Diagnosis and treatment planning method, device and equipment for bladder cancer risk population and storage medium

Abstract

The invention discloses a bladder cancer risk population diagnosis and treatment planning method, device and equipment and a storage medium, and the method comprises the steps: obtaining the user data of a to-be-recommended user, and the user data comprises basic feature data, health data and living habit data; inputting the user data into a trained bladder cancer risk assessment model, and outputting a risk assessment score corresponding to the to-be-recommended user through the bladder cancer risk assessment model; and according to the risk assessment score, carrying out bladder cancer risk prompting on the to-be-recommended user, and pushing a diagnosis and treatment planning scheme determined according to the risk assessment score and a preset bladder cancer knowledge graph. By constructing the bladder cancer risk assessment model and the preset bladder cancer knowledge graph, the diagnosis and treatment planning scheme is determined, the feature information provided by the user data can be fully utilized, the accuracy of bladder cancer risk assessment is improved, the diagnosis and treatment planning scheme is provided for the user in a targeted manner, and the early discovery rate of bladder cancer is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method, device, equipment and storage medium for diagnosis and treatment planning for people at risk of bladder cancer. Background Art

[0002] Bladder cancer, as one of the most common malignant tumors in the world, has been widely studied. Many risk factors that may cause bladder cancer have been found through research, such as age, smoking, and occupational exposure. However, currently, doctors generally conduct bladder cancer risk assessment by combining these risk factors, which requires a high degree of reliance on the doctor's medical ability and medical experience, thus affecting the objectivity and accuracy of bladder cancer risk assessment.

[0003] Therefore the prior art still needs to be improved and enhanced. Summary of the invention

[0004] The technical problem to be solved by this application is how to improve the accuracy of bladder cancer risk assessment. In view of the shortcomings of the existing technology, a method, device, equipment and storage medium for diagnosis and treatment planning of people at risk of bladder cancer are provided.

[0005] In order to solve the above technical problems, the first aspect of the embodiment of the present application provides a method for diagnosis and treatment planning of a bladder cancer risk group, the method comprising:

[0006] Acquire user data of the user to be recommended, wherein the user data includes basic feature data, health data and life habit data;

[0007] Inputting the user data into a trained bladder cancer risk assessment model, and outputting a risk assessment score corresponding to the user to be recommended through the bladder cancer risk assessment model;

[0008] According to the risk assessment score, the bladder cancer risk is prompted to the user to be recommended, and a diagnosis and treatment plan determined according to the risk assessment score and a preset bladder cancer knowledge graph is pushed.

[0009] According to the above technical means, by constructing a bladder cancer risk assessment model, the bladder cancer risk assessment of users can be carried out, and the characteristic information provided by the user data can be fully utilized, thereby improving the accuracy of the risk assessment. At the same time, the diagnosis and treatment planning scheme determined by the risk assessment score and the preset bladder cancer knowledge map can improve the user's understanding of their own situation through the diagnosis and treatment planning scheme, bringing convenience to the user.

[0010] In one embodiment of the present application, the diagnosis and treatment planning method for a group at risk of bladder cancer is described, wherein the basic characteristic data includes age, gender, race and family medical history; the health data includes diabetes data, weight data and hypertension data; and the lifestyle habit data includes smoking data and occupational exposure data.

[0011] According to the above technical means, by obtaining the user's basic characteristic data, health data and living habit data, characteristic information is provided to the bladder cancer risk assessment model, so that the bladder cancer risk assessment model can accurately output the risk level of the user to be recommended, thereby improving the accuracy of the risk level assessment.

[0012] In one embodiment of the present application, the method for diagnosis and treatment planning for a bladder cancer risk group, wherein the step of providing a bladder cancer risk reminder to the user to be recommended based on the risk assessment score and pushing a diagnosis and treatment planning scheme determined based on the risk assessment score specifically includes:

[0013] comparing the risk assessment score to a preset score threshold;

[0014] If the risk assessment score is greater than a preset score threshold, the risk level corresponding to the risk assessment score is determined based on a preset level sequence, a diagnosis and treatment plan is determined based on a preset bladder cancer knowledge graph, and the risk level and the diagnosis and treatment plan are pushed to the user to be recommended;

[0015] If the risk assessment score is less than or equal to the preset score threshold, the risk assessment score is pushed to the user to be recommended.

[0016] According to the above technical means, the push mode is divided by pre-setting score thresholds, so that the risk level and the treatment plan can be pushed to the recommended users with high risks, and the risk level and the treatment plan can be avoided from affecting the users with low risks.

[0017] In one embodiment of the present application, the diagnosis and treatment planning method for a population at risk of bladder cancer, wherein the step of determining a diagnosis and treatment planning scheme based on a preset bladder cancer knowledge graph specifically includes:

[0018] Searching for diagnostic and treatment methods corresponding to bladder cancer and the diagnostic and treatment effects corresponding to each diagnostic and treatment method in the preset bladder cancer knowledge graph;

[0019] Based on the diagnosis and treatment impact and the user data, a diagnosis and treatment planning scheme corresponding to the user to be recommended is determined.

[0020] According to the above technical means, by searching for the corresponding diagnosis and treatment methods in the bladder cancer knowledge graph and determining the user's diagnosis and treatment plan, doctors can formulate targeted diagnosis and treatment plans by querying the bladder cancer knowledge graph, so that patients can be diagnosed and treated in a targeted manner, the allocation of medical resources can be optimized, and the efficiency and effectiveness of medical services can be improved.

[0021] In one embodiment of the present application, the diagnosis and treatment planning method for a bladder cancer risk group, wherein the diagnosis and treatment planning scheme is determined according to a preset bladder cancer knowledge graph, and the determination process of the preset bladder cancer knowledge graph specifically includes:

[0022] Acquiring bladder cancer medical data, wherein the bladder cancer medical data carries bladder cancer related information;

[0023] Entity extraction and relationship extraction are performed on the bladder cancer medical data, and a preset bladder cancer knowledge graph is constructed based on all the extracted entities and the relationships.

[0024] According to the above-mentioned technical means, by constructing a bladder cancer knowledge graph based on bladder cancer medical data, medical knowledge related to bladder cancer can be integrated, which helps to understand the risk factors, pathophysiological processes, diagnostic methods, and treatment plans of bladder cancer.

[0025] In one embodiment of the present application, a method for diagnosis and treatment planning for a population at risk of bladder cancer, wherein the method further comprises:

[0026] According to the preset bladder cancer knowledge graph and the user data, the bladder cancer risk factors of the to-be-recommended user are determined, and the bladder cancer risk factors are pushed to the to-be-recommended user.

[0027] According to the above technical means, by pushing bladder cancer risk factors to users, users can clearly identify their own risk factors for bladder cancer, thereby adjusting or changing their own lifestyle habits and reducing the probability of bladder cancer risk.

[0028] In one embodiment of the present application, the method for diagnosis and treatment planning of a population at risk of bladder cancer, wherein the method further comprises:

[0029] The bladder cancer risk assessment model is updated at preset time intervals, and the preset bladder cancer knowledge graph is updated, wherein when the preset bladder cancer knowledge graph is updated, the difference bladder cancer medical data between the bladder cancer medical data obtained at the updating time and the bladder cancer medical data obtained at the construction time of the preset bladder cancer knowledge graph is used as the updated bladder cancer medical data.

[0030] According to the above-mentioned technical means, by regularly updating the bladder cancer risk assessment model and the bladder cancer knowledge graph, it is ensured that the bladder cancer risk assessment model and the bladder cancer knowledge graph are always kept up to date, thereby ensuring the accuracy of bladder cancer risk assessment for users.

[0031] A second aspect of the embodiment of the present application provides a diagnosis and treatment planning device for a group of people at risk of bladder cancer, wherein the diagnosis and treatment planning device for a group of people at risk of bladder cancer specifically comprises:

[0032] An acquisition module, used to acquire user data of the user to be recommended, wherein the user data includes basic feature data, health data and life habit data;

[0033] An evaluation module, used for inputting the user data into a trained bladder cancer risk evaluation model, and outputting a risk evaluation score corresponding to the user to be recommended through the bladder cancer risk evaluation model;

[0034] The planning module is used to provide bladder cancer risk warnings to the recommended user based on the risk assessment score, and to push a diagnosis and treatment planning plan determined based on the risk assessment score and a preset bladder cancer knowledge graph.

[0035] A third aspect of an embodiment of the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the diagnosis and treatment planning method for a bladder cancer risk group as described in any of the above.

[0036] A fourth aspect of the embodiments of the present application provides a terminal device, which includes: a processor and a memory;

[0037] The memory stores a computer-readable program executable by the processor;

[0038] When the processor executes the computer-readable program, the processor implements the steps in any of the above-mentioned methods for diagnosis and treatment planning for a group of people at risk of bladder cancer.

[0039] Beneficial effects: Compared with the existing technology,

[0040] 1) This application constructs a bladder cancer risk assessment model to conduct a risk assessment on a user's risk of bladder cancer and obtain a risk assessment score, which can make full use of the characteristic information provided by the user data, thereby improving the accuracy of bladder cancer risk assessment;

[0041] 2) By building a bladder cancer knowledge graph based on bladder cancer medical data, we can integrate medical knowledge related to bladder cancer and help understand the risk factors, pathophysiological processes, diagnostic methods, and treatment plans of bladder cancer;

[0042] 3) By determining the diagnosis and treatment plan through the risk assessment score and the bladder cancer knowledge graph, the diagnosis and treatment plan can be provided to the user in a targeted manner and pushed to the user accordingly. The user can clarify his or her own risk factors for bladder cancer, improve the user's understanding of his or her own situation, and bring convenience to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without inventive work.

[0044] Figure 1 A flowchart of a preferred embodiment of the diagnosis and treatment planning method for people at risk of bladder cancer provided in this application.

[0045] Figure 2 The bladder cancer knowledge graph in the preferred embodiment of the diagnosis and treatment planning method for the bladder cancer risk population provided in this application.

[0046] Figure 3 This is a flowchart of step S30 in a preferred embodiment of the diagnosis and treatment planning method for a population at risk of bladder cancer provided in the present application.

[0047] Figure 4 Module diagram of the diagnosis and treatment planning device for people at risk of bladder cancer provided in this application.

[0048] Figure 5 This is a schematic diagram of the structure of the terminal device provided in this application. DETAILED DESCRIPTION

[0049] The present application provides a method, device, equipment and storage medium for bladder cancer risk group diagnosis and treatment planning. In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0052] It should be understood that the sequence numbers and sizes of the steps in this embodiment do not mean the order of execution. The execution order of each process is determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0053] The inventors have found through research that bladder cancer is one of the most common malignant tumors in the world, with the characteristics of no obvious symptoms in the early stage, difficult diagnosis, and high recurrence rate. The risk factors of bladder cancer have been widely studied, such as age, smoking, and occupational exposure. However, at present, doctors generally conduct bladder cancer risk assessment by combining these risk factors, which requires a high degree of reliance on the doctor's medical ability and medical experience, thus affecting the objectivity and accuracy of bladder cancer risk assessment.

[0054] In recent years, with the development of big data and artificial intelligence technology, it has become possible to use statistics or machine learning algorithms to assess disease risk. Therefore, how to effectively integrate bladder cancer risk factors and use these technologies to assess bladder cancer risk for users and improve the accuracy of bladder cancer risk assessment is an urgent problem to be solved.

[0055] In order to solve the above problems, in an embodiment of the present application, the user data of the user to be recommended is obtained, wherein the user data includes basic feature data, health data and life habit data; the user data is input into a trained bladder cancer risk assessment model, and the risk assessment score corresponding to the user to be recommended is output through the bladder cancer risk assessment model; according to the risk assessment score, the user to be recommended is given a bladder cancer risk prompt, and a diagnosis and treatment plan determined according to the risk assessment score and the preset bladder cancer knowledge graph is pushed. By constructing a bladder cancer risk assessment model and a preset bladder cancer knowledge graph to determine the diagnosis and treatment plan, the present application can make full use of the feature information provided by the user data, improve the accuracy of bladder cancer risk assessment, provide users with targeted diagnosis and treatment plans, and improve the early detection rate of bladder cancer.

[0056] The application content is further explained below through the description of embodiments in conjunction with the accompanying drawings.

[0057] This embodiment provides a diagnosis and treatment planning method for a population at risk of bladder cancer, such as Figure 1 As shown, the method includes:

[0058] S10. Obtain user data of the user to be recommended, wherein the user data includes basic feature data, health data, and life habit data.

[0059] Specifically, the user data is some characteristic information related to the risk factors of bladder cancer, such as age, smoking history, occupational exposure, etc. The user data is obtained through medical record system, questionnaire survey, detection equipment, etc.

[0060] The basic feature data includes age, gender, race and family medical history, the health data includes diabetes data, weight data and hypertension data, and the lifestyle data includes smoking data and occupational exposure data. Among them, the family medical history includes bladder cancer or other cancers. The occupational exposure data is the relevant factors that the user is exposed to at work and makes him or her susceptible to bladder cancer, for example, the frequency and intensity of the user's exposure to harmful chemicals at work. In an embodiment of the present application, the health data also includes body mass index (BMI), urine test results, sex hormone levels, drug use history, genetic mutations, etc., and the lifestyle data also includes eating habits, such as the amount of fruits, vegetables and meat consumed. By acquiring the user's basic feature data, health data and lifestyle data, the embodiment of the present application can integrate these feature information related to bladder cancer factors into user data.

[0061] S20: Input the user data into a trained bladder cancer risk assessment model, and output a risk assessment score corresponding to the user to be recommended through the bladder cancer risk assessment model.

[0062] Specifically, the bladder cancer risk assessment model is a machine learning model. The bladder cancer risk assessment model is used to assess the probability of a user suffering from bladder cancer. The input of the bladder cancer risk assessment model is user data, and the output is a risk assessment score.

[0063] In practical applications, the machine learning model needs to be trained before it is used. Therefore, in the embodiment of the present application, the training process of the trained bladder cancer risk assessment model is as follows:

[0064] Preprocess the user data to obtain a data set;

[0065] Divide the dataset into training and testing sets;

[0066] The initial bladder cancer risk assessment model is trained according to the training set to obtain a trained bladder cancer risk assessment model;

[0067] The trained bladder cancer risk assessment model was tested using the test set.

[0068] Specifically, the user data is preprocessed to obtain a data set. In practical applications, some feature information in the collected user data may contain abnormal values, missing data, etc. Therefore, it is necessary to preprocess the feature information in the user data. The data preprocessing includes data cleaning, processing missing values, data standardization or normalization, etc.

[0069] The data cleaning includes removing outliers and correcting errors. Outliers are detected by statistical methods, and the detected outliers are deleted or corrected. For example, the age of the user to be recommended is 500 years old, which is obviously an incorrect value. At this time, this age value can be deleted or a reasonable age value, such as an average age value, can be used to correct it.

[0070] The processing of missing values ​​may delete rows containing missing values ​​or use a filling method to fill in missing values. In practical applications, different methods for processing missing values ​​are used for different types of data. Therefore, in an embodiment of the present application, user data may be divided into numerical user data and categorical user data. For numerical user data, an average value may be used for filling, and for categorical user data, a mode may be used for filling. For example, if a person's urine test result value is missing, and the urine test result value belongs to numerical user data, we can use the average value of all people's urine test results as the urine test result value for filling.

[0071] The data normalization is to convert the values ​​of each feature into the same range to eliminate the dimension and scale differences between the features. Commonly used data normalization methods include Min-Max normalization and Z-score normalization. For example, in an embodiment of the present application, the range of age may be 0-100, and the range of weight may be 0-200. The dimensions and numerical ranges of these two features are different. Using Min-Max normalization, both features can be scaled to the range of 0-1, so that the model will not be affected by the original numerical range. By preprocessing the user data to obtain a data set, the quality and applicability of the data can be improved.

[0072] The data set is divided into a training set and a test set. The training set is used to train the bladder cancer risk assessment model, and the test set is used to evaluate the performance of the trained bladder cancer risk assessment model. The data in the training set and the data in the test set may be the same or different.

[0073] The initial bladder cancer risk assessment model is trained according to the training set to obtain a bladder cancer risk assessment model. In the embodiment of the present application, the training set is converted into a feature vector, and the feature vector is input into the initial bladder cancer risk assessment model for training. For example, if the training set is age, gender, weight, and smoking history, then age, gender, weight, and smoking history are converted into a set of feature vectors.

[0074] The initial bladder cancer risk assessment model can be a supervised learning model, such as logistic regression, random forest, support vector machine, random network, etc. In the process of training the initial bladder cancer risk assessment model, the initial bladder cancer risk assessment model is adjusted and optimized by continuously adjusting the model's hyperparameters, selecting different feature information, and selecting different supervised learning models. The effect of the initial bladder cancer risk assessment model is verified on the training set using verification methods such as cross-validation. When the effect is consistent with the preset effect, the model training is terminated to obtain a trained bladder cancer risk assessment model.

[0075] The trained bladder cancer risk assessment model is tested using a test set. In the embodiment of the present application, the test set and training set used are different data sets. Therefore, for the trained bladder cancer risk assessment model, the test set is a new set of data sets, which can ensure the credibility of the test results. By inputting the risk assessment score obtained by the test set, it can be determined whether the trained bladder cancer risk assessment model has achieved satisfactory performance. When satisfactory performance is achieved, the trained bladder cancer risk assessment model can be deployed in an actual environment for actual bladder cancer risk assessment. The embodiment of the present application uses a test set to test the trained bladder cancer risk assessment model, which can ensure the accuracy of the trained bladder cancer risk assessment model in assessing bladder cancer risk.

[0076] The risk assessment score corresponding to the user to be recommended is outputted through a trained bladder cancer risk assessment model, wherein the risk assessment score is used to indicate the probability of the user's risk of bladder cancer, and the larger the value of the risk assessment score, the higher the probability of the user's risk of bladder cancer. For example, in an embodiment of the present application, the supervised learning model used by the bladder cancer risk assessment model is a logistic regression model, then the bladder cancer risk assessment model calculates the user's risk probability of bladder cancer through the feature information in the input data set, such as the feature information is age, physical condition, family medical history, smoking history, then through the bladder cancer risk assessment model, each feature information will have a corresponding weight, the model will multiply the value of the feature information with the corresponding weight to obtain the multiplication result value, and then add the multiplication result values, and finally convert the added result value into a probability value through the sigmoid function as the risk assessment score of bladder cancer.

[0077] The embodiment of the present application constructs a bladder cancer risk assessment model to obtain a risk assessment score, which can accurately assess the user's bladder cancer risk, improve the accuracy of bladder cancer risk assessment, and can also timely identify the user's bladder cancer risk level, so that the user can receive timely prompts and examinations, thereby improving the early detection rate of bladder cancer.

[0078] S30. According to the risk assessment score, the user to be recommended is provided with a bladder cancer risk warning, and a diagnosis and treatment plan determined according to the risk assessment score and a preset bladder cancer knowledge graph is pushed.

[0079] Specifically, the risk warning may be provided by sending an email, text message, or making a phone call to the user to be recommended.

[0080] The preset bladder cancer knowledge graph is pre-built to reflect the relationship between each feature information in the user data, bladder cancer, symptoms, and treatment methods for bladder cancer. For example, if the feature information is smoking and the symptom is hematuria, the relationship between smoking, bladder cancer, and hematuria can be expressed as "smoking-increased risk-bladder cancer-leading-hematuria".

[0081] In the embodiment of the present application, the diagnosis and treatment planning method for the bladder cancer risk group, wherein the diagnosis and treatment planning scheme is determined according to a preset bladder cancer knowledge graph, and the determination process of the preset bladder cancer knowledge graph specifically includes:

[0082] Acquiring bladder cancer medical data, wherein the bladder cancer medical data carries bladder cancer related information;

[0083] Entity extraction and relationship extraction are performed on the bladder cancer medical data, and a preset bladder cancer knowledge graph is constructed based on all the extracted entities and the relationships.

[0084] Specifically, the bladder cancer medical data are the medical literature and clinical guidelines for bladder cancer and case data of bladder cancer patients before the current time node. Among them, the medical literature for bladder cancer includes scientific research literature, clinical guidelines, patient medical records, etc. Case data includes basic patient information, laboratory tests, imaging tests, surgery-related information, drug-related information, etc., and also includes other factors that may affect the risk of bladder cancer, such as environmental factors, genetic factors, etc. Environmental factors include air quality and water quality in the place of residence. Genetic factors include mutations in specific genes, epigenetic markers, etc.

[0085] In the embodiment of the present application, the bladder cancer medical data needs to be preprocessed, and entity extraction and relationship extraction are performed on the preprocessed bladder cancer medical data. The entities and the relationships are basic elements for constructing a knowledge graph. The processing method for preprocessing the bladder cancer medical data is the same as the processing method for preprocessing the user data.

[0086] The entity is the basic unit in the knowledge graph, usually used to represent a specific thing or concept. For example, in bladder cancer medical data, entities may include: medical concepts, such as "bladder cancer", "urinary tract infection", "smoking" and other disease names or risk factors; people, such as specific patients or doctors; institutions, such as hospitals or research institutions; chemicals or drugs, such as "cisplatin", "paclitaxel", etc.

[0087] The entity extraction includes entity extraction of normalized data and entity extraction of non-normalized data. When entity extraction is performed on normalized data, entities are directly extracted according to text matching rules; when entity extraction is performed on non-normalized data, the parts of speech are first marked to extract nouns that meet the field, and then entities in the medical field of bladder cancer are obtained through text-based rule matching, added to the dictionary, and finally the words in the sentence are matched through the dictionary, and entities are extracted according to the matching results.

[0088] The relationship is used to represent the connection or interaction between two entities. For example, in bladder cancer medical data, the relationships mainly include: the relationship between disease and risk factors, such as "smoking-increases risk-bladder cancer"; the relationship between disease and symptoms, such as "bladder cancer-cause-hematuria"; the relationship between disease and treatment, such as "cisplatin-used to treat-bladder cancer".

[0089] The relationship extraction includes the relationship extraction of structured data and the relationship extraction of unstructured data. The relationship extraction of structured data includes the relationship extraction between entities and the attribute relationship extraction of some entities; the relationship extraction of unstructured data is to extract the relationship using the extraction method based on word vector convolution neural network.

[0090] The embodiments of the present application can extract useful medical knowledge about bladder cancer from a large amount of text data through entity extraction and relationship extraction, and construct a knowledge graph reflecting the medical knowledge about bladder cancer. The extraction of entities and relationships can also help determine which characteristic information in user data may be related to the risk of bladder cancer.

[0091] Construct a preset bladder cancer knowledge graph based on all extracted entities and all relationships. The knowledge graph is a graphical knowledge representation method, in which the nodes in the knowledge graph represent entities and the edges represent the relationships between entities. For example, suppose the following entity information and relationship information are obtained through text extraction: Entities: Bladder Cancer (Disease), Smoking (Risk Factor), Long-term Exposure to Chemicals (Risk Factor), Hematuria (Symptoms), Abdominal Pain (Symptoms), Chemotherapy (Treatment Method), Surgery (Treatment Method); Relationships: Smoking-Increases Risk-Bladder Cancer, Long-term Exposure to Chemicals-Increases Risk-Bladder Cancer, Bladder Cancer-Causes-Hematuria, Bladder Cancer-Causes-Abdominal Pain, Chemotherapy-Used to Treat-Bladder Cancer, Surgery-Used to Treat-Bladder Cancer. Based on the extracted entity information and relationship information, the following can be constructed: Figure 2 The preset bladder cancer knowledge graph is shown.

[0092] By presetting the bladder cancer knowledge graph, you can clearly see how various risk factors increase the risk of bladder cancer, what symptoms bladder cancer may cause, and what methods can be used to treat bladder cancer. Then, by presetting the bladder cancer knowledge graph, doctors can query the knowledge graph to obtain the latest treatment options, and patients can also query the knowledge graph to understand their condition and treatment options.

[0093] The embodiment of the present application can integrate bladder cancer medical knowledge from different sources by constructing a bladder cancer knowledge graph based on bladder cancer medical data. This can provide a comprehensive and structured knowledge base that helps to understand the risk factors, pathophysiological processes, diagnostic methods, treatment plans, etc. of bladder cancer.

[0094] In the embodiments of the present application, Figure 3 As shown, the bladder cancer risk reminder is given to the recommended user according to the risk assessment score, and the diagnosis and treatment plan determined according to the risk assessment score is pushed, which specifically includes:

[0095] S31, comparing the risk assessment score with a preset score threshold;

[0096] S32. If the risk assessment score is greater than a preset score threshold, determining the risk level corresponding to the risk assessment score based on a preset level sequence, determining a diagnosis and treatment plan based on a preset bladder cancer knowledge graph, and pushing the risk level and the diagnosis and treatment plan to the user to be recommended;

[0097] S33: If the risk assessment score is less than or equal to a preset score threshold, the risk assessment score is pushed to the user to be recommended.

[0098] Specifically, in step S31, the preset score threshold is used to determine whether the user to be recommended has a numerical value of the risk of bladder cancer. The setting of the preset score threshold usually depends on the need to balance misdiagnosis and missed diagnosis, and the receiver operating characteristic curve (ROC) can be used to help set the optimal preset score threshold. The preset score threshold is not a fixed value, and the preset score threshold can be adjusted according to different patient groups or different medical conditions. Among them, the patient group can be divided into groups according to age, gender, etc.; medical conditions are divided according to medical resources, for example, urban hospitals and rural hospitals.

[0099] In step S32, if the risk assessment score is greater than a preset score threshold, it indicates that the user to be recommended has a risk of developing bladder cancer.

[0100] The preset level sequence is used to determine the risk level of the recommended user who has the risk of bladder cancer. The preset level sequence includes a low risk level sequence, a medium risk level sequence, and a high risk level sequence. By determining which level sequence the risk assessment score belongs to, the risk level of the user suffering from bladder cancer is obtained.

[0101] In an embodiment of the present application, the risk levels are divided into low risk, medium risk and high risk. Low risk means that the user's risk of bladder cancer is low and requires a lower frequency of routine testing. Medium risk means that the user's risk of bladder cancer is moderate and requires a higher frequency of regular and comprehensive monitoring. High risk means that the user's risk of bladder cancer is very high and requires a risk warning and push notification of a diagnosis and treatment plan. For example, if the value range of the risk assessment score is set to 0-1, 0 means that it is impossible to get bladder cancer, the larger the value, the greater the probability of getting bladder cancer, and 1 means that you will definitely get bladder cancer. At this time, the preset score threshold is set to 0.5. When the risk assessment score is less than or equal to 0.5, it means that there is no risk of bladder cancer or the probability of bladder cancer is extremely small; when the risk assessment score is greater than 0.5, it means that there is a certain risk of bladder cancer. At this time, if the low risk level sequence is set to 0.5-0.7, the medium risk level sequence is set to 0.71-0.85, and the high risk level sequence is set to 0.86-1, if the risk assessment score of the user to be recommended is 0.78, then the risk assessment score is in the medium risk level sequence. At this time, the risk level of the user to be recommended is medium risk, and the user needs regular and comprehensive monitoring at a higher frequency.

[0102] In step S33, if the risk assessment score is less than or equal to the preset score threshold, it means that the user to be recommended has no risk of bladder cancer or the probability of bladder cancer risk is extremely small, and the risk assessment score only needs to be pushed to the user to be recommended.

[0103] The embodiment of the present application divides the push mode by presetting a score threshold, so that the risk level and the treatment plan can be pushed to the recommended users with high risks, and the impact of the risk level and the treatment plan on the users with low risks can be avoided.

[0104] In the embodiment of the present application, the diagnosis and treatment planning method for the bladder cancer risk group, wherein the determination of the diagnosis and treatment planning scheme based on the preset bladder cancer knowledge graph specifically includes:

[0105] Searching for diagnostic and treatment methods corresponding to bladder cancer and the diagnostic and treatment effects corresponding to each diagnostic and treatment method in the preset bladder cancer knowledge graph;

[0106] Based on the diagnosis and treatment impact and the user data, a diagnosis and treatment planning scheme corresponding to the user to be recommended is determined.

[0107] Specifically, the diagnostic and treatment methods corresponding to bladder cancer and the diagnostic and treatment effects corresponding to each diagnostic and treatment method are searched in the preset bladder cancer knowledge graph. For example, the user to be recommended is a long-term smoker, and the risk assessment level of the user to be recommended is high risk. Then, according to the constructed bladder cancer knowledge graph "smoking--increased risk-->bladder cancer", the corresponding diagnostic and treatment methods can be used to warn the user of the risk and push the diagnosis and treatment plan.

[0108] Based on the diagnosis and treatment impact and the user data, a diagnosis and treatment plan corresponding to the recommended user is determined, wherein the diagnosis and treatment plan may include further urine cytology examination, urine biomarker test, imaging examination, etc., so as to detect possible bladder cancer as early as possible.

[0109] The embodiment of the present application constructs a bladder cancer knowledge graph to search for corresponding diagnosis and treatment methods and determine the user's diagnosis and treatment plan. Doctors can obtain the latest diagnosis and treatment plans by querying the knowledge graph, so that they can provide targeted diagnosis and treatment for patients, optimize the allocation of medical resources, and improve the efficiency and effectiveness of medical services.

[0110] In the embodiment of the present application, the diagnosis and treatment planning method for the bladder cancer risk group, wherein the method further comprises:

[0111] According to the preset bladder cancer knowledge graph and the user data, the bladder cancer risk factors of the to-be-recommended user are determined, and the bladder cancer risk factors are pushed to the to-be-recommended user.

[0112] Specifically, risk factor prompts and treatment plans may require interaction with users, such as pushing risk factor prompts and treatment plans to recommended users via email, text messages, mobile application notifications, phone calls, etc.

[0113] By pushing bladder cancer risk factors to users, the embodiments of the present application can help users identify their own risk factors for bladder cancer, thereby adjusting or changing their lifestyle habits to reduce the probability of developing bladder cancer.

[0114] In the embodiment of the present application, the diagnosis and treatment planning method for the bladder cancer risk group, wherein the method further comprises:

[0115] The bladder cancer risk assessment model is updated at preset time intervals, and the preset bladder cancer knowledge graph is updated, wherein when the preset bladder cancer knowledge graph is updated, the difference bladder cancer medical data between the bladder cancer medical data obtained at the updating time and the bladder cancer medical data obtained at the construction time of the preset bladder cancer knowledge graph is used as the updated bladder cancer medical data.

[0116] In the embodiment of the present application, updating the bladder cancer risk assessment model at every preset time interval specifically includes:

[0117] Collect new user data, perform data preprocessing on the new user data, and obtain a new data set;

[0118] Input a new data set to train the bladder cancer risk assessment model, and obtain a newly trained bladder cancer risk assessment model;

[0119] Compare the performance of the newly trained bladder cancer risk assessment model with the current bladder cancer risk assessment model to obtain comparative results;

[0120] Based on the comparison results, decide whether to update the current bladder cancer risk assessment model.

[0121] The embodiment of the present application ensures that the risk assessment model is always kept up to date by updating the bladder cancer risk assessment model at preset time intervals and updating the preset bladder cancer knowledge graph, so as to dynamically identify and examine the risk population with the highest accuracy.

[0122] In summary, this embodiment provides a method, device, equipment and storage medium for diagnosis and treatment planning of bladder cancer risk groups, and the method includes: obtaining user data of a user to be recommended, wherein the user data includes basic feature data, health data and living habit data; inputting the user data into a trained bladder cancer risk assessment model, and outputting the risk assessment score corresponding to the user to be recommended through the bladder cancer risk assessment model; according to the risk assessment score, providing a bladder cancer risk prompt to the user to be recommended, and pushing a diagnosis and treatment planning scheme determined according to the risk assessment score and a preset bladder cancer knowledge graph. By constructing a bladder cancer risk assessment model and a bladder cancer knowledge graph, a diagnosis and treatment planning scheme is obtained, and the user's bladder cancer risk can be accurately assessed, which improves the accuracy of risk assessment, and the user's risk of bladder cancer can be identified in time, so that the user can get timely prompts and examinations, and the early detection rate of bladder cancer is improved. At the same time, early diagnosis and treatment can also reduce the impact of the disease on the patient's quality of life. By providing users with targeted diagnosis and treatment planning schemes, the allocation of medical resources can be optimized and the efficiency and effectiveness of medical services can be improved. At the same time, the large amount of user data collected and analyzed and the results of risk assessment can also provide important data resources for bladder cancer research.

[0123] Based on a method for diagnosing and planning treatment for a population at risk of bladder cancer, this embodiment provides a device for diagnosing and planning treatment for a population at risk of bladder cancer, such as Figure 4 As shown, the diagnosis and treatment planning device for the bladder cancer risk group specifically includes:

[0124] The acquisition module 100 is used to acquire user data of the user to be recommended, wherein the user data includes basic feature data, health data and life habit data;

[0125] An evaluation module 200, configured to input the user data into a trained bladder cancer risk evaluation model, and output a risk evaluation score corresponding to the user to be recommended through the bladder cancer risk evaluation model;

[0126] The planning module 300 is used to provide bladder cancer risk warnings to the recommended user based on the risk assessment score, and push a diagnosis and treatment planning plan determined based on the risk assessment score and a preset bladder cancer knowledge graph.

[0127] Based on a method for diagnosis and treatment planning for a group at risk of bladder cancer, an embodiment of the present application provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps in any of the methods for diagnosis and treatment planning for a group at risk of bladder cancer as described above.

[0128] Based on a method for diagnosis and treatment planning of a population at risk of bladder cancer, an embodiment of the present application provides a terminal device, which includes: a processor and a memory;

[0129] The memory stores a computer-readable program executable by the processor;

[0130] When the processor executes the computer-readable program, the processor implements the steps in any of the above-mentioned methods for diagnosis and treatment planning for a group of people at risk of bladder cancer.

[0131] The terminal device, such as Figure 5 As shown, it includes at least one processor (processor) 20; display screen 21; and memory (memory) 22, and may also include a communications interface (Communications Interface) 23 and a bus 24. Among them, the processor 20, the display screen 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a preset user guide interface in the initial setting mode. The communication interface 23 can transmit information. The processor 20 can call the logic instructions in the memory 22 to execute the method in the above embodiment.

[0132] In addition, the logic instructions in the memory 22 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.

[0133] The memory 22 is a computer-readable storage medium that can be configured to store software programs, computer executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions or modules stored in the memory 22, that is, implementing the methods in the above embodiments.

[0134] The memory 22 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 22 may include a high-speed random access memory and may also include a non-volatile memory. For example, a variety of 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, may also be a transient storage medium.

[0135] In addition, the specific process of loading and executing the multiple instruction processors in the above storage medium and the terminal device has been described in detail in the above method and will not be described here one by one.

[0136] 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 method for diagnosis and treatment planning for people at risk of bladder cancer. It is characterized in that The diagnosis and treatment planning method for the bladder cancer risk group specifically includes: Acquire user data of the user to be recommended, wherein the user data includes basic feature data, health data and life habit data; Inputting the user data into a trained bladder cancer risk assessment model, and outputting a risk assessment score corresponding to the user to be recommended through the bladder cancer risk assessment model; According to the risk assessment score, the bladder cancer risk is prompted to the recommended user, and a diagnosis and treatment plan determined according to the risk assessment score and a preset bladder cancer knowledge graph is pushed.

2. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to claim 1, It is characterized in that The basic characteristic data include age, gender, race and family medical history; the health data include diabetes data, weight data and hypertension data; the lifestyle data include smoking data and occupational exposure data.

3. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to claim 1, It is characterized in that Prompting the user to be recommended for bladder cancer risk based on the risk assessment score and pushing a diagnosis and treatment plan determined based on the risk assessment score specifically includes: comparing the risk assessment score to a preset score threshold; If the risk assessment score is greater than a preset score threshold, the risk level corresponding to the risk assessment score is determined based on a preset level sequence, a diagnosis and treatment plan is determined based on a preset bladder cancer knowledge graph, and the risk level and the diagnosis and treatment plan are pushed to the user to be recommended; If the risk assessment score is less than or equal to the preset score threshold, the risk assessment score is pushed to the user to be recommended.

4. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to claim 1, It is characterized in that Determining the diagnosis and treatment plan based on the preset bladder cancer knowledge graph specifically includes: Searching for diagnostic and treatment methods corresponding to bladder cancer and the diagnostic and treatment effects corresponding to each diagnostic and treatment method in the preset bladder cancer knowledge graph; Based on the diagnosis and treatment impact and the user data, a diagnosis and treatment planning scheme corresponding to the user to be recommended is determined.

5. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to any one of claims 1 to 4, It is characterized in that The diagnosis and treatment plan is determined according to a preset bladder cancer knowledge graph, wherein the process of determining the preset bladder cancer knowledge graph specifically includes: Acquiring bladder cancer medical data, wherein the bladder cancer medical data carries bladder cancer related information; Entity extraction and relationship extraction are performed on the bladder cancer medical data, and a preset bladder cancer knowledge graph is constructed based on all the extracted entities and the relationships.

6. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to claim 1, It is characterized in that The method further comprises: According to the preset bladder cancer knowledge graph and the user data, the bladder cancer risk factors of the to-be-recommended user are determined, and the bladder cancer risk factors are pushed to the to-be-recommended user.

7. The method for diagnosis and treatment planning for a population at risk of bladder cancer according to claim 1, It is characterized in that The method further comprises: The bladder cancer risk assessment model is updated at preset time intervals, and the preset bladder cancer knowledge graph is updated, wherein when the preset bladder cancer knowledge graph is updated, the difference bladder cancer medical data between the bladder cancer medical data obtained at the updating time and the bladder cancer medical data obtained at the construction time of the preset bladder cancer knowledge graph is used as the updated bladder cancer medical data.

8. A diagnosis and treatment planning device for people at risk of bladder cancer, It is characterized in that The diagnosis and treatment planning device for the bladder cancer risk group specifically includes: An acquisition module, used to acquire user data of the user to be recommended, wherein the user data includes basic feature data, health data and life habit data; An evaluation module, used for inputting the user data into a trained bladder cancer risk evaluation model, and outputting a risk evaluation score corresponding to the user to be recommended through the bladder cancer risk evaluation model; The planning module is used to provide bladder cancer risk warnings to the recommended user based on the risk assessment score, and to push a diagnosis and treatment planning plan determined based on the risk assessment score and a preset bladder cancer knowledge graph.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the diagnosis and treatment planning method for a bladder cancer risk group as described in any one of claims 1-7.

10. A terminal device, It is characterized in that include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the processor implements the steps of the method for diagnosis and treatment planning for a group of people at risk of bladder cancer as described in any one of claims 1-7.

Images