Intelligent pre-examination triage method and system for child patients in emergency treatment

Abstract

The invention relates to the technical field of emergency triage, in particular to an intelligent pre-examination triage method and system for an emergency child patient, and the method comprises the steps: collecting the vital sign data, symptom complaint information and past medical history of the emergency child patient in real time through a medical Internet of Things device; an illness crisis degree evaluation model is constructed, an illness crisis coefficient K of the child patient is calculated based on a multivariate parameter fusion algorithm, and the parameters comprise a respiratory rate abnormal value delta R, a blood oxygen saturation degree deviation degree S, a consciousness state classification C and a pain index P; according to the method, the predicted available time T of the doctor can be calculated according to the coefficient eta of the doctor resource dynamic evaluation matrix, and the predicted available time T is matched with the illness state critical coefficient K of the child patient, so that reasonable distribution of the child patient and the doctor is realized; therefore, doctors with high professional ability and low workload can be distributed to the child patients with critical illness, the treatment efficiency and quality are improved, and meanwhile, the doctor-patient problem caused by the fact that the child patients with serious illness cannot be treated in time is also avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency triage, and particularly to an intelligent pre-triage method and system for emergency children patients. Background Art

[0002] In the modern medical system, the emergency department, as an important part of the hospital, undertakes the heavy responsibility of providing emergency treatment for patients with sudden diseases and accidental injuries. The main functions of the emergency department include emergency treatment and rescue, and its existence ensures that patients can quickly obtain professional and scientific medical treatment when suffering from sudden diseases or accidental injuries.

[0003] Emergency pre-triage is a key link in the emergency treatment process, which is directly related to medical quality and patient safety. Especially in pediatric emergencies, due to the large number of critically ill children patients, complex disease types and rapid changes in the condition, the standardized construction of the emergency department is an important principle to ensure the timely and effective treatment of critically ill children patients. In this principle, correct pre-triage plays a key role. The purpose of pre-triage is to quickly classify patients according to the severity of the disease and the treatment priority order, and clarify the treatment priority order, so as to reasonably allocate emergency resources.

[0004] However, there is a significant problem in the existing emergency pre-triage system, that is, it cannot ensure the timely matching between doctors and multiple children patients. Especially for critically ill children patients, they often cannot receive timely treatment from doctors with better capabilities. This situation may not only lead to poor treatment effects for children patients, but even endanger their lives, and at the same time exacerbate the contradictions between doctors and patients. Summary of the Invention

[0005] The purpose of the present invention is to solve the disadvantages in the existing technology such as the inability to ensure the timely matching between doctors and multiple children patients, and to propose an intelligent pre-triage method and system for emergency children patients.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solutions: Design an intelligent pre-triage method for emergency children patients, including: Real-time collect the vital sign data, symptom complaint information and past medical history of emergency children patients through medical Internet of Things devices; Construct a disease criticality assessment model, and calculate the disease criticality coefficient K of children patients based on a multi-parameter fusion algorithm. The parameters include the abnormal value of respiratory rate ΔR, the deviation degree of blood oxygen saturation S, the consciousness state classification C and the pain index P; Establish a dynamic assessment matrix of doctor resources, and calculate the expected available time T of each admitting doctor in real time; Create a two-way matching optimization algorithm, and perform matrix matching according to the descending order of the criticality coefficient K and the ascending order of the doctor available time T; Generate a visual triage decision interface and synchronously push the classification warning signal to the medical staff terminal.

[0007] Further, the vital sign data includes heart rate, respiratory rate, blood pressure, and blood oxygen saturation. The symptom complaint information includes the pain location, pain level, whether accompanied by vomiting or diarrhea. The past medical history includes allergy history and chronic disease history.

[0008] Further, when constructing the critical illness assessment model, a multi-parameter fusion algorithm is used to calculate the critical coefficient K of the child's condition, and its formula is: ; Where: ΔR is the abnormal value of the respiratory rate, calculated by comparing the actual respiratory rate with the normal value. S is the deviation degree of blood oxygen saturation, obtained by calculating the gap between the actual blood oxygen saturation and the normal range. C is the classification of the consciousness state, which is a discrete value and is assigned according to the standard classification system of the consciousness state; P is the pain index, which is a quantitative value based on the child's pain expression; w1, w2, w3, and w4 are the weights of each parameter.

[0009] Further, the coefficient of the doctor resource dynamic assessment matrix is η, which includes: Doctor's professional ability value η 1 : including the specialty qualification certification level, the processing efficiency of typical cases, and the experience value of complication handling; Real-time workload assessment η 2 : Monitor the doctor's physiological fatigue index through a wearable device and predict the remaining reception capacity in combination with historical reception data; Emergency response module η 3 : Automatically freeze the doctor's queue and initiate resource reallocation when a rescue event occurs.

[0010] Further, when no rescue event occurs, η 3 =0, η = η 1 +η 2 ; When a rescue event occurs, η 3 = +∞.

[0011] Further, the calculation formula for the estimated available time T is: ; Where is the remaining processing time of the current reception case, is the estimated processing duration of the jth case in the waiting queue, is the number of cases in the waiting queue.

[0012] Further, the specific implementation steps of the two-way matching optimization algorithm are: Establish a two-dimensional coordinate system of [K, T], and calculate the Euclidean distance between each waiting child and the on-call doctor ; Among them, α and β are weight coefficients, and α + β = 1. The Hungarian algorithm is used to solve the optimal matching combination to ensure the minimization of the global waiting time; Set the threshold of the emergency green channel. When K > K max it triggers the cross-queue direct access mechanism, where K max is the threshold of the emergency green channel.

[0013] Furthermore, it also includes: implementing a dynamic priority adjustment mechanism, which triggers real-time reordering of the triage queue when a new child arrives or the doctor's reception status changes.

[0014] In addition, the present invention also provides an intelligent pre-triage system for emergency children, including: Collection module: Real-time collect the vital sign data, symptom complaint information and past medical history of emergency children through medical Internet of Things devices; Evaluation module: Construct a disease criticality evaluation model, and calculate the disease criticality coefficient K of the child based on the multi-parameter fusion algorithm. The parameters include the abnormal value of respiratory rate ΔR, the deviation degree of blood oxygen saturation S, the consciousness state classification C, and the pain index P; Calculation module: Establish a dynamic evaluation matrix of doctor resources, and calculate the expected available time T of each receiving doctor in real time; Matching module: Create a two-way matching optimization algorithm, and perform matrix matching according to the descending order of the criticality coefficient K and the ascending order of the doctor's available time T; Generation module: Generate a visual triage decision interface, and synchronously push the graded warning signal to the medical staff terminal.

[0015] Furthermore, it also includes an adjustment module: implementing a dynamic priority adjustment mechanism, which triggers real-time reordering of the triage queue when a new child arrives or the doctor's reception status changes.

[0016] For the intelligent pre-triage method and system for emergency children proposed by the present invention, the beneficial effects are as follows: In the present invention, the expected available time T of the doctor can be calculated according to the coefficient of the dynamic evaluation matrix of doctor resources, and it is matched with the disease criticality coefficient K of the child to realize the reasonable allocation of children and doctors. In this way, it can ensure that children with critical conditions can be assigned to doctors with strong professional ability and low workload, improve the treatment efficiency and quality, and at the same time avoid doctor-patient problems caused by the failure of seriously ill children to receive timely treatment. Brief Description of the Drawings

[0017] Figure 1 is a flowchart of the present invention; Figure 2 is a coordinate diagram of the Euclidean distance of the present invention. Detailed implementation manners

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0019] Refer to Figure 1 For an embodiment of the present invention, it discloses an intelligent pre - triage method for emergency children, which is mainly used to match emergency children with doctors to ensure that children with more serious current conditions can obtain medical treatment in time and improve the timeliness of treatment; Specifically, the method includes: Step 1: Real - time collect the vital sign data, symptom main complaint information and past medical history of emergency children through medical Internet of Things devices; Step 2: Construct a disease criticality assessment model, and calculate the disease criticality coefficient K of the child based on a multi - parameter fusion algorithm. The parameters include the abnormal value of respiratory rate ΔR, the deviation degree of blood oxygen saturation S, the consciousness state grade C, and the pain index P; Step 3: Establish a dynamic assessment matrix of doctor resources, and calculate the expected available time T of each receiving doctor in real - time; Step 4: Create a two - way matching optimization algorithm, and perform matrix matching according to the descending order of the criticality coefficient K and the ascending order of the doctor's available time T; Step 5: Generate a visual triage decision interface, and synchronously push a graded warning signal to the medical staff terminal. That is, after matching the doctor corresponding to the child, the matching information can be sent to the doctor's computer or the display screen in the waiting room, so as to quickly display the waiting and medical treatment information of the child, so as to facilitate reaching the doctor's ward in time when making subsequent adjustments or reminding the child to seek medical treatment.

[0020] In some embodiments, the vital sign data in Step 1 includes heart rate, respiratory rate, blood pressure, and blood oxygen saturation. The symptom main complaint information includes the pain location, pain degree, whether accompanied by vomiting and diarrhea. The past medical history includes allergy history and chronic disease history. In this embodiment, through the three - dimensional data fusion of signs - symptoms - medical history, not only the triage priority judgment is optimized, but also an individual risk profile of the child is constructed, providing continuous data support for subsequent treatment.

[0021] Furthermore, when constructing the disease criticality assessment model in Step 2, a multi - parameter fusion algorithm is used to calculate the disease criticality coefficient K of the child, and its formula is: ; Where: ΔR is the abnormal value of respiratory rate, which is calculated by comparing the difference between the actual respiratory rate and the normal value; S is the deviation degree of blood oxygen saturation, which is obtained by calculating the gap between the actual blood oxygen saturation and the normal range; C is the classification of consciousness state, which is a discrete value and is assigned according to the standard classification system of consciousness state; P is the pain index, which is a quantitative value based on the pain expression of the child; w1, w2, w3, and w4 are the weights of each parameter.

[0022] Specifically, according to medical research and clinical experience, the weights w1, w2, w3, and w4 of each parameter can be determined. This weight reflects the relative importance of each parameter in evaluating the critical degree of the child's condition. For example, if the respiratory rate has a greater impact on the condition, then the value of w1 can be relatively large. At the same time, it is necessary to ensure that w1 + w2 + w3 + w4 = 1. By comprehensively considering multiple parameters closely related to the condition, such as respiratory rate, blood oxygen saturation, consciousness state, and pain index, the critical degree of the emergency child's condition can be evaluated more comprehensively and accurately, and the critical degree of the child's condition can be converted into a specific value K, which is convenient for medical staff to make quantitative comparisons and decisions. During the emergency triage process, when facing multiple children, the children can be sorted according to the size of the critical coefficient K of the condition, and the children with more critical conditions can be given priority for treatment, improving the efficiency and accuracy of triage.

[0023] Based on the above embodiments, in this embodiment, the coefficient of the doctor resource dynamic assessment matrix is η, which includes: Doctor's professional ability value η 1 : including the specialty qualification certification level, the processing efficiency of typical cases, and the experience value of complication handling; Among them, the specialty qualification certification level can be assigned a value of 0.3, the intermediate specialty certification is assigned a value of 0.6, and the advanced specialty certification is assigned a value of 0.9. Specifically, it can be evaluated according to the general specialty qualification certification system in the medical field. The processing efficiency of typical cases and the experience value of complication handling can update the data according to a certain time period, such as one month or one quarter, etc., to reflect the doctor's latest processing efficiency.

[0024] Real-time workload assessment η 2 : By monitoring the doctor's physiological fatigue index through wearable devices and predicting the remaining reception capacity in combination with historical reception data. Specifically, wearable devices such as smart bracelets and smart watches can be equipped for doctors to monitor the doctor's physiological indicators in real time, such as heart rate variability and the number of exercise steps. When the doctor is fatigued after working for a long time, the corresponding η 2 increases, which will increase the value of the waiting time T. For example, if a doctor has been working continuously for a long time, with a high physiological fatigue index and a low remaining reception capacity, then when calculating the estimated available time T, the remaining processing time of the current reception case and the processing duration of the waiting queue will both increase, resulting in a longer estimated available time T. Emergency situation response module η 3 : When a rescue event occurs, the doctor queue is automatically frozen and resource reallocation is initiated. That is, in this embodiment, once a rescue event is detected, the doctor's reception queue is automatically frozen, and new children are prohibited from being assigned to this doctor. At the same time, a resource reallocation mechanism is initiated to recalculate the expected available time T of other doctors, and a two-way matching is performed again according to the critical coefficient K of the child's condition, and the children originally assigned to this doctor are reassigned to other available doctors to ensure the timeliness of medical treatment.

[0025] It should be noted that in the present invention, when no rescue event occurs, η 3 =0, η = η 1 +η 2 ; When a rescue event occurs, η 3 =+∞, that is, when there is an emergency, η 3 will become larger. For example, when a doctor needs to handle a rescue event in the hospital, to ensure the reasonable allocation of doctor resources in an emergency. When a rescue event occurs, the queue of relevant doctors is frozen and resource reallocation is performed, which can avoid treatment delays caused by improper allocation of doctor resources and ensure the safety of children's lives.

[0026] More specifically, in this embodiment, the calculation formula for the expected available time T is: ; Where is the remaining processing time of the current received case, is the expected processing duration of the jth case in the waiting queue, is the number of cases in the waiting queue.

[0027] That is to say, in the intelligent pre-triage process of emergency children in the present invention, the expected available time T of the doctor is calculated according to the coefficient of the doctor resource dynamic evaluation matrix and matched with the critical coefficient K of the child's condition to achieve the reasonable allocation of children and doctors, which can ensure that children with critical conditions can be assigned to doctors with strong professional capabilities and low workloads, improving the treatment efficiency and quality.

[0028] Based on the above embodiments, the specific implementation steps of the two-way matching optimization algorithm in this embodiment are as follows: Establish a [K, T] two-dimensional coordinate system and calculate the Euclidean distance between each waiting child and the standby doctor , specifically, reference can be made to the appendix of the specification of the present invention Figure 2As shown, it is a two-dimensional coordinate system of [K, T]. In this embodiment, α and β are weight coefficients, and α + β = 1. The values of the weight coefficients can be adjusted according to the actual situation. For example, if more emphasis is placed on the criticality of the condition, the value of α can be appropriately increased; if more attention is paid to the available time of the doctor, the value of β can be appropriately increased. The Hungarian algorithm is used to solve the optimal matching combination to ensure the minimization of the global waiting time. Set the threshold of the emergency green channel. When K > K max a cross-queue direct access mechanism is triggered, where K max is the threshold of the emergency green channel. Specifically, according to the actual situation of the hospital and clinical experience, the threshold K of the emergency green channel can be set. max， This threshold is used to determine whether the condition of the child is critical enough to require special treatment.

[0029] Specifically, in this embodiment, by using the Hungarian algorithm to solve the optimal matching combination, the sum of the waiting times of all children can be minimized, thereby reducing the overall waste of medical resources and improving the operation efficiency of the hospital. Setting the threshold of the emergency green channel and triggering the cross-queue direct access mechanism can ensure that children with extremely critical conditions receive priority treatment. In case of emergency, this mechanism can avoid treatment delays caused by the normal triage process and improve the survival probability of critical children.

[0030] Furthermore, the embodiment of the present invention further includes Step Six: Implement a dynamic priority adjustment mechanism. When a new child arrives or the doctor's reception status changes, a real-time reordering of the triage queue is triggered. As described above, when a new child comes to see a doctor, the staff enters the basic information, vital sign data, symptom complaint information, and past medical history of the child into the system. After the system receives the new data, the dynamic priority adjustment mechanism can be triggered. Specifically, in this embodiment, by reordering the triage queue in real time, the matching relationship between children and doctors can be reasonably adjusted according to the dynamic changes of the children's conditions and doctor resources. This enables medical resources to be more efficiently allocated to the children who need them most, avoiding resource waste and uneven distribution.

[0031] In addition, an intelligent pre-triage system for emergency children in the present invention includes: A collection module: Real-time collection of the vital sign data, symptom complaint information, and past medical history of emergency children through medical Internet of Things devices. In some embodiments, the vital sign data includes heart rate, respiratory rate, blood pressure, and blood oxygen saturation. The symptom complaint information includes the pain location, pain level, whether accompanied by vomiting or diarrhea. The past medical history includes allergy history and chronic disease history. In this embodiment, through the three-dimensional data fusion of signs - symptoms - medical history, not only the triage priority judgment is optimized, but also an individual risk profile of the child is constructed, providing continuous data support for subsequent treatment.

[0032] Evaluation module: Construct a critical condition assessment model, and calculate the critical coefficient K of the child's condition based on a multi-parameter fusion algorithm. The parameters include the abnormal value of respiratory rate ΔR, the deviation degree of blood oxygen saturation S, the consciousness state classification C, and the pain index P. In some embodiments, when constructing the critical condition assessment model, a multi-parameter fusion algorithm can be used to calculate the critical coefficient K of the child's condition. The formula is: ; Where: ΔR is the abnormal value of respiratory rate, which can be calculated by comparing the actual respiratory rate with the normal value. S is the deviation degree of blood oxygen saturation, which can be obtained by calculating the gap between the actual blood oxygen saturation and the normal range. C is the consciousness state classification, usually a discrete value, which can be assigned according to the standard classification system of consciousness state. P is the pain index, which can be a quantitative value based on the child's pain expression. w1, w2, w3, and w4 are the weights of each parameter. Calculation module: Establish a dynamic assessment matrix of doctor resources and calculate the expected available time T of each attending physician in real time. In some embodiments, the coefficient of the dynamic assessment matrix of doctor resources is η, which includes the doctor's professional ability value η 1 , the real-time workload assessment η 2 and the emergency response module η 3； . In the present invention, when no rescue event occurs, η 3 =0, η = η 1 +η 2 ; when a rescue event occurs, η 3 =+∞; During the intelligent pre-triage of emergency children, the expected available time T of the doctor is calculated according to the coefficient of the dynamic assessment matrix of doctor resources and matched with the critical coefficient K of the child's condition, so as to realize the reasonable allocation of children and doctors. This can ensure that children with critical conditions can be assigned to doctors with strong professional ability and low workload, improving the treatment efficiency and quality. Matching module: Create a two-way matching optimization algorithm, and perform matrix matching according to the descending order of the critical coefficient K and the ascending order of the doctor's available time T. In some embodiments, by establishing a [K, T] two-dimensional coordinate system, the Euclidean distance between each waiting child and the standby doctor is calculated , specifically, please refer to the appendix of the specification of the present invention Figure 2 as shown. It is a schematic diagram of the [K, T] two-dimensional coordinate system and the Euclidean distance. The abscissa represents the critical coefficient K of the child's condition, the ordinate represents the available time T of the doctor, and the color change in the figure represents different Euclidean distance D values.

[0033] In this embodiment, α and β are weight coefficients, and α + β = 1. The values of the weight coefficients can be adjusted according to the actual situation. For example, if more importance is attached to the criticality of the condition, the value of α can be appropriately increased; if more attention is paid to the available time of the doctor, the value of β can be appropriately increased; In some embodiments, the matching cases are shown in Table 1: Table 1

[0034] The Hungarian algorithm is used to solve the optimal matching combination to ensure the minimization of the global waiting time; Set the threshold of the emergency green channel. When K > K max Trigger the cross - queue direct - through mechanism. Specifically, according to the actual situation of the hospital and clinical experience, set the emergency green channel threshold K max， This threshold is used to determine whether the condition of the child is critical enough to require special treatment; Generation module: Generate a visual triage decision interface, and synchronously push the hierarchical warning signal to the medical staff terminal. That is, after the doctor corresponding to the child is matched, the matching information can be sent to the doctor's computer or the display screen in the waiting room, so as to quickly display the waiting and medical treatment information of the child, so as to facilitate reaching the doctor's ward in time when making subsequent adjustments or reminding for medical treatment.

[0035] Based on the above - mentioned embodiment, the system further includes an adjustment module: Implement a dynamic priority adjustment mechanism. When a new child arrives or the doctor's reception status changes, trigger the real - time re - sorting of the triage queue. Specifically, in this embodiment, by re - sorting the triage queue in real time, the matching relationship between the child and the doctor can be reasonably adjusted according to the dynamic changes of the child's condition and doctor resources. So that medical resources can be more efficiently allocated to the children who need them most, avoiding resource waste and uneven distribution.

[0036] To sum up, in the present invention, the expected available time T of the doctor can be calculated according to the coefficients of the dynamic evaluation matrix of doctor resources and matched with the criticality coefficient K of the child's condition, so as to realize the reasonable allocation of the child and the doctor. In this way, it can be ensured that children with critical conditions can be assigned to doctors with strong professional capabilities and low workloads, improving the treatment efficiency and quality, and at the same time avoiding doctor - patient problems caused by the failure of seriously ill children to receive timely treatment.

[0037] The above - mentioned are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent replacements or changes, and all should be covered within the protection scope of the present invention.

Claims

1. An intelligent pre-examination and triage method for emergency children, characterized in that: include: Medical IoT devices can be used to collect vital signs, symptom information, and medical history of emergency patients in real time; A criticality assessment model was constructed to calculate the criticality coefficient K of the child based on a multivariate parameter fusion algorithm. The parameters included abnormal respiratory rate value ΔR, blood oxygen saturation deviation S, consciousness state grade C, and pain index P. Establish a dynamic evaluation matrix for doctor resources and calculate the estimated available time T of each attending physician in real time; Create a two-way matching optimization algorithm to perform matrix matching based on the descending order of the criticality coefficient K and the ascending order of the doctor's available time T; Generate a visual triage decision-making interface and simultaneously push graded warning signals to medical terminals.

2. The intelligent pre-examination and triage method for emergency children according to claim 1, characterized in that: The vital signs data include heart rate, respiratory rate, blood pressure, and blood oxygen saturation. The symptom information includes the location of pain, the degree of pain, and whether there is vomiting or diarrhea. The past medical history includes a history of allergies and chronic diseases.

3. The intelligent pre-examination and triage method for emergency children according to claim 1, characterized in that: When constructing the disease severity assessment model, a multivariate parameter fusion algorithm is used to calculate the disease severity coefficient K of the child, and the formula is: ; Among them: ΔR is the abnormal value of respiratory rate, which is calculated by comparing the difference between the actual respiratory rate and the normal value; S is the deviation of blood oxygen saturation, which is obtained by calculating the difference between the actual blood oxygen saturation and the normal range; C is the consciousness state classification, which is a discrete value assigned according to the standard classification system of consciousness state; P is the pain index, which is a quantitative value based on the child's pain expression; w1, w2, w3, w4 are the weights of each parameter.

4. The intelligent pre-examination and triage method for emergency children according to claim 1, characterized in that: The coefficient of the doctor resource dynamic evaluation matrix is ​​η, which includes: Doctor's professional ability value η1: including specialist qualification certification level, typical case handling efficiency, and complication handling experience value; Real-time workload assessment η2: Monitor the doctor's physiological fatigue index through wearable devices and predict the remaining reception capacity based on historical reception data; Emergency response module η3: When a rescue incident occurs, the doctor queue is automatically frozen and resource reallocation is initiated.

5. The intelligent pre-examination and triage method for emergency children according to claim 4, characterized in that: When no rescue event occurs, η3=0, η=η1+η2; When a rescue incident occurs, η3=+∞.

6. The intelligent pre-examination and triage method for emergency children according to claim 5, characterized in that: The calculation formula for the estimated available time T is: ； in The remaining processing time for the current case. is the expected processing time for the jth case in the waiting queue, is the number of cases in the waiting queue.

7. The intelligent pre-examination and triage method for emergency children according to claim 1, characterized in that: The specific implementation steps of the two-way matching optimization algorithm are: Establish a [K, T] two-dimensional coordinate system and calculate the Euclidean distance between each waiting patient and the on-call doctor ; Where α and β are weight coefficients, and α+β=1. The Hungarian algorithm is used to solve the optimal matching combination to ensure that the global waiting time is minimized; Set the emergency green channel threshold when K>K max The cross-queue direct-through mechanism is triggered when K max It is the emergency green channel threshold.

8. The intelligent pre-examination and triage method for emergency children according to claim 1, characterized in that: Also includes: Implement a dynamic priority adjustment mechanism to trigger real-time reordering of the triage queue when new patients arrive or the doctor's reception status changes.

9. An intelligent pre-examination and triage system for emergency children, characterized in that: include: Collection module: collects vital signs data, symptom information and medical history of emergency children in real time through medical Internet of Things devices; Evaluation module: construct a disease severity assessment model, and calculate the disease severity coefficient K of the child based on a multivariate parameter fusion algorithm. The parameters include abnormal respiratory rate value ΔR, blood oxygen saturation deviation S, consciousness state classification C, and pain index P; Calculation module: Establish a dynamic evaluation matrix of doctor resources and calculate the estimated available time T of each attending physician in real time; Matching module: Create a two-way matching optimization algorithm to perform matrix matching based on the descending order of the criticality coefficient K and the ascending order of the doctor's available time T; Generation module: Generates a visual triage decision-making interface and simultaneously pushes graded warning signals to medical terminals.

10. The intelligent pre-examination and triage system for emergency children according to claim 9, characterized in that: It also includes an adjustment module: implementing a dynamic priority adjustment mechanism to trigger real-time reordering of the triage queue when new patients arrive or the doctor's reception status changes.

Images