Hemodialysis nursing method, hemodialysis nursing server and storage medium

Abstract

The invention discloses a hemodialysis nursing method, a hemodialysis nursing server and a storage medium, and the hemodialysis nursing method comprises the steps: in a pre-dialysis preparation stage, obtaining initial exercise ability data of a patient, generating a virtual reality exercise plan of a current period, and sending the virtual reality exercise plan to a patient client; acquiring updated exercise ability data formed by executing the virtual reality exercise plan of the current period by the patient through the patient client; generating a virtual reality exercise plan of the next period according to the updated exercise ability data, and sending the virtual reality exercise plan of the next period to the patient client; and obtaining physique evaluation data after the patient completes the virtual reality exercise plans of the preset period number, generating a hemodialysis treatment scheme of the patient according to the physique evaluation data, and sending the hemodialysis treatment scheme to the patient client. According to the hemodialysis treatment system and method, health management before hemodialysis can be effectively carried out on a patient, a proper hemodialysis treatment scheme is formulated, and the hemodialysis treatment effect is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of digital medical technology, and in particular, to a hemodialysis care method, a hemodialysis care server, and a computer-readable storage medium. Background Art

[0002] The existing traditional hemodialysis care mode has the following disadvantages: Due to the limitations of time and space, the management of patient compliance is insufficient, and there is a lack of individualized dynamic adjustment of hemodialysis care. For hemodialysis patients, long-term hemodialysis brings them physical pain and economic burden, their mental health and social activity ability are damaged, and there is a lack of effective supervision for self-care management during the hemodialysis interval, which is not conducive to the treatment effect of hemodialysis. Summary of the Invention

[0003] The embodiments of the present application provide a hemodialysis care method, a hemodialysis care server, and a computer-readable storage medium, aiming to use digital medical technology to monitor the patient's motor ability, provide an individualized virtual reality exercise plan for the patient to improve the patient's physical fitness and mental state, and at the same time formulate a suitable dialysis treatment plan according to the patient's physical fitness assessment data to improve the effectiveness of hemodialysis treatment.

[0004] In a first aspect, the embodiments of the present application provide a hemodialysis care method, and the method includes: In the pre-dialysis preparation stage, obtain the patient's initial motor ability data, generate the virtual reality exercise plan for the current cycle according to the initial motor ability data, and send the virtual reality exercise plan for the current cycle to the patient client; Obtain the updated motor ability data formed by the patient executing the virtual reality exercise plan for the current cycle through the patient client; Generate the virtual reality exercise plan for the next cycle according to the updated motor ability data, and send the virtual reality exercise plan for the next cycle to the patient client; Obtain the physical fitness assessment data of the patient after completing the virtual reality exercise plan for the preset number of cycles, generate the hemodialysis treatment plan of the patient according to the physical fitness assessment data, and send the hemodialysis treatment plan to the patient client.

[0005] The hemodialysis care method provided by the embodiments of this application, in the pre-dialysis preparation stage, generates a cycle of virtual reality exercise plans according to the initial motor ability data, monitors the motor ability data of the patient executing the current cycle of virtual reality exercise plans through the client, and formulates the next cycle of virtual reality exercise plans according to the motor ability data of the current cycle, so as to provide an individualized exercise prescription for the patient, implement effective health management for the patient in the pre-dialysis preparation stage, improve the physical fitness and psychological state of the patient, and at the same time, can formulate a suitable hemodialysis treatment plan according to the physical fitness assessment data of the patient to improve the hemodialysis treatment effect.

[0006] In a possible implementation manner of the first aspect, generating the hemodialysis treatment plan for the patient according to the physical fitness assessment data includes: Based on the physical fitness assessment data, call a pre-trained treatment plan automatic generation model to obtain the hemodialysis treatment plan for the patient output by the treatment plan automatic generation model; wherein, the treatment plan automatic generation model is constructed based on a hemodialysis treatment knowledge graph, and the hemodialysis treatment knowledge graph includes a physical fitness assessment entity corresponding to the physical fitness assessment data, a hemodialysis treatment plan entity corresponding to the hemodialysis treatment plan, and an edge used to represent the relationship between the physical fitness assessment entity and the hemodialysis treatment plan entity.

[0007] In a possible implementation manner of the first aspect, the method further includes: In the pre-dialysis preparation stage, obtain the basic examination data of the patient; Based on the basic examination data, call a pre-trained complication prediction model to obtain the complication prediction result output by the complication prediction model; Formulate a preventive treatment plan according to the complication prediction result and send the preventive treatment plan to the patient client.

[0008] In a possible implementation manner of the first aspect, the basic examination data includes original numerical data and original image data; after obtaining the basic examination data of the patient, the method further includes: Based on a preset conversion rule, convert the original numerical data into standard numerical data; Based on a preset image preprocessing rule, convert the original image data into standard image data, The based on the basic examination data, calling a pre-trained complication prediction model to obtain the complication prediction result output by the complication prediction model includes: Input the standard numerical data into a pre-trained first feature extraction network to obtain a first embedding representation; Input the standard image data into a pre-trained second feature extraction network to obtain a second embedding representation; Concatenate the first embedding representation and the second embedding representation into a third embedding representation; Input the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model.

[0009] In a possible implementation manner of the first aspect, the complication prediction model includes an intradialytic hypotension probability prediction model and a renal anemia probability prediction model. The step of inputting the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model includes: Input the third embedding representation into the intradialytic hypotension probability prediction model to obtain the intradialytic hypotension prediction probability; Input the third embedding representation into the renal anemia probability prediction model to obtain the renal anemia prediction probability.

[0010] In a possible implementation manner of the first aspect, the method further includes: In the post-dialysis continuous care stage, obtain the patient's vital sign monitoring data sent by the intelligent wearable device through the patient client; Input the vital sign monitoring data into a pre-trained health status assessment model to obtain the health status assessment results of multiple preset items; When the health status assessment result of any one of the preset items is in a potential health risk warning state, send a warning message to the patient's communication device.

[0011] In a possible implementation manner of the first aspect, after obtaining the health status assessment results, the method further includes: Input the health status assessment results of the multiple preset items into a pre-trained nursing plan generation model to obtain an individualized continuous care plan for the patient; Send the individualized continuous care plan to the patient client.

[0012] In a second aspect, an embodiment of the present application provides a hemodialysis care server, which includes: A virtual reality exercise plan generation module, configured to obtain the patient's initial motor ability data in the pre-dialysis preparation stage, generate the virtual reality exercise plan for the current cycle according to the initial motor ability data, and send the virtual reality exercise plan for the current cycle to the patient client; A motor ability data acquisition module, configured to obtain the updated motor ability data formed by the patient executing the virtual reality exercise plan for the current cycle through the patient client; A virtual reality exercise plan adjustment module, configured to generate a virtual reality exercise plan for the next cycle according to the updated motor ability data, and send the virtual reality exercise plan for the next cycle to the patient client; A hemodialysis treatment plan generation module, configured to obtain physical fitness assessment data of a patient after completing a preset number of cycles of virtual reality exercise plans, generate a hemodialysis treatment plan for the patient according to the physical fitness assessment data, and send the hemodialysis treatment plan to the patient client.

[0013] In a third aspect, an embodiment of the present application provides a server, including: A memory, configured to store a program; A processor, configured to execute the program stored in the memory. When the processor executes the program stored in the memory, the processor is configured to execute the hemodialysis care method described in the first aspect above.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the hemodialysis care method described in the first aspect above.

[0015] The solutions provided in the second to fourth aspects above are used to implement or cooperate with the implementation of the hemodialysis care method provided in the first aspect above. Therefore, the same or corresponding beneficial effects can be achieved as those in the first aspect, and details are not described herein again.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 A flowchart of a hemodialysis care method provided by an embodiment of the present application Figure 1 ; Figure 2 A flowchart of a hemodialysis care method provided by an embodiment of the present application Figure 2 ; Figure 3 A flowchart of a hemodialysis care method provided by an embodiment of the present application Figure 3 ; Figure 4A schematic structural diagram of a blood dialysis care server provided by an embodiment of the present application; Figure 5 A schematic structural diagram of a server provided by an embodiment of the present application. Detailed implementation manners

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that in the flowchart. In the description of the specification, claims and the above drawings, "at least one" means one or more, and the meaning of multiple (or multiple items) is more than two. Understandings such as greater than, less than, exceeding, etc. do not include the present number, and understandings such as above, below, within, etc. include the present number. If there is a description of "first", "second", etc., it is only for the purpose of distinguishing technical features and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0021] In the embodiments of the present application, the "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent the situation of A existing alone, A and B existing simultaneously, and B existing alone. Among them, A and B may be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c may represent: a existing alone, b existing alone, c existing alone, a and b existing simultaneously, a and c existing simultaneously, b and c existing simultaneously, or a, b, and c existing simultaneously, where a, b, and c may be single or multiple.

[0022] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific manner.

[0023] Hemodialysis is a long-term and frequent treatment that may cause complications such as hypotension and muscle spasms in patients. Moreover, patients are prone to fatigue, depression, and anxiety after dialysis, which affects their daily life. Self-care of patients before and after dialysis is of positive significance for improving the dialysis treatment effect and reducing the impact of dialysis on the quality of life. For example, if patients perform appropriate regular exercise before receiving dialysis treatment, it can increase the blood flow of the whole body tissues. In particular, metabolites in muscle tissues (such as urea, creatinine, uric acid, etc.) can enter the blood circulation faster, and thus be removed by the dialysate, significantly improving the solute clearance during dialysis and the adequacy of dialysis. Exercise can also help patients recover their physical strength better after dialysis, reduce fatigue, enhance the body's tolerance and adaptability, and help patients relieve depression and anxiety emotions of dialysis patients and improve sleep quality. However, due to the limitations of time and space in the existing traditional hemodialysis care model, the patient compliance management is insufficient, and there is a lack of individualized dynamic adjustment of hemodialysis care. For hemodialysis patients, long-term hemodialysis brings physical pain and economic burden to them, their mental health and social activity ability are damaged, and there is a lack of effective supervision in the self-care management during the hemodialysis interval, which is not conducive to the treatment effect of hemodialysis.

[0024] Based on the above problems, the embodiments of the present application provide a hemodialysis care method, a hemodialysis care server, and a computer-readable storage medium, aiming to use digital medical technology to monitor the patient's exercise ability, provide an individualized virtual reality exercise plan for the patient to improve the patient's physical fitness and mental state, and at the same time formulate a suitable dialysis treatment plan according to the patient's physical fitness assessment data to improve the effectiveness of hemodialysis treatment.

[0025] Please refer to Figure 1 , which is a flowchart showing a hemodialysis care method provided by an embodiment of the present application. Figure 1 , as Figure 1 shown, the hemodialysis care method provided by the embodiments of the present application includes the following steps S101-S104, which will be specifically described below.

[0026] Step S101: In the pre-dialysis preparation stage, obtain the patient's initial exercise ability data, generate the virtual reality exercise plan for the current cycle according to the initial exercise ability data, and send the virtual reality exercise plan for the current cycle to the patient client.

[0027] In specific implementation, a patient can undergo a series of health checks and exercise ability tests in a hospital to obtain their initial exercise ability data. The patient's initial exercise ability data can be uploaded to the server through the hospital's medical staff client. After the server obtains the patient's initial exercise ability data, it generates a virtual reality exercise plan for the current cycle based on the initial exercise ability data and sends the virtual reality exercise plan for the current cycle to the patient client so that the patient can receive the virtual reality exercise plan. It should be noted that the initial exercise ability data can also be uploaded to the server by the patient himself through the patient client, and the embodiments of the present application do not limit this.

[0028] Exemplarily, the initial exercise ability data may include the following types: (1) Basic vital sign data, such as blood pressure, heart rate, weight, body fat percentage, etc., to understand the patient's overall physical condition; (2) Exercise load test data, such as muscle strength and endurance test data, aerobic exercise ability test data, to understand the patient's exercise ability and physical fitness; (3) Electrocardiogram data to evaluate the patient's heart function and ensure heart safety during exercise.

[0029] By evaluating and analyzing the above various types of exercise ability data, the server can comprehensively understand the exercise ability of dialysis patients, thereby formulating a personalized exercise plan to ensure the safety and effectiveness of exercise.

[0030] Exemplarily, the specific process of generating a virtual reality exercise plan for the current cycle based on the initial exercise ability data may be to call an exercise ability scoring model, and through the exercise ability scoring model, according to the patient's initial exercise ability data, output the patient's initial exercise ability score; select a virtual reality exercise plan that matches the patient's initial exercise ability score from a preset virtual reality exercise plan library as the virtual reality exercise plan for the current cycle.

[0031] Exemplarily, the exercise ability scoring model can be a deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory neural network (LSTM), etc., and use deep learning algorithms to analyze the patient's exercise ability data and output the patient's initial exercise ability score.

[0032] Exemplarily, after the server obtains the patient's initial exercise ability data, it performs preprocessing such as cleaning, normalization, and feature extraction on the initial exercise ability data and then inputs it into the exercise ability scoring model, and the corresponding initial exercise ability score is output through the exercise ability scoring model.

[0033] Exemplarily, the motor ability scoring model can be trained and obtained in the following manner: Obtain a training set, which includes motor ability data samples of multiple patients and corresponding initial motor ability score labels; Input the motor ability data samples in the training set into the motor ability scoring model to obtain an initial motor ability score; Determine the loss function value according to the initial motor ability score and the initial motor ability score label; Update the model parameters of the motor ability scoring model according to the loss function value; Repeat the above process until the motor ability scoring model converges.

[0034] It can be understood that the virtual reality exercise plan may include at least one of the following: exercise frequency, exercise type, exercise intensity, exercise duration, training groups, rest time, and diet suggestions. For example, when the current cycle time is one week, divided into 4 training days and 3 rest days, the virtual reality exercise plan includes the exercise plan corresponding to each training day, such as the exercise type, exercise intensity, exercise duration, training groups, and rest time on that day. The virtual reality exercise plan also includes the diet suggestions for the current cycle.

[0035] It can be understood that the virtual reality exercise plan in the embodiments of the present application is used to provide the virtual reality exercise arrangement within the patient's cycle. Virtual reality exercises usually need to be combined with virtual reality (VR) devices. Due to renal insufficiency, dialysis patients usually suffer from problems such as physical decline, muscle atrophy, and osteoporosis. Therefore, suitable exercises need to be of low intensity, low risk, and capable of improving physical function and mental health. VR technology can provide a safe and interesting exercise experience for dialysis patients while avoiding over-fatigue and injury.

[0036] It can be understood that the exercise types in the virtual reality exercise plan may include VR flexibility training, VR balance training, VR light aerobic training, VR upper limb strength training, etc. When training, the patient wears a VR device (such as a head-mounted display, handle, chest strap, or wristband). The VR device captures the patient's movements with the help of sensors (such as optical sensors, accelerometers, and gyroscopes), monitors the accuracy of the patient's movements in real time, and provides guidance and correction through a virtual coach to help the user complete the training movements more accurately.

[0037] It can be understood that the VR device also collects the motor ability data of the patient during the training process. For example, it uses optical sensors, accelerometers, and gyroscopes to collect the patient's body posture (such as joint angles, acceleration) data, and uses heart rate sensors, blood oxygen sensors, respiratory sensors, electromyography sensors, etc. to collect the patient's physical signs data such as heart rate, blood oxygen, respiration, and muscle contraction intensity during the training process. The VR device generates updated motor ability data based on the above motor ability data collected by the sensors. This updated motor ability data can provide a data analysis basis for formulating the virtual reality exercise plan for the next cycle.

[0038] Exemplarily, updating the exercise ability data may include one or more of the following data: average heart rate, average blood oxygen, respiratory rate, training duration, action completion degree, muscle contraction intensity, and fatigue degree.

[0039] Step S102: Obtain the updated exercise ability data formed by the patient executing the virtual reality exercise plan in the current cycle through the patient client.

[0040] Step S103: Generate a virtual reality exercise plan for the next cycle based on the updated exercise ability data, and send the virtual reality exercise plan for the next cycle to the patient client.

[0041] Exemplarily, the VR device is communicatively connected to the patient client, and the VR device sends the updated exercise ability data generated by the patient in the virtual reality exercise plan of the current cycle to the patient client. The patient can view the exercise ability data generated in each cycle through the patient client.

[0042] Exemplarily, the patient client sends the updated exercise ability data of the patient to the server, and the server generates a virtual reality exercise plan for the next cycle based on the updated exercise ability data. For example, the server dynamically adjusts the exercise intensity according to the patient's heart rate, action completion degree, muscle contraction intensity, and fatigue degree.

[0043] Exemplarily, if the patient's heart rate is too high during exercise, when formulating the virtual reality exercise plan for the next cycle, the server appropriately reduces the exercise intensity or extends the rest time; if the patient's heart rate changes little during exercise, when formulating the virtual reality exercise plan for the next cycle, the server appropriately increases the exercise intensity.

[0044] Exemplarily, the virtual reality exercise plan for each cycle includes multiple training contents. For example, if the number of days in each cycle is 7 days, it includes 4 training days, and each training day corresponds to one training content. After the patient completes the corresponding training content on each training day, corresponding updated exercise ability data will be generated, such as data on average heart rate, average blood oxygen, respiratory rate, training duration, action completion degree, muscle contraction intensity, and fatigue degree. After the patient completes the virtual reality exercise plan for one cycle, the patient client packs and uploads the updated exercise ability data of the current cycle to the server. The server generates a virtual reality exercise plan for the next cycle based on the updated exercise ability data generated by the patient in the current cycle.

[0045] Exemplarily, the specific process of the server generating the virtual reality exercise plan for the next cycle based on the updated motor ability data generated by the patient in the current cycle can be as follows: for each training content, according to the preset target achievement degree algorithm, calculate the distance between the updated motor ability data and the preset target motor ability data to obtain the target achievement degree; when the target achievement degree exceeds the first preset threshold, increase the exercise intensity of this training content; when the target achievement degree exceeds the second preset threshold but is less than the first preset threshold, maintain the exercise intensity of this training content; when the target achievement degree is less than the second preset threshold, reduce the exercise intensity of this training content.

[0046] It can be understood that the target motor ability data includes the target values of n indicators, and the updated motor ability data includes the actual values of these n indicators, where n≥1; calculating the target achievement degree according to the target achievement degree algorithm can be achieved through the following formula:

[0047] Among them, represents the weight of the i th indicator, , are the actual value and target value of the i-th indicator.

[0048] It can be understood that the first preset threshold can be set to 1, and the second preset threshold can be set to 0.8. When it is necessary to adjust the exercise intensity of the training content, the adjustment ratio can be determined according to the distance from the preset threshold, and the exercise intensity of the training content is adjusted according to the adjustment ratio.

[0049] Step S104: Obtain the physical fitness assessment data of the patient after completing the virtual reality exercise plan for the preset number of cycles, generate the hemodialysis treatment plan for the patient according to the physical fitness assessment data, and send the hemodialysis treatment plan to the patient client.

[0050] It can be understood that after the patient completes the virtual reality exercise plan for the preset number of cycles, the patient's physical fitness is evaluated to obtain the patient's physical fitness assessment data. The content of the physical fitness assessment can include at least one of the following: (1) General situation assessment. For example, the patient's basic information (age, gender, height, weight, medical history); the patient's symptoms and signs, including the patient's physical strength, appetite, sleep situation, degree of edema, blood pressure, heart function, etc.; the patient's nutritional status, including indicators such as the patient's body mass index (BMI), lean body mass (LBM), serum albumin, prealbumin, hemoglobin, etc.

[0051] (2) Vascular access assessment, including the type of the patient's vascular access (such as autogenous arteriovenous fistula, graft arteriovenous fistula or central venous catheter) and its functional status.

[0052] (3) Renal function assessment, including serum creatinine, urea nitrogen, β2-microglobulin, cystatin C, etc.

[0053] (4) Electrolyte and acid-base balance assessment, including serum potassium, calcium, phosphorus, bicarbonate, etc.

[0054] (5) Other index assessments: blood routine, coagulation function, infection indexes, etc.

[0055] Exemplarily, the specific process of generating a hemodialysis treatment plan for a patient based on the physical condition assessment data may be to call a treatment plan automatic generation model based on the patient's physical condition assessment data, and obtain the hemodialysis treatment plan of the patient output by the treatment plan automatic generation model. Among them, the hemodialysis treatment plan may include at least one or more of the following contents: dialysis frequency, dialysis duration, dialysate composition, dialysate temperature, ultrafiltration volume, ultrafiltration speed, anticoagulation method, and anticoagulant dose.

[0056] Exemplarily, after the server obtains the patient's physical condition assessment data, it performs preprocessing such as cleaning, normalization, and feature extraction on the physical condition assessment data, and then inputs it into the treatment plan automatic generation model, and outputs the patient's hemodialysis treatment plan through the treatment plan automatic generation model.

[0057] Exemplarily, the treatment plan automatic generation model may be constructed based on a hemodialysis treatment knowledge graph, which includes a physical condition assessment entity corresponding to the physical condition assessment data, a hemodialysis treatment plan entity corresponding to the hemodialysis treatment plan, and an edge used to represent the relationship between the physical condition assessment entity and the hemodialysis treatment plan entity.

[0058] Exemplarily, the physical condition assessment entity includes at least one of age, gender, height, weight, medical history, physical strength, appetite, sleep condition, degree of edema, blood pressure, cardiac function, type of vascular access, serum creatinine, urea nitrogen, β2-microglobulin, cystatin C, blood routine, coagulation function, and infection indexes.

[0059] Exemplarily, the hemodialysis treatment plan entity includes at least one of dialysis frequency, dialysis duration, dialysate composition, dialysate temperature, ultrafiltration volume, ultrafiltration speed, anticoagulation method, and anticoagulant dose.

[0060] Exemplarily, the edge of the hemodialysis treatment knowledge graph connects the physical condition assessment entity and the hemodialysis treatment plan entity with a corresponding relationship, and is used to represent the corresponding relationship between the physical condition assessment entity and the hemodialysis treatment plan entity.

[0061] For example, a knowledge graph for hemodialysis treatment includes age entities, dialysis frequency entities, and dialysis duration entities. Among them, the age entities include entities for multiple different age ranges, the dialysis frequency entities include entities for multiple different frequency ranges, and the dialysis duration entities include entities for multiple different duration ranges. For the age entity representing the high-age range, this age entity is respectively connected to the dialysis frequency entity representing low frequency and the dialysis duration entity representing low duration. Generally speaking, the physical function of the elderly declines, and their tolerance to dialysis is poor. Therefore, it is necessary to appropriately reduce the dialysis frequency and time. Therefore, in the knowledge graph, a connection relationship is established between the age entity representing the high-age range and the dialysis frequency entity representing low frequency and the dialysis duration entity representing low duration, indicating that for elderly patients, they need to select a dialysis plan with low frequency and low duration.

[0062] Exemplarily, a knowledge graph for hemodialysis treatment includes a coagulation function entity and an anticoagulant dose entity. Among them, the coagulation function entity includes entities for multiple different coagulation function levels, and the anticoagulant dose entity includes entities for multiple different dose ranges. For the entity representing a low coagulation function level, it is connected to the anticoagulant dose entity representing a large dose, indicating that patients with poor coagulation function need to increase the anticoagulant dose to reduce the bleeding risk during dialysis.

[0063] Exemplarily, the specific process of training a treatment plan automatic generation model can be as follows: taking the physical fitness assessment data and the hemodialysis treatment plan as entities, and taking the relationship between the physical fitness assessment data and the hemodialysis treatment plan as edges, construct a knowledge graph for hemodialysis treatment; then, use a graph embedding method (such as TransE) to train the knowledge graph to obtain vector representations of entities and relationships, and embed them into the treatment plan automatic generation model; obtain training samples, where the training samples include physical fitness assessment data samples and corresponding hemodialysis treatment plan labels; perform feature extraction on the physical fitness assessment data samples through a feature extraction network to obtain physical fitness assessment data features; input the physical fitness assessment data features into the treatment plan automatic generation model to obtain a predicted result of the hemodialysis treatment plan; and train the treatment plan automatic generation model according to the loss value between the predicted result of the hemodialysis treatment plan and the hemodialysis treatment plan label.

[0064] In the embodiments of the present application, the formulation of the hemodialysis plan comprehensively considers the patient's physical fitness assessment results (including general conditions, nutritional status, vascular access function, laboratory indicators, etc.), and ensures the dialysis effect, reduces complications, and improves the patient's quality of life through individualized dialysis frequency, time, dialysis fluid composition, ultrafiltration volume, and anticoagulation plan.

[0065] The hemodialysis care method provided by the embodiments of the present application, in the pre-dialysis preparation stage, generates a cycle of virtual reality exercise plans according to the initial motor ability data, monitors the motor ability data of the patient executing the current cycle of virtual reality exercise plans through the client, and formulates the next cycle of virtual reality exercise plans according to the motor ability data of the current cycle, so as to provide an individualized exercise prescription for the patient, thereby effectively managing the patient's health before dialysis, improving the patient's physical fitness and mental state, and at the same time, a suitable dialysis treatment plan can be formulated according to the patient's physical fitness assessment data, improving the effectiveness of hemodialysis treatment.

[0066] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a hemodialysis care method provided by the embodiments of the present application. Figure 2 . It can be understood that Figure 2 the steps in the illustrated embodiments can be regarded as reasonable deformations or supplements to the above Figure 1 illustrated embodiments; or, it can be understood that the hemodialysis care method in the embodiments of the present application can also be regarded as an independently executable embodiment, and the present application makes no limitation thereto. As Figure 2 shown, the hemodialysis care method provided by the embodiments of the present application includes but is not limited to the following steps S201-S203: Step S201, in the pre-dialysis preparation stage, obtain the patient's basic examination data; Step S202, based on the basic examination data, call a pre-trained complication prediction model to obtain the complication prediction result output by the complication prediction model; Step S203, formulate a preventive treatment plan according to the complication prediction result, and send the preventive treatment plan to the patient client.

[0067] Exemplarily, the patient's basic examination data includes at least one of the following: age, gender, height, weight, medical history, blood routine data, renal function data, iron metabolism data, electrocardiogram, echocardiogram, and color ultrasound of peripheral blood vessels.

[0068] It can be understood that the above basic examination data includes original numerical data and original image data. Among them, the original numerical data includes: age, gender, height, weight, medical history, blood routine data, renal function data, and iron metabolism data. The original image data includes: electrocardiogram, echocardiogram, and color ultrasound of peripheral blood vessels.

[0069] Exemplarily, after obtaining the patient's basic examination data, the hemodialysis care method of the embodiments of the present application further includes: converting the original numerical data into standard numerical data based on a preset conversion rule; converting the original image data into standard image data based on a preset image preprocessing rule.

[0070] It is understandable that for the original numerical data and the original image data, both need to be converted into standard data that can be processed by the complication prediction model.

[0071] For the original numerical data, it can be converted into standard numerical data based on preset conversion rules. For example, for gender, convert the gender "male" to "1" and the gender "female" to "0"; for weight, determine the interval where the weight is located, and represent the patient's weight by the identification value corresponding to this interval. For example, if the body mass is 60 kg and it is in the interval [50 kg, 70 kg), and the identification value corresponding to the interval [50 kg, 70 kg) is "2", so the patient's weight is converted to "2" for representation.

[0072] For the original image data, it can be converted into standard image data based on preset image preprocessing rules, including at least one of the following: Normalize the image size to ensure that all images have the same resolution; Remove noise to reduce random noise in the image; Enhance the contrast to make the details of the image clearer; Normalize to adjust the pixel value range to meet the requirements of the algorithm.

[0073] Exemplarily, based on the basic examination data, the specific process of calling the pre-trained complication prediction model to obtain the complication prediction result output by the complication prediction model may include: Input the standard numerical data into the pre-trained first feature extraction network to obtain the first embedding representation; Next, input the standard image data into the pre-trained second feature extraction network to obtain the second embedding representation; Next, splice the first embedding representation and the second embedding representation into a third embedding representation; Next, input the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model.

[0074] It is understandable that the basic examination data in the embodiments of the present application is multi-modal data including numerical data and graphical data, and two different modal data need to be feature-extracted through different feature extraction networks. In the embodiments of the present application, the standard numerical data converted from the numerical data is feature-extracted through the first feature extraction network, and the standard image data converted from the image data is feature-extracted through the second feature extraction network.

[0075] It can be understood that after the embodiments of the present application obtain the first embedding representation corresponding to the standard numerical data and the second embedding representation corresponding to the standard image data, the first embedding representation and the second embedding representation are concatenated into a third embedding representation, and then the third embedding representation is input into the complication prediction model, and the complication prediction result is output through the complication prediction model.

[0076] Among them, the complication prediction result may include at least one of the following: the prediction probability of intradialytic hypotension (IDH), and the prediction probability of renal anemia.

[0077] In a possible embodiment, the complication prediction model includes an intradialytic hypotension probability prediction model and a renal anemia probability prediction model. Correspondingly, inputting the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model includes: Inputting the third embedding representation into the intradialytic hypotension probability prediction model to obtain the prediction probability of intradialytic hypotension; And inputting the third embedding representation into the renal anemia probability prediction model to obtain the prediction probability of renal anemia.

[0078] It can be understood that the embodiments of the present application use the third embedding representation for downstream prediction tasks, and the downstream prediction tasks include the prediction of the probability of intradialytic hypotension (IDH) and the prediction of the probability of renal anemia. The IDH probability prediction is realized through the intradialytic hypotension probability prediction model, and the renal anemia probability prediction is realized through the renal anemia probability prediction model.

[0079] It can be understood that both the intradialytic hypotension probability prediction model and the renal anemia probability prediction model can adopt models such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a long short-term memory neural network (LSTM).

[0080] The training process of the intradialytic hypotension probability prediction model may be to first construct a training sample, where the training sample includes basic examination data and the corresponding intradialytic hypotension label; convert the numerical data in the basic examination data into standard numerical data, and convert the image data in the basic examination data into standard image data; perform feature extraction on the standard numerical data and the standard image data respectively to obtain the first embedding representation and the second embedding representation; concatenate the first embedding representation and the second embedding representation into a third embedding representation; input the third embedding representation into the intradialytic hypotension probability prediction model to obtain the prediction probability of intradialytic hypotension output by the intradialytic hypotension probability prediction model; train the intradialytic hypotension probability prediction model according to the loss value between the prediction probability of intradialytic hypotension and the intradialytic hypotension label.

[0081] The training process of the renal anemia probability prediction model can be as follows: First, construct training samples, where the training samples include basic examination data and corresponding renal anemia labels; convert the numerical data in the basic examination data into standard numerical data, and convert the image data in the basic examination data into standard image data; perform feature extraction on the standard numerical data and the standard image data respectively to obtain a first embedded representation and a second embedded representation; splice the first embedded representation and the second embedded representation into a third embedded representation; input the third embedded representation into the renal anemia probability prediction model to obtain the renal anemia prediction probability output by the renal anemia probability prediction model; train the renal anemia probability prediction model according to the loss value between the renal anemia prediction probability and the renal anemia label.

[0082] In the embodiment of the present application, in the pre-dialysis preparation stage, complication prediction is performed based on the patient's basic examination data to predict the probabilities of complications such as intradialytic hypotension (IDH) and renal anemia during dialysis treatment. According to the prediction results, corresponding preventive treatment plans are provided to the patient and sent to the patient's client to prompt the patient to carry out the corresponding preventive treatment plan to reduce the treatment risk.

[0083] For example, when the predicted probability of intradialytic hypotension output by the intradialytic hypotension probability prediction model is a high probability, educate the patient to avoid eating a large amount of food before dialysis, so as to avoid blood concentrating in the gastrointestinal tract after eating and inducing hypotension; educate the patient to avoid suddenly changing body position during dialysis, and should change body position slowly during dialysis to reduce orthostatic hypotension; educate the patient to pay attention to controlling weight gain during the interdialytic period, control fluid intake, and avoid excessive weight gain during the interdialytic period (usually not exceeding 3%-5% of the dry weight); educate the patient to supplement electrolytes, correct electrolyte disorders such as hyponatremia and hypocalcemia, and improve plasma colloid osmotic pressure by diet or albumin supplementation; educate the patient to limit fluid intake during the interdialytic period and avoid excessive weight gain.

[0084] For example, when the predicted probability of renal anemia output by the renal anemia probability prediction model is a high probability, educate the patient to use erythropoietin (EPO) or iron agents to improve anemia and enhance the oxygen-carrying capacity of the blood; educate the patient to consume foods rich in iron and vitamins (such as red meat, green leafy vegetables, beans), and emphasize the importance of regular examinations and taking medicine on time.

[0085] Please refer to Figure 3 , Figure 3 which is a flowchart illustration of a hemodialysis care method provided by an embodiment of the present application. Figure 3 . It can be understood that Figure 3 the steps in the illustrated embodiment can be regarded as the above Figure 1Reasonable deformations or supplements of the illustrated embodiments; or, it can be understood that the hemodialysis care method in the embodiments of the present application can also be regarded as an independently executable embodiment, and the present application makes no limitation thereto. As Figure 3 As shown, the hemodialysis care method provided by the embodiments of the present application includes but is not limited to the following steps S401 - S403: Step S401, in the continuous care stage after dialysis, obtain the physical sign monitoring data of the patient sent by the intelligent wearable device through the patient client; Step S402, input the physical sign monitoring data into the pre-trained health status evaluation model to obtain the health status evaluation results of multiple preset items; Step S403, when the health status evaluation result of any one of the preset items is in a potential health risk warning state, send a warning message to the communication device of the patient.

[0086] It can be understood that after the patient completes hemodialysis, the physical signs of the patient are monitored by the intelligent wearable device worn by the patient, and the physical sign monitoring data is uploaded to the patient client, which is convenient for the patient to view their own physical sign monitoring data.

[0087] It can be understood that the patient client sends the physical sign monitoring data to the server, and the server performs a health status evaluation based on the physical sign monitoring data to obtain the health status evaluation results of multiple preset items.

[0088] Exemplarily, the physical sign monitoring data includes at least one of the following: heart rate, blood oxygen saturation, blood pressure, blood glucose, electrocardiogram, sleep monitoring data, respiratory rate, body temperature data, and stress and emotion data.

[0089] Exemplarily, the health status evaluation results of multiple preset items may include: cardiovascular system, respiratory system, metabolic function, sleep quality, infection risk, and mental health evaluation results.

[0090] It can be understood that the embodiments of the present application input the physical sign monitoring data of the patient into the health status evaluation model, and the health status evaluation results of multiple preset items are output through the health status evaluation model. If the health status evaluation result of any one item is in a potential health risk warning state, a warning message is sent to the communication device of the patient to remind the patient to take timely prevention and go to the hospital for a reexamination.

[0091] It can be understood that the training process of the health status evaluation model can be to first construct training samples, where the training samples include physical sign monitoring data and corresponding health status evaluation labels; input the physical sign monitoring data into the health status evaluation model to obtain the health status evaluation results output by the health status evaluation model; and train the health status evaluation model according to the loss value between the health status evaluation result and the health status evaluation label.

[0092] It can be understood that after obtaining the health status assessment result, the hemodialysis care in the embodiments of the present application may further include the following steps: inputting the health status assessment results of multiple preset items into a pre-trained care plan generation model to obtain an individualized follow-up care plan for the patient; and sending the individualized follow-up care plan to the patient's client.

[0093] Exemplarily, the individualized follow-up care plan may include the following aspects: diet guidance, breathing training guidance, sleep hygiene guidance, infection prevention guidance, and psychological support, etc.

[0094] In the embodiments of the present application, a variety of digital medical technologies such as virtual reality technology, artificial intelligence, big data, and mobile medical APP are combined and used in the care process of hemodialysis patients to create a "new model of hemodialysis care based on the combination of multiple digital medical technologies", which helps nursing staff obtain comprehensive patient information in one stop, achieve seamless data docking, effectively supervise the compliance management of patients, comprehensively consider various factors related to the health of hemodialysis patients based on the health data of hemodialysis patients, realize dynamic care planning, and provide comprehensive, personalized, and continuous care for hemodialysis patients.

[0095] Please refer to Figure 4 , the embodiments of the present application also provide a hemodialysis care server, and the server includes: A virtual reality exercise plan generation module, configured to obtain the initial motor ability data of the patient during the pre-dialysis preparation stage, generate the virtual reality exercise plan for the current cycle according to the initial motor ability data, and send the virtual reality exercise plan for the current cycle to the patient's client; A motor ability data acquisition module, configured to obtain the updated motor ability data formed by the patient executing the virtual reality exercise plan for the current cycle through the patient's client; A virtual reality exercise plan adjustment module, configured to generate the virtual reality exercise plan for the next cycle according to the updated motor ability data, and send the virtual reality exercise plan for the next cycle to the patient's client; A hemodialysis treatment plan generation module, configured to obtain the physical fitness assessment data of the patient after completing the virtual reality exercise plan for a preset number of cycles, generate the hemodialysis treatment plan for the patient according to the physical fitness assessment data, and send the hemodialysis treatment plan to the patient's client.

[0096] As an embodiment, the hemodialysis treatment plan generation module is specifically configured to obtain the physical fitness assessment data of a patient after completing a virtual reality exercise plan for a preset number of cycles, and based on the physical fitness assessment data, call a pre-trained treatment plan automatic generation model to obtain the hemodialysis treatment plan of the patient output by the treatment plan automatic generation model; wherein, the treatment plan automatic generation model is constructed based on a hemodialysis treatment knowledge graph, and the hemodialysis treatment knowledge graph includes a physical fitness assessment entity corresponding to the physical fitness assessment data, a hemodialysis treatment plan entity corresponding to the hemodialysis treatment plan, and an edge used to represent the relationship between the physical fitness assessment entity and the hemodialysis treatment plan entity.

[0097] As an embodiment, the server further includes a complication prediction module and a preventive treatment plan formulation module. Among them, the complication prediction module is used to obtain the basic examination data of the patient during the pre-dialysis preparation stage, and based on the basic examination data, call a pre-trained complication prediction model to obtain the complication prediction result output by the complication prediction model; the preventive treatment plan formulation module is used to formulate a preventive treatment plan according to the complication prediction result and send the preventive treatment plan to the patient client.

[0098] As an embodiment, the basic examination data includes original numerical data and original image data; the server further includes a data preprocessing module, which is used to convert the original numerical data into standard numerical data based on preset conversion rules, and convert the original image data into standard image data based on preset image preprocessing rules, input the standard numerical data into a pre-trained first feature extraction network to obtain a first embedding representation, input the standard image data into a pre-trained second feature extraction network to obtain a second embedding representation; the complication prediction module is specifically configured to input the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model.

[0099] As an embodiment, the complication prediction model includes a probability prediction model for intradialytic hypotension and a probability prediction model for renal anemia. Inputting the third embedding representation into the complication prediction model to obtain the complication prediction result output by the complication prediction model includes: inputting the third embedding representation into the probability prediction model for intradialytic hypotension to obtain the predicted probability of intradialytic hypotension; inputting the third embedding representation into the probability prediction model for renal anemia to obtain the predicted probability of renal anemia.

[0100] As an embodiment, the server further includes a vital sign monitoring module, which is used to obtain the vital sign monitoring data of the patient sent by the intelligent wearable device through the patient client during the post-dialysis follow-up care stage; input the vital sign monitoring data into a pre-trained health status assessment model to obtain the health status assessment results of multiple preset items; when the health status assessment result of any one of the preset items is in a potential health risk warning state, send a warning message to the communication device of the patient.

[0101] As an embodiment, the server further includes an individualized extended care plan generation module, which is configured to input the health status assessment results of multiple preset items into a pre-trained care plan generation model to obtain an individualized extended care plan for the patient; and send the individualized extended care plan to the patient client.

[0102] It should be noted that for the information interaction, execution process, etc. between the above modules / units, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought about can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0103] It should be noted that the device described in the embodiments of the present application is only illustrative. For example, the division of units is only a logical function division, and there may be other division methods in specific implementation scenarios. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0106] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product, and this computer software product is stored in a storage medium.

[0107] Please refer to Figure 5 , the embodiments of the present application further provide a server 300. The server 300 can be a server or a terminal, and the internal structure of the server 300 includes but is not limited to: A memory 310 for storing programs; A processor 320 is configured to execute a program stored in a memory 310. When the processor 320 executes the program stored in the memory 310, the processor 320 is configured to execute the hemodialysis care method in any of the previous embodiments.

[0108] The processor 320 and the memory 310 may be connected via a bus or other means.

[0109] The memory 310, as a non-transitory computer-readable storage medium, can be used to store a non-transitory software program and non-transitory computer-executable programs, such as the hemodialysis care method described in any embodiment of the present application. The processor 320 realizes the hemodialysis care method in any of the previous embodiments by running the non-transitory software program and instructions stored in the memory 310.

[0110] The memory 310 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data for executing the above-mentioned hemodialysis care method. In addition, the memory 310 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 310 may optionally include a memory remotely disposed relative to the processor 320, and these remote memories can be connected to the processor 320 through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0111] The non-transitory software program and instructions required to implement the above-mentioned hemodialysis care method are stored in the memory 310. When executed by one or more processors 320, the hemodialysis care method provided in any embodiment of the present application is executed.

[0112] An embodiment of the present application also provides a computer-readable storage medium storing computer-executable instructions for executing the above-mentioned hemodialysis care method.

[0113] In one embodiment, the storage medium stores computer-executable instructions that are executed by one or more control processors, for example, by one or more processors 320 in the above-mentioned server 300, so that the one or more processors 320 can execute the hemodialysis care method provided in any embodiment of the present application.

[0114] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] Those of ordinary skill in the art can understand that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and their appropriate combinations. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information transmission medium.

[0116] In addition, an embodiment of the present application also provides a computer program product, including a computer program, which when executed by a processor implements the hemodialysis care method in any of the previous embodiments.

[0117] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] It should be noted that in the description of this specification, the descriptions referring to the reference terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0119] Finally, it should be noted that the above embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting it. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present application can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered by the protection scope of the present application.

Claims

1. A hemodialysis nursing method, characterized in that: The method comprises: In the pre-dialysis preparation stage, the initial exercise capacity data of the patient is obtained, a virtual reality exercise plan for the current cycle is generated according to the initial exercise capacity data, and the virtual reality exercise plan for the current cycle is sent to the patient client; Acquiring updated athletic ability data formed by the patient executing the current cycle of the virtual reality exercise plan through the patient client; generating a virtual reality exercise plan for the next cycle according to the updated athletic ability data, and sending the virtual reality exercise plan for the next cycle to the patient client; Acquire physical fitness assessment data of the patient after completing a preset number of cycles of a virtual reality exercise program, generate a hemodialysis treatment plan for the patient based on the physical fitness assessment data, and send the hemodialysis treatment plan to the patient client.

2. The hemodialysis nursing method according to claim 1, characterized in that: Generating a hemodialysis treatment plan for the patient according to the physical fitness assessment data comprises: Based on the physical fitness assessment data, a pre-trained treatment plan automatic generation model is called to obtain the hemodialysis treatment plan of the patient output by the treatment plan automatic generation model; wherein the treatment plan automatic generation model is constructed based on a hemodialysis treatment knowledge graph, and the hemodialysis treatment knowledge graph includes a physical fitness assessment entity corresponding to the physical fitness assessment data, a hemodialysis treatment plan entity corresponding to the hemodialysis treatment plan, and an edge for characterizing the relationship between the physical fitness assessment entity and the hemodialysis treatment plan entity.

3. The hemodialysis nursing method according to claim 1, characterized in that: The method further comprises: In the pre-dialysis preparation stage, obtain the patient's basic examination data; Based on the basic examination data, calling a pre-trained complication prediction model to obtain a complication prediction result output by the complication prediction model; A preventive treatment plan is formulated according to the complication prediction result, and the preventive treatment plan is sent to the patient client.

4. The hemodialysis nursing method according to claim 3, characterized in that: The basic examination data includes original numerical data and original image data; after obtaining the basic examination data of the patient, the method further includes: Based on a preset conversion rule, convert the original numerical data into standard numerical data; Based on a preset image preprocessing rule, the original image data is converted into standard image data, The method of calling a pre-trained complication prediction model based on the basic examination data to obtain a complication prediction result output by the complication prediction model includes: Inputting the standard numerical data into a pre-trained first feature extraction network to obtain a first embedding representation; Inputting the standard image data into a pre-trained second feature extraction network to obtain a second embedding representation; Concatenate the first embedding representation and the second embedding representation into a third embedding representation; The third embedded representation is input into the complication prediction model to obtain a complication prediction result output by the complication prediction model.

5. The hemodialysis nursing method according to claim 4, characterized in that: The complication prediction model includes a probability prediction model for hypotension during osmosis and a probability prediction model for renal anemia. The third embedded representation is input into the complication prediction model to obtain a complication prediction result output by the complication prediction model, including: Inputting the third embedding representation into the infiltration hypotension probability prediction model to obtain the infiltration hypotension prediction probability; The third embedded representation is input into the renal anemia probability prediction model to obtain the renal anemia prediction probability.

6. The hemodialysis nursing method according to claim 1, characterized in that: The method further comprises: In the post-dialysis continuing care stage, the patient's vital sign monitoring data sent by the smart wearable device is obtained through the patient client; Inputting the physical sign monitoring data into a pre-trained health status assessment model to obtain health status assessment results of multiple preset items; When the health status assessment result of any preset item is a potential health risk warning state, a warning message is sent to the patient's communication device.

7. The hemodialysis nursing method according to claim 6, characterized in that: After obtaining the health status assessment result, the method further includes: Inputting the health status assessment results of the plurality of preset items into a pre-trained nursing plan generation model to obtain an individualized continuing nursing plan for the patient; The individualized continuing care plan is sent to the patient client.

8. A hemodialysis nursing service terminal, characterized in that: The server includes: A virtual reality exercise plan generation module is used to obtain the patient's initial exercise capacity data in the pre-dialysis preparation stage, generate a virtual reality exercise plan for the current cycle according to the initial exercise capacity data, and send the virtual reality exercise plan for the current cycle to the patient client; A sports ability data acquisition module, used to acquire updated sports ability data formed by the patient executing the virtual reality exercise plan of the current cycle through the patient client; A virtual reality exercise plan adjustment module, used to generate a virtual reality exercise plan for the next cycle according to the updated athletic ability data, and send the virtual reality exercise plan for the next cycle to the patient client; The hemodialysis treatment plan generation module is used to obtain the physical fitness assessment data of the patient after completing a preset number of cycles of the virtual reality exercise plan, generate a hemodialysis treatment plan for the patient based on the physical fitness assessment data, and send the hemodialysis treatment plan to the patient client.

9. A server, characterized in that: include: Memory, used to store programs; A processor is used to execute the program stored in the memory. When the processor executes the program stored in the memory, the processor is used to execute: the hemodialysis care method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute: the hemodialysis care method according to any one of claims 1 to 7.

Images