Puerpera pre-hospital health information management and evaluation system based on Internet hospital

Abstract

The invention relates to the technical field of electronic medical treatment, in particular to a puerpera pre-hospital health information management and evaluation system based on an internet hospital, and the system comprises the steps: employing an information system to automatically push a pre-hospital nursing evaluation table based on the internet hospital according to a hospital admission sheet issued by a doctor, and enabling a patient to fill in the evaluation table online; automatically matching corresponding hospital admission preparation data according to the pre-hospital nursing evaluation sheet filled by the patient; the information management system provided by the invention has innovativeness and practicability, and brings an all-around change for obstetrical service. According to the invention, one-stop information integration is realized through an innovative means, information of doctor seeing departments, information of certificates, departments, articles and the like involved in hospital admission preparation and knowledge of the whole course of pregnancy and delivery are integrated together, and the information acquisition efficiency is greatly improved. Meanwhile, personalized features are highlighted on the service subdivision level, and specific knowledge and science popularization are provided for all stages of pregnancy and delivery from article preparation distinguishing according to different conditions of the pregnant women, so that the actual requirements of different pregnant women are met.

Description

Technical Field

[0001] The present invention relates to the field of electronic medical technology, and in particular to a maternal pre-hospital health information management and evaluation system based on an Internet hospital. Background Art

[0002] With the development of the times, from "Internet + medical care" to "Internet hospital", medical services relying on information technology have opened a new chapter and entered a new stage. With the continuous standardization and improvement of Internet + medical services, more and more application scenarios such as intelligent medical guidance, pre-consultation, and physical sign monitoring can be integrated into medical intelligence services.

[0003] However, the existing technology has the following disadvantages when used: patients suffer from anxiety due to their unfamiliarity with the hospitalization process and lack of psychological preparation; the lack of information on pre-hospitalization nursing assessments leads to delayed screening of high-risk patients and lack of risk prevention and control; the traditional standardized education system leads to inefficient and lack of targeted repetitive admission guidance.

[0004] In summary, the development of a maternal pre-hospital health information management and evaluation system based on an Internet hospital is still a key issue that needs to be urgently addressed in the field of electronic medical technology. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the prior art, such as the anxiety of patients caused by their unfamiliarity with the hospitalization process and insufficient psychological preparation; the information gap in pre-hospitalization nursing assessment leads to delayed screening of high-risk patients and lack of risk prevention and control; the traditional standardized education system leads to inefficient and lack of targeted repetitive admission guidance. The present invention provides a pre-hospital health information management and evaluation system for parturients based on an Internet hospital.

[0006] To achieve the above object, the present invention provides the following technical solutions: The present invention provides a maternal pre-hospital health information management and evaluation system based on an Internet hospital, which includes: The information system is based on the Internet hospital. According to the admission form issued by the doctor, the information system automatically pushes the pre-hospital care assessment form, and the patient fills in the assessment form online; The admission management module automatically matches the corresponding admission preparation information based on the pre-hospital care assessment form filled out by the patient; The intelligent push module intelligently pushes personalized nursing information based on the nurse's nursing assessment record, the patient's surgery date and admission preparation information; the admission management module includes an intelligent data analysis module: analyzes the patient's filled-in information, generates charts, and identifies potential nursing risks R;

[0007] Where: Si is the i-th basic risk indicator; W i is the weight coefficient; is the coefficient of variation of the jth dynamic monitoring index; Tj is the clinical threshold boundary value, and the fuzzy membership function is used to quantify the degree of deviation; is the time decay coefficient of the jth dynamic monitoring indicator, which is used to strengthen the impact of recent data: ; t is the time interval between the current time point and the data collection time point; τ is the time scale parameter of exponential decay; C is the behavioral compliance based on the questionnaire submission rate and the execution of medical orders; θ is the clinical experience constant, which is 0.2-0.4; k is the sensitivity parameter. By controlling k so that C is greater than 80%, the risk mitigation effect is significant, that is, Small enough; Ep: step function of the pth critical value event, Ep takes the value of 0.20.2 for a single warning, 0.7 for a continuous abnormality, and 1.2 for multiple systems concurrently.

[0008] The calculation formula of C is:

[0009] in, It indicates the ratio of the actual number of questionnaire submissions to the number of questionnaire submissions that should have been submitted; It indicates the ratio of the execution time of the doctor's order to the planned time; L active It indicates the frequency of patients actively logging into the system, and α, β, and γ are weight coefficients.

[0010] The W i is the clinical weight coefficient calibrated by Logistic regression.

[0011] The health education module intelligently pushes personalized health education information based on the patient's nursing information.

[0012] Beneficial Effects Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects: When the present invention is in use, it is advantageous to connect with the hospital inpatient system through the information system. The inpatient system automatically associates the patient's pre-admission information, improves the efficiency of admission processing, optimizes the patient's medical process, and utilizes the intelligent data analysis module to analyze the patient's filled-in information, generate charts, identify potential nursing risks, and formulate personalized nursing plans. Relevant health education can be completed online, which is beneficial to reduce the workload of nurses and improve work efficiency. In addition, the complete and comprehensive evaluation information also provides a large amount of data reference for the subsequent development of specialties.

[0013] The present invention integrates static questionnaire data, dynamic monitoring flow data, and behavioral verification data through a nonlinear coupling model, and realizes dynamic attenuation memory of risk status through a time decay function; at that time, the weight redistribution algorithm is automatically triggered to reduce the interference of secondary indicators and output a visualized risk contribution map for each risk component, which meets the medical AI interpretability standards.

[0014] The information management system of the present invention is highly innovative and practical, and has brought about an all-round change in obstetric services. The present invention uses innovative means to achieve one-stop information integration, which brings together information about the treatment department, information about the certificates, departments, items, etc. involved in hospital preparation, and knowledge about the entire pregnancy and childbirth process, greatly improving the efficiency of information acquisition. At the same time, the personalized characteristics are highlighted at the service segmentation level, from differentiating the preparation of items according to the different situations of pregnant women to providing exclusive knowledge popularization for each stage of pregnancy and childbirth, meeting the actual needs of different pregnant women.

[0015] What is particularly outstanding is that the system can be deeply linked with various assessment forms. Based on the assessment results, health education content is automatically and accurately pushed to pregnant women. For example, if the risk of gestational hypertension is assessed before delivery, the corresponding prevention and treatment knowledge will be pushed; for example, once a pregnant woman undergoes a cesarean section, the system will trigger the push of wound care, pain relief, recovery training and nutritional supplement knowledge. This not only realizes precise health intervention and meets personalized needs, but also transforms traditional passive health education into an active push mode, changing "people looking for information" to "information looking for people", which not only reduces the workload of medical staff, but also ensures that pregnant women and their families obtain key knowledge in a timely manner and enhance their self-management capabilities. In terms of decision-making and care support, the management system provides surgical risk decision-making support to help pregnant women and their families make scientific choices. In terms of care, it focuses on postpartum maternal and child care, provides professional guidance for mothers and their families, fills the gap in information support in traditional health education, and improves the depth of obstetric service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system diagram of a nursing pre-hospital assessment system based on an Internet hospital of the present invention; Figure 2 This is an extended flow chart of the maternal pre-hospital health information management and evaluation system based on the Internet hospital of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] Dynamic monitoring indicators include: Physiological indicators: blood pressure fluctuations, fetal heart rate, blood oxygen saturation, and uterine contraction frequency.

[0020] Behavioral indicators: patients’ response speed and dropout rate when filling out the online evaluation form.

[0021] Basic risk indicators, including: Demographic characteristics: age (e.g., women aged ≥35 years are considered older mothers), BMI, and pregnancy and delivery history.

[0022] Medical history and test results: gestational diabetes, preeclampsia, hemoglobin level.

[0023] Behavioral characteristics: exercise habits, medication compliance, and psychological assessment scores.

[0024] Critical events include: Single indicator critical values: systolic blood pressure ≥160 mmHg, fetal heart rate <110 beats / min, blood oxygen saturation <90%.

[0025] Composite critical value: “History of preeclampsia + sudden headache + blurred vision” → risk of eclampsia.

[0026] “Premature rupture of membranes + fever ≥38°C” → risk of chorioamnionitis.

[0027] The present invention is further described in detail below in conjunction with the accompanying drawings: Embodiment 1: like Figure 1-2 As shown, the present invention provides a maternal pre-hospital health information management and evaluation system based on an Internet hospital, including: S1, based on the Internet hospital, according to the admission form issued by the doctor, the information system automatically pushes the pre-hospital nursing evaluation form, and the patient fills in the evaluation form online; Further, in step S1, based on the Internet hospital's admission form issued by the doctor, the information system automatically pushes the pre-hospital care evaluation form, and the patient fills in the evaluation form online: The doctor issues an admission form for the patient in the Internet hospital system, records the patient's basic information, including name, gender, age, hospitalization department and diagnosis, and automatically pushes the corresponding pre-hospital nursing assessment form to the patient's Internet hospital account. The pre-hospital nursing assessment form includes basic health conditions, daily living ability and psychological state. The push channels include: Internet hospital APP, WeChat public account and SMS notification. Basic information: ,in It is basic information. It's your name. It's gender, It's age. It's an inpatient department. is the reason for hospitalization, classification model: ,in For the predicted hospital admission department, is the weight matrix of the classification model, is the bias term, is the Softmax activation function.

[0028] Further, in step S1, based on the Internet hospital's admission form issued by the doctor, the information system automatically pushes the pre-hospital care evaluation form, and the patient fills in the evaluation form online: With the automatic reminder function, when the patient fails to fill out the assessment form within one day, the weight distribution mechanism is used to calculate the priority of the push channel, and any one of the three methods, APP push, SMS and voice call, is selected to remind the patient to fill out the form. The completed pre-hospital assessment form is directly imported into the Jingyi nursing document. According to the nursing level requirements, a nursing plan is formulated. The assessment form submitted by the patient is analyzed and reviewed through the electronic medical record database, and the patient's nursing demand level is classified, and the nursing plan is recorded. Automatic reminder function: ,in is the reminder intensity, Respectively represent the triggering times of APP push, SMS reminder and voice call, is the weight coefficient, and the weight distribution mechanism is: ,in It is the pre-hospital care assessment form. It's basic health condition. It is the ability of daily life. It's a psychological state. The final selected push channel, Represent the weight of each channel, It is an Internet hospital APP. It is a WeChat public account. It’s a text message notification.

[0029] Specifically, by automatically pushing assessment forms and reducing manual allocation work, it is beneficial to improve the accuracy and timeliness of patient data collection, dynamically adjust reminder methods based on patient behavior data, ensure that patients complete the assessment as soon as possible, improve the recovery rate of assessment forms, use classification models to analyze patient data, match appropriate assessment forms and nursing plans, and achieve personalized care. The electronic medical record database automatically reviews assessment results, facilitates the scientific and reasonable classification of nursing needs, and provides nurses with accurate nursing guidance, which is beneficial to improving overall nursing quality and patient satisfaction.

[0030] The admission management module includes an intelligent data analysis module: analyzing the information filled in by the patient, generating charts, and identifying potential nursing risks R;

[0031] Where: S i is the i-th basic risk indicator; W i is the weight coefficient; is the coefficient of variation of the jth dynamic monitoring index; Tj is the clinical threshold boundary value, and the fuzzy membership function is used to quantify the degree of deviation; is the time decay coefficient of the jth dynamic monitoring indicator, which is used to strengthen the impact of recent data: ; t is the time interval between the current time point and the data collection time point; τ is the time scale parameter of exponential decay; C is the behavioral compliance based on the questionnaire submission rate and the execution of medical orders; θ is the clinical experience constant, which is 0.2-0.4; k is the sensitivity parameter. By controlling k so that C is greater than 80%, the risk mitigation effect is significant, that is, Small enough; Ep: step function of the pth critical value event, Ep value is 0.2 for single warning, Ep value is 0.7 for continuous abnormality, and Ep value is 1.2 for multiple systems concurrently.

[0032] The calculation formula of C is:

[0033] in, It indicates the ratio of the actual number of questionnaire submissions to the number of questionnaire submissions that should have been submitted; It indicates the ratio of the execution time of the doctor's order to the planned time; L active It indicates the frequency of patients actively logging into the system, and α, β, and γ are weight coefficients.

[0034] The Wi is the clinical weight coefficient calibrated by Logistic regression.

[0035] S2. Automatically match the corresponding admission preparation information according to the pre-hospital care assessment form filled out by the patient; Further, in step S2, according to the pre-hospital care assessment form filled in by the patient, a method for automatically matching corresponding hospital admission preparation materials is as follows: Based on the content of the pre-hospital nursing assessment form filled out by the patient, a machine learning model is used to identify the patient's hospitalization department, main diagnosis, nursing needs matching, medication guidelines and examination matching during hospitalization, and automatically match the corresponding admission preparation materials. The admission preparation materials include necessary items, special examination preparations, preoperative preparations, personal care products, medication and allergy management, and nursing instructions. The admission preparation materials are automatically pushed to patients through the Internet Hospital APP, WeChat public account and text messages. Patients log in to the Internet Hospital system and view the matching admission preparation materials through the admission management module. If they have any questions, they can consult the nurse online. If the patient does not view and confirm the admission preparation materials within the specified time, the automatic reminder function is used to remind the patient regularly every hour. Admission preparation materials: ,in It is the preparation material for admission. It is a must-have item. It is a special inspection preparation. It's preoperative preparation. It's a personal care product. is medication and allergy management, It is the nursing instructions and admission management module: ,in To remind the intensity, For the The triggering situation of the round reminder, For weight, regular reminders: ,in =1 hour indicates the reminder interval, is the time, and S is the number of reminders.

[0036] Specifically, accurate analysis and evaluation data based on machine learning models can facilitate each patient to obtain personalized admission preparation guidance, which is conducive to improving the efficiency of pre-admission preparation. Admission information can be pushed through APP, WeChat, SMS and other methods, so that patients can obtain key information in time and reduce admission delays caused by missing information. A regular automatic reminder mechanism is adopted to facilitate patients to review and confirm admission preparation materials on time, reducing the risk of affecting the admission process due to non-review of information. By recording patients' reading behavior and consultation situations, data support is provided for subsequent optimization of the admission process, which is conducive to further improving the hospital's information management level.

[0037] Based on the pre-hospital care assessment form, it also includes: an intelligent data analysis step: analyzing the information filled out by the patient, generating charts, and identifying potential care risks.

[0038] Multidimensional data analysis includes: Descriptive analysis: calculation of population characteristics distribution (such as age segment statistics, proportion of pregnancy complications).

[0039] Correlation analysis: chi-square test or logistic regression was used to identify risk factor associations (e.g., the relationship between hyperlipidemia during pregnancy and the risk of postpartum deep vein thrombosis).

[0040] Supervised learning: Use historical datasets to train classification models (such as XGBoost, random forests) to predict risks such as falls, pressure ulcers, and deep vein thrombosis.

[0041] Natural language processing (NLP): Entity recognition is performed on the text of the patient's subjective description (such as "chest tightness has worsened in the past three days"), and keywords (such as "chest tightness" and "shortness of breath") are extracted and associated with potential cardiopulmonary risks.

[0042] Dynamic Rating System: Risk levels are generated using standardized nursing assessment tools (such as the Braden Pressure Ulcer Score and the Morse Falls Score) and are updated dynamically.

[0043] Comprehensive risk assessment: Single risk marker: directly outputs the model prediction results (such as the probability of high risk of falling is 85%).

[0044] Composite risk superposition: Combine multi-dimensional data (such as advanced age, use of anticoagulants, etc.) to generate a comprehensive risk index, which is divided into low / medium / high / extremely high risk levels.

[0045] Visual chart generation Risk Overview Dashboard: Pie charts show the proportion of each risk type, and heat maps show the temporal and spatial distribution of high-risk patients.

[0046] Individual trend chart: The line chart shows the changing trend of the patient's continuous monitoring indicators (such as blood pressure and pain score).

[0047] Comparative analysis chart: The radar chart compares the patient's current data with the benchmark values ​​of the population with similar diseases.

[0048] Report Automation: Generate a PDF or interactive dashboard with detailed risk descriptions, evidence data, and references (e.g., clinical guideline basis).

[0049] S3, intelligently push personalized nursing information based on the nurse's nursing assessment records, the patient's surgery date and admission preparation information; Further, in step S3, according to the nurse's nursing assessment record, the patient's surgery date and admission preparation information, the method of intelligently pushing personalized nursing information is: Nurses record the patient's nursing situation in the specialty system to generate nursing records. The nursing records are stored in the electronic medical record database, and the current nursing stage is calculated through the nursing stage identification function to automatically push nursing information matching the current nursing stage. The nursing information includes prenatal education, diet management, postoperative nursing management, pain management, etc. Personalized nursing information is pushed based on the patient's surgery date. The preoperative nursing information includes pushing a reminder of fasting and water deprivation 1 day before surgery, reminding the patient to change surgical clothing, remove metal ornaments, empty the bladder, and providing preoperative psychological guidance 2 hours before surgery. Postoperative position management is pushed 6 hours after surgery. The preoperative nursing information pushed on the day of surgery includes pushing a reminder of fasting and water deprivation 1 day before surgery, reminding the patient to change surgical clothing, remove metal ornaments, empty the bladder, and providing preoperative psychological guidance 2 hours before surgery. Postoperative position management is pushed 6 hours after surgery. Precautions related to postoperative fundus massage are pushed on the day of surgery. Health education content such as early ambulation and catheter removal is pushed 24 hours after surgery. Nursing stage identification function: , where is the current nursing stage, means taking the maximum value of, is the nursing stage identification function, are all possible nursing stages, is under the condition of a given nursing record .

[0050] Furthermore, in step S3, the method for intelligently pushing personalized nursing information based on the nurse's nursing assessment record, the patient's surgery date, and the admission preparation materials is as follows: Based on the patient's admission preparation materials, the content applicable to the current nursing stage is screened, and personalized nursing information is pushed, including but not limited to preoperative guidance matching when the patient is admitted to the hospital. Then, during the postoperative stage, the pictures, texts, and videos of the health education for postoperative nursing will be automatically pushed. The personalized nursing information is pushed to the patient through push methods such as APP messages, text messages, WeChat, voice assistants, and synchronization on the nurse side.

[0051] Specifically, based on the patient's admission preparation materials, using the intelligent data analysis module, the data filled in by the patient is analyzed to generate charts, identify potential nursing risks. Through nursing stage identification and data matching, nursing information is accurately pushed, which is convenient for improving the personalization level and accuracy of patient care, automatically pushing nursing information, reducing the repetitive education work of nurses, enabling nursing staff to be more focused on high-quality nursing services, regularly pushing nursing information, helping patients better follow the nursing plan, improving the recovery effect, reducing the risk of postoperative complications, recording the reading rate and feedback of nursing information, and continuously optimizing nursing content, which is beneficial to enhancing the patient experience and the quality of medical services.

[0052] S4. Intelligently push personalized health education information based on the patient's nursing information; Further, in step S4, the method for intelligently pushing personalized health education information according to the patient's nursing information is: The information system automatically matches relevant health education content based on the patient's nursing information when the nurse enters a new nursing record in the information system. It automatically updates the health education content when the patient's condition and / or treatment plan changes. When the patient is discharged, it pushes post-discharge health management guidance, matches wound care, pain management and nutrition management based on nursing information, matches relevant nursing content based on changes in patient status, records the patient's health education reading rate, analyzes the needs and preferences of different patient groups, optimizes push content to provide more intuitive video guidance, and combines artificial intelligence and machine learning to adjust the push frequency and content of health education information according to the patient's condition and recovery speed, and defines personalized push adjustment functions: ,in It is the push adjustment strategy of health education information. is the weight parameter, is the reading rate of health education content, is the number of times the patient has read the health education content, is the total number of health education content pushed by the system. is the weight parameter, The patient is at time Health status at all times, is the weight parameter, is the matching probability of health education content, and automatically updates the health education content: ,in It's time The patient's status at the moment, It's time The patient's status at the moment, The patient is arrive The amount of changes in treatment plan adjustment, recovery progress, etc. during the period, is the adjustment factor.

[0053] Specifically, through the connection between the information system and the hospitalization system, the hospitalization system automatically links the patient's pre-admission information to improve the efficiency of admission processing. By dynamically adjusting the push content, patients can receive the most relevant health information, which is beneficial to improving the effectiveness of health management. The health education content is intelligently updated according to factors such as the patient's recovery progress and treatment plan adjustments to avoid interference from outdated or irrelevant information. By analyzing reading rates and demand preferences and adjusting the way information is presented, it is beneficial to improve patients' participation and compliance in health management. Combining APP, text messages, voice assistants, videos and other forms can meet the learning habits of different patient groups and enhance the acceptability of health education.

[0054] Embodiment 2: like Figure 1 As shown, embodiment 2 provides a nursing pre-hospital assessment system based on an Internet hospital, which includes the following steps: The information system is based on the Internet hospital. According to the admission form issued by the doctor, the information system automatically pushes the pre-hospital care assessment form, and the patient fills in the assessment form online; The admission management module automatically matches the corresponding admission preparation information based on the pre-hospital care assessment form filled out by the patient; Intelligent push module, which intelligently pushes personalized nursing information based on the nurse's nursing assessment records, the patient's surgery date and admission preparation information; The health education module intelligently pushes personalized health education information based on the patient's nursing information.

[0055] Furthermore, the workflow of the information system is: The doctor issues an admission form for the patient in the Internet hospital system, records the patient's basic information, including name, gender, age, hospitalization department and diagnosis, and automatically pushes the corresponding pre-hospital nursing assessment form to the patient's Internet hospital account. The pre-hospital nursing assessment form includes basic health conditions, daily living ability and psychological state. The push channels include: Internet hospital APP, WeChat public account and SMS notification. Basic information: ,in It is basic information. It's your name. It's gender, It's age. It's an inpatient department. is the reason for hospitalization, classification model: ,in For the predicted hospital admission department, is the weight matrix of the classification model, is the bias term, It is a Softmax activation function. It uses the automatic reminder function. When the patient fails to fill out the evaluation form within one day, it uses a weight distribution mechanism to calculate the priority of the push channel. It selects any one of the three methods, APP push, SMS, and voice call, to remind the patient to fill out the form. The completed pre-hospital evaluation form is directly imported into the Jingyi nursing document. According to the nursing level requirements, a nursing plan is formulated. After analyzing and reviewing the evaluation form submitted by the patient through the electronic medical record database, the patient's nursing demand level is classified and the nursing plan is recorded. The automatic reminder function: ,in is the reminder intensity, Respectively represent the triggering times of APP push, SMS reminder and voice call, is the weight coefficient, and the weight distribution mechanism is: ,in It is the pre-hospital care assessment form. It's basic health condition. It is the ability of daily life. It's a psychological state. The final selected push channel, Represent the weight of each channel, It is an Internet hospital APP. It is a WeChat public account. It’s a text message notification.

[0056] Furthermore, the workflow of the admission management module is: Based on the content of the pre-hospital nursing assessment form filled out by the patient, a machine learning model is used to identify the patient's hospitalization department, main diagnosis, nursing needs matching, medication guidelines and examination matching during hospitalization, and automatically match the corresponding admission preparation materials. The admission preparation materials include necessary items, special examination preparations, preoperative preparations, personal care products, medication and allergy management, and nursing instructions. The admission preparation materials are automatically pushed to patients through the Internet Hospital APP, WeChat public account and text messages. Patients log in to the Internet Hospital system and view the matching admission preparation materials through the admission management module. If they have any questions, they can consult the nurse online. If the patient does not view and confirm the admission preparation materials within the specified time, the automatic reminder function is used to remind the patient regularly every hour. Admission preparation materials: ,in It is the preparation material for admission. It is a must-have item. It is a special inspection preparation. It's preoperative preparation. It's a personal care product. is medication and allergy management, It is the nursing instructions and admission management module: ,in To remind the intensity, For the The triggering situation of the round reminder, For weight, regular reminders: ,in =1 hour indicates the reminder interval, It's time. The number of reminders.

[0057] Furthermore, the workflow of the smart push module is: Nurses record the patient's nursing situation in the specialist system and generate nursing records. The nursing records are stored in the electronic medical record database, and the current nursing stage is calculated through the nursing stage identification function. Nursing information matching the current nursing stage is automatically pushed. Nursing information includes prenatal education, diet management, postoperative nursing management and pain management. Personalized nursing information is pushed based on the patient's surgery date. Preoperative nursing information includes preoperative fasting and drinking reminders pushed one day before surgery, reminders for patients to change surgical clothes, remove metal jewelry, empty the bladder and preoperative psychological guidance 2 hours before surgery, postoperative position management pushed 6 hours after surgery, and preoperative nursing information pushed on the day of surgery. Preoperative nursing information includes preoperative fasting and drinking reminders pushed one day before surgery, reminders for patients to change surgical clothes, remove metal jewelry, empty the bladder and preoperative psychological guidance 2 hours before surgery, postoperative position management pushed 6 hours after surgery, postoperative uterine fundus massage related precautions pushed on the day of surgery, and early bed activity and catheter removal and other health education content pushed 24 hours after surgery. Nursing stage identification function: ,in The current stage of care, Indicates the maximum value , is the nursing stage identification function, are all possible stages of care, Is in a given nursing record In this case, based on the patient's admission preparation information, we screen the content suitable for the current nursing stage and push personalized nursing information, including but not limited to the preoperative guidance matched when the patient is admitted to the hospital. In the postoperative stage, pictures, texts and videos of health education for postoperative care will be automatically pushed. Personalized nursing information will be pushed to patients through APP messages, SMS, WeChat, voice assistants and synchronous push on the nurse side.

[0058] Furthermore, the workflow of the health education module is as follows: The information system automatically matches relevant health education content based on the patient's nursing information when the nurse enters a new nursing record in the information system. It automatically updates the health education content when the patient's condition and / or treatment plan changes. When the patient is discharged, it pushes post-discharge health management guidance, matches wound care, pain management and nutrition management based on nursing information, matches relevant nursing content based on changes in patient status, records the patient's health education reading rate, analyzes the needs and preferences of different patient groups, optimizes push content to provide more intuitive video guidance, and combines artificial intelligence and machine learning to adjust the push frequency and content of health education information according to the patient's condition and recovery speed, and defines personalized push adjustment functions: ,in It is the push adjustment strategy of health education information. is the weight parameter, is the reading rate of health education content, is the number of times the patient has read the health education content, is the total number of health education content pushed by the system. is the weight parameter, The patient is at time Health status at all times, is the weight parameter, is the matching probability of health education content, and automatically updates the health education content: ,in It's time The patient's status at the moment, It's time The patient's status at the moment, The patient is arrive The amount of changes in treatment plan adjustment, recovery progress, etc. during the period, is the adjustment factor.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A maternal pre-hospital health information management and evaluation system based on an Internet hospital, characterized in that: The system comprises: The information system is based on the Internet hospital. According to the admission form issued by the doctor, the information system automatically pushes the pre-hospital care assessment form, and the patient fills in the assessment form online; The admission management module automatically matches the corresponding admission preparation information according to the pre-hospital nursing assessment form filled in by the patient; the admission management module includes an intelligent data analysis module: analyzes the information filled in by the patient, generates charts, and identifies potential nursing risks R; Where: S i is the i-th basic risk indicator; W i is the weight coefficient; is the coefficient of variation of the jth dynamic monitoring indicator; T j is the clinical threshold boundary value, and the fuzzy membership function is used to quantify the degree of deviation; is the time decay coefficient of the jth dynamic monitoring indicator, which is used to strengthen the impact of recent data: ; t is the time interval between the current time point and the data collection time point; τ is the time scale parameter of exponential decay; C is the behavioral compliance based on the questionnaire submission rate and the execution of medical orders; θ is the clinical experience constant, which is 0.2-0.4; k is the sensitivity parameter. By controlling k so that C is greater than 80%, the risk mitigation effect is significant, that is, Small enough; Ep: step function of the pth critical value event, Ep value is 0.2 for single warning, Ep value is 0.7 for continuous abnormality, and Ep value is 1.2 for multiple systems concurrently.

2. According to claim 1, a maternal pre-hospital health information management and evaluation system based on an Internet hospital is characterized in that: The calculation formula of C is: in, It indicates the ratio of the actual number of questionnaire submissions to the number of questionnaire submissions that should have been submitted; It indicates the ratio of the execution time of the doctor's order to the planned time; L active It indicates the frequency of patients actively logging into the system, and α, β, and γ are weight coefficients.

3. According to claim 1, a maternal pre-hospital health information management and evaluation system based on an Internet hospital is characterized in that: The W i is the clinical weight coefficient calibrated by Logistic regression.

4. According to claim 1, a maternal pre-hospital health information management and evaluation system based on an Internet hospital is characterized in that: The workflow of the information system is as follows: The doctor issues an admission form to the patient in the Internet hospital system and records the patient's basic information; The corresponding pre-hospital nursing assessment form is automatically pushed to the patient's Internet hospital account. The pre-hospital nursing assessment form includes basic health conditions, daily living ability and psychological state; Develop nursing plans in accordance with nursing level requirements, analyze and review the assessment forms submitted by patients through the electronic medical record database, classify the patients' nursing needs levels, and record the nursing plans.

5. According to the Internet hospital-based maternal pre-hospital health information management and evaluation system of claim 1, it is characterized in that: The workflow of the admission management module is as follows: Automatically match the corresponding admission preparation information based on the content of the pre-hospital care assessment form filled out by the patient; Automatically push admission preparation information to patients; The patient logs in to the Internet hospital system and checks the matching admission preparation information through the admission management module. If the patient does not check and confirm the admission preparation information within the specified time, the patient will be reminded regularly. The formula for the intensity P of the reminder is: in For the The triggering situation of the round reminder, For weight, regular reminders: ,in =1 hour indicates the reminder interval, is the time, and S is the number of reminders.

6. According to the Internet hospital-based maternal pre-hospital health information management and evaluation system of claim 1, it is characterized in that: The system also includes an intelligent push module, and the working process is as follows: Document patient care in specialty systems to generate nursing records; Nursing records are stored in the electronic medical record database, and the current nursing stage is calculated through the nursing stage recognition function, and nursing information matching the current nursing stage is automatically pushed; The current formula for Care Stage D is: in Indicates taking The maximum value of is the nursing stage identification function, are all possible stages of care, Is in a given nursing record In the case of a hospital admission, filter the content applicable to the current stage of care based on the patient's admission preparation information.

7. According to claim 1, a maternal pre-hospital health information management and evaluation system based on an Internet hospital is characterized in that: The system also includes a health education module, and the workflow is as follows: When entering new nursing records, relevant health education content will be automatically matched; Automatically update health education content when the patient's condition and / or treatment plan changes; When the patient is discharged from the hospital, push the post-discharge health management guidance and push the adjustment function for: in, is the weight parameter, is the reading rate of health education content, is the number of times the patient has read the health education content, is the total number of health education content pushed by the system. is the weight parameter, The patient is at time Health status at all times, is the weight parameter, is the matching probability of health education content.

Images