Prediction system and method for gestational hypertension risk

Abstract

The invention provides a prediction system and method for gestational hypertension risk, and belongs to the technical field of gynaecology and obstetrics. According to the system, a data list generation module is used for generating a pregnant woman personal data list; the scoring module is configured to be used for processing and analyzing a pregnant woman personal data list, matching and contrasting each item of data in the pregnant woman personal data list with items in a preset judgment list, identifying matched data, scoring according to a corresponding preset rating standard to obtain main element scores, and sending the main element scores to the pregnant woman personal data list; summarizing the main element scores corresponding to the data to obtain a total score result; and the judgment module is configured to compare the total scoring result with a preset threshold value and judge the risk level of the hypertension risk in the gestation period of the pregnant woman. According to the method, personalized comprehensive risk assessment can be provided, the limitation of a traditional method is overcome, a doctor can formulate corresponding prevention and intervention measures according to specific conditions, and therefore the intervention effectiveness is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of obstetrics and gynecology, and in particular relates to a system and method for predicting the risk of hypertension during pregnancy. Background Art

[0002] Gestational hypertension is a common disease during pregnancy, usually occurring after 20 weeks of pregnancy, and its main manifestations are systolic blood pressure ≥140 mmHg or diastolic blood pressure ≥90 mmHg.

[0003] The cause of this disease has not yet been fully elucidated, but it is closely related to the mother's vascular function, the development of the placenta, and physiological changes during pregnancy. Hypertension during pregnancy may lead to a series of serious complications, including placental abruption, fetal growth restriction, premature birth, and even threaten the mother's life. For pregnant women and fetuses, the impact of hypertension during pregnancy is not only reflected in the short term, but the long-term health consequences cannot be ignored, such as an increased risk of maternal cardiovascular disease.

[0004] In order to reduce the incidence of gestational hypertension, some preventive measures are currently taken clinically.

[0005] For example, pregnant women should measure their blood pressure regularly during prenatal checkups to detect abnormalities in a timely manner. For those pregnant women with high-risk factors, such as previous gestational hypertension, obesity, or family history, clinical monitoring and intervention will be carried out more closely. In these high-risk groups, the use of low-dose aspirin has been shown to effectively reduce the risk of gestational hypertension, and it is usually recommended to start taking it in early pregnancy.

[0006] Although some studies are exploring biomarkers associated with hypertension in pregnancy, such as specific proteins and hormone levels in the blood, these studies have not yet been widely used clinically.

[0007] Currently, doctors mostly rely on traditional risk assessment and symptom monitoring, lacking a comprehensive and systematic means to predict which pregnant women may develop gestational hypertension. This makes some pregnant women suddenly develop hypertension in the later stage without being recognized.

[0008] At the same time, individual differences in gestational hypertension also increase the complexity of prediction. Each pregnant woman may have different physical conditions, genetic backgrounds, and lifestyles. This limitation prevents many potentially high-risk pregnant women from receiving timely prevention and intervention, leading to the occurrence of the disease. This not only increases the risk to maternal and child health, but also easily leads to missing the best time for intervention.

[0009] In summary, how to provide a system and method that can predict the risk of gestational hypertension is a technical problem that urgently needs to be solved. Summary of the invention

[0010] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a system and method for predicting the risk of hypertension during pregnancy. By integrating the collected multi-dimensional data to generate a personal data list of the pregnant woman, and comparing and analyzing it with the preset judgment list, a personalized comprehensive risk assessment can be provided.

[0011] The present invention provides a prediction system for the risk of hypertension during pregnancy, comprising: The data list generation module is configured to collect physiological index data, family medical history data, personal medical history data, life habit data and pregnancy history data of the pregnant woman, and to collect the collected data to generate a corresponding personal data list of the pregnant woman; The scoring module is configured to process and analyze the personal data list of the pregnant woman, match and compare each data item therein with the items in the preset judgment list, and identify the matching data, wherein the judgment list includes risk factors related to hypertension and judgment criteria related to the risk factors; score each matching data item according to the corresponding preset rating criteria to obtain the main element score, wherein the preset rating criteria are set according to the degree of influence of each risk factor on the risk of hypertension complicating pregnancy, and the main element scores corresponding to each data item are summarized to obtain the total score result; The determination module is configured to compare the total score result with a preset threshold value to determine the risk level of the pregnant woman's gestational hypertension risk.

[0012] Furthermore, the physiological index data include age, height, weight, body mass index, body temperature, blood pressure level, resting heart rate, blood sugar level, renal function index, blood index, edema, antiphospholipid antibodies, basal metabolic rate, and the body mass index is calculated based on weight and height; The basal metabolic rate is calculated based on age, weight, height and collected body composition data.

[0013] Further, the collecting of the family medical history data includes searching and identifying the identity information of at least one patient or accompanying person who is related to the pregnant woman by blood in the medical big data system, and establishing a list of persons related to the pregnant woman, wherein the medical big data system stores the identity information of persons related to the pregnant woman by blood and the personal historical medical record data corresponding to each person; According to the identity information of each person on the list of persons related to the pregnant woman, the personal historical medical record data corresponding to the identity information is extracted respectively, and the personal historical medical record data of the persons related are collected to generate family medical history data related to the pregnant woman.

[0014] Furthermore, the collecting of the living habit data of pregnant women includes collecting the data through at least one of face-to-face interviews, questionnaire surveys, mobile terminal tracking and monitoring, wearable device monitoring, and home environment testing.

[0015] Furthermore, the method further includes collecting personal emotional data of the pregnant woman, including at least one of the following methods: Based on the aforementioned data on the living habits of pregnant women, whether the living habits of pregnant women are good or not is determined, and based on the determination result, the emotional state of the pregnant women is scored; and / or, extracting communication data from the pregnant woman's living habit data, determining the pregnant woman's personal emotions based on the communication data, and scoring the pregnant woman's emotional state, wherein the communication data includes at least one of text data and image data; Use sentiment rating as a secondary factor rating.

[0016] Furthermore, the main symptoms are extracted from the collected personal data of pregnant women, and the concurrent symptoms related to the main symptoms are obtained; the personal data of pregnant women related to the concurrent symptoms are obtained, the severity of the concurrent disease is determined and scored as the secondary factor score.

[0017] Furthermore, different weights are assigned to the aforementioned sub-factor scores and the aforementioned main factor scores, and weighted operations are performed to obtain a total score result.

[0018] Further, based on the aforementioned determination results, a corresponding prevention plan is generated; And, collecting data information of pregnant women-related parties, setting pregnant women-related parties as group members of a pregnant women information exchange group, wherein the pregnant women-related parties at least include pregnant women, medical staff related to the pregnant women, and pregnant women data parties; Output the prevention plan in the communication group, and extract the personal data in the pregnant woman's personal data list corresponding to the aforementioned main factor score, import it into the communication group, use the data name corresponding to the personal data as the pregnant woman's data party, and output the data in the group interaction interface of the communication group.

[0019] Furthermore, it also includes tracking the changing trend of the main factor scores, and for the main factor scores showing an upward trend, extracting the corresponding personal data of the pregnant woman and importing it into the communication group, wherein when outputting a message in the group interaction interface of the communication group, adjusting the output form of the message according to the main factor scores; And / or, collect the message sent by the medical staff, match the message with each data in the pregnant woman's personal data list, identify the matching data; extract the content of the message to update the matching data.

[0020] The present invention provides a method for predicting the risk of hypertension during pregnancy, comprising the following steps: Collect the pregnant woman's physiological index data, family medical history data, personal medical history data, living habits data and pregnancy history data, and combine the collected data to generate a corresponding list of the pregnant woman's personal data; Processing and analyzing the pregnant woman's personal data list, matching and comparing each item of data therein with items in a preset determination list, and identifying matching data, wherein the determination list includes risk factors associated with hypertension and determination criteria associated with the risk factors; Each matching data item is scored according to its corresponding preset rating standard to obtain the main factor score. The preset rating standard is set according to the degree of influence of each risk factor on the risk of gestational hypertension, and the main factor scores corresponding to each data item are summarized to obtain the total score result; The total score result is compared with the pre-set threshold to determine the risk level of gestational hypertension in pregnant women.

[0021] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art, as an example: It supports diversified and multi-dimensional collection methods to ensure the comprehensiveness and reliability of the collection results. It integrates multi-dimensional data such as pregnant women's physiological indicators, family medical history, living habits, emotional state and personal medical history. By comparing and analyzing the collected data with the preset judgment list, it provides a comprehensive evaluation system, improves the accuracy of predicting the risk of gestational hypertension, and analyzes the personal data of each pregnant woman to provide personalized risk assessment. It overcomes the limitations of traditional methods and enables doctors to formulate corresponding prevention and intervention measures according to specific circumstances, thereby improving the effectiveness of intervention.

[0022] A friendly interactive user interface is used, and pregnant women's data are regarded as group members. Information corresponding to each data party is output, allowing pregnant women and medical staff to easily access and understand relevant data, which is conducive to the transparency, updating and exchange of information, avoiding information lag, untimely and errors in communication, and is conducive to improving the effectiveness and timeliness of intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a module structure diagram of the system for predicting the risk of hypertension during pregnancy provided by the present invention.

[0024] Figure 2 This is a flow chart of the steps of the method for predicting the risk of hypertension during pregnancy provided by the present invention. DETAILED DESCRIPTION

[0025] The technical solution disclosed in the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated, and they can be combined with each other to achieve better technical effects.

[0026] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0027]

[0028] It also includes collecting body composition data and obtaining a basal metabolic rate as one of the physiological indicator data, wherein the basal metabolic rate is calculated based on age, weight, height, and body composition.

[0029] The above physiological index data can be obtained by conducting on-site testing of relevant items in the hospital to obtain the latest physiological index data, or by retrieving historical physiological index data.

[0030] By comparing historical physiological indicator data with the latest physiological indicator data, the changing trend of the patient's physiological condition can be obtained, which can also be used as a reference factor for subsequent prediction of gestational hypertension.

[0031] The family medical history data includes the identity information of at least one patient or accompanying person who is related to the pregnant woman by blood, which is searched and identified in the medical big data system, wherein the medical big data system can store the identity information of the patients, the personal historical medical record data corresponding to each patient, and the identity information of the accompanying person.

[0032] For patients, the identity information here usually includes name, date of birth, gender, name of emergency contact, and relationship between the emergency contact and the patient. The emergency contact here may be a family member or friend of the patient, and the friend is not counted in the family medical history data.

[0033] For accompanying persons, the identity information here usually includes name and relationship with the patient.

[0034] Specifically, when the pregnant woman herself is the patient, the pregnant woman’s family members can be identified from the identity information of the emergency contact or the accompanying person.

[0035] In addition, pregnant women themselves may also serve as accompanying persons, accompanying their family members or friends to the doctor. Then, when extracting the pregnant woman as the accompanying person, the identity information of the patient is identified to obtain the relevant information of the pregnant woman's family members.

[0036] Based on the relationship between the accompanying person and the patient, as well as the relationship between the emergency contact and the patient, the family members of the pregnant woman are extracted and identified, and a list of people related to the pregnant woman is established.

[0037] According to the identity information of each person in the list of persons related to the pregnant woman, the personal medical record data corresponding to the identity information is extracted respectively. The personal medical record data of each person is collected to generate the family medical history data related to the pregnant woman.

[0038] Personal medical record data mainly refers to all past medical records, including but not limited to previous illnesses, surgical history, allergy history, family medical history, chief complaints, diagnoses, various laboratory tests and imaging examination records.

[0039] Pregnancy history data are usually extracted from personal medical records, mainly including the medical records of pregnant women in the past when they were hospitalized for delivery until they were discharged after delivery, including the time of each pregnancy, delivery method and complications. The number of pregnancies was obtained from the number of medical records.

[0040] The collecting of the living habit data of pregnant women includes collecting the data through at least one of face-to-face interviews, questionnaire surveys, mobile terminal tracking and monitoring, wearable device monitoring, and home environment testing.

[0041] Among them, mobile terminal tracking and monitoring mainly tracks the daily life of pregnant women through relevant applications or applets, such as diet record applications, exercise tracking applications, log records, etc.

[0042] Wearable device monitoring mainly involves monitoring heart rate, blood pressure, number of steps, and sleep quality through smart watches, fitness trackers, smart bracelets, and other devices.

[0043] Home environment monitoring is mainly carried out through electronic devices in the home, such as cameras, weight scales, smart home devices that can detect temperature and humidity, air quality, light and noise, etc., to obtain the living habit data of pregnant women in the home environment.

[0044] The above-collected data can be processed together to generate a corresponding list of personal data of pregnant women.

[0045] The processing process includes cleaning the collected data, removing invalid or duplicate data, ensuring data accuracy, and integrating data from different sources into a personal data list to ensure data consistency and integrity.

[0046] You can choose a relational database (such as MySQL) or a non-relational database (such as MongoDB) to store the personal data list of pregnant women, which supports efficient data query and management. Take encryption, access control and other measures to restrict access rights and protect the personal privacy of pregnant women.

[0047] The personal data list of the pregnant woman is processed and analyzed, and each data item is matched and compared with the items in the preset judgment list to identify the matching data. The judgment list includes risk factors related to hypertension and judgment criteria related to the risk factors.

[0048] Taking the physiological index data of pregnant women as an example, part of the corresponding judgment list is as follows:

[0049] Taking the physiological index data of a pregnant woman as an example, the data related to the physiological indexes in the personal data list of the pregnant woman are as follows:

[0050] After matching and comparing with the judgment list, the main factor scores obtained are as follows:

[0051] Other family medical history data, personal medical history data, lifestyle data, and pregnancy history data in the pregnant woman's personal data list are scored in the same way.

[0052]

[0053] S m Refers to the main factor score obtained for each data in the personal data list.

[0054] What is special is that the processing of lifestyle data includes judging whether the living habits of pregnant women are good.

[0055] For each type of lifestyle data collected, select different judgment criteria from the judgment list.

[0056] Specifically, as an example and not a limitation, the following aspects are used for judgment: Eating habits: amount of fruits and vegetables consumed daily; amount of water consumed daily; frequency of high-sugar and high-fat food intake; actual number and regularity of meals.

[0057] Exercise habits: frequency and duration of weekly exercise, number of steps per day or exercise intensity (e.g., light, moderate, high).

[0058] Sleep quality: average sleep duration per night. Sleep regularity (e.g., whether bedtime and wake-up times are consistent).

[0059] Mental health: Self-reported emotional state (e.g., levels of anxiety and depression). Perceived level of social support (e.g., frequency of contact with family and friends).

[0060] Entertainment methods: specific types and quantity of methods, duration and frequency.

[0061] Taking eating habits as an example, the corresponding data content in the living habits data of pregnant women is extracted, such as from the collected image data, health tracking applications, and instant messaging data on the pregnant women’s mobile phones, to find content related to fruit and vegetable intake, and determine the amount of fruits and vegetables consumed by pregnant women every day.

[0062] For example, a pregnant woman should consume 6 servings of fruits and vegetables per day.

[0063] The corresponding judgment criteria are: 10 points for consuming more than 5 servings of fruits and vegetables per day, 5 points for 3-4 servings, and 0 points for less than 3 servings.

[0064] Then the pregnant woman's score for the amount of fruits and vegetables she consumes daily is 10. In the same way, she is scored for eating habits, exercise habits, sleep quality, mental health and entertainment methods.

[0065] Add up the scores for each item to get the total score. For example: Diet score + exercise score + sleep score + mental health score + entertainment score = total score

[0066] The judgment is made based on the total score and a scoring standard is established: Good: The total score is above 80 points, and the living habits are good. The corresponding main factor score in the judgment list is 0 points.

[0067] Moderate: Total score is 60-79 points, some bad habits exist and need to be improved, and the corresponding main factor score in the judgment list is 1 point.

[0068] Poor: Total score below 60 points, poor living habits, need for comprehensive improvement, the corresponding main factor score in the judgment list is 2 points.

[0069] Furthermore, it also includes collecting personal emotional data of pregnant women, including at least one of the following methods: judging whether the living habits of pregnant women are good, and scoring the emotional state of pregnant women.

[0070] For example, according to the above scoring criteria, if the total score of living habits is above 80, the emotion is judged to be positive.

[0071] If the total score of lifestyle habits is above 60-79, the emotion is judged to be neutral.

[0072] If the total score of lifestyle habits is below 60, the emotion is judged to be negative.

[0073] And / or, extracting communication data from the pregnant woman's living habit data, determining the pregnant woman's personal emotions based on the communication data, and scoring the pregnant woman's emotional state, wherein the communication data includes at least one of text data and image data.

[0074] Processing text information includes but is not limited to searching and identifying keywords related to emotions, such as "happy" and "sad", as well as parsing the overall content, analyzing the topics and meanings involved, and then identifying the emotions of pregnant women.

[0075] For image data, computer vision technology is used to identify and analyze facial expressions in images and then recognize the emotions of pregnant women.

[0076] For image data, computer vision technology is used to identify and analyze facial expressions in images and then recognize the emotions of pregnant women.

[0077] For emotions, set the score: Positive: +10 points Neutral: 0 points Negative: -10 points

[0078] Of course, you can also combine lifestyle habits with the emotion score to get a comprehensive emotion score. For example, the emotion score of pregnant women is mainly based on the analysis of communication data and adjusted in combination with lifestyle habits: Final emotion score = total emotion score + h*lifestyle score.

[0079] h is a coefficient used to adjust the impact of lifestyle habits on the total score.

[0080] Optionally, another sub-factor score is obtained by: The main symptoms were extracted from the collected personal data of pregnant women, and the complications related to the main symptoms were obtained.

[0081] The main diseases here refer to the previous diseases that the pregnant woman has been diagnosed with, such as diabetes, hypertension, liver disease, heart disease, nervous system diseases, etc.

[0082] Obtaining personal data of pregnant women related to the concurrent conditions refers to the current concurrent conditions of pregnant women related to these pre-existing diseases.

[0083] For example, whether the pregnant woman has hair loss, tooth loss, changes in complexion, weight changes, abnormal fatigue, headaches, vision changes, etc.

[0084] From the above complications, identify all complications related to a previous disease, and infer and analyze the severity of the previous disease based on the number and severity of the complications.

[0085] For example, take diabetes.

[0086]

[0087] The scores for all symptoms were added together to obtain a total score = 18.

[0088] Based on the total score, the severity of diabetes is analyzed as mild, moderate, or severe, and the score corresponding to the rating is obtained.

[0089] All major symptoms were analyzed in the same way to obtain the sub-factor scores corresponding to each major symptom.

[0090] Different weights are assigned to the aforementioned secondary factor scores and the aforementioned main factor scores, and weighted calculations are performed to obtain the total score result.

[0091] Can be designed as:

[0092] Among them, S mtotal It is the total score of the main factors.

[0093] S e It is the emotion sub-factor score.

[0094] S c It is the complication sub-element score.

[0095] k and j are the weight coefficients of the emotion sub-factor score and the complication sub-factor score, respectively.

[0096] The total score is used to compare with the pre-set threshold to determine the risk level of gestational hypertension in pregnant women.

[0097] By way of example and not limitation, a score of 0 means no risk.

[0098] A score of 0-10 means low risk.

[0099] A score of 10-20 means medium risk.

[0100] A score of 20 or above indicates high risk.

[0101] Furthermore, it also includes generating a prevention plan based on the aforementioned determination results.

[0102] You can select the prevention plan corresponding to each data with a score of 0 or above from the preset plan database, and formulate corresponding prevention measures for different risk factors.

[0103] By way of example, this could include: Dietary management: low-salt diet, increased fruit and vegetable intake, limiting high-sugar and high-fat foods, etc.

[0104] Exercise tips: How to increase moderate physical activity.

[0105] Mental Health: Provide psychological counseling and support to help pregnant women relieve stress.

[0106] Program classification: preventive programs are classified and stored, and associated with risk factors in the scoring system.

[0107] These prevention plans are combined into a complete prevention plan for each pregnant woman, covering all potential risk factors that increase the risk of hypertension during pregnancy.

[0108] Prevention programs may also include additional prevention recommendations and medical advice from health care professionals for pregnant women.

[0109] Furthermore, data information of pregnant women-related parties is collected, and the pregnant women-related parties are set as group members of a pregnant women information exchange group. The pregnant women-related parties at least include the pregnant women, medical staff related to the pregnant women, and the pregnant women data party.

[0110] Output the prevention plan in the communication group, and the medical staff can be the sender of the message.

[0111] And, extract the personal data in the pregnant woman's personal data list corresponding to the aforementioned main factor score, import it into the communication group, use the data name corresponding to the personal data as the pregnant woman's data party, and output the data.

[0112] The output method here can select the medical staff side or the pregnant woman data side as the sender of the message.

[0113] The pregnant woman data here refers to the name corresponding to the data with a main factor score of 0 or above in the pregnant woman's personal data list.

[0114] For example, taking the personal medical records of a pregnant woman as an example, her past medical conditions include diabetes, nephritis, and lumbar disc herniation. Then each of diabetes, nephritis, and lumbar disc herniation will be a separate group member, and the member name is the name of the disease.

[0115] Alternatively, physiological indicator data, family medical history data, personal medical history data, lifestyle data and pregnancy history data are taken as five independent group members.

[0116] The personal data in the pregnant woman's personal data list corresponding to the aforementioned main factor score is extracted and imported into the communication group. In the group interaction interface of the communication group, the data name corresponding to the personal data is used as the pregnant woman's data party to output the data.

[0117] As a group member, the pregnant woman data party only sends messages related to herself.

[0118] That is, if diabetes is a group member, the member only sends message content related to diabetes.

[0119] If the physiological indicator data is used as the group member, then the group member only sends the content related to each data included in the physiological indicator data, that is, whether it is blood indicators, weight, age, etc., the group member uses the physiological indicator data as the output data.

[0120] For example, a member with diabetes: My recent blood sugar level is 120 mg / dL, and I am advised to follow a low-sugar diet. Then the types and methods of low-sugar diets are specifically explained.

[0121] Another example is the physiological index data of members: the latest blood pressure of pregnant women is 150 / 90 mmHg. It is recommended to see a doctor as soon as possible to check whether there are risks related to hypertension and follow the doctor's advice for management.

[0122] Furthermore, it also includes tracking the changing trends of the main factor scores.

[0123] First, you can set a tracking period according to your needs, such as a week, a month, or a longer period. During this period, when there is a change in the data in the pregnant woman's personal data list, update and record the new main factor score obtained by the data. Each score will be marked with a timestamp.

[0124] In the subsequent analysis process, the main factor scores of the same data point at different scoring times are compared. Identify the upward or downward trend of the main factor score corresponding to the data. If there are multiple consecutive records, please note that different standards can be set for different tracking time periods. For example, more than three times in a week, more than 15 times in a month, and the latest timestamp score is higher than the score at the earliest timestamp, it means that the main factor score shows an overall upward trend, which may indicate that the risk of gestational hypertension caused by this data is increasing. On the contrary, if the score continues to decrease, it may indicate that the risk is decreasing.

[0125] For the main element scores showing an upward trend, the corresponding personal data of the pregnant women are extracted and imported into the communication group, wherein when outputting messages in the group interaction interface of the communication group, the output form of the messages is adjusted according to the main element scores.

[0126] Specifically, the output form of the message corresponding to different main factor scores is different. For example, in the last tracking period, the system determined that the blood pressure data of the pregnant woman showed an upward trend and obtained a main factor score of 1. When outputting messages in the group interaction interface of the communication group, the member "blood pressure data" is used as the message sender, and then the message "I had an upward trend last week, it is recommended to continue to observe." is sent. In the next tracking period, the blood pressure data of the pregnant woman still showed an upward trend and obtained a main factor score of 2. Then, with the member "blood pressure data" as the message sender, the content of the message sent will be adjusted from the previous content form, "This week's blood pressure data continues to rise, it is recommended to see a doctor as soon as possible and pay attention to a light diet." Generally speaking, the impact of the data on the risk of hypertension during pregnancy is reflected in the form of content.

[0127] In the communication group, the personal messages sent by medical staff as the senders are not necessarily covered by the content recorded in the pregnant woman's personal data list.

[0128] For example, medical staff sent a message saying, "Pregnant women have recently been suffering from severe mouth and tongue ulcers."

[0129] Collect messages sent by medical staff, for example, extract the key words in the message, "mouth sores", and then match and compare them with each data in the pregnant woman's personal data list. It is found that the message matches the oral medical record data in the pregnant woman's personal medical record data. Oral case data includes oral health records, previous oral disease history, and recent oral examination results.

[0130] The message content of "The pregnant woman has recently had severe mouth ulcers" is extracted, converted into a format consistent with the oral medical record data, and updated into the oral medical record data.

[0131] Example update format: Medical record items: Oral health status Update content: Mouth ulcers, severity: relatively severe Record time: the time the message was sent Note: Medical staff provided feedback in the communication group and recommended monitoring and relevant examinations.

[0132] The system can automatically generate a confirmation message to notify the medical staff that the update is complete. For example: "The information 'Pregnant woman recently had severe mouth and tongue ulcers' has been updated to the oral health record, with the status 'Mouth and tongue ulcers, severity: severe'." At the same time, the pregnant woman can also access the updated records to ensure information sharing.

[0133] The present invention also provides a system using the method for predicting the risk of hypertension complicating pregnancy as described in any one of the above, such as Figure 1 As shown, including: The data list generation module is configured to collect physiological index data, family medical history data, personal medical history data, life habit data and pregnancy history data of the pregnant woman, and to collect the collected data to generate a corresponding personal data list of the pregnant woman; The scoring module is configured to process and analyze the personal data list of the pregnant woman, match and compare each data item therein with the items in the preset judgment list, and identify the matching data, wherein the judgment list includes risk factors related to hypertension and judgment criteria related to the risk factors; score each matching data item according to the corresponding preset rating criteria to obtain the main element score, wherein the preset rating criteria are set according to the degree of influence of each risk factor on the risk of hypertension complicating pregnancy, and the main element scores corresponding to each data item are summarized to obtain the total score result; The determination module is configured to compare the total score result with a preset threshold value to determine the risk level of the pregnant woman's gestational hypertension risk.

[0134] In the scope of the intended protection of the present disclosure, terms such as "including" and the like should be interpreted as inclusive or open by default, rather than exclusive or closed, unless they are expressly defined to the contrary. All technical, scientific or other terms have the meanings understood by those skilled in the art unless they are defined to the contrary. Common terms found in dictionaries should not be interpreted too idealistically or too impractically in the context of relevant technical documents, unless the present disclosure expressly defines them as such.

[0135] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0136] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A prediction system for the risk of hypertension during pregnancy, characterized in that: include: The data list generation module is configured to collect physiological index data, family medical history data, personal medical history data, life habit data and pregnancy history data of the pregnant woman, and to collect the collected data to generate a corresponding personal data list of the pregnant woman; The scoring module is configured to process and analyze the personal data list of the pregnant woman, match and compare each data item therein with the items in the preset judgment list, and identify the matching data, wherein the judgment list includes risk factors related to hypertension and judgment criteria related to the risk factors; score each matching data item according to the corresponding preset rating criteria to obtain the main element score, wherein the preset rating criteria are set according to the degree of influence of each risk factor on the risk of hypertension complicating pregnancy, and the main element scores corresponding to each data item are summarized to obtain the total score result; The determination module is configured to compare the total score result with a preset threshold value to determine the risk level of the pregnant woman's gestational hypertension risk.

2. The system for predicting the risk of hypertension during pregnancy according to claim 1, characterized in that: The physiological index data include age, height, weight, body mass index, body temperature, blood pressure level, resting heart rate, blood sugar level, renal function index, blood index, edema, antiphospholipid antibodies, basal metabolic rate, and the body mass index is calculated based on weight and height; The basal metabolic rate is calculated based on age, weight, height and collected body composition data.

3. The system for predicting the risk of hypertension during pregnancy according to claim 2, characterized in that: The collecting of the family medical history data comprises: Searching and identifying the identity information of at least one patient or accompanying person who is related to the pregnant woman by blood in the medical big data system, and establishing a list of persons related to the pregnant woman, wherein the medical big data system stores the identity information of persons related to the pregnant woman by blood and the personal historical medical record data corresponding to each person; According to the identity information of each person on the list of persons related to the pregnant woman, the personal historical medical record data corresponding to the identity information is extracted respectively, and the personal historical medical record data of the persons related are collected to generate family medical history data related to the pregnant woman.

4. The system for predicting the risk of hypertension during pregnancy according to claim 1, characterized in that: The collecting of the living habit data of pregnant women includes collecting the data through at least one of face-to-face interviews, questionnaire surveys, mobile terminal tracking and monitoring, wearable device monitoring, and home environment testing.

5. The system for predicting the risk of hypertension during pregnancy according to claim 1, characterized in that: It also includes collecting personal emotional data of pregnant women, including at least one of the following methods: Based on the aforementioned data on the living habits of pregnant women, whether the living habits of pregnant women are good or not is determined, and based on the determination result, the emotional state of the pregnant women is scored; and / or, extracting communication data from the pregnant woman's living habit data, determining the pregnant woman's personal emotions based on the communication data, and scoring the pregnant woman's emotional state, wherein the communication data includes at least one of text data and image data; Use sentiment rating as a secondary factor rating.

6. The system for predicting the risk of hypertension during pregnancy according to claim 1, characterized in that It also includes: extracting the main symptoms from the collected personal data of pregnant women, and obtaining the complications related to the main symptoms; obtaining the personal data of pregnant women related to the complications, determining the severity of the complications and scoring them as secondary factor scores.

7. The system for predicting the risk of hypertension during pregnancy according to claim 5 or 6, characterized in that: Different weights are assigned to the aforementioned secondary factor scores and the aforementioned main factor scores, and weighted calculations are performed to obtain the total score result.

8. The system for predicting the risk of hypertension during pregnancy according to any one of claims 1 to 7, characterized in that Also includes: Based on the aforementioned determination results, a corresponding prevention plan is generated; And, collecting data information of pregnant women-related parties, setting pregnant women-related parties as group members of a pregnant women information exchange group, wherein the pregnant women-related parties at least include pregnant women, medical staff related to the pregnant women, and pregnant women data parties; Output the prevention plan in the communication group, and extract the personal data in the pregnant woman's personal data list corresponding to the aforementioned main factor score, import it into the communication group, use the data name corresponding to the personal data as the pregnant woman's data party, and output the data in the group interaction interface of the communication group.

9. The system for predicting the risk of hypertension during pregnancy according to claim 8, characterized in that: The method also includes tracking the trend of changes in the main factor scores, and for main factor scores that show an upward trend, extracting the corresponding personal data of pregnant women and importing them into the communication group, wherein when outputting messages in the group interaction interface of the communication group, the output form of the messages is adjusted according to the main factor scores; And / or, collect the message sent by the medical staff, match the message with each data in the pregnant woman's personal data list, identify the matching data; extract the content of the message to update the matching data.

10. A method for predicting the risk of hypertension during pregnancy, characterized in that: The steps include: Collect the pregnant woman's physiological index data, family medical history data, personal medical history data, living habits data and pregnancy history data, and combine the collected data to generate a corresponding list of the pregnant woman's personal data; Processing and analyzing the pregnant woman's personal data list, matching and comparing each item of data therein with items in a preset determination list, and identifying matching data, wherein the determination list includes risk factors associated with hypertension and determination criteria associated with the risk factors; Each matching data item is scored according to its corresponding preset rating standard to obtain the main factor score. The preset rating standard is set according to the degree of influence of each risk factor on the risk of gestational hypertension, and the main factor scores corresponding to each data item are summarized to obtain the total score result; The total score result is compared with the pre-set threshold to determine the risk level of gestational hypertension in pregnant women.

Images