Intelligent emergency pre-examination triage system based on big data

Abstract

The invention discloses an intelligent emergency pre-examination triage system based on big data, and relates to the technical field of data analysis, the emergency pre-examination triage system comprises a data acquisition module, an evaluation index extraction module, an intelligent analysis module, a triage evaluation module, a triage decision module, a feedback interaction module and a patient information management module, all the modules are connected through electric signals. According to the intelligent emergency treatment pre-examination triage system based on the big data, the comprehensive evaluation model and the triage evaluation coefficient are integrated, and the symptoms of the patient are evaluated quickly and accurately, so that the triage level and the recommended treatment department are quickly determined, the emergency treatment efficiency is remarkably improved, the waiting time of the patient is shortened, and the patient experience is improved. According to the method, medical resources are configured more reasonably, meanwhile, more comprehensive patient portraits can be provided for medical staff according to multi-dimensional information such as medical history and examination results of patients, and making of more accurate diagnosis and treatment decisions is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an intelligent emergency pre-examination and triage system based on big data. Background Art

[0002] With the development of social economy, the demand for emergency medical services continues to grow, and medical institutions have accumulated a huge amount of medical data, such as patients' basic information, symptoms, examination results, medical history, treatment process, etc. At the same time, medical resources, especially high-quality emergency medical resources, are relatively tight, which makes the emergency department face tremendous pressure. The traditional manual pre-examination and triage method is often difficult to quickly and accurately evaluate and classify a large number of patients, which can easily lead to inaccurate triage, long waiting time for patients, and other problems, which in turn affects the efficiency of emergency treatment.

[0003] Different patients have individual differences in their response and tolerance to diseases. When conducting pre-examination and triage, only considering a single evaluation indicator will lead to deviations in the triage of some patients. Therefore, how to comprehensively evaluate the patient's disease status is a problem we need to solve. To this end, an intelligent emergency pre-examination and triage system based on big data is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent emergency pre-examination and triage system based on big data, the emergency pre-examination and triage system comprising a data acquisition module, an evaluation index extraction module, an intelligent analysis module, a triage evaluation module, a triage decision module, a feedback interaction module and a patient information management module, wherein the modules are connected by electrical signals;

[0005] The data collection module is used to collect the patient's basic information, medical history, symptom description, vital signs data, and patient source data, connect to various information systems of the hospital, including the electronic medical record system, the inspection and examination system, and the monitoring equipment, and perform pre-processing such as cleaning, deduplication, and formatting of the collected data to ensure the accuracy and consistency of the data, improve the data quality, and reduce the triage deviation caused by data errors;

[0006] The evaluation index extraction module screens and extracts evaluation indicators related to emergency pre-examination and triage from the pre-processed data to form a comprehensive evaluation system;

[0007] The intelligent analysis module uses machine learning technology to perform intelligent analysis on patient data, predict the development trend of the patient's disease, provide scientific prediction results, and assist medical staff in making more accurate triage decisions;

[0008] The triage assessment module divides the triage level based on the patient's disease trend prediction results and the urgency of the patient's triage, and matches the corresponding triage decision suggestions;

[0009] The triage decision module semi-automatically generates triage suggestions based on the triage assessment results, combined with the hospital's resources and emergency procedures, and sends them to relevant medical personnel for verification, thereby improving triage efficiency and ensuring that patients can receive appropriate treatment in a timely manner;

[0010] The feedback interaction module feeds back the triage decision results to medical staff, patients and their families, and displays triage information in various ways such as display screens and mobile applications, including condition assessment, treatment departments and estimated waiting time, and provides interactive functions. Medical staff can confirm, adjust or supplement the triage results based on clinical experience;

[0011] The patient information management module establishes a patient information database to store the patient's personal information, medical history, and examination results, and integrates the patient's triage evaluation and decision results, making it convenient for medical staff to check at any time, improving information retrieval efficiency, reducing repeated examinations, and reducing medical costs.

[0012] Preferably, in the data acquisition module, the patient data acquisition and preprocessing process includes:

[0013] The categories of patient data collection are clarified, namely basic information, medical history information, symptom description, vital signs data and patient source. Among them, the basic information of the patient includes the patient's name, gender, age, contact information and other basic information; the medical history information includes the patient's previous medical history, allergy history, surgical history, etc.; the symptom description includes the patient's current main symptoms, symptom duration, symptom changes, etc., which helps doctors quickly understand the patient's condition; the vital signs data includes the patient's temperature, blood pressure, heart rate, respiratory rate and other key vital signs data, which can reflect the patient's physiological state; the patient's source is the way the patient came to the hospital, including coming by himself, ambulance, referral, which helps doctors understand the patient's urgency and condition background;

[0014] Connect with the hospital's internal electronic medical record system, testing and inspection system, and monitoring equipment, and establish a safe and stable data connection channel based on the data interface of each system;

[0015] Aggregate multi-source data collected from different systems according to a unified data template, and use the patient's unique identity (medical card number or ID number) as an index to integrate data from various sources to form a patient-centric, multi-dimensional data set;

[0016] Perform pre-processing operations such as data cleaning, deduplication and formatting on the data set, clean the collected data, remove invalid, redundant or erroneous data, ensure the accuracy and completeness of the data, deduplicate the duplicate data to avoid repeated calculations or misjudgments in subsequent analysis and decision-making, and format the collected data into a unified standard format to facilitate subsequent analysis and decision-making.

[0017] Preferably, in the evaluation index extraction module, the process of forming the comprehensive evaluation system includes:

[0018] Build a local knowledge base based on medical professional knowledge maps, clinical diagnosis and treatment guidelines, and emergency triage practice experience. The local knowledge base covers the patient's basic information, medical history information, symptom descriptions, vital signs data, and patient sources.

[0019] Statistical methods (Pearson correlation coefficient) were used to analyze the correlation between the preprocessed data and the emergency pre-examination triage results, and evaluation indicators that were highly correlated with the triage results were screened out, namely, vital signs evaluation indicators, symptom severity evaluation indicators, and patient source evaluation indicators. The relationship information in the medical knowledge graph was used to analyze the causal relationship between symptoms and medical history, determine which symptoms may be caused by specific medical history, or which medical history may increase the risk of specific symptoms, and integrate single evaluation indicators into a multi-dimensional comprehensive evaluation system;

[0020] The screened evaluation indicators are quantified, the severity of symptoms is divided into mild, moderate, and severe, and corresponding numerical values ​​are assigned. The vital signs data are standardized to ensure the comparability between different indicators. The quantified evaluation indicators are coded so that they can be recognized and utilized by subsequent analysis models.

[0021] Preferably, in the intelligent analysis module, the process of predicting the development trend of a patient's disease includes:

[0022] According to the importance and influence of the evaluation indicators, a corresponding weight is assigned to each evaluation indicator, and based on the selected evaluation indicators and the assigned weights, a comprehensive evaluation model is trained in combination with a neural network model;

[0023] After the data of new emergency patients are collected, processed, and the evaluation indicators are extracted and quantified, they are input into the intelligent analysis module. The trained comprehensive evaluation model is used to intelligently analyze the patient data, extract key information and patterns related to the development of the disease, and identify abnormal evaluation indicators of patients;

[0024] Based on the analysis results, the development trend of the patient's disease is predicted, and the predicted results of the disease development risk are output, including the probability of disease worsening and the estimated time window for emergency intervention.

[0025] Preferably, in the triage assessment module, the process of dividing the triage levels includes:

[0026] According to the disease trend prediction results, different weights are assigned to evaluation indicators of different dimensions;

[0027] Combine the disease trend prediction results output by the intelligent analysis module with the vital sign deviation score, symptom severity score, and patient source score to calculate the triage assessment coefficient and assess the patient's triage urgency;

[0028] According to the hospital's emergency resource carrying capacity, clinical treatment priority conventions, and the patient's triage urgency, different triage levels are divided, namely critical triage level, emergency triage level, sub-emergency triage level, and ordinary triage level, and the corresponding triage evaluation threshold is matched for each triage level;

[0029] According to the patient's triage level, the corresponding suggestions are matched from the predefined triage decision recommendation strategy library. The triage decision recommendation strategy library includes treatment plans, referral suggestions, and further examination suggestions for different triage levels. Among them, the triage decision recommendation strategy library is built based on the hospital's existing emergency diagnosis and treatment process specifications, the expertise of each department, and the resource distribution. For patients at the critical triage level, the strategy is to send them directly to the emergency room, immediately convene multidisciplinary experts such as cardiology, emergency department, and anesthesia department for consultation, and simultaneously start the preparation of emergency equipment and drugs. Emergency triage levels are arranged to be quickly sent to specialized emergency rooms (such as chest pain centers for chest pain patients), with priority given to key examinations (electrocardiogram, CT, etc.), and treatment is carried out while the patient is being examined; sub-emergency triage levels are guided to the comprehensive emergency treatment area, and a series of routine examinations are carried out in an orderly manner before being diagnosed by specialists; ordinary triage levels are diverted to the emergency outpatient waiting area, and registration, waiting, and diagnosis and treatment are carried out according to routine procedures.

[0030] Preferably, the process of assigning differentiated weights to evaluation indicators of different dimensions includes:

[0031] For patients whose vital signs are seriously deviated from the normal range, such as systolic blood pressure below 90 mmHg or above 180 mmHg, heart rate below 40 beats / minute or above 150 beats / minute, respiratory rate above 30 times per minute or below 8 times per minute, and body temperature above 40°C or below 35°C, a weight coefficient of 0.4-0.5 is assigned based on the incidence of critical illness in previous cases.

[0032] For the severity of symptoms, according to the degree of interference, pain and discomfort caused by the symptoms on body functions, combined with the impact on the prognosis of the corresponding disease, moderate to severe pain and severe dyspnea symptoms are given a weight of 0.2-0.3;

[0033] Regarding the source of patients, referrals, ambulance transfers and on-site critical situation feedback are given a weight of 0.1-0.2, while those who come on their own have a relatively lower weight, in the range of 0.05-0.1.

[0034] Preferably, the calculation expression of the triage evaluation coefficient is:

[0035] ;

[0036] in, is the triage assessment coefficient, which represents the comprehensive quantitative assessment result of the urgency of patient triage, and its value range is between 0 and 1. The value is close to 1, indicating that the patient's triage urgency is high. The more critical the condition, the more urgent the priority. The closer the value is to 0, the lower the urgency of triage and the milder the condition. is the evaluation index, , is the deviation value of vital signs, Score the severity of symptoms, Scoring the patient's origin is used to distinguish data processing of different evaluation indicators in summation functions and related operations. is the weight coefficient, is the weight corresponding to the deviation value of vital signs, Corresponding to the symptom severity score weight, Corresponding to the patient source score weight, the weight coefficient is set according to the influence of each evaluation indicator on the urgency of the disease, and meets the ,at the same time , so as to ensure that each evaluation indicator participates in the evaluation reasonably, is the original score value, Score vital sign deviations, is the symptom severity score, represents the patient source score, The minimum value of each evaluation index score is used for normalization and measurement. The degree of deviation from the benchmark, Corresponding to the minimum reference value of vital signs assessment indicators, It is the minimum reference value of the symptom severity assessment index. The minimum reference value for patient source assessment indicators. is the adjustment coefficient, which is a constant greater than 0 and is used to adjust the shape of the exponential function curve;

[0037] The values ​​of the triage evaluation coefficient and the triage evaluation thresholds preset for the triage level are obtained to match the four-level triage levels, which are:

[0038] Emergency triage level: ;

[0039] Emergency triage level: ;

[0040] Sub-urgent triage level: ;

[0041] General triage level: ;

[0042] in, is the triage assessment coefficient, is the lower threshold corresponding to the critical triage level and the upper threshold corresponding to the emergency triage level, is the lower threshold corresponding to the emergency triage level and the upper threshold corresponding to the sub-emergency triage level, is the lower threshold corresponding to the sub-urgent triage level and the upper threshold corresponding to the ordinary triage level, , , .

[0043] Preferably, in the triage decision module, the process of generating triage suggestions includes:

[0044] Receive the results from the triage assessment module, including the patient's triage level, triage assessment coefficient, and related vital signs and symptom description information, and comprehensively analyze the current hospital bed occupancy, medical staff work status, emergency equipment, and drug reserve resources;

[0045] According to the hospital's emergency procedures and specifications, the patient's triage level is matched with the corresponding emergency treatment process to determine the department the patient needs to go to, the examination items to be performed, and the corresponding treatment measures;

[0046] Based on the analysis results, the triage decision module semi-automatically generates triage recommendations and sends them to relevant medical personnel, including emergency doctors, nurses, and transport personnel, through the hospital's internal communication system;

[0047] After receiving the triage recommendation, the medical staff will check it according to the actual situation of the patient and the actual situation of the hospital, and adjust or supplement the triage recommendation. Once the triage recommendation is confirmed by the medical staff, the relevant treatment measures will be implemented immediately, including sending the patient to the designated department, conducting necessary examinations, and providing emergency treatment.

[0048] Preferably, in the feedback interaction module, the feedback interaction process includes:

[0049] Obtain the final triage decision results from the triage decision module, including the condition assessment, recommended treatment department, and estimated waiting time, and sort out and format the triage decision results;

[0050] The relevant information of triage decision results is displayed to relevant personnel through display screens and mobile applications (mobile phone apps or mini-programs) in the hospital. Medical staff can view it on workstations or mobile devices, and patients and their families can obtain triage information through designated query areas or mobile phone applications.

[0051] Medical staff confirm, adjust or supplement the triage results through the interactive portal. When the medical staff confirm, adjust or supplement the triage results, the feedback interaction module receives the feedback, processes the feedback, updates the triage information, and ensures that the updated information can be accurately and promptly displayed to relevant personnel.

[0052] Preferably, in the patient information management module, the process of establishing the patient information database includes:

[0053] The patient information management module is integrated with the triage assessment module and the triage decision module. After the triage assessment and decision are completed, the patient information management module obtains the assessment results and decision information and stores them in the patient information database;

[0054] Provide information retrieval function, so that medical staff can quickly search according to the patient's name, medical card number, medical record number and other conditions, and intuitively display the search results, including the patient's personal information, medical history, examination results, and triage evaluation and decision results;

[0055] Regularly maintain and update the patient information database to ensure the accuracy and timeliness of the data, delete outdated or invalid information, update the patient's latest examination results and medical history information, and add new triage assessment and decision results.

[0056] The present invention provides an intelligent emergency pre-examination and triage system based on big data. It has the following beneficial effects:

[0057] 1. This intelligent emergency pre-examination and triage system based on big data can quickly and accurately evaluate the patient's symptoms by integrating comprehensive evaluation models and triage evaluation coefficients, so as to quickly determine the triage level and recommended treatment department, significantly improving the efficiency of emergency treatment, reducing patient waiting time, and making medical resources more reasonably allocated. At the same time, it can provide medical staff with a more comprehensive patient portrait based on multi-dimensional information such as the patient's medical history and examination results, which helps to make more accurate diagnosis and treatment decisions.

[0058] 2. The intelligent emergency pre-examination and triage system based on big data enables patients to understand their treatment progress and condition assessment at any time by providing clear, accurate and timely information display and query functions. It can also provide personalized treatment recommendations and services, further improving patients' treatment experience and satisfaction. By integrating information such as patients' medical history, examination results and triage decision results, it provides medical staff with a comprehensive and accurate patient information database, which not only reduces repeated examinations and unnecessary medical operations, reduces medical costs, but also reduces medical risks caused by incomplete or inaccurate information. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a module structure diagram of an intelligent emergency pre-examination and triage system based on big data of the present invention;

[0060] Figure 2 A flowchart for predicting the disease development trend of a patient of the present invention;

[0061] Figure 3 This is a flow chart for dividing the triage levels of the present invention. DETAILED DESCRIPTION

[0062] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0063] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an intelligent emergency pre-examination and triage system based on big data, the emergency pre-examination and triage system includes a data acquisition module, an evaluation index extraction module, an intelligent analysis module, a triage evaluation module, a triage decision module, a feedback interaction module and a patient information management module, wherein the modules are connected by electrical signals;

[0064] The data collection module is used to collect the patient's basic information, medical history, symptom description, vital signs data, and patient source data. It connects to various information systems of the hospital, including the electronic medical record system, inspection and examination system, and monitoring equipment, and performs pre-processing such as cleaning, deduplication, and formatting of the collected data to ensure the accuracy and consistency of the data, improve data quality, and reduce triage deviations caused by data errors. The collection categories of patient data are clarified, namely basic information, medical history information, symptom description, vital signs data, and patient source. Among them, the patient's basic information includes the patient's name, gender, age, contact information and other basic information. The medical history information includes the patient's previous medical history, allergy history, surgical history, etc. The symptom description includes the patient's current main symptoms, symptom duration, symptom changes, etc., which helps doctors quickly understand the patient's condition. Vital signs data includes key vital signs data such as the patient's body temperature, blood pressure, heart rate, and respiratory rate, which can reflect the patient's physiological state. The patient's source is the way the patient came to the hospital, including coming by himself, ambulance, and referral, which helps doctors understand the patient's urgency and condition background, and is connected to the hospital's internal electronic medical record system. The system is connected with the hospital's electronic medical record system, the inspection and testing system, and the monitoring equipment. According to the data interface of each system, a safe and stable data connection channel is established. Among them, it is connected with the hospital's electronic medical record system to obtain the patient's medical record information in real time, including past medical history, test results, diagnosis records, etc. It is connected with the hospital's inspection and testing system to obtain the patient's latest test results, including blood routine, urine routine, electrocardiogram, etc. It is connected with various monitoring equipment in the hospital to obtain the patient's vital signs data in real time, including heart rate, blood pressure, blood oxygen saturation, etc. The multi-source data collected from different systems are aggregated according to a unified data template, and the patient's unique identity (medical card number or ID number) is used as an index to integrate the data from various sources to form a patient-centered, multi-dimensional data set. The data set is pre-processed by data cleaning, deduplication and formatting. The collected data is cleaned to remove invalid, redundant or erroneous data to ensure the accuracy and completeness of the data. Duplicate data is deduplicated to avoid repeated calculations or misjudgments in subsequent analysis and decision-making, and the collected data is formatted into a unified standard format to facilitate subsequent analysis and decision-making;

[0065] The evaluation index extraction module screens and extracts evaluation indicators related to emergency pre-examination and triage from the pre-processed data to form a comprehensive evaluation system, and quantifies and encodes the extracted features so that they can be effectively used by subsequent analysis models, so that they can more comprehensively reflect the patient's disease status and reduce the triage deviation caused by a single evaluation indicator. A local knowledge base is built based on medical professional knowledge maps, clinical diagnosis and treatment guidelines, and emergency triage practical experience. The local knowledge base covers the patient's basic information, medical history information, symptom descriptions, vital signs data, and patient sources. Among them, using the existing medical knowledge map, SNOMED CT, ICD, etc., provide standardized coding and description for medical history, symptoms and vital signs, integrate clinical diagnosis and treatment guidelines, ensure that triage standards are consistent with the latest medical practices, collect and analyze actual cases of emergency triage, clarify triage standards and decision-making processes under different conditions, use statistical methods (Pearson correlation coefficient) to analyze the correlation between pre-processed data and emergency pre-examination triage results, screen out evaluation indicators that are highly correlated with triage results, namely vital sign evaluation indicators, symptom severity evaluation indicators, and patient source evaluation indicators, and use the relationship information in the medical knowledge graph to analyze the causal relationship between symptoms and medical history, determine which symptoms may be caused by specific medical history, or which medical history may increase the risk of specific symptoms, integrate single evaluation indicators into a multi-dimensional comprehensive evaluation system, quantify the selected evaluation indicators, divide the symptom severity into mild, moderate, and severe, assign corresponding values, and standardize the vital sign data to ensure the comparability between different indicators, and encode the quantified evaluation indicators so that subsequent analysis models can identify and use them;

[0066] The intelligent analysis module uses machine learning technology to perform intelligent analysis on patient data, predict the development trend of patients' diseases, provide scientific prediction results, and assist medical staff in making more accurate triage decisions. According to the importance and impact of the evaluation indicators, corresponding weights are assigned to each evaluation indicator. Based on the screened evaluation indicators and the assigned weights, the comprehensive evaluation model is trained in combination with the neural network model. The model parameters are adjusted through optimization algorithms such as gradient descent and back propagation to improve the prediction accuracy. The model is verified by cross-validation, holdout method or bootstrap method. The model parameters and structure are adjusted according to the verification results to optimize the model performance. After the data of new emergency patients are collected, processed, and the evaluation indicators are extracted and quantified and encoded, they are input into the intelligent analysis module. The trained comprehensive evaluation model is used to perform intelligent analysis on the patient data, extract key information and patterns related to the development of the disease, identify the patient's abnormal evaluation indicators, predict the development trend of the patient's disease according to the analysis results, and output the prediction results of the disease development risk, including the probability of disease worsening and the expected time window for emergency intervention.

[0067] The triage assessment module divides the triage level based on the patient's disease trend prediction results and the urgency of the patient's triage, and matches the corresponding triage decision suggestions;

[0068] The triage decision module semi-automatically generates triage recommendations based on the results of the triage assessment, combined with the hospital's resources and emergency procedures, and sends them to relevant medical personnel for verification, thereby improving triage efficiency and ensuring that patients can receive appropriate treatment in a timely manner;

[0069] The feedback interaction module feeds back the triage decision results to medical staff, patients and their families. It displays triage information in a variety of ways, including condition assessment, treatment department and estimated waiting time, through display screens and mobile applications. It also provides interactive functions, so that medical staff can confirm, adjust or supplement the triage results based on clinical experience.

[0070] The patient information management module establishes a patient information database to store the patient's personal information, medical history, and examination results, and integrates the patient's triage evaluation and decision-making results, making it convenient for medical staff to access at any time, improving information retrieval efficiency, reducing repeated examinations, and reducing medical costs.

[0071] The second embodiment is based on the first embodiment. Figure 3 As shown in the figure, in the triage assessment module, the triage level division process includes:

[0072] According to the disease trend prediction results, different weights are assigned to evaluation indicators of different dimensions. For vital signs that are seriously deviated from the normal range, systolic blood pressure is lower than 90mmHg or higher than 180mmHg, heart rate is lower than 40 times / minute or higher than 150 times / minute, respiratory rate is higher than 30 times per minute or lower than 8 times, and body temperature is higher than 40℃ or lower than 35℃, a weight coefficient of 0.4-0.5 is assigned based on the incidence of critical illness in previous cases. For the severity of symptoms, a weight coefficient of 0.4-0.5 is assigned based on the interference of symptoms on body functions, pain and discomfort, combined with the corresponding disease prognosis impact. The weight of moderate to severe pain and severe dyspnea is 0.2-0.3. For the source of patients, referral, ambulance transfer and on-site critical situation feedback are given a weight of 0.1-0.2. The weight of self-transfer is relatively low, in the range of 0.05-0.1. The disease trend prediction results output by the intelligent analysis module are combined with the vital signs deviation value score, symptom severity score and patient source score to calculate the triage assessment coefficient, evaluate the urgency of triage of patients, and conclude based on the hospital's emergency resource carrying capacity and clinical treatment priority practices. According to the urgency of the patient's triage, different triage levels are divided, namely, critical triage level, emergency triage level, sub-emergency triage level and ordinary triage level, and the corresponding triage evaluation threshold is matched for each triage level. According to the patient's triage level, the corresponding suggestions are matched from the predefined triage decision suggestion strategy library. The triage decision suggestion strategy library includes treatment plans, referral suggestions, and further examination suggestions for different triage levels. Among them, the triage decision suggestion strategy library is constructed based on the hospital's existing emergency diagnosis and treatment process specifications, the expertise of each department, and the resource distribution. For patients at the critical triage level, the strategy is to send them directly to the emergency room, immediately convene multidisciplinary experts such as cardiology, emergency department, and anesthesia department for consultation, and simultaneously start the preparation of emergency equipment and drugs. Emergency triage level arrangements are quickly sent to specialized emergency rooms (such as chest pain centers for chest pain patients), and key examinations (electrocardiogram, CT, etc.) are given priority, and treatment is provided while examination is being performed; sub-emergency triage level is guided to the comprehensive emergency treatment area, and a series of routine examinations are carried out in an orderly manner before being diagnosed by specialists; ordinary triage level is diverted to the emergency outpatient waiting area, and registration, waiting, and diagnosis and treatment are carried out according to the conventional process;

[0073] The calculation expression of the triage evaluation coefficient is:

[0074] ;

[0075] in, is the triage assessment coefficient, which represents the comprehensive quantitative assessment result of the urgency of patient triage, and its value range is between 0 and 1. The value is close to 1, indicating that the patient's triage urgency is high. The more critical the condition, the more urgent the priority. The closer the value is to 0, the lower the urgency of triage and the milder the condition. is the evaluation index, , is the deviation value of vital signs, Score the severity of symptoms, Scoring the patient's origin is used to distinguish data processing of different evaluation indicators in summation functions and related operations. is the weight coefficient, is the weight corresponding to the deviation value of vital signs, Corresponding to the symptom severity score weight, Corresponding to the patient source score weight, the weight coefficient is set according to the influence of each evaluation indicator on the urgency of the disease, and meets the ,at the same time , so as to ensure that each evaluation indicator participates in the evaluation reasonably, is the original score value, Score vital sign deviations, is the symptom severity score, represents the patient source score. The vital sign deviation score corresponds to different scores according to the degree of deviation from the normal range. The symptom severity score is divided into levels and corresponding scores according to the degree of interference with body functions, pain and discomfort. The patient source score is given according to whether the patient is transferred by ambulance and the critical condition is reported or comes on his own. The value range is between 0 and some positive upper limit. The minimum value of each evaluation index score is used for normalization and measurement. The degree of deviation from the benchmark, Corresponding to the minimum reference value of vital signs assessment indicators, It is the minimum reference value of the symptom severity assessment index. The minimum reference value for patient source assessment indicators. is the adjustment coefficient, which is a constant greater than 0 and is used to adjust the shape of the exponential function curve and control The rate of change of each evaluation index score can be finely adjusted to determine the contribution of each evaluation index score to the final triage evaluation coefficient. The appropriate Value, when the patient's vital signs seriously deviate from normal ( Increased size), more severe symptoms ( Increased), more urgent sources of patients ( When the The value of each item approaches 1, the sum of the numerators increases, and when the denominator is relatively stable (the weight is fixed), The value will continue to approach 1, indicating that the urgency of triage is increasing; conversely, the closer the indicators are to the minimum reference state ( near ), the exponential function term approaches 1, the numerator approaches 0, The value is close to 0, which means the urgency of triage is low;

[0076] Get the value of the triage evaluation coefficient and the preset triage evaluation threshold of the triage level to match the four-level triage level, which are:

[0077] Emergency triage level: ; When the triage assessment coefficient reaches this range, it means that the patient's vital signs are seriously deviated from the normal range, the symptoms are extremely serious, or the patient is transferred by ambulance and the on-site condition is critical. For example, the patient has cardiac arrest, severe respiratory failure, severe trauma resulting in massive blood loss and a sharp decline in vital signs. The condition of such patients is extremely dangerous and the highest level of emergency measures need to be initiated immediately;

[0078] Emergency triage level: Patients in this range are in a more serious condition, with significant deviations from normal vital signs, and symptoms that significantly interfere with body functions, or whose source indicates a more urgent condition, such as patients in the early stages of acute myocardial infarction, patients with severe craniocerebral injuries but relatively stable vital signs, etc. Patients need to receive specialist treatment and corresponding emergency examinations (electrocardiogram, CT, etc.) in a relatively short period of time (10-15 minutes) to prevent further deterioration of their condition;

[0079] Sub-urgent triage level: Patients in this range have obvious symptoms, but the condition is not urgent. The deviation of vital signs and the severity of symptoms are at a medium level. For example, the patient may be in moderate pain or have general trauma that needs to be treated. There is a certain amount of time buffer to complete a series of routine examinations, blood tests, X-rays, etc., and then be diagnosed by a specialist. A consultation can be arranged within 30 minutes.

[0080] General triage level: Patients with triage assessment coefficients within this range have mild symptoms, such as mild colds, minor sprains, etc., or are regular follow-up patients for chronic diseases. Their vital signs are basically normal or only slightly deviated, and their symptoms have little impact on their body functions. Most of them come to the hospital on their own. Patients can register, wait, and receive treatment in the emergency outpatient waiting area according to the regular process. The waiting time can be relatively long, such as about 60 minutes.

[0081] in, is the triage assessment coefficient, is the lower threshold corresponding to the critical triage level and the upper threshold corresponding to the emergency triage level, is the lower threshold corresponding to the emergency triage level and the upper threshold corresponding to the sub-emergency triage level, is the lower threshold corresponding to the sub-urgent triage level and the upper threshold corresponding to the ordinary triage level, , , ;

[0082] In the triage decision module, the process of generating triage suggestions includes:

[0083] Receive the results from the triage assessment module, including the patient's triage level, triage assessment coefficient, and related vital signs and symptom description information, and comprehensively analyze the current hospital bed occupancy, medical staff working status, emergency equipment and drug reserve resources of each department. According to the hospital's emergency procedures and specifications, match the patient's triage level with the corresponding emergency treatment process, determine the department the patient needs to go to, the examination items to be performed, and the corresponding treatment measures. Based on the analysis results, the triage decision module semi-automatically generates triage suggestions and sends the triage suggestions to relevant medical personnel, including emergency doctors, nurses, and transport personnel, through the hospital's internal communication system. After receiving the triage suggestions, the medical personnel will check according to the actual situation of the patient and the actual situation of the hospital, and adjust or supplement the triage suggestions. Once the triage suggestions are confirmed by the medical personnel, the relevant treatment measures will be immediately implemented, including sending the patient to the designated department, conducting necessary examinations, and providing emergency treatment.

[0084] In the feedback interaction module, the feedback interaction process includes:

[0085] The final triage decision result is obtained from the triage decision module, including the condition assessment, recommended treatment department, and estimated waiting time. The triage decision result is sorted and formatted to meet the standard requirements of different display channels, ensuring that the information is clear, accurate, and easy to understand, so that it can be pushed and displayed quickly and accurately in the future. The relevant information of the triage decision result is displayed to relevant personnel through the display screen and mobile application (mobile phone APP or mini program) in the hospital. Medical staff view it on the workstation or mobile device. Patients and their families obtain triage information through the designated query area or mobile phone application. Medical staff confirm, adjust or supplement the triage result through the interactive entrance. When the medical staff confirms, adjusts or supplements the triage result, the feedback interaction module receives the feedback, processes the feedback, and updates the triage information to ensure that the updated information can be accurately and timely displayed to relevant personnel;

[0086] In the patient information management module, the process of establishing the patient information database includes:

[0087] The patient information management module is integrated with the triage evaluation module and the triage decision-making module. After the triage evaluation and decision are completed, the patient information management module obtains the evaluation results and decision information and stores them in the patient information database. It provides information retrieval function, allowing medical staff to quickly search based on multiple conditions such as the patient's name, medical card number, and medical record number, and intuitively display the retrieval results, including the patient's personal information, medical history, examination results, and triage evaluation and decision results. The patient information database is regularly maintained and updated to ensure the accuracy and timeliness of the data, delete outdated or invalid information, update the patient's latest examination results and medical history information, and add new triage evaluation and decision results.

[0088] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An intelligent emergency pre-examination and triage system based on big data, characterized in that: The emergency pre-examination and triage system includes a data acquisition module, an evaluation index extraction module, an intelligent analysis module, a triage evaluation module, a triage decision module, a feedback interaction module and a patient information management module, wherein the modules are connected by electrical signals; The data collection module is used to collect the patient's basic information, medical history, symptom description, vital signs data, patient source data, and pre-process the collected data; The evaluation index extraction module screens and extracts evaluation indicators related to emergency pre-examination and triage from the pre-processed data to form a comprehensive evaluation system; The intelligent analysis module performs intelligent analysis on the patient's data to predict the patient's disease development trend; The triage assessment module divides the triage level based on the patient's disease trend prediction results and the urgency of the patient's triage, and matches the corresponding triage decision suggestions; The triage decision module semi-automatically generates triage recommendations based on the triage assessment results, combined with the hospital's resources and emergency procedures; The feedback interaction module feeds back the triage decision results to medical staff, patients and their families, displays the triage information in various ways through display screens and mobile applications, and provides interactive functions; The patient information management module establishes a patient information database to store the patient's personal information, medical history, examination results, and integrate the patient's triage evaluation and decision-making results.

2. According to the big data-based intelligent emergency pre-examination and triage system of claim 1, it is characterized by: In the data acquisition module, the patient data acquisition and preprocessing process includes: The categories of patient data collection are clarified, namely basic information, medical history information, symptom description, vital signs data and patient source. Among them, the basic information of the patient includes the patient's name, gender, age, and contact information. The medical history information includes the patient's previous medical history, allergy history, and surgical history. The symptom description includes the patient's current main symptoms, symptom duration, and symptom changes. The vital signs data includes the patient's body temperature, blood pressure, heart rate, and respiratory rate. The patient source is the way the patient came to the hospital, including coming by himself, by ambulance, and by referral; Connect with the hospital's internal electronic medical record system, testing and inspection system, and monitoring equipment, and establish data connection channels based on the data interfaces of each system; Aggregate multi-source data collected from different systems according to a unified data template, and use the patient's unique identity as an index to integrate data from various sources to form a patient-centric, multi-dimensional data set; Perform pre-processing operations such as data cleaning, deduplication and formatting on the data set, clean the collected data, remove invalid, redundant or erroneous data, deduplicate duplicate data, and format the collected data into a unified standard format.

3. The intelligent emergency pre-examination and triage system based on big data according to claim 2 is characterized by: In the evaluation index extraction module, the formation process of the comprehensive evaluation system includes: Build a local knowledge base based on medical professional knowledge maps, clinical diagnosis and treatment guidelines, and emergency triage practice experience. The local knowledge base covers the patient's basic information, medical history information, symptom descriptions, vital signs data, and patient sources. Statistical methods were used to analyze the correlation between the preprocessed data and the emergency pre-examination triage results, and evaluation indicators that were highly correlated with the triage results were screened out, namely, vital signs evaluation indicators, symptom severity evaluation indicators, and patient source evaluation indicators. The relationship information in the medical knowledge graph was used to analyze the causal relationship between symptoms and medical history, and the single evaluation indicators were integrated into a multi-dimensional comprehensive evaluation system. The screened evaluation indicators are quantified, the severity of symptoms is divided into mild, moderate, and severe, and corresponding numerical values ​​are assigned. The vital signs data are standardized and the quantified evaluation indicators are coded.

4. The intelligent emergency pre-examination and triage system based on big data according to claim 3 is characterized by: In the intelligent analysis module, the prediction process of the patient's disease development trend includes: According to the importance and influence of the evaluation indicators, a corresponding weight is assigned to each evaluation indicator, and based on the selected evaluation indicators and the assigned weights, a comprehensive evaluation model is trained in combination with a neural network model; After the data of new emergency patients are collected, processed, and the evaluation indicators are extracted and quantified, they are input into the intelligent analysis module. The trained comprehensive evaluation model is used to intelligently analyze the patient data, extract key information and patterns related to the development of the disease, and identify abnormal evaluation indicators of patients; Based on the analysis results, the development trend of the patient's disease is predicted, and the predicted results of the disease development risk are output, including the probability of disease worsening and the estimated time window for emergency intervention.

5. According to the big data-based intelligent emergency pre-examination and triage system of claim 4, it is characterized by: In the triage assessment module, the triage level division process includes: According to the disease trend prediction results, different weights are assigned to evaluation indicators of different dimensions; Combine the disease trend prediction results output by the intelligent analysis module with the vital sign deviation score, symptom severity score, and patient source score to calculate the triage assessment coefficient and assess the patient's triage urgency; According to the urgency of the patient's triage, different triage levels are divided into critical triage level, emergency triage level, sub-emergency triage level and ordinary triage level, and the corresponding triage evaluation threshold is matched for each triage level; According to the patient's triage level, the corresponding suggestions are matched from the predefined triage decision recommendation strategy library, which includes treatment plans, referral suggestions, and further examination suggestions for different triage levels.

6. The intelligent emergency pre-examination and triage system based on big data according to claim 5 is characterized by: The process of assigning differentiated weights to evaluation indicators of different dimensions includes: For patients whose vital signs are seriously deviated from the normal range, such as systolic blood pressure below 90 mmHg or above 180 mmHg, heart rate below 40 beats / minute or above 150 beats / minute, respiratory rate above 30 times per minute or below 8 times per minute, and body temperature above 40°C or below 35°C, a weight coefficient of 0.4-0.5 is assigned based on the incidence of critical illness in previous cases. For the severity of symptoms, according to the degree of interference, pain and discomfort caused by the symptoms on body functions, combined with the impact on the prognosis of the corresponding disease, moderate to severe pain and severe dyspnea symptoms are given a weight of 0.2-0.3; Regarding the source of patients, referrals, ambulance transfers and on-site critical situation feedback are given a weight of 0.1-0.2, while those who come on their own have a relatively lower weight, in the range of 0.05-0.

1.

7. The intelligent emergency pre-examination and triage system based on big data according to claim 6 is characterized by: The calculation expression of the triage evaluation coefficient is: ； in, is the triage assessment coefficient, ranging from 0 to 1. The value approaches 1, indicating that the patient's triage urgency is high. is the evaluation index, , is the deviation value of vital signs, Score the severity of symptoms, Score the patient source, is the weight coefficient, is the weight corresponding to the deviation value of vital signs, Corresponding to the symptom severity score weight, Corresponding to the patient source scoring weight, and meeting ,at the same time , is the original score value, Score vital sign deviations, is the symptom severity score, represents the patient source score, is the minimum reference value for each evaluation indicator score, Corresponding to the minimum reference value of vital signs assessment indicators, It is the minimum reference value of the symptom severity assessment index. The minimum reference value for the patient source assessment indicator. is the adjustment coefficient, which is a constant greater than 0 and is used to adjust the shape of the exponential function curve; The values ​​of the triage evaluation coefficient and the triage evaluation thresholds preset for the triage level are obtained to match the four-level triage levels, which are: Emergency triage level: ; Emergency triage level: ; Sub-urgent triage level: ; General triage level: ; in, is the triage assessment coefficient, is the lower threshold corresponding to the critical triage level and the upper threshold corresponding to the emergency triage level, is the lower threshold corresponding to the emergency triage level and the upper threshold corresponding to the sub-emergency triage level, is the lower threshold corresponding to the sub-urgent triage level and the upper threshold corresponding to the ordinary triage level, , , .

8. The intelligent emergency pre-examination and triage system based on big data according to claim 7 is characterized by: In the triage decision module, the process of generating triage suggestions includes: Receive the results from the triage assessment module, including the patient's triage level, triage assessment coefficient, and related vital signs and symptom description information, and comprehensively analyze the current hospital bed occupancy, medical staff work status, emergency equipment, and drug reserve resources; According to the hospital's emergency procedures, the patient's triage level is matched with the corresponding emergency treatment process to determine the department the patient needs to go to, the examination items to be performed, and the corresponding treatment measures; Based on the analysis results, the triage decision module semi-automatically generates triage recommendations and sends them to relevant medical personnel, including emergency doctors, nurses, and transport personnel, through the hospital's internal communication system; After receiving the triage recommendation, the medical staff will check it according to the actual situation of the patient and the actual situation of the hospital, and adjust or supplement the triage recommendation. Once the triage recommendation is confirmed by the medical staff, the relevant treatment measures will be implemented immediately.

9. The intelligent emergency pre-examination and triage system based on big data according to claim 8 is characterized by: In the feedback interaction module, the feedback interaction process includes: Obtain the final triage decision results from the triage decision module, including the condition assessment, recommended treatment department, and estimated waiting time, and sort out and format the triage decision results; The relevant information of triage decision results is displayed to relevant personnel through display screens and mobile applications in the hospital. Medical staff can view it on workstations or mobile devices, and patients and their families can obtain triage information through designated query areas or mobile applications. Medical staff confirm, adjust or supplement the triage results through the interactive portal. When the medical staff confirm, adjust or supplement the triage results, the feedback interaction module receives the feedback, processes the feedback, and updates the triage information.

10. The intelligent emergency pre-examination and triage system based on big data according to claim 9, characterized in that: In the patient information management module, the process of establishing the patient information database includes: The patient information management module is integrated with the triage assessment module and the triage decision module. After the triage assessment and decision are completed, the patient information management module obtains the assessment results and decision information and stores them in the patient information database; Provide information retrieval function, so that medical staff can quickly search according to the patient's name, medical card number, medical record number and other conditions, and intuitively display the search results, including the patient's personal information, medical history, examination results, and triage evaluation and decision results; Regularly maintain and update the patient information database, delete outdated or invalid information, update the patient's latest examination results and medical history information, and add new triage assessment and decision results.

Images