Control method and device based on medical monitoring system

Abstract

The invention provides a control method and device based on a medical monitoring system, and the method comprises the steps: obtaining a first data set and a second data set, the first data set comprises the real-time operation data of a first medical device, and the second data set comprises the monitoring data of a second medical device; inputting the first data set and the second data set into a target anomaly detection model, and outputting an anomaly result of the target user; and generating a target adjustment scheme according to the abnormal result, and sending the target adjustment scheme to the first medical device. According to the first data set of the first medical equipment associated with the target user, the second data set of the second medical equipment and the use model, the abnormity of the user is detected, the efficiency and accuracy of judging the abnormity of the user can be improved, the adjustment scheme for the first medical equipment is generated according to the abnormity, and the user experience is improved. Medical staff can conveniently and timely process postoperative abnormal phenomena of the user, risks are reduced, and the life safety of the user is improved.

Description

Technical Field

[0001] This application relates to the technical field of medical devices, and in particular, to a control method and device based on a medical monitoring system. Background Art

[0002] Heart failure is a clinical syndrome involving severe impairment of the heart's pumping function. Left heart failure mainly affects the heart's pumping ability, leading to pulmonary congestion; right heart failure mainly affects systemic circulation return. As an effective means of treating heart failure patients, a ventricular assist device is an artificial mechanical device that partially or fully replaces the work of the ventricles.

[0003] However, after the implantation surgery of the ventricular assist device, the patient's death risk is very high and the management is complex. Medical staff still need to monitor the hemodynamic characteristics of the whole body circulation such as the heart, lungs, and kidneys in real time to timely monitor whether the patient has any changes, so as to adjust the medication and the operation of the ventricular assist device. Currently, this process highly depends on the doctor's personal experience judgment, which is inefficient and has a high risk of human error. Summary of the Invention

[0004] The embodiments of this application provide a control method and device based on a medical monitoring system, which improve the efficiency and accuracy of abnormal judgment for users, so as to facilitate medical staff to timely handle the postoperative abnormal phenomena of users, reduce risks, and increase the life safety of users.

[0005] In a first aspect, the embodiments of this application provide a control method based on a medical monitoring system. The medical monitoring system includes a first medical device, a second medical device, and a server. The method includes:

[0006] Obtain a first data set and a second data set. The first data set includes the real-time operation data of the first medical device, and the second data set includes the monitoring data of the second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user.

[0007] Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user.

[0008] Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

[0009] In a second aspect, a medical monitoring system provided by the embodiments of this application includes a first medical device, a second medical device, and a server. The server includes one or more processors, and the one or more processors are used for:

[0010] Obtain a first data set and a second data set, where the first data set includes real-time operation data of the first medical device, and the second data set includes monitoring data of the second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user;

[0011] Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user;

[0012] Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

[0013] In a third aspect, an embodiment of the present application provides a medical device, which includes a processor, a memory, a communication interface, and one or more programs. The one or more programs are stored in the memory and are configured to be executed by the processor. The programs include instructions for performing some or all of the steps described in the method according to the first aspect above.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program for electronic data exchange. The computer program enables a computer to perform some or all of the steps described in the method according to the first aspect above.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to enable a computer to perform some or all of the steps described in the method according to the first aspect of the embodiments of the present application. The computer program product can be a software installation package.

[0016] The technical solution provided by the present application obtains a first data set and a second data set. The first data set includes real-time operation data of a first medical device, and the second data set includes monitoring data of a second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user; input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user; generate a target adjustment plan according to the anomaly result and send it to the first medical device. The present application can improve the efficiency and accuracy of judging user anomalies based on the first data set of the first medical device, the second data set of the second medical device associated with the target user, and using a model to detect user anomalies. Generating an adjustment plan for the first medical device according to the anomaly can facilitate medical staff to timely handle postoperative abnormal phenomena of users, reduce risks, and increase the life safety of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0018] Figure 1 is a schematic diagram of a medical monitoring system provided by an embodiment of the present application;

[0019] Figure 2 is a schematic flowchart of a control method based on a medical monitoring system provided by an embodiment of the present application;

[0020] Figure 3 is a schematic structural diagram of a medical device provided by an embodiment of the present application. Detailed implementation manners

[0021] For better understanding of the technical solutions of the present application by those skilled in the art, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the description of the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope protected by the present application.

[0022] The terms "first", "second", etc. in the specification and claims of the present application and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, software, product or device that includes a series of steps or units is not limited to the listed steps or units, but also includes unlisted steps or units, or other steps or units inherent to these processes, methods, products or devices.

[0023] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0024] The medical devices and pumps involved in the present application may be ventricular assist devices (VADs), such as implantable ventricular assist devices, interventional ventricular assist devices, biventricular assist devices, etc.; the ventricular assist device may include at least one blood pump, where the blood pump may be a centrifugal pump, an axial flow pump, etc.

[0025] The "current" in the present application refers to the current driving the motor or the electric machine, which is associated with the power of the motor or the electric machine when the supply voltage remains unchanged. The "rotation speed" refers to the rotational speed of the motor or the electric machine, which is associated with the rotational speed of the rotor or the impeller of the ventricular assist device and can be defined as revolutions per minute. The "flow rate", "fluid flow rate", and "pumping flow rate" refer to the volume of fluid transported through the ventricular assist device per unit time, which can be estimated and measured in liters per minute.

[0026] Please refer to Figure 1 , Figure 1 which is a schematic diagram of a medical monitoring system provided by an embodiment of the present application. The medical monitoring system includes a plurality of first medical devices, a plurality of second medical devices, and a server. The server is communicatively connected to the plurality of first medical devices and the plurality of second medical devices respectively. The first medical device is used to be implanted into a user's body to provide cardiac assistance functions for the user; the second medical device is used to monitor the user's health status. The plurality of first medical devices and the plurality of second medical devices are used to simultaneously implement the treatment and monitoring of the user.

[0027] Exemplarily, the first medical device may be a medical device for assisting cardiac pumping functions such as a ventricular assist device, an extracorporeal circulation blood pump, an ECMO, a cardiac pacemaker, etc. The ventricular assist device may be an implantable ventricular assist device, an interventional pump ventricular assist device, or a biventricular assist device. The ventricular assist device can be used for the left ventricle or the right ventricle.

[0028] Exemplarily, the second medical device may include at least one of the following: a vital sign monitoring device, an imaging examination device, a laboratory testing device. For example, an electrocardiogram monitor, a comprehensive vital sign monitor, an ultrasound device, a CT device, an X-ray device, a blood analyzer, a biochemical analyzer, etc.

[0029] The server receives in real time the operation data of the first medical device, as well as the vital sign data, laboratory data, imaging results, etc. sent by the second medical device. The server processes and analyzes these data to assist medical staff in judging the hemodynamic characteristics and physiological state of the user after surgery, and can predict and judge postoperative complications and whether there are abnormal phenomena in the user currently according to the analysis results. Furthermore, when an abnormality occurs in the user, the server can avoid the deterioration and aggravation of the user's condition by adjusting the operation of the first medical device and the medication plan for the user.

[0030] In combination with the above description, the present application will be described from the perspective of method examples below.

[0031] Please refer to Figure 2 , Figure 2 , which is a schematic flowchart of a control method based on a medical monitoring system provided by an embodiment of the present application, and is applied to a medical monitoring system as shown in Figure 1 . As shown in Figure 2 , the method includes the following steps.

[0032] S210. Obtain a first data set and a second data set. The first data set includes real-time operation data of the first medical device, and the second data set includes monitoring data of the second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user.

[0033] The server can receive and store data sent by multiple first medical devices and multiple second medical devices in real time. The server can obtain the first data set of the first medical device associated with the target user and the second data set of the second medical device from the data sent by the stored multiple first medical devices and multiple second medical devices. That is to say, the real-time operation data in the first data set is the real-time operation data of the first medical device implanted into the target user, and the second data set is the monitoring data generated by monitoring the target user.

[0034] Among them, the first medical device is a ventricular assist device, and the first data set is the real-time operation data of the ventricular assist device. The real-time operation data may include at least one of the following: rotational speed, flow rate, power, pulsation index. The second medical device may include at least one of the following: a vital sign monitoring device, an imaging examination device, a laboratory testing device. For example. The second medical device includes: an electrocardiogram monitor, a comprehensive vital sign monitor, an ultrasonic device, a CT device, an X-ray device, a blood analyzer, a biochemical analyzer. The second data set is the monitoring data of the second medical device, and the monitoring data includes: heart rate, respiratory rate, blood oxygen content, aortic pressure, pulmonary artery pressure, central venous pressure, various blood indicators, ultrasonic images, pulmonary images, etc.

[0035] The server can judge the physical state of the current target user according to the second data set, so as to determine whether there are common postoperative complications in the target user under the current operating state of the ventricular assist device, and then notify the medical staff for corresponding treatment in time after predicting or judging the occurrence of common complications, improving the safety of the user.

[0036] S220. Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user.

[0037] In this application, the server can pre-store a trained target anomaly detection model, which is used to determine whether the user's vital signs are abnormal. After the server filters out the first data set and the second data set, it inputs the first data set and the second data set into the target anomaly detection model to obtain the anomaly result of the target user.

[0038] Among them, the target anomaly detection model is implemented by integrating multi-modal data (such as vital sign monitoring, laboratory test data, imaging, etc.) and combining anomaly detection algorithms. Exemplarily, the target anomaly detection model can be a deep learning model (such as a generative adversarial network GAN, a variational autoencoder VAE), which is based on a multi-modal AI architecture, integrates technologies such as machine learning and deep learning, and analyzes the anomaly phenomena corresponding to the first data set and the second data set of the user in real time.

[0039] Exemplarily, the target anomaly detection model can be an unsupervised neural network model, such as an autoencoder, which uses the autoencoder to reconstruct the normal data features, identifies the abnormal parameter data through the reconstruction error, and thus determines the anomaly phenomenon corresponding to the abnormal parameter data.

[0040] Exemplarily, the target anomaly detection model can be models such as random forest, support vector machine, isolation forest, etc., and this application does not make any limitations in this regard.

[0041] Optionally, the step of inputting the first data set and the second data set into the target anomaly detection model and outputting the anomaly result of the target user includes: extracting multiple performance parameters from the real-time operation data of the first data set, performing feature encoding transformation on the multiple performance parameters to obtain a first feature vector; classifying the second data set according to the data type to obtain a numerical data set, a text data set, and an image data set; respectively performing feature encoding transformation on the numerical data set, the text data set, and the image data set to obtain second feature vectors; splicing the first feature vector and the second feature vectors to obtain a spliced feature vector; inputting the spliced feature vector into the target anomaly detection model to obtain the anomaly result.

[0042] The first data set and the second data set contain multi-modal data, such as numerical values, text, images, etc. Different data types may require different processing methods. For example, for image data, image recognition methods, convolutional neural networks, or traditional feature extraction methods such as SIFT, HOG, etc. may be required. For text data, the bag-of-words model, TF-IDF, or word embeddings such as Word2Vec, GloVe, or BERT may be required. For numerical data, standardization, normalization, or feature extraction through statistical methods such as mean, variance, etc. may be required.

[0043] In this application, the server may first extract features from the first data set and the second data set to generate structured feature vectors. After the server extracts the features, it can uniformly normalize them and splice the processed features column by column into a vector, so that the processed features are combined into a vector, with each sample corresponding to a vector, and each element representing the value of a feature. Furthermore, it determines whether each feature value is abnormal based on the feature value, and then determines the abnormal phenomenon based on the abnormal data.

[0044] The first data set is the real-time operation data of the ventricular assist device, all of which are numerical data. The server can directly extract the numerical values of each performance parameter from the first data set, and obtain the first feature vector corresponding to the first data set after performing feature encoding transformation on each performance parameter.

[0045] The second data set includes numerical data, text data, and image data. Therefore, before extracting useful information from the second data set, the server can first classify the data in the second data set to obtain a numerical data set, a text data set, and an image data set respectively. Then, corresponding feature extraction methods are respectively adopted for the numerical data set, the text data set, and the image data set to extract features, and each extracted feature is normalized (feature encoding transformation) to obtain the second feature vector corresponding to the second data set. The first feature vector and the second feature vector are spliced to obtain a spliced feature vector with the same final feature order and dimension. The spliced feature vector is input into the target anomaly detection model, and by classifying and clustering the characteristics, the anomaly result of the target user can be obtained.

[0046] Exemplarily, for image data, it may be necessary to use a pre-trained CNN model to extract features, such as the features before the output layer of ResNet as the feature vector. For text, the output of models such as BERT can be used as the feature vector.

[0047] Among them, performing feature encoding transformation on the multiple performance parameters to obtain the first feature vector includes: comparing the multiple performance parameters with their corresponding preset threshold ranges respectively; if the first performance parameter is within the preset threshold range, setting the feature encoding of the first performance parameter to the first value, otherwise setting it to the second value, where the first performance parameter is any one of the multiple performance parameters; sorting the feature encodings according to the priority of the performance parameters to generate the first feature vector.

[0048] Normalization processing can scale the extracted features to the interval [0, 1], so that each feature corresponds to a binary feature, that is, binary encoding is performed on each feature.

[0049] Among them, the first value can be 0 and the second value can be 1. Or the first value is 1 and the second value is 0.

[0050] For numerical data, the server can directly compare the numerical value with the corresponding threshold value. If the numerical value is greater than its corresponding threshold value, the numerical value is normalized to 1. If the numerical value is less than its corresponding threshold value, the numerical value is normalized to 0. For text data, it can be determined whether there is a keyword in the text. If there is a keyword, the text data is normalized to 1, otherwise it is normalized to 0. The keyword is the text indicating the existence of an abnormal phenomenon. For image data, the features of the image can be compared with the features of a normal image. If the features of the image are equal to or within a certain range of the features of the normal image, the image data can be normalized to 1; otherwise it is normalized to 0.

[0051] Specifically, for the first data set, the server can directly compare multiple performance parameters with the corresponding preset threshold ranges respectively. If the performance parameter is within its preset threshold range, the feature code of the performance parameter is set to the first value, otherwise it is set to the second value. In the second data set, for text data, by comparing it with the corresponding preset threshold range, its feature code is set to the first value or the second value; for text data, by comparing it with the corresponding keyword, its feature code is set to the first value or the second value; for image data, by comparing it with the features of the corresponding normal image, its feature code is set to the first value or the second value.

[0052] For example, for the flow rate of a ventricular assist device, if the flow rate is greater than 1 L / min and less than 6 L / min, the feature code of the flow rate is set to 0, otherwise it is set to 1. For the heart rate detection result of a patient, if keywords such as "premature beats, ventricular fibrillation, atrial fibrillation" are present in the heart rate detection result, it is considered that the patient has arrhythmia, and the feature code of the patient's heart rate detection result can be set to 1, otherwise it is set to 0.

[0053] For example, to determine whether the left and right ventricular volumes of a patient are balanced based on an ultrasound image, the ultrasound image is compared with the ultrasound image of a normal user; if they are not the same or similar, it is considered that the left and right ventricular volumes of the patient are unbalanced, and it is further determined whether the left ventricular volume or the right ventricular volume of the patient is more, and then the ultrasound image is compared with the ultrasound image with more left ventricular volume; if they are the same or similar, it is considered that the patient's left ventricle is swollen, and the feature code of the ultrasound image is set to 11; if they are not the same or not similar, it is considered that the patient's right ventricle is swollen, and the feature code of the ultrasound image is set to 10; if the ultrasound image is the same or similar to the ultrasound image of a normal user, it is considered that the left and right ventricular volumes of the patient are balanced, and the feature code of the ultrasound image is set to 00.

[0054] For another example, for lung images, there are various abnormal phenomena. First, compare the lung image with the lung images of normal users; if they are different or not similar, then compare the lung image with the lung images of patients with pulmonary edema; if they are the same or similar, and the patient is considered to have pulmonary edema, then set the feature code of the lung image to 100; if they are different or not similar, then compare the lung image with the lung images of patients with lung infection; if they are the same or similar, and the patient is considered to have lung infection, then set the feature code of the lung image to 110; if they are different or not similar, then compare the lung image with the lung images of patients with pulmonary embolism; if they are the same or similar, and the patient is considered to have pulmonary embolism, then set the feature code of the lung image to 111; if the lung image is the same or similar to the lung images of normal users, and the patient is considered to have normal lungs, then set the feature code of the lung image to 000.

[0055] Further, after performing feature extraction and feature coding on the data in both the first data set and the second data set, the feature codes can be sorted according to the importance (priority) of each data to ensure structured feature vectors with the same feature order. For example, the first data set sorts the feature codes in the order of flow rate, rotational speed, pulsatility index, and power to generate a first feature vector; the second data set sorts the feature codes in the order of heart rate, respiratory rate, blood oxygen content, aortic pressure, pulmonary artery pressure, central venous pressure, ultrasound image, lung image, and various blood indicators to generate a second feature vector. The first feature vector and the second feature vector are spliced adjacent to each other to obtain a spliced feature vector, and each element in the spliced feature vector represents a feature. The feature order and dimension of each spliced feature vector are the same.

[0056] It should be noted that if a certain performance parameter or monitoring parameter is missing in the first data set or the second data set, the performance parameter or monitoring parameter can be directly filled so that its feature code is the same as the feature code under normal users.

[0057] After obtaining the spliced feature vector, use the spliced feature vector as the input of the target anomaly detection model to output the anomaly result of the target user.

[0058] S230. Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

[0059] When it is detected that the target patient has an anomaly, the server can generate corresponding treatment suggestions according to the anomaly result. For example, the treatment suggestions include: adjusting the rotational speed of the ventricular assist device, adjusting the parameters of the cardiac pacemaker, adjusting the dosage of vasoactive drugs, etc. At the same time, the server can send the corresponding treatment suggestions to the first medical device so that medical staff can timely treat the target user according to the treatment suggestions and reduce the mortality rate of the patient.

[0060] Among them, the abnormal result includes one or more abnormal causes.

[0061] The abnormal cause includes abnormal phenomena that may occur after the patient's operation, such as arrhythmia, insufficient perfusion, right heart failure, pulmonary hemorrhage, pulmonary edema, pericardial effusion and other common complications after ventricular assist device operation.

[0062] Optionally, generating a target adjustment plan according to the abnormal result includes: obtaining a target mapping table, where the target mapping table is the medication situation and / or the adjustment plan for the first medical device corresponding to the user under different abnormal conditions; determining the target adjustment plan corresponding to the target abnormal cause according to the target mapping table, and the target abnormal cause is any one of the one or more abnormal causes.

[0063] The server can pre-store the target mapping table, which is the adjustment plan of the ventricular assist device, the adjustment plan of the pacemaker parameters, the dosage adjustment plan of vasoactive drugs, etc. corresponding to each abnormal cause. Search for the treatment suggestions corresponding to each abnormal cause from the target mapping table. Then send each treatment suggestion to the first medical device.

[0064] Among them, determining the target adjustment plan corresponding to the target abnormal cause according to the target mapping table includes: determining the abnormal levels of the multiple target abnormal causes; determining the abnormal cause with the highest abnormal level as the main abnormal cause; determining the adjustment plan corresponding to the main abnormal cause as the target adjustment plan according to the target mapping table. Among them, the target adjustment plan may include: increasing or decreasing the rotation speed of the ventricular assist device, increasing or decreasing the pacing frequency of the pacemaker, adding, increasing or decreasing the dosage of vasoactive drugs, and so on.

[0065] When the target user has multiple abnormal causes, the server can determine the most urgent and most harmful abnormal cause among the multiple abnormal causes, and then generate a treatment suggestion for the target user according to this abnormal cause.

[0066] Specifically, the server can pre-store the abnormal level corresponding to each abnormal cause. Determine the priority levels of the multiple abnormal causes, and determine the abnormal cause with the highest abnormal priority level as the main abnormal cause, and this main abnormal cause can cause the most serious or most urgent harm to the patient. Then search for the adjustment plan corresponding to this main abnormal cause from the target mapping table, and determine this adjustment plan as the final target adjustment plan, and send this target adjustment plan to the first medical device.

[0067] Further, when an anomaly is detected, the server can also send an anomaly alarm signal to the first medical device to notify medical staff in a timely manner. The server can also determine an anomaly alarm plan for the target user based on the priority of the anomaly cause. The higher the priority of the anomaly cause, the higher its anomaly alarm level. For example, when the anomaly cause of the target user is arrhythmia, its anomaly alarm level is low, and the alarm light on the first medical device shows; when the anomaly cause of the target user is pericardial effusion, its anomaly alarm level is medium, and the alarm light on the first medical device shows and the horn sounds; when the anomaly cause of the target user is right heart failure and pulmonary hemorrhage, its anomaly alarm level is high, the alarm light on the first medical device shows, the horn sounds, and a signal is sent to the attending doctor.

[0068] It can be seen that this application proposes a control method based on a medical monitoring system, which obtains a first data set and a second data set. The first data set includes the real-time operation data of the first medical device, and the second data set includes the monitoring data of the second medical device. The first medical device is used to provide assistance to the target user, and the second medical device is used to monitor the health status of the target user; the first data set and the second data set are input into the target anomaly detection model, and the anomaly result of the target user is output; a target adjustment plan is generated according to the anomaly result and sent to the first medical device. According to the first data set of the first medical device associated with the target user, the second data set of the second medical device, and using a model to detect the user's anomaly, this application can improve the efficiency and accuracy of judging the user's anomaly. And generating an adjustment plan for the first medical device according to the anomaly can facilitate medical staff to handle the user's postoperative abnormal phenomena in a timely manner, reduce risks, and increase the user's life safety.

[0069] The above mainly introduces the solution of the embodiment of this application from the perspective of the execution process on the method side. It can be understood that in order for the network device to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments provided in this article, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0070] Exemplarily, the embodiment of this application also provides a medical monitoring system, which includes a first medical device, a second medical device, and a server; the server includes one or more processors, and the one or more processors are used for:

[0071] Obtain a first data set and a second data set, where the first data set includes real-time operation data of the first medical device, and the second data set includes monitoring data of the second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user;

[0072] Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user;

[0073] Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

[0074] Exemplarily, the present application also provides a medical device, which includes the above-mentioned server or medical monitoring system.

[0075] Among them, the server of each of the above solutions has the function of implementing the corresponding steps executed by the medical device in the above method; the function can be implemented by hardware or by hardware executing corresponding software.

[0076] In an embodiment of the present application, the server may also be a chip or a chip system, such as: a system on chip (SoC).

[0077] Please refer to Figure 3 , Figure 3 is a schematic structural diagram of a medical device provided by an embodiment of the present application. The medical device includes: one or more processors, one or more memories, one or more communication interfaces, and one or more programs; the one or more programs are stored in the memory and are configured to be executed by the one or more processors.

[0078] The above programs include instructions for performing the following steps:

[0079] Obtain a first data set and a second data set, where the first data set includes real-time operation data of a first medical device, and the second data set includes monitoring data of a second medical device. The first medical device is used to provide auxiliary assistance to a target user, and the second medical device is used to monitor the health status of the target user;

[0080] Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user;

[0081] Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

[0082] Among them, all relevant contents of each scenario involved in the above method embodiments can be cited in the function descriptions of the corresponding functional modules, and will not be elaborated here.

[0083] It should be understood that the above-mentioned memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0084] In the embodiments of the present application, the processor of the above device may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0085] It should be understood that "at least one" involved in the embodiments of the present application refers to one or more, and "a plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B may be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c may be single or multiple.

[0086] Also, unless otherwise stated, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects and are not used to limit the order, time sequence, priority, or importance of multiple objects. For example, the first information and the second information are only used to distinguish different information, rather than indicating differences in the content, priority, sending order, or importance of these two pieces of information, etc.

[0087] In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by the combination of the hardware and software units in the processor. The software unit can be located in mature storage media in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. This storage media is located in the memory, and the processor executes the instructions in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0088] The embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables the computer to execute some or all of the steps of any method described in the above method embodiments.

[0089] The embodiments of the present application also provide a computer program product. The above computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the above computer program is operable to enable the computer to execute some or all of the steps of any method described in the above method embodiments. The computer program product can be a software installation package.

[0090] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0091] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0093] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the objectives of the solution of the embodiments of the present application.

[0094] In addition, in each embodiment of the present application, the various functional units may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0095] If the above integrated unit 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 memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a TRP, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), external hard drives, magnetic disks, or optical discs, etc., which are all media that can store program codes.

[0096] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, ROMs, RAMs, magnetic disks, or optical discs, etc.

[0097] The above has introduced the embodiments of the present application in detail. Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A control method based on a medical monitoring system, characterized in that The medical monitoring system includes a first medical device, a second medical device, and a server; the method includes: Obtaining a first data set and a second data set, where the first data set includes real-time operation data of the first medical device, and the second data set includes monitoring data of the second medical device. The first medical device is used to provide assistance to a target user, and the second medical device is used to monitor the health status of the target user; Inputting the first data set and the second data set into a target anomaly detection model, and outputting an anomaly result of the target user; Generating a target adjustment plan according to the anomaly result and sending it to the first medical device.

2. The method according to claim 1, wherein The first medical device is a ventricular assist device, and the second medical device includes at least one of the following: a vital sign monitoring device, an imaging examination device, and a laboratory testing device.

3. The method according to claim 2, wherein The step of inputting the first data set and the second data set into a target anomaly detection model and outputting an anomaly result of the target user includes: Extracting a plurality of performance parameters from the real-time operation data of the first data set, and performing feature encoding transformation on the plurality of performance parameters to obtain a first feature vector; Classifying the second data set according to data types to obtain a numerical data set, a text data set, and an image data set; Respectively performing feature encoding transformation on the numerical data set, the text data set, and the image data set to obtain a second feature vector; Concatenating the first feature vector and the second feature vector to obtain a concatenated feature vector; Inputting the concatenated feature vector into a target anomaly detection model to obtain the anomaly result.

4. The method according to claim 3, wherein The step of performing feature encoding transformation on the plurality of performance parameters to obtain a first feature vector includes: Respectively comparing the plurality of performance parameters with corresponding preset threshold ranges; If a first performance parameter is within the preset threshold range, setting the feature encoding of the first performance parameter to a first value, otherwise setting it to a second value, where the first performance parameter is any one of the plurality of performance parameters; Sorting the feature encodings according to the priority of the performance parameters to generate the first feature vector.

5. The method according to claim 4, wherein The performance parameters include: rotational speed, flow rate, power, and pulsation index.

6. The method according to claim 1, characterized in that, The anomaly result includes one or more anomaly causes; the step of generating a target adjustment plan according to the anomaly result includes: Obtaining a target mapping table, where the target mapping table is the medication situation and / or the adjustment plan of the first medical device corresponding to the user under different anomaly situations; According to the target mapping table, determining the target adjustment plan corresponding to the target anomaly cause, where the target anomaly cause is any one of the one or more anomaly causes.

7. The method according to claim 6, wherein The step of determining the target adjustment plan corresponding to the target anomaly cause according to the target mapping table includes: Determining the anomaly level of the one or more target anomaly causes; Determining the anomaly cause with the highest anomaly level as the main anomaly cause; According to the target mapping table, determining the adjustment plan corresponding to the main anomaly cause as the target adjustment plan.

8. A medical monitoring system, characterized in that, The medical monitoring system includes a first medical device, a second medical device, and a server; the server includes one or more processors, and the one or more processors are configured to: Obtain a first data set and a second data set, where the first data set includes real-time operation data of the first medical device, and the second data set includes monitoring data of the second medical device. The first medical device is used to provide assistance to a target user, and the second medical device is used to monitor the health status of the target user; Input the first data set and the second data set into a target anomaly detection model, and output an anomaly result of the target user; Generate a target adjustment plan according to the anomaly result and send it to the first medical device.

9. A medical device, characterized in that, It includes a processor, a memory, and a communication interface. The memory stores one or more programs, and the one or more programs are executed by the processor. The one or more programs include instructions for performing the steps in the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for electronic data exchange, where the computer program causes a computer to execute the steps of the method according to any one of claims 1-7.

Images