Pre-examination triage method and equipment for child emergency treatment and medium

Abstract

The embodiment of the invention discloses a pre-examination triage method and equipment for child emergency treatment and a medium, and relates to the technical field of emergency treatment triage, the method comprises the following steps: obtaining multi-source treatment data of each emergency treatment child patient, so as to construct a current pre-examination triage data set corresponding to each emergency treatment child patient, and according to demographic information of the emergency treatment child patient, establishing a current pre-examination triage data set corresponding to each emergency treatment child patient; matching is carried out in a pre-constructed model library, and an age pre-examination intelligent triage model corresponding to each emergency treatment child patient is determined to generate initial triage grading information of each emergency treatment child patient; when the initial triage classification information is a non-endangered level, determining an affiliated emergency treatment area of each emergency treatment child patient, and collecting real-time waiting queue information; based on the real-time waiting queue information, determining predicted grading change trend information of each emergency treatment child patient; and by predicting the grading change trend information, the treatment area and the treatment sequence are adjusted in real time, and the real-time triage information of each emergency treatment child patient is determined.

Description

Technical Field

[0001] The present specification relates to the technical field of emergency triage, and in particular to a pre-examination and triage method, equipment and medium for pediatric emergency. Background Art

[0002] Emergency pre-examination and triage is the primary link in emergency treatment, and it is also an important support for ensuring medical quality and patient safety, and ensuring that critically ill patients can receive more rapid treatment. The characteristics of pediatric emergency are that there are many children with acute, critical, and severe diseases, the types of diseases are complex, the condition changes rapidly, and family members are required to accompany the whole process. The symptoms of the patients need the assistance of family members, and the family members are nervous and impatient. This requires triage nurses to have keen observation skills, first aid awareness, and good communication skills. Therefore, the standardized construction of emergency is an important principle to ensure that critically ill children receive timely and effective treatment. Among them, correct pre-examination and triage plays a key role in the effective diagnosis and treatment. Pre-examination and triage is based on the principles of disease severity and treatment priority, and the principle of rational use of emergency resources to quickly classify patients and clarify the treatment priority.

[0003] At present, the pre-examination triage classification of emergency departments mainly relies on manual triage. During the peak period of pediatric emergency visits, the efficiency of manual triage is low, and the triage process is easily affected by the special characteristics of the pediatric population. The accuracy of triage needs to be improved. In addition, when conducting pre-examination triage, most of the classifications are determined through a single triage. After the classification is determined, the waiting time for visits during the peak period of emergency visits shows an increasing trend. In this process, there may be a variety of variable factors, such as changes in the patient's illness status, and an increase in the examination time due to the patient's non-cooperation during the examination. Therefore, the current pediatric emergency pre-examination triage relies on manual single triage, which has the problem of low triage efficiency. In addition, during the triage process, only the single patient classification information corresponding to the child patient is considered, and the variable factors generated during the actual waiting process are not considered, which increases the hidden dangers in the waiting process of queuing for treatment. Summary of the invention

[0004] One or more embodiments of the present specification provide a method, device and medium for pre-examination and triage of pediatric emergency, which are used to solve the following technical problems: the current pre-examination and triage of pediatric emergency relies on manual single triage, which has the problem of low triage efficiency, and only considers the single patient classification information corresponding to the child patient during the triage process, without considering the variable factors generated during the actual waiting process for the consultation, which increases the hidden dangers of queuing for the consultation.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of the present specification provide a method for pre-examination and triage of pediatric emergency departments, the method comprising: obtaining multi-source medical data of each pediatric emergency patient to construct a current pre-examination and triage data set corresponding to each of the pediatric emergency patients, wherein the multi-source medical data comprises chief complaint information, demographic information of the pediatric emergency patient, and clinical sign information of the pediatric emergency patient; matching in a pre-constructed model library according to the demographic information of the pediatric emergency patient to determine an age-group pre-examination intelligent triage model corresponding to each of the pediatric emergency patients, and generating initial triage and classification information for each of the pediatric emergency patients based on the current pre-examination and triage data set and the age-group pre-examination intelligent triage model; information; when the initial triage classification information is at a non-critical level, based on the initial triage classification information of each of the emergency pediatric patients, determine the emergency area to which each of the emergency pediatric patients belongs, so as to collect the real-time consultation queue information of the current regional queue of the emergency area to which they belong; based on the real-time consultation queue information of the current regional queue, predict the disease evolution risk of each of the emergency pediatric patients, and determine the predicted classification change trend information of each of the emergency pediatric patients; through the predicted classification change trend information of each of the emergency pediatric patients, make real-time adjustments to the visiting area and visiting order of each of the emergency pediatric patients, and determine the real-time triage information of each of the emergency pediatric patients.

[0007] One or more embodiments of this specification provide a pre-examination and triage device for children's emergency department, including:

[0008] at least one processor; and,

[0009] a memory communicatively connected to the at least one processor; wherein,

[0010] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above method.

[0011] One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0012] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: through the above technical solution, by integrating multi-source medical data such as chief complaint information, demographic information and clinical sign information, a more comprehensive understanding of the patient's condition and background can be obtained, thereby improving the accuracy of triage; matching is performed in a pre-built model library according to the patient's demographic information, and the most suitable age-group pre-examination intelligent triage model is selected, further improving the pertinence and accuracy of triage; based on the real-time consultation queue information and the predicted results of the disease evolution risk, the patient's treatment area and sequence are adjusted in real time, making the emergency process more flexible and efficient, and for patients whose conditions may deteriorate rapidly, they can be given priority to arrange treatment, significantly reducing their waiting time and improving medical efficiency. In this process, the non-cooperation factors of waiting children in the waiting process are taken into account through the real-time consultation queue information, and the indicator change factors of emergency pediatric patients are taken into account through the predicted graded change trend information; by predicting the risk of disease evolution, those patients whose conditions may deteriorate can be identified in advance, so as to take timely intervention measures to avoid further deterioration of the condition, and give priority treatment to high-risk patients according to the predicted results to ensure patient safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0014] Figure 1 A flowchart of a method for pre-examination and triage of pediatric emergency department provided in an embodiment of this specification;

[0015] Figure 2 This is a schematic diagram of the structure of a pediatric emergency pre-examination and triage device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0017] The embodiments of this specification provide a method for pre-examination and triage of pediatric emergency. It should be noted that the execution subject in the embodiments of this specification can be a server or any device with data processing capabilities. Figure 1 A flowchart of a method for pre-examination and triage of pediatric emergency department provided in the embodiment of this specification is shown in FIG. Figure 1 As shown, it mainly includes the following steps:

[0018] Step S101, obtaining multi-source medical data of each emergency pediatric patient to construct a current pre-examination and triage data set corresponding to each emergency pediatric patient.

[0019] In one embodiment of the present specification, multi-source medical data of each emergency pediatric patient is obtained, and the multi-source medical data here includes the chief complaint information, the demographic information of the emergency pediatric patient, and the clinical sign information of the emergency pediatric patient. It should be noted that the chief complaint data refers to a brief description of the patient's medical history or symptoms, such as systemic symptoms such as fever and fatigue, respiratory symptoms such as cough, sore throat, runny nose, and hemoptysis, digestive system symptoms such as abdominal pain, diarrhea, blood in the stool, vomiting blood, vomiting, circulatory system symptoms such as cyanosis of the face, lips, nail beds, palpitations, palpitations, and precordial pain, nervous system: dizziness, headache, loss of consciousness, abnormal behavior, mental abnormality, abnormal movement and other nervous system symptoms, frequent urination, urgency, urinary pain, lumbar colic and other urinary system symptoms. In general, the chief complaint data is expressed by the patient, but since the patient object in the embodiment of the present specification is a child, there is a particularity of language expression. Therefore, the chief complaint data in the embodiment of the present specification is divided into two cases, one is the patient himself who has the ability to express himself, and the other is the expression of the accompanying caregiver. The demographic information of emergency pediatric patients includes age, gender, etc. Clinical sign information refers to the physical examination and preliminary sign collection information obtained during the emergency pre-examination transaction, for example, general characteristics such as height and weight, vital signs such as pulse, blood pressure, heart rate, respiratory rate, and blood oxygen saturation, bladder irritation signs such as frequent urination, urgency, and pain, peritoneal irritation signs such as tenderness, rebound pain, and abdominal muscle tension, meningeal irritation signs such as neck stiffness, Kernig's sign, and Brudzinski's sign, and intracranial hypertension characteristics such as headache, vomiting, and papilledema.

[0020] In actual application scenarios, the chief complaint information is generally provided by the conscious patient himself. However, due to the particularity of the language expression of child patients, there may be problems with imperfect language expression. The chief complaint information corresponding to child patients should be corrected in combination with the chief complaint information of the accompanying caregiver to ensure the accuracy of the chief complaint data.

[0021] Obtain multi-source medical data of each emergency child patient to construct the current pre-examination and triage data set corresponding to each emergency child patient, specifically including: first, obtain multiple chief complaint text data in the chief complaint information of each emergency child patient, and determine the data source of each chief complaint text data; the data source here includes any one or more of the child patient and the accompanying caregiver. According to the data source, the chief complaint text data is classified to obtain the chief complaint text subset corresponding to each data source; through the demographic information of the emergency child patient and the preset age group chief complaint correction parameter table, the current reference weight corresponding to each data source is determined, wherein the age group chief complaint correction parameter table includes multiple age groups and the reference weight information of each data source corresponding to each age group, and the age group includes infant age group, school age group and adolescent age group.

[0022] It should be noted that children are divided into multiple age groups in advance according to their cognitive levels and expression abilities, including infants and toddlers aged 0-3, school-age children aged 6-12, and adolescents aged 12-18. According to the cognitive levels and expression abilities of children in each age group, reference weight information of different data sources in each age group is set. For example, infants and toddlers are often unable to express their discomfort in words, and therefore rely mainly on their parents' observations and descriptions. Therefore, the reference weight of the care source corresponding to this age group is set to 1, and the reference weight of the child patient source is set to 0; school-age children begin to be able to express their feelings in simple language, but may not be accurate or comprehensive enough. Therefore, the reference weight of the care source corresponding to this age group is set to a weight greater than 0.5, such as 0.6, and the reference weight of the child patient source can be set to 1-0.6, that is, 0.4; children in the adolescent age group already have strong self-awareness and expression ability, and can describe their symptoms and needs more accurately. The reference weight of the child patient source corresponding to this age group is set to a weight greater than 0.5, such as 0.8, and the reference weight of the care source can be set to 1-0.8, that is, 0.2, so as to construct the age group chief complaint correction parameter table. According to the current reference weight corresponding to each data source, at least one subset of the chief complaint text is corrected to determine the chief complaint correction information; based on the chief complaint correction information and the clinical sign information, a current pre-examination and triage data set corresponding to each emergency pediatric patient is constructed.

[0023] According to the current reference weight corresponding to each of the data sources, at least one of the chief complaint text subsets is corrected to determine the chief complaint correction information, specifically including: according to the current reference weight corresponding to each of the data sources, a reference weight comparison is performed to determine the first chief complaint text subset corresponding to the first data source and the second chief complaint text subset corresponding to the second data source, wherein the current reference weight of the first data source is greater than the second chief complaint text subset; according to the demographic information of the emergency pediatric patient, the corresponding chief complaint age group of the emergency pediatric patient and the corresponding age group correction method are determined, wherein the age group correction method includes semantic extension replacement correction and linguistic any one of the semantic superposition corrections; when the age group correction method is semantic extension replacement, the field of the chief complaint text in the second chief complaint text subset is split to obtain multiple second chief complaint text fields; according to the corresponding chief complaint age group of the emergency pediatric patient, the corresponding field set is matched, wherein the field set includes the standard texts corresponding to multiple high-frequency fuzzy chief complaint texts of the belonging chief complaint age group; the second chief complaint text field is semantically expanded, and semantic replacement is performed according to the field set to determine the correction of the second chief complaint text subset; based on the first chief complaint text subset, the second chief complaint text subset is superimposed to determine the chief complaint correction information.

[0024] In one embodiment of the present specification, the first chief complaint text subset refers to a subset with a larger current reference weight of the data source, and the second chief complaint text subset refers to a subset with a smaller current reference weight of the data source. According to the patient age of the emergency pediatric patient, the corresponding chief complaint age group of the pediatric patient is determined, and the age group correction method corresponding to the chief complaint age group is determined through the expert database and other means, wherein the age group correction method includes any one of the semantic extension replacement correction and the semantic superposition correction. Generally, when the chief complaint age group belongs to the infant age group, the first chief complaint text subset is the chief complaint data from the accompanying source. In this case, since children in the infant age group do not have the ability to express themselves in language, the second chief complaint text subset is empty and the first chief complaint text subset does not need to be corrected. When the age range of the chief complaint belongs to the school age range, the patient has the problem of incomplete or inaccurate expression. The first chief complaint text subset is the chief complaint data from the caregiver, and the second chief complaint text subset is the chief complaint data from the child patient. Therefore, it is necessary to semantically extend and replace the second chief complaint text subset, and then superimpose it with the first chief complaint text subset, that is, the corresponding age correction method is semantic extension and replacement correction. When the age range of the chief complaint belongs to the adolescent age range, the patient can describe his or her symptoms and needs more accurately. The first chief complaint text subset is the chief complaint data from the child patient, and the second chief complaint text subset is the chief complaint data from the caregiver. Therefore, it only needs to be superimposed on the two to achieve the correction method corresponding to the semantic superposition correction.

[0025] When the age correction method is semantic extension replacement, the field of the main complaint text in the second main complaint text subset is split to obtain multiple second main complaint text fields; according to the corresponding main complaint age of the emergency pediatric patient, the corresponding field set is matched, wherein the field set includes the standard text corresponding to multiple high-frequency fuzzy main complaint texts of the main complaint age, and the field set can be determined by using the expression text replacement database pre-built with the language expression ability corresponding to each age group in historical situations. For example, when a child patient of a certain age group expresses headache, multiple samples show the problem of inaccurate pronunciation of the head. At this time, the corresponding relationship between the annotated texts of multiple fuzzy pronunciation texts of "head" can be established in the expression text replacement database. The second main complaint text field is semantically extended and expanded, and semantic replacement is performed according to the field set to determine the correction of the second main complaint text subset. Based on the first main complaint text subset, the second main complaint text subset is superimposed to determine the main complaint correction information.

[0026] By distinguishing the data sources (child patients and accompanying caregivers) and assigning different reference weights to data from different sources, the patient's true condition can be more accurately reflected, because data from different sources may have different subjectivity and accuracy. For example, child patients may not be able to accurately describe their symptoms. By using the preset age-group chief complaint correction parameter table, the weight of the data source is adjusted according to the patient's age group, and personalized processing of the data is achieved. Children of different age groups have differences in expression ability and cognitive level. Such differences are fully considered in pre-examination and triage to ensure the accuracy of triage results; by constructing a current pre-examination and triage data set based on chief complaint correction information and clinical sign information, emergency triage work can be more effectively guided, the efficiency and accuracy of triage can be improved, and the medical risks caused by misdiagnosis or missed diagnosis can be reduced.

[0027] Step S102, according to the demographic information of emergency pediatric patients, matching is performed in a pre-constructed model library to determine the age group pre-examination intelligent triage model corresponding to each emergency pediatric patient, so as to generate the initial triage grading information for each emergency pediatric patient based on the current pre-examination triage data set and the age group pre-examination intelligent triage model.

[0028] According to the demographic information of the emergency pediatric patient, matching is performed in a pre-constructed model library to determine the age group pre-examination intelligent triage model corresponding to each of the emergency pediatric patients, the method also includes: collecting historical patient multi-source data and corresponding historical post-diagnosis grading information corresponding to multiple historical emergency pediatric patients who visited the emergency department for the first time within a specified historical time period; classifying the multiple historical patient multi-source data according to the age of each of the historical emergency pediatric patients, and determining a historical multi-source data set of patients of the same age corresponding to each unit age; extracting features from each of the historical multi-source data sets of patients of the same age and the corresponding historical post-diagnosis grading information, and determining multiple historical visit features and corresponding grading features; and performing feature extraction on the multiple historical visit features and the grading features. Feature correlation analysis is performed to determine the corresponding feature correlation coefficient of patients of the same age; based on the feature correlation coefficient of each patient of the same age, the unit age is combined for emergency children to determine multiple feature-related age groups, wherein the feature correlation coefficient of patients of the same age corresponding to each feature-related age group meets the preset requirements; according to the multiple feature-related age groups and the multi-source data sets of historical patients of the same age corresponding to each unit age, a multi-source data set of patients of historical age groups corresponding to each feature-related age group is constructed; based on each multi-source data set of patients of the historical age group and the corresponding historical post-diagnosis grading information, a pre-examination intelligent triage model corresponding to each feature-related age group is constructed; according to the feature-related age group, a model identifier is set for the pre-examination intelligent triage model to construct the model library.

[0029] For example, historical patient multi-source data and corresponding historical post-diagnosis grading information corresponding to multiple historical emergency pediatric patients who visited the emergency department for the first time in the past five years are collected. The historical post-diagnosis grading information here may include the prognosis outcome. According to the age of each historical emergency pediatric patient, the multiple historical patient multi-source data are classified to determine the historical multi-source data set of patients of the same age corresponding to each unit age, such as under 1 year old, 1-2 years old, 2-3 years old, and so on, to obtain 18 historical multi-source data sets of patients of the same age. Feature extraction is performed on each historical multi-source data set of patients of the same age and the corresponding historical post-diagnosis grading information respectively, and multiple historical visit features and corresponding grading features are determined. Feature correlation analysis is performed on multiple historical visit features and grading features to determine the corresponding correlation coefficient of the characteristics of patients of the same age. It should be noted that when performing the correlation analysis here, the correlation between each historical visit feature and the grading feature is analyzed by using statistical methods (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.) to analyze the correlation between the historical visit feature and the grading feature, determine the correlation coefficient between the historical visit feature and the grading feature, and determine the significant visit feature that is significantly associated with the post-diagnosis grading. According to the above steps, the significant visit characteristics and the correlation coefficients between the historical visit characteristics and the grading characteristics corresponding to the 18 historical multi-source data sets of patients of the same age are obtained. According to the correlation coefficients between the significant visit characteristics and the historical visit characteristics and the grading characteristics, the 18 historical multi-source data sets of patients of the same age are analyzed to find age groups with similar or identical characteristic correlation coefficients. According to the similarity of the characteristic correlation coefficients or the preset error range, the age groups are merged into characteristic-related age groups to determine multiple characteristic-related age groups, and the characteristic correlation coefficients of the patients of the same age in each age group should be the same or similar within the preset error range. It should be noted that the division method of the characteristic-related age groups here is different from the age group division in step S101, and due to the differences in the regional locations of the emergency clinics, there are differences in the data sources, so the results of the corresponding characteristic-related age groups are different for the emergency clinics in different regional locations.

[0030] According to multiple feature-related age groups, the multi-source data sets of historical patients of the same age corresponding to each unit age are combined to construct a multi-source data set of patients in historical age groups corresponding to each feature-related age group. Based on the multi-source data set of patients in each historical age group and the corresponding historical post-diagnosis grading information, a pre-examination intelligent triage model corresponding to each feature-related age group is constructed. The multi-source data set of patients in the historical age group is cleaned to remove duplicate, erroneous or irrelevant records, handle missing values, and perform necessary formatting and standardization. According to the historical post-diagnosis grading information, the data of each patient is labeled to ensure that there is a clear supervision signal during model training. For the pre-examination triage of emergency pediatric patients, classification algorithms (such as decision trees and support vector machines) can be used. The selected model is trained using the labeled data set. During the training process, the parameters of the model need to be adjusted to optimize its performance. The performance of the model is evaluated by methods such as cross-validation, and the model is tuned according to the evaluation results. At the same time, it is also necessary to avoid overfitting and underfitting problems. The process of model construction can refer to the existing intelligent triage model, which will not be repeated here. According to the feature-related age group, the model identifier is set for the pre-examination intelligent triage model to build the model library.

[0031] In one embodiment of the present specification, according to the age in the demographic information of the emergency pediatric patient, a match is made in the pre-built model library to determine the age-group pre-examination intelligent triage model corresponding to each emergency pediatric patient, so as to generate the initial triage and classification information for each emergency pediatric patient based on the current pre-examination and triage data set and the age-group pre-examination intelligent triage model. Children of different age groups have differences in disease manifestations, physiological reactions, and psychological states. By matching the pre-examination intelligent triage model suitable for their age group, the patient's condition can be more accurately assessed, and misdiagnosis or missed diagnosis caused by age differences can be reduced. By matching the pre-examination intelligent triage model suitable for the patient's age group, more personalized medical services can be provided to patients, meeting the needs of patients and improving the quality and effectiveness of medical services.

[0032] Step S103, when the initial triage classification information is at a non-critical level, the emergency area to which each emergency pediatric patient belongs is determined based on the initial triage classification information of each emergency pediatric patient, so as to collect the real-time consultation queue information of the current area queue of the emergency area to which the patient belongs.

[0033] In one embodiment of the present specification, the classification of the initial triage classification information can be endangered level, critical level, emergency level and non-emergency level. Since the endangered level requires immediate evaluation and treatment, the patient is arranged to enter the resuscitation room or emergency room, which is time-sensitive and there is almost no waiting. Therefore, the embodiment of the present specification performs real-time triage adjustment for the non-endangered level.

[0034] When the initial triage and grading information is at a non-critical level, the initial rescue response information of the emergency pediatric patient is determined based on the initial triage and grading information of each emergency pediatric patient, wherein the initial rescue response information includes the response procedure, response time and response location. Based on the initial rescue response information, the emergency area to which each emergency pediatric patient belongs is determined. It should be noted that the belonging emergency area here is a functional partition. There is at least one regional queue in each belonging emergency area. The regional queue here is determined according to the medical resources in the belonging emergency area. The queue with the least number of people is determined as the current regional queue through the number of people in each regional queue. The position of this patient in the current regional queue can be determined according to the initial triage and grading information of the emergency pediatric patient. Generally, it is set at the end of the current regional queue. Since the corresponding initial triage and grading information in this regional queue is the same, it is usually sorted by time, but in an emergency, it can be set at a designated position in the regional queue to shorten the waiting time. In the current regional queue, the real-time consultation queue information of the current regional queue is collected. It should be noted that there is more than one regional queue corresponding to each emergency pediatric patient, for example, a doctor diagnosis queue, an equipment inspection queue, etc. The embodiment of this specification is described with one regional queue.

[0035] According to the patient's initial triage classification, allocating patients to emergency areas of different levels can ensure a more reasonable allocation of medical resources; non-critical patients can wait for treatment in relatively less urgent areas, while critically ill patients can receive priority treatment; by collecting real-time consultation queue information belonging to the emergency area in real time, the hospital can more accurately grasp the waiting situation in each area, thereby dynamically adjusting resources and reducing patients' waiting time; based on the initial triage classification information, patients can be quickly allocated to the corresponding emergency area, which helps shorten the triage process and improve triage efficiency; by subdividing the emergency area, doctors can focus more on dealing with patients in their respective areas, thereby improving the accuracy and quality of diagnosis and treatment.

[0036] Step S104, based on the real-time consultation queue information of the current regional queue, predict the disease evolution risk of each emergency pediatric patient, and determine the predicted grade change trend information of each emergency pediatric patient.

[0037] Based on the waiting queue information of the current regional queue, the risk of disease evolution of each emergency pediatric patient is predicted, and the predicted grade change trend information of each emergency pediatric patient is determined, specifically including: determining the expected waiting time of each emergency pediatric patient based on the waiting queue information of the current regional queue; predicting multiple clinical signs information of each emergency pediatric patient in real time according to the expected waiting time of each emergency pediatric patient, and determining multiple corresponding predicted signs change information; determining real-time predicted grade information based on the multiple predicted signs change information and the pre-examination intelligent triage model for the age group; performing an indicator comparison between the multiple predicted signs change information and the clinical signs information, and determining the corresponding indicator change range, so as to generate a predicted indicator change trend through the multiple indicator change ranges; on the basis of the predicted indicator change trend, determining the predicted grade change trend information of each emergency pediatric patient according to the real-time predicted grade information.

[0038] In one embodiment of the present specification, based on the waiting queue information of the current regional queue, the estimated waiting time of each child emergency patient is determined, specifically including: obtaining the waiting order information in the waiting queue information, the waiting patient information of each waiting patient, and the regional medical resource information, and the waiting patient information includes the patient's age data and the child's pre-examination and triage data. It should be noted that the waiting child here refers to the child who is located before the emergency child patient and needs to share the same medical resources; the child's pre-examination and triage data can be the current pre-examination and triage data set corresponding to the waiting child in the initial stage, which refers to the child's clinical sign information and the corrected chief complaint correction information, and can also include the initial triage and classification information of the waiting child. The corresponding current child treatment strategy is matched with the pre-examination and triage data of each waiting child, wherein the current child treatment strategy has at least one diagnosis and treatment medical resource, and the diagnosis and treatment medical resources include medical care resources, medical equipment resources, etc., which can be determined according to the initial triage information. Generally, the diagnosis and treatment medical resources corresponding to the waiting children belonging to the same waiting queue overlap. In the embodiment of the present specification, this waiting queue refers to a queuing queue that shares the same diagnosis and treatment medical resources.

[0039] According to the age data of the child and the current diagnosis and treatment strategy of each waiting child, a match is made in the preset patient cooperation index mapping table to determine the current consultation cooperation index of each waiting child. The current consultation cooperation index is used to indicate the degree of consultation cooperation of the waiting child under the current diagnosis and treatment strategy. The time difference generated by different waiting children can be estimated through the degree of consultation cooperation. The current diagnosis and treatment efficiency information corresponding to the regional medical resource information is collected. Different doctors have different consultation times. By collecting the current diagnosis and treatment efficiency information corresponding to the regional medical resource information, the diagnosis and treatment differences of the regional medical resource information can be met. The current diagnosis and treatment efficiency information can be represented by the average duration of regional medical resources for each child. Based on the current diagnosis and treatment efficiency information and the current consultation cooperation index of each waiting child, the predicted consultation time of each waiting child is generated. The predicted consultation time of each waiting child is obtained by multiplying the average duration of regional medical resources for each child and the current consultation cooperation index of the waiting child. Through the waiting order information, multiple designated waiting children who are ahead of the emergency child patient are determined, and the estimated waiting time of each emergency child patient is determined through the predicted consultation time of multiple designated waiting children. Here, the predicted consultation time of multiple designated waiting children is added, and the time correction value is added on this basis to obtain the estimated waiting time of each emergency child patient. The time correction value is used to represent the time consumed when the order of waiting children is changed, and can be calculated by the following formula: Among them, T is the expected waiting time for each emergency child patient, i is the i-th waiting child in the current waiting queue, and there are n waiting children before this emergency child patient, S average is the average time for each patient to be treated by the current regional medical resources, α i is the current consultation cooperation index of each waiting child, and Δt is the corresponding time correction value when two adjacent children alternate.

[0040] In one embodiment of the present specification, according to the age data of the patient and the current diagnosis and treatment strategy of each waiting patient, a match is made in the preset patient cooperation index mapping table to determine the current consultation cooperation index of each waiting patient, specifically including: collecting multiple historical diagnosis and treatment data corresponding to each patient's diagnosis and treatment strategy, and analyzing the diagnosis and treatment time information in the multiple historical diagnosis and treatment data based on statistical analysis technology to determine the average diagnosis and treatment time corresponding to each of the patient's diagnosis and treatment strategies. It should be noted that the diagnosis and treatment strategy of the patient here refers to the average diagnosis and treatment time corresponding to the operation difference of medical resources without considering the diagnosis and treatment strategy, which should be consistent with S average There is a difference between the two. average is the average time for each patient to be treated by the current regional medical resources, for example, the average treatment time for ultrasound examination, which is the average treatment time without considering the operating medical staff, Saverage The average length of time that the current medical staff who perform ultrasound examinations spend treating each child.

[0041] In the multiple historical diagnosis and treatment data, the age-average diagnosis and treatment time corresponding to each patient's age is determined through the age information of the diagnosis and treatment object corresponding to each historical diagnosis and treatment data, and the aggregated average diagnosis and treatment time corresponding to each patient's age is counted and divided by the number of patients of this patient's age to obtain the age-average diagnosis and treatment time corresponding to each patient's age. Based on the age-average diagnosis and treatment time t1 corresponding to each patient's age and the average diagnosis and treatment time t2 corresponding to the diagnosis and treatment strategy of the patient, the consultation cooperation index α corresponding to the diagnosis and treatment strategy of the patient's age is determined. i It can be calculated by the following formula: A patient cooperation index mapping table is constructed by using the consultation cooperation index of the patient's age corresponding to each patient's diagnosis and treatment strategy. According to the current patient diagnosis and treatment strategy of each waiting patient and the patient's age data of each waiting patient, a match is made in the patient cooperation index mapping table to determine the current consultation cooperation index of each waiting patient.

[0042] In one embodiment of the present specification, based on the waiting queue information of the current regional queue, the estimated waiting time of each child emergency patient is determined, and according to the estimated waiting time of each child emergency patient, multiple clinical signs information of each child emergency patient is predicted in real time to determine the corresponding multiple predicted signs change information. The historical data in the hospital information system (HIS), including the medical records, diagnosis results, treatment plans, vital signs monitoring data (such as heart rate, blood pressure, body temperature, blood oxygen saturation, etc.) and waiting time of children with different conditions, are used to analyze the possible sign changes of children with similar conditions within similar waiting times; the clinical experience and knowledge of pediatric emergency experts are collected, including common disease diagnosis pathways, sign change patterns and treatment measures, and a prediction model is constructed in combination with clinical experience and expert knowledge base to predict the changes in children's signs in real time, and a linear regression prediction model is used to predict the continuously changing sign values. Based on multiple predicted sign change information and the pre-examination intelligent triage model for this age group, real-time predicted grading information is determined. The multiple predicted sign change information and the clinical sign information are compared to determine the corresponding indicator change range. The indicator change range here can be determined by the difference between the predicted sign change information and the clinical sign information, with positive and negative indicator differences. Through multiple indicator change ranges, a predicted indicator change trend is generated. The predicted indicator change trend can be presented in the form of a trend chart, with the horizontal axis being time information and the vertical axis being the indicator change range. Based on the predicted indicator change trend, the predicted grade change trend information of each emergency pediatric patient is determined according to the real-time predicted grade information. The predicted grade change trend information here includes the predicted indicator change trend and the real-time predicted grade information.

[0043] Based on the real-time consultation queue information of the current regional queue, the risk of disease evolution of each emergency pediatric patient is predicted. By predicting the patient's indicator evolution risk, patients with indicator changes can be identified in advance, so that timely intervention measures can be taken to avoid further deterioration of the condition. For patients whose predicted graded change trends show that their condition may deteriorate, the hospital can give priority to treatment to ensure that the patient receives timely and effective treatment. According to the patient's condition evolution risk prediction results, medical resources, such as medical staff, medical equipment and drugs, can be allocated more reasonably to ensure the most effective use of resources. Over-medicalization of patients with stable or slightly deteriorating conditions is avoided, thereby reducing unnecessary waste of medical resources.

[0044] Step S105, based on the predicted grade change trend information of each emergency child patient, the visiting area and visiting sequence of each emergency child patient are adjusted in real time to determine the real-time triage information of each emergency child patient.

[0045] Through the predicted grading change trend information of each emergency child patient, the visiting area and visiting order of each emergency child patient are adjusted in real time to determine the real-time triage information of each emergency child patient, specifically including: obtaining the prediction index change trend and real-time prediction grading information in the predicted grading change trend information; when the real-time prediction grading information is the same as the initial triage grading information, determining the change rate of the prediction index change trend, when the prediction index change trend is a curve graph, the change rate can be determined by the slope of a certain point; when the change rate of the prediction index change trend is greater than the preset threshold, adjusting the visiting order of the emergency child patient in the current area queue; the setting of the preset threshold can be determined by the influence of the change speed of each indicator of the medical expert database on the change of the disease. When the real-time prediction grading information is different from the initial triage grading information, the visiting area of ​​the emergency child patient is adjusted according to the real-time prediction grading information.

[0046] When the real-time predicted classification information is different from the initial triage classification information, or the rate of change of the predicted indicator trend exceeds the preset threshold, the patient's treatment order or area can be adjusted quickly to ensure that high-risk patients are given priority and their condition is prevented from worsening; continuous monitoring and prediction of changes in the patient's condition enable medical staff to make decisions based on the latest information, thereby improving the protection of patient safety; dynamic adjustment of the treatment order and area based on the predicted results makes the medical process more flexible and efficient, reducing the long waiting time or idle resources caused by a fixed treatment order; for patients whose condition may deteriorate rapidly, their waiting time is significantly reduced by arranging treatment in advance, thereby improving their medical experience; patients are assigned to the most appropriate treatment area based on the severity of their condition and the predicted trend of change, ensuring accurate matching and efficient use of medical resources; reducing the excessive use or idleness of medical resources due to misdiagnosis or misjudgment, and improving the overall utilization efficiency of medical resources.

[0047] Through the above technical solutions, by integrating multi-source medical data such as chief complaint information, demographic information and clinical sign information, a more comprehensive understanding of the patient's condition and background can be achieved, thereby improving the accuracy of triage; matching is performed in the pre-built model library according to the patient's demographic information, and the most suitable age-group pre-examination intelligent triage model is selected, further improving the pertinence and accuracy of triage; based on the real-time consultation queue information and the predicted results of the disease evolution risk, the patient's treatment area and sequence are adjusted in real time, making the emergency process more flexible and efficient. For patients whose conditions may deteriorate rapidly, they can be given priority to see a doctor, significantly reducing their waiting time and improving medical efficiency. In this process, the non-cooperation factors of waiting children in the waiting process are taken into account through the real-time consultation queue information, and the indicator change factors of emergency pediatric patients are taken into account through the predicted graded change trend information; by predicting the risk of disease evolution, patients whose conditions may deteriorate can be identified in advance, so that timely intervention measures can be taken to avoid further deterioration of the condition. According to the predicted results, high-risk patients are given priority treatment to ensure patient safety.

[0048] The present specification also provides a pre-diagnosis and triage device for children's emergency department, such as Figure 2 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0049] The embodiments of the present specification also provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0050] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0051] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The devices and media provided in the embodiments of this specification correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0053] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0054] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0055] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0056] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0057] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0058] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0059] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0060] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0061] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A pre-examination and triage method for pediatric emergency, characterized in that: The method comprises: Acquire multi-source medical consultation data of each emergency pediatric patient to construct a current pre-examination triage data set corresponding to each of the emergency pediatric patients, wherein the multi-source medical consultation data includes chief complaint information, demographic information of the emergency pediatric patient, and clinical sign information of the emergency pediatric patient; According to the demographic information of the emergency pediatric patients, matching is performed in a pre-constructed model library to determine the age-group pre-examination intelligent triage model corresponding to each of the emergency pediatric patients, so as to generate initial triage and classification information for each of the emergency pediatric patients based on the current pre-examination and triage data set and the age-group pre-examination intelligent triage model; When the initial triage classification information is at a non-critical level, determining the emergency area to which each emergency child patient belongs based on the initial triage classification information of each emergency child patient, so as to collect the real-time consultation queue information of the current regional queue of the emergency area to which the patient belongs; Based on the real-time consultation queue information of the current regional queue, predict the risk of disease evolution of each of the emergency pediatric patients, and determine the predicted grade change trend information of each of the emergency pediatric patients; By using the predicted grade change trend information of each of the emergency child patients, the visiting area and visiting sequence of each of the emergency child patients are adjusted in real time to determine the real-time triage information of each of the emergency child patients.

2. A method for pre-examination and triage of pediatric emergency according to claim 1, characterized in that: Obtain multi-source medical data of each emergency pediatric patient to construct a current pre-examination and triage data set corresponding to each emergency pediatric patient, specifically including: Acquire multiple main complaint text data in the main complaint information of each emergency pediatric patient, and determine the data source of each main complaint text data; Classifying the chief complaint text data according to the data source to obtain a chief complaint text subset corresponding to each data source, wherein the data source includes any one or more of the child patient and the accompanying caregiver; Determine the current reference weight corresponding to each of the data sources through the demographic information of the emergency pediatric patients and the preset age-group chief complaint correction parameter table, wherein the age-group chief complaint correction parameter table includes multiple age groups and reference weight information of each of the data sources corresponding to each age group, and the age groups include infant age group, school age group and adolescent age group; According to the current reference weight corresponding to each of the data sources, at least one of the chief complaint text subsets is modified to determine the chief complaint modification information; Based on the chief complaint correction information and the clinical sign information, a current pre-examination and triage data set corresponding to each of the emergency pediatric patients is constructed.

3. A method for pre-examination and triage of pediatric emergency according to claim 2, characterized in that: According to the current reference weight corresponding to each of the data sources, at least one of the chief complaint text subsets is modified to determine the chief complaint modification information, specifically including: According to the current reference weight corresponding to each of the data sources, a reference weight comparison is performed to determine a first main complaint text subset corresponding to the first data source and a second main complaint text subset corresponding to the second data source, wherein the current reference weight of the first data source is greater than that of the second main complaint text subset; Determine the age range of the chief complaint of the emergency pediatric patient and the corresponding age range correction method according to the demographic information of the emergency pediatric patient, wherein the age range correction method includes any one of semantic extension replacement correction and semantic superposition correction; When the age group correction method is semantic extension replacement, the main complaint text in the second main complaint text subset is field-split to obtain multiple second main complaint text fields; According to the age range of the chief complaint of the emergency pediatric patient, a corresponding field set is matched, wherein the field set includes standard texts corresponding to a plurality of high-frequency fuzzy chief complaint texts of the age range of the chief complaint; Performing semantic expansion on the second main complaint text field, and performing semantic replacement according to the field set to determine and modify the second main complaint text subset; The first chief complaint text subset is used as a basis and the second chief complaint text subset is superimposed to determine the chief complaint correction information.

4. A method for pre-examination and triage of pediatric emergency according to claim 1, characterized in that: According to the demographic information of the emergency pediatric patients, matching is performed in a pre-constructed model library to determine the age group pre-examination intelligent triage model corresponding to each of the emergency pediatric patients, and the method further includes: Collect historical patient multi-source data and corresponding historical post-diagnosis classification information corresponding to multiple historical emergency pediatric patients who visited the emergency department for the first time within a specified historical time period; Classifying the plurality of multi-source data of historical patients according to the age of each of the historical emergency pediatric patients, and determining a multi-source data set of historical patients of the same age corresponding to each unit age; Extracting features from each of the multi-source data sets of patients of the same age and the corresponding historical post-diagnosis grading information, respectively, to determine a plurality of historical diagnosis features and corresponding grading features; Performing feature correlation analysis on the multiple historical medical visit features and the grading features to determine corresponding feature correlation coefficients of patients of the same age; According to the characteristic correlation coefficient of each patient of the same age, the unit age is combined for the emergency children to determine a plurality of characteristic-related age groups, wherein the characteristic correlation coefficient of the patient of the same age corresponding to each characteristic-related age group meets the preset requirements; According to the plurality of feature-related age groups and the multi-source data sets of historical patients of the same age corresponding to each unit age, construct a multi-source data set of historical patients of age groups corresponding to each feature-related age group; Based on the multi-source data set of patients in each of the historical age groups and the corresponding historical post-diagnosis grading information, construct a pre-examination intelligent triage model corresponding to each of the feature-related age groups; According to the feature-related age groups, a model identifier is set for the pre-examination intelligent triage model to construct the model library.

5. A method for pre-examination and triage of pediatric emergency according to claim 1, characterized in that: Based on the waiting queue information of the current regional queue, the risk of disease progression of each of the emergency pediatric patients is predicted, and the predicted grade change trend information of each of the emergency pediatric patients is determined, specifically including: Determine the estimated waiting time of each of the emergency pediatric patients based on the waiting queue information of the current regional queue; According to the estimated waiting time of each of the emergency pediatric patients, multiple clinical signs information of each of the emergency pediatric patients are predicted in real time to determine corresponding multiple predicted signs change information; Determining real-time predicted grading information based on the multiple predicted physical sign change information and the age group pre-examination intelligent triage model; Comparing the plurality of predicted physical sign change information with the clinical physical sign information, and determining the corresponding index change ranges, so as to generate a predicted index change trend through the plurality of index change ranges; Based on the change trend of the prediction index, the prediction grade change trend information of each of the emergency pediatric patients is determined according to the real-time prediction grade information.

6. A method for pre-examination and triage of pediatric emergency according to claim 5, characterized in that: Based on the waiting queue information of the current regional queue, the estimated waiting time of each emergency pediatric patient is determined, specifically including: Obtaining the waiting order information, waiting patient information of each waiting patient, and regional medical resource information in the waiting queue information, wherein the waiting patient information includes the patient's age data and the patient's pre-examination and triage data; Matching the corresponding current diagnosis and treatment strategy for the child through the pre-examination and triage data of each waiting child, wherein the current diagnosis and treatment strategy for the child has at least one diagnosis and treatment medical resource; According to the patient age data and the current patient diagnosis and treatment strategy of each of the waiting patients, matching is performed in a preset patient cooperation index mapping table to determine the current consultation cooperation index of each of the waiting patients; Collecting the current diagnosis and treatment efficiency information corresponding to the regional medical resource information, and generating the predicted consultation time of each waiting patient based on the current diagnosis and treatment efficiency information and the current consultation cooperation index of each waiting patient; The plurality of designated waiting children who are ahead of the emergency child patient are determined by using the waiting order information, and the estimated waiting time of each of the emergency child patients is determined by using the predicted consultation times of the plurality of designated waiting children.

7. A method for pre-examination and triage of pediatric emergency according to claim 6, characterized in that: According to the patient age data and the current patient diagnosis and treatment strategy of each of the waiting patients, matching is performed in a preset patient cooperation index mapping table to determine the current consultation cooperation index of each of the waiting patients, specifically including: Collect multiple historical diagnosis and treatment data corresponding to the diagnosis and treatment strategy of each child, analyze the diagnosis and treatment time information in the multiple historical diagnosis and treatment data based on statistical analysis technology, and determine the average diagnosis and treatment time corresponding to each diagnosis and treatment strategy of the child; In the plurality of historical diagnosis and treatment data, the average diagnosis and treatment duration corresponding to the age of each patient is determined by using the age information of the diagnosis and treatment object corresponding to each historical diagnosis and treatment data; Determine the consultation cooperation index of the age of the patient corresponding to the diagnosis and treatment strategy of each patient based on the average diagnosis and treatment time corresponding to the age of each patient and the average diagnosis and treatment time corresponding to the diagnosis and treatment strategy of the patient; Constructing a patient cooperation index mapping table through the consultation cooperation index of the patient's age corresponding to each of the patient's diagnosis and treatment strategies; According to the current diagnosis and treatment strategy of each waiting child and the age data of each waiting child, matching is performed in the patient cooperation index mapping table to determine the current consultation cooperation index of each waiting child.

8. A method for pre-examination and triage of pediatric emergency according to claim 1, characterized in that: According to the predicted grade change trend information of each emergency child patient, the visiting area and visiting order of each emergency child patient are adjusted in real time to determine the real-time triage information of each emergency child patient, specifically including: Obtaining the prediction index change trend and real-time prediction grading information in the prediction grading change trend information; When the real-time prediction grading information is the same as the initial triage grading information, determining a rate of change of the prediction indicator change trend; When the change rate of the change trend of the prediction indicator is greater than a preset threshold, adjusting the visiting order of the emergency pediatric patients in the current regional queue; When the real-time predicted grading information is different from the initial triage grading information, the treatment area of ​​the emergency pediatric patient is adjusted according to the real-time predicted grading information.

9. A pre-examination and triage device for children's emergency, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to execute the method according to any one of claims 1 to 8.

Images