CN119279520A

CN119279520A - Intelligent nursing methods for severe fever patients

Info

Publication number: CN119279520A
Application number: CN202411667964.1A
Authority: CN
Inventors: 臧莉; 刘佳佳
Original assignee: Fourth Military Medical University FMMU
Current assignee: Fourth Military Medical University FMMU
Priority date: 2024-11-21
Filing date: 2024-11-21
Publication date: 2025-01-10

Abstract

The invention relates to the technical field of intelligent nursing, and particularly discloses an intelligent nursing method for severe hyperthermia patients, which can improve the classification accuracy of intelligent nursing, achieve the aim of high-quality safe nursing for severe hyperthermia patients, and improve the clinical nursing value. The method comprises the steps of inputting vital sign change parameters of an intensive hyperthermia patient in a monitoring period and illness state change characteristics of the intensive hyperthermia patient in an effective nursing period into a circulating neural network model for training and outputting nursing grade results, obtaining monitoring safety risk prompt information according to the nursing grade results, retrieving nursing grade parameters in a preset nursing grading system according to the monitoring safety risk prompt information, inputting the retrieved nursing grade parameters into the circulating neural network model which is trained at present, outputting adjustment coefficients of the current nursing grade results, and developing nursing work according to the current adjustment coefficients.

Description

Intelligent nursing method for severe hyperthermia patient

Technical Field

The invention relates to the technical field of intelligent nursing, in particular to an intelligent nursing method for severe hyperthermia patients.

Background

The treatment and management of patients with severe hyperthermia is a complex process, and needs to comprehensively consider the specific disease and etiology of the patients, and when treating patients with severe hyperthermia, medical teams need to closely monitor the change of the disease of the patients and adjust the treatment scheme according to the latest clinical guidelines and research results. Meanwhile, the treatment method combining the traditional Chinese medicine and the western medicine can provide a more comprehensive treatment strategy so as to improve the treatment effect and the survival rate of patients.

The existing vital sign information of a patient and the current monitoring course and monitoring state of the patient are monitored in real time, a patient safety intelligent early warning system is generally constructed to monitor the nursing state of the patient to a certain extent, along with the rapid increase of patients with infectious diseases in recent years, more nursing staff is required to be added for coping with the increase of corresponding nursing persons, nursing wards and monitoring courses, and the real-time monitoring data of a monitoring end and corresponding management staff are required to be added, and generally, because of the limitation of the area of a treatment yard and the diversity of the disease types of the severe hyperthermia patients, isolation monitoring and other measures are required, a large number of monitoring staff are not beneficial to the treatment and rehabilitation process of the severe hyperthermia patients.

The existing intelligent and systematic nursing grading system based on the Internet of things is applied to nursing work, but with the increase of severe hyperthermia patients, due to the fact that the number of nursing staff is limited, the scheme of directly dispatching nursing staff is not suitable for nursing processes of a large number of severe hyperthermia patients any more, the nursing quality and efficiency of the existing grading nursing are difficult to objectively embody through data evaluation, analysis is needed according to specific data of the current nursing staff on the discovery rate of potential complications of the current patients, the postoperative complications and the occurrence rate of adverse events, however, for the severe hyperthermia patients, due to the fact that the severity of treatment urgency and life safety risk is high, the clinical efficiency is low only through nursing modes of oral ward communication of medical care, and the treatment recovery efficiency of the actual patients is affected.

Disclosure of Invention

The invention aims to provide an intelligent nursing method for severe hyperthermia patients, which solves the following technical problems:

how to improve the classification accuracy of intelligent nursing, achieve the high-quality safe nursing purpose of severe hyperthermia patients, and improve the clinical value of nursing.

The aim of the invention can be achieved by the following technical scheme:

an intelligent nursing method for severe hyperthermia patients, comprising the following steps:

S1, acquiring vital sign change parameters of a severe hyperthermia patient in a monitoring period and disease change characteristics of the severe hyperthermia patient in an effective nursing period, inputting the vital sign change parameters and the disease change characteristics of the severe hyperthermia patient in the effective nursing period into a recurrent neural network model for training, and outputting a nursing grade result;

the vital sign change parameters comprise a body temperature change value, a heart rate change value and a blood pressure change value;

the change characteristics of the disease include improvement, worsening and stabilization of the disease;

the nursing grade result is sequentially divided into primary nursing, secondary nursing and tertiary nursing from high to low according to the nursing intervention severity;

S2, acquiring monitoring safety risk prompt information according to a nursing grade result;

S3, according to the monitoring safety risk prompt information, invoking the nursing grade parameters in a preset nursing grading system;

S4, inputting the retrieved nursing grade parameters into a current trained cyclic neural network model, outputting an adjustment coefficient of a current nursing grade result, and carrying out nursing work according to the current adjustment coefficient.

Preferably, the method for acquiring the nursing grade data in step S1 is as follows:

Determining a vital sign change parameter set { x ₁,x₂,......x_m } of the critically ill and hyperthermia patient within the monitoring period;

Determining a disease change characteristic parameter set { B ₁,B₂,......B_n } of severe hyperthermia patients in all effective nursing periods, wherein n is the effective nursing period number;

All elements { (y ₁)_i,(y₂)_i,......(y_m)_i } of the illness state change characteristic parameter set B _i in each effective nursing period are obtained and combined with the corresponding vital sign change parameter set { x ₁,x₂,......x_m } in the same time point to form a new set C, wherein the set C∈{(x₁y₁)_i,(x₂y₂)_i,......(x_my_m)_i};i is the current effective nursing period;

and inputting all elements in the new set C as training sets into a cyclic neural network model for training, obtaining effective nursing values corresponding to each element, dividing the current effective nursing values from large to small according to a preset effective nursing value threshold interval, and outputting nursing level results.

Preferably, the effective care value is calculated by:

By the formula Calculating a real-time effective care value Ef _j;

Wherein j is the current time point, j is [1, m ], epsilon and delta are preset weight coefficients, epsilon and delta are both larger than 0;f and are preset nursing functions, vs _j is the vital sign change parameter of the current time point, vs _j0 is the standard vital sign change parameter of the same time point, deltaVs _j is the vital sign change parameter deviation value of the preset current time point, Q _k is a disease state change conversion function, k is a disease state change feature, co _j is a disease state change feature parameter of the current time point, co _j0 is the standard disease state change feature parameter of the current time point, and beta _i is the influence coefficient of the ith effective nursing period.

Preferably, the care grade result comprises:

Comparing the current effective care value Ef _j with a preset effective care value threshold interval [ Ef _a,Ef_b ]:

If Ef _j＜Ef_a is found, judging that the current effective nursing quality is good, the needed nursing intervention is less, and the nursing grade is set to be three-level nursing;

If Ef _a≤Ef_j≤Ef_b, judging that the current effective nursing quality is general, requiring more nursing interventions, and setting the nursing level as secondary nursing;

if Ef _j＞Ef_b, the current effective care quality is judged to be poor, more care interventions are needed, and the care level is set as primary care.

Preferably, the guardianship safety risk prompting information includes:

confirming a care grade signal for each critically ill, hyperthermia patient based on the care grade results;

confirming the nursing staff information matched with the corresponding grade according to the nursing grade signal, wherein the nursing staff information comprises nursing staff grade and nursing staff experience parameters;

Generating an early warning signal according to the primary care grade, and monitoring the change of the nursing state of the severe hyperthermia patient of the primary care grade.

Preferably, in step S3:

inputting the nursing grade signals of all severe hyperthermia patients and corresponding nursing staff information into an analysis model of a preset nursing grading system, and outputting nursing grade parameters;

And feeding back the adjustment information of the severe hyperthermia patient of the primary care level according to the early warning signal, and generating an adjustment table.

Preferably, in step S4:

By the formula Calculating an adjustment coefficient Adj;

The method comprises the steps of setting a time point of an effective nursing period in a preset time period, setting Nur _i as a real-time nursing grade parameter in an accumulated time period of the i-th effective nursing period, setting Nur _i0 as a preset standard nursing grade parameter of the i-th effective nursing period, setting DeltaNur _i as a deviation value of the preset nursing grade parameter of the i-th effective nursing period, setting H (·) as a conversion function of the nursing grade parameter, and setting Ef _i (t) as a real-time effective nursing value of the i-th effective nursing period.

Preferably, the adjustment coefficient Adj is compared with a preset adjustment coefficient threshold interval [ Adj ₁,Adj₂ ]:

If the Adj epsilon [ Adj ₁,Adj₂ ], judging that the current adjustment coefficient is normal, keeping the current nursing level, and continuously keeping the current nursing work;

If Adj > Adj ₂, judging that the current adjustment coefficient is larger, reducing the current nursing grade, and carrying out corresponding nursing work according to the adjustment result;

If Adj (t) < Adj ₁, judging that the current adjustment coefficient is smaller, improving the current nursing grade, and carrying out corresponding nursing work according to the adjustment result.

The method has the beneficial effects that vital sign change parameters of the severe hyperthermia patient in a monitoring period and illness state change characteristics of the severe hyperthermia patient in an effective nursing period are obtained, the patient is input into the recurrent neural network model for training, a nursing grade result is output, nursing conditions of the severe hyperthermia patient are reflected through monitoring safety risk prompt information, and corresponding nursing staff are matched accurately according to nursing grade signals to form nursing and safety monitoring processes of the severe hyperthermia patient in different grades. And inputting the nursing grade parameters after the calling into a current trained circulatory neural network model to output an adjustment coefficient of a current nursing grade result, and developing nursing work according to the current adjustment coefficient.

Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of the intelligent nursing method for severe hyperthermia patients.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, in order to solve the above technical problems, the method for intelligent care of severe hyperthermia patients of the present invention includes:

In the above technical solution, in this embodiment, the care level is obtained by analyzing the existing disease state monitoring result, monitoring security risk prompt is performed, and the rationality of the care level parameter is determined according to the monitoring security risk prompt information, and finally, the further accurate process of the care related data is realized by adjusting the care level, which specifically includes the following steps:

firstly, step S1 is to input a circulating neural network model training by acquiring vital sign change parameters of a patient with severe hyperthermia in a monitoring period and illness state change characteristics of the patient with severe hyperthermia in an effective nursing period and output a nursing grade result, wherein the vital sign change parameters comprise a body temperature change value, a heart rate change value and a blood pressure change value based on medical physiological knowledge analysis, the illness state change characteristics comprise illness state improvement, illness state deterioration and illness state stabilization, the nursing grade is sequentially divided into primary nursing, secondary nursing and tertiary nursing according to nursing intervention severity from high to low, and different from a method of directly distributing nursing staff to a patient of a general type, the nursing method is used for judging nursing demands of the patient from nursing intervention angle degree, and a more proper nursing mode is provided.

The circulating neural network model is used for training vital sign change parameters of the severe hyperthermia patient in a monitoring period and disease change characteristic sequence data of the severe hyperthermia patient in an effective nursing period, judging the relation between self-care ability and nursing requirement of the patient, acquiring nursing grades, and dividing historical data marked with nursing grade results into a training set, a verification set and a test set. For example, according to the medical record data of the prior severe hyperthermia patient, the vital sign change parameters, the illness change characteristics and the corresponding nursing grade results are determined, and then the patient is divided into a training set, a verification set and a test set according to a certain proportion (such as 7:2:1). In the actual training process, a loss function (such as a cross entropy loss function) is used to measure the difference between the model output result and the real care grade result. The model weights are continually adjusted by the back propagation algorithm to minimize the loss function. And if the loss of the verification set starts to rise or the accuracy is not improved, the phenomenon that the model is over-fitted is indicated, and the structure or training parameters of the model need to be adjusted (such as reducing the learning rate, increasing the regularization term and the like).

Specifically, the method for acquiring the nursing grade data in step S1 includes:

According to the technical scheme, the matching reference of the nursing demands of the severe hyperthermia patient is achieved through the acquisition of the nursing grade, specifically, a vital sign change parameter set { x ₁,x₂,......x_m } of the severe hyperthermia patient in a monitoring period is firstly determined, combination analysis is carried out according to a body temperature change value, a heart rate change value and a blood pressure change value of the vital sign change parameter set { x ₁,x₂,......x_m }, then a disease change characteristic parameter set { B ₁,B₂,......B_n } of the severe hyperthermia patient in all effective nursing periods is determined, statistical combination is carried out on conditions of disease improvement, disease deterioration and disease stability in the disease change characteristic data, then calculation analysis is carried out to obtain a disease change characteristic parameter under each effective nursing period, further, time matching recombination is carried out on the two sets of information, all elements { (y ₁)_i,(y₂)_i,......(y_m)_i } of the disease change characteristic parameter set B _i in each effective nursing period are obtained and elements in the corresponding vital sign change parameter set { x ₁,x₂,......x_m } in the same time point are combined to form a new set C, finally all elements in the new set C are taken as training sets to be input into a training set, the training set to obtain corresponding effective nursing values, and the current nursing values are divided into a large-level nursing range according to the effective nursing values, and the current nursing values are divided into the current nursing values and the effective nursing values are provided.

The effective nursing period is relative to the condition change information data of the patient, and can be called as an effective nursing period as long as the patient treatment is improved or the deterioration is slowed down within the time distance under the intervention of a historical medical staff, and the effective nursing period is usually staged and also comprises a plurality of effective nursing periods due to the stage of a hospital treatment scheme and different disease treatment course time spans in the treatment or rehabilitation process.

As an implementation manner of the present invention, the effective care value is calculated in this embodiment, and a specific calculation manner is as follows:

By the formula Calculating a real-time effective care value Ef _j;

According to the technical scheme, the nursing quality condition corresponding to the nursing requirement of the severe hyperthermia patient, which is the current element, can be directly judged through the effective nursing value, and the effective nursing value is judged through analyzing the vital sign change parameters and the illness state change characteristic parameters as main factors, so that the accurate confirmation of the effective nursing value at the current time point is realized.

It should be explained that the preset weight coefficient epsilon and delta are selected and set according to experience data, the specific setting can be quantitatively or qualitatively set by judging the specific gravity of the vital sign change influence and the disease change characteristic influence to the effective nursing result in the whole nursing requirement, and the disease change conversion function Q _k is obtained by fitting according to the disease change characteristic parameter test data of the current patient in the normal nursing state.

The preset function is usually a predefined rule or logic in some systems or algorithms for guiding the distribution process of resources, data or tasks, and the preset care function f in the design is customized according to the specific condition and disease change of the patient, is an optimized function set according to the historical data condition, and can ensure that the result calculated by the current formula accords with the reasonable range of effective care values.

Vs _j0、Co_j0 are respectively determined by machine simulation of the average value or average variance of the vital sign change effect and the disease change characteristic effect data in normal effective nursing requirement state, deltaVs _j are selected and set according to empirical data, which are not described in detail herein, and the effective nursing period influence coefficient beta _i is selected and set according to comprehensive nursing states of different effective nursing periods of severe hyperthermia patients, which are not described in detail herein.

As one embodiment of the present invention, the care grade results include:

In the above technical solution, the care level result in this embodiment is determined by the size of the effective care value Ef _j, and by comparing the size with the preset effective care value threshold interval [ Ef _a,Ef_b ], if Ef _j＜Ef_a, it is determined that the current effective care quality is good, less care intervention is required, the care level is determined to be three-level care, if Ef _a≤Ef_j≤Ef_b, it is determined that the current effective care quality generally requires more care intervention, the care level is determined to be two-level care, if Ef _j＞Ef_b, it is determined that the current effective care quality is poor, more care interventions are required, the care level is determined to be one-level care, and the accurate determination of the care level is achieved. It should be noted that the final care level of the patient is comprehensively determined according to the real-time effective care value Ef _j of the effective treatment period or the preset period.

And step S2, the nursing condition of the severe hyperthermia patient is reflected by the monitored safety risk prompt information, and nursing and safety monitoring processes of the severe hyperthermia patient with different nursing grades are formed by accurately matching corresponding nursing staff according to the nursing grade signals.

As one embodiment of the present invention, the guardian security risk prompting message includes:

According to the technical scheme, the monitoring safety risk prompt information mainly comprises a nursing grade signal of each severe hyperthermia patient according to a nursing grade result, then, nursing personnel information matched with the corresponding grade is confirmed according to the nursing grade signal, the nursing personnel information comprises nursing personnel grade and nursing personnel experience parameters, and an early warning signal is generated according to the primary nursing grade to monitor nursing state change of the severe hyperthermia patient of the primary nursing grade.

Then, step S3 is to retrieve the nursing grade parameters in the preset nursing grading system according to the monitoring safety risk prompt information, specifically to input the nursing grade signals of all the severe hyperthermia patients and the corresponding nursing personnel information into an analysis model of the preset nursing grading system to output the nursing grade parameters, and to feed back the adjustment information of the severe hyperthermia patients with the primary nursing grade according to the early warning signals and to generate an adjustment table.

According to the technical scheme, the safety risk prompt information is monitored through the analysis of the last step, and the patient care level is prompted, so that patient care staff are allocated, the current display information is trained through the analysis model of the existing care grading system, the parameterized result of the care level is achieved, the current care level parameter is output, meanwhile, the adjustment information of the severe hyperthermia patient of the primary care level is fed back according to the early warning signal, and an adjustment table is generated.

The analytical model of the care grading system is a triagle model, which is a commonly used model for determining disability level and care level, and a graded care system comprising three-level care rating indexes is constructed by combining a literature-based evidence-based method and related rating scales. For example, primary care assessment indicators may include activities of daily living, functional daily activity care, medical care, and mental well-being.

And finally, step S4, readjusting the nursing grade data in the pre-trained cyclic neural network model according to the acquired nursing grade parameters, generating corresponding adjustment coefficients, carrying out corresponding nursing work according to the sizes of the adjustment coefficients, carrying out intervention analysis on the effective nursing values corresponding to the pre-acquired nursing grade data through the brought nursing grade parameters, outputting the adjustment coefficients, and timely completing updating and adjusting of the nursing grade data.

As an embodiment of the present invention, specifically, the method for obtaining the adjustment coefficient in step S4 includes:

By the formula Calculating an adjustment coefficient Adj;

In the above technical solution, the relationship between the preset care level parameter of the effective care period and the implemented effective care value is calculated to obtain the real-time adjustment coefficient Adj (t), and the conversion is mainly performed on the reference value of the current preset care level parameter through the conversion function H (·), where the conversion function H (·) is obtained by fitting the care test data in the accumulated time period of the current effective care period, and the effective care value in the current state is substituted to perform calculation, so as to determine the value of the obtained real-time adjustment coefficient.

It should be noted that, the preset time period Δt is determined according to empirical data, and can be adaptively adjusted according to specific clinical condition monitoring requirements, nur _i0 is a standard value obtained by combining and calculating a vital sign change parameter and condition change characteristic information in a current normal care period state, and Δnur _i is selected and set according to empirical data, which is not described in detail herein.

As an embodiment of the present invention, the adjustment coefficient Adj is compared with a preset adjustment coefficient threshold interval [ Adj ₁,Adj₂ ]:

In the above technical solution, in this embodiment, the adjustment information of the care level is determined by analyzing the magnitude of the adjustment coefficient, and the care work is performed according to the specific adjustment direction.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the part of the description of method embodiments being relevant.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar thereto, by those skilled in the art, without departing from the principles of the invention or beyond the scope of the appended claims.

Claims

1. An intelligent nursing method for severe hyperthermic patients, characterized in that the method comprises:

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;

The vital sign change parameters include: body temperature change value, heart rate change value, blood pressure change value;

The characteristics of the disease condition change include: improvement of the disease condition, worsening of the disease condition, and stable disease condition;

The nursing level results are divided into primary nursing, secondary nursing and tertiary nursing according to the severity of nursing intervention from high to low;

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

S3. Retrieving nursing grade parameters in the preset nursing grade 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 hyperthermic patients according to claim 1 is characterized in that the method for obtaining the nursing level data in step S1 is:

Determine a set of vital sign change parameters {x ₁ , x ₂ , ... x _m } of severe high fever patients during a monitoring period;

Determine a set of characteristic parameters of the condition change of severe hyperthermic patients in all effective nursing cycles {B ₁ , B ₂ , ... B _n }, where n is the number of effective nursing cycles;

Get all elements {(y ₁ ) _i , (y ₂ ) _i , … (y _m ) _i } of the condition change characteristic parameter set B _i in each effective nursing cycle and combine them with the corresponding vital sign change parameter set {x ₁ , x ₂ , … x _m ) at the same time point to form a new set C, and the set v∈{(x ₁ y ₁ ) _i , (x ₂ y ₂ ) _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;

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.

3. The intelligent nursing method for severe hyperthermic patients according to claim 2 is characterized in that the effective nursing value is calculated as follows:

By formula Calculate the real-time effective nursing value Ef _j ;

Among them, j is the current time point, and j∈[1, m]; ε and δ are both preset weight coefficients, and ε and 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 is the preset deviation value of the vital sign change parameter at the current time point; Q _k is the condition change conversion function, k is the condition change characteristic; Co _j is the condition change characteristic parameter at the current time point, Co _j0 is the standard condition change characteristic parameter 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 hyperthermic patients according to claim 3, characterized in that the nursing level result includes:

Compare the current effective nursing value Ef _j with the preset effective nursing value threshold interval [Ef _a , Ef _b ]:

If Ef _j <Ef _a , the current effective nursing care is judged to be excellent, less nursing intervention is required, and the nursing level is determined to be level 3 nursing;

If Ef _a ≤Ef _j ≤Ef _b , the current effective nursing quality is judged to be average, requiring more nursing intervention, and the nursing level is determined to be secondary care;

If Ef _j > Ef _b , the current effective nursing quality is judged to be poor and more nursing intervention is needed, and the nursing level is determined to be primary care.

5. The intelligent nursing method for severe hyperthermic patients according to claim 1, characterized in that the monitoring safety risk prompt information includes:

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

Confirming 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;

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.

6. The intelligent nursing method for severe hyperthermic patients according to claim 5, characterized in that in step S3:

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;

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.

7. The intelligent nursing method for severe hyperthermic patients according to claim 4, characterized in that in step S4:

By formula Calculate the adjustment coefficient Adj;

Wherein, Δt is the preset time period within the effective nursing cycle time point number; _Nuri is the real-time nursing level parameter within the cumulative time period of the i-th effective nursing cycle, _Nuri0 is the preset standard nursing level parameter of the i-th effective nursing cycle, _ΔNuri 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, characterized in that the adjustment coefficient Adj is compared with a preset adjustment coefficient threshold interval [Adj ₁ , Adj ₂ ]:

If Adj∈[Adj ₁ , Adj ₂ ], the current adjustment coefficient is judged to be normal, the current nursing level is maintained, and the current nursing work is continued;

If Adj＞Adj ₂ , 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;

If Adj(t)<Adj ₁ , the current adjustment coefficient is judged to be too small, the current nursing level is improved, and corresponding nursing work is carried out according to the adjustment results.