Patient state monitoring method and system

Abstract

The invention relates to the technical field of health monitoring methods, and particularly provides a patient state monitoring method and system, and the method comprises the steps: obtaining the static data of a patient, and building an initial state model between the static data and the patient state; periodically acquiring dynamic data and clinical state data of the patient according to a preset time interval, and performing iterative correction on the initial state model to form an iterative state model; monitoring and acquiring dynamic data of a patient in real time, and acquiring patient calculation state data according to the iterative state model; when the calculated state data reaches or exceeds a preset threshold value, an alarm mechanism is triggered, and an intervention signal is sent to medical personnel or medical equipment. According to the patient state monitoring method, the correlation model between the dynamic data and the patient state which are easy to obtain is established, so that the patient state is monitored in real time, the monitoring efficiency and accuracy are effectively improved, and a powerful guarantee is provided for the safety of the patient.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring methods, and in particular to a patient status monitoring method and system. Background Art

[0002] In the current medical field, the incidence of neurological diseases has increased year by year, posing a serious threat to the quality of life and life safety of patients. For the monitoring of neurological patients, the traditional method mainly relies on manual observation by medical staff and limited detection equipment. However, this monitoring method has many inconveniences and limitations. On the one hand, manual observation is difficult to achieve 24-hour uninterrupted monitoring, and it is easy to miss key information on changes in the condition; on the other hand, existing detection equipment is often complicated to operate and costly, and some equipment cannot monitor the patient's physical condition in real time.

[0003] In addition, during the course of the disease progression of neurological patients, the changes in various physical indicators have certain correlations, but the existing monitoring methods fail to fully utilize these correlations, resulting in unsatisfactory monitoring results. Therefore, how to achieve convenient, efficient and accurate status monitoring of neurological patients has become an urgent problem to be solved in the current medical field. Summary of the invention

[0004] The embodiments of the present invention provide a patient status monitoring method and system to solve the problem in the prior art that the status monitoring operation of neurology patients is complicated and real-time monitoring cannot be performed.

[0005] In view of this, a first aspect of the present invention provides a patient status monitoring method, comprising the following steps:

[0006] Obtain patient static data and establish an initial state model between the static data and the patient status;

[0007] The patient's dynamic data and clinical status data are periodically acquired at preset time intervals, and the initial state model is iteratively modified to form an iterative state model;

[0008] Monitor and obtain the patient's dynamic data in real time, and obtain the patient's calculation status data based on the iterative state model;

[0009] When the calculated status data reaches or exceeds the preset threshold, an alarm mechanism is triggered to send an intervention signal to medical personnel or medical equipment;

[0010] Among them, the static data includes multiple physiological parameters of the patient that remain stable or change within a certain time range with a range less than a preset threshold, and the dynamic data includes multiple physiological parameters of the patient that change within a certain time range with a range exceeding a preset threshold.

[0011] Optionally, the method further includes the following steps:

[0012] Establishing a state prediction model, wherein the state prediction model is used to predict the state change trend within a period of time in the future from the current time;

[0013] When the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed the preset threshold, the warning mechanism is triggered to send an intervention signal to the patient.

[0014] Optionally, obtaining patient static data and establishing an initial state model between the static data and the patient state includes:

[0015] Obtain static data, dynamic data and clinical status data of a large number of patients;

[0016] Classify patients based on the characteristics of static data;

[0017] For each patient category, a machine learning algorithm is used to establish a mapping relationship between the dynamic data and clinical status data of patients in that category to obtain a general status model;

[0018] According to the patient's static data, the patient category is determined by matching the static data in the general state model, and then the initial state model suitable for the patient is determined.

[0019] Optionally, the patient's dynamic data and clinical status data are periodically acquired at preset time intervals, and the initial state model is iteratively corrected to form an iterative state model, including:

[0020] Periodically acquiring the dynamic data and corresponding clinical status data of the monitored patient at preset time intervals;

[0021] Based on the dynamic data of the monitored patient and the initial state model, the patient's computational state data is calculated;

[0022] Comparing the calculated state data with the actual clinical state data to determine whether the difference between the two is less than a preset error threshold; if the difference is greater than the preset error threshold, adjusting the parameters of the initial state model according to the comparison result to reduce the difference between the calculated state data and the clinical state data;

[0023] In the next preset cycle, the state model corrected in the previous cycle is used to obtain the calculated state data, and the comparison and correction process is repeated;

[0024] The above steps are repeated until the difference between the calculated state data and the clinical state data in a plurality of consecutive preset cycles is less than a preset error threshold, thereby forming an iterative state model.

[0025] Optionally, each preset cycle includes acquiring dynamic data and corresponding clinical status data of one or more groups of patients.

[0026] Optionally, a state prediction model is established, where the state prediction model is used to predict the state change trend within a period of time from the current time, including:

[0027] Obtain relevant historical data, which includes dynamic data and status data at different time points;

[0028] Preprocess historical data to eliminate noise and outliers in the data;

[0029] Train a state prediction model using a prediction model algorithm based on historical data;

[0030] Compare the state change trend predicted by the state prediction model with the actual change trend, and adjust the state prediction model;

[0031] When the predicted state model meets a preset standard, the state prediction model is determined.

[0032] Optionally, the prediction model algorithm includes at least time series analysis, a machine learning algorithm or a deep learning network.

[0033] Optionally, the state prediction model includes at least two prediction intervals, each interval corresponds to a different future time range, and the prediction accuracy of the time interval closer to the current time is higher than that of the time interval farther away.

[0034] Optionally, when the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold, a warning mechanism is triggered to send an intervention signal to the patient, including:

[0035] When the predicted state change trend of the first interval closest to the current time obtained based on the state prediction model causes the state data to reach or exceed the preset threshold in the area, an emergency intervention warning is issued to the patient;

[0036] When the predicted state change trend in other intervals obtained based on the state prediction model causes the state data to reach or exceed the preset threshold within the interval, a general intervention warning is issued to the patient.

[0037] A second aspect of the present invention provides a patient status monitoring system, which is used to implement the above-mentioned patient status monitoring method, comprising:

[0038] Data collection module, used to obtain static and dynamic data of patients;

[0039] A state model building module is used to build an initial state model according to static data, and iteratively modify the initial state model according to dynamic data and patient clinical state data to obtain an iterative state model;

[0040] A prediction model building module is used to build a state prediction model that predicts the state change trend within a period of time in the future from the current time;

[0041] The response module is used to trigger an alarm or warning mechanism and send an intervention signal to medical personnel, medical equipment or patients when the calculated state data obtained by the state model construction module reaches or exceeds a preset threshold, or when the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold.

[0042] It can be seen from the above technical solutions that the embodiments of the present invention have the following beneficial effects:

[0043] The present invention proposes an innovative patient status monitoring method, which constructs an initial state model by collecting static data of patients, and regularly updates the dynamic data and clinical status data of patients at predetermined time intervals, so as to continuously iterate and optimize the model. The method can create a customized monitoring model for the specific situation of each patient, ensuring the accuracy of the monitoring results. By real-time monitoring and calculating the dynamic data of patients, the present invention can continuously track the health status of patients and provide patients and their medical staff with instant and coherent disease information. Once the monitored status data reaches or exceeds the established threshold, the system will automatically start the alarm mechanism and send an alarm to medical personnel or medical equipment, significantly speeding up the response speed to the patient's sudden condition, facilitating timely treatment measures, thereby reducing the risk of patients. The patient status monitoring method of the present invention realizes real-time monitoring of the patient's status by establishing an association model between dynamic data that is easy to obtain and the patient's status, effectively improving the efficiency and accuracy of monitoring, and providing a strong guarantee for the safety of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some of the implementations recorded in this application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0045] Figure 1 This is a flow chart of a patient status monitoring method according to Embodiment 1 of the present invention;

[0046] Figure 2 This is a flow chart of a patient status monitoring method according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0047] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0048] Example 1

[0049] like Figure 1 As shown, the patient status monitoring method provided by the embodiment of the present invention includes the following steps:

[0050] S10: Obtain patient static data and establish an initial state model between the static data and the patient state.

[0051] Specifically, static data includes multiple physiological parameters of patients that remain stable or change within a certain time range and are less than a preset threshold, such as age, gender, weight, height, medical history, etc.; dynamic data includes multiple physiological parameters of patients that change within a certain time range and exceed a preset threshold, such as heart rate, blood pressure, body temperature, respiratory rate, blood oxygen saturation, etc. Of course, the above distance between static data and dynamic data is only partial, not complete, and all patient data that meets the above definition of static data and dynamic data are included.

[0052] S20: Periodically obtain the patient's dynamic data and clinical status data at preset time intervals, iteratively modify the initial state model, and form an iterative state model.

[0053] Specifically, the initial state model is initially established based on the patient's static data, which may not be completely suitable for the patient and has low accuracy. By periodically acquiring the patient's dynamic data and clinical status data, the model is constantly revised and iterated, and the model will gradually become more accurate and personalized, and can better predict and reflect the patient's health status. This iterative process is continuous, and the model may be fine-tuned after each data collection, so that the monitoring results are more accurate and reliable.

[0054] Clinical status data is obtained by quantitatively evaluating clinical monitoring data such as doctors' or nurses' observation records, patients' symptom descriptions, and the effects of drug treatment, and can be used to compare and analyze patients' conditions.

[0055] S30: Monitor and obtain the patient's dynamic data in real time, and obtain the patient's calculation status data according to the iterative state model.

[0056] Specifically, after obtaining an iterative state model that meets the accuracy requirements, the accurate patient status can be obtained through the model according to the patient's real-time dynamic data, providing a reference for medical staff to help them understand the patient's health status more timely. Of course, step S20 will be performed in the process to continuously optimize the model to ensure the accuracy of the model.

[0057] S40: When the calculated status data reaches or exceeds a preset threshold, an alarm mechanism is triggered to send an intervention signal to medical personnel or medical equipment.

[0058] It can significantly speed up the response to patients' emergencies, facilitate timely treatment measures, and thus reduce the risk of patients

[0059] In some embodiments, step S10 obtains patient static data and establishes an initial state model between the static data and the patient state, including the following steps:

[0060] S11: Obtain static data, dynamic data and clinical status data of a large number of patients.

[0061] A large amount of patient data can be collected from multiple sources, including but not limited to electronic health records, laboratory test results, medical imaging reports, patient demographic information, etc.

[0062] S12: Classify patients according to the characteristics of static data.

[0063] Data mining technology can be used to extract and analyze features of the collected static data. Based on these features, patients can be divided into several categories, such as age, gender, disease type, etc. Classification can better understand the physiological and pathological characteristics of patients in different categories, laying the foundation for establishing an accurate model.

[0064] S13 For each patient category, a machine learning algorithm is used to establish a mapping relationship between the dynamic data of patients in this category and the clinical status data to obtain a general status model.

[0065] Machine learning algorithms, such as random forests, support vector machines, neural networks, etc., can be used to analyze the dynamic data and clinical status data in each patient category. Through the training data set, the algorithm learns the complex relationship between dynamic data and clinical status and establishes a mapping model. The model of each patient category constructed in this way is basically universal for patients within this type, and it can represent most patients in this category.

[0066] S14: According to the static data of the patient, the static data is matched in the general state model to determine the patient category, and then determine the initial state model suitable for the patient.

[0067] The patient's static data is compared with the classification criteria in the general state model to determine the specific category to which the patient belongs. Once the patient category is determined, the corresponding general state model is selected as the patient's initial state model for subsequent monitoring.

[0068] In some embodiments, step S20 periodically acquires the patient's dynamic data and clinical status data at a preset time interval, iteratively modifies the initial state model, and forms an iterative state model, including:

[0069] S21: Periodically acquiring the dynamic data and corresponding clinical status data of the monitored patient at preset time intervals.

[0070] The monitoring system will automatically collect the patient's dynamic data, such as heart rate, blood pressure, respiratory rate, etc., at pre-set time intervals, such as every hour, every half hour or every day. At the same time, the system will also collect clinical status data corresponding to these dynamic data, which may include doctors' evaluations, laboratory test results or patients' self-reports.

[0071] S22: Based on the dynamic data of the monitored patient and the initial state model, the patient's calculation state data is calculated.

[0072] S23: Compare the calculated state data with the actual clinical state data to determine whether the difference between the two is less than a preset error threshold; if the difference is greater than the preset error threshold, adjust the parameters of the initial state model according to the comparison result to reduce the difference between the calculated state data and the clinical state data.

[0073] The patient status data calculated according to the model is compared with the actual observed clinical status data. By comparing, the difference between the calculated value and the actual value can be determined to evaluate the accuracy of the model prediction. If the difference is greater than the preset error threshold, it indicates that the prediction accuracy of the model is insufficient and further adjustment is required. The adjustment process may include adjusting model parameters, retraining the model, or introducing new data features.

[0074] S24: In the next preset cycle, the state model corrected in the previous cycle is used to obtain the calculated state data, and the comparison and correction process is repeated.

[0075] S25: Repeat the above steps until the difference between the calculated state data and the clinical state data in a plurality of consecutive preset cycles is less than a preset error threshold, thereby forming an iterative state model.

[0076] Through continuous iterative modification, the difference between the calculated state data and the clinical state data in multiple consecutive preset cycles is less than the preset error threshold, thus forming an iterative state model. This process ensures that the model can continuously adapt to individual changes of patients over time and with the accumulation of data, and improve the accuracy and reliability of monitoring. Ultimately, the iterative state model can provide patients with more personalized and accurate health status monitoring.

[0077] Optionally, each preset cycle includes acquiring dynamic data and corresponding clinical status data of one or more groups of patients.

[0078] At each preset cycle, the system collects a set of dynamic data for a patient, which usually includes data points collected continuously at a specific time point or within a short period of time. Correspondingly, clinical status data is also collected at the same time point or time period. This method is suitable for monitoring patients whose conditions do not change quickly or require regular checks.

[0079] In some cases, in order to more accurately understand the patient's condition, it may be necessary to obtain multiple sets of data in each preset period. Multiple sets of data can be collected at different time points (for example, morning, noon, and evening), or collected at the same time point but under different conditions (for example, when resting, after activity). This can provide a more comprehensive understanding of the patient's health status, especially when the condition changes rapidly or requires detailed monitoring.

[0080] Example 2

[0081] like Figure 2 As shown, the patient status monitoring method provided by the embodiment of the present invention includes the following steps:

[0082] S10: Obtain patient static data and establish an initial state model between the static data and the patient state.

[0083] S20: Periodically obtain the patient's dynamic data and clinical status data at preset time intervals, iteratively modify the initial state model, and form an iterative state model.

[0084] S30 monitors and obtains the patient's dynamic data in real time, and obtains the patient's calculation status data according to the iterative state model.

[0085] S40: When the calculated status data reaches or exceeds a preset threshold, an alarm mechanism is triggered to send an intervention signal to medical personnel or medical equipment.

[0086] S50: Establishing a state prediction model, which is used to predict the state change trend within a period of time in the future from the current time;

[0087] S60: When the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold, a warning mechanism is triggered to send an intervention signal to the patient.

[0088] By establishing a patient status prediction model, the patient status monitoring method can not only monitor the patient's current status in real time, but also predict and warn of potential health risks, thereby providing patients with more comprehensive and forward-looking health care. This prediction and warning function is of great value for chronic disease management, acute disease prevention, and improving patients' self-management capabilities.

[0089] For the description of S10-S20, reference may be made to the description in Implementation 1.

[0090] In some embodiments, step S50 establishes a state prediction model, which is used to predict the state change trend within a period of time from the current time, including:

[0091] S51: Acquire relevant historical data, which includes dynamic data and status data at different time points;

[0092] S52: preprocess historical data to eliminate noise and outliers in the data;

[0093] S53: training a state prediction model using a prediction model algorithm based on historical data;

[0094] S54: comparing the state change trend predicted by the state prediction model and the actual change trend, and adjusting the state prediction model;

[0095] S55: When the predicted state model meets the preset standard, determine the state prediction model.

[0096] Optionally, the prediction model algorithm includes at least time series analysis, a machine learning algorithm, or a deep learning network.

[0097] Optionally, the state prediction model includes at least two prediction intervals, each interval corresponds to a different future time range, and the prediction accuracy of the time interval closer to the current time is higher than that of the time interval farther away. For example, the state prediction model is divided into short-term and long-term, and the short-term prediction intervals are usually more accurate because they are closer to the current time and have lower uncertainty. The long-term prediction interval may contain more uncertainty, so the prediction accuracy may be lower.

[0098] Optionally, when the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold, a warning mechanism is triggered to send an intervention signal to the patient, including:

[0099] When the predicted state change trend of the first interval closest to the current time obtained based on the state prediction model causes the state data to reach or exceed the preset threshold in the area, an emergency intervention warning is issued to the patient;

[0100] When the predicted state change trend in other intervals obtained based on the state prediction model causes the state data to reach or exceed the preset threshold within the interval, a general intervention warning is issued to the patient.

[0101] By establishing a graded warning mechanism, patients and medical staff can decide on appropriate intervention measures based on the urgency of the warning, thereby more effectively managing the patient's health status.

[0102] The embodiment of the present invention further provides a patient status monitoring system, which is used to implement the above-mentioned patient status monitoring method, including:

[0103] Data collection module, used to obtain static and dynamic data of patients;

[0104] A state model building module is used to build an initial state model according to static data, and iteratively modify the initial state model according to dynamic data and patient clinical state data to obtain an iterative state model;

[0105] A prediction model building module is used to build a state prediction model that predicts the state change trend within a period of time in the future from the current time;

[0106] The response module is used to trigger an alarm or warning mechanism and send an intervention signal to medical personnel, medical equipment or patients when the calculated state data obtained by the state model construction module reaches or exceeds a preset threshold, or when the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold.

[0107] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A patient status monitoring method, characterized in that: The following steps are involved: Obtain patient static data and establish an initial state model between the static data and the patient status; The patient's dynamic data and clinical status data are periodically acquired at preset time intervals, and the initial state model is iteratively modified to form an iterative state model; Monitor and obtain the patient's dynamic data in real time, and obtain the patient's calculation status data based on the iterative state model; When the calculated status data reaches or exceeds the preset threshold, an alarm mechanism is triggered to send an intervention signal to medical personnel or medical equipment; Among them, the static data includes multiple physiological parameters of the patient that remain stable or change within a certain time range with a range less than a preset threshold, and the dynamic data includes multiple physiological parameters of the patient that change within a certain time range with a range exceeding a preset threshold.

2. A patient status monitoring method according to claim 1, characterized in that: The following steps are also included: Establishing a state prediction model, wherein the state prediction model is used to predict the state change trend within a period of time in the future from the current time; When the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed the preset threshold, the warning mechanism is triggered to send an intervention signal to the patient.

3. A patient status monitoring method according to claim 1 or 2, characterized in that: Obtain patient static data and establish an initial state model between static data and patient status, including: Obtain static data, dynamic data and clinical status data of a large number of patients; Classify patients based on the characteristics of static data; For each patient category, a machine learning algorithm is used to establish a mapping relationship between the dynamic data and clinical status data of patients in that category to obtain a general status model; According to the patient's static data, the patient category is determined by matching the static data in the general state model, and then the initial state model suitable for the patient is determined.

4. A patient status monitoring method according to claim 1 or 2, characterized in that: The patient's dynamic data and clinical status data are periodically acquired at preset time intervals, and the initial state model is iteratively modified to form an iterative state model, including: Periodically acquiring the dynamic data and corresponding clinical status data of the monitored patient at preset time intervals; Based on the dynamic data of the monitored patient and the initial state model, the patient's computational state data is calculated; Comparing the calculated state data with the actual clinical state data to determine whether the difference between the two is less than a preset error threshold; if the difference is greater than the preset error threshold, adjusting the parameters of the initial state model according to the comparison result to reduce the difference between the calculated state data and the clinical state data; In the next preset cycle, the state model corrected in the previous cycle is used to obtain the calculated state data, and the comparison and correction process is repeated; The above steps are repeated until the difference between the calculated state data and the clinical state data in a plurality of consecutive preset cycles is less than a preset error threshold, thereby forming an iterative state model.

5. A patient status monitoring method according to claim 4, characterized in that: Each preset cycle includes acquiring dynamic data and corresponding clinical status data of one or more groups of patients.

6. A patient status monitoring method according to claim 2, characterized in that: Establish a state prediction model, which is used to predict the state change trend in a period of time from the current time, including: Obtain relevant historical data, which includes dynamic data and status data at different time points; Preprocess historical data to eliminate noise and outliers in the data; Train a state prediction model using a prediction model algorithm based on historical data; Compare the state change trend predicted by the state prediction model with the actual change trend, and adjust the state prediction model; When the predicted state model meets a preset standard, the state prediction model is determined.

7. A patient status monitoring method according to claim 6, characterized in that: The prediction model algorithm includes at least time series analysis, machine learning algorithm or deep learning network.

8. A patient status monitoring method according to claim 2, characterized in that: The state prediction model includes at least two prediction intervals, each interval corresponds to a different future time range, and the prediction accuracy of the time interval closer to the current time is higher than that of the time interval farther away.

9. A patient status monitoring method according to claim 8, characterized in that: When the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed the preset threshold, the warning mechanism is triggered to send an intervention signal to the patient, including: When the predicted state change trend of the first interval closest to the current time obtained based on the state prediction model causes the state data to reach or exceed the preset threshold in the area, an emergency intervention warning is issued to the patient; When the predicted state change trend in other intervals obtained based on the state prediction model causes the state data to reach or exceed the preset threshold within the interval, a general intervention warning is issued to the patient.

10. A patient status monitoring system, characterized in that: A method for monitoring the patient status according to any one of claims 1 to 9, comprising: Data collection module, used to obtain static and dynamic data of patients; A state model building module is used to build an initial state model according to static data, and iteratively modify the initial state model according to dynamic data and patient clinical state data to obtain an iterative state model; A prediction model building module is used to build a state prediction model that predicts the state change trend within a period of time in the future from the current time; The response module is used to trigger an alarm or warning mechanism and send an intervention signal to medical personnel, medical equipment or patients when the calculated state data obtained by the state model construction module reaches or exceeds a preset threshold, or when the predicted state change trend obtained based on the state prediction model causes the state data to reach or exceed a preset threshold.

Images