CN115274102B - Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism - Google Patents
Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism Download PDFInfo
- Publication number
- CN115274102B CN115274102B CN202210630539.XA CN202210630539A CN115274102B CN 115274102 B CN115274102 B CN 115274102B CN 202210630539 A CN202210630539 A CN 202210630539A CN 115274102 B CN115274102 B CN 115274102B
- Authority
- CN
- China
- Prior art keywords
- patient
- layer
- information
- risk level
- booster pump
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Abstract
The embodiments of the present specification provide systems, methods, devices, and media for artificial intelligence prevention and treatment of venous thromboembolism. The system comprises an acquisition module, a risk level determination module and a prevention and treatment measure determination module. The acquisition module is used for acquiring patient information, wherein the patient information comprises basic information and relevant information for treatment; the risk level determining module is used for processing patient information through the risk assessment model and determining a first venous thromboembolism risk level and a first bleeding risk level of a patient; the prevention measure determination module is to determine a prevention measure for venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level.
Description
Technical Field
The present disclosure relates to the field of venous thromboembolic disorders, and in particular, to venous thromboembolic disorders artificial intelligence control systems, methods, devices, and media.
Background
Venous thromboembolism (venous thromboembolism, VTE) is a collective name of deep venous thrombosis (deep venous thrombosis, DVT) and pulmonary embolism (pulmonary embolism, PE) and is a manifestation of the same disease at different stages. Deep vein thrombosis is a venous return obstructive condition caused by the inability of blood to coagulate normally in deep veins, and is commonly found in the lower extremities. Pulmonary embolism is caused by thrombus shedding. Venous thromboembolism has the characteristics of high morbidity, high mortality, high missed diagnosis rate and high misdiagnosis rate, and constitutes a potential risk of medical quality and patient safety, and becomes a serious problem faced by clinical medical staff and hospital managers. However, venous thromboembolism is taken as a preventable disease, the occurrence rate of the disease can be obviously reduced by active and effective prevention, and the death rate of the disease can be obviously reduced by standard diagnosis and treatment. By combining with artificial intelligence (Artificial Intelligence, AI) technology, a medical care cooperative venous thromboembolic disease prevention and treatment system is constructed, so that the timely detection of high-risk people can be realized, and medical care personnel can effectively perform early intervention of venous thromboembolic disease.
Therefore, how to combine artificial intelligence technology to realize the risk assessment of venous thromboembolism and assist medical staff in preventing and treating is a problem to be solved urgently.
Disclosure of Invention
One or more embodiments of the present specification provide an artificial intelligence control system for venous thromboembolism. The venous thromboembolism artificial intelligence prevention and cure system includes: the system comprises an acquisition module, a risk level determination module and a prevention and treatment measure determination module; the acquisition module is used for acquiring patient information, wherein the patient information comprises basic information and relevant information of treatment; the risk level determining module is used for processing the patient information through a risk assessment model and determining a first venous thromboembolism risk level and a first bleeding risk level of the patient; the prevention measure determination module is to determine a prevention measure for venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level.
One or more embodiments of the present specification provide an artificial intelligence method for controlling venous thromboembolism, the artificial intelligence method for controlling venous thromboembolism comprising: acquiring patient information, wherein the patient information comprises basic information and relevant information of treatment; processing the patient information through a risk assessment model, and determining a first venous thromboembolic risk level and a first hemorrhagic risk level of the patient; determining a measure of prevention and treatment of venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level.
One or more embodiments of the present specification provide an artificial intelligence prevention and treatment device for venous thromboembolism, the device comprising at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the venous thromboembolic artificial intelligence method of controlling.
One or more embodiments of the present disclosure provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, perform the method of artificial intelligence control of venous thromboembolism.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a schematic illustration of an application scenario of an artificial intelligence control system for venous thromboembolism according to some embodiments of the present description;
FIG. 2 is an exemplary block diagram of an artificial intelligence control system for venous thromboembolism in accordance with some embodiments of the present description;
FIG. 3 is an exemplary flow chart of an artificial intelligence method of controlling venous thromboembolism according to some embodiments of the present description;
FIG. 4 is an exemplary block diagram of a risk assessment model according to some embodiments of the present description;
fig. 5 is an exemplary block diagram of a booster pump analysis model shown in accordance with some embodiments of the present disclosure.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic illustration of an application scenario of an artificial intelligence control system for venous thromboembolism according to some embodiments of the present description.
In some embodiments, the application scenario 100 of the venous thromboembolic artificial intelligence prevention system may include a storage device 110, a network 120, a processing device 130, a booster pump 140, and a user terminal 150.
In some embodiments, one or more components of the application scenario 100 may be connected and/or in communication with each other via a network 120 (e.g., a wireless connection, a wired connection, or a combination thereof). As shown in fig. 1, storage device 110 may be connected to processing device 130 through network 120. As another example, processing device 130 may be connected to user terminal 150 via network 120.
Storage device 110 may be used to store data and/or instructions. In some embodiments, the storage device 110 may store basic information of a patient, and the relevant description of the basic information of a patient may be found in particular in the detailed description of fig. 2. In some embodiments, the storage device 110 may also obtain and store data and/or instructions that are executed or used by the processing device 130 via the network 120 to perform the exemplary methods described in this specification.
The network 120 may connect components of the application scenario 100 and/or connect the application scenario 100 with external resource portions. Information and/or data may be exchanged between one or more components of the venous thromboembolic artificial intelligence control system via the network 120. For example, the network 120 may obtain basic information of the patient from the storage device 110, and so on. In some embodiments, network 120 may be any one or more of a wired network or a wireless network. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points. The network may be a local area network, a wide area network, the internet, etc., and may be a combination of various network structures.
The processing device 130 may be used to process information and/or data related to the application scenario 100, such as patient basic information, patient history visits, and the like. The processing device 130 may include a risk assessment model and a booster pump analysis model. Wherein the risk assessment model may be used to assess a first venous thromboembolic risk level and a first bleeding risk level. The booster pump analysis model can be used for outputting the working parameters of the booster pump and the corresponding sign anomaly probabilities thereof. In some embodiments, processing device 130 may process data, information, and/or processing results obtained from other devices or system components and execute program instructions based on such data, information, and/or processing results to perform one or more functions described herein.
The booster pump 140 may be used to control a patient. The pressurizing pump 140 includes an intermittent inflation pressurizing pump, and can promote fluid reflux of the veins and lymph of the limbs by periodically inflating and deflating the cuff (inflation and deflation correspond to pressurization and depressurization, respectively). In some embodiments, the booster pump 140 may obtain the booster pump operating parameters output by the processing apparatus 130, such as pressure magnitude, operating duration, pressurization interval, etc. The booster pump 140 can operate according to the operating parameters of the booster pump, so as to realize the prevention and treatment of venous thromboembolism.
User terminal 150 may include one or more terminal devices or software. In some embodiments, user terminal 150 may include one or any combination of mobile device 150-1, tablet computer 150-2, desktop computer 150-3, and the like, as well as other input and/or output enabled devices. In some embodiments, a user may view information and/or input data and/or instructions through a user terminal. For example, user terminal 150 may receive a risk assessment reminder and a reminder to manually set parameters from processing device 130.
Fig. 2 is an exemplary block diagram of an artificial intelligence control system for venous thromboembolism, according to some embodiments of the present description.
In some embodiments, the venous thromboembolic artificial intelligence prevention system 200 may include an acquisition module 210, a risk level determination module 220, and a prevention measure determination module 230.
The acquisition module 210 may be used to acquire patient information including basic information and visit related information.
Basic information refers to information related to the identity and physical condition of the patient. For example, the basic information may include one or more of gender, age, height weight, blood pressure, etc. The visit information refers to information related to a patient visit. For example, the visit information may include one or more of a care record, an admission record, an order, a surgical record, a medical record, an inspection report, and the like.
In some embodiments, the patient may actively upload the basic information to the terminal device, and the acquiring module 210 may acquire the basic information of the patient through the terminal device. In some embodiments, the acquisition module 210 may acquire the patient's basic information through a medical system that stores the patient's basic information. Among them, the medical system refers to a system for collecting, organizing and storing patient information.
The risk level determination module 220 may be configured to process patient information via a risk assessment model to determine a first venous thromboembolic risk level and a first bleeding risk level of the patient.
The first venous thromboembolic risk level refers to a risk level determined based on the level of risk of the patient for venous thromboembolic disease. For example, a first venous thromboembolic risk level may be classified as between 1 and 10, with a higher number of levels representing a higher risk of venous thromboembolism in the patient. As another example, the first venous thromboembolic risk level may be classified as mild, severe, very severe, etc.
The first bleeding risk level refers to a risk level determined according to the level of risk of bleeding in the patient. For example, the first bleeding risk level may be classified as level 1-10, with a higher number of levels representing a higher risk of bleeding in the patient. As another example, the first bleeding risk level may be classified as mild, severe, very severe, etc.
In some embodiments, patient information may be input into a base layer of the risk assessment model, which outputs patient characteristic information. And then inputting the characteristic information of the patient into a first venous thromboembolic disease assessment layer and a first bleeding assessment layer of the risk assessment model respectively, wherein the first venous thromboembolic disease assessment layer outputs a first venous thromboembolic disease risk level, and the first bleeding assessment layer outputs a first bleeding risk level.
The patient characteristic information refers to characteristic information extracted from the patient information and related to determining venous thromboembolism of the patient. In some embodiments, the patient characteristic information may include one or more of patient physical condition information, patient thrombus information, patient bleeding information, and the like.
The patient physical condition information refers to information related to the physical condition of the patient. For example, the patient condition information may include one or more of patient condition health, patient condition sub-health, patient condition poor, and the like. Patient thrombus information refers to information related to the history of patient thrombus onset. For example, the patient thrombus information may include one or more of a patient thrombus site, a patient time of onset, a patient time of cure, a number of patient thrombus occurrences, and the like. Patient bleeding information refers to information related to the history of patient bleeding. For example, the patient bleeding information may include one or more of a patient bleeding site, a patient bleeding time, a patient healing time, a number of patient bleeding occurrences, and the like.
For further details of the risk assessment model, the underlying layer of the risk assessment model, the first venous thromboembolic disorder assessment layer, and the first hemorrhage assessment layer, see fig. 4 and its associated description.
The prevention measure determination module 230 may be configured to determine a prevention measure for venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level.
The prevention and treatment may be a prevention and treatment for venous thromboembolism in the patient. In some embodiments, the prevention measures may include one or more of active measures, wearable measures, external force measures, and medication measures, among others.
Proactive measures refer to the patient's timed out-of-bed activities. The active measures are suitable for patients with low risk level of venous thromboembolism. For example, patients with a venous thromboembolic risk level of 2 or below.
The wearing measure is to wear the graded pressurizing elastic socks for the patient. The wearing measure is suitable for patients with lower risk of venous thromboembolism. For example, patients with a venous thromboembolic risk level of between 2 and 5. In some embodiments, the higher the risk level, the greater the compression level of the stretch stocking used by the patient may be.
External force measures refer to the use of a booster pump (e.g., an intermittent inflation booster pump) for patient control. The external force measures are suitable for patients with higher risk grades of venous thromboembolism. For example, patients with a venous thromboembolic risk level of between 6 and 10.
The taking measures refer to taking anticoagulant drugs under the guidance of doctors. The taking measures are suitable for patients with higher risk level of venous thromboembolism and patients with lower risk level of bleeding. For example, patients with venous thromboembolic risk levels between 8 and 10 and bleeding risk levels of 5 and below.
In some embodiments, the prevention measure determination module 230 may determine the prevention measure of venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level. For example, when patients with venous thromboembolic risk levels of 2 or less, the prevention and treatment measures employed are proactive measures; when the risk level of the venous thromboembolism is 2-5 level, the adopted prevention and treatment measures are wearing measures; when the risk level of the venous thromboembolism is between 6 and 10, adopting external force measures as prevention measures; when the risk level of venous thromboembolism is 8-10 and the risk level of bleeding is 5 or below, the prevention and treatment measures are taken as medicine taking measures.
In some embodiments, when the control measure includes controlling the patient using a booster pump, the venous thromboembolic artificial intelligence control system 200 may also include a booster pump control module 240. The booster pump prevention and treatment module 240 may be configured to process the patient information, the first venous thromboembolic risk level, and the first hemorrhage risk level via a booster pump analysis model to determine operating parameters of the booster pump and a patient-corresponding sign anomaly probability.
In some embodiments, the operating parameters of the booster pump may include one or more of a pressure level of the booster pump, an operating duration of the booster pump, a pressurization interval of the booster pump, and the like.
Abnormal signs refer to the occurrence of an abnormality in the physical index of the patient or the occurrence of a significant pathological condition in the patient. For example, a sign abnormality may refer to an abnormality in the heart rate, blood pressure, etc. of a patient. For another example, a sign disorder may refer to a patient suffering from pain, skin discoloration, dyspnea, or the like.
In some embodiments, patient information may be input into a base layer of the booster pump analysis model, which outputs patient characteristic information. And then inputting the characteristic information of the patient, the first venous thromboembolism risk level and the first bleeding risk level into a parameter analysis layer of the booster pump analysis model, and outputting the working parameters of the booster pump by the parameter analysis layer.
In some embodiments, the operating parameters of the booster pump and the patient characteristic information may be input into a probabilistic analysis layer of the booster pump analysis model, which outputs the sign anomaly probabilities.
In some embodiments, the operating parameters of the pressurization pump and the patient characteristic information may also be entered into a second venous thromboembolic assessment layer, which outputs a second venous thromboembolic risk level. The operating parameters of the compression pump and patient characteristic information may be input to a second hemorrhage assessment layer, which outputs a second hemorrhage risk level. And then inputting the second venous thromboembolism risk level, the second bleeding risk level, the working parameters of the pressurizing pump and the patient characteristic information into a probability analysis layer of the pressurizing pump analysis model, and outputting the abnormal sign probability by the probability analysis layer.
For more description of the booster pump analysis model, the base layer of the booster pump analysis model, the parameter analysis layer, the second venous thromboembolic disorder assessment layer, the second hemorrhage assessment layer, and the probability analysis layer, please refer to fig. 5 and its associated description.
In some embodiments, the booster pump prevention module 240 may be further configured to send a reminder message to the user terminal of the target user when the sign anomaly probability is greater than a preset threshold, the reminder message being configured to remind the target user to monitor the prevention process.
In some embodiments, the preset threshold may be empirically set by one skilled in the art. For example, the preset threshold may be 80%, 85%, etc.
In some embodiments, the alert information may be used to alert the target user to monitor the control process. The reminding information can be one or more of text, images or videos.
The target user refers to a person monitoring the real-time course of the patient's preventive measures. For example, the target user may be a nurse or doctor, or the like.
The monitoring of the course of control may be the monitoring of the course of action of the targeted user in the control of venous thromboembolism in the patient. In some embodiments, when the targeted user monitors the course of implementation of a prevention and treatment measure for venous thromboembolism in a patient, the parameters of the prevention and treatment measure may be changed directly by the targeted user (e.g., nurse or doctor) or after the targeted user (e.g., nurse) consults with the doctor's advice when the prevention and treatment measure is found to have poor effect on improving venous thromboembolism in the patient.
In some embodiments, the alert information may include alerting the targeted user (e.g., nurse, doctor, etc.) to the frequency of manual monitoring of the control process.
In some embodiments, the frequency of the manual monitoring control process may be determined based on the sign anomaly probability. In some embodiments, the greater the sign anomaly probability value, the greater the frequency of the manual monitoring prevention process. For example, if the abnormal sign probability value is greater than 90%, setting the frequency of the manual monitoring prevention and treatment process to be once every two minutes; if the abnormal probability value of the physical sign is greater than 80% and less than 90%, setting the frequency of the manual monitoring prevention and treatment process to be once every four minutes; if the abnormal probability value of the physical sign is more than 70% and less than 80%, setting the fixed frequency of the manual monitoring prevention and treatment process to be once every six minutes.
In some embodiments, the frequency of the manual monitoring prevention procedure may be modified based on the confidence of the second venous thromboembolic assessment layer and the second hemorrhage assessment layer of the booster pump analysis model.
For more details on the second venous thromboembolic assessment layer and the second hemorrhage assessment layer, see fig. 5 and the related description.
In some embodiments, the booster pump control module 240 may weight average the confidence of the second venous thromboembolic assessment layer and the second hemorrhage assessment layer to obtain a combined confidence. In some embodiments, the confidence of the second venous thromboembolic assessment layer may be weighted more than the confidence of the second hemorrhage assessment layer. For example, the weight value of the confidence of the second venous thromboembolic evaluation layer may be preset to 0.7, the weight value of the confidence of the second hemorrhagic evaluation layer is 0.3, and if the confidence of the second venous thromboembolic evaluation layer is 0.9 and the confidence of the second hemorrhagic evaluation layer is 0.8, the overall confidence=0.9×0.7+0.8×0.3=0.87.
In some embodiments, the booster pump control module 240 may modify the frequency of the manual monitoring control process based on the integrated confidence. For example, f=f can be set 0 Z, wherein F is the corrected frequency, F 0 And Z is the comprehensive confidence coefficient for the preset frequency. For example F 0 Once every four minutes, z=0.8, then f=f 0 The representative frequency was corrected from once every four minutes to once every five minutes.
In some embodiments of the present disclosure, by acquiring patient information and then intelligently analyzing the patient information, a first venous thromboembolic risk level and a first hemorrhagic risk level of a patient can be determined, so as to implement risk assessment of venous thromboembolic diseases, thereby quickly and accurately determining venous thromboembolic disease prevention measures suitable for the patient, and assisting medical staff in prevention and treatment. In other embodiments of the present disclosure, the frequency of the manual monitoring and controlling process is modified by setting the weight value of the confidence level of the second venous thromboembolic disorder assessment layer to be greater than the weight value of the confidence level of the second hemorrhagic disorder assessment layer, and then weighting and averaging the confidence levels of the second venous thromboembolic disorder assessment layer and the second hemorrhagic disorder assessment layer to obtain a comprehensive confidence level, so that the modified frequency is more accurate, and monitoring of the controlling and controlling measure process by medical staff is better assisted.
It should be noted that the above description of the venous thromboembolic artificial intelligence control system and its modules is for descriptive convenience only and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the acquisition module 210, the risk level determination module 220, the prevention measure determination module 230, and the booster pump prevention module 240 disclosed in fig. 2 may be different modules in one system, or may be one module to implement the functions of two or more modules described above. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.
Fig. 3 is an exemplary flow chart of an artificial intelligence method of controlling venous thromboembolism in accordance with some embodiments of the present description. In some embodiments, the process 300 may be performed by the venous thromboembolic artificial intelligence control system 200 or the processing device 130. As shown in fig. 3, the process 300 includes the following steps.
In step 310, patient information is obtained, the patient information including basic information and visit related information. In some embodiments, step 310 may be performed by the acquisition module 210.
For definitions and descriptions of related terms, and methods of acquiring patient information, please refer to the acquisition module 210 of fig. 2 and its related description.
At step 320, patient information is processed through a risk assessment model to determine a first venous thromboembolic risk level and a first bleeding risk level for the patient.
For definition and explanation of related terms, and methods of determining a first venous thromboembolic risk level and a first bleeding risk level for a patient, please refer to the risk level determination module 220 in fig. 2 and its related description.
At step 330, a measure of prevention and treatment of venous thromboembolism in the patient is determined based on the first venous thromboembolism risk level and the first bleeding risk level.
For definitions and descriptions of related terms, and methods of determining a measure of prevention of venous thromboembolism in a patient, reference is made to the prevention determination module 230 of FIG. 2 and its associated description.
In some embodiments, when the treatment includes controlling the patient using a booster pump, the process 300 may further include the following steps 340-350 (not shown).
And step 340, processing the patient information, the first venous thromboembolism risk level and the first bleeding risk level through a booster pump analysis model, and determining the working parameters of the booster pump and the abnormal sign probability corresponding to the patient.
For definitions and descriptions of related terms, and methods for determining the operating parameters of the booster pump and the corresponding abnormal probabilities of physical signs for the patient, please refer to the booster pump control module 240 in fig. 2 and related description thereof.
And 350, when the abnormal sign probability is greater than a preset threshold value, sending reminding information to a user terminal of the target user, wherein the reminding information is used for reminding the target user to monitor the prevention and treatment process.
For definitions and descriptions of related terms, please refer to the booster pump control module 240 in fig. 2 and its related description.
It should be noted that the above description of the process 300 is for purposes of example and illustration only and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description. For example, flow 300 may perform only steps 310-330 without performing steps 340-350.
FIG. 4 is an exemplary block diagram of a risk assessment model, shown in accordance with some embodiments of the present description.
As shown in structure 400, the risk assessment model is used to assess the patient's venous thromboembolic risk level and hemorrhage risk level. In some embodiments, the input of the risk assessment model may include patient information and the output of the risk assessment model may include a first venous thromboembolic risk level and a first bleeding risk level. In some embodiments, the risk assessment model may include a base layer, a first venous thromboembolic assessment layer, and a first hemorrhage assessment layer. The output of the base layer serves as input to a first venous thromboembolic assessment layer and a first hemorrhage assessment layer, the output of which serves as output to a risk assessment model.
The base layer is used to determine patient characteristic information. The input of the base layer may include patient information. The output of the base layer may include patient characteristic information.
The first venous thromboembolic evaluation layer is used to determine a first venous thromboembolic risk level. The input of the first venous thromboembolic assessment layer may include patient characteristic information. The output of the first venous thromboembolic assessment layer may include a first venous thromboembolic risk level.
The first hemorrhage assessment layer is for determining a first hemorrhage risk level. The input of the first hemorrhage assessment layer can include patient characteristic information. The output of the first hemorrhage assessment layer may include a first hemorrhage risk level. In some embodiments, the risk level may be divided according to the degree size.
In some embodiments, the confidence level of the output results of the first venous thromboembolic assessment layer and the first hemorrhage assessment layer is less than a threshold, and a reminder message is sent to a user terminal (e.g., a terminal used by a doctor) to remind the person to assess risk. In some embodiments, the confidence threshold may be manually preset. For example, if the confidence coefficient of the first venous thromboembolism evaluation layer is preset to be 0.7 and the actual confidence coefficient of the output result is 0.5 to be smaller than the threshold, a reminding message is sent to the terminal of the doctor to remind the doctor to manually evaluate the risk level of the first venous thromboembolism.
In some embodiments, the base layer, the first venous thromboembolic assessment layer, and the first hemorrhage assessment layer of the risk assessment model may be trained alone.
In some embodiments, the training data of the base layer may be sets of labeled training samples, which may be patient information. The patient information may be derived from patient history information stored in the storage device. In some embodiments, the training samples may include at least sample physical condition information, sample care records, sample surgical records, and the like of the patient. The label of the training samples of the base layer is patient characteristic information. In some embodiments of the present description, the tag may be obtained from patient history information recorded by a storage device, and the tag may also be obtained by manual labeling.
In some embodiments, the training data of the first venous thromboembolic assessment layer and the first hemorrhage assessment layer may be sets of labeled training samples, which may be patient characteristic information output by the base layer. The training sample of the first venous thromboembolic assessment layer is labeled as a first venous thromboembolic risk level. The label of the training sample of the first venous thromboembolic evaluation layer may be obtained by calculating thrombus related parameters of the inputted patient characteristic information, for example, calculating a thrombus occurrence probability according to the number of thrombus occurrences and time, and evaluating the first venous thromboembolic risk level according to the thrombus occurrence probability. The label of the training sample of the first bleeding evaluation layer is the first bleeding risk level. The label of the training sample of the first bleeding evaluation layer may be obtained by calculating bleeding related parameters of the entered patient characteristic information, e.g. calculating the bleeding severity from the bleeding occurrence site and the healing time, and evaluating the first bleeding risk level from the bleeding severity.
In some embodiments, a loss function is constructed from the label and the result correspondence of the layer of the initial risk assessment model, and parameters of the risk assessment model are iteratively updated by gradient descent or other methods based on the loss function. And when the preset conditions are met, model training is completed, and a trained risk assessment model is obtained. The preset condition may be that the loss function converges, the number of iterations reaches a threshold value, etc.
In some embodiments, the base layer, the first venous thromboembolic assessment layer, and the first hemorrhage assessment layer are obtained by joint training.
In some embodiments, the risk assessment model may train the base layer, the first venous thromboembolic assessment layer, and the first hemorrhage assessment layer based on a plurality of labeled training data. Specifically, training data with labels, namely patient information, can be input into a base layer to obtain patient characteristic information output by the base layer; and then inputting the characteristic information of the patient into the first venous thromboembolic disease assessment layer and the first hemorrhage assessment layer respectively to obtain a first venous thromboembolic disease risk level output by the first venous thromboembolic disease assessment layer and a first hemorrhage risk level output by the first hemorrhage assessment layer. And (3) updating parameters of the basic layer, the first venous thromboembolic evaluation layer and the first hemorrhage evaluation layer through training, and acquiring the trained basic layer, the first venous thromboembolic evaluation layer and the first hemorrhage evaluation layer when the trained model meets preset conditions. The preset condition may be that the loss function is smaller than a threshold, converges, or the training period reaches the threshold.
The risk assessment model can preliminarily determine the first venous thromboembolic risk level and the first hemorrhagic risk level of the patient based on the patient information, so that the manual judgment time is shortened, reminding is timely sent to medical staff, and the medical staff is helped to timely conduct venous thromboembolic prevention measures.
Fig. 5 is an exemplary block diagram of a booster pump analysis model shown in accordance with some embodiments of the present disclosure.
As shown in structure 500, the booster pump analysis model may obtain a sign anomaly probability. The booster pump analysis model may include a base layer, a parameter analysis layer, and a probability analysis layer connected in sequence. Patient information may be entered into the base layer, which outputs patient characteristic information. And inputting the characteristic information of the patient, the first venous thromboembolism risk level and the first bleeding risk level into a parameter analysis layer, and outputting the working parameters of the pressurizing pump by the parameter analysis layer. And then, the working parameters of the pressurizing pump and the characteristic information of the patient are input into a probability analysis layer, and the probability analysis layer outputs the abnormal probability of the physical sign. In some embodiments, the booster pump analysis model, the base layer, the parameter analysis layer, and the probability analysis layer may include convolutional neural networks (Convolutional Neural Networks, CNN), deep neural networks (Deep Neural Networks, DNN), or a combination thereof resulting model, or the like.
In some embodiments, the booster pump analysis model may further include a second venous thromboembolic assessment layer and a second hemorrhage assessment layer, each connected between the parameter analysis layer and the probability analysis layer. The patient characteristic information and the booster pump operating parameters may be input to a second venous thromboembolic assessment layer that outputs a second venous thromboembolic risk level. Patient characteristic information and booster pump operating parameters may be input to a second hemorrhage assessment layer, which outputs a second hemorrhage risk level. And then inputting the second venous thromboembolism risk level, the second bleeding risk level, the patient characteristic information and the working parameters of the booster pump into a probability analysis layer, and outputting the abnormal sign probability by the probability analysis layer. In some embodiments, the second venous thromboembolic assessment layer and the second hemorrhage assessment layer may include a convolutional neural network, a deep neural network, or a combination thereof derived model, or the like.
In some embodiments, the base layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic disorder assessment layer, and the second hemorrhage assessment layer may be obtained by training. Training of the base layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic assessment layer, and the second hemorrhage assessment layer may be performed by the processing device 130, the training of which may be based on the following method.
And respectively acquiring training samples of the basic layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic disease assessment layer and the second bleeding assessment layer and labels thereof.
The training samples of the base layer may be historical patient information. The labels of the training samples of the base layer may be corresponding historical patient characteristic information in the historical patient information. The historical patient characteristic information can be obtained by manually extracting the historical patient information.
The training samples of the parameter analysis layer may be historical patient characteristic information, historical first venous thromboembolic risk level, and historical first bleeding risk level. The label of the training sample of the parameter analysis layer may be the operating parameters of the historical booster pump.
The training samples of the probabilistic analysis layer may be the historical pump operating parameters and the historical patient characteristic information, or may be the historical pump operating parameters, the historical patient characteristic information, the historical second venous thromboembolic risk level, and the historical second bleeding risk level. The labels of the training samples of the probability analysis layer may be historical sign anomaly probabilities.
The training samples of the second venous thromboembolic assessment layer may be historical patient characteristic information and historical booster pump operating parameters. The label of the training sample of the second venous thromboembolic assessment layer may be a historical second venous thromboembolic risk level.
The training samples of the second hemorrhage assessment layer may be historical patient characteristic information and historical booster pump operating parameters. The training sample of the second hemorrhage assessment layer may be labeled with a historical second hemorrhage risk level.
In some embodiments, the operating parameter of the historical booster pump, the historical sign anomaly probability, the historical second venous thromboembolic risk level, and the historical second hemorrhage risk level are all obtained by the medical system. For example, the medical system may store historical pump operating parameters that the physician determines based on historical patient characteristic information, historical first venous thromboembolic risk level, and historical first hemorrhage risk level.
The plurality of labeled training samples are respectively input into a corresponding initial basal layer, an initial parameter analysis layer, an initial probability analysis layer, an initial second venous thromboembolic disease assessment layer and an initial second bleeding assessment layer. Parameters of the initial base layer, the initial parameter analysis layer, the initial probability analysis layer, the initial second venous thromboembolic assessment layer, and the initial second hemorrhage assessment layer are updated by training iterations. And when the trained model meets the preset conditions, training is finished, and a trained basic layer, a parameter analysis layer, a probability analysis layer, a second venous thromboembolism evaluation layer and a second bleeding evaluation layer are obtained. In some embodiments, the preset condition may be that the loss function is less than a threshold, converges, or that the training period reaches a threshold.
In some embodiments, the base layer, the parameter analysis layer, and the probability analysis layer in the booster pump analysis model may be jointly trained to obtain a trained booster pump analysis model. In some embodiments, the base layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic disorder assessment layer, and the second hemorrhage assessment layer in the booster pump analysis model may be jointly trained to obtain a trained booster pump analysis model. In some embodiments, the loss term weight of the second venous thromboembolic assessment layer is greater than the loss term weight of the second hemorrhagic assessment layer. The joint training may be performed by the processing device 130. The joint training may be implemented based on the following method.
In some embodiments, the training samples of the booster pump analysis model may be historical patient information, a historical first venous thromboembolic risk level, and a historical first bleeding risk level, and the labels of the training samples may be historical sign anomaly probabilities corresponding to the historical patient information, the historical first venous thromboembolic risk level, and the historical first bleeding risk level.
In some embodiments, the historical patient information in the training sample is input to a base layer in the booster pump analysis model, the output of the base layer, the historical first venous thrombosis risk level and the historical first bleeding risk level in the training sample are input to a parameter analysis layer in the booster pump analysis model, the output of the parameter analysis layer and the output of the base layer are input to the probability analysis layer, or the output of the parameter analysis layer and the output of the base layer are input to a second venous thrombosis evaluation layer and a second bleeding evaluation layer in the booster pump analysis model, the output of the second venous thrombosis evaluation layer, the output of the second bleeding evaluation layer, the output of the base layer and the output of the parameter analysis layer are input to the probability analysis layer, a loss function is constructed based on the output of the probability analysis layer and a label, and parameters of the base layer, the parameter analysis layer and the probability analysis layer are iteratively updated based on the loss function, or the parameters of the base layer, the parameter analysis layer, the probability analysis layer, the second venous thrombosis evaluation layer and the second bleeding evaluation layer are iteratively updated based on the loss function until the preset conditions are satisfied, and the trained booster pump analysis model is obtained. In some embodiments, the preset condition may be that the loss function is less than a threshold, converges, or that the training period reaches a threshold.
In some embodiments, the base layer parameters of the trained booster pump analysis model are the same as the base layer parameters of the trained risk assessment model.
In some embodiments, whether to send reminding information to the user terminal may be determined based on whether the abnormal sign probability obtained by the booster pump analysis model is greater than a preset threshold or a confidence level of a booster pump working parameter result of the booster pump analysis model, where the reminding information is used to remind the user terminal to manually set the booster pump working parameter of the booster pump analysis model. In some embodiments, the confidence of the parameter analysis layer of the booster pump analysis model may be used as the confidence of the booster pump operating parameter results. The confidence level of the parameter analysis layer may refer to a confidence level of the parameter analysis layer of the pressure pump analysis model. For example, if the abnormal sign probability obtained by the booster pump analysis model is greater than a preset threshold (for example, 90%), a prompting message is sent to the user terminal, where the prompting message is used to prompt the user terminal to manually reset the current booster pump working parameter of the booster pump analysis model. For another example, if the confidence of the result of the operation parameter of the booster pump analysis model is low, a prompting message is sent to the user terminal, wherein the prompting message is used for prompting the user terminal to manually reset the current operation parameter of the booster pump analysis model.
In some embodiments, the confidence of the result of the operating parameters of the booster pump may be determined by fusing the confidence of the parameter analysis layer of the risk assessment model, the confidence of the first venous thromboembolic disorder assessment layer and the first hemorrhage assessment layer of the risk assessment model. In some embodiments, the manner of fusing may be to weight average the confidence of the parameter analysis layer of the risk assessment model, the confidence of the first venous thromboembolic assessment layer and the first hemorrhage assessment layer of the risk assessment model. For example, the confidence level of the operation parameter result of the booster pump may be obtained by performing weighted average in such a manner that the weight value of the confidence level of the parameter analysis layer is set to be maximum, the weight value of the confidence level of the first venous thromboembolic disorder assessment layer is set to be secondary, and the weight value of the confidence level of the first hemorrhage assessment layer is set to be minimum.
In some embodiments of the present disclosure, parameters of the booster pump analysis model are obtained by a combined training manner, which in some cases is advantageous in solving the problems that it is difficult to obtain a label when training the base layer alone, it is difficult to obtain a label and a training sample when training the parameter analysis layer alone, it is difficult for the second venous thromboembolic disorder assessment layer and the second hemorrhage assessment layer alone, and it is difficult to obtain a training sample when training the probability analysis layer alone; because the confidence level of the working parameter result of the booster pump is determined, the confidence level of the parameter analysis layer of the risk assessment model and the confidence level of the first venous thromboembolism assessment layer and the first hemorrhage assessment layer of the risk assessment model are fused, so that the finally determined working parameter of the booster pump is more accurate and meets the actual prevention and treatment measure needs of the patient.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.
Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.
Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (6)
1. An artificial intelligence prevention and cure system for venous thromboembolism is characterized by comprising an acquisition module, a risk grade determination module and a prevention and cure measure determination module;
The acquisition module is used for acquiring patient information, wherein the patient information comprises basic information and relevant information of treatment;
the risk level determining module is used for processing the patient information through a risk assessment model, determining a first venous thromboembolism risk level and a first bleeding risk level of the patient, and the risk assessment model is obtained through training based on training data with labels;
the prevention measure determination module is to determine a prevention measure for venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level;
wherein the control measures include controlling the patient using a booster pump, the system further including a booster pump control module;
the booster pump control module is used for processing the patient information, the first venous thromboembolic risk level and the first bleeding risk level through a booster pump analysis model, determining working parameters of the booster pump and abnormal sign probability corresponding to the patient, wherein the booster pump analysis model comprises a base layer, a parameter analysis layer, a probability analysis layer, a second venous thromboembolic risk assessment layer and a second bleeding assessment layer, and the base layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic risk assessment layer and the second bleeding assessment layer are deep neural networks;
The base layer determines patient characteristic information based on the patient information, wherein the patient characteristic information comprises one or more of patient physical condition information, patient thrombus information and patient bleeding information, the patient physical condition information is information related to physical condition of the patient, the patient thrombus information is information related to disease history of the patient thrombus, and the patient bleeding information is information related to disease history of the patient bleeding;
the parameter analysis layer determines an operating parameter of the booster pump based on the patient characteristic information, the first venous thromboembolic risk level, and the first bleeding risk level, the operating parameter including one or more of a pressure magnitude of the booster pump, an operating duration of the booster pump, and a pressurization interval of the booster pump;
the second venous thromboembolic evaluation layer determining a second venous thromboembolic risk level based on the patient characteristic information and the booster pump operating parameter;
the second bleeding evaluation layer determines a second bleeding risk level based on the patient characteristic information and the booster pump operating parameter;
the probability analysis layer determining the sign abnormality probability based on the operating parameter of the booster pump, the patient characteristic information, the second venous thromboembolic risk level, and the second bleeding risk level;
And performing combined training on the basic layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic evaluation layer and the second bleeding evaluation layer to obtain a booster pump analysis model, wherein the loss term weight of the second venous thromboembolic evaluation layer is greater than that of the second bleeding evaluation layer during the combined training.
2. The artificial intelligence control system for venous thromboembolism of claim 1, wherein the risk assessment model comprises a base layer, a first venous thromboembolism assessment layer and a first hemorrhage assessment layer,
the base layer is used for processing the patient information and determining patient characteristic information;
the first venous thromboembolic assessment layer is used for processing the patient characteristic information and determining the first venous thromboembolic risk level; and
the first hemorrhage assessment layer is configured to process the patient characteristic information and determine the first hemorrhage risk level.
3. The venous thromboembolic artificial intelligence control system of claim 1, wherein said booster pump control module is further configured to:
and when the sign abnormality probability is greater than a preset threshold value, sending reminding information to a user terminal of a target user, wherein the reminding information is used for reminding the target user to monitor the prevention and treatment process.
4. An artificial intelligence method for preventing and treating venous thromboembolism, which is characterized by comprising the following steps:
acquiring patient information, wherein the patient information comprises basic information and relevant information of treatment;
processing the patient information through a risk assessment model, and determining a first venous thromboembolism risk level and a first bleeding risk level of the patient, wherein the risk assessment model is obtained through training based on training data with labels;
determining a measure of prevention and treatment of venous thromboembolism in the patient based on the first venous thromboembolism risk level and the first bleeding risk level;
wherein the controlling means includes controlling the patient using a booster pump, the controlling the patient using a booster pump including:
processing the patient information, the first venous thromboembolic risk level and the first bleeding risk level through a booster pump analysis model, and determining working parameters of the booster pump and abnormal sign probability corresponding to the patient, wherein the booster pump analysis model comprises a base layer, a parameter analysis layer, a probability analysis layer, a second venous thromboembolic risk assessment layer and a second bleeding assessment layer, and the base layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic risk assessment layer and the second bleeding assessment layer are deep neural networks;
The base layer determines patient characteristic information based on the patient information, wherein the patient characteristic information comprises one or more of patient physical condition information, patient thrombus information and patient bleeding information, the patient physical condition information is information related to physical condition of the patient, the patient thrombus information is information related to disease history of the patient thrombus, and the patient bleeding information is information related to disease history of the patient bleeding;
the parameter analysis layer determines an operating parameter of the booster pump based on the patient characteristic information, the first venous thromboembolic risk level, and the first bleeding risk level, the operating parameter including one or more of a pressure magnitude of the booster pump, an operating duration of the booster pump, and a pressurization interval of the booster pump;
the second venous thromboembolic evaluation layer determining a second venous thromboembolic risk level based on the patient characteristic information and the booster pump operating parameter;
the second bleeding evaluation layer determines a second bleeding risk level based on the patient characteristic information and the booster pump operating parameter;
the probability analysis layer determining the sign abnormality probability based on the operating parameter of the booster pump, the patient characteristic information, the second venous thromboembolic risk level, and the second bleeding risk level;
And performing combined training on the basic layer, the parameter analysis layer, the probability analysis layer, the second venous thromboembolic evaluation layer and the second bleeding evaluation layer to obtain a booster pump analysis model, wherein the loss term weight of the second venous thromboembolic evaluation layer is greater than that of the second bleeding evaluation layer during the combined training.
5. An artificial intelligence prevention and treatment device for venous thromboembolism characterized in that said device comprises at least one processor and at least one memory;
the at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement the venous thromboembolic artificial intelligence prevention method as recited in claim 4.
6. A computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs the method of artificial intelligence for prevention and treatment of venous thromboembolism according to claim 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210630539.XA CN115274102B (en) | 2022-06-06 | 2022-06-06 | Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210630539.XA CN115274102B (en) | 2022-06-06 | 2022-06-06 | Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115274102A CN115274102A (en) | 2022-11-01 |
| CN115274102B true CN115274102B (en) | 2023-09-19 |
Family
ID=83760650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210630539.XA Active CN115274102B (en) | 2022-06-06 | 2022-06-06 | Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115274102B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006052952A2 (en) * | 2004-11-09 | 2006-05-18 | The Brigham And Women's Hospital, Inc. | System and method for determining whether to issue an alert to consider prophylaxis for a risk condition |
| CN105992552A (en) * | 2013-11-27 | 2016-10-05 | 美敦力公司 | Precision dialysis monitoring and synchonization system |
| CN107145755A (en) * | 2017-05-16 | 2017-09-08 | 陈韵岱 | Cardiovascular chronic diseases management method based on Intelligent Decision Support Technology |
| CN108498076A (en) * | 2018-04-19 | 2018-09-07 | 金华市中心医院 | Inpatient's venous thromboembolism safety management system and application |
| CN112164457A (en) * | 2020-10-23 | 2021-01-01 | 南通市第二人民医院 | Hemodialysis chamber instrument management method and device |
| CN113470825A (en) * | 2021-07-23 | 2021-10-01 | 北京惠每云科技有限公司 | Venous thromboembolism prediction system, method, equipment and medium |
| CN113571187A (en) * | 2014-11-14 | 2021-10-29 | Zoll医疗公司 | Medical premonitory event estimation system and externally worn defibrillator |
-
2022
- 2022-06-06 CN CN202210630539.XA patent/CN115274102B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006052952A2 (en) * | 2004-11-09 | 2006-05-18 | The Brigham And Women's Hospital, Inc. | System and method for determining whether to issue an alert to consider prophylaxis for a risk condition |
| CN105992552A (en) * | 2013-11-27 | 2016-10-05 | 美敦力公司 | Precision dialysis monitoring and synchonization system |
| CN113571187A (en) * | 2014-11-14 | 2021-10-29 | Zoll医疗公司 | Medical premonitory event estimation system and externally worn defibrillator |
| CN107145755A (en) * | 2017-05-16 | 2017-09-08 | 陈韵岱 | Cardiovascular chronic diseases management method based on Intelligent Decision Support Technology |
| CN108498076A (en) * | 2018-04-19 | 2018-09-07 | 金华市中心医院 | Inpatient's venous thromboembolism safety management system and application |
| CN112164457A (en) * | 2020-10-23 | 2021-01-01 | 南通市第二人民医院 | Hemodialysis chamber instrument management method and device |
| CN113470825A (en) * | 2021-07-23 | 2021-10-01 | 北京惠每云科技有限公司 | Venous thromboembolism prediction system, method, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115274102A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kaur et al. | Early stroke prediction methods for prevention of strokes | |
| JP7240789B2 (en) | Systems for screening and monitoring of encephalopathy/delirium | |
| RU2728855C2 (en) | Quantitative indicator of cardiovascular deterioration warning | |
| Hernandez-Silveira et al. | Assessment of the feasibility of an ultra-low power, wireless digital patch for the continuous ambulatory monitoring of vital signs | |
| WO2020103289A1 (en) | Method and system for analyzing hypertensive retinal blood vessel change feature data | |
| US11925487B2 (en) | System and method for assessing and monitoring the hemodynamic condition of a patient | |
| CN110827994A (en) | Myocardial infarction early warning method, device and equipment and storage medium | |
| WO2019214495A1 (en) | Electronic health record-based health management system and method for early prevention of diabetes | |
| CN111356993A (en) | Wearable device and internet of things network for predicting and managing chronic diseases | |
| US20220059208A1 (en) | Systems, methods, and devices for sleep intervention quality estimation | |
| CN111899867B (en) | Operation complication prediction and avoidance aid decision-making system based on deep learning | |
| CN112037896A (en) | Intelligent cloud nurse assistant system for hemodialysis | |
| CN106137152A (en) | Remote health detection and method of servicing and system thereof | |
| WO2020103288A1 (en) | Analysis method and system for feature data change of diabetic retinopathy fundus, and storage device | |
| CN115274102B (en) | Artificial intelligent prevention and treatment system, method, device and medium for venous thromboembolism | |
| Panagiotou et al. | A multi: modal decision making system for an ambient assisted living environment | |
| US20220254502A1 (en) | System, method and apparatus for non-invasive & non-contact monitoring of health racterstics using artificial intelligence (ai) | |
| KR102541362B1 (en) | Apparatus for predicting intradialytic hypotension using AI and method thereof | |
| CN115602312A (en) | Postoperative rehabilitation scheme generation method and device, electronic equipment and storage medium | |
| US20220375607A1 (en) | Information processing apparatus, information processing method, and program | |
| CN110867248A (en) | Postoperative monitoring method and device | |
| Valsalan et al. | Remote healthcare monitoring using expert system | |
| Dey et al. | Patient Health Observation and Analysis with Machine Learning and IoT Based in Realtime Environment | |
| US20230230693A1 (en) | Artificial intelligence-based system and method for remote treatment of patients | |
| Ikawati et al. | VidyaMedic: Smart Alert System For Continous Vital Sign Monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |