Intelligent diagnosis system and method for thyroid disease

Through the intelligent diagnostic system, logistic regression and big data machine learning algorithms are used to solve the problem that it is difficult for grassroots doctors to accurately diagnose thyroid function abnormalities during pregnancy, and individualized thyroid disease diagnosis and treatment plans are realized, which improves the scientificity and accuracy of risk assessment. sex, reducing the risk of adverse pregnancy outcomes.

CN114822813BActive Publication Date: 2024-12-06NAT HEALTH COMMISSION INST OF SCI & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210382084.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2021-12-03
Filing Date
2022-04-12
Publication Date
2024-12-06
Estimated Expiration
2042-04-12

AI Technical Summary

Technical Problem

It is difficult for clinicians at the grassroots maternal and child health hospitals to perform accurate stratification and precise treatment of thyroid function abnormalities during pregnancy, resulting in a lack of scientificity and accuracy in the identification, risk assessment and disease diagnosis and treatment of high-risk groups.

Method used

Provide an intelligent diagnostic system, including the first to third terminal devices for collecting basic information, thyroid function-related indicators and physical examination data. The server constructs a risk assessment model through logistic regression and big data machine learning algorithms, and calculates relative risk ratios and personality. Integrated intervention plans to achieve individualized identification, risk assessment and intelligent diagnosis of thyroid function abnormalities.

Benefits of technology

Realize real-time online diagnosis and individualized intervention programs for thyroid diseases during pregnancy, provide standard and standardized diagnosis and treatment programs for grassroots maternal and child health care institutions, optimize risk assessment efficacy and accuracy through continuous accumulation of data, and reduce adverse pregnancy outcomes and adverse offspring outcomes. risk.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114822813B_ABST
    Figure CN114822813B_ABST
Patent Text Reader

Abstract

The present invention relates to an intelligent diagnosis system and method for thyroid disease in pregnancy, comprising a first terminal device, a second terminal device, a third terminal device, the detection and monitoring device, and a server, wherein the server can receive data collected by the first terminal device, the second terminal device, the third terminal device, and the detection and monitoring device; the server sends the data to the second terminal device, so that the second terminal device can obtain the risk assessment model and / or the personalized intervention plan. By continuously accumulating real clinical diagnosis and treatment data, the prediction model is updated and iterated, thereby continuously optimizing the risk assessment efficiency and accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the medical field, and in particular to an intelligent diagnosis system method for thyroid diseases. Background Art

[0002] Thyroid dysfunction during pregnancy has been one of the hot research areas in the endocrinology and perinatal medicine fields in the past decade. Thyroid dysfunction during pregnancy not only increases the risk of adverse pregnancy outcomes such as miscarriage, premature birth, and low birth weight, but also affects the neurological and intellectual development of the fetus, and increases the risk of diabetes and thyroid disease in the mother in the long term after delivery. It directly affects the improvement of the overall quality of the national population and has become a major public health issue. Among them, subclinical hypothyroidism (SCH) during pregnancy is an important and common type of thyroid dysfunction during pregnancy. Its impact on women's health runs through the entire pregnancy, delivery, and even postpartum period. It has certain hazards to fetal growth and development, especially neurological and intellectual development.

[0003] Early, timely, standardized, and active intervention and treatment of thyroid diseases during pregnancy are of great significance for reducing adverse fetal outcomes and promoting maternal and infant health. However, the diagnostic capabilities of clinicians in primary maternal and child health care hospitals vary widely, making it difficult to accurately stratify and treat patients with different types of thyroid dysfunction. The identification, risk assessment, risk prediction, and disease diagnosis and treatment of high-risk groups for thyroid diseases during pregnancy and women who are preparing for pregnancy lack accuracy and scientificity.

[0004] Therefore, there is an urgent need to provide a system and method for providing clinical doctors with scientific and standardized clinical intelligent diagnostic services for risk assessment, risk prediction and identification of high-risk groups of thyroid dysfunction during pregnancy for primary maternal and child health care institutions and obstetric clinicians, targeting women of childbearing age or pregnant women who wish to have children. At the same time, the system and method can monitor, follow up and record the thyroid-related clinical detection indicators and disease conditions of high-risk groups during pregnancy and delivery, and provide clinicians with individualized clinical intervention plans, so as to effectively prevent and control thyroid diseases during pregnancy and promote the health of mothers and babies. Summary of the invention

[0005] The present invention is committed to solving the problems of the scientificity, timeliness and accuracy of primary care clinicians' risk assessment of thyroid dysfunction in women of childbearing age with fertility intentions and pregnant women, as well as the identification, diagnosis and risk assessment of high-risk groups, and clinical intervention plans provided by clinicians for high-risk groups, thereby providing an intelligent diagnosis system and method for thyroid disease, which can not only provide standard and individualized diagnosis and treatment plans for thyroid disease in pregnancy to the majority of primary care maternal and child health institutions and obstetricians and gynecologists in real time online, but also can update and iterate the evaluation model by continuously accumulating real clinical diagnosis data, thereby continuously optimizing the efficiency and accuracy of risk assessment.

[0006] In order to achieve the above objectives, one aspect of the present invention provides an intelligent diagnosis system for thyroid diseases, which is used for identification, risk assessment, risk prediction and intelligent diagnosis of people with abnormal thyroid function, and comprises:

[0007] The first terminal device is used to collect basic information of women who are preparing for pregnancy or pregnant women;

[0008] Detection and monitoring equipment, used to collect clinical indicators related to thyroid function in women preparing for pregnancy or pregnant women, and to monitor clinical indicators related to thyroid function and maternal and fetal outcome information after recovery;

[0009] The second terminal device is used to collect diagnostic data of women who are preparing for pregnancy or pregnant women, and collect clinical index tests related to thyroid function and maternal and fetal outcome information after recovery;

[0010] The third terminal device is used to collect physical examination data of women preparing for pregnancy or pregnant women;

[0011] The server is used to store data related to thyroid function, maternal and fetal outcome data, data preprocessing, generation of thyroid function risk assessment models, intelligent diagnosis of thyroid function risk abnormalities, and grading and classifying thyroid function of women preparing for pregnancy or pregnant women;

[0012] The server uses intelligent algorithms of logistic regression and big data machine learning to build a risk assessment model for preset disease endpoint events, calculate relative risk ratios and / or risk probability scores, calculate personalized intervention plans based on a clinical expert knowledge base and association rules, and optimize the risk assessment model and personalized intervention plans based on clinically accumulated diagnostic data and outcome data;

[0013] The first terminal device, the second terminal device, the third terminal device and the detection and monitoring device are respectively connected to the server in a communication manner, so that the server can receive data collected by the first terminal device, the second terminal device, the third terminal device and the detection and monitoring device;

[0014] The server sends the data to the second terminal device so that the second terminal device can obtain the assessment result of the risk assessment model and / or the personalized intervention plan.

[0015] Preferably, the server includes a data communication unit, a data storage unit, and a data processing unit;

[0016] The data communication unit is used to communicate with the first terminal device, the second terminal device, the third terminal device and the detection and monitoring device;

[0017] The data storage unit is used to store clinical expert knowledge base data, association rule data, disease diagnosis database data, and data from the first terminal device, the second terminal device, the third terminal device and / or the detection and monitoring device.

[0018] Furthermore, the data processing unit includes a data preprocessing module, and the data preprocessing module is used to perform data cleaning and format correction on the data of the storage unit.

[0019] Furthermore, the data processing unit also includes a risk assessment module, which is used to construct the risk assessment model according to the thyroid function screening data and clinical examination data, and based on the clinical expert knowledge base and association rules.

[0020] Furthermore, the data processing unit also includes an intelligent diagnosis module, which is used for intelligent diagnosis of abnormal thyroid function risk and calculates a personalized intervention plan based on a clinical expert knowledge base and association rules.

[0021] Furthermore, the data processing unit also includes a population classification module, which is used to grade and classify the thyroid function of women preparing for pregnancy or pregnant women.

[0022] Furthermore, the data processing unit also includes a post-recovery monitoring and maternal-fetal outcome follow-up module, which iteratively upgrades the risk assessment model and the personalized intervention plan based on clinically accumulated diagnostic data and outcome data.

[0023] Preferably, the first terminal device is a device for registering basic information of women preparing for pregnancy or pregnant women, including a registration machine, a registration website, a registration telephone, a mobile terminal App, and a mini-program.

[0024] Preferably, the clinical indicators related to thyroid function include TSH, FT4, and TPOAb.

[0025] Another aspect of the present invention provides an intelligent diagnosis method for thyroid disease, which is used for identification, risk assessment, risk prediction and intelligent diagnosis of people with abnormal thyroid function, and comprises:

[0026] Obtain basic information about women who are planning to have a baby or are pregnant;

[0027] Obtain information on clinical indicators related to thyroid function in women who are preparing for pregnancy or are pregnant, as well as monitor the clinical indicators related to thyroid function and maternal and fetal outcomes after recovery;

[0028] Obtain clinical diagnosis data of women who are planning to become pregnant or who are pregnant, as well as post-treatment thyroid function-related clinical index tests and maternal and fetal outcome data;

[0029] Obtaining physical examination data of women who are planning to become pregnant or pregnant;

[0030] Pre-processing clinical data related to thyroid function of women preparing for pregnancy or pregnant women;

[0031] According to the thyroid function screening data and clinical examination data, and based on the clinical expert knowledge base and association rules, the risk assessment model is constructed, and a personalized intervention plan is calculated;

[0032] To grade and classify thyroid function in women who are trying to become pregnant or who are pregnant;

[0033] Based on the clinically accumulated diagnostic data and outcome data, the risk assessment model and personalized intervention plan are optimized.

[0034] The intelligent diagnosis system and method of thyroid disease of the present invention establishes a full-chain collaborative intervention prevention and control path of pre-pregnancy screening intervention and pregnancy thyroid function monitoring intervention, which can achieve primary prevention of abnormal thyroid function during pregnancy, effectively reduce the risk of adverse pregnancy outcomes and adverse offspring outcomes, and promote maternal and infant health. The present invention can not only provide standard and individualized diagnosis and treatment plans for pregnancy thyroid diseases for the majority of grassroots maternal and child health care institutions and obstetricians and gynecologists in real time online, but also can realize the update and iteration of risk assessment models by continuously accumulating real clinical diagnosis data, thereby continuously optimizing the efficiency and accuracy of risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] This specification describes the complete and instructive disclosure of the present application, including its best mode of implementation, for those skilled in the art. This specification refers to the accompanying drawings, in which:

[0036] Figure 1 A schematic diagram of an intelligent diagnosis system for thyroid disease according to the present invention;

[0037] Figure 2A flow chart of an intelligent diagnosis system and method for thyroid disease according to the present invention;

[0038] Figure 3 This is a management flow chart of an intelligent diagnosis system and method for thyroid disease according to the present invention. DETAILED DESCRIPTION

[0039] Now with reference to the embodiments of the present application in detail, one or more examples of the embodiments of the present application are illustrated in the drawings. Each example is provided to explain the present application, not to limit the present application. In fact, it will be clear to those skilled in the art that various modifications and changes can be made in the present application without departing from the scope or spirit of the present application. For example, the features described or described as a part of an embodiment can be used together with another embodiment to produce another embodiment. Therefore, it is hoped that the present application covers such modifications and changes, which are within the scope of the attached claims and their equivalents. As used in this specification, the terms "first", "second", etc. are used interchangeably to distinguish one component from another component without intending to indicate the position or importance of each component. As used in the specification, unless the context clearly indicates otherwise, the terms "one", "an", "the" and "said" are intended to indicate that there are one or more elements. The terms "include", "include" and "have" are intended to be inclusive and mean that there may be other elements in addition to the listed elements.

[0040] Now referring to the drawings, in which like numerals represent like elements throughout the drawings, the present invention will be further explained below in conjunction with specific embodiments.

[0041] like Figure 1 As shown, the intelligent diagnosis system for thyroid disease of the present invention is used for identification, risk assessment, risk prediction and intelligent diagnosis of thyroid dysfunction in women preparing for pregnancy and women who are pregnant, and includes:

[0042] The first terminal device 101 may include a registration machine, a registration website, a registration phone, a mobile terminal App, a mini-program, or other similar devices or units capable of registering basic information of women preparing for pregnancy or pregnant women. The first terminal device may be used to collect basic information of women preparing for pregnancy or pregnant women, such as name, place of origin, age of preparing for pregnancy, age of conception, whether iodized salt, iodine-containing drugs, use of seafood, history of diabetes, history of hypertension, history of female thyroid disease, history of adverse pregnancy outcomes, whether menstruation is regular, and other indicators that may affect female thyroid function and reproductive health. The first device terminal 101 is capable of data communication with the server 300 to send the collected data to the data storage unit 301 of the server 300.

[0043] The detection and monitoring device 102 can collect clinical indicators related to thyroid function of women preparing for pregnancy or pregnant women, such as height, weight, blood pressure level, blood sugar level, blood creatinine level, hemoglobin level, alanine aminotransferase level, blood biochemistry, smoking, passive smoking, drinking, psychological stress, heart rate, urine routine, Amygdalitis infection, TORCH infection, etc.) and clinical indicators related to thyroid function such as thyroid stimulating hormone (TSH), free thyroid hormone (FT4) and thyroid peroxidase antibody (TPOAb). The detection and monitoring device 102 is also used to monitor clinical indicators related to thyroid function and maternal and child outcome information after recovery, such as monitoring data records of thyroid function indicators of high-risk groups during pregnancy and postpartum (including clinical test data before and after initial screening and clinical treatment, and each follow-up), as well as follow-up data records of pregnancy diseases (abnormal thyroid function during pregnancy, gestational diabetes, and hypertensive diseases during pregnancy), pregnancy outcomes (spontaneous abortion, premature birth, perinatal death, small for gestational age, etc.), and offspring growth and development (0-3 years old neurological and intellectual development scale measurement data, growth and development indicator measurement data). The detection and monitoring device 102 can communicate data with the server 300 to send the collected data to the data storage unit 301 of the server 300.

[0044] The second terminal device 201 records the doctor's clinical diagnosis and can collect diagnostic data of women preparing for pregnancy or pregnant women. The second terminal device 201 can also collect thyroid function-related clinical indicator tests and maternal and child outcome information after recovery; the second terminal device 201 can communicate data with the server 300 to send the collected data to the data storage unit 301 of the server 300, and obtain the risk assessment results given by the risk assessment model and the personalized intervention plan given by the intelligent diagnosis model from the server.

[0045] The third terminal device 202 can communicate data with the server 300 to send the collected data to the data storage unit 301 of the server 300; the third terminal device 202 collects the physical examination data of women preparing for pregnancy or pregnant women, and can be set in a physical examination center or a physical examination service center of each medical institution.

[0046] Server 300, which can be used for data storage, collection of data related to thyroid function of women preparing for pregnancy or pregnant women, data preprocessing, generation of thyroid function risk assessment model, intelligent diagnosis of thyroid function risk abnormality, and grading and classification of thyroid function of women preparing for pregnancy or pregnant women.

[0047] The server 300 includes a data communication unit 303, a data storage unit 301, and a data processing unit. The data communication unit 303 is used to communicate with the first terminal device 101, the second terminal device 201, the third terminal device 202, the detection and monitoring device 102, and other diagnostic and treatment devices 103, so that the server can receive data collected by the first terminal device 101, the second terminal device 201, the third terminal device 202, the detection and monitoring device 102, and other diagnostic and treatment devices 102;

[0048] The server 300 may also send data to the second terminal device 201 at the request of the second terminal device 201, so that the second terminal device 201 can obtain the risk assessment results of the risk assessment model and / or the personalized intervention plan calculated by the intelligent diagnosis model.

[0049] The server 300 uses intelligent algorithms of logistic regression and big data machine learning, such as random forest, decision tree, support vector machine and other artificial intelligence algorithms, to build a risk assessment model for preset disease endpoint events including abnormal thyroid function during pregnancy, complications during pregnancy and adverse pregnancy outcomes, calculate the relative risk ratio and / or risk probability score, and divide the high-risk population, so as to achieve accurate identification, risk assessment and risk monitoring of high-risk groups of abnormal thyroid function during pregnancy for the majority of grassroots clinical obstetricians and gynecologists.

[0050] Based on thyroid disease-related monographs, guidelines for the diagnosis and treatment of thyroid diseases during pregnancy, scientific papers, drug instructions and other literature, combined with the diagnosis and treatment experience of clinical doctors and experts, a knowledge base and association rules are generated, and a personalized intervention plan is calculated based on the clinical expert knowledge base and association rules. Based on the clinically accumulated diagnostic data and outcome data, the risk assessment model and personalized intervention plan are optimized;

[0051] In another embodiment, based on the real clinical diagnosis and treatment data and prospective pregnancy cohort data collected and stored by the system, artificial intelligence algorithm technologies such as logistic regression, lasso regression and big data machine learning methods (such as random forest, decision tree, support vector machine, etc.) are used to construct a risk assessment model with different endpoint events such as abnormal thyroid function during pregnancy, gestational diabetes, miscarriage, premature birth, perinatal death, small for gestational age, and abnormal neurological and intellectual development as outcome variables.

[0052] On the other hand, the Monte-Carlo method was used to simulate and compare the evaluation models constructed by the above methods to screen and optimize the models, and the bootstrap resampling method and 10-fold cross-validation method were used for internal validation, and the corresponding statistics and 95% confidence intervals of each predictor variable were calculated; 80% were used as training samples and 20% as validation samples, and the diagnosis and treatment screening and follow-up data records of the subsequent clinical diagnosis and treatment data were fully utilized as external validation. The discriminant ability of the model was evaluated by comparing the difference in C-statistics (i.e., the area under ROC). C-statistics>0.5 indicate that the model has good predictive discrimination ability, while in the application, it is believed that the predictive ability between 0.5-0.7 is average, the predictive ability between 0.71-0.79 is good, and the predictive ability>0.8 is very good.

[0053] The calibration graph of the model was drawn, and the calibration slope, predicted probability, and actual probability were used to evaluate the calibration ability of the model. The Hosmer-Lemeshow test was used to evaluate the goodness of fit of the model. According to the results of the model goodness of fit evaluation, the optimal model for abnormal thyroid function during pregnancy, adverse pregnancy outcomes, and abnormal offspring development was screened, and different models were optimized and integrated to form a comprehensive risk score for risk grading and classification of risk groups. At the same time, according to the types of independent variables and their weights included in the optimal model, a disease risk prediction index system was constructed to accurately define the key risk factor spectrum for early thyroid function screening of women preparing for pregnancy and pregnant women and clinical examinations before and during pregnancy, so as to improve the screening efficiency and realize individualized intervention and precise prevention and control of the disease.

[0054] The data storage unit 301 is used to store clinical expert knowledge base data, association rule data, disease diagnosis database data, and data from the first terminal device, the second terminal device, the third terminal device and / or the detection and monitoring device.

[0055] The data storage unit 301 is also used to store prospective pregnancy cohort data.

[0056] The data processing unit 302 includes a data preprocessing module 307 , a risk assessment module 306 , an intelligent diagnosis module 305 , and a population classification module 304 .

[0057] The data preprocessing module 307 performs data preprocessing such as data cleaning and format correction on the data of the storage unit.

[0058] The risk assessment module 306 can construct the risk assessment model based on the thyroid function screening data and clinical examination data, and based on the clinical expert knowledge base and association rules, and automatically generate a risk assessment report text for clinical subjects; the intelligent diagnosis module 305 can intelligently generate personalized disease diagnosis and treatment suggestions and treatment plans for clinical doctors to refer to. The diagnosis and treatment suggestions and treatment plans mainly include treatment path information such as diet, medication, follow-up laboratory testing and other plans.

[0059] On the other hand, the intelligent diagnosis module is used for intelligent diagnosis of abnormal thyroid function risk, and calculates a personalized intervention plan based on the clinical expert knowledge base and association rules.

[0060] The population classification module 304 is used to classify the thyroid function of women preparing for pregnancy or pregnant women. For all people determined to be at high risk, the changes in clinical indicators related to thyroid function before, during and after pregnancy are monitored, and the incidence of pregnancy diseases, pregnancy outcomes, and maternal and child outcomes are recorded.

[0061] The data processing unit 302 also includes a recovery monitoring and maternal-fetal outcome follow-up module (not shown in the figure), which iteratively upgrades the risk assessment model and the personalized intervention plan based on the clinically accumulated diagnostic data and outcome data.

[0062] The thyroid function-related clinical indicators may include TSH, FT4, TPOAb, etc. The thyroid function-related clinical indicators may also include one or more of the thyroid function-related clinical detection indicators such as free thyroxine 3, total thyroxine 3 (TT3), total thyroxine 4 (TT4), thyroglobulin antibodies (TGAb), thyroid stimulating hormone receptor antibodies (TRAb), etc., which can be combined together to achieve risk prediction of abnormal thyroid function during pregnancy and adverse pregnancy outcomes and identification of high-risk groups.

[0063] Another aspect of the present invention provides an intelligent diagnosis method for thyroid disease, which is used for identification, risk assessment, risk prediction and intelligent diagnosis of people with abnormal thyroid function, and comprises:

[0064] Obtain basic information about women who are planning to have a baby or are pregnant;

[0065] Obtain information on clinical indicators related to thyroid function in women who are preparing for pregnancy or are pregnant, as well as monitor the clinical indicators related to thyroid function and maternal and fetal outcomes after recovery;

[0066] Obtain clinical diagnosis data of women who are planning to become pregnant or who are pregnant, as well as post-treatment thyroid function-related clinical index tests and maternal and fetal outcome data;

[0067] Obtaining physical examination data of women who are planning to become pregnant or pregnant;

[0068] Pre-processing clinical data related to thyroid function of women preparing for pregnancy or pregnant women;

[0069] According to the thyroid function screening data and clinical examination data, and based on the clinical expert knowledge base and association rules, the risk assessment model is constructed, and a personalized intervention plan is calculated;

[0070] To grade and classify thyroid function in women who are trying to become pregnant or who are pregnant;

[0071] Based on the clinically accumulated diagnostic data and outcome data, the risk assessment model and personalized intervention plan are optimized.

[0072] In one embodiment, Figure 2 As shown, an intelligent diagnosis system and method for thyroid disease, including a clinical data collection module, a perinatal care screening information collection module for pregnant women, and a thyroid function-related indicator detection module; a module for uploading and preprocessing the above-collected data; a knowledge base and association rules are generated based on thyroid disease-related monographs, guidelines for the diagnosis and treatment of thyroid diseases during pregnancy, scientific papers, drug instructions and other literature, combined with the diagnosis and treatment experience of clinical doctors and experts; the disease risk assessment module can be based on real clinical diagnosis and treatment data and prospective pregnancy cohort data, using big data deep learning algorithm technology to build a risk prediction model (or "risk assessment model"); based on the assessment conclusions of the risk assessment module, the risks of the assessed object are graded and classified; the risk assessment package and clinical diagnosis and treatment recommendation production module is used to automatically generate a risk assessment report text for clinical subjects based on the risk assessment results of the assessed object based on the risk assessment model, and intelligently generate targeted disease diagnosis and treatment recommendations and treatment plans. The post-disease monitoring and maternal and child outcome follow-up module is used to record the monitoring data of thyroid function indicators during pregnancy and postpartum in high-risk groups (including the initial screening and clinical test data before and after clinical treatment, and each follow-up), as well as pregnancy diseases (abnormal thyroid function during pregnancy, gestational diabetes, and hypertensive disorders during pregnancy), pregnancy outcomes (spontaneous abortion, premature birth, perinatal death, small for gestational age, etc.), and follow-up data of offspring growth and development (measurement data of the 0-3 years old neuro-intelligence development scale, and measurement data of growth and development indicators).

[0073] The data storage module is used for storing all clinical collection data and monitoring follow-up data, and is used to provide data support for the later verification and continuous iterative upgrade of risk prediction models with different endpoint events such as abnormal thyroid function during pregnancy, gestational diabetes, miscarriage, premature birth, perinatal death, small for gestational age, abnormal neurological and intellectual development as outcome variables.

[0074] Furthermore, we continuously perform iterative operations based on newly accumulated data, update the algorithm model, and establish a disease risk prediction indicator system based on the changes and weights in the risk prediction model, so as to accurately define the key risk factor spectrum for early thyroid function screening of women preparing for pregnancy and pregnant women, as well as clinical examinations before and during pregnancy, improve screening efficiency, and achieve individualized intervention and precise prevention and control of the disease.

[0075] Figure 3 It shows a clinical pathway and management process for thyroid disease screening, intervention and treatment during pregnancy, which starts before pregnancy and runs through pregnancy and postpartum. In this management process, the target population is screened for TSH during pregnancy, and different treatment and management plans are adopted according to the screening results. Preparation for pregnancy is carried out after the thyroid function is normal; strict thyroid function tests are carried out during pregnancy, and treatment and management measures are taken for the subjects according to the status of thyroid function during pregnancy. The thyroid function of subjects with abnormal thyroid function is tested until delivery; the thyroid function of the mother is reviewed after delivery. A full-chain coordinated intervention and prevention and control path of pre-pregnancy screening intervention and pregnancy thyroid function monitoring intervention has been established, which can achieve primary prevention of abnormal thyroid function during pregnancy, effectively reduce the risk of adverse pregnancy outcomes and adverse offspring outcomes, and promote maternal and child health.

[0076] This specification uses examples to disclose the present application, including the best embodiment, and also to enable those skilled in the art to practice the present application, including making and using any device or system and performing any incorporated method. The patentable scope of the present application is defined by the claims, and may include other embodiments that occur to those skilled in the art. If such other embodiments include structural elements that are not different from the literal language of the claims, or if they include equivalent structural elements that are not substantially different from the literal language of the claims, then they are intended to be within the scope of the claims.

Claims

1. An intelligent diagnosis system for thyroid diseases, used for identification, risk assessment, risk prediction and intelligent diagnosis of people with abnormal thyroid function, comprising: The first terminal device is used to collect basic information of women who are preparing for pregnancy or pregnant women; Detection and monitoring equipment, used to collect clinical indicators related to thyroid function in women preparing for pregnancy or pregnant women, and to monitor clinical indicators related to thyroid function and maternal and fetal outcome information after recovery; The second terminal device is used to collect diagnostic data of women who are preparing for pregnancy or pregnant women, and collect clinical index tests related to thyroid function and maternal and fetal outcome information after recovery; The third terminal device is used to collect physical examination data of women preparing for pregnancy or pregnant women; Servers are used to store data related to thyroid function, maternal and fetal outcome data, data preprocessing, generation of thyroid function risk assessment models, intelligent diagnosis of thyroid function risk abnormalities, and grading and classifying thyroid function of women preparing for pregnancy or pregnant women; The server uses intelligent algorithms of logistic regression and big data machine learning to build a risk assessment model for preset disease endpoint events, calculate relative risk ratios and / or risk probability scores, calculate personalized intervention plans based on a clinical expert knowledge base and association rules, and optimize the assessment results of the risk assessment model and personalized intervention plans based on clinically accumulated diagnostic data and outcome data; The first terminal device, the second terminal device, the third terminal device and the detection and monitoring device are respectively connected to the server in a communication manner, so that the server can receive data collected by the first terminal device, the second terminal device, the third terminal device and the detection and monitoring device; The server sends the data to the second terminal device so that the second terminal device can obtain the risk assessment model and / or the personalized intervention plan.

2. The intelligent diagnosis system for thyroid disease according to claim 1, characterized in that: The server includes a data communication unit, a data storage unit, and a data processing unit; The data communication unit is used to communicate with the first terminal device, the second terminal device, the third terminal device and the detection and monitoring device; The data storage unit is used to store clinical expert knowledge base data, association rule data, disease diagnosis database data, and data from the first terminal device, the second terminal device, the third terminal device and / or the detection and monitoring device.

3. The intelligent diagnosis system for thyroid disease according to claim 2, characterized in that: The data processing unit includes a data preprocessing module, and the data preprocessing module is used to perform data cleaning and format correction on the data of the storage unit.

4. The intelligent diagnosis system for thyroid disease according to claim 3, characterized in that: The data processing unit also includes a risk assessment module, which is used to construct the risk assessment model according to the thyroid function screening data and clinical examination data, and based on the clinical expert knowledge base and association rules.

5. The intelligent diagnosis system for thyroid disease according to claim 3, characterized in that: The data processing unit also includes an intelligent diagnosis module, which is used for intelligent diagnosis of abnormal thyroid function risk and calculates a personalized intervention plan based on a clinical expert knowledge base and association rules.

6. The intelligent diagnosis system for thyroid disease according to claim 4, characterized in that: The data processing unit also includes a population classification module, which is used to grade and classify the thyroid function of women preparing for pregnancy or pregnant women.

7. The intelligent diagnosis system for thyroid disease according to claim 4, characterized in that: The data processing unit also includes a post-recovery monitoring and maternal-fetal outcome follow-up module, which iteratively upgrades the risk assessment model and the personalized intervention plan based on clinically accumulated diagnostic data and outcome data.

8. The intelligent diagnosis system for thyroid disease according to claim 1, characterized in that: The first terminal device is a device used to register basic information of women preparing for pregnancy or pregnant women, including registration machines, registration websites, registration telephones, mobile terminal apps, and mini-programs.

9. The intelligent diagnosis system for thyroid disease according to claim 1, characterized in that: The thyroid function-related clinical indicators include TSH, FT4, and TPOAb.

10. An intelligent diagnosis method for thyroid disease, used for identification, risk assessment, risk prediction and intelligent diagnosis of people with abnormal thyroid function, characterized by: Obtain basic information about women who are planning to have a baby or are pregnant; Obtain information on clinical indicators related to thyroid function in women who are preparing for pregnancy or are pregnant, as well as monitor the clinical indicators related to thyroid function and maternal and fetal outcomes after recovery; Obtain clinical diagnosis data of women who are planning to become pregnant or who are pregnant, as well as post-treatment thyroid function-related clinical index tests and maternal and fetal outcome data; Obtaining physical examination data of women who are planning to become pregnant or pregnant; Pre-processing clinical data related to thyroid function of women preparing for pregnancy or pregnant women; Adopt intelligent algorithms of logistic regression and big data machine learning to build a risk assessment model for preset disease endpoint events, calculate relative risk ratios and / or risk probability scores, calculate personalized intervention plans based on the clinical expert knowledge base and association rules, and optimize the assessment results of the risk assessment model and personalized intervention plans based on the clinically accumulated diagnostic data and outcome data; To grade and classify thyroid function in women who are trying to become pregnant or who are pregnant; Based on the clinically accumulated diagnostic data and outcome data, the risk assessment model and personalized intervention plan are optimized.

Citation Information

Patent Citations

  • Telemedicine system of thyroid diseases.

    CN107506596A

  • System and method for predicting gestational diabetes mellitus

    CN110808097A