CN111899888A - Gynecological tumor disease risk prediction visualization system - Google Patents

Abstract

The invention discloses a gynecological tumor disease risk prediction visualization system, which comprises a risk prediction model construction module, wherein gynecological related disease variables are obtained from gynecological cases, correlation analysis is carried out on the gynecological related disease variables and gynecological events, and a gynecological risk prediction model is constructed on the basis of screened risk factors; the gynecological probability prediction module receives the disease risk prediction request, calls a related historical disease data queue, and obtains a gynecological disease probability prediction result based on a gynecological prediction model; and the health report generation module is used for generating a visual report according to the gynecological morbidity prediction result, the acquired physiological index information of the user, the risk factors related to the user and the contribution rate of the risk factors. The gynecological disease probability is predicted according to the physiological indexes of the tested person, the probability value determined by the indexes can be intuitively known, and the data relation among the indexes is intuitively displayed by combining the visualization of the diagnosis report result.

Description

A visualization system for risk prediction of gynecological tumor diseases

technical field

The invention belongs to the technical field of medical big data processing, and in particular relates to a gynecological tumor disease risk prediction visualization system.

Background technique

The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

Gynecological tumor diseases include ovarian cancer, cervical cancer, breast cancer, endometrial cancer, etc. At present, there are several clinical indicators for gynecological risk prediction, such as the prediction of ovarian cancer. Cancer antigen CA125 is the most commonly used to monitor ovarian cancer. Tumor marker, CA125 exists in epithelial gynecological tissues and serum of patients. It is mainly used to assist in the diagnosis of malignant serous ovarian cancer and epithelial ovarian cancer. However, the inventors found that CA125 is not sensitive for early ovarian cancer surveillance. Another marker, human epididymal protein 4 (HE4), is highly expressed in ovarian cancer tissues and patient serum, but is low or not expressed in normal ovarian tissues or benign tumors, but the inventors found that this method can be used in large-scale applications The quality control, sample preparation and other problems encountered in the detection of serum samples; and the definition of the critical value and the combination of CA125 in the joint detection of CA125.

Furthermore, when constructing prediction models, the Gail model and Claus model are commonly used, such as the prediction of breast cancer. The Gail model is the world's first breast cancer risk prediction model, which incorporates four risk factors: age at menarche, previous breast Number of biopsies, age at first live birth, and number of first-degree relatives (mother or sister) with breast cancer. However, because the model is based on white Americans, it may have racial limitations; in addition, the Gail model HIA ignores the age at diagnosis of breast cancer in first-degree relatives, the status of breast cancer in second-degree relatives, and the family history of breast cancer.

The Claus model is mainly used to evaluate women with a family history of breast cancer. The risk factors included in the model are age, the number of relatives with breast cancer, and the age of onset, but the model is not applicable to women without a family history of breast cancer, and in Applications for other races are also subject to further verification.

To sum up, very few gynecological risk prediction models have been established at present, and the indicators used in the establishment of the models are mainly obtained by means of clinical experience and existing public literature. Some models are not universal; at the same time, the above-mentioned methods of diagnosing gynecology based on markers or extracting relevant pathological images for image recognition and diagnosis are all methods of diagnosing gynecology. In the process of physical examination, only the above methods cannot find the potential incidence of disease, or the abnormality of a certain physical examination index cannot effectively diagnose whether there is an incidence of disease.

Secondly, for the diagnosis results, most of them are in the form of paper physical examination reports for users to view, or in the form of spreadsheets, the indicators of the diagnosis process are presented in tables; the data are presented in the form of tables, static data The form reduces the user's physical examination, lacks intuitiveness, and data visualization can realize dynamic display; in addition, it cannot visually display the data relationship between various indicators, and the visualization technology of prediction results is not promoted.

In addition, in the field of insurance, premiums are determined for customers based on age and gender factors, and the pricing is single and does not have individual specificity; moreover, in the traditional insurance industry, the risk model for user health assessment is constructed based on traditional industry experience. , it is impossible to accurately obtain and evaluate customer health information, nor to update it in real time, and it is impossible to exclude false information. There are problems such as single pricing and simple underwriting in the design of customer-oriented insurance products.

SUMMARY OF THE INVENTION

In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a gynecological tumor disease risk prediction visualization system, which can predict the probability of suffering from gynecology according to the physiological indicators of the subject, and can intuitively understand which indicators determine the probability value. At the same time, combined with the visualization of the diagnostic report results, the data relationship between each indicator can be visually displayed.

To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:

A gynecological tumor disease risk prediction visualization system, including:

Risk prediction model building module, obtain relevant disease variables in cases, conduct correlation analysis with gynecological tumor events, and screen out risk factors; build gynecological tumor disease risk prediction models based on the screened risk factors;

The probability prediction module of gynecological tumor diseases receives the request for prediction of the incidence risk, retrieves the relevant historical disease data queue, and obtains the prediction result of the probability of gynecological incidence based on the gynecological prediction model;

The health report generation module generates a visual report according to the prediction result of the incidence probability of gynecological tumor diseases, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

In further embodiments, there is provided an electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, the computer instructions, when executed by the processor, perform the following steps:

Obtain relevant disease variables in gynecological tumor cases, conduct correlation analysis with tumor events, and screen out risk factors; build gynecological tumor disease risk prediction models based on the screened risk factors;

Receive disease risk prediction requests, retrieve relevant historical disease data queues, and obtain gynecological tumor disease incidence probability prediction results based on prediction models;

A visual report is generated according to the prediction results of the incidence probability of gynecological tumor diseases, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

In further embodiments, a computer-readable storage medium is provided for storing computer instructions that, when executed by a processor, perform the following steps:

Obtain gynecological tumor disease-related variables from gynecological tumor cases, conduct correlation analysis with gynecological tumor events, and screen out risk factors; build a gynecological tumor disease risk prediction model based on the screened risk factors;

Receive disease risk prediction requests, retrieve relevant historical disease data queues, and obtain gynecological tumor disease incidence probability prediction results based on prediction models;

A visual report is generated according to the prediction results of the incidence probability of gynecological tumor diseases, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

One or more of the above technical solutions have the following beneficial effects:

The present invention adopts data visualization, uses charts to summarize complex data, ensures that users can clearly and intuitively understand data relationships, and uses big data visualization tools to report complex information with short graphics, even a single graphic can do it, Interpret various data relationships through interactive elements and new visualization tools like heatmaps, fever charts, and more.

In the field of insurance, insurance companies can supplement and support traditional insurance underwriting methods according to the disease risk of the insured output by the system, accurately block high-risk customer groups, and improve the efficiency of manual underwriting. At the same time, the disease risk prediction results based on the population can also provide more accurate disease incidence data for insurance companies to design insurance products in the future, making it possible to design differentiated premium insurance products for different individual health levels, allowing customers to enjoy more Reasonable rates, more comprehensive insurance protection, and support for insurance companies to innovate health insurance products to attract more high-quality customers.

The gynecological tumor disease prediction model of the present invention is based on disease-related risk factors, rather than markers or image processing methods, and the existing model does not take into account the influence of disease risk factors, and cannot find potential potential with normal physiological indicators. The incidence of the disease, or the abnormality of a certain physical examination index cannot effectively diagnose whether there is an incidence of the disease. Based on the modeling of disease risk factors, the present invention facilitates the discovery of high-risk individuals, early intervention or treatment, and improvement of life quality.

Based on the disease big data queue, the invention fully mines the risk factors related to gynecology by using data mining methods such as correlation analysis, which largely makes up for the subjectivity of only manual screening; and, under the support of disease big data, It ensures that risk factors are not omitted, and the generality of subsequent prediction models is guaranteed.

Description of drawings

The accompanying drawings forming a part of the present invention are used to provide further understanding of the present invention, and the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, and do not constitute an improper limitation of the present invention.

1 is a functional architecture diagram of a gynecological risk prediction visualization system provided in Embodiment 1 of the present invention;

FIG. 2 is a flowchart of the data standardization method provided in Embodiment 1 of the present invention.

Detailed ways

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the invention. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be noted that the terminology used herein is for the purpose of describing specific embodiments only, and is not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural as well, furthermore, it is to be understood that when the terms "comprising" and/or "including" are used in this specification, it indicates that There are features, steps, operations, devices, components and/or combinations thereof.

Embodiments of the invention and features of the embodiments may be combined with each other without conflict.

Example 1

As shown in FIG. 1 , this embodiment discloses a visualization system for risk prediction of gynecological tumor diseases, including a cloud platform, and the cloud platform includes:

Risk prediction model building module, obtain gynecological-related disease variables in gynecological cases, conduct correlation analysis with gynecological events, and screen out risk factors; build gynecological risk prediction models based on the screened risk factors;

The gynecological probability prediction module receives the request for onset risk prediction, retrieves the relevant historical disease data queue, and obtains the gynecological onset probability prediction result based on the gynecological prediction model;

The health report generation module generates a visual report according to the prediction result of gynecological incidence probability, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

In the said risk prediction model building block:

The disease big data queue is retrieved from the distributed database system, specifically:

Step 1.1: According to the preset disease-related fields, find the data tables containing these fields in the distributed database system;

Step 1.2: Based on the found data table, extract fields such as ID number, disease, disease code, onset time, etc., and record the data source of the disease, such as source city, source data table, ID in the data table, etc., Generate disease big data cohorts.

The distributed database system includes medical information databases located in various cities. In this embodiment, the medical information database includes a full-staff population information database, a public health database, an electronic medical record database, a medical insurance database, a health examination database, a cause-of-death database, etc. distributed in various cities in Shandong Province.

Wherein, the population information database of all employees includes: basic personal information of residents, social security information, housing information, and information on residents' integrity and dishonesty.

The public health database includes: basic personal health information, disabled person form, health check-up form, student medical check-up form, birth medical certificate, newborn family visit information, child health examination information, prenatal follow-up service information, and birth record form , postpartum visit service information, pregnancy examination record form, vaccination card information, infectious disease report card, occupational disease report card, food-borne disease card, death medical certificate, follow-up form for patients with hypertension, follow-up form for patients with type 2 diabetes, severe Sexual mental illness patient management table, serious mental illness patient information, serious mental illness patient discharge information, coronary heart disease patient information, stroke patient information, tumor patient information, tuberculosis patient follow-up form, childbearing age couple information, marriage information, birth registration and Fertility approval information, pregnancy information, women's reproductive history information, contraceptive information, family planning surgery information, outflow population information, inflow population information, outpatient summary information, and hospitalization summary information.

The electronic medical record database includes: outpatient/emergency registration, outpatient/emergency visit records, outpatient/emergency/inpatient western medicine prescriptions, outpatient/emergency/inpatient Chinese medicine prescriptions, inspection records, details of inspection results, inspection records, admission records, inpatient medical records Home page, home page of TCM inpatient medical records, and discharge records.

The health check-up database includes: a check-up report, a check-up item table, and a check-up item list.

The medical insurance database includes: basic information, diagnosis and treatment information, general information on medical insurance expenses, and detailed information on medical insurance expenses.

As shown in Figure 2, data normalization is performed on the disease big data cohort:

Step 2.1: Screen the sample data set from the disease big data queue, compare the disease names in the sample data with the disease names in the disease classification standard, and standardize the disease names in the sample data;

Wherein, the standardizing the disease names in the sample data includes: creating a standardized name field, and performing the standardization according to the following steps in sequence:

(1) Control with the same name: Obtain sample data whose disease name is completely consistent with the disease name in the disease classification standard, and write the original disease name into the standardized name field.

(2) Name similarity comparison: obtain sample data whose disease name and disease name similarity in disease classification standards exceed the set threshold, and write the original disease name into the standardized name field; the similarity measure can be cosine similarity, European Existing text similarity methods, such as Clan distance, are not limited here.

(3) Inclusion control: Obtain sample data with an inclusion relationship between the disease name and the disease name in the disease classification standard, such as "prostatitis (non-surgical treatment)" and "prostatitis", and write the original disease name into the standardized name field.

(4) The standardized name of the sample data is manually reviewed by the user via the client. Specifically, during manual review, the disease names can be sorted by frequency, and the disease names with high frequency are prioritized for review.

During the standardization process, the system automatically records the comparison method corresponding to each disease name in the disease big data queue. In this embodiment, the sample data set selects medical insurance data with better data quality (about 60,000 pieces), and the disease classification standard is coded by ICD10.

Step 2.2: For the unstandardized data in the disease big data cohort, compare the disease name with the original disease name in the sample data, and complete the standardization of some disease names;

Wherein, the control method is the same as step 2.1. Specifically, for the data in which the disease name and the original disease name in the sample data satisfy the same name, the name similarity is greater than the set threshold, or there is an inclusion relationship, the standardized name corresponding to the original disease name in the sample data is written into the standardized field.

Step 2.3: For the remaining unstandardized data in the disease big data cohort, compare the disease code with the code in the disease classification standard, and for the data with successful coding comparison, write the disease name corresponding to the code in the disease classification standard into the standardized field .

Specifically, the disease codes are compared with the codes in the disease classification standards in stages: firstly, all 6 digits of the codes in the disease classification standards are compared, then the first 4 digits are compared, and finally the first 2 digits are compared.

Step 2.4: The standardized names in the disease big data queue are manually reviewed by the user through the client. Due to the large amount of data to be standardized (about 7 million), the disease names can be sorted by frequency here, and only the review frequency is large. the name of the disease;

Step 2.5: Statistical comparison rate, if the comparison rate exceeds the set threshold, the standardization ends.

For medical big data with complex sources, this embodiment obtains standardized data of sample data based on multiple levels of text matching methods, and then completes massive data standardization based on the standardized data of samples in sequence by matching names and codes. Compared with the direct matching between all medical big data and standard data, higher standardization rate and accuracy rate can be obtained, and the efficiency of standardization can be taken into account.

Based on the disease big data cohort standardized by disease data, establish a gynecological tumor disease cohort, specifically:

Step 3.1: Retrieve the names of diseases related to gynecology from the disease big data queue; since there are many expressions related to gynecology, synonym expansion is required here, and those skilled in the art can understand that it can also be retrieved by constructing logical expressions;

Step 3.2: The user reviews the retrieved gynecological-related disease names via the client; those skilled in the art can understand that the review can be performed for individual deletion of data records, or can be deleted in batches by constructing logical expressions;

Step 3.3: According to the names of gynecological-related diseases, match the ID number, gender, region and other data from the disease big data cohort to obtain the gynecological tumor disease cohort.

Each data in the gynecological tumor disease cohort can be used as an index for additional retrieval. For example, for a certain ID number in the gynecological tumor disease cohort, all relevant medical data records corresponding to the ID number can be obtained from the distributed database.

In this embodiment, the receiving queue is included in the exclusion criteria, and a final queue is constructed, one part is used for modeling, and the other part is used for model verification. is configured to perform the following steps:

In this example, the inclusion criteria for cohort cases are: the initial diagnosis of gynecology from January 1, 2012 to December 31, 2016, the incidence of gynecology, with clear clinical imaging examination or/and pathological verification information ; Cohort exclusion criteria: individuals who died and developed all types of cancer before January 1, 2012.

In the risk prediction model building module, relevant risk factors are counted and screened according to gynecological-related disease variables:

Step 4.1: Perform correlation analysis between each disease variable and gynecological events, and use disease variables with a correlation greater than a set threshold as a candidate risk factor; this embodiment adopts a multi-factor Cox proportional hazards model.

(1) According to whether there is a disease variable, construct a binary risk factor matrix X, in which each row corresponds to a person, each column corresponds to a type of risk factor, and the mth row of the matrix X and the nth column X(m, n) represent Whether the mth person has the nth disease variable, if so, record it as 1, if not, record it as 0;

(2) According to whether a gynecological event occurs, construct a binarized gynecological matrix Y, wherein the matrix Y includes a column, and each row corresponds to whether a gynecological event occurs in a person;

(3) Perform correlation analysis between each column of the binary risk factor matrix X and matrix Y to obtain a correlation matrix R. Each element in the matrix R represents the correlation between each disease variable and gynecology, and the correlation is greater than the set value. Threshold disease variables served as candidate risk factors.

Step 4.2: Based on the Bayesian network, screen the final risk factors from the candidate risk factors.

A Bayesian network is a graphical pattern representing the probability of connections between variables, which can be used to discover potential relationships between data. The result of Bayesian learning is represented as a probability distribution of random variables, which can be interpreted as the degree of trust in different possibilities . In this embodiment, the candidate risk factors and gynecological events obtained in the step 4.1 are input into the Bayesian network, and the candidate risk factors related to the gynecological events are obtained as the final risk factors.

Those skilled in the art can understand that, based on literature, clinical data and national standards, artificial auxiliary index screening can also be used, and various index screening methods can be adopted to prevent the omission of important indicators.

In the gynecological probability prediction module, the calculation method of the gynecological incidence probability prediction result is:

Receive the prediction request sent by the user terminal, and retrieve the historical disease data queue of the user. For each risk factor variable in the prediction model, if the user suffers from the disease corresponding to the risk factor, the risk factor variable is assigned as 1, otherwise it is assigned a value of 0, and the probability of gynecological morbidity of the user is calculated.

Obtain the user's gynecological risk factors and the contribution rate of each risk factor;

Specifically, the calculation method of the contribution rate of each risk factor is:

For each risk factor variable with a value of 1 above, assign a value of 0 and calculate the incidence probability of gynecology to obtain the incidence probability when the user does not suffer from the disease corresponding to the risk factor; compare it with the incidence probability obtained by the gynecology probability prediction module Do the difference, and get the contribution rate of each risk factor's corresponding disease to the user's gynecology.

In more embodiments, an ovarian cancer disease risk prediction system is provided, comprising constructing a risk prediction model according to the screened risk factors;

The ovarian cancer-related disease variables include endometriosis, polycystic ovary syndrome, pelvic inflammatory disease, ovarian cysts, uterine fibroids, benign ovarian tumors, and diabetes.

Screening risk factors included: age, endometriosis, pelvic inflammatory disease, ovarian cysts, uterine fibroids, benign ovarian tumors, and diabetes.

Build risk prediction models, including:

Step 5.1: Based on the screened risk factors, the Cox risk regression model was used for univariate analysis, and the independent predictors were selected by the stepwise screening method to establish a multi-factor Cox proportional hazards model. Inspection level α=0.05.

Step 5.2: The risk factors of age, endometriosis, pelvic inflammatory disease, ovarian cysts, uterine fibroids, benign ovarian tumors and diabetes were entered into the multivariate Cox proportional hazards model to establish a disease prediction model.

Specifically, firstly, single-factor modeling is performed based on each risk factor to obtain the initial prediction model with the best prediction performance, and the corresponding risk factor is the most important factor; then, on the basis of the initial prediction model, other risks are introduced. One of the factors, carry out two-factor modeling, and obtain the two-factor prediction model with the best prediction performance. The newly introduced risk factor is the second most important factor; and so on, new risk indicators are introduced in turn, until the performance of the prediction model is no longer. enhanced.

Among them, each time a prediction model is constructed, ROC, sensitivity and specificity are calculated; then NRI=(sensitivity test2+specificity test2)-(sensitivity test1+specificity test1) is calculated as a measure of model performance. If NRI>0, it indicates that after adding new predictors, the predictive ability of the new model has improved, and the proportion of correct classification has increased by NRI percentage points. The more the NRI improves, the better the variable predicts and the more important the variable is.

The construction of the model in this embodiment adopts the method of introducing one risk factor at a time, and gradually determines the risk factor most relevant to gynecology, and ensures the accuracy of prediction.

Based on this, the prediction model with the best performance was obtained, and at the same time, the importance of the screened risk factors was ranked.

In more embodiments, a cervical cancer risk prediction system is provided, which adopts the Gail model to establish a cervical cancer disease prediction model;

Cervical cancer-related disease variables included human papillomavirus infection, pelvic inflammatory disease, cervicitis, IUD installation, uterine leiomyomas, pregnancy with macrosomia, and ectopic pregnancy;

Post-screening risk factors include: human papillomavirus infection, pelvic inflammatory disease, cervicitis, uterine leiomyomas, and IUD installation.

In more embodiments, a breast cancer risk prediction system is provided, which adopts a logistic regression model and a Gail model to construct a breast cancer risk prediction model;

Breast cancer-related disease variables included age, mastitis, benign breast tumors, breast hyperplasia, uterine fibroids, breast cysts, breast masses, breast duct fistulas, breast dysplasia, and premature breast development;

Screened risk factors included age, mastitis, benign breast tumors, breast hyperplasia, uterine fibroids, and breast cysts.

In more embodiments, an endometrial cancer risk prediction system is provided, using a logistic regression model to construct an endometrial cancer risk prediction model based on the screened risk factors,

Endometrial cancer-related disease variables include hypertension, diabetes, obesity, coronary heart disease, infertility, anemia, ovarian disease, and uterine fibroids;

Risk factors screened for include diabetes, hypertension, ovarian disease, infertility, uterine fibroids and anemia.

In this embodiment, the system further includes:

The user management module is used to manage the identity information of registered users;

The disease coping strategy management module is used to store the precautions and coping suggestions for various diseases;

The gynecological risk factor guidance module, to obtain the corresponding coping strategies for the diseases that the user suffers from affecting gynecology;

The health report generation module is used to generate visual reports based on health information, gynecological incidence probability prediction results and gynecological risk factor guidance results. The visual report includes graphics, such as dot plots, heat maps, bubble charts, and the like.

The relevant data processing methods are pre-packaged in the cloud platform. The above data processing is performed on the cloud platform, and the data will not be transmitted to other terminals, which ensures the security of the data and protects the privacy of users.

In this embodiment, the cloud platform is used as the core of data aggregation and data processing, and is connected with the databases of medical institutions at all levels, so as to ensure the authenticity and integrity of the data and the security of the data.

This embodiment provides a health assessment system for the user, which can predict the probability of the user's gynecological onset and the contribution rate of the gynecological-related diseases suffered by the user, and provide coping strategies for these diseases, so as to guide the user to prevent gynecology.

In this embodiment, the system includes a working terminal, and the working terminal includes:

The data standardization module is used to review the standardization results of sample data and all data standardization results in the cloud platform;

A gynecology-related disease name acquisition module, used to receive gynecology-related disease names input by the user, or a logical expression for retrieving disease names; and reviewing the retrieved disease names;

The risk factor determination module is used to obtain candidate risk factors and their Bayesian network structure diagram from the cloud platform, receive the user's confirmation and correction of risk factors and send them to the cloud platform;

Model building blocks for receiving case inclusion criteria and the model employed;

The model correction module is used to correct the adopted model and model parameters.

User terminal, including:

The login authentication module is used to authenticate the user identity;

The health report viewing module is used to obtain the user's health information from the cloud platform, including historical physical examination information, case information, etc.;

The gynecological probability prediction module is used to obtain the gynecological incidence probability prediction results from the cloud platform;

The gynecological risk factor guide module is used to obtain the user's gynecological risk factors and the contribution rate of each risk factor from the cloud platform;

The health report generation module is used to generate visual reports based on health information, gynecological incidence probability prediction results and gynecological risk factor guidance results.

In further embodiments, there is also provided:

An electronic device, comprising a memory and a processor and computer instructions stored in the memory and running on the processor, when the computer instructions are executed by the processor, the following steps are completed:

Obtain gynecological-related disease variables from gynecological cases, conduct correlation analysis with gynecological events, and screen out risk factors; build a gynecological risk prediction model based on the screened risk factors;

Receive disease risk prediction requests, retrieve relevant historical disease data queues, and obtain gynecological incidence probability prediction results based on gynecological prediction models;

A visual report is generated according to the prediction result of gynecological incidence probability, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

A computer-readable storage medium for storing computer instructions, when the computer instructions are executed by a processor, the following steps are completed:

Obtain gynecological-related disease variables from gynecological cases, conduct correlation analysis with gynecological events, and screen out risk factors; build a gynecological risk prediction model based on the screened risk factors;

Receive disease risk prediction requests, retrieve relevant historical disease data queues, and obtain gynecological incidence probability prediction results based on gynecological prediction models;

A visual report is generated according to the prediction result of gynecological incidence probability, the obtained user's physiological index information, the risk factors related to the user and the contribution rate of the risk factors.

Those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by the computing device, so that they can be stored in a storage device. The device is executed by a computing device, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps in them are fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Although the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, they do not limit the scope of protection of the present invention. Those skilled in the art should understand that on the basis of the technical solutions of the present invention, those skilled in the art do not need to pay creative work. Various modifications or variations that can be made are still within the protection scope of the present invention.

Claims (10)

1. A system for visualizing risk prediction of a gynecological tumor disease, comprising:

the risk prediction model building module is used for obtaining gynecological relevant disease variables in gynecological cases, carrying out correlation analysis on the gynecological relevant disease variables and gynecological events, and screening to obtain risk factors; constructing a gynecological risk prediction model based on the screened risk factors;

the gynecological probability prediction module receives the disease risk prediction request, calls a related historical disease data queue, and obtains a gynecological disease probability prediction result based on a gynecological prediction model;

and the health report generation module is used for generating a visual report according to the gynecological morbidity prediction result, the acquired physiological index information of the user, the risk factors related to the user and the contribution rate of the risk factors.

2. The system of claim 1, wherein the risk prediction visualization system for gynecological tumor diseases,

the gynecological tumor diseases comprise: endometrial, breast, cervical and ovarian cancer.

3. The system of claim 1, wherein the risk prediction visualization system for gynecological tumor diseases,

the risk prediction model building module further comprises:

performing single factor analysis based on the screened risk factors, and selecting independent prediction factors of gynecological tumor diseases by a step-by-step screening method to establish a multi-factor proportional risk model;

and inputting the risk factors into a multi-factor proportional risk model, and establishing a gynecological tumor disease prediction model.

4. The system for visualizing risk prediction of gynecological tumor diseases according to claim 1, wherein the calculation method of the gynecological incidence probability prediction result comprises:

and for each risk factor variable in the prediction model, if the disease corresponding to the risk factor is suffered, assigning the value of the risk factor variable to be 1, otherwise, assigning the value of the risk factor variable to be 0, and calculating the gynecological morbidity probability.

5. The system for visualizing risk prediction of gynecological tumor diseases according to claim 1, wherein the calculation method of the contribution rate of risk factors comprises:

respectively assigning the risk factors to be 0 and calculating the gynecological disease incidence probability to obtain the disease incidence probability without the risk factors; and (4) subtracting the risk probability with the incidence probability obtained by the gynecological probability prediction module to obtain the contribution rate of each risk factor to the gynecological event.

6. The system of claim 1, wherein the acquiring of gynecological-related disease variables in gynecological cases comprises:

searching the gynecological disease name from the disease big data queue, and auditing the gynecological disease name;

according to the gynecological related disease name, matching the identification number, the sex and the regional data from the disease big data queue to obtain a gynecological tumor disease queue;

the received cases are included in the standard, and gynecological cases are obtained from the gynecological tumor disease queue.

7. The system of claim 6, wherein the risk prediction visualization system for gynecological tumor diseases,

the disease big data queue searches a data table containing fields in a database system according to preset fields related to diseases; and based on the searched data table, extracting the identification number and the fields related to the diseases to generate a disease big data queue.

8. The system of claim 6, wherein the risk prediction visualization system for gynecological tumor diseases,

disease data normalization on a disease big data cohort, the disease data normalization comprising:

screening a sample data set from the disease big data queue, comparing the disease name in the sample data with the disease name in the disease classification standard, and standardizing the disease name in the sample data;

for the data which is not standardized in the disease big data queue, comparing the disease name with the original disease name in the sample data, and for the successfully compared data, writing the corresponding standardized disease name completion part in the sample data into the standardized field;

and for the data which is not standardized and remains in the disease big data queue, comparing the disease codes with the codes in the disease classification standard, and writing the disease names corresponding to the codes in the disease classification standard into the standardized fields for the data with successful code comparison.

9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the steps of:

acquiring gynecological related disease variables in gynecological cases, carrying out correlation analysis on the gynecological related disease variables and gynecological affected events, and screening to obtain risk factors; constructing a gynecological risk prediction model based on the screened risk factors;

receiving a disease risk prediction request, calling a related historical disease data queue, and obtaining a gynecological disease probability prediction result based on a gynecological prediction model;

and generating a visual report according to the gynecological morbidity prediction result, the acquired physiological index information of the user, the risk factors related to the user and the contribution rate of the risk factors.

10. A computer readable storage medium storing computer instructions that, when executed by a processor, perform the steps of:

acquiring gynecological related disease variables in gynecological cases, carrying out correlation analysis on the gynecological related disease variables and gynecological affected events, and screening to obtain risk factors; constructing a gynecological risk prediction model based on the screened risk factors;

receiving a disease risk prediction request, calling a related historical disease data queue, and obtaining a gynecological disease probability prediction result based on a gynecological prediction model;

and generating a visual report according to the gynecological morbidity prediction result, the acquired physiological index information of the user, the risk factors related to the user and the contribution rate of the risk factors.

Images