Intelligent nursing method for severe hyperpyrexia patient

Abstract

The invention relates to the technical field of intelligent nursing, in particular to an intelligent nursing method for severe hyperpyrexia patients, and aims to improve the intelligent nursing grading accuracy, achieve the purpose of high-quality and safe nursing of the severe hyperpyrexia patients and improve the nursing clinical value. The method specifically comprises the following steps: inputting vital sign change parameters of a severe hyperpyrexia patient in a monitoring time period and illness state change characteristics of the severe hyperpyrexia patient in an effective nursing period into a recurrent neural network model for training, and outputting a nursing grade result; monitoring safety risk prompt information is obtained according to the nursing grade result; calling nursing grade parameters in a preset nursing grade system according to the monitoring safety risk prompt information; and inputting the called nursing grade parameters into the currently trained recurrent neural network model to output an adjustment coefficient of a current nursing grade result, and carrying out nursing work according to the size of the current adjustment coefficient.

Description

Technical Field

[0001] The present invention relates to the field of intelligent nursing technology, and in particular to an intelligent nursing method for severe high fever patients. Background Art

[0002] The treatment and management of patients with severe fever is a complex process that requires comprehensive consideration of the patient's specific condition and cause. When treating patients with severe fever, the medical team needs to closely monitor changes in the patient's condition and adjust the treatment plan based on the latest clinical guidelines and research results. At the same time, the combination of Chinese and Western medicine can provide a more comprehensive treatment strategy to improve treatment outcomes and patient survival rates.

[0003] The existing patient safety intelligent early warning system is usually built by real-time monitoring of the patient's vital signs information and the current patient's monitoring course and monitoring status, which can monitor the patient's nursing status to a certain extent. With the sharp increase in patients with infectious diseases in recent years, the corresponding increase in the number of nursing staff, nursing wards and monitoring courses requires more nursing staff to cope with it, and it is also necessary to increase the monitoring end and corresponding management personnel to obtain real-time monitoring data. Usually, due to the limitation of the treatment hospital area and the diversity of disease types of severe fever patients, isolation monitoring and other measures are required. A large number of monitoring personnel is not conducive to the treatment and rehabilitation process of severe fever patients.

[0004] Existing, an intelligent and systematic nursing grading system based on the Internet of Things is designed and applied in nursing work. However, with the increase in the number of patients with severe fever, due to the limited number of nursing staff, the plan of directly increasing the number of nursing staff is no longer applicable to the nursing process of a large number of patients with severe fever, and the nursing quality and efficiency of the existing graded nursing are difficult to objectively reflect through data-based evaluation. It is necessary to analyze based on the specific data of the current nursing staff's detection rate of potential complications of the current patients, postoperative complications and adverse events. However, for patients with severe fever, due to the urgency of treatment and the severity of life safety risks, the nursing method that only communicates through oral rounds between medical staff has low clinical efficiency and affects the actual treatment and rehabilitation efficiency of patients. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent nursing method for severe hyperthermia patients to solve the following technical problems:

[0006] How to improve the accuracy of intelligent nursing grading to achieve high-quality and safe nursing for critically ill and febrile patients while improving the clinical value of nursing.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] Intelligent nursing methods for severe fever patients include:

[0009] S1. Obtain the vital sign change parameters of patients with severe hyperthermia during the monitoring period and the condition change characteristics of patients with severe hyperthermia during the effective nursing period, input them into the recurrent neural network model training and output the nursing level results;

[0010] The vital signs change parameters include: temperature change value, heart rate change value, blood pressure change value;

[0011] The characteristics of disease changes include: improvement, worsening, and stable disease;

[0012] The nursing level results were divided into primary care, secondary care, and tertiary care according to the severity of nursing intervention from high to low;

[0013] S2. Obtaining monitoring safety risk warning information based on the nursing level results;

[0014] S3, retrieve the nursing level parameters in the preset nursing grading system according to the monitoring safety risk prompt information;

[0015] S4. Input the retrieved nursing level parameters into the currently trained recurrent neural network model to output the adjustment coefficient of the current nursing level result, and carry out nursing work according to the size of the current adjustment coefficient.

[0016] Preferably, the method for obtaining the nursing level data in step S1 is:

[0017] Determine the set of vital sign change parameters {x1, x2, ... x m};

[0018] Determine the characteristic parameter set {B1, B2, ... B1, B2, ... B2, B1, B2, ... ... n}, n is the number of effective nursing cycles;

[0019] Obtain the characteristic parameter set B of the condition change in each effective nursing cycle i All elements of {(y1) i , (y2) i ,......(y m ) i} and the corresponding vital sign change parameter set {x1, x2, ... x m} to form a new set C, and the set C∈{(x1y1) i , (x2y2) i ,......(x m y m ) i}; i is the current effective nursing cycle; m is the total number of time points in the effective nursing cycle;

[0020] All elements in the new set C are input into the recurrent neural network model as training sets for training, the effective care value corresponding to each element is obtained, and the current effective care value is divided from large to small according to the preset effective care value threshold range and the care level result is output.

[0021] Preferably, the effective care value is calculated as follows:

[0022] By formula Calculate the real-time effective nursing value Ef j ;

[0023] Where, j is the current time point, and j∈[1,m]; ε, δ are both preset weight coefficients, and ε, δ are both greater than 0; f is the preset nursing function; Vs j is the vital sign change parameter at the current time point, Vs j0 is the standard vital sign change parameter at the same time point, ΔVs j Q is the deviation value of the vital sign change parameter at the preset current time point; k is the disease condition change conversion function, k is the disease condition change characteristic; Co j is the characteristic parameter of the disease change at the current time point, Co j0 is the characteristic parameter of the standard disease condition change at the current time point; β i is the influence coefficient of the i-th effective nursing cycle.

[0024] Preferably, the care level results include:

[0025] The current effective care value Ef j Compared with the preset effective nursing value threshold interval [Ef a , Ef b ] for comparison:

[0026] If Ef j <Ef a , then the current effective nursing quality is judged to be excellent, less nursing intervention is required, and the nursing level is determined to be level 3 nursing;

[0027] If Ef a ≤Ef j ≤Ef b , then the current effective nursing quality is judged to be average, more nursing intervention is needed, and the nursing level is determined to be secondary nursing;

[0028] If Ef j >Ef b , then it is judged that the current effective nursing quality is poor and more nursing intervention is needed, and the nursing level is determined to be primary care.

[0029] Preferably, the monitoring safety risk warning information includes:

[0030] Confirm the care level signal for each critically ill febrile patient based on the care level results;

[0031] Confirm the matching nursing staff information of the corresponding level according to the nursing level signal; the nursing staff information includes the nursing staff level and nursing staff experience parameters;

[0032] Generate early warning signals based on the first-level nursing level to monitor changes in the nursing status of critically ill high fever patients with the first-level nursing level.

[0033] Preferably, in step S3:

[0034] Input the nursing level signals and corresponding nursing staff information of all severe high fever patients into the analysis model of the preset nursing grading system, and output the nursing level parameters;

[0035] And based on the early warning signals, the adjustment information of severe high fever patients with first-level nursing level is fed back and an adjustment form is generated.

[0036] Preferably, in step S4:

[0037] By formula Calculate the adjustment coefficient Adj;

[0038] Among them, Δt is the preset time period within the effective nursing cycle time points; Nur i is the real-time nursing level parameter in the cumulative time period of the i-th effective nursing cycle, Nur i0 is the preset standard nursing level parameter of the i-th effective nursing cycle, ΔNur i is the deviation value of the preset nursing level parameter of the i-th effective nursing cycle; H(·) is the conversion function of the nursing level parameter; Ef i (t) is the real-time effective nursing value of the i-th effective nursing cycle.

[0039] Preferably, the adjustment coefficient Adj is compared with a preset adjustment coefficient threshold interval [Adj1, Adj2]:

[0040] If Adj∈[Adj1, Adj2], the current adjustment coefficient is judged to be normal, the current nursing level is maintained, and the current nursing work is continued;

[0041] If Adj>Adj2, the current adjustment coefficient is judged to be too large, the current nursing level is reduced, and corresponding nursing work is carried out according to the adjustment result;

[0042] If Adj(t)<Adj1, it is judged that the current adjustment coefficient is too small, the current nursing level is improved, and corresponding nursing work is carried out according to the adjustment results.

[0043] Beneficial effects of the present invention: The present invention obtains the vital sign change parameters of patients with severe hyperthermia during the monitoring period and the condition change characteristics of patients with severe hyperthermia during the effective nursing period, inputs them into the recurrent neural network model for training and outputs the nursing level results; reflects the nursing situation of patients with severe hyperthermia through monitoring safety risk prompt information, and accurately matches the corresponding nursing staff according to the nursing level signal to form a nursing and safety monitoring process for patients with severe hyperthermia of different levels. According to the monitoring safety risk prompt information, the nursing level parameters in the preset nursing grading system are retrieved; the retrieved nursing level parameters are input into the currently trained recurrent neural network model to output the adjustment coefficient of the current nursing level result, and the nursing work is carried out according to the current adjustment coefficient.

[0044] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 This is a schematic diagram of the steps of the intelligent nursing method for severe high fever patients of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Existing, an intelligent and systematic nursing grading system based on the Internet of Things is designed and applied in nursing work. However, with the increase in the number of patients with severe fever, due to the limited number of nursing staff, the plan of directly increasing the number of nursing staff is no longer applicable to the nursing process of a large number of patients with severe fever, and the nursing quality and efficiency of the existing graded nursing are difficult to objectively reflect through data-based evaluation. It is necessary to analyze based on the specific data of the current nursing staff's detection rate of potential complications of the current patients, postoperative complications and adverse events. However, for patients with severe fever, due to the urgency of treatment and the severity of life safety risks, the nursing method that only communicates through oral rounds between medical staff has low clinical efficiency and affects the actual treatment and rehabilitation efficiency of patients.

[0049] See also Figure 1 As shown, in order to solve the above technical problems, the present invention is an intelligent nursing method for severe high fever patients, the method comprising:

[0050] S1. Obtain the vital sign change parameters of patients with severe hyperthermia during the monitoring period and the condition change characteristics of patients with severe hyperthermia during the effective nursing period, input them into the recurrent neural network model training and output the nursing level results;

[0051] The vital signs change parameters include: temperature change value, heart rate change value, blood pressure change value;

[0052] The characteristics of disease changes include: improvement, worsening, and stable disease;

[0053] The nursing level results were divided into primary care, secondary care, and tertiary care according to the severity of nursing intervention from high to low;

[0054] S2. Obtaining monitoring safety risk warning information based on the nursing level results;

[0055] S3, retrieve the nursing level parameters in the preset nursing grading system according to the monitoring safety risk prompt information;

[0056] S4. Input the retrieved nursing level parameters into the currently trained recurrent neural network model to output the adjustment coefficient of the current nursing level result, and carry out nursing work according to the size of the current adjustment coefficient.

[0057] In the above technical scheme, in this embodiment, the nursing level is obtained by analyzing the existing disease status monitoring results, and the monitoring safety risk prompt is performed and the rationality of the nursing level parameters is determined according to the monitoring safety risk prompt information. Finally, by adjusting the nursing level, the nursing-related data is further refined. The specific steps are:

[0058] First, step S1 obtains the vital sign change parameters of severe hyperthermia patients within the monitoring period and the condition change characteristics of severe hyperthermia patients within the effective nursing period, inputs them into the recurrent neural network model for training and outputs the nursing level results; wherein, the vital sign change parameters analyzed based on medical physiological knowledge include: body temperature change value, heart rate change value, blood pressure change value; the condition change characteristics are set to include: condition improvement, condition worsening, and condition stabilization; and the nursing level is divided into primary care, secondary care, and tertiary care according to the severity of nursing intervention from high to low; different from the method of directly assigning nursing staff to general types of patients, this design judges the patient's nursing needs from the perspective of nursing intervention, and then provides a more appropriate nursing method.

[0059] Among them, the recurrent neural network model is used to train the vital sign change parameters of patients with severe high fever during the monitoring period and the characteristic sequence data of the condition change of patients with severe high fever during the effective nursing cycle, judge the relationship between the patient's self-care ability and nursing needs to obtain the nursing grade, and divide the historical data with marked nursing grade results into training set, validation set and test set. For example, based on the medical records of patients with severe high fever in the past, their vital sign change parameters, condition change characteristics and corresponding nursing grade results are determined, and then divided into training set, validation set and test set according to a certain ratio (such as 7:2:1). In the actual training process, a loss function (such as cross entropy loss function, etc.) is used to measure the difference between the model output results and the actual nursing grade results. The weight of the model is continuously adjusted through the back propagation algorithm to minimize the loss function. Overfitting is also prevented by monitoring indicators such as the loss and accuracy of the validation set; if the loss of the validation set begins to rise or the accuracy no longer increases, it means that the model may be overfitting, and the structure or training parameters of the model need to be adjusted (such as reducing the learning rate, increasing the regularization term, etc.).

[0060] Specifically, the method for obtaining the nursing level data in step S1 is:

[0061] Determine the set of vital sign change parameters {x1, x2, ... x m};

[0062] Determine the characteristic parameter set {B1, B2, ... B1, B2, ... B2, B1, B2, ... ... n}, n is the number of effective nursing cycles;

[0063] Obtain the characteristic parameter set B of the condition change in each effective nursing cycle i All elements of {(y1) i , (y2) i ,......(y m ) i} and the corresponding vital sign change parameter set {x1, x2, ... x m} to form a new set C, and the set C∈{(x1y1) i , (x2y2) i ,......(x m y m ) i}; i is the current effective nursing cycle; m is the total number of time points in the effective nursing cycle;

[0064] All elements in the new set C are input into the recurrent neural network model as training sets for training, the effective care value corresponding to each element is obtained, and the current effective care value is divided from large to small according to the preset effective care value threshold range and the care level result is output.

[0065] In the above technical solution, this embodiment realizes matching reference to the nursing needs of severe hyperthermic patients by obtaining the nursing level. Specifically, firstly, a set of vital sign change parameters {x1, x2, ... x m};; According to the temperature change value, heart rate change value, and blood pressure change value, a combined analysis is performed, and then the characteristic parameter set of the condition change of all severe high fever patients within the effective nursing cycle is determined {B1, B2, ... B n}, by statistically combining the improvement, deterioration, and stabilization of the condition in the characteristic data of condition change, and then calculating and analyzing, the characteristic parameters of condition change in each effective nursing cycle are obtained; further, the two sets of information are recombined by time matching, and the characteristic parameter set B of condition change in each effective nursing cycle is obtained. i All elements of {(y1) i , (y2) i ,......(y m ) i} and the corresponding vital sign change parameter set {x1, x2, ... x m} to form a new set C, and finally input all the elements in the new set C as the training set into the recurrent neural network model for training, obtain the effective nursing value corresponding to each element, and divide the current effective nursing value from large to small according to the preset effective nursing value threshold range and output the nursing level result.

[0066] Among them, the effective nursing cycle is relative to the information data of the patient's condition change. As long as the patient's treatment shows improvement or deterioration slows down within the time distance of historical medical staff intervention, it can be called an effective nursing cycle; such an effective nursing cycle is usually phased, and due to the phased nature of the hospital's treatment plan and the time span of different disease treatment courses during the treatment or rehabilitation process, it also includes multiple effective nursing cycles.

[0067] As an implementation of the present invention, this embodiment calculates the effective care value, and the specific calculation method is:

[0068] By formula Calculate the real-time effective nursing value Ef j ;

[0069] Where, j is the current time point, and j∈[1,m]; ε, δ are both preset weight coefficients, and ε, δ are both greater than 0; f is the preset nursing function; Vs j is the vital sign change parameter at the current time point, Vs j0 is the standard vital sign change parameter at the same time point, ΔVs j Q is the deviation value of the vital sign change parameter at the preset current time point; k is the disease condition change conversion function, k is the disease condition change characteristic; Co j is the characteristic parameter of the disease change at the current time point, Co j0 is the characteristic parameter of the standard disease condition change at the current time point; β i is the influence coefficient of the i-th effective nursing cycle.

[0070] In the above technical solution, the effective nursing value can be used to directly judge the nursing quality corresponding to the nursing needs of the current element, that is, severe high fever patients. By analyzing the vital signs change parameters and the characteristic parameters of the condition change as the main factors, the effective nursing value can be judged to achieve accurate confirmation of the effective nursing value at the current time point.

[0071] It should be explained that the preset weight coefficients ε and δ are selected and set based on empirical data. The specific settings can be quantitatively or qualitatively set by judging the proportion of the impact of vital sign changes and the impact of disease change characteristics in the effective nursing results of the entire nursing needs; the disease change conversion function Q k It is obtained by fitting the test data of characteristic parameters of the patient's condition changes under normal care status.

[0072] A preset function usually refers to a rule or logic pre-defined in some system or algorithm to guide the allocation process of resources, data or tasks; the preset nursing function f in this design is customized according to the patient's specific situation and changes in the condition. It is an optimization function set according to historical data and can ensure that the result calculated by the current formula is within the reasonable range of effective nursing values.

[0073] Vs j0 、Co j0 The average value or average variance of the data on the influence of the changes in vital signs and the influence of the characteristics of the disease state under the normal effective nursing demand state simulated by the machine in advance; ΔVs j The setting is selected based on empirical data and will not be described in detail here; the influencing coefficient of the effective nursing cycle β i The comprehensive nursing status selection and setting are based on different effective nursing cycles for severe high fever patients, which will not be described in detail here.

[0074] As an embodiment of the present invention, the nursing level result includes:

[0075] The current effective care value Ef j Compared with the preset effective nursing value threshold interval [Ef a , Ef b ] for comparison:

[0076] If Ef j <Ef a , then the current effective nursing quality is judged to be excellent, less nursing intervention is required, and the nursing level is determined to be level 3 nursing;

[0077] If Ef a ≤Ef j ≤Ef b , then the current effective nursing quality is judged to be average, more nursing intervention is needed, and the nursing level is determined to be secondary nursing;

[0078] If Ef j >Ef b , then it is judged that the current effective nursing quality is poor and more nursing intervention is needed, and the nursing level is determined to be primary care.

[0079] In the above technical solution, the nursing level result in this embodiment is expressed by the effective nursing value Ef j The size is determined by comparing it with the preset effective nursing value threshold interval [Ef a , Ef b ] to compare the size and determine if Ef j <Ef a , then the current effective nursing quality is judged to be excellent, requiring less nursing intervention, and the nursing level is set as level 3 nursing; if Ef a ≤Ef j≤Ef b , then the current effective nursing quality is judged to be average, more nursing intervention is needed, and the nursing level is determined to be secondary nursing; if Ef j >Ef b , then the current effective nursing quality is judged to be poor, more nursing intervention is needed, and the nursing level is set to first-level nursing; the nursing level is accurately determined. It should be noted that according to the real-time effective nursing value Ef of the effective treatment cycle or the preset time period j Comprehensively determine the patient's final level of care.

[0080] Then, step S2 obtains monitoring safety risk warning information according to the nursing level result; the monitoring safety risk warning information reflects the nursing situation of severe hyperthermia patients, and accurately matches the corresponding nursing staff according to the nursing level signal to form a nursing and safety monitoring process for severe hyperthermia patients with different nursing levels.

[0081] As an implementation mode of the present invention, the monitoring safety risk prompt information includes:

[0082] Confirm the care level signal for each critically ill febrile patient based on the care level results;

[0083] Confirm the matching nursing staff information of the corresponding level according to the nursing level signal; the nursing staff information includes the nursing staff level and nursing staff experience parameters;

[0084] Generate early warning signals based on the first-level nursing level to monitor changes in the nursing status of critically ill high fever patients with the first-level nursing level.

[0085] In the above technical scheme, specifically, the process of obtaining monitoring safety risk warnings based on the judgment results of the nursing level, the monitoring safety risk warning information mainly includes: confirming the nursing level signal of each critically ill high fever patient according to the nursing level result; then, confirming the nursing staff information matching the corresponding level according to the nursing level signal; the nursing staff information includes the nursing staff level and the nursing staff experience parameters; and also generating an early warning signal based on the first-level nursing level to monitor the changes in the nursing status of critically ill high fever patients with the first-level nursing level.

[0086] Next, step S3 retrieves the nursing level parameters in the preset nursing grading system according to the monitoring safety risk warning information; specifically, inputs the nursing level signals of all critically ill and hyperthermic patients and the corresponding nursing staff information into the analysis model of the preset nursing grading system, outputs the nursing level parameters; and feeds back the adjustment information of critically ill and hyperthermic patients with the first-level nursing level according to the early warning signal, and generates an adjustment table.

[0087] In the above technical scheme, the monitoring safety risk prompt information is analyzed in the previous step, including prompting the patient's nursing level and allocating patient care personnel. The current display information is trained through the analysis model of the existing nursing grading system, the result of nursing level parameterization is achieved, and the current nursing level parameters are output. At the same time, the adjustment information of the first-level nursing level critically ill high fever patients is fed back according to the early warning signal, and an adjustment table is generated.

[0088] The analysis model of the nursing grading system is the Triangle model, which is a commonly used model for determining disability levels and nursing levels. By combining literature evidence-based methods and relevant rating scales, a graded nursing system with three-level nursing assessment indicators is constructed. For example, the first-level nursing assessment indicators may include daily living activities, functional daily activities care, medical care, and spiritual comfort.

[0089] Finally, step S4 readjusts the nursing level data in the pre-trained recurrent neural network model according to the retrieved nursing level parameters, generates the corresponding adjustment coefficient, and carries out corresponding nursing work according to the size of the adjustment coefficient; the effective nursing value corresponding to the pre-acquired nursing level data is intervened and analyzed by the introduced nursing level parameters, and the adjustment coefficient is output to complete the update and adjustment of the nursing level data in a timely manner.

[0090] As an implementation of the present invention, specifically, the method for obtaining the adjustment coefficient in step S4 is:

[0091] By formula Calculate the adjustment coefficient Adj;

[0092] Among them, Δt is the preset time period within the effective nursing cycle time points; Nur i is the real-time nursing level parameter in the cumulative time period of the i-th effective nursing cycle, Nur i0 is the preset standard nursing level parameter of the i-th effective nursing cycle, ΔNur i is the deviation value of the preset nursing level parameter of the i-th effective nursing cycle; H(·) is the conversion function of the nursing level parameter; Ef i (t) is the real-time effective nursing value of the i-th effective nursing cycle.

[0093] In the above technical solution, the relationship between the preset nursing level parameters of the effective nursing cycle and the implemented effective nursing value is calculated to obtain the real-time adjustment coefficient Adj(t), which is mainly achieved by converting the reference value of the current preset nursing level parameter through the conversion function H(·), wherein the conversion function H(·) is obtained by fitting the nursing test data within the cumulative time period of the current effective nursing cycle, and the effective nursing value in the current state is substituted for calculation to determine the size of the real-time adjustment coefficient.

[0094] It should be noted that the preset time period Δt is determined based on empirical data and can be adaptively adjusted according to specific clinical condition monitoring needs; i0 It is the standard value calculated based on the vital sign change parameters and disease change characteristic information under the current normal nursing cycle; ΔNur i The settings are selected based on empirical data and are not described in detail here.

[0095] As an implementation mode of the present invention, the adjustment coefficient Adj is compared with the preset adjustment coefficient threshold interval [Adj1, Adj2]:

[0096] If Adj∈[Adj1, Adj2], the current adjustment coefficient is judged to be normal, the current nursing level is maintained, and the current nursing work is continued;

[0097] If Adj>Adj2, the current adjustment coefficient is judged to be too large, the current nursing level is reduced, and corresponding nursing work is carried out according to the adjustment result;

[0098] If Adj(t)<Adj1, it is judged that the current adjustment coefficient is too small, the current nursing level is improved, and corresponding nursing work is carried out according to the adjustment results.

[0099] In the above technical solution, this embodiment determines the adjustment information of the nursing level by analyzing the size of the adjustment coefficient, and carries out nursing work according to the specific adjustment direction.

[0100] 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.

[0101] 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.

[0102] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent nursing method for severe hyperthermic patients, characterized in that: The method includes: S1. Obtain the vital sign change parameters of critically ill patients with high fever during the monitoring period and the disease change characteristics of critically ill patients with high fever during the effective nursing period, input them into a recurrent neural network model for training, and output the nursing level result; The vital sign change parameters include: body temperature change value, heart rate change value, blood pressure change value; The disease change characteristics include: improvement of the disease condition, deterioration of the disease condition, and stability of the disease condition; The nursing level results are divided into first-level nursing, second-level nursing, and third-level nursing in descending order according to the severity of nursing intervention; S2. Obtain the monitoring safety risk prompt information according to the nursing level result; S3. Retrieve the nursing level parameters in the preset nursing classification system according to the monitoring safety risk prompt information; S4. Input the retrieved nursing level parameters into the currently trained recurrent neural network model to output the adjustment coefficient of the current nursing level result, and carry out nursing work according to the size of the current adjustment coefficient.

2. The intelligent nursing method for severe hyperthermia patients according to claim 1 is characterized in that: The method for obtaining the nursing level data in step S1 is: Determine the set of vital sign change parameters {x1, x2, ... x m }; Determine the characteristic parameter set {B1, B2, ... B1, B2, ... B2, B1, B2, ... ... n }, n is the number of effective nursing cycles; Obtain the characteristic parameter set B of the condition change in each effective nursing cycle i All elements of {(y1) i , (y2) i ,……(y m ) i } and the corresponding vital sign change parameter set {x1, x2, ... x m ) to form a new set C, and the set v∈{(x1y1) i , (x2y2) i ,……(x m y m ) i }; i is the current effective nursing cycle; m is the total number of time points in the effective nursing cycle; Take all elements in the new set C as the training set and input them into the recurrent neural network model for training to obtain the effective nursing value corresponding to each element, and divide the current effective nursing value from large to small according to the preset effective nursing value threshold interval and output the nursing level result.

3. The intelligent nursing method for severe hyperthermia patients according to claim 2 is characterized in that: The calculation method of the effective nursing value is: By formula Calculate the real-time effective nursing value Ef j ; Where, j is the current time point, and j∈[1,m]; ε, δ are both preset weight coefficients, and ε, δ are both greater than 0; f is the preset nursing function; Vs j is the vital sign change parameter at the current time point, Vs j0 is the standard vital sign change parameter at the same time point, ΔVs j Q is the deviation value of the vital sign change parameter at the preset current time point; k is the disease condition change conversion function, k is the disease condition change characteristic; Co j is the characteristic parameter of the disease change at the current time point, Co j0 is the characteristic parameter of the standard disease condition change at the current time point; β i is the influence coefficient of the i-th effective nursing cycle.

4. The intelligent nursing method for severe hyperthermia patients according to claim 3 is characterized in that: The nursing level results include: The current effective care value Ef j Compared with the preset effective nursing value threshold interval [Ef a , Ef b ] for comparison: If Ef j <Ef a , then it is judged that the current effective nursing care is excellent, less nursing intervention is needed, and the nursing level is determined to be level 3 nursing; If Ef a ≤Ef j ≤Ef b , then the current effective nursing quality is judged to be average, more nursing intervention is needed, and the nursing level is determined to be secondary nursing; If Ef j >Ef b , then it is judged that the current effective nursing quality is poor and more nursing intervention is needed, and the nursing level is determined to be primary care.

5. The intelligent nursing method for severe hyperthermia patients according to claim 1 is characterized in that: The monitoring safety risk prompt information includes: Confirm the nursing level signal of each critically ill patient with high fever according to the nursing level result; Confirm and match the corresponding nursing staff information according to the nursing level signal; the nursing staff information includes the nursing staff level and the nursing staff experience parameter; Generate a warning signal according to the first-level nursing level, and monitor the change of the nursing status of critically ill patients with high fever at the first-level nursing level.

6. The intelligent nursing method for severe hyperthermic patients according to claim 5 is characterized in that: In step S3: Input the nursing level signals and the corresponding nursing staff information of all critically ill patients with high fever into the analysis model of the preset nursing classification system to output the nursing level parameters; And feedback the adjustment information of critically ill patients with high fever at the first-level nursing level according to the warning signal, and generate an adjustment form.

7. The intelligent nursing method for severe hyperthermia patients according to claim 4 is characterized in that: In step S4: By formula Calculate the adjustment coefficient Adj; Among them, Δt is the preset time period within the effective nursing cycle time points; Nur i is the real-time nursing level parameter in the cumulative time period of the i-th effective nursing cycle, Nur i0 is the preset standard nursing level parameter of the i-th effective nursing cycle, ΔNur i is the deviation value of the preset nursing level parameter of the i-th effective nursing cycle; H(·) is the conversion function of the nursing level parameter; Ef i (t) is the real-time effective nursing value of the i-th effective nursing cycle.

8. The intelligent nursing method for severe hyperthermic patients according to claim 1 is characterized in that: Compare the adjustment coefficient Adj with the preset adjustment coefficient threshold interval [Adj1, Adj2]: If Adj ∈ [Adj1, Adj2], it is determined that the current adjustment coefficient is normal, maintain the current nursing level, and continue to maintain the current nursing work; If Adj > Adj2, it is determined that the current adjustment coefficient is too large, lower the current nursing level, and carry out corresponding nursing work according to the adjustment result; If Adj(t) < Adj1, it is determined that the current adjustment coefficient is too small, raise the current nursing level, and carry out corresponding nursing work according to the adjustment result.

Images