in the same treatment pathway is calculated and compared with the set limit standard deviation. If the standard deviation of the treatment effect characterization values ​​of patients in a treatment pathway is less than or equal to the limit standard deviation, the average value of the treatment effect characterization values ​​of each patient in the treatment pathway is taken as the typical treatment effect characterization value of the treatment pathway; otherwise, the minimum value of the treatment effect characterization values ​​of each patient in the treatment pathway is taken as the typical treatment effect characterization value of the treatment pathway.

[0072] The above calculation of the standard deviation allows us to assess the consistency of the treatment pathway's effectiveness across different patients. A small standard deviation indicates that the treatment pathway is consistently effective across the majority of patients and is therefore highly reliable. When the standard deviation is large, selecting the minimum value as the representative treatment effect is a conservative approach, ensuring that even in the most adverse circumstances, the treatment pathway maintains a certain level of efficacy. This approach considers both the consistency of the treatment pathway and the minimum efficacy in extreme cases, offering both flexibility and robustness.

[0073] Substitute the typical treatment effect representation value of each treatment path and the number of patients into the evaluation formula Get the selection value of each treatment path Where i represents the treatment pathway number, i=1,2,......,n, Q 典型 i represents the typical treatment effect representation value of the i-th treatment path, x i Indicates the number of patients for which the i-th treatment path exists.

[0074] The selection values ​​of various treatment paths are compared, and the treatment path with the greatest selection value is selected as the preferred treatment path.

[0075] The above calculation method can find a balance between efficacy and popularity, ensuring that the selected treatment path is not only effective but also applicable to more patients. By comparing the selection value of each treatment path, the treatment path with the best overall effect and the widest applicability can be selected as the preferred option in clinical practice.

[0076] The auxiliary diagnosis module is used to create a search platform based on the reproductive knowledge graph, thereby inputting the patient's symptoms and matching them with the reproductive knowledge graph to judge whether the match is successful, and outputting the preferred treatment path that matches the patient's symptoms when the match is successful. When the match fails, the patient's onset environment information is input and matched with the reproductive knowledge graph, and then the patient's potential reproductive diseases are output.

[0077] Specifically, the process of judging whether the match is successful is as follows: the patient's symptoms are matched with the symptom sets of various reproductive diseases in the reproductive knowledge graph. If a certain symptom falls within the symptom set of a certain reproductive disease, the reproductive disease is used as the primary matching reproductive disease.

[0078] The number of primary reproductive symptoms formed by the patient's symptoms in the matching is counted, and the proportion of patient symptoms matched by each primary reproductive symptom is obtained, and then compared with the set effective proportion value. If the proportion of patient symptoms matched by the primary reproductive symptom reaches the effective proportion value, the match is judged to be successful, otherwise the match is judged to be unsuccessful.

[0079] More specifically, when the match is successful, the preferred treatment path that matches the patient's symptoms is output as follows: the number of successfully matched primary reproductive diseases is counted; if there is only one successfully matched primary reproductive disease, the preferred treatment path corresponding to the corresponding reproductive disease is extracted from the reproductive knowledge graph; if there is more than one successfully matched primary reproductive disease, the preferred treatment path corresponding to each primary reproductive disease is extracted from the reproductive knowledge graph, and they are arranged in descending order according to the proportion of the patient's symptoms corresponding to the primary reproductive disease.

[0080] Furthermore, when the matching fails, the patient's disease environment information is input and matched with the reproductive knowledge graph. See the following process: various reproductive diseases existing in the reproductive knowledge graph are arranged in the order of priority of the first matching reproductive disease.

[0081] According to the arrangement order of reproductive diseases, the patient's disease environment information is matched with the risk disease environment of the corresponding reproductive diseases in the reproductive knowledge graph. If the patient's disease environment information is consistent with the risk disease environment of a certain reproductive disease, the reproductive disease will be regarded as a prone reproductive disease.

[0082] Going further, the output of the patient's potential reproductive diseases is implemented as follows: count the number of prone reproductive diseases, if there is only one prone reproductive disease, then use this reproductive disease as the patient's potential reproductive disease, if there is more than one prone reproductive disease, then compare the patient's disease environment information with the disease environment set corresponding to each prone reproductive disease in the reproductive knowledge graph, count the number of patients' disease environment information that falls within the disease environment set for each prone reproductive disease, and then take the prone reproductive disease corresponding to the largest number that falls as the patient's potential reproductive disease.

[0083] In constructing a reproductive knowledge graph, this invention systematically integrates patient medical records and incorporates data on environmental factors at the time of illness. This information is then deeply correlated and analyzed to identify risk environments associated with disease onset. A search platform based on this enhanced knowledge graph matches patient symptoms with information on the onset of disease, providing potential symptom indicators and optimal treatment pathway recommendations. This not only enhances early warning capabilities but also strengthens the effectiveness of preventive interventions, significantly increasing the value and accuracy of knowledge graph-assisted diagnosis.

[0084] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A Chinese medicine reproductive endocrine disease diagnosis auxiliary system based on clinical knowledge graph, characterized by , including the following modules: The reproductive knowledge graph construction module is used to integrate patient medical information from different hospitals to form a reproductive medical data set and construct a reproductive knowledge graph from it; Disease data description statistics module, used to extract the symptoms, pathogenesis and treatment pathways of various reproductive diseases from the constructed reproductive knowledge graph; The disease-causing environment association analysis module is used to conduct disease-causing environment association analysis based on the disease-causing environment of various reproductive diseases to identify risky disease-causing environments; The treatment effect analysis module is used to analyze the treatment effects of various reproductive diseases according to the corresponding treatment paths of patients, so as to select the optimal treatment path; The auxiliary diagnosis module is used to create a search platform based on the reproductive knowledge graph. By inputting the patient's symptoms and matching them with the reproductive knowledge graph, it is judged whether the match is successful. When the match is successful, the preferred treatment path matching the patient's symptoms is output. When the match fails, the patient's onset environment information is input and matched with the reproductive knowledge graph, and then the patient's potential reproductive diseases are output.

2. A TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 1, characterized in that: The process of constructing the reproductive knowledge graph is as follows: Retrieve the medical information of each patient from the reproductive medical treatment data set, and extract the symptoms, onset environment, type of reproductive disease, and treatment path; The reproductive disease types of each patient were classified into the same disease type to form patient groups of each reproductive disease type; Comparing the symptoms of each patient in the patient groups of various reproductive diseases and removing duplicates to form a set of symptoms of various reproductive diseases; The disease environment of each patient in the patient group of each type of reproductive disease is formed into a disease environment set of each type of reproductive disease, and the occurrence frequency of the same disease environment is marked in the set; The treatment pathways of each patient in the patient groups of each type of reproductive disease are used to form a treatment pathway set for each type of reproductive disease; The set of symptoms, the set of onset environments and the set of treatment pathways of various reproductive diseases are taken as the knowledge items of various reproductive diseases; A node is created for each reproductive disease and assigned an identifier and attributes. Edges connecting the nodes are created based on the relationships in the knowledge items. Attribute information is added to the nodes and edges. The nodes and edges thus created constitute the reproductive knowledge graph.

3. A TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 2, characterized in that: The disease-environment association analysis also includes the evaluation of whether there is a disease-environment association, and the specific operation is as follows: Retrieve the pathogenic environment set of various reproductive diseases from the reproductive knowledge graph, and extract the occurrence frequency of different pathogenic environment information in each marked pathogenic environment parameter; Compare the occurrence frequencies of different pathogenic environment information in each pathogenic environment parameter, extract the maximum occurrence frequency and the minimum occurrence frequency, and divide the maximum occurrence frequency by the maximum occurrence frequency to obtain the recurrence difference of each pathogenic environment parameter; The recurrence difference of each pathogenic environment parameter is compared with the set critical difference. If the recurrence difference of all pathogenic environments is less than the critical difference, it is judged that there is no pathogenic environment correlation; otherwise, it is judged that there is a pathogenic environment correlation.

4. A TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 3, characterized in that: The process of identifying the risk environment is as follows: When judging whether there is a pathogenic environment association, the pathogenic environment parameters whose repeated differences reach the critical difference will be recorded as valid pathogenic environment parameters; The occurrence frequencies of different pathogenic environment information in the effective pathogenic environment parameters are compared, and the pathogenic environment information with the highest occurrence frequency is selected as the risk pathogenic environment.

5. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 2 is characterized by: The treatment effect analysis is described in the following process: Retrieve a set of treatment pathways for various reproductive diseases from the reproductive knowledge graph, mark the treatment stages of each treatment pathway, and extract the treatment duration and symptom indicators for each treatment stage; Compare the symptom indicators of each treatment stage with those of the previous treatment stage to calculate the improvement of the symptoms in each treatment stage; Substitute the improvement degree of each treatment stage and the treatment duration into the formula The treatment effect coefficient Q of each treatment stage is obtained, where η represents the improvement degree of the symptoms in the treatment stage, and t represents the treatment duration of the treatment stage; The treatment effect improvement rate of each treatment stage is calculated by subtracting the treatment effect coefficient of each treatment stage from the treatment effect coefficient of the previous treatment stage and dividing it by the treatment effect coefficient of the previous treatment stage; The therapeutic effect representation value of the treatment path is obtained by accumulating the therapeutic effect improvement rate of each treatment stage on the treatment path.

6. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 5 is characterized by: The screening of the preferred treatment pathway is performed as follows: Patients with the same treatment path in the treatment path set of various reproductive diseases are classified to obtain a number of patients corresponding to each treatment path, and the number of patients with each treatment path is counted; The standard deviation of the treatment effect representation value of each patient in the same treatment pathway is calculated and compared with the set limit standard deviation. If the standard deviation of the treatment effect representation value of the patients in a treatment pathway is less than or equal to the limit standard deviation, the average value of the treatment effect representation value of each patient in the treatment pathway is taken as the typical treatment effect representation value of the treatment pathway. Otherwise, the minimum value of the treatment effect representation value of each patient in the treatment pathway is taken as the typical treatment effect representation value of the treatment pathway; Substitute the typical treatment effect representation value of each treatment path and the number of patients into the evaluation formula Get the selection value of each treatment path Where i represents the treatment pathway number, i=1,2,......,n, Q 典型 i represents the typical treatment effect representation value of the i-th treatment path, x i represents the number of patients with the i-th treatment path; The selection values ​​of various treatment paths are compared, and the treatment path with the greatest selection value is selected as the preferred treatment path.

7. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 2 is characterized by: The process of judging whether the match is successful is as follows: Match the patient's symptoms with the symptom sets of various reproductive diseases in the reproductive knowledge graph. If a symptom falls within the symptom set of a reproductive disease, then the reproductive disease is regarded as the primary reproductive disease. The number of primary reproductive symptoms formed by the patient's symptoms in the matching is counted, and the proportion of patient symptoms matched by each primary reproductive symptom is obtained, and then compared with the set effective proportion value. If the proportion of patient symptoms matched by the primary reproductive symptom reaches the effective proportion value, the match is judged to be successful, otherwise the match is judged to be unsuccessful.

8. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 7 is characterized by: The operation of outputting the preferred treatment path matching the patient's symptoms when the match is successful is as follows: The number of successfully matched primary reproductive symptoms is counted. If there is only one successfully matched primary reproductive disease, the preferred treatment path corresponding to the corresponding reproductive disease is extracted from the reproductive knowledge graph. If there is more than one successfully matched primary reproductive disease, the preferred treatment path corresponding to each primary reproductive disease is extracted from the reproductive knowledge graph and arranged in descending order according to the proportion of the patient's symptoms corresponding to the primary reproductive disease.

9. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 8 is characterized by: When the matching fails, the patient's disease environment information is input and matched with the reproductive knowledge graph. Please refer to the following process: Arrange the various reproductive diseases in the reproductive knowledge graph in the order of priority of the first reproductive disease; According to the arrangement order of reproductive diseases, the patient's disease environment information is matched with the risk disease environment of the corresponding reproductive diseases in the reproductive knowledge graph. If the patient's disease environment information is consistent with the risk disease environment of a certain reproductive disease, the reproductive disease will be regarded as a prone reproductive disease.

10. The TCM reproductive endocrine disease diagnosis assistance system based on clinical knowledge graph according to claim 9 is characterized by: The output of the patient's potential reproductive condition is implemented as follows: Count the number of reproductive disease tendencies. If there is only one reproductive disease tendency, then this reproductive disease is regarded as the patient's potential reproductive disease. If there is more than one reproductive disease tendency, then compare the patient's disease environment information with the disease environment set corresponding to each reproductive disease tendency in the reproductive knowledge graph, and count the number of patients' disease environment information that falls within the disease environment set for each reproductive disease tendency, and then take the reproductive disease tendency corresponding to the largest number that falls as the patient's potential reproductive disease.

Images