Postoperative anticoagulant drug follow-up management method, device, equipment and medium

By collecting and extracting multi-dimensional data of postoperative patients and generating postoperative anticoagulant follow-up reports, the problems of timely follow-up of postoperative anticoagulant drug management and drug adverse events were solved, and efficient and accurate drugs were achieved manage.

CN118942619APending Publication Date: 2024-11-12THE SIXTH AFFILIATED HOSPITAL OF SUN YAT SEN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411114851.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The use of anticoagulants after surgery cannot be followed up in time, resulting in an increase in drug adverse events and complex drug management, requiring efficient and accurate personalized management.

Method used

By collecting the physiological, situational and clinical data of the target user, using convolutional neural networks and long-term memory networks for feature extraction and fusion, input into the anticoagulant label prediction model, and generate a postoperative anticoagulant follow-up report, including drug effectiveness Sex simulation, adverse reaction prediction and drug recommendation.

Benefits of technology

It has achieved efficient and accurate follow-up management of postoperative anticoagulant drugs, reduced the risk of venous thrombosis and major bleeding, and improved the safety and effectiveness of drug use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942619A_ABST
    Figure CN118942619A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of artificial intelligence, and provides a postoperative anticoagulant drug follow-up management method, device and equipment and a medium, which can screen acquired target physiological data, target situation data and target clinical data of a target user to improve data quality and further improve the efficiency and accuracy of subsequent data processing. Time sequence segmentation is performed on the physiological data and the situation data by using a time point segmentation strategy to obtain continuous data with time sequence, so that the accuracy of data processing is further improved; feature extraction and fusion are carried out by utilizing a convolutional neural network model and a long-short-term memory network model, fusion features are input into an anticoagulant drug label prediction model, a postoperative anticoagulant drug follow-up report is generated, and then efficient and accurate prediction is carried out on an anticoagulant drug label by integrating features of multiple dimensions and an artificial intelligence means. And the generated postoperative anticoagulant drug follow-up report is more comprehensive and reasonable, so that effective follow-up management of the postoperative anticoagulant drug is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for follow-up management of postoperative anticoagulant drugs. Background Art

[0002] Venous thromboembolism (VTE) refers to a series of pathological and physiological changes caused by abnormal blood coagulation in the veins, which completely or incompletely blocks the veins and causes abnormal blood return. Depending on the location of the embolism, VTE can be divided into deep vein thrombosis (DVT) and pulmonary thromboembolism (PE). VTE has become one of the major causes of death worldwide.

[0003] Anticoagulants refer to a series of drugs that are used to prevent and treat thrombotic diseases by inhibiting the activation or action of coagulation factors and blocking the coagulation cascade process. In recent years, new anticoagulants have been continuously discovered and used in clinical diagnosis and treatment. Currently, there are dozens of anticoagulant drugs on the market. However, while anticoagulants play a role in preventing and treating thromboembolic diseases, they may also cause adverse drug events in patients by disrupting the balance of coagulation and bleeding in the patient's body. For example, by inhibiting the activity of vitamin K epoxide reductase, the generation and activation of coagulation factors II, VII, IX, and X are inhibited, which plays an anticoagulant role. However, due to the narrow therapeutic window, the pharmacokinetic process is affected by many factors. The race, gender, age, genetic genomics, types of concomitant medications, and lifestyle of the drug users may affect the drug metabolism process and the efficacy and safety of the patient after taking the drug. Therefore, pharmacists are required to carry out personalized pharmaceutical monitoring and management, which not only consumes a lot of manpower costs, but also requires high professional quality of pharmacists. Otherwise, it is easy to increase the risk of VTE in patients due to the lack of professionalism of pharmacists.

[0004] Based on the above problems, it is necessary to provide an automatic, efficient and accurate method for postoperative anticoagulant follow-up management. Summary of the invention

[0005] In view of the above, it is necessary to provide a postoperative anticoagulant follow-up management method, device, equipment and medium, aiming to solve the problem of the inability to follow up on the use of anticoagulants in a timely manner and unreasonable configuration after surgery.

[0006] A postoperative anticoagulant drug follow-up management method, the postoperative anticoagulant drug follow-up management method comprising:

[0007] In response to a postoperative anticoagulant drug follow-up management instruction for a target user, collecting target physiological data, target situational data, and target clinical data of the target user;

[0008] Screening the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data;

[0009] Performing time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time series characteristics;

[0010] Using a first convolutional neural network model to extract features from the first data to obtain a first feature;

[0011] Using a long short-term memory network model to extract features from the fourth data to obtain a second feature;

[0012] Using a second convolutional neural network model to extract features from the third data to obtain a third feature;

[0013] Performing feature fusion on the first feature, the second feature and the third feature to obtain a fused feature;

[0014] The fusion features are input into an anticoagulant drug label prediction model obtained by training a network model with predictive function to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk;

[0015] A postoperative anticoagulant drug follow-up report for the target user is generated based on the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes effectiveness simulation data of the anticoagulant drug, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan.

[0016] According to a preferred embodiment of the present invention, the collecting of target physiological data, target situational data and target clinical data of the target user includes:

[0017] Collecting data and physiological signals related to physiological conditions as the target physiological data through the wearable sensors, target physiological data monitoring equipment and medical equipment of the target user; wherein the physiological signals include central physiological signals and peripheral physiological signals;

[0018] Collecting the target user's lifestyle, disease situation and activity data during hospitalization within a specified period as the target situation data; wherein the target situation data includes one or more of the following combinations: preoperative pre-rehabilitation data, smoking data, preoperative bowel preparation data, catheter management data, intraoperative body temperature data, postoperative nausea and vomiting data, multimodal analgesia data, VTE prevention data, early postoperative feeding data, early postoperative activity and physical therapy data, and behavioral data;

[0019] The data used to construct the patient's health profile is collected as the target clinical data.

[0020] According to a preferred embodiment of the present invention, the target physiological data, the target situational data and the target clinical data are screened to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data, including:

[0021] Get the quality filter constructed based on the quality metric parameters;

[0022] Using the quality filter to filter the target physiological data, the target situational data, and the target clinical data to obtain high-quality data and low-quality data;

[0023] Sending the low-quality data to a designated terminal device for marking and annotation;

[0024] Acquire data marked as available from the low-quality data as supplementary data;

[0025] The high-quality data and the supplementary data are integrated to obtain the first data, the second data, and the third data.

[0026] According to a preferred embodiment of the present invention, the use of a time point segmentation strategy to perform time series segmentation on the first data and the second data to obtain continuous and time-sequential fourth data includes:

[0027] Obtaining a start time and an end time from the time point segmentation strategy;

[0028] Obtaining a time interval from the time point segmentation strategy;

[0029] The first data and the second data are segmented with the start time as the starting point, the end time as the end point, and the time interval as the segmentation length to obtain the fourth data.

[0030] According to a preferred embodiment of the present invention, the performing feature fusion on the first feature, the second feature and the third feature to obtain the fused feature includes:

[0031] The first feature, the second feature and the third feature are input into a feature fusion model to obtain the fused feature.

[0032] According to a preferred embodiment of the present invention, before fusing the first feature, the second feature and the third feature, the method further includes:

[0033] Obtaining an initial deep neural network model; wherein the initial deep neural network model consists of an input layer, a hidden layer, and an output layer;

[0034] Acquire training samples; wherein the training samples include a first sample set constructed by extracting features from physiological data using the first convolutional neural network model, a second sample set constructed by extracting features from the physiological data and contextual data after time series segmentation using the short-term memory network model, and a third sample set constructed by extracting features from clinical data using the second convolutional neural network model;

[0035] Continuously using the first sample set, the second sample set, and the third sample set to update the network parameters of the initial deep neural network model, and obtaining the reconstruction error of the current round in each round of updating;

[0036] When it is detected that the reconstruction error is less than a preset threshold, the updating is stopped, and the currently obtained network parameters are determined as the final network parameters of the initial deep neural network model to obtain the feature fusion model.

[0037] According to a preferred embodiment of the present invention, the continuously using the first sample set, the second sample set and the third sample set to update the network parameters of the initial deep neural network model includes:

[0038] For any round of update process, obtaining any first sample in the first sample set that has not participated in the update, inputting the first sample into the initial deep neural network model to update the network parameters of the initial deep neural network model, and obtaining first network parameters and a second network layer;

[0039] Using the first network parameter as the initial parameter value of the second network layer, and inputting the second sample corresponding to the first sample in the second sample set into the second network layer to update the network parameter of the second network layer, thereby obtaining the second network parameter and the third network layer;

[0040] The second network parameters are used as the initial parameter values ​​of the third network layer, and the third sample corresponding to the first sample in the third sample set is input into the third network layer to update the network parameters of the third network layer, so as to obtain the network parameters of the initial deep neural network model after the update in the current round.

[0041] A postoperative anticoagulant drug follow-up management device, the postoperative anticoagulant drug follow-up management device comprising:

[0042] a collection unit, configured to collect target physiological data, target situational data, and target clinical data of the target user in response to a postoperative anticoagulant drug follow-up management instruction for the target user;

[0043] a screening unit, configured to screen the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data;

[0044] A segmentation unit, configured to perform time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time sequence characteristics;

[0045] An extraction unit, configured to perform feature extraction on the first data using a first convolutional neural network model to obtain a first feature;

[0046] The extraction unit is further used to extract features from the fourth data using a long short-term memory network model to obtain a second feature;

[0047] The extraction unit is further used to perform feature extraction on the third data using a second convolutional neural network model to obtain a third feature;

[0048] a fusion unit, configured to fuse the first feature, the second feature and the third feature to obtain a fused feature;

[0049] An input unit, used to input the fusion feature into an anticoagulant drug label prediction model obtained by training a network model with predictive function, to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk;

[0050] A generating unit is used to generate a postoperative anticoagulant drug follow-up report for the target user according to the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes the effectiveness simulation data of the anticoagulant drug, the adverse reaction simulation data, the drug recommendation list, the user publicity and the monitoring plan.

[0051] A computer device, comprising:

[0052] a memory storing at least one instruction; and

[0053] A processor executes the instructions stored in the memory to implement the postoperative anticoagulant drug follow-up management method.

[0054] A computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the postoperative anticoagulant drug follow-up management method.

[0055] It can be seen from the above technical solutions that the present invention can screen the collected target physiological data, target situational data and target clinical data of the target user to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data, so as to improve the data quality, thereby improving the efficiency and accuracy of subsequent data processing; the first data and the second data are segmented in time series using a time point segmentation strategy to obtain continuous and time-series fourth data, further improving the accuracy of data processing; the first convolutional neural network model is used to extract features from the first data to obtain the first feature, the long short-term memory network model is used to extract features from the fourth data to obtain the second feature, and the third data is used to extract features from the fourth data to obtain the second feature. The second convolutional neural network model extracts features from the third data to obtain a third feature, and fuses the first, second and third features to obtain a fused feature, and inputs the fused feature into an anticoagulant drug label prediction model trained based on a network model with predictive function to obtain a label prediction result, and generates a postoperative anticoagulant drug follow-up report for the target user based on the label prediction result, including anticoagulant drug effectiveness simulation data, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan, and integrates features from multiple dimensions and artificial intelligence means to perform efficient and accurate prediction of anticoagulant drug labels, so that the generated postoperative anticoagulant drug follow-up report is more comprehensive and reasonable, thereby realizing effective follow-up management of postoperative anticoagulant drugs. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of a preferred embodiment of the postoperative anticoagulant drug follow-up management method of the present invention.

[0057] Figure 2 It is a functional module diagram of a preferred embodiment of the postoperative anticoagulant drug follow-up management device of the present invention.

[0058] Figure 3 It is a structural schematic diagram of a computer device of a preferred embodiment of the present invention for implementing a postoperative anticoagulant drug follow-up management method. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] like Figure 1 FIG. 1 is a flow chart of a preferred embodiment of the postoperative anticoagulant follow-up management method of the present invention. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

[0061] The postoperative anticoagulant drug follow-up management method is applied to one or more computer devices, which are devices that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and their hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0062] The computer device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0063] The computer device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0064] The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0065] Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0066] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0067] The network where the computer device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0068] The nursing staff, clinical staff, and health professionals mentioned in this technical plan refer to professionals whose current positions are in health technical work among all employees paid by health institutions, including Chinese medicine practitioners, Western medicine practitioners, senior doctors of integrated Chinese and Western medicine, nurses, Chinese medicine pharmacists, Western pharmacists, laboratory technicians, other technicians, Chinese medicine practitioners, Western medicine practitioners, nurses, midwives, Chinese medicine pharmacists, Western pharmacists, laboratory technicians, other technicians, other Chinese medicine practitioners, nurses, Chinese medicine pharmacists, Western pharmacists, laboratory technicians, other technicians, other Chinese medicine practitioners, nurses, Chinese medicine pharmacists, Western pharmacists, laboratory technicians, other primary health technical personnel.

[0069] S10, in response to a postoperative anticoagulant drug follow-up management instruction for a target user, collecting target physiological data, target situational data, and target clinical data of the target user.

[0070] In this embodiment, the postoperative anticoagulant drug follow-up management instruction can be automatically triggered after the surgical plan of the target user is detected, or it can be automatically triggered by relevant medical staff according to actual needs, which is not limited by the present invention.

[0071] In this embodiment, the collecting of target physiological data, target situational data and target clinical data of the target user includes:

[0072] Collecting data and physiological signals related to physiological conditions as the target physiological data through the wearable sensors, target physiological data monitoring equipment and medical equipment of the target user; wherein the physiological signals include central physiological signals and peripheral physiological signals;

[0073] Collecting the target user's lifestyle, disease situation and activity data during hospitalization within a specified period as the target situation data; wherein the target situation data includes one or more of the following combinations: preoperative pre-rehabilitation data, smoking data, preoperative bowel preparation data, catheter management data, intraoperative body temperature data, postoperative nausea and vomiting data, multimodal analgesia data, VTE (Venous Thrombembolism) prevention data, early postoperative feeding data, early postoperative activity and physical therapy data, and behavioral data;

[0074] The data used to construct the patient's health profile is collected as the target clinical data.

[0075] The target physiological data may include, but is not limited to, a combination of one or more of the following data: heart rate, respiratory rate, body temperature, and other information related to physiological conditions. Specifically, data such as heart rate, respiratory rate, body temperature, ECG (electrocardiogram), PPG (Post-Prandial Glycaemia), heart sounds, and blood oxygen saturation can be input through implanted devices, manually input, or continuously recorded through smart portable devices (such as smart phones, etc.). In addition, the target physiological data may also include data recorded occasionally, such as weight and blood pressure measured at irregular intervals.

[0076] The target physiological data includes not only data related to physiological conditions, but also physiological parameters such as central physiological signals and peripheral physiological signals. The central physiological signals may include: electroencephalographic signals, magnetic brain signals, functional magnetic resonance imaging, etc.; the peripheral physiological signals may include: electromyographic signals, electrocardiographic signals, electrooculographic signals, galvanic skin response, respiratory signals, skin temperature signals, volume pulse waves, gastric electrical signals, blood pressure, heart sound signals, blood flow, oxygen partial pressure and carbon dioxide partial pressure, etc.

[0077] The target physiological data can also be collected in combination with wearable sensors, target physiological data monitoring devices and medical devices and / or environmental sensors, such as temperature sensors, altitude sensors, air quality sensors, and accelerometers. These sensors can be embedded in the living environment of the target user or integrated into portable devices such as smart phones and tablet computers.

[0078] The target context data may include information about the patient's actions, positions, activities, attributes and / or other similar situations during the detection period. These data may reflect the patient's lifestyle, disease situation, and especially the activities during hospitalization. In the ERAS treatment process, changes in context data are crucial to improving treatment outcomes.

[0079] The target situational data includes one or more of the following combinations: preoperative pre-rehabilitation data, smoking data, preoperative bowel preparation data, catheter management data, intraoperative body temperature data, postoperative nausea and vomiting data, multimodal analgesia data, VTE prevention data, early postoperative feeding data, early postoperative activity and physical therapy data, and behavioral data.

[0080] The preoperative rehabilitation data includes preoperative exercise, which is an important part of preoperative education. It is through preoperative rehabilitation exercise that the patient's body functions are regulated, the patient's physiological functions are enhanced, and the patient can smoothly cope with the strong stress of surgery, which is conducive to postoperative rehabilitation. The medical field has not yet given specific suggestions on the time, intensity and structure of preoperative exercise and the choice of patient exercise type, but generally it can include climbing stairs, deep breathing, walking machine (appropriately increasing the speed within an acceptable range), etc.

[0081] The smoking data: Smoking also has an important impact on patients' postoperative recovery and drug treatment methods. It is one of the high-risk factors for postoperative complications and readmission. It is generally believed that reducing smoking before surgery can reduce postoperative complications and improve the quality of patient recovery.

[0082] The preoperative intestinal preparation data: The general postoperative rehabilitation process is to fast for 12 hours and 6 hours before surgery, in order to reduce the risk of reflux aspiration during anesthesia induction. However, long-term fasting and abstinence on the night before surgery and the day of surgery will cause severe discomfort to patients. Hunger and thirst not only increase the secretion of insulin antagonists such as glucocorticoids and catecholamines, but may also aggravate the patient's postoperative insulin resistance. In the case of normal gastrointestinal function and no obstruction, solid food can be emptied after 6 hours, and liquid food can be emptied after 2 hours. Therefore, some medical guidelines recommend that patients take an appropriate amount of water 2 hours before surgery, stop taking solid food 6 hours before surgery, and still eat normally on the night before surgery. In large abdominal surgeries, it is recommended to take liquid carbohydrates before surgery so that the body's preoperative carbohydrate level reaches the metabolic state after eating, so as to reduce surgery-related insulin resistance and reduce the risk of related complications, and improve patient comfort, such as taking 200-400 ml of 10% glucose orally 2 hours before surgery. However, different types of liquid carbohydrates have different effects on gastric emptying, and there may be other complex beverages that are more suitable for use before surgery. For example, drinking 250-500 ml of soy milk on the morning of surgery can not only properly supplement carbohydrates, but also consume much less cholesterol and fat than milk.

[0083] Catheter management data: In traditional surgical models, urinary output is measured by indwelling urinary catheters during and after surgery to assess the amount of fluid replacement during and after surgery and to prevent postoperative urinary difficulties caused by anesthesia. However, the indwelling time of the urinary catheter has a variety of effects on the patient's postoperative recovery. For example, the urinary catheter will significantly affect the patient's postoperative comfort and easily cause restlessness during the anesthesia recovery period; or it may cause inconvenience to the patient's early postoperative bed activities, increase the risk of urinary tract infection, or cause urinary retention.

[0084] Intraoperative temperature data: When the body temperature drops during anesthesia and surgery, the patient's body temperature is prone to large fluctuations due to long-term exposure to the low temperature in the operating room, the inhibition of temperature regulation caused by anesthesia, a large amount of low-temperature fluid replacement, and evaporative losses caused by exposure of the surgical area to dry air. Low temperature may impair the body's normal coagulation function, increase the risk of bleeding, affect the body's white blood cell function, and increase the risk of cardiovascular complications. In addition, intraoperative low temperature may bring about changes in pharmacokinetic ability and affect postoperative anesthesia recovery.

[0085] Postoperative nausea and vomiting data: Postoperative nausea and vomiting is one of the most common postoperative complications, which will greatly affect the early postoperative recovery and slow down the patient's postoperative rehabilitation progress. Continuous nausea and vomiting will lead to more serious consequences, such as water and electrolyte disorders, aspiration pneumonia, wound dehiscence, etc. A variety of postoperative medications are related to nausea and vomiting, including opioid analgesics used during or after surgery, whether sufficient carbohydrates are supplemented before surgery to avoid fasting, the appropriate amount of fluid replacement, the use of volatile anesthetics, and whether COX-2 inhibitors or other non-steroidal anti-inflammatory drugs are used in combination to replace opioid receptor drugs.

[0086] Multimodal analgesia data: refers to the use of non-opioid drugs to replace part of the opioid dosage to achieve the combined use of multiple analgesics to manage the patient's pain treatment plan. Preoperative education also plays an important role. Patients can reduce pain by understanding their condition and making psychological predictions about postoperative pain. Compared with traditional analgesia models, large-scale and long-term use of opioids can easily cause adverse reactions, such as nausea and vomiting, slow recovery of gastrointestinal function, and affecting postoperative recovery of eating and activities. Pain is the most basic evaluation standard for patient satisfaction and is related to the patient's compliance with the treatment plan. It is worth noting that pain is a subjective feeling of the patient. There is currently no way to objectively evaluate pain, but pain can still be estimated through the patient's daily life performance.

[0087] Data on prevention of VTE: Age, malignant tumors, and preoperative induction chemoradiotherapy can increase the risk of venous thromboembolism. VTE prevention measures include the use of anti-thrombotic elastic stockings, intermittent air pressure devices, etc., and continue until the patient resumes independent activities. VTE risk assessment should be actively performed on patients before and after surgery, and education on thrombosis prevention should be strengthened for patients, and patients should be encouraged to get out of bed and move early after surgery. For patients with a lower risk of bleeding, low molecular weight heparin should be routinely used for VTE prevention after surgery. The use of low molecular weight heparin is often clinically related to the amount of pleural drainage and the properties of the drainage fluid. Excessive use of anticoagulants may cause excessive drainage or brighter color of the pleural fluid, thereby affecting the removal time of the chest drainage tube and increasing the patient's discomfort and anxiety. Near-infrared light source and photosensitive detector: In a non-contact way, near-infrared light can penetrate human tissue and be absorbed by thrombus. The reflected light generated can be detected by the module and relevant hemodynamic parameters can be obtained; temperature sensor: used to measure the temperature change around the thrombus, because the presence of thrombus will change the blood flow state of surrounding tissue, thus affecting the temperature distribution, so this sensor can provide additional information for the detection of thrombus. When it comes to thrombus, thrombus will block blood flow, thereby reducing blood supply to the area. This may cause the temperature of tissue to drop, because blood not only provides oxygen and nutrients, but also helps to disperse body heat. Therefore, if there is a thrombus, a certain area of ​​the patient's body surface (such as the area near the thrombus) will be lower than other areas. This temperature difference can be directly read by the temperature sensor; pressure sensor: due to the thrombus blocking the deep vein, blood accumulates in the vein, causing local swelling and induration, which may make the touched skin area harder than the surrounding tissue. By measuring these characteristics, the presence of thrombus can be further determined, and it can also be evaluated by comparing the data of suspicious areas and normal areas.

[0088] Data on early postoperative feeding: In the traditional surgical model, it is believed that surgical patients should drink water 6 hours after surgery and eat after anal gas is discharged. In fact, most patients can tolerate eating before anal gas is discharged. On the one hand, long-term fasting after surgery brings extremely uncomfortable experience to patients, which may reduce compliance. On the other hand, eating may inhibit gastrointestinal motility. Studies have shown that early postoperative feeding is beneficial to the recovery of gastrointestinal function, protects intestinal mucosa, reduces the risk of infection, shortens hospital stay and reduces hospitalization costs, and it is safe and feasible to drink water within 6 hours after general anesthesia. Therefore, in the ERAS (Enhanced recovery after surgery) pathway, after the patient wakes up from anesthesia more thoroughly, he can drink a small amount of water within 6 hours after surgery, and can resume normal diet according to the patient's condition on the first morning after surgery. For complex cases or patients after major surgery, a step-by-step approach can be adopted to gradually adjust the diet to avoid situations that the patient cannot tolerate.

[0089] Early postoperative mobilization and physical therapy data: Early postoperative ambulation is one of the most important links in the ERAS pathway, which can directly and effectively reduce complications related to immobilization and shorten hospital stay. In traditional concepts, due to anesthesia and surgical trauma, the first time a patient gets out of bed after surgery is usually 24 hours after surgery. Bed rest and immobilization not only reduce physical adaptability and weaken muscle strength, but also increase the incidence of atelectasis and pneumonia, and increase the risk of VTE and prolong hospital stay. Therefore, early ambulation of patients is of great significance to the implementation of ERAS, but due to large individual differences and different surgeries, there is currently no uniform standard for the specific time to get out of bed. In clinical practice, the time for getting out of bed should be formulated according to the specific situation of the patient, and patients should be encouraged to get out of bed as soon as possible while ensuring safety. The main factors affecting patients' early ambulation after surgery include orthostatic intolerance, limited activity (catheter, chest drainage tube, continuous fluid infusion), pain and poor compliance. Different from the traditional model and concept, each link in the ERAS pathway, such as avoiding fasting and drinking, early postoperative feeding, prevention and treatment of postoperative nausea and vomiting, unconventional indwelling catheterization, active strategy for chest tube removal, use of digital water seal bottle, restrictive fluid infusion, multimodal analgesia, etc., can effectively promote early ambulation after surgery. Therefore, education should be strengthened for patients and their families, and the importance of early activity should be repeatedly emphasized to change patients' inherent ideas and encourage them to cooperate actively.

[0090] Behavioral data: can be obtained from different sources, such as phone call records, emails, social media information interactions, and physical activities actively reported by patients. In addition, information related to patient behavior can be obtained by monitoring web browsing history, business activities, clickstream data, etc. A comprehensive understanding of the patient's behavioral data, including social interactions, daily activities, and Internet usage habits, can help to better understand the patient's lifestyle and behavior patterns. This in-depth understanding can be used to adjust personalized treatment plans, thereby improving treatment effectiveness.

[0091] Among them, the target clinical data may include administrative and demographic information, diagnosis, treatment, prescription drugs, over-the-counter drugs, laboratory test results, etc. These data can be collected through a variety of channels, including electronic medical record systems, laboratory information management systems, clinical databases, etc. These clinical data are clinical notes written by health professionals, digital nurse records, or data reported by subjects and / or health professionals through follow-up, questionnaires, general surveys, health event reports, clinical event reports, etc. These data provide detailed information about the patient's health status and help to more comprehensively evaluate the patient's condition and treatment effect. Comprehensive analysis of this information can provide the medical team with a comprehensive patient health portrait, so as to better formulate personalized treatment plans and health management strategies.

[0092] Through the above embodiments, multi-dimensional data of the target physiological data, target situational data and target clinical data of the target user can be collected to improve the accuracy of subsequent label prediction.

[0093] In this embodiment, the collected data can be uploaded through a designated data receiving interface, such as a distributed interface. In this way, data can be received directly from the patient (i.e., the target user) monitoring device, or physiological data from the device can be received through other components or computer devices, and these data can be received and / or aggregated in an indirect manner. For example: the target user's physiological biological signals and contextual data from wearable biosensors, medical devices, or implants can be continuously synchronized. Mobile sensors and smartphone-based mobile applications can be used to obtain data actively reported by the target user and other contextual data.

[0094] The data receiving interface can be provided by software running on a portable or local terminal device, including wearable devices, smart watches, smart phones, tablet computers, laptops, and personal desktops. These devices can establish a connection through a device to download data. The connection can be completed through a local area network or the Internet. Various devices for data collection can be connected to a local network (such as a hospital network), and the data receiving interface can be executed on a computer that is part of the local network, or a connection is established with the computer through the data receiving interface, and the data is forwarded to the data receiving interface. Through these connection methods, it is ensured that the collected data can be efficiently received.

[0095] S11, screening the target physiological data, the target situational data and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data.

[0096] In this embodiment, the target physiological data, the target situational data, and the target clinical data are screened to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data, including:

[0097] Get the quality filter constructed based on the quality metric parameters;

[0098] Using the quality filter to filter the target physiological data, the target situational data, and the target clinical data to obtain high-quality data and low-quality data;

[0099] Sending the low-quality data to a designated terminal device for marking and annotation;

[0100] Acquire data marked as available from the low-quality data as supplementary data;

[0101] The high-quality data and the supplementary data are integrated to obtain the first data, the second data, and the third data.

[0102] The metric parameters may include, but are not limited to: variance estimation, signal-to-noise ratio estimation, and other quality metric parameters based on morphology, statistics, and image features.

[0103] Among them, the designated terminal device can be a terminal device of a nursing team member, or a terminal device with a machine learning classifier (the terminal device with a machine learning classifier is used to further detect the quality of the data) to further confirm the data quality or supplement and improve the data. For example: when poor quality data is detected, the poor quality data can be sent to the terminal of the nursing team and an alarm can be issued. After receiving the alarm, the nursing staff will carefully review the poor quality data and mark or annotate it. These markings may include discarding the data or sending it to a designated analysis module of a terminal device with a machine learning classifier to activate the learning function. The activation of this learning function enables the machine learning classifier to continuously enhance its performance over time. This organic process not only helps to improve the system's judgment of data quality in real time, but also improves the reliability of subsequent analysis.

[0104] Through the above embodiments, poor quality data can be excluded, effectively improving data quality and making it more suitable for subsequent data analysis. In addition, the poor quality data is handed over to the designated terminal for marking and annotation to further optimize the data and avoid the accidental deletion of valid data.

[0105] S12, performing time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time series.

[0106] In this embodiment, the time point segmentation strategy is used to perform time series segmentation on the first data and the second data to obtain continuous and time-sequential fourth data, which includes:

[0107] Obtaining a start time and an end time from the time point segmentation strategy;

[0108] Obtaining a time interval from the time point segmentation strategy;

[0109] The first data and the second data are segmented with the start time as the starting point, the end time as the end point, and the time interval as the segmentation length to obtain the fourth data.

[0110] For example, taking the time of surgery as an example, the patient's surgery time is used as the time point for data segmentation, and the patient's data is segmented at a fixed time length (such as 24 hours, 48 ​​hours, 72 hours before surgery, and 24 hours, 48 ​​hours, 72 hours after surgery, etc.). In the field of accelerated recovery surgery, the patient's physiological and situational data may change significantly before and after surgery, and these data are closely related to the patient's recovery speed. Therefore, careful analysis of these data is of great significance for the patient's drug treatment management. Taking the time for patients to get out of bed after surgery as an example, this may be related to the patient's use of analgesics and anticoagulants. In the concept of accelerated recovery surgery, patients are allowed to get out of bed as soon as possible after surgery within the patient's tolerance range to conduct rehabilitation training and reduce bed rest time, which can significantly reduce the patient's hospitalization time and accelerate their postoperative recovery time. After data segmentation, the data of each time period can also be marked with the start and end time, situational information, and the corresponding statistics of physiological data, which include but are not limited to the mean, median, variance, etc. of physiological biological signals. By using segmentation algorithms, the noise within the segmented segments can be significantly reduced, making the downstream analysis process more efficient, helping to obtain more accurate and substantial data, and providing a solid data foundation for subsequent analysis.

[0111] S13: Use a first convolutional neural network model to perform feature extraction on the first data to obtain a first feature.

[0112] S14, using a long short-term memory network model to extract features from the fourth data to obtain a second feature.

[0113] S15, using the second convolutional neural network model to extract features of the third data to obtain a third feature.

[0114] Of course, in other embodiments, the feature extraction method may also include: time domain feature extraction, frequency domain feature extraction method. Specifically, the time-frequency feature extraction method mainly includes short time Fourier transform (STFT), wavelet packet transform (WPT), empirical mode decomposition (EMD), dual tree complex wavelet packet transform (DTCWPT), sequential forward selection (SFS), sequential backward selection (SBS), bidirectional search (SDS), plus L minus-R selection algorithm (LRS), sequential floating selection algorithm (SFFS / SFBS), etc.

[0115] S16, performing feature fusion on the first feature, the second feature and the third feature to obtain a fused feature.

[0116] In this embodiment, the performing feature fusion on the first feature, the second feature and the third feature to obtain the fused feature includes:

[0117] The first feature, the second feature and the third feature are input into a feature fusion model to obtain the fused feature.

[0118] Through the above embodiments, it is possible to achieve the fusion of multi-dimensional features to facilitate subsequent analysis.

[0119] In this embodiment, before the feature fusion is performed on the first feature, the second feature and the third feature, the method further includes:

[0120] Obtaining an initial deep neural network model; wherein the initial deep neural network model consists of an input layer, a hidden layer, and an output layer;

[0121] Acquire training samples; wherein the training samples include a first sample set constructed by extracting features from physiological data using the first convolutional neural network model, a second sample set constructed by extracting features from the physiological data and contextual data after time series segmentation using the short-term memory network model, and a third sample set constructed by extracting features from clinical data using the second convolutional neural network model;

[0122] Continuously using the first sample set, the second sample set, and the third sample set to update the network parameters of the initial deep neural network model, and obtaining the reconstruction error of the current round in each round of updating;

[0123] When it is detected that the reconstruction error is less than a preset threshold, the updating is stopped, and the currently obtained network parameters are determined as the final network parameters of the initial deep neural network model to obtain the feature fusion model.

[0124] The preset threshold value can be configured according to actual usage requirements.

[0125] In this embodiment, the continuously using the first sample set, the second sample set, and the third sample set to update the network parameters of the initial deep neural network model includes:

[0126] For any round of update process, obtaining any first sample in the first sample set that has not participated in the update, inputting the first sample into the initial deep neural network model to update the network parameters of the initial deep neural network model, and obtaining first network parameters and a second network layer;

[0127] Using the first network parameter as the initial parameter value of the second network layer, and inputting the second sample corresponding to the first sample in the second sample set into the second network layer to update the network parameter of the second network layer, thereby obtaining the second network parameter and the third network layer;

[0128] The second network parameters are used as the initial parameter values ​​of the third network layer, and the third sample corresponding to the first sample in the third sample set is input into the third network layer to update the network parameters of the third network layer, so as to obtain the network parameters of the initial deep neural network model after the update in the current round.

[0129] Through the above embodiments, it is possible to achieve alternate optimization of network parameters through continuous iteration and updating, and finally obtain the feature fusion model with feature fusion function.

[0130] S17, inputting the fusion features into an anticoagulant drug label prediction model obtained by training a network model with predictive function to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk.

[0131] The anticoagulant drug label prediction model can be obtained by training based on a neural network with predictive function.

[0132] Of course, the anticoagulant drug label prediction model can also be other machine learning models, such as: logistic regression (LR), multi-layer perceptron (MLP), k-Nearest Neighbor (KNN), random forest (RF), XGB (Extreme Gradient Boosting), principal component analysis (PCA) + support vector machine (SVM), stacked autoencoder (SAE) + long short-term memory network (LSTM), and maximum relevance and minimum redundancy (mRMR) + extreme learning machine (ELM), etc.

[0133] The label prediction result may include the risk level of each sub-label. For example, the venous thrombosis risk index may include high risk level 1, high risk level 2, high risk level 3, or more risk assessment levels.

[0134] S18, generating a postoperative anticoagulant drug follow-up report for the target user based on the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes the effectiveness simulation data of the anticoagulant drug, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan.

[0135] Specifically, predictions can be made based on the venous thrombosis risk index and the major bleeding risk index to generate simulation data on the effectiveness of the anticoagulant drug; analysis can be made based on the clinically relevant non-major bleeding risk index and the drug-related problem risk to generate the adverse reaction simulation data; multiple predicted sub-tags such as the venous thrombosis risk index, the major bleeding risk index, the clinically relevant non-major bleeding risk index, and the drug-related problem risk can be integrated and matched with the drugs in the designated drug database to obtain the drug recommendation list; a comprehensive analysis can be made based on the drug recommendation list and multiple predicted sub-tags to obtain the user promotion and monitoring plan.

[0136] Among them, the user publicity and monitoring plan can be presented in the form of educational materials, monitoring plan tables, etc., to inform patients of the significance of various clinical intervention measures in a way that patients can accept and understand, and to give full play to their own initiative to obtain the best surgical outcome and rehabilitation effect. After the educational materials are generated, medical staff can also manually annotate the educational materials in order to achieve an effect that patients can understand. The generated educational materials can also have multiple levels, including patient levels specifically for sending to patients, with low professional and technical requirements for interpretation, and clinical levels specifically for medical staff to adjust patient treatment plans, with high professional and technical requirements for interpretation.

[0137] In this embodiment, the predicted labels can assist in the hierarchical management of the risk of MRP (Medication Related Problem) so as to rationally allocate the human resources of clinical nursing staff, especially the resources of clinical pharmacists. In addition, it can also achieve the effect of dynamically updating the MRP. Since the mining of the patient's MRP can rely on the real-time monitoring equipment already on the patient (such as electrocardiograms and blood gas analysis used by hospitalized patients, smart watches and smart phones used by patients in the transition period from hospitalization to outpatient clinics, etc.), it can greatly save the time and labor costs of clinical nursing staff, and at the same time expand clinical benefits.

[0138] In this embodiment, for postoperative patients in the ERAS management mode, effective follow-up management of postoperative anticoagulant drugs can be carried out by analyzing multi-dimensional information such as situational data, which can greatly reduce the risk of VTE in patients, while reducing the demand for medical staff and compliance with professionalism.

[0139] It can be seen from the above technical solutions that the present invention can screen the collected target physiological data, target situational data and target clinical data of the target user to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data, so as to improve the data quality, thereby improving the efficiency and accuracy of subsequent data processing; the first data and the second data are segmented in time series using a time point segmentation strategy to obtain continuous and time-series fourth data, further improving the accuracy of data processing; the first convolutional neural network model is used to extract features from the first data to obtain the first feature, the long short-term memory network model is used to extract features from the fourth data to obtain the second feature, and the third data is used to extract features from the fourth data to obtain the second feature. The second convolutional neural network model extracts features from the third data to obtain a third feature, and fuses the first, second and third features to obtain a fused feature, and inputs the fused feature into an anticoagulant drug label prediction model trained based on a network model with predictive function to obtain a label prediction result, and generates a postoperative anticoagulant drug follow-up report for the target user based on the label prediction result, including anticoagulant drug effectiveness simulation data, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan, and integrates features from multiple dimensions and artificial intelligence means to perform efficient and accurate prediction of anticoagulant drug labels, so that the generated postoperative anticoagulant drug follow-up report is more comprehensive and reasonable, thereby realizing effective follow-up management of postoperative anticoagulant drugs.

[0140] like Figure 2 The figure shows a functional module diagram of a preferred embodiment of the postoperative anticoagulant drug follow-up management device of the present invention. The postoperative anticoagulant drug follow-up management device 11 includes a collection unit 110, a screening unit 111, a segmentation unit 112, an extraction unit 113, a fusion unit 114, an input unit 115, and a generation unit 116. The module / unit referred to in the present invention refers to a series of computer program segments that can be executed by a processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0141] The acquisition unit 110 is used to collect target physiological data, target situational data and target clinical data of the target user in response to a postoperative anticoagulant drug follow-up management instruction for the target user;

[0142] The screening unit 111 is used to screen the target physiological data, the target situational data and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data;

[0143] The segmentation unit 112 is used to perform time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time sequence characteristics;

[0144] The extraction unit 113 is used to extract features from the first data using a first convolutional neural network model to obtain a first feature;

[0145] The extraction unit 113 is further used to extract features from the fourth data using a long short-term memory network model to obtain a second feature;

[0146] The extraction unit 113 is further used to extract features from the third data using a second convolutional neural network model to obtain a third feature;

[0147] The fusion unit 114 is used to fuse the first feature, the second feature and the third feature to obtain a fused feature;

[0148] The input unit 115 is used to input the fusion feature into the anticoagulant drug label prediction model obtained by training based on the network model with predictive function to obtain the label prediction result; wherein the label prediction result includes the risk index of venous thrombosis, the risk index of major bleeding, the risk index of clinically relevant non-major bleeding, and the risk of drug-related problems;

[0149] The generating unit 116 is used to generate a postoperative anticoagulant drug follow-up report for the target user according to the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes the effectiveness simulation data of the anticoagulant drug, the adverse reaction simulation data, the drug recommendation list, the user publicity and the monitoring plan.

[0150] It can be seen from the above technical solutions that the present invention can screen the collected target physiological data, target situational data and target clinical data of the target user to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data, so as to improve the data quality, thereby improving the efficiency and accuracy of subsequent data processing; the first data and the second data are segmented in time series using a time point segmentation strategy to obtain continuous and time-series fourth data, further improving the accuracy of data processing; the first convolutional neural network model is used to extract features from the first data to obtain the first feature, the long short-term memory network model is used to extract features from the fourth data to obtain the second feature, and the third data is used to extract features from the fourth data to obtain the second feature. The second convolutional neural network model extracts features from the third data to obtain a third feature, and fuses the first, second and third features to obtain a fused feature, and inputs the fused feature into an anticoagulant drug label prediction model trained based on a network model with predictive function to obtain a label prediction result, and generates a postoperative anticoagulant drug follow-up report for the target user based on the label prediction result, including anticoagulant drug effectiveness simulation data, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan, and integrates features from multiple dimensions and artificial intelligence means to perform efficient and accurate prediction of anticoagulant drug labels, so that the generated postoperative anticoagulant drug follow-up report is more comprehensive and reasonable, thereby realizing effective follow-up management of postoperative anticoagulant drugs.

[0151] like Figure 3 , which is a schematic diagram of the structure of a computer device of a preferred embodiment of the present invention for implementing a method for follow-up management of postoperative anticoagulant drugs.

[0152] The computer device 1 may include a memory 12 , a processor 13 , and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13 , such as a postoperative anticoagulant drug follow-up management program.

[0153] Those skilled in the art will appreciate that the schematic diagram is merely an example of the computer device 1 and does not constitute a limitation on the computer device 1. The computer device 1 may be a bus-type structure or a star-type structure. The computer device 1 may also include more or less other hardware or software than shown in the diagram, or a different arrangement of components. For example, the computer device 1 may also include input and output devices, network access devices, etc.

[0154] It should be noted that the computer device 1 is only an example, and other existing or future electronic products that are suitable for the present invention should also be included in the protection scope of the present invention and included here by reference.

[0155] The memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 12 may be an internal storage unit of the computer device 1 in some embodiments, such as a mobile hard disk of the computer device 1. The memory 12 may also be an external storage device of the computer device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 1. Further, the memory 12 may also include both an internal storage unit of the computer device 1 and an external storage device. The memory 12 may be used not only to store application software and various types of data installed in the computer device 1, such as the code of the postoperative anticoagulant drug follow-up management program, but also to temporarily store data that has been output or is to be output.

[0156] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the computer device 1, and uses various interfaces and lines to connect various components of the entire computer device 1, and executes or executes programs or modules stored in the memory 12 (for example, executing a postoperative anticoagulant drug follow-up management program, etc.), and calls data stored in the memory 12 to execute various functions of the computer device 1 and process data.

[0157] The processor 13 executes the operating system of the computer device 1 and various installed application programs. The processor 13 executes the application programs to implement the steps in each of the above-mentioned postoperative anticoagulant drug follow-up management method embodiments, for example Figure 1 Steps shown.

[0158] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a collection unit 110, a screening unit 111, a segmentation unit 112, an extraction unit 113, a fusion unit 114, an input unit 115, and a generation unit 116.

[0159] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute the part of the postoperative anticoagulant drug follow-up management method described in each embodiment of the present invention.

[0160] If the module / unit integrated in the computer device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware devices through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0161] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0162] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0163] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0164] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by only one straight line, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 12 and at least one processor 13, etc.

[0165] Although not shown, the computer device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 13 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The computer device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0166] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the computer device 1 and other computer devices.

[0167] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the computer device 1 and to display a visual user interface.

[0168] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0169] Figure 3 Only the computer device 1 having components 12-13 is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0170] Combination Figure 1 The memory 12 in the computer device 1 stores a plurality of instructions to implement a postoperative anticoagulant drug follow-up management method, and the processor 13 can execute the plurality of instructions to implement:

[0171] In response to a postoperative anticoagulant drug follow-up management instruction for a target user, collecting target physiological data, target situational data, and target clinical data of the target user;

[0172] Screening the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data;

[0173] Performing time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time series characteristics;

[0174] Using a first convolutional neural network model to extract features from the first data to obtain a first feature;

[0175] Using a long short-term memory network model to extract features from the fourth data to obtain a second feature;

[0176] Using a second convolutional neural network model to extract features from the third data to obtain a third feature;

[0177] Performing feature fusion on the first feature, the second feature and the third feature to obtain a fused feature;

[0178] The fusion features are input into an anticoagulant drug label prediction model obtained by training a network model with predictive function to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk;

[0179] A postoperative anticoagulant drug follow-up report for the target user is generated based on the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes effectiveness simulation data of the anticoagulant drug, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan.

[0180] Specifically, the specific implementation method of the processor 13 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0181] It should be noted that the data involved in this case were all obtained legally.

[0182] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0183] The present invention can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present invention can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0184] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0186] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0187] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0188] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the present invention can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0189] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A postoperative anticoagulant drug follow-up management method, characterized in that: The postoperative anticoagulant drug follow-up management method includes: In response to a postoperative anticoagulant drug follow-up management instruction for a target user, collecting target physiological data, target situational data, and target clinical data of the target user; Screening the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data; Performing time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time series characteristics; Using a first convolutional neural network model to extract features from the first data to obtain a first feature; Using a long short-term memory network model to extract features from the fourth data to obtain a second feature; Using a second convolutional neural network model to extract features from the third data to obtain a third feature; Performing feature fusion on the first feature, the second feature and the third feature to obtain a fused feature; The fusion features are input into an anticoagulant drug label prediction model obtained by training a network model with predictive function to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk; A postoperative anticoagulant drug follow-up report for the target user is generated based on the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes effectiveness simulation data of the anticoagulant drug, adverse reaction simulation data, a drug recommendation list, user publicity and monitoring plan.

2. The postoperative anticoagulant drug follow-up management method according to claim 1, characterized in that: The collecting of target physiological data, target situational data and target clinical data of the target user includes: Collecting data and physiological signals related to physiological conditions as the target physiological data through the wearable sensors, target physiological data monitoring equipment and medical equipment of the target user; wherein the physiological signals include central physiological signals and peripheral physiological signals; Collecting the target user's lifestyle, disease situation and activity data during hospitalization within a specified period as the target situation data; wherein the target situation data includes one or more of the following combinations: preoperative pre-rehabilitation data, smoking data, preoperative bowel preparation data, catheter management data, intraoperative body temperature data, postoperative nausea and vomiting data, multimodal analgesia data, VTE prevention data, early postoperative feeding data, early postoperative activity and physical therapy data, and behavioral data; The data used to construct the patient's health profile is collected as the target clinical data.

3. The postoperative anticoagulant drug follow-up management method according to claim 1, characterized in that: The step of screening the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data includes: Get the quality filter constructed based on the quality metric parameters; Using the quality filter to filter the target physiological data, the target situational data, and the target clinical data to obtain high-quality data and low-quality data; Sending the low-quality data to a designated terminal device for marking and annotation; Acquire data marked as available from the low-quality data as supplementary data; The high-quality data and the supplementary data are integrated to obtain the first data, the second data, and the third data.

4. The postoperative anticoagulant drug follow-up management method according to claim 1, characterized in that: The method of performing time-series segmentation on the first data and the second data by using the time point segmentation strategy to obtain continuous and time-series fourth data includes: Obtaining a start time and an end time from the time point segmentation strategy; Obtaining a time interval from the time point segmentation strategy; The first data and the second data are segmented with the start time as the starting point, the end time as the end point, and the time interval as the segmentation length to obtain the fourth data.

5. The postoperative anticoagulant drug follow-up management method according to claim 1, characterized in that: The performing feature fusion on the first feature, the second feature and the third feature to obtain the fused feature comprises: The first feature, the second feature and the third feature are input into a feature fusion model to obtain the fused feature.

6. The postoperative anticoagulant drug follow-up management method according to claim 5, characterized in that: Before fusing the first feature, the second feature, and the third feature, the method further includes: Obtaining an initial deep neural network model; wherein the initial deep neural network model consists of an input layer, a hidden layer, and an output layer; Acquire training samples; wherein the training samples include a first sample set constructed by extracting features from physiological data using the first convolutional neural network model, a second sample set constructed by extracting features from the physiological data and contextual data after time series segmentation using the short-term memory network model, and a third sample set constructed by extracting features from clinical data using the second convolutional neural network model; Continuously using the first sample set, the second sample set, and the third sample set to update the network parameters of the initial deep neural network model, and obtaining the reconstruction error of the current round in each round of updating; When it is detected that the reconstruction error is less than a preset threshold, the updating is stopped, and the currently obtained network parameters are determined as the final network parameters of the initial deep neural network model to obtain the feature fusion model.

7. The postoperative anticoagulant drug follow-up management method according to claim 6, characterized in that: The method of continuously using the first sample set, the second sample set, and the third sample set to update the network parameters of the initial deep neural network model includes: For any round of update process, obtaining any first sample in the first sample set that has not participated in the update, inputting the first sample into the initial deep neural network model to update the network parameters of the initial deep neural network model, and obtaining first network parameters and a second network layer; Using the first network parameter as the initial parameter value of the second network layer, and inputting the second sample corresponding to the first sample in the second sample set into the second network layer to update the network parameter of the second network layer, thereby obtaining the second network parameter and the third network layer; The second network parameters are used as the initial parameter values ​​of the third network layer, and the third sample corresponding to the first sample in the third sample set is input into the third network layer to update the network parameters of the third network layer, so as to obtain the network parameters of the initial deep neural network model after the update in the current round.

8. A postoperative anticoagulant drug follow-up management device, characterized in that: The postoperative anticoagulant drug follow-up management device comprises: a collection unit, configured to collect target physiological data, target situational data, and target clinical data of the target user in response to a postoperative anticoagulant drug follow-up management instruction for the target user; a screening unit, configured to screen the target physiological data, the target situational data, and the target clinical data to obtain first data corresponding to the target physiological data, second data corresponding to the target situational data, and third data corresponding to the target clinical data; A segmentation unit, configured to perform time-series segmentation on the first data and the second data using a time point segmentation strategy to obtain fourth data that is continuous and has time sequence characteristics; An extraction unit, configured to perform feature extraction on the first data using a first convolutional neural network model to obtain a first feature; The extraction unit is further used to extract features from the fourth data using a long short-term memory network model to obtain a second feature; The extraction unit is further used to perform feature extraction on the third data using a second convolutional neural network model to obtain a third feature; a fusion unit, configured to fuse the first feature, the second feature and the third feature to obtain a fused feature; An input unit, used to input the fusion feature into an anticoagulant drug label prediction model obtained by training a network model with predictive function, to obtain a label prediction result; wherein the label prediction result includes a venous thrombosis risk index, a major bleeding risk index, a clinically relevant non-major bleeding risk index, and a drug-related problem risk; A generating unit is used to generate a postoperative anticoagulant drug follow-up report for the target user according to the tag prediction result; wherein the postoperative anticoagulant drug follow-up report includes the effectiveness simulation data of the anticoagulant drug, the adverse reaction simulation data, the drug recommendation list, the user publicity and the monitoring plan.

9. A computer device, characterized in that: The computer device comprises: a memory storing at least one instruction; and A processor executes instructions stored in the memory to implement the postoperative anticoagulant drug follow-up management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the postoperative anticoagulant drug follow-up management method as described in any one of claims 1 to 7.