A drug rash patient management system and a nursing plan generation method
Through the drug rash patient management system and BP neural network generation nursing program, the inefficiency problem of drug rash record management and nursing program design in the existing technology is solved, and rapid and accurate nursing program generation and personalized nursing are achieved, and nursing is improved. Effect and efficiency.
Patent Information
- Application Number
- CN202110346988.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-31
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-03-31
AI Technical Summary
The prior art cannot effectively manage and query the records of patients with drug rashes, and cannot quickly generate personalized nursing plans, resulting in medical staff spending a lot of time on artificial design, which is prone to errors.
A drug rash patient management system was designed, including an information management system, an information acquisition system and an information storage unit. The BP neural network was used to generate nursing plans, combined with image and text input, and automatically generate diet, medication and psychological care plans based on the patient's Generate exclusive care plans in specific situations.
It realizes convenient query and management of patient information, and the generated nursing plans are more in line with individual needs, reduces the working hours of medical staff, and improves nursing effect and efficiency.
Smart Images

Figure CN113066548B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of drug rash nursing, and in particular to a drug rash patient management system and a nursing program generating method. Background Art
[0002] Drug rash is also called drug eruption. It is an inflammatory reaction of the skin and mucous membranes caused by drugs entering the human body through various routes such as oral administration, injection, inhalation, suppository, perfusion and external absorption. The morphology of drug rash can be varied, and the time of rash onset varies from person to person, and also varies from male to female patients. In order to conveniently record and check the dosage, adverse reactions, visit time, treatment measures and disappearance time of the patient's medication, clinical work sometimes needs to ask the patient, but the patient's memory may not be accurate, and it may be inaccurate, and querying medical records is time-consuming and laborious, and difficult to search; Chinese patent CN201880020400.5 proposes an electronic medical record management system and method, which can facilitate doctors to quickly and comprehensively view the patient's medical record information, but the following problems still exist:
[0003] 1. It is not possible to manage and compare patients with drug rash, and it is not possible to query the drug rash records of patients conveniently and quickly;
[0004] 2. It is not possible to directly generate nursing plans based on the different types of drug rash patients. Medical staff are required to manually design nursing plans, which is not only time-consuming but also prone to errors. Summary of the invention
[0005] 1. Technical issues to be resolved
[0006] In view of the deficiencies in the prior art, one of the purposes of the present invention is to provide a drug rash patient management system to solve the problems of being unable to manage and compare drug rash patients and being unable to conveniently and quickly query patients' drug rash records.
[0007] The second purpose is to provide a method for generating nursing plans for patients with drug rash, so as to solve the problem that nursing plans cannot be directly generated according to different drug rash patients, and medical staff are required to manually design nursing plans, which is not only time-consuming but also prone to errors.
[0008] (II) Technical solution
[0009] To achieve the above-mentioned object, the present invention provides the following technical solutions: a drug rash patient management system, comprising an information management system, an information acquisition system, an information storage unit and a display device;
[0010] The information management system is used to unify the allocation information acquisition system, information storage unit and display device, and is used for the calculation and processing of various information;
[0011] The information acquisition system includes an image acquisition unit and a text input unit, the text input unit inputs the patient's information, and the image system acquires the QR code or rash image information;
[0012] The information storage unit is used to store various information of the patient, including identity information, medication information, consultation time, rash area and rash disappearance time, etc.;
[0013] The display device is used to display, retrieve and input various information, and can directly display and compare the information in the information storage unit.
[0014] Preferably, after storing the patient information, the information storage unit generates a process chart that changes with time based on data changes in different time periods, for comparison by medical staff.
[0015] Preferably, the information management system can also directly extract the patient information in the information storage unit, and then generate a nursing plan based on different patients using a neural network, and generate an expected nursing effect.
[0016] Preferably, the area of the rash is acquired based on the rash image.
[0017] A method for generating a nursing plan for a patient with drug rash, which determines the patient's various indicator information and nursing level based on the patient's condition and BP neural network, comprises the following steps:
[0018] Step 1: Enter the patient's age, height, weight, medication information, visit time, rash area, and last rash disappearance time;
[0019] Step 2: confirm the input layer neuron vector x = {x1, x2, x3, x4, x5, x6, x7} of the three-layer BP neural network;
[0020] Among them, x1 is the patient's age, x2 is the patient's height, x3 is the patient's weight, x4 is the patient's medication information, x5 is the patient's visit time, x6 is the patient's rash area, and x7 is the patient's last rash disappearance time;
[0021] Step 3: The input layer vector is mapped to the middle layer, and the middle layer vector y={y1,y2,y3...y m};
[0022] Where m is the number of nodes in the middle layer;
[0023] Step 4: Get the output layer neuron vector o={o1,o2,o3...o5};
[0024] Among them, o1 represents the patient's stress tolerance level, o2 represents the patient's susceptibility to stress, o3 represents the medications that the patient can take, o4 represents the patient's nursing level, and o5 represents the frequency of the patient's nursing. The output layer neuron value is When o1 is A1, the patient's stress resistance level is weak, when o1 is B1, the patient's stress resistance level is medium, and when o1 is C1, the patient's stress resistance level is strong; When o2 is A2, the patient's susceptibility to flare-ups is weak, when o2 is B2, the patient's susceptibility to flare-ups is moderate, and when o2 is C2, the patient's susceptibility to flare-ups is strong; When o4=1, it represents primary care, when o4=2, it represents secondary care, and when o4=3, it represents tertiary care.
[0025] Preferably, a dietary care plan is obtained, specifically including:
[0026] Get the patient's daily food intake:
[0027] in is the normal daily food intake of the human body, m is the patient's weight, h is the patient's height, h0 is the average height of a person, and m0 is the standard weight corresponding to the average height of a person;
[0028] Get the patient's daily water intake:
[0029] in is the normal daily water intake of the human body, e is the base of the natural logarithm, t is the patient's body temperature, t0 is the normal body temperature of the human body, t max is the maximum temperature in the room, t min is the lowest temperature in the room, s represents the patient's age coefficient, s = 0 when the age is older than fourteen years old, and s = 0.2 when the age is younger than fourteen years old;
[0030] Generate a dietary care plan based on the patient's daily food and water intake.
[0031] Preferably, obtain a medication care plan, specifically including:
[0032] Get the patient's medication time:
[0033] Where T r represents the dosage of drug r, r = 1, 2, 3...n, represents drug 1, drug 2 and drug n, s0 represents the age of the patient, s1 represents the number of years the patient has used the drug that caused the rash, T 0r represents the usual dosage of the drug;
[0034] Generate a medication care plan based on medication time, medication type, and the patient's susceptibility to rash.
[0035] Preferably, a psychological care plan is generated according to the patient's stress tolerance level, nursing level and nursing frequency, and the content of the psychological care plan includes asking the patient about his or her psychological state, giving reasonable small gifts, outdoor activities and watching entertainment programs, etc.
[0036] Preferably, after generating the dietary care plan, medication care plan and psychological care plan, the expected care effect is obtained, including the healthy state of the diet, the degree of improvement of the disease and the psychological state.
[0037] (III) Beneficial effects
[0038] Compared with the prior art, the present invention has the following beneficial effects:
[0039] 1. The drug rash patient management system provided by the present invention is simple to operate, convenient for medical staff to query at any time, and can be modified and stored. After the same type of information is updated, a chart is generated according to the change over time, and then displayed through a display device, so that medical staff can compare and obtain the progress of treatment, which is more convenient for medical staff to use.
[0040] 2. The present invention provides a method for generating a nursing plan for patients with drug rash, which automatically generates different nursing plans. Taking into account various information of the patients, it is possible to generate exclusive nursing plans according to different patients, so that the later nursing effects are better. The automatic generation of nursing plans takes less time, which can facilitate medical staff to obtain nursing plans more quickly, saving a lot of time. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 This is a flow chart of a drug rash patient management system according to the present invention;
[0042] Figure 2 The present invention is a flowchart of a method for generating a nursing plan for patients with drug rash. DETAILED DESCRIPTION
[0043] 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.
[0044] See also Figure 1 , a drug rash patient management system, comprising an information management system, an information acquisition system, an information storage unit and a display device;
[0045] The information management system is used to uniformly allocate information acquisition systems, information storage units and display devices, and is used for the calculation and processing of various information;
[0046] The information acquisition system includes an image acquisition unit and a text input unit, the text input unit inputs the patient's information, and the image system acquires the QR code or rash image information;
[0047] The information storage unit is used to store various information of the patient, including identity information, medication information, consultation time, rash area and rash disappearance time, etc.;
[0048] The display device is used to display, retrieve and enter various information, and can directly display and compare the information in the information storage unit.
[0049] After the information storage unit stores the patient information, it generates a process chart that changes with time based on the data changes in different time periods, which is used for comparison by medical staff.
[0050] The information management system can also directly extract patient information from the information storage unit, and then use the neural network to generate nursing plans and expected nursing effects based on different patients.
[0051] The area of the rash is obtained based on the rash image.
[0052] After entering the information of the drug rash patient, a QR code or barcode information is generated as identity information, and then the various information of the drug rash patient can be obtained by directly scanning the code. The operation is simple, which is convenient for medical staff to query, and can be changed and stored. After the same type of information is updated, a chart is generated according to the change over time, and then displayed through a display device, so that medical staff can compare and obtain the progress of treatment.
[0053] See also Figure 2 A method for generating a nursing plan for drug rash patients, which determines the patient's various indicator information and nursing level based on the BP neural network according to the patient's condition, includes the following steps:
[0054] Step S10: Establish a database with various information of the patient:
[0055] Enter the patient's age, height, weight, medication information, visit time, rash area, and last time the rash resolved.
[0056] Step S20: Establishing a BP neural network model:
[0057] In the BP model, neurons at all levels are fully interconnected, and there is no connection between neurons within each level. The output of neurons in the input layer is the same as the input, that is, i =xi , the operating characteristics of the neurons in the intermediate layer and the output layer are:
[0058] net pj =∑ i ω ji o pi
[0059] o pj =f j (net pj )
[0060] Where p represents the current input sample, ω ji is the connection weight from neuron i to neuron j, o pi is the current input of neuron j, o pj For its output; f j is a nonlinear differentiable non-decreasing function, generally taken as an S-type function, that is, f j (x) = 1 / (1+e -x ).
[0061] The BP network architecture adopted in the present invention consists of three layers. The first layer is the input layer, which has n nodes in total, corresponding to the n input signals representing the patient; the second layer is the middle layer, which has m nodes in total, which is determined in an adaptive manner by the network training process; the third layer is the output layer, which has p nodes in total, which is determined by the response that the system actually needs to output.
[0062] The mathematical model of the network is:
[0063] Input vector: x = (x1, x2, ..., x n ) T
[0064] Intermediate layer vector: y=(y1,y2,...,y m ) T
[0065] Output vector: o = (o1, o2, ..., o p ) T
[0066] In the present invention, the number of input layer nodes is n=7, the number of output layer nodes is p=5, and the number of hidden layer nodes is m=10.
[0067] The 7 parameters of the input layer are expressed as follows: x1 is the patient's age, x2 is the patient's height, x3 is the patient's weight, x4 is the patient's medication information, x5 is the patient's visit time, x6 is the patient's rash area, and x7 is the patient's last rash disappearance time;
[0068] The output layer parameters are as follows: o1 represents the patient's stress tolerance level, o2 represents the patient's susceptibility to disease, o3 represents the medication the patient can take, o4 represents the patient's nursing level, and o5 represents the frequency of the patient's nursing. The output layer neuron value is When o1 is A1, the patient's stress resistance level is weak, when o1 is B1, the patient's stress resistance level is medium, and when o1 is C1, the patient's stress resistance level is strong; When o2 is A2, the patient's susceptibility to flare-ups is weak, when o2 is B2, the patient's susceptibility to flare-ups is moderate, and when o2 is C2, the patient's susceptibility to flare-ups is strong; When o4=1, it represents primary care, when o4=2, it represents secondary care, and when o4=3, it represents tertiary care.
[0069] Step S30: Perform BP neural network training:
[0070] After the BP neural network node model is established, the BP neural network training can be carried out. The training samples are obtained according to the historical experience data of the product, and the connection weights between the input node i and the hidden layer node j, and the connection weights between the hidden layer node j and the output layer node k are given.
[0071] 1. Training Methods
[0072] Each subnetwork is trained separately. During training, a set of training samples must be provided first. Each sample consists of an input sample and an ideal output pair. When all actual outputs of the network are consistent with their ideal outputs, the training is completed. Otherwise, the ideal output of the network is made consistent with the actual output by correcting the weights.
[0073] 2 Training Algorithm
[0074] The BP network uses the Backward Propagation algorithm for training, and its steps can be summarized as follows:
[0075] Step 1: Select a network with a reasonable structure and set the initial values of all node thresholds and connection weights.
[0076] Step 2: Calculate each input sample as follows:
[0077] a Forward calculation: for the j unit of layer l
[0078]
[0079] In the formula, is the weighted sum of the information of j units in layer l during the nth calculation, is the connection weight between unit j in layer l and unit i in the previous layer (i.e., layer l-1), For the previous layer (i.e., layer l-1, the number of nodes is n l-1 ) is sent by unit i; when i = 0, let is the threshold of unit j in layer l.
[0080] If the activation function of unit j is the sigmoid function, then
[0081]
[0082] and
[0083]
[0084] If neuron j belongs to the first hidden layer (l = 1), then
[0085]
[0086] If neuron j belongs to the output layer (l = L), then
[0087] And e j (n) = x j (n)-o j (n);
[0088] b Reverse calculation error:
[0089] For output units
[0090]
[0091] Hidden Unit
[0092]
[0093] c Correction weight:
[0094]
[0095] Step 3: Input new samples or samples from a new cycle until the network converges. During training, the input order of samples in each cycle must be re-randomized.
[0096] The BP algorithm uses the gradient descent method to find the extreme value of nonlinear functions, which has problems such as falling into local minima and slow convergence. A more effective algorithm is the Levenberg-Marquardt optimization algorithm, which shortens the network learning time and can effectively prevent the network from falling into local minima. The weight adjustment rate is selected as
[0097] Δω=(J T J+μI) -1 J T e
[0098] Where J is the Jacobian matrix of the error differential with respect to the weight, I is the input vector, e is the error vector, and the variable μ is an adaptively adjusted scalar that determines whether learning is done according to Newton's method or the gradient method.
[0099] When designing the system, the system model is a network that has only been initialized. The weights need to be learned and adjusted based on the data samples obtained during use. For this purpose, the system's self-learning function is designed. When the learning samples and quantity are specified, the system can perform self-learning to continuously improve network performance.
[0100] Step S40, obtaining the stress resistance level, the degree of proneness to rash, the medication that can be taken, the nursing level and the nursing frequency;
[0101] Step S41, obtaining a dietary care plan, specifically including:
[0102] Get the patient's daily food intake:
[0103] in is the normal daily food intake of the human body, m is the patient's weight, h is the patient's height, h0 is the average height of a person, and m0 is the standard weight corresponding to the average height of a person;
[0104] Get the patient's daily water intake:
[0105] in is the normal daily water intake of the human body, e is the base of the natural logarithm, t is the patient's body temperature, t0 is the normal body temperature of the human body, t max is the maximum temperature in the room, t min is the lowest temperature in the room, s represents the patient's age coefficient, s = 0 when the age is older than fourteen years old, and s = 0.2 when the age is younger than fourteen years old;
[0106] Generate a dietary care plan based on the patient's daily food and water intake.
[0107] Step S42: Obtaining a medication and nursing plan, specifically including:
[0108] Get the patient's medication time:
[0109] Where T r represents the dosage of drug r, r = 1, 2, 3...n, represents drug 1, drug 2 and drug n, s0 represents the age of the patient, s1 represents the number of years the patient has used the drug that caused the rash, T 0r represents the usual dosage of the drug;
[0110] Generate a medication care plan based on medication time, medication type, and the patient's susceptibility to rash.
[0111] Step S43: Generate a psychological care plan based on the patient's stress tolerance level, nursing level and nursing frequency. The psychological care plan includes asking the patient about his or her psychological state, giving reasonable small gifts, outdoor activities and watching entertainment programs, etc.
[0112] After generating dietary care plans, medication care plans and psychological care plans, the expected care effects can be obtained, including the health status of the diet, the degree of improvement of the disease and the psychological state.
[0113] Different nursing plans are automatically generated, taking into account various information of the patient. Therefore, exclusive nursing plans can be generated according to different patients, making the later nursing effects better. The automatic generation of nursing plans takes less time, which enables medical staff to get nursing plans faster and saves a lot of time.
[0114] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0115] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for generating a nursing plan for a patient with a drug rash, characterized in that: Includes care plan generation based on the drug rash patient management system; The drug rash patient management system comprises an information management system, an information acquisition system, an information storage unit and a display device; The information management system is used to uniformly coordinate the information acquisition system, the information storage unit and the display device, and is used for the calculation and processing of various information; The information acquisition system includes an image acquisition unit and a text input unit, the text input unit inputs the patient's information, and the image system acquires the QR code or rash image information; The information storage unit is used to store various information of the patient, including identity information, medication information, consultation time, rash area and rash disappearance time; The display device is used to display, retrieve and input various information, and can directly display and compare the information in the information storage unit; After the information storage unit stores the patient information, it generates a process chart that changes with time based on the data changes in different time periods, which is used for comparison by medical staff; The information management system directly extracts the patient information in the information storage unit, and then generates a nursing plan based on different patients using a neural network, and generates an expected nursing effect; Obtain the area of the rash based on the rash image; According to the patient's condition, the patient's various indicators and nursing level are determined based on the BP neural network, including the following steps: Step 1: Enter the patient's age, height, weight, medication information, visit time, rash area, and last rash disappearance time; Step 2: Confirm the input layer neuron vector of the three-layer BP neural network ; in, is the patient's age, is the patient's height, is the patient's weight, Medication information for patients, The patient's visit time, For patients with rash area, The time when the patient's last rash disappeared; Step 3: The input layer vector is mapped to the middle layer, and the middle layer vector ; Where m is the number of nodes in the middle layer; Step 4: Get the output layer neuron vector ; in Represents the patient's stress tolerance level. Represents the patient's susceptibility to disease. Represents the medications that the patient can take, represents the patient's level of care, Represents the frequency of patient care, and the output layer neuron value is ,when for When the patient's stress resistance level is weak, for When the patient's stress tolerance level is medium, for When , the patient's stress tolerance level is strong; ,when for When the patient's susceptibility to disease is weak, for When the patient's susceptibility to disease is moderate, for When the patient is at high risk of developing the disease, ,when When When, it represents secondary care, when , represents tertiary care; Get a dietary care plan that includes: Get the patient's daily food intake: ; in is the normal daily food intake of the human body, m is the patient's weight, h is the patient's height, The average height of a person, The standard weight corresponding to the average height of a person; Get the patient's daily water intake: ; in is the normal daily water intake of the human body, e is the base of the natural logarithm, t is the patient's body temperature, Normal body temperature, is the maximum temperature in the room, is the lowest temperature in the room, s represents the patient's age coefficient, s=0 when the age is older than fourteen years old, s=0.2 when the age is younger than fourteen years old; Generate a dietary care plan based on the patient's daily food and water intake; Get a medication care plan that includes: Get the patient's medication time: ; in Represents the dosage of drug r, r=1,2,3...n, represents drug 1, drug 2 and drug n, represents the patient's age, represents the number of years the patient used the drug that caused the rash. represents the usual dosage of the drug; Generate a medication care plan based on medication time, medication type, and the patient's susceptibility to rash.
2. The method for generating a nursing plan for drug rash patients according to claim 1, characterized in that: A psychological care plan is generated based on the patient's stress tolerance level, care level and care frequency. The psychological care plan includes asking the patient about his or her mental state, giving reasonable small gifts, outdoor activities and watching entertainment programs.
3. The method for generating a nursing plan for drug rash patients according to claim 2, characterized in that: After generating dietary care plans, medication care plans and psychological care plans, the expected care effects can be obtained, including the health status of the diet, the degree of improvement of the disease and the psychological state.
