Interventional nursing process monitoring method and device and electronic equipment
By constructing a multi-dimensional data screening and prediction model, the risk of bleeding after interventional treatment is automatically identified, which solves the problem of relying on subjective experience in existing technologies, realizes early identification and prevention of bleeding, and improves the safety of the nursing stage.
Patent Information
- Application Number
- CN202511665837.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-13
- Publication Date
- 2026-02-24
AI Technical Summary
In existing technologies, the risk assessment of bleeding after interventional treatment relies on subjective experience and lacks automated identification methods, leading to missed diagnoses of bleeding. Furthermore, patients take antiplatelet drugs for a long time, which can cause side effects.
By constructing multi-dimensional data screening and prediction models, and combining basic medical data, drug usage data, and medical physicochemical data, linear regression and machine learning methods are used to automatically identify bleeding risks and provide quantitative risk scores.
It enables early identification of high-risk patients for bleeding, reduces the occurrence of bleeding, improves patients' quality of life, and lowers the risk of readmission.
Smart Images
Figure CN121565486A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of automated medical technology, specifically to an interventional nursing process control scheme, and more specifically to an interventional nursing process monitoring method, device, and electronic equipment. Background Technology
[0002] Cerebrovascular disease is one of the major threats to people's health. Currently, surgical intervention is the most effective treatment for intracranial aneurysm (UIA), mainly including open craniotomy clipping and endovascular interventional therapy. While open craniotomy clipping has a high clipping rate, it suffers from drawbacks such as significant surgical trauma, large intraoperative bleeding, and long operation time, thus limiting its application. In recent years, with the continuous development of imaging and interventional technologies, endovascular interventional therapy has gradually become the preferred treatment for UIA. Compared to open craniotomy clipping, interventional therapy has advantages such as less trauma and faster postoperative recovery. However, due to the high metal coverage of these intracranial stents, tissue compatibility issues, and the potential damage to the vascular endothelium during intervention, platelet aggregation is easily induced, increasing the risk of postoperative thrombosis and ischemia. Therefore, antiplatelet drugs are needed after stent implantation to reduce the risk of these complications. However, long-term use of antiplatelet drugs (such as aspirin, clopidogrel, and ticagrelor) can lead to skin bruising, gastrointestinal bleeding, or intracranial hemorrhage.
[0003] Therefore, it is crucial to identify high-risk patients for bleeding early and to prevent and intervene in them in a timely manner to reduce the occurrence of bleeding, improve patients' quality of life, and reduce readmissions. Summary of the Invention
[0004] To address the aforementioned technical problems, this invention provides a method, device, and electronic device for monitoring interventional nursing processes. This method involves constructing clinically relevant medical data and filtering the data using linear regression to obtain data relevant to interventional nursing. Furthermore, it uses machine learning to predict risks based on this data. To achieve the above objectives, the technical solution adopted by this invention is as follows:
[0005] In a first aspect, a method for monitoring interventional nursing processes is provided. The method includes: acquiring basic medical data of clinical patients, and obtaining related medical data concerning changes in the nursing process status based on the basic medical data through a screening model; the basic medical data includes basic status data, medication usage data, and medical physicochemical data; retrieving real-time related medical data corresponding to real-time clinical patients, forming a joint input sequence from the real-time related medical data, and inputting the joint input sequence into a training convergent prediction model to obtain clinical bleeding risk.
[0006] In some specific implementations, the basic status data includes age, gender, smoking status value, alcohol consumption status value, hypertension status value, diabetes status value, cerebrovascular disease status value, cardiovascular disease status value, and cardiovascular and cerebrovascular surgery status value.
[0007] In some specific embodiments, the drug usage data includes monoclonal antibody usage status values, bispecific antibody usage status values, and statin drug usage status values.
[0008] In some specific embodiments, the medical physicochemical data include the number of aneurysms, white blood cell count, serum creatinine levels, hemoglobin levels, platelet count, albumin levels, aspartate aminotransferase (AST) levels, alanine aminotransferase (ALT) levels, glomerular filtration rate, body mass index, AA inhibition rate, and ADP inhibition rate.
[0009] In some specific implementations, the associated medical data includes age, gender, serum creatinine levels, aspartate aminotransferase (AST) levels, and ADP inhibition rate.
[0010] In some specific embodiments, the screening model includes a composite model consisting of a unit regression analysis model and a multivariate regression analysis model; obtaining related medical data concerning changes in the nursing process status through the screening model includes: obtaining a first screening result from the basic medical data through the unit regression analysis model, and obtaining the related medical data based on the first screening result using the multivariate regression analysis model.
[0011] In some specific implementations, the prediction model includes an input layer, a hidden layer, and an output layer; the hidden layer includes a 4-layer hidden layer structure, and the number of neurons is allocated through a decreasing strategy.
[0012] In some specific embodiments, the hidden layer includes a first hidden layer, a second hidden layer, a third hidden layer, and a fourth hidden layer. The first hidden layer includes 48 neurons, the second hidden layer includes 24 neurons, the third hidden layer includes 12 neurons, and the fourth hidden layer includes 6 neurons.
[0013] Secondly, an interventional nursing process monitoring device is provided, the device comprising: a data construction module for acquiring basic medical data of clinical patients and obtaining related medical data concerning changes in the nursing process status based on the basic medical data through a screening model; and a prediction module for retrieving real-time related medical data corresponding to real-time clinical patients, forming a joint input sequence from the real-time related medical data, and inputting the joint input sequence into a training convergent prediction model to obtain the clinical bleeding risk.
[0014] Thirdly, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the interventional care process monitoring method described in any of the preceding claims based on instructions stored in the memory.
[0015] The technical solution provided in this application constructs basic medical data relevant to clinical practice. This basic medical data is then subjected to two linear regression processes using a screening model combining unit linear regression and multiple linear regression models to obtain associated medical data highly correlated with bleeding risk. The associated medical data is then used to calculate the risk probability through a prediction model, yielding a final risk value, thereby determining the bleeding risk during the nursing stage. Compared to existing technologies, this application's embodiment can automatically identify high-risk patients for bleeding in the early stages of nursing care, reducing the occurrence of bleeding. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] The methods, systems, and / or procedures shown in the accompanying drawings will be further described with reference to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example figures represent similar mechanisms in the various views of the drawings.
[0018] Figure 1 This is a schematic diagram of the interventional nursing process monitoring method provided in the embodiments of this application.
[0019] Figure 2 This is a schematic diagram of the interventional nursing process monitoring device provided in the embodiments of this application.
[0020] Figure 3 This is a schematic diagram of the terminal device structure provided in the embodiments of this application. Detailed Implementation
[0021] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.
[0022] In the detailed description below, numerous specific details are illustrated with examples to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that this application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level without detail to avoid unnecessarily obscuring aspects of this application.
[0023] This application uses flowcharts to illustrate the execution process performed by a system according to embodiments of this application. It should be clearly understood that the execution processes in the flowcharts may not be executed sequentially. Instead, these execution processes may be executed in reverse order or simultaneously. Additionally, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.
[0024] Before providing a further detailed description of the embodiments of the present invention, the nouns and terms involved in the embodiments of the present invention will be explained, and the nouns and terms involved in the embodiments of the present invention shall be interpreted as follows.
[0025] (1) In response to, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which the operation is performed are met, one or more operations may be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.
[0026] (2) Based on, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order of execution of the multiple operations.
[0027] The recovery period from general anesthesia refers to the process by which a patient recovers from unconsciousness to full consciousness and regains complete protective reflexes. This includes the period from the discontinuation of anesthetic drugs at the end of the procedure until the patient is fully conscious. Delayed recovery from anesthesia refers to a patient not waking up more than two hours after general anesthesia. It is a common complication following general anesthesia. Risk factors for delayed recovery from anesthesia can be broadly categorized into four types: patient-related factors, anesthetic drug factors, surgical procedure and anesthesia management factors, and perioperative metabolic factors.
[0028] This application provides a method for monitoring interventional nursing procedures, applied to predict the risk of bleeding following stent implantation in patients with unruptured intracranial aneurysms (UIA) after the use of antiplatelet drugs. Ischemic complications are most common after stent implantation in UIA patients, with an incidence rate of 2.5%–28%. Therefore, postoperative antiplatelet drugs are necessary for the prevention of ischemic complications. Currently, there is no consensus or guideline regarding the type, dosage, and duration of antiplatelet drugs used after stent implantation in UIA patients. The influencing factors for postoperative bleeding after antiplatelet drug use are also unclear, and nursing staff often rely on subjective experience or single indicators to assess postoperative bleeding risk, which can easily lead to missed diagnoses.
[0029] To address this technical challenge, a method for monitoring the interventional nursing process is provided. This method can integrate multi-dimensional data to output a quantitative risk score, helping nurses quickly identify high-risk patients and reducing misjudgments in nursing assessments.
[0030] For details on this method, please refer to [link / reference]. Figure 1 This includes the following steps:
[0031] Step S11. Obtain basic medical data of clinical patients, and obtain related medical data on changes in the nursing process status based on the basic medical data through a screening model.
[0032] In this embodiment, the screening model is a composite model consisting of a unit regression analysis model and a multivariate regression analysis model. The basic medical data includes basic condition data, drug usage data, and medical physicochemical data.
[0033] The baseline data includes age, sex, smoking status, alcohol consumption status, hypertension status, diabetes status, cerebrovascular disease status, cardiovascular disease status, and cardiovascular surgery status; the medication use data includes monoclonal antibody use status, dual antibody use status, and statin use status; the medical physiochemical data includes aneurysm number, white blood cell count, serum creatinine levels, hemoglobin levels, platelet count, albumin levels, aspartate aminotransferase (AST) levels, alanine aminotransferase (ALT) levels, glomerular filtration rate, body mass index, AA inhibition rate, and ADP inhibition rate; and the associated medical data includes age, sex, serum creatinine levels, AST levels, and ADP inhibition rate.
[0034] The screening model first processes the aforementioned basic medical data using a unit regression analysis model to obtain the first screening result. Then, it processes the first screening result using a multiple regression analysis model to obtain the second screening result, which is the associated medical data in this embodiment. Specifically, the associated medical data includes age, gender, serum creatinine levels, aspartate aminotransferase (AST) levels, and ADP inhibition rate.
[0035] In this embodiment, for the above state value of 0 or 1, the state value is 0 when the corresponding drug is not used, and the state value is 1 when the corresponding drug is used.
[0036] Step S12. Retrieve real-time related medical data corresponding to real-time clinical patients, form a joint input sequence from the real-time related medical data, and input the joint input sequence into a training convergent prediction model to obtain the clinical bleeding risk.
[0037] In this embodiment, the prediction model is constructed using an ANN model built with the PyTorch framework. To improve the model's interpretability, an attention mechanism is used in the network to assign different weights to each feature, allowing the model to automatically learn the importance of each feature. The top 10 features by weight are modeled. To reduce the risk of overfitting, Dropout regularization is used in the model, which improves the model's generalization ability by randomly dropping some neurons during training.
[0038] Specifically, the prediction model includes an input layer, hidden layers, and an output layer. The number of neurons in the input layer is the same as the number of input features; in this embodiment, the input layer has 5 neurons. The number of neurons in the hidden layers is typically adjusted based on the input dimensionality, task complexity, and empirical formulas. For datasets with small input dimensionality, a shallow depth may lead to insufficient model learning ability, while an excessively deep depth may lead to overfitting. This embodiment uses a 4-layer hidden layer structure, and the number of neurons is allocated using a decreasing strategy, specifically including a first hidden layer, a second hidden layer, a third hidden layer, and a fourth hidden layer.
[0039] Specifically, the first hidden layer comprises 48 neurons. This layer is used for feature transformation, mapping the original features to a higher-dimensional space, enabling subsequent layers to better capture patterns. In this embodiment, the number of neurons is chosen to be three times the input dimension to ensure the model has sufficient learning capacity. The second hidden layer comprises 24 neurons. Based on the features extracted from the first layer, this layer uses a decreasing strategy to reduce the number of neurons to 24, in order to filter key features, improve computational efficiency, and reduce redundant information and the risk of overfitting. The third hidden layer comprises 12 neurons. This layer further reduces the number of neurons to 12, performs feature depth compression, and reduces computational cost. At this point, the network has learned a relatively refined feature representation, gradually approaching the decision layer. The third hidden layer comprises 6 neurons. This layer serves as the final feature selection layer, retaining 6 neurons to ensure that the output layer can classify based on refined features, while avoiding overfitting due to too many parameters.
[0040] In this embodiment, the output layer uses the Sigmoid activation function to map the final output result to a probability value between 0 and 1, which is used to determine whether the patient has a specific bleeding risk. When the bleeding probability value is greater than a preset threshold, an alarm is directly triggered to indicate the risk.
[0041] This application provides a method for monitoring interventional nursing processes. It constructs basic medical data relevant to clinical practice, and then performs two linear regression processes on this data using a screening model combining unit linear regression and multiple linear regression models to obtain associated medical data highly correlated with bleeding risk. This associated medical data is then used to calculate the risk probability using a predictive model, yielding a final risk value, thereby determining the bleeding risk during the nursing stage. Compared to existing technologies, this application can automatically identify high-risk patients for bleeding in the early stages of nursing care, reducing the occurrence of bleeding.
[0042] See Figure 2 This application embodiment also provides an interventional nursing process monitoring device 20, the device comprising:
[0043] The data construction module 21 is used to acquire basic medical data of clinical patients and obtain related medical data about changes in the nursing process status based on the basic medical data through a screening model.
[0044] The prediction module 22 is used to retrieve real-time related medical data corresponding to real-time clinical patients, form a joint input sequence from the real-time related medical data, and input the joint input sequence into a prediction model that has been trained to convergence to obtain the clinical bleeding risk.
[0045] See Figure 3 The above methods can also be integrated into the provided terminal device 300. Since devices may vary significantly due to differences in configuration or performance, it can include one or more processors 301 and memories 302. The memories 302 can store one or more application programs or data. The memories 302 can be temporary or persistent storage. The application programs stored in the memories 302 can include one or more modules (not shown in the figures), each module including a series of computer-executable instructions from the terminal device. Furthermore, the processor 301 can be configured to communicate with the memories 302, and the terminal device can execute the series of computer-executable instructions stored in the memories 302. The terminal device can also include one or more power supplies 303, one or more wired / wireless network interfaces 304, one or more input / output interfaces 305, one or more keyboards 306, etc.
[0046] In one specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for use in the terminal device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:
[0047] Acquire basic medical data of clinical patients, and obtain related medical data on changes in the nursing process status based on the basic medical data through a screening model;
[0048] Real-time related medical data corresponding to real-time clinical patients are retrieved, and the real-time related medical data are combined into a joint input sequence. The joint input sequence is then input into a training and convergent prediction model to obtain the clinical bleeding risk.
[0049] Optionally, the processor can perform various functions, such as the above-mentioned functions, by running or executing software programs stored in memory and by calling data stored in memory. Figure 1 The method shown.
[0050] In a specific implementation, as one example, the processor may include one or more microprocessors.
[0051] The memory is used to store the software program that executes the solution of this application, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.
[0052] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.
[0053] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0054] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0055] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0056] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0057] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for monitoring interventional nursing processes, characterized in that, The method includes: Acquire basic medical data of clinical patients, and obtain related medical data concerning changes in the nursing process status through a screening model based on the basic medical data; the basic medical data includes basic status data, medication use data, and medical physicochemical data; Real-time related medical data corresponding to real-time clinical patients are retrieved, and the real-time related medical data are combined into a joint input sequence. The joint input sequence is then input into a training and convergent prediction model to obtain the clinical bleeding risk.
2. The method for monitoring the interventional nursing process according to claim 1, characterized in that, The basic status data includes age, gender, smoking status, alcohol consumption status, hypertension status, diabetes status, cerebrovascular disease status, cardiovascular disease status, and cardiovascular surgery status.
3. The method for monitoring the interventional nursing process according to claim 1, characterized in that, The drug usage data includes monoclonal antibody usage status values, bispecific antibody usage status values, and statin drug usage status values.
4. The method for monitoring the interventional nursing process according to claim 1, characterized in that, The medical physiochemical data include the number of aneurysms, white blood cell count, serum creatinine levels, hemoglobin levels, platelet count, albumin levels, aspartate aminotransferase (AST) levels, alanine aminotransferase (ALT) levels, glomerular filtration rate, body mass index, AA inhibition rate, and ADP inhibition rate.
5. The method for monitoring the interventional nursing process according to claim 1, characterized in that, The associated medical data includes age, gender, serum creatinine levels, aspartate aminotransferase (AST) levels, and ADP inhibition rate.
6. The interventional nursing process monitoring method according to claim 5, characterized in that, The screening model includes a composite model consisting of a unit regression analysis model and a multivariate regression analysis model; obtaining related medical data concerning changes in the nursing process status through the screening model includes: obtaining a first screening result from the basic medical data through the unit regression analysis model, and obtaining the related medical data based on the first screening result using the multivariate regression analysis model.
7. The method for monitoring the interventional nursing process according to claim 6, characterized in that, The prediction model includes an input layer, a hidden layer, and an output layer; the hidden layer includes a 4-layer hidden layer structure, and the number of neurons is allocated through a decreasing strategy.
8. The method for monitoring the interventional nursing process according to claim 7, characterized in that, The hidden layer includes a first hidden layer, a second hidden layer, a third hidden layer, and a fourth hidden layer. The first hidden layer includes 48 neurons, the second hidden layer includes 24 neurons, the third hidden layer includes 12 neurons, and the fourth hidden layer includes 6 neurons.
9. A monitoring device for interventional nursing processes, characterized in that, The device includes: The data construction module is used to acquire basic medical data of clinical patients and, based on the basic medical data, obtain related medical data concerning changes in the nursing process status through a screening model. The prediction module is used to retrieve real-time related medical data corresponding to real-time clinical patients, form a joint input sequence from the real-time related medical data, and input the joint input sequence into a prediction model that has been trained to convergence to obtain the clinical bleeding risk.
10. An electronic device, comprising: Memory; and a processor coupled to the memory, the processor being configured to execute the interventional care process monitoring method of any one of claims 1-8 based on instructions stored in the memory.