Ward calling system and method based on intelligent nursing vehicle

Abstract

The invention discloses a ward calling system and method based on an intelligent nursing vehicle, and belongs to the technical field of medical nursing equipment, and the method comprises the steps: S1, installing a nursing vehicle display terminal which carries out data interaction with a nurse station display control terminal on the nursing vehicle; s2, when a patient presses a calling button at the bedside, the sickbed calling terminal sends a nursing request signal to the nurse station display control terminal; s3, the nurse station display control terminal sends the nursing request signal to a nursing vehicle display terminal; s4, the nursing vehicle display terminal sends a nursing signal; s5, the nurse carries out confirmation and processing through the nurse station display control terminal or any one nursing vehicle display terminal; and S6, after confirmation, cancelling the calling signals of the nurse station display control terminal and the nursing vehicle display terminal. The nursing vehicle serves as a carrier of the display control terminal, on one hand, the nursing request can be received in time, and on the other hand, intelligent sorting of the nursing priority can be achieved through the nursing priority module.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical care equipment, and in particular relates to a ward calling system and method based on an intelligent nursing vehicle. Background Art

[0002] In the modern medical environment, the ward call system plays a vital role. It is an efficient communication tool specially designed for use within the hospital, especially between the nurse station and the bed. Through this system, patients can easily call and talk with nurses, so as to quickly obtain necessary medical services and care. This system not only provides great convenience for patients, enabling them to get the help they need in a timely manner, but also significantly improves the overall service efficiency of the hospital and the quality of the medical environment. The ward call system mainly consists of several parts, including the hospital intercom system host (usually located at the nurse station), the extension next to the bed, and the waterproof extension designed for the bathroom. In addition, the system may also include ward door phones, display screens in the corridor, three-color door lights to indicate the patient's status, alarms during infusion, and auxiliary equipment such as wireless watch transmitters and receivers.

[0003] In actual hospital operations, we often observe the following common situations:

[0004] Situation 1: When patients feel unwell or need help, they will press the call button at the bedside to send a signal for help. However, since the nurse in charge of the patient may be busy working in other wards and cannot immediately detect this signal, this may result in the patient's urgent needs not being responded to in a timely manner. This situation will not only delay the patient's treatment and care process, but may also cause additional anxiety and inconvenience to the patient, affecting their recovery experience.

[0005] Case 2: In some cases, multiple patients may press the call button at the bedside almost at the same time to send out a signal for help. In this case, the nurse needs to prioritize and process these signals. In traditional technical applications, this priority judgment often relies on the subjective judgment of the nurse, but this subjectivity often lacks scientific basis, sometimes leading to unreasonable processing order, which in turn affects the patient's treatment effect and nursing quality.

[0006] In view of the above situation, it is particularly urgent to develop a new type of ward call system. This system should ensure that nurses can receive the signals sent by patients through the caller in time, and can make objective and scientific priority judgments on multiple signals sent simultaneously. The ward call system based on intelligent nursing vehicles and related methods are proposed to solve this problem. By introducing intelligent technology, this system can automatically record and analyze call signals, and intelligently provide nurses with priority sorting suggestions based on the patient's urgency and actual situation, thereby ensuring that every patient can receive timely and appropriate nursing services. This innovation can not only improve the work efficiency of the hospital, but also significantly improve the patient's medical experience, and has very important practical application value. Summary of the invention

[0007] The purpose of the present invention is to meet actual needs and provide a ward call system and method based on an intelligent nursing car. The nursing car is used as a carrier of a display control terminal. On the one hand, it can receive nursing requests in a timely manner, and on the other hand, it can use a nursing priority module to realize intelligent sorting of nursing priorities.

[0008] The first object of the present invention is to provide a ward calling method based on an intelligent nursing vehicle, comprising:

[0009] S1. Install a nursing car display terminal on the nursing car to exchange data with the nurse station display control terminal;

[0010] S2. When the patient presses the call button at the bedside as needed, the bed call terminal sends a nursing request signal to the nurse station display control terminal;

[0011] S3, the display control terminal of the nurse station sends the nursing request signal to the corresponding nursing vehicle display terminal;

[0012] S4. The nursing vehicle display terminal sends a nursing signal; specifically:

[0013] When a single patient presses the call button at the bedside as needed, the nursing signal sent by the nursing car display terminal is the bed information corresponding to the call button;

[0014] When multiple patients press the call button at the bedside within the preset time as needed, the nursing priority module generates a priority ranking of the nursing of multiple patients based on the basic information of the patients, other examination values, laboratory information, disease codes, quantitative values ​​of the degree of disease progression, basic disease marker values, basic physical constitution marker values, and observation, smell, questioning, and palpation values. The display terminal of the nursing car issues the order of nursing according to the priority ranking;

[0015] S5. The nurse confirms and processes the result through the display control terminal at the nurse station or on any display terminal on the nursing cart;

[0016] S6. After confirmation, the call signal of the nurse station display control terminal and the nursing car display terminal is cancelled.

[0017] Preferably, the basic information includes ward number, bed number, name, gender, and age; the laboratory information is the key laboratory indicators commonly used in the department to judge the patient's condition; and the other examination values ​​include the quantitative results of various imaging results.

[0018] Preferably, the nursing priority module is a double hidden layer non-fully connected BP network architecture.

[0019] Preferably, the neuron model adopts the MP neuron model, that is,

[0020] f(x)=f(Σ i w i x i -θ)

[0021] Among them, x is the input, w is the connection weight, and θ is the threshold;

[0022] The connection between the input layer and hidden layer 1 is that each composite input indicator is connected to 2 neurons of hidden layer 1, all single input indicators are connected to 2 neurons of hidden layer 1, and hidden layer 2 is set with 2 neurons.

[0023] Preferably, f uses the Sigmoid function, that is,

[0024]

[0025] The second object of the present invention is to provide a ward call system based on an intelligent nursing vehicle, comprising a plurality of bed call terminals and a display control terminal for data interaction with the bed call terminal; the display control terminal comprises a nurse station display control terminal and a nursing vehicle display terminal; and also comprises a nursing priority module; when multiple patients press the call button at the bedside within a preset time as needed, the nursing priority module generates a priority ranking for the care of multiple patients based on the patient's basic information, other examination values, laboratory information, disease code, quantitative value of the degree of disease progression, basic disease marker value, basic physical constitution marker value and observation, smell, questioning and palpation value, and the nursing vehicle display terminal issues the order of care based on the priority ranking.

[0026] Preferably, the basic information includes ward number, bed number, name, gender, and age; the laboratory information is the key laboratory indicators commonly used in the department to judge the patient's condition; and the other examination values ​​include the quantitative results of various imaging results.

[0027] Preferably, the nursing priority module is a double hidden layer non-fully connected BP network architecture.

[0028] Preferably, the neuron model adopts the MP neuron model, that is,

[0029] f(x)=f(Σ i w i x i -θ)

[0030] Among them, x is the input, w is the connection weight, and θ is the threshold;

[0031] The connection between the input layer and hidden layer 1 is that each composite input indicator is connected to 2 neurons of hidden layer 1, all single input indicators are connected to 2 neurons of hidden layer 1, and hidden layer 2 is set with 2 neurons.

[0032] Preferably, f uses the Sigmoid function, that is,

[0033]

[0034] The advantages and positive effects of this application are:

[0035] The present invention proposes a ward call system based on an intelligent nursing car, the core of which is to integrate a display control terminal into the nursing car, thereby upgrading the technology on the basis of the traditional nursing car. Specifically, the present invention adds a nursing car display terminal to the nursing car. Such a design has multiple advantages: first, it ensures that nurses can quickly and promptly receive patients' nursing requests, thereby improving the response speed of nursing work. Secondly, this design avoids the inconvenience of nurses having to wear additional equipment when receiving nursing requests, simplifies the work process, and improves work efficiency.

[0036] In addition, the present invention also includes a nursing priority module, which can intelligently prioritize nursing tasks. The specific workflow is as follows: when multiple patients press the call button at the bedside within a preset time range according to their own needs, the nursing priority module will be activated. This module comprehensively considers multiple dimensions of data such as the patient's basic information, other examination values, laboratory information, disease codes, quantitative values ​​of the degree of disease progression, basic disease marker values, basic physical constitution marker values, and evaluation values ​​of observation, auscultation, olfaction, questioning, and palpation. Through comprehensive analysis of these data, the nursing priority module can generate a nursing priority ranking list for different patients.

[0037] Subsequently, the display terminal of the nursing car will issue clear instructions to the nurses based on this priority list, informing them in what order they should perform nursing work. Such a system design not only improves the efficiency of nursing work, but also ensures that patients can receive timely care according to the severity and urgency of their illness, thereby improving the overall quality of care. In this way, the present invention not only improves the efficiency and quality of nursing, but also optimizes the allocation of medical resources, making medical care work more scientific and systematic. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 is a system block diagram of a preferred embodiment of the present invention;

[0040] Figure 2 is a flow chart of a preferred embodiment of the present invention;

[0041] Figure 3 It is a structural diagram of a nursing vehicle in a preferred embodiment of the present invention.

[0042] Figure 4 It is the neural network architecture designed in the preferred embodiment of the present invention.

[0043] Among them, 1. Nursing car display terminal; 2. Nursing car. DETAILED DESCRIPTION

[0044] 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.

[0045] See also Figures 1 to 4

[0046] A ward calling method based on an intelligent nursing vehicle comprises the following steps:

[0047] S1. First, a nursing car display terminal is installed on the nursing car for data interaction with the nurse station display control terminal; then a wireless communication network is established between the nursing car display terminal and the nurse station display control terminal for data interaction; for example, data communication can be performed through a WiFi network, a 5G network, or a 4G network;

[0048] S2. When the patient feels unwell or needs help, the patient can press the call button at the bedside as needed. At this time, the bed call terminal sends a nursing request signal to the nurse station display control terminal;

[0049] S3, the nurse station display control terminal sends the nursing request signal to the corresponding nursing car display terminal; because when there are many wards, in order to avoid all the nurse station display control terminals sending nursing request signals, for this purpose, a certain nursing ward area is matched for each nursing car, that is, the nurse station display control terminal sends the nursing request signal to the corresponding nursing car display terminal;

[0050] S4. When the nursing vehicle display terminal receives the nursing request signal, the nursing vehicle display terminal sends a nursing signal; specifically:

[0051] When a single patient presses the call button at the bedside as needed, the nursing signal sent by the nursing car display terminal is the bed information corresponding to the call button;

[0052] When multiple patients press the call button at the bedside within a preset time (such as one minute or two minutes) as needed, the issue of nursing priority is involved. The nursing priority module generates a priority ranking of the nursing of multiple patients based on the patient's basic information, other examination values, laboratory information, disease code, quantitative value of the degree of disease progression, basic disease marker value, basic physical marker value and observation, smell, questioning and palpation value. The nursing car display terminal issues the order of nursing according to the priority ranking;

[0053] S5. The nurse confirms and processes the result through the display control terminal at the nurse station or on any display terminal on the nursing cart;

[0054] S6. After confirmation, the call signal of the nurse station display control terminal and the nursing car display terminal is cancelled.

[0055] A ward call system based on an intelligent nursing vehicle comprises a plurality of bed call terminals and a display control terminal for data interaction with the bed call terminals; the display control terminal comprises a nurse station display control terminal and a nursing vehicle display terminal; and further comprises a nursing priority module; when a plurality of patients press the bedside call button within a preset time as required, the nursing priority module generates a priority ranking of the nursing of a plurality of patients according to the patients' basic information, other examination values, laboratory information, disease codes, quantitative values ​​of the degree of disease progression, basic disease marker values, basic physical constitution marker values ​​and observation, auscultation, questioning and palpation values, and the nursing vehicle display terminal issues the order of nursing according to the priority ranking.

[0056] The bed call terminal is usually installed on the wall near each bed in the ward. It has a request signal sending button. The patient sends a call request signal through the button. The bed call terminal is connected to the display control terminal at the nurse station through a wired method (such as optical fiber and other communication cables). The nurse station display control terminal can receive call signals from different bed call terminals in each ward, and display them on the nurse station display control terminal. At the same time, it can send out prompt sounds, lights and other signals. When the nurse station display control terminal receives the call signal from the bed call terminal, it forwards the signal to the nursing car display terminal through the wireless communication module. There can generally be one or more nursing car display terminals, such as Figure 3 As shown, the nursing car display terminal 1 is installed on the nursing car 2, and these nursing car display terminals interact with the nurse station display control terminal through wireless communication methods (such as WiFi, etc.). Among them, when the patient sends a call signal, the nursing car display terminal and the nurse station display control terminal can synchronously display the caller's ward number, bed number and other information in real time, and issue sound and light prompts.

[0057] like Figure 2 As shown, a control method of a ward call system based on an intelligent nursing vehicle includes:

[0058] Step 1: The patient calls through the call terminal in the ward

[0059] Step 2: The call signal is transmitted to the display control terminal at the nurse station via wired mode

[0060] Step 3: The display control terminal sends a patient call signal at the nurse station, and forwards the patient call signal to the smart nursing car in real time via wireless.

[0061] Step 4: The responsible nurse can confirm and process the case at the nurse station or on any smart nursing cart.

[0062] Step 5: Once the responsible nurse confirms the called bed through sound, light and other prompts, the call signals of the nurse station and the smart nursing car are cancelled at the same time.

[0063] In practice, we often encounter situations where two or more patients call almost at the same time. At this time, it is necessary to distinguish the severity and urgency of the cases and deal with them accordingly. The intelligent calling system can prioritize the treatment according to the specific conditions of the patients, and remind the medical staff which patient is more critical and needs to be dealt with first. The sorting results will be displayed on the screen of the intelligent nursing car and the display control terminal of the nurse station. However, there are many reasons why a patient may make a call, and it is not just one or several factors that can determine the urgency of the call. The intelligent calling system involved in this patent solves the problem of two or more patients calling at the same time through machine learning methods, and gives medical staff priority response suggestions.

[0064] The following uses the urology department of a hospital as an example to explain how the call system uses machine learning to determine and prioritize patients who are calling at least two patients at the same time. The details are as follows:

[0065] The artificial neural network algorithm in machine learning is used. However, the ordinary fully connected neural network will make the network too complex and prone to overfitting, which is not conducive to the network training effect and reduces the training efficiency. Therefore, the present invention proposes to use a double hidden layer non-fully connected BP network architecture to achieve it, as follows:

[0066] 1. Design of artificial neural network architecture

[0067] Different from the standard BP network, this patent adopts the "double hidden layer non-fully connected BP network" design, which is a multi-input single-output network. Figure 4 As shown in the figure, the network complexity can be reduced in a targeted manner and the training time can be reduced.

[0068] The neuron model adopts the MP neuron model, that is,

[0069] f(x)=f(∑ i w i x i -θ)

[0070] Among them, x is the input, w is the connection weight, and θ is the threshold.

[0071] The connection between the input layer and hidden layer 1 is not fully connected, such as Figure 4 As shown, each composite input indicator is connected to 2 neurons of hidden layer 1, all single input indicators are connected to 2 neurons of hidden layer 1, and 2 neurons are set in hidden layer 2.

[0072] Among them, the activation function can be selected according to the situation. In particular, here f uses the Sigmoid function, that is,

[0073]

[0074] 2. Input layer parameters

[0075] The input parameters proposed by the present invention include basic information (such as ward number, bed number, name, gender, age, etc.), main laboratory information (referring to the key laboratory indicators commonly used in this department to judge the patient's condition), other test values ​​(referring to other test results commonly used in this department, such as the quantitative results of various imaging results, etc.), disease code, quantitative value of the degree of disease progression, basic disease marker value, basic physical constitution marker value, observation, smell, questioning and palpation value, etc. The above input parameters can be used to comprehensively evaluate the patient's condition, providing a fundamental basis for scientifically proposing treatment priorities. It should be noted that the input parameters of different departments of the hospital are different and should be determined according to actual conditions. An example is given below to illustrate.

[0076] Taking urology as an example, as shown in Table 1, basic information includes 1 to 5, main laboratory test information includes 6 to 7, and other inputs include 8 to 13.

[0077] Table 1 Examples of input layer parameters

[0078]

[0079] In the above table, indicators such as blood test values ​​and urine test values, which are composed of many sub-indicators, are defined as composite indicators, and the remaining indicators are single indicators. Figure 4 The input layer in .

[0080] 3. Acquisition and representation of training sets and setting of loss functions.

[0081] A department in a hospital ward has long-term and detailed case records for the patients admitted. These records contain the parameters in the input layer, such as the input parameters in Table 1. As for the output, it can be determined by scoring by medical staff. Medical staff refer to medical records, laboratory test results, and patient status information to score the severity of the disease. The score ranges from 1 to 100 from mild to severe, as the output. The input x is a one-dimensional vector, which includes d elements in total, such as Figure 4 As shown, the corresponding input has a value, denoted as y, and a set of input and output (x, y) is denoted as a training example. Suppose there are m training examples in the training set D, that is

[0082] D={(x1,y1),(x2,y2),…,(x k ,y k ),…,(x m ,y m )}

[0083] Then the loss function is the mean square error, that is

[0084]

[0085] in

[0086]

[0087] Indicates that the input is x k is the output value obtained by forward propagation of the designed neural network. The ultimate goal is to minimize the error E on the training set D by updating the network parameters (weights and thresholds), which is the next step of network training.

[0088] 4. Network training

[0089] After the network parameters are initialized, the weight parameter w and threshold parameter θ are iteratively updated by back propagation according to the gradient descent method.

[0090] like Figure 4 As shown, there are p composite indicators and q single indicators. There are 2d weights from the input layer to the hidden layer 1, 2(2p+2) weights from the hidden layer 1 to the hidden layer 2, and 2 weights from the hidden layer 2 to the output layer. Therefore, there are 2(d+2p+3) weight parameters and (2p+5) threshold parameters.

[0091] Suppose the update formula of any parameter v is

[0092] v←v+Δv

[0093]

[0094] In the formula, η is the learning rate, and the parameters are adjusted in the negative gradient direction. It is necessary to obtain the partial derivative of the error function with respect to each parameter, and then use the above formula to calculate. The specific method is the same as the general BP algorithm, so it will not be described in detail here.

[0095] In order to avoid the overfitting problem, the data set can be divided into two groups: training set and validation set. The training set is used to calculate the gradient, update the weights and thresholds, and the validation set is used to estimate the error. If the training set error decreases but the validation set error begins to increase, the training is stopped, and the weights and thresholds with the minimum validation set error are returned. Alternatively, the objective error function is replaced by the following formula to compromise the error and network complexity. At the same time, in order to avoid local optimal solutions, multiple groups of different parameter values ​​should be initialized. After training is completed, the solution with the smallest error is taken as the final parameter.

[0096]

[0097] 5. Application of trained network model

[0098] The trained network is placed in the call system. When two or more patients call at the same time in a short period of time, the system automatically calculates the severity of the two patients and gives suggestions for treatment priority. At the same time, the new patients in the ward every day can be used as new training examples, so that new data can be continuously accumulated, the model can be continuously optimized, and the judgment can be more accurate.

[0099] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When the use is implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL) or wireless (e.g., infrared, wireless, microwave, etc.) mode) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0100] The above is only a preferred embodiment of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A ward calling method based on an intelligent nursing vehicle, characterized in that: include: S1. Install a nursing car display terminal on the nursing car to exchange data with the nurse station display control terminal; S2. When the patient presses the call button at the bedside as needed, the bed call terminal sends a nursing request signal to the nurse station display control terminal; S3, the display control terminal of the nurse station sends the nursing request signal to the corresponding nursing vehicle display terminal; S4. The nursing vehicle display terminal sends a nursing signal; specifically: When a single patient presses the call button at the bedside as needed, the nursing signal sent by the nursing car display terminal is the bed information corresponding to the call button; When multiple patients press the call button at the bedside within the preset time as needed, the nursing priority module generates a priority ranking of the nursing of multiple patients based on the basic information of the patients, other examination values, laboratory information, disease codes, quantitative values ​​of the degree of disease progression, basic disease marker values, basic physical constitution marker values, and observation, smell, questioning, and palpation values. The display terminal of the nursing car issues the order of nursing according to the priority ranking; S5. The nurse confirms and processes the result through the display control terminal at the nurse station or on any display terminal on the nursing cart; S6. After confirmation, the call signal of the nurse station display control terminal and the nursing car display terminal is cancelled.

2. The ward calling method based on the intelligent nursing vehicle according to claim 1 is characterized in that: The basic information includes ward number, bed number, name, gender, and age; the laboratory information is the key laboratory indicators commonly used by the department to judge the patient's condition; and the other examination values ​​include the quantitative results of various imaging results.

3. The ward calling method based on the intelligent nursing vehicle according to claim 1 is characterized in that: The nursing priority module is a double hidden layer non-fully connected BP network architecture.

4. The ward calling method based on the intelligent nursing vehicle according to claim 3 is characterized in that: The neuron model adopts the MP neuron model, that is, f(x)=f(Σ i w i x i -i) Among them, x is the input, w is the connection weight, and θ is the threshold; The connection between the input layer and hidden layer 1 is that each composite input indicator is connected to 2 neurons of hidden layer 1, all single input indicators are connected to 2 neurons of hidden layer 1, and hidden layer 2 is set with 2 neurons.

5. The ward calling method based on the intelligent nursing vehicle according to claim 4 is characterized in that: f uses the Sigmoid function, that is 6. A ward call system based on an intelligent nursing vehicle, comprising a plurality of bed call terminals and a display control terminal for data interaction with the bed call terminals; characterized in that: The display control terminal includes a nurse station display control terminal and a nursing vehicle display terminal; it also includes a nursing priority module; when multiple patients press the bedside call button within a preset time as needed, the nursing priority module generates a priority ranking for the care of multiple patients based on the patient's basic information, other examination values, laboratory information, disease code, quantitative value of the degree of disease progression, basic disease marker value, basic physical constitution marker value and observation, auscultation, questioning and palpation values, and the nursing vehicle display terminal issues the order of care based on the priority ranking.

7. The ward call system based on the intelligent nursing vehicle according to claim 6 is characterized in that: The basic information includes ward number, bed number, name, gender, and age; the laboratory information is the key laboratory indicators commonly used by the department to judge the patient's condition; and the other examination values ​​include the quantitative results of various imaging results.

8. The ward call system based on the intelligent nursing vehicle according to claim 7 is characterized in that: The nursing priority module is a double hidden layer non-fully connected BP network architecture.

9. The ward call system based on the intelligent nursing vehicle according to claim 8 is characterized in that: The neuron model adopts the MP neuron model, that is, f(x)=f(Σ i w i x i -i) Among them, x is the input, w is the connection weight, and θ is the threshold; The connection between the input layer and hidden layer 1 is that each composite input indicator is connected to 2 neurons of hidden layer 1, all single input indicators are connected to 2 neurons of hidden layer 1, and hidden layer 2 is set with 2 neurons.

10. The ward call system based on the intelligent nursing vehicle according to claim 9 is characterized in that: f uses the Sigmoid function, that is

Images