Intelligent management platform and management method for atrial fibrillation patient

Abstract

The invention relates to an atrial fibrillation patient intelligent management platform and management method, which combines an AI algorithm model to perform big data learning on atrial fibrillation symptom data and clinical diagnosis and treatment measures of an atrial fibrillation patient, and utilizes the model to provide symptom recognition for the atrial fibrillation patient and recommend an emergency use strategy of an atrial fibrillation drug warfarin. According to the method, the model can recommend correspondingly matched warfarin usage and dosage according to the atrial fibrillation symptoms of the atrial fibrillation patient, so that first-aid measures which can be referenced and executed are quickly provided for the atrial fibrillation patient, manual analysis is replaced, the first-aid management capability of the atrial fibrillation patient is improved, the prevention and management level of atrial fibrillation is improved, and the prevention and management efficiency is improved. The potential safety hazard caused by the fact that the atrial fibrillation patient cannot obtain the first-aid medicine is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of smart medical management technology, and in particular to a smart management method for patients with atrial fibrillation, a smart management platform for patients with atrial fibrillation, and electronic equipment. Background Art

[0002] Atrial fibrillation, or atrial fibrillation, is a common heart rhythm disorder with varying symptoms that may include: Palpitations: manifested as panic and abnormal heartbeat, which may occur intermittently or continuously, affecting life and work.

[0003] Chest tightness: The atria cannot pump blood effectively, resulting in insufficient blood supply to the body's organs, especially the cardiopulmonary system. Patients have a feeling of tightness in the chest, which may be accompanied by shortness of breath and difficulty breathing.

[0004] Fatigue: Impaired heart function affects blood circulation, insufficient energy supply to various tissues and organs, muscle involvement, general fatigue and weakness, decreased activity endurance, easy fatigue with mild physical activity, and severe cases can affect limb movement and self-care.

[0005] Dizziness: Abnormal heart pumping causes insufficient blood supply to the brain, leading to dizziness, which may be accompanied by vertigo and blurred vision. The severity and frequency of attacks vary from person to person, seriously affecting the quality of life and safety.

[0006] Polyuria: During atrial fibrillation, the atria lose their contractile function, the pressure inside the atria increases, leading to increased secretion of substances such as atrial natriuretic peptide, causing increased urine volume.

[0007] Emotional problems: Some patients may also experience increased psychological stress, anxiety, depression and other emotional problems due to long-term atrial fibrillation.

[0008] In addition, symptoms such as cold hands and feet and dizziness may also occur.

[0009] Clinical treatments for atrial fibrillation mainly include: General treatment: Adjust your mentality and avoid negative emotional stimulation. When hypoxia is severe, it can be relieved by oxygen inhalation. At the same time, ECG monitoring can be performed to observe the condition.

[0010] Drug treatment: mainly by controlling ventricular rate, preventing thrombosis and other methods to relieve symptoms and reduce risks. The choice of drugs should be based on the specific cause of the patient. For example, if atrial fibrillation is caused by rheumatic heart disease, nitroglycerin tablets, quick-acting heart-saving pills and other drugs can be used for treatment; if it is caused by infective endocarditis, penicillin V potassium tablets, amoxicillin capsules and other drugs can be used for treatment; if atrial fibrillation has a persistent fast heart rate, metoprolol tartrate tablets, atenolol tablets and other drugs can be used for treatment. Antiarrhythmic drugs such as amiodarone and propafenone are mainly used to control ventricular rate and prevent atrial fibrillation. Anticoagulants such as warfarin and rivaroxaban are mainly used to prevent thrombosis.

[0011] Surgical treatment: If drug treatment is ineffective, surgical treatment can be considered. Common surgical methods include cardiac radiofrequency ablation and surgical maze surgery, which achieve the purpose of treatment by eliminating the atrial fibrillation lesions.

[0012] Other treatments: For atrial fibrillation in emergency situations (such as myocardial infarction, heart failure, etc.) or patients with severe atrial fibrillation symptoms, electrical cardioversion can be considered to restore sinus rhythm.

[0013] In the existing technology, drug therapy is still an important method for treating atrial fibrillation. Drugs can restore and maintain sinus rhythm, control ventricular rate and prevent thromboembolic complications. Warfarin is one of the main drugs for treating patients with atrial fibrillation. In the existing medical field, the use of warfarin already has usage specifications to guide doctors and patients to correctly use the dose of warfarin. However, in the actual medical process, medical staff do not have a clear understanding of the use specifications of warfarin. They also need to manually analyze the condition of patients with atrial fibrillation and issue corresponding warfarin medication orders. Therefore, it takes a long analysis cycle and the use efficiency is low, resulting in patients' prevention of atrial fibrillation not reaching the ideal management level, and there are major safety risks. Summary of the invention

[0014] In order to solve the above problems, the present application proposes an intelligent management method for atrial fibrillation patients, an intelligent management platform for atrial fibrillation patients and an electronic device.

[0015] On the one hand, the present application proposes a smart management method for patients with atrial fibrillation, comprising the following steps: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4. Send the atrial fibrillation diagnosis and treatment instructions to the medical staff, and notify the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient.

[0016] As an optional implementation scheme of the present application, optionally, the method for generating the atrial fibrillation diagnosis and treatment prediction model includes: Collecting atrial fibrillation symptom big data of several atrial fibrillation patients, wherein the atrial fibrillation symptom big data includes the sinus rhythm, ventricular rate control and corresponding warfarin doctor's advice strategy of the atrial fibrillation patients, and the warfarin doctor's advice strategy includes the corresponding warfarin usage frequency and dosage each time; Performing feature engineering on the atrial fibrillation symptom big data, identifying and extracting atrial fibrillation symptom features of each atrial fibrillation patient undergoing clinical management of atrial fibrillation and corresponding warfarin doctor's advice strategy, and obtaining a feature set consisting of several groups of features: {atrial fibrillation symptom features, warfarin doctor's advice strategy}; Divide the feature set into training set and validation set according to the preset ratio; The training set is input into a preset RF random forest model, the corresponding relationship characteristics between each group of atrial fibrillation symptom characteristics and the corresponding warfarin doctor's advice strategy are learned, and the atrial fibrillation diagnosis and treatment prediction model is constructed through training; The prediction performance of the atrial fibrillation diagnosis and treatment prediction model is verified using the verification set: If the verification is successful, the atrial fibrillation diagnosis and treatment prediction model is deployed and applied on the background server; If the verification fails, the above steps are repeated to reconstruct the atrial fibrillation diagnosis and treatment prediction model.

[0017] As an optional implementation scheme of the present application, optionally, S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, identifying the atrial fibrillation symptom characteristics in the atrial fibrillation symptom data by the atrial fibrillation diagnosis and treatment prediction model, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics, including: Read the atrial fibrillation symptom data of the atrial fibrillation patient from the electronic medical record of the atrial fibrillation patient stored in the HIS system: sinus rhythm and controlled ventricular rate; The atrial fibrillation symptom data is input into the atrial fibrillation diagnosis and treatment prediction model, and the atrial fibrillation diagnosis and treatment prediction model is used to match and output a warfarin prescription strategy that matches the sinus rhythm and controlled ventricular rate based on the learned relationship features, including the frequency of warfarin use that matches the sinus rhythm and controlled ventricular rate and the current warfarin dosage.

[0018] On the other hand, the present application proposes an intelligent management platform for patients with atrial fibrillation, which is used to implement an intelligent management method for patients with atrial fibrillation, including: The medical end is used to collect and upload atrial fibrillation symptom data of patients with atrial fibrillation; Backend server, used for: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4, sending the atrial fibrillation diagnosis and treatment instructions to the medical terminal, and notifying the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient; The medical end is communicatively connected with the background server.

[0019] In another aspect, the present application further provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the intelligent management method for atrial fibrillation patients when executing the executable instructions.

[0020] Technical effects of the present invention: This application combines AI algorithm models to conduct big data learning on atrial fibrillation symptom data and clinical diagnosis and treatment measures of atrial fibrillation patients, and uses the model to provide symptom identification for atrial fibrillation patients and recommend emergency use strategies for the atrial fibrillation drug warfarin. The model can recommend corresponding warfarin usage and dosage based on the atrial fibrillation symptoms of atrial fibrillation patients, thereby quickly providing atrial fibrillation patients with reference and executable emergency measures, thereby replacing manual analysis to improve the emergency management capabilities of atrial fibrillation patients, improve the level of prevention and management of atrial fibrillation, and reduce the safety risks caused by the lack of emergency drugs for atrial fibrillation patients.

[0021] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0023] Figure 1 It is shown as a schematic diagram of the implementation process of the present invention; Figure 2 It is shown as a schematic diagram of the model training process of the present invention; Figure 3 It is a schematic diagram showing the structure of the platform architecture system of the present invention; Figure 4 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0024] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0025] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0026] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0027] In this embodiment, clinical examinations of patients with atrial fibrillation can be combined with existing technologies to perform examinations and upload data. For electronic medical records of patients with atrial fibrillation, an administrator can create and bind the patient's medical ID on the HIS system. Example 1

[0028] like Figure 1 As shown, on the one hand, the present application proposes a smart management method for patients with atrial fibrillation, comprising the following steps: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4. Send the atrial fibrillation diagnosis and treatment instructions to the medical staff, and notify the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient.

[0029] The present invention mainly combines AI algorithm models to conduct big data learning on atrial fibrillation symptom data and clinical diagnosis and treatment measures of atrial fibrillation patients, and uses the model to provide symptom recognition for atrial fibrillation patients and recommend emergency use strategies for the atrial fibrillation drug warfarin. The model can recommend corresponding warfarin usage and dosage based on the atrial fibrillation symptoms of atrial fibrillation patients, thereby quickly providing atrial fibrillation patients with reference and executable emergency measures, thereby replacing manual analysis to improve the emergency management capabilities of atrial fibrillation patients, improve the level of prevention and management of atrial fibrillation, and reduce the safety hazards caused by the lack of emergency drugs for atrial fibrillation patients.

[0030] The specific implementation of this plan is as follows: S1. Obtain AF symptom data of AF patients: Symptom data of atrial fibrillation patients, such as palpitations, dyspnea, fatigue, syncope, and shortness of breath after activity, were collected through self-report, electrocardiogram monitoring, wearable devices, etc.

[0031] S2. Import atrial fibrillation symptom data into the preset atrial fibrillation diagnosis and treatment prediction model: Utilize advanced algorithms and big data analysis techniques to establish a predictive model for the diagnosis and treatment of atrial fibrillation.

[0032] The collected atrial fibrillation symptom data is input into the model, and the model automatically identifies symptom characteristics, such as abnormal heart rate and arrhythmia.

[0033] Based on the symptom characteristics, the model recommends a warfarin prescription strategy that matches the symptoms of atrial fibrillation, including dosage, frequency of medication, etc.

[0034] S3. Generate the corresponding atrial fibrillation diagnosis and treatment instructions and bind them with the atrial fibrillation patient's visit ID: Detailed diagnosis and treatment orders are automatically generated based on the warfarin order strategy recommended by the model.

[0035] The generated medical instructions are bound to the patient's medical ID to ensure the accuracy and traceability of the instructions.

[0036] S4. Send the atrial fibrillation diagnosis and treatment instructions to the medical staff, and notify the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient: The generated atrial fibrillation diagnosis and treatment instructions are sent to the medical staff through the electronic medical record system, text messages, emails, etc.

[0037] Notify medical staff to check and execute medical orders in a timely manner to ensure that patients receive timely and effective treatment.

[0038] Therefore, this solution can have the following technical advantages: ‌High efficiency‌: Through automated and intelligent means, atrial fibrillation symptom data can be quickly collected, analyzed and processed to improve diagnosis and treatment efficiency.

[0039] ‌Accuracy‌: Utilize advanced algorithms and big data analysis technology to establish an accurate prediction model for the diagnosis and treatment of atrial fibrillation to ensure the accuracy and effectiveness of medical advice.

[0040] ‌Personalization‌: Based on the patient's specific symptom characteristics, a personalized warfarin prescription strategy is recommended to meet the patient's personalized treatment needs.

[0041] ‌Traceability‌: Bind the generated medical instructions to the patient’s medical ID to ensure the traceability of the instructions, facilitating subsequent medical quality management and patient health management.

[0042] Convenience: Through electronic medical record systems and other means, medical orders can be delivered and executed instantly, reducing the workload of medical staff and improving the convenience of diagnosis and treatment services.

[0043] The construction scheme of this model will be further described below.

[0044] like Figure 2 As shown, as an optional implementation scheme of the present application, optionally, the method for generating the atrial fibrillation diagnosis and treatment prediction model includes: Collecting atrial fibrillation symptom big data of several atrial fibrillation patients, wherein the atrial fibrillation symptom big data includes the sinus rhythm, ventricular rate control and corresponding warfarin doctor's advice strategy of the atrial fibrillation patients, and the warfarin doctor's advice strategy includes the corresponding warfarin usage frequency and dosage each time; Performing feature engineering on the atrial fibrillation symptom big data, identifying and extracting atrial fibrillation symptom features of each atrial fibrillation patient undergoing clinical management of atrial fibrillation and corresponding warfarin doctor's advice strategy, and obtaining a feature set consisting of several groups of features: {atrial fibrillation symptom features, warfarin doctor's advice strategy}; Divide the feature set into training set and validation set according to the preset ratio; The training set is input into a preset RF random forest model, the corresponding relationship characteristics between each group of atrial fibrillation symptom characteristics and the corresponding warfarin doctor's advice strategy are learned, and the atrial fibrillation diagnosis and treatment prediction model is constructed through training; The prediction performance of the atrial fibrillation diagnosis and treatment prediction model is verified using the verification set: If the verification is successful, the atrial fibrillation diagnosis and treatment prediction model is deployed and applied on the background server; If the verification fails, the above steps are repeated to reconstruct the atrial fibrillation diagnosis and treatment prediction model.

[0045] In daily medical care management, the medical care records of several atrial fibrillation patients can be recorded in the background database. These records contain the patient's atrial fibrillation symptoms and corresponding medication records. Therefore, the corresponding data can be collected from the background and used for model training.

[0046] Preprocessing such as data cleaning can be handled by the administrator.

[0047] ‌The detailed implementation and examples of the model building scheme are as follows:‌ ‌1. Data Collection‌ ‌Data Source‌: Medical record data of patients with atrial fibrillation were collected from the electronic medical record systems of multiple hospitals. Real-time physiological data of patients with atrial fibrillation were collected through wearable devices or remote monitoring systems.

[0048] ‌Data Content‌: Sinus rhythm: Record the patient's basic heart rhythm as an important reference for atrial fibrillation symptoms.

[0049] Control ventricular rate: Record the patient's ventricular rate during atrial fibrillation to assess the severity of atrial fibrillation.

[0050] Warfarin prescription strategy: includes the frequency of warfarin use (such as how many times a day) and the dosage each time (such as how many tablets each time) prescribed by the doctor for the patient.

[0051] ‌Example‌: Suppose data is collected from 1,000 patients with atrial fibrillation, each of whom has multiple recordings of sinus rhythm, ventricular rate control, and corresponding warfarin prescription strategies.

[0052] ‌2. Feature Engineering‌ ‌Data Preprocessing‌: Clean the data to remove invalid or erroneous records.

[0053] The data are normalized or standardized to ensure comparability between different features.

[0054] ‌Feature Extraction‌: Identify and extract the symptom characteristics of atrial fibrillation during each clinical management of atrial fibrillation, such as the abnormal degree of sinus rhythm, the fluctuation of ventricular rate control, etc.

[0055] The corresponding warfarin prescription strategy was also included as one of the characteristics.

[0056] ‌Example‌: For each patient, the sinus rhythm value and the controlled ventricular rate value at each atrial fibrillation attack, as well as the frequency and dosage of warfarin prescribed by the doctor were extracted. In this way, a feature set consisting of {atrial fibrillation symptom features, warfarin doctor's prescription strategy} was obtained.

[0057] ‌3. Dataset Division‌ ‌Division ratio‌: The feature set is divided into a training set and a validation set in a ratio of 8:2.

[0058] ‌Example‌: In the feature set of 1000 patients, the data of 800 patients were randomly selected as the training set, and the data of the remaining 200 patients were used as the validation set.

[0059] ‌4. Model training‌ ‌Model Selection‌: The RF random forest model was selected as the prediction model.

[0060] ‌Model Training‌: The training set is input into the RF random forest model.

[0061] The learning and training process of the random forest model for the feature set can refer to the following steps: 1) Sample extraction Random forest uses Bootstraping (sampling with replacement) to randomly extract multiple training sets from the original sample set. The number of samples in each training set is the same as that in the original sample set, but during the extraction process, there may be samples that are repeatedly extracted, or there may be samples that are not extracted at all.

[0062] 2. Feature selection When generating each decision tree, random forest will randomly select a part of the features from the original feature set to build the decision tree. This random feature selection method helps to increase the diversity of the model, thereby improving the generalization ability of the model.

[0063] 3) Decision tree generation The decision tree is trained using the extracted training set and the selected feature set. The decision tree generation process is a recursive process until the stopping condition is met (such as reaching the maximum depth, the number of samples in the node is less than the preset threshold, all samples belong to the same category, etc.). In the process of generating the decision tree, no pruning operation is performed.

[0064] 4) Model combination The generated multiple decision trees are combined into a random forest model. For classification problems, the final classification result is determined by the votes of all decision trees; for regression problems, the final output result is the mean of the outputs of all decision trees.

[0065] V) Model Validation The validation of the random forest model can be performed by using a dataset that was not used for training (such as OOB samples, i.e., out-of-bag samples). By calculating the predictive performance of the OOB samples on the model, the generalization ability of the model can be evaluated.

[0066] The random forest model trains multiple decision trees by randomly extracting samples and features multiple times, and uses the integrated decision of multiple decision trees to improve the stability and accuracy of the model. This integrated learning method makes the random forest model more robust and generalizable when processing complex data sets.

[0067] The model learns the corresponding relationship characteristics between each group of atrial fibrillation symptom characteristics and the corresponding warfarin doctor's advice strategy.

[0068] Through iterative training and optimization of model parameters, a prediction model for the diagnosis and treatment of atrial fibrillation was constructed.

[0069] ‌Example‌: The RF random forest model was trained using a training set of 800 patients. By adjusting the model parameters, such as the number of trees and maximum depth, a prediction model for the diagnosis and treatment of atrial fibrillation was obtained that can accurately predict the warfarin prescription strategy for patients with atrial fibrillation.

[0070] ‌V. Model Validation‌ ‌Verification method‌: The validation set was used to verify the predictive performance of the atrial fibrillation diagnosis and treatment prediction model.

[0071] The predictive accuracy of the model was evaluated by comparing the differences between the warfarin ordering strategies predicted by the model and the actual ordering strategies issued by physicians.

[0072] ‌Verification Result‌: If the verification passes (such as accuracy, recall rate and other indicators reach the preset standards), the atrial fibrillation diagnosis and treatment prediction model will be deployed and applied on the background server.

[0073] If the verification fails, repeat the above steps to rebuild the atrial fibrillation diagnosis and treatment prediction model.

[0074] ‌Example‌: The remaining 200 patients’ validation set was used to validate the atrial fibrillation diagnosis and treatment prediction model. By calculating the accuracy, recall and other indicators between the warfarin prescription strategy predicted by the model and the actual prescription strategy, it was found that the prediction performance of the model reached the preset standard. Therefore, the model was deployed and applied on the background server to support the clinical management of atrial fibrillation patients.

[0075] As an optional implementation scheme of the present application, optionally, S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, identifying the atrial fibrillation symptom characteristics in the atrial fibrillation symptom data by the atrial fibrillation diagnosis and treatment prediction model, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics, including: Read the atrial fibrillation symptom data of the atrial fibrillation patient from the electronic medical record of the atrial fibrillation patient stored in the HIS system: sinus rhythm and controlled ventricular rate; The atrial fibrillation symptom data is input into the atrial fibrillation diagnosis and treatment prediction model, and the atrial fibrillation diagnosis and treatment prediction model is used to match and output a warfarin prescription strategy that matches the sinus rhythm and controlled ventricular rate based on the learned relationship features, including the frequency of warfarin use that matches the sinus rhythm and controlled ventricular rate and the current warfarin dosage.

[0076] Please understand this in conjunction with the above model training and its principles. In an embodiment of clinical prediction: ‌Using a clinical example of a patient with atrial fibrillation to implement the solution‌ Patient basic information: Name: Zhang Age: 65 Gender: Male Medical history: 3-year history of atrial fibrillation, with recent symptoms of palpitations and chest tightness.

[0077] ‌Steps to implement the plan‌: ‌Read atrial fibrillation symptom data from HIS system‌: Medical staff log into the hospital's HIS (Hospital Information System) system.

[0078] Zhang’s electronic medical record file was located in the system.

[0079] The atrial fibrillation symptom data of Zhang during this visit was read from the electronic medical record, including: Sinus rhythm: recorded as 100 beats / minute (slightly fast).

[0080] Control ventricular rate: recorded as 120 beats / minute (during atrial fibrillation).

[0081] ‌Input atrial fibrillation symptom data into the atrial fibrillation diagnosis and treatment prediction model‌: The medical staff input Zhang's sinus rhythm and controlled ventricular rate data into the atrial fibrillation diagnosis and treatment prediction model that had been deployed on the background server.

[0082] After the model receives the data, it starts matching based on the previously learned relationship features.

[0083] ‌Match and output warfarin order strategy‌: The atrial fibrillation diagnosis and treatment prediction model matches similar historical case data based on the input sinus rhythm and controlled ventricular rate data.

[0084] The model analyzes the warfarin usage strategies in these historical case data, and combines Zhang's specific situation (such as age, weight, previous medication history, etc., which have been taken into account during model training), and outputs a warfarin prescription strategy that matches Zhang's current symptoms.

[0085] The exported warfarin ordering strategy includes: Frequency of warfarin use: It is recommended to take it once a day.

[0086] The recommended dosage of warfarin for this time is 2.5 mg (adjusted according to Zhang’s specific situation).

[0087] Medical staff executes the doctor's orders: Medical staff wrote a specific medication prescription for Zhang based on the warfarin prescription strategy output by the atrial fibrillation diagnosis and treatment prediction model.

[0088] Explain the medication methods, precautions, etc. to Zhang in detail and ensure his understanding.

[0089] Arrange a follow-up plan to monitor Zhang’s medication effectiveness and changes in his condition.

[0090] Through this example, we can see the value of the atrial fibrillation diagnosis and treatment prediction model in actual clinical applications. It can help medical staff quickly and accurately formulate personalized warfarin medication strategies based on the patient's atrial fibrillation symptom data, thereby improving the effectiveness and safety of treatment. At the same time, this also reflects the huge potential of big data and artificial intelligence technology in the medical field.

[0091] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory. Example 2

[0092] like Figure 3 As shown, based on the implementation principle of Example 1, the present application, on the other hand, proposes an intelligent management platform for patients with atrial fibrillation, which is used to implement an intelligent management method for patients with atrial fibrillation, including: The medical end is used to collect and upload atrial fibrillation symptom data of patients with atrial fibrillation; Backend server, used for: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4, sending the atrial fibrillation diagnosis and treatment instructions to the medical terminal, and notifying the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient; The medical end is communicatively connected with the background server.

[0093] Please understand the above-mentioned interaction between the medical terminal and the background server in conjunction with the description of Example 1.

[0094] The modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software. Example 3

[0095] like Figure 4 As shown, further, in another aspect, the present application also proposes an electronic device, including: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the intelligent management method for atrial fibrillation patients when executing the executable instructions.

[0096] The electronic device according to the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to implement any of the above-mentioned intelligent management methods for patients with atrial fibrillation when executing the executable instructions.

[0097] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device in the embodiment of the present disclosure may also include an input device and an output device. Among them, the processor, memory, input device and output device may be connected through a bus or in other ways, which are not specifically limited here.

[0098] The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the intelligent management method for patients with atrial fibrillation in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0099] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0100] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for intelligent management of patients with atrial fibrillation, characterized in that: The steps include: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4. Send the atrial fibrillation diagnosis and treatment instructions to the medical staff, and notify the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient.

2. The intelligent management method for patients with atrial fibrillation according to claim 1, characterized in that: The method for generating the atrial fibrillation diagnosis and treatment prediction model comprises: Collecting atrial fibrillation symptom big data of several atrial fibrillation patients, wherein the atrial fibrillation symptom big data includes the sinus rhythm, ventricular rate control and corresponding warfarin doctor's advice strategy of the atrial fibrillation patients, and the warfarin doctor's advice strategy includes the corresponding warfarin usage frequency and dosage each time; Performing feature engineering on the atrial fibrillation symptom big data, identifying and extracting atrial fibrillation symptom features of each atrial fibrillation patient undergoing clinical management of atrial fibrillation and corresponding warfarin doctor's advice strategy, and obtaining a feature set consisting of several groups of features: {atrial fibrillation symptom features, warfarin doctor's advice strategy}; Divide the feature set into training set and validation set according to the preset ratio; The training set is input into a preset RF random forest model, the corresponding relationship characteristics between each group of atrial fibrillation symptom characteristics and the corresponding warfarin doctor's advice strategy are learned, and the atrial fibrillation diagnosis and treatment prediction model is constructed through training; The prediction performance of the atrial fibrillation diagnosis and treatment prediction model is verified using the verification set: If the verification is successful, the atrial fibrillation diagnosis and treatment prediction model is deployed and applied on the background server; If the verification fails, the above steps are repeated to reconstruct the atrial fibrillation diagnosis and treatment prediction model.

3. The intelligent management method for atrial fibrillation patients according to claim 2, characterized in that: S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics, including: Read the atrial fibrillation symptom data of the atrial fibrillation patient from the electronic medical record of the atrial fibrillation patient stored in the HIS system: sinus rhythm and controlled ventricular rate; The atrial fibrillation symptom data is input into the atrial fibrillation diagnosis and treatment prediction model, and the atrial fibrillation diagnosis and treatment prediction model is used to match and output a warfarin prescription strategy that matches the sinus rhythm and controlled ventricular rate based on the learned relationship features, including the frequency of warfarin use that matches the sinus rhythm and controlled ventricular rate and the current warfarin dosage.

4. An intelligent management platform for patients with atrial fibrillation, used to implement the intelligent management method for patients with atrial fibrillation according to any one of claims 1 to 3, characterized in that: include: The medical end is used to collect and upload atrial fibrillation symptom data of patients with atrial fibrillation; Backend server, used for: S1. Obtain atrial fibrillation symptom data of patients with atrial fibrillation; S2, importing the atrial fibrillation symptom data into a preset atrial fibrillation diagnosis and treatment prediction model, allowing the atrial fibrillation diagnosis and treatment prediction model to identify atrial fibrillation symptom characteristics in the atrial fibrillation symptom data, and recommending a warfarin prescription strategy that matches the atrial fibrillation symptom characteristics; S3. Generate corresponding atrial fibrillation diagnosis and treatment orders according to the warfarin doctor's order strategy and bind them to the doctor's ID of the atrial fibrillation patient; S4, sending the atrial fibrillation diagnosis and treatment instructions to the medical terminal, and notifying the medical staff to execute the atrial fibrillation diagnosis and treatment instructions on the atrial fibrillation patient; The medical end is communicatively connected with the background server.

5. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the intelligent management method for atrial fibrillation patients as described in any one of claims 1-3 when executing the executable instructions.

Images