Clinical Patient Health Management Methods and Systems Based on Smart Healthcare

Abstract

This invention discloses a clinical patient health management method and system based on smart healthcare. It calculates the degree of influence of factors such as abnormal data transmission from devices, patient medication reactions, and patient emotional fluctuations on historical data based on the stability of the patient's historical vital sign data and the correlation between changes in different vital sign data. The influence weight of each historical data point in the prediction model is then adjusted accordingly. This effectively reduces the impact of historical data, which does not reflect the patient's true health condition, on the prediction results, improving the accuracy of the predictions. This allows doctors to take timely and effective measures based on the patient's current health condition. This method can predict abnormalities in the patient's vital sign data, offering superior timeliness.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology and relates to a clinical patient health management method and system based on smart healthcare. Background Technology

[0002] Clinical patient health management refers to the management process that dynamically monitors, assesses risks, and provides personalized interventions for patients' physiological status, disease progression, treatment adherence, and health behaviors throughout the entire process of patient visits, treatment, hospitalization, rehabilitation, and discharge follow-up. This is based on multi-source health data and clinical information, combined with modern information technology. With the development of science and technology, clinical patient health management has gradually become an important part of hospital management, playing a crucial role in improving treatment efficiency, enhancing patient prognosis, and reducing the incidence of complications.

[0003] Current clinical patient health management methods mainly rely on electronic medical record (EMR) systems, clinical pathways, remote monitoring devices, and manual follow-up, primarily for risk warnings of postoperative recovery patients, critically ill patients, and patients with chronic diseases. However, existing management methods are mostly rule-driven, lacking analysis of individual patient differences and disease evolution characteristics, making it difficult to provide effective personalized intervention strategies. Furthermore, existing methods have low data integration, and some systems increase the burden on medical staff, resulting in insufficient practicality and widespread adoption. Summary of the Invention

[0004] The purpose of this invention is to address the problem that existing health management methods lack analysis and judgment of the evolution of patients' diseases and only issue alarms after abnormalities in patients' vital signs data, resulting in poor timeliness. The invention provides a clinical patient health management method and system based on smart healthcare.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] A clinical patient health management method based on smart healthcare includes the following steps:

[0007] Obtain real-time monitoring data of the patient's vital signs;

[0008] Based on real-time monitoring data of the patient's vital signs, the instability of the patient's vital signs data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotions are calculated.

[0009] The reliability of the data at each monitoring time point is calculated based on the degree of instability at each monitoring time point and the possibility that the data at each monitoring time point is affected by the patient's emotions.

[0010] Obtain the prediction model, adjust the parameters of the prediction model based on the reliability of the data at each monitoring time, and obtain the adjusted prediction model;

[0011] The patient's vital signs monitoring data are used as input to the revised prediction model to obtain the predicted values ​​of the patient's vital signs data. The current health status of the patient is analyzed based on the predicted values ​​of the patient's vital signs data, and corresponding measures are taken based on the health status.

[0012] A further improvement of the present invention is that:

[0013] The calculation of the instability of the patient's vital signs data at each monitoring time includes:

[0014] Calculate the probability that the data at each monitoring time point is abnormal equipment data:

[0015]

[0016] in, This indicates the probability that the data at the i-th monitoring time in the s-th type of vital sign data is abnormal equipment data. This represents the number of monitoring times contained within the time period corresponding to the i-th monitoring time. Including the i-th monitoring time, This represents the data value at the j-th monitoring time within the time period corresponding to the i-th monitoring time in the s-th type of vital sign data. This indicates the trend of the vital sign data between the (j+1)th monitoring time and the jth monitoring time. This indicates the degree of fluctuation of the s-th type of vital sign data within adjacent monitoring periods. That is, if the fluctuation of this vital sign data is small, the data at different monitoring times will show the same trend. Represents the normalization function;

[0017] Calculate the probability of abnormal drug response at each monitoring time point:

[0018]

[0019] in, This indicates the probability of an abnormal drug response in the data at the i-th monitoring time point within the s-th type of vital signs data. This represents the monitored value of the data at the i-th monitoring time in the s-th type of vital sign data. This represents the fitted value of the i-th monitoring time on its corresponding fitted curve. Represents the normalization function;

[0020] Based on the probability that the data at each monitoring time point is from equipment malfunction and the probability that the data at each monitoring time point shows abnormal drug response, the degree of instability of the patient's vital signs data at each monitoring time point is calculated:

[0021]

[0022] in, This indicates the degree of instability of the data at the i-th monitoring time in the s-th type of vital sign data. This indicates the probability that the data at the i-th monitoring time in the s-th type of vital sign data is abnormal equipment data. This indicates the probability of an abnormal drug response in the data at the i-th monitoring time point within the s-th type of vital signs data.

[0023] The calculated probability of data being affected by the patient's emotions at each monitoring time point includes:

[0024]

[0025] in, This indicates the probability that the data at the i-th monitoring time point is affected by the patient's emotions. This indicates the total number of patient vital signs categories monitored. The number of vital sign categories other than category s. This represents the total number of monitoring times contained within the time period of the i-th monitoring time. This represents the difference between the s-th type of vital sign data at the j-th monitoring time and the previous monitoring time within the time period of the ith monitoring time. This represents the ratio of the change in the s-th type of vital sign data to the change in the t-th type of vital sign data at the j-th monitoring time. This represents the absolute value of the difference between the ratios of the changes in the s-th type of vital sign data and the t-th type of vital sign data at adjacent monitoring times. The smaller the absolute value of the difference between the ratio of the changes in the s-th type of vital sign data and the t-th type of vital sign data at adjacent monitoring times, the more closely these two types of vital sign data change according to a fixed proportional relationship, indicating a stronger correlation between them. This represents the normalization function.

[0026] The calculation of the reliability of data at each monitoring time point includes:

[0027]

[0028] in, This indicates the reliability of the data at the i-th monitoring time point in the s-th type of vital sign data. This indicates the degree of instability of the data at the i-th monitoring time in the s-th type of vital sign data. This indicates the probability that the data at the i-th monitoring time point is affected by the patient's emotions. This represents the normalization function.

[0029] The parameters of the prediction model, which are based on the reliability of data at each monitoring time, include:

[0030]

[0031] in, This represents the adjusted parameter value at the i-th monitoring time in the s-th type of vital sign data. This represents the original parameter value. This represents the reliability of the data at the i-th monitoring time in the s-th type of vital sign data.

[0032] The prediction model is an ARIMA model, based on the obtained adjusted parameter values. The ARIMA model is modified and optimized to obtain the modified prediction model ARIMA.

[0033] The process of analyzing the patient's current health status based on predicted values ​​of vital sign data and taking corresponding measures based on that health status includes:

[0034] Set monitoring thresholds for each vital sign data. If the predicted value exceeds the set threshold, the current vital sign data is determined to be abnormal, and corresponding measures are taken based on the current abnormal data.

[0035] A clinical patient health management system based on smart healthcare, comprising:

[0036] The data acquisition module is used to acquire real-time monitoring data of the patient's vital signs;

[0037] The first data calculation module is used to calculate the instability of the patient's vital signs data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotions, based on the real-time monitoring data of the patient's vital signs.

[0038] The second data calculation module is used to calculate the reliability of the data at each monitoring time based on the degree of instability at each monitoring time and the possibility that the data at each monitoring time is affected by the patient's emotions.

[0039] The third data calculation module is used to obtain the prediction model, correct the parameters of the prediction model based on the reliability of the data at each monitoring time, and obtain the corrected prediction model.

[0040] The fourth data calculation module is used to take the patient's vital sign monitoring data as input to the corrected prediction model, obtain the predicted value of the patient's vital sign data, analyze the current health status of the patient based on the predicted value of the patient's vital sign data, and take corresponding measures based on the health status.

[0041] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described in this invention.

[0042] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of any of the methods described in this invention.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] This invention discloses a clinical patient health management method based on smart healthcare. It calculates the degree of influence of factors such as abnormal data transmission from devices, patient medication reactions, and patient emotional fluctuations on historical data based on the stability of the patient's historical vital sign data and the correlation between changes in different vital sign data. The method then adjusts the influence weight of each historical data point in the prediction model accordingly. This effectively reduces the impact of historical data, which does not reflect the patient's true health condition, on the prediction results, improving the accuracy of the predictions. This allows doctors to take timely and effective measures based on the patient's current health condition. Furthermore, this method can predict abnormalities in the patient's vital sign data, offering superior timeliness. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of a clinical patient health management method based on smart healthcare, as disclosed in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0048] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0049] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0050] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0051] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0052] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0053] The present invention will now be described in further detail with reference to the accompanying drawings:

[0054] See Figure 1 This invention discloses a clinical patient health management method based on smart healthcare. This method utilizes historical monitoring data of clinical patients to predict their vital signs and provides targeted early warnings based on the degree of abnormality in the predicted values ​​of various vital signs and the reflection of different abnormalities on the patient's health status. This effectively improves the timeliness of patient risk warnings. Furthermore, it provides different warning information for different abnormal manifestations, greatly reducing the management burden on medical staff.

[0055] This method first continuously monitors the vital signs data of clinical patients, then predicts the patient's health status based on changes in historical monitoring data, and finally takes corresponding treatment measures based on abnormalities in the predicted values ​​of various vital signs data. Specifically, it includes the following steps:

[0056] Step 1: Continuously monitor the vital signs data of clinical patients using clinical monitoring instruments.

[0057] Specifically, it includes:

[0058] Clinical patient health management primarily targets critically ill and postoperative patients. These patients have unstable health conditions and are prone to complications and other abnormalities, thus requiring continuous monitoring of their vital signs. This method utilizes a bedside monitor to track vital signs, including heart rate, respiratory rate, blood pressure, and blood oxygen saturation. The monitoring instrument acquires relevant patient data every second.

[0059] Step 2: Based on the patient's historical monitoring data, use the ARIMA model to calculate the predicted values ​​of the patient's vital signs.

[0060] For critically ill patients, postoperative patients, and other clinical patients requiring continuous monitoring, ensuring stable vital signs data and maintaining them within the normal range is a crucial treatment objective. Therefore, when a patient's health is relatively good, all vital signs should be relatively stable and within abnormal thresholds. Thus, predicting the presence of abnormalities in a patient's vital signs data allows for timely intervention to address potential risks. However, a patient's vital signs data may fluctuate significantly due to equipment malfunctions, medication use, and the patient's emotional state. These fluctuations are temporary and do not reflect the patient's true health condition, affecting the accuracy of predicted vital sign data. Therefore, based on the stability of the data at each monitoring moment and the likelihood of emotional influence, the reliability of each monitoring data point is calculated, and the weight of each data point's impact on the predicted value is adjusted accordingly.

[0061] Furthermore, this invention predicts a patient's health status by analyzing the patient's historical vital sign monitoring data, specifically including the following steps:

[0062] Step 2.1: Calculate the stability of each vital sign data within its respective time period based on the fluctuations of the patient's various vital signs.

[0063] Step 2.2: Based on the correlation of fluctuations in different vital signs data of the patient within the same time period, calculate the probability that the data at each monitoring time point is affected by the patient's emotions.

[0064] Step 2.3: Calculate the reliability of each monitoring data point based on its stability and the likelihood of being affected by emotions, and calculate the predicted values ​​of the patient's vital signs data.

[0065] The details are as follows:

[0066] Step 2.1: Calculate the stability of each vital sign data within its respective time period based on the fluctuations of the patient's various vital signs.

[0067] A patient's vital signs should be relatively stable under normal conditions, and even during recovery, they should show a relatively gradual trend. However, when monitoring equipment is unstable, data transmission errors occur, or the patient experiences adverse drug reactions, the patient's vital signs may exhibit brief but dramatic fluctuations. In such cases, the monitoring data may not reflect the patient's true health condition and may interfere with health predictions. Therefore, it is necessary to calculate the stability of each vital sign data point based on its fluctuations.

[0068] Specifically, it includes:

[0069] First, data errors caused by anomalies during equipment monitoring and transmission often only affect data from a few monitoring moments. Therefore, by observing whether each monitoring data point exhibits significant fluctuations within a short period, the unstable data caused by equipment anomalies can be identified. Thus, for each monitoring moment, the probability that the data from that moment is from an equipment anomaly is calculated based on the fluctuation levels of the data from the 10 nearest monitoring moments.

[0070]

[0071] in, This indicates the probability that the data at the i-th monitoring time in the s-th type of vital sign data is abnormal equipment data. This indicates the number of monitoring times contained within the time period corresponding to the i-th monitoring time ( (including the i-th monitoring time). This represents the data value at the j-th monitoring time within the time period corresponding to the i-th monitoring time in the s-th type of vital sign data. This indicates the trend of the vital sign data between the (j+1)th monitoring time and the jth monitoring time. This indicates the degree of fluctuation of the s-th type of vital sign data within adjacent monitoring periods. In other words, if the degree of fluctuation of the vital sign data is small, the data at different monitoring times should show the same trend. This represents the normalization function.

[0072] Furthermore, when patients use short-acting medications, their vital signs may show a significant increase or decrease within minutes. During this time, the monitored data may exhibit a consistent trend, but will quickly recover after discontinuation of the medication. Therefore, this type of data should also be considered unstable and cannot accurately reflect the patient's health condition. Because vital signs change significantly during drug response and recovery, based on the drug response time, monitoring data within a corresponding 10-minute period (empirical value) is obtained at each monitoring moment as the center time. Each type of vital sign data is then plotted as a "time-monitoring value" coordinate graph. The least squares method is used to fit the graph, and the probability of an abnormal drug response at the center monitoring moment is calculated based on the difference between the monitoring value at the center monitoring moment and the fitted value on the curve.

[0073]

[0074] in, This indicates the probability of an abnormal drug response in the data at the i-th monitoring time point within the s-th type of vital signs data. This represents the monitored value of the data at the i-th monitoring time in the s-th type of vital sign data. This represents the fitted value of the i-th monitoring time on its corresponding fitted curve. This represents the normalization function.

[0075] Furthermore, based on the probability that the monitoring data is abnormal equipment data and the probability of abnormal drug reactions, the degree of instability of each monitoring data is calculated.

[0076]

[0077] in, This indicates the degree of instability of the data at the i-th monitoring time in the s-th type of vital sign data. This indicates the probability that the data at the i-th monitoring time in the s-th type of vital sign data is abnormal equipment data. This indicates the probability of an abnormal drug response in the data at the i-th monitoring time point within the s-th type of vital signs data.

[0078] Step 2.2. Based on the correlation of fluctuations in different vital signs data of the patient within the same time period, calculate the probability that the data at each monitoring moment is affected by the patient's emotions.

[0079] Because a patient's vital signs are significantly affected by their emotions—for example, when a patient is emotionally agitated, their heart rate, respiratory rate, and blood pressure may remain at consistently high levels—but patients are not always in a state of emotional distress, the data influenced by patient emotions are less effective in predicting a patient's health condition. Drug treatment for patients is usually targeted at only one aspect, meaning the correlation between different vital signs during treatment is relatively weak. However, emotional changes often have a comprehensive impact on patients; that is, when a patient's emotions change, multiple vital signs may simultaneously experience significant changes. Therefore, based on the correlation between changes in different vital signs, the probability of data being affected by the patient's emotions at each monitoring time point is calculated.

[0080] Specifically, it includes:

[0081] First, because emotional changes respond quickly to vital sign data, for each monitoring moment, monitoring data within one minute of that moment is obtained to calculate the likelihood of the data being affected by the patient's emotions. Since different vital sign data have different ranges and units, they cannot be directly compared; therefore, all monitoring data needs to be normalized. The data discussed in this step below refers to the normalized data values.

[0082] Because changes in a patient's emotions can cause correlated changes in multiple vital signs, we first calculate the change in each type of vital sign data at each monitoring time point within the monitoring period compared to the previous monitoring time point. (The difference between the ith monitoring time and the s-th type of vital sign data from the previous monitoring time). If the changes between different vital sign data are correlated, then the changes in different vital sign data should always follow a fixed ratio. Therefore, the probability that the data at each monitoring time is affected by the patient's emotions is calculated:

[0083]

[0084] in, This indicates the probability that the data at the i-th monitoring time point is affected by the patient's emotions. This indicates the total number of patient vital signs categories monitored. The number of vital sign categories other than category s. This represents the total number of monitoring times contained within the time period (1 minute) of the i-th monitoring time. This represents the difference between the s-th type of vital sign data at the j-th monitoring time and the previous monitoring time within the time period of the ith monitoring time. This represents the ratio of the change in the s-th type of vital sign data to the change in the t-th type of vital sign data at the j-th monitoring time. This represents the absolute value of the difference between the ratios of the changes in the s-th type of vital sign data and the t-th type of vital sign data at adjacent monitoring times. The smaller the absolute value of the difference between the changes in the s-th type of vital signs data and the t-th type of vital signs data at adjacent monitoring times, the more closely the two types of vital signs data change according to a fixed proportional relationship, that is, the stronger the correlation between the two types of vital signs data. This represents the normalization function.

[0085] Step 2.3. Calculate the reliability of each monitoring data point based on its stability and the likelihood of being influenced by emotions, and calculate the predicted values ​​for the patient's vital signs.

[0086] Based on the above steps, the stability of the monitored data and the stability of the patient's emotional state during monitoring are important factors affecting the responsiveness of vital sign data to the patient's health status. Unstable data and data significantly influenced by the patient's emotions will lead to a decrease in the accuracy of the predicted values ​​of the patient's vital signs, that is, the reliability of these data in the prediction process is low. Therefore, combining the stability of each monitoring data point and the possibility of emotional influence, the reliability of each monitoring data point is calculated, and the parameters in the ARIMA model are adjusted accordingly.

[0087]

[0088] in, This indicates the reliability of the data at the i-th monitoring time point in the s-th type of vital sign data. This indicates the degree of instability of the data at the i-th monitoring time in the s-th type of vital sign data. This indicates the probability that the data at the i-th monitoring time point is affected by the patient's emotions. This represents the normalization function.

[0089] Furthermore, the autoregressive coefficients in the ARIMA model are obtained using maximum likelihood estimation. Then, the parameter is adjusted based on the reliability of each historical data point.

[0090]

[0091] in, This represents the adjusted parameter value at the i-th monitoring time in the s-th type of vital sign data. This represents the original parameter value. This represents the reliability of the data at the i-th monitoring time in the s-th type of vital sign data.

[0092] Furthermore, the patient's historical vital sign monitoring data were substituted into the adjusted parameters of the ARIMA model to obtain the predicted value of each vital sign data.

[0093] Step 3: Analyze the patient's current health status and implement corresponding measures based on the degree of abnormality in the predicted values ​​of the patient's vital signs data.

[0094] Specifically, it includes:

[0095] Set thresholds for each vital sign monitoring data;

[0096] The adjusted predicted values ​​of patient vital signs were compared with the monitoring thresholds for each vital sign:

[0097] When a predicted value exceeds a threshold warning line, the predicted value of that vital sign is considered to have an abnormal risk. By comprehensively considering the abnormal risk of multiple predicted values, since the predicted value represents the development of the patient's subsequent health status monitoring data, the patient's potential future health status risks can be judged based on the predicted value, thereby allowing for early intervention in clinical treatment and improving the timeliness of patient health management.

[0098] The method disclosed in this invention calculates the degree of influence of historical data on factors such as abnormal data transmission from the device, patient medication response, and patient emotional fluctuations based on the stability of the patient's historical vital sign data and the correlation of changes in different vital sign data. It then adjusts the influence weight of each historical data in the prediction model accordingly. This effectively reduces the impact of historical data that does not reflect the patient's true health condition on the prediction results, improves the accuracy of the prediction results, and helps doctors take timely and effective measures for the current health condition of the patient.

[0099] This embodiment also discloses a clinical patient health management system based on smart healthcare, including:

[0100] The data acquisition module is used to acquire real-time monitoring data of the patient's vital signs;

[0101] The first data calculation module is used to calculate the instability of the patient's vital signs data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotions, based on the real-time monitoring data of the patient's vital signs.

[0102] The second data calculation module is used to calculate the reliability of the data at each monitoring time based on the degree of instability at each monitoring time and the possibility that the data at each monitoring time is affected by the patient's emotions.

[0103] The third data calculation module is used to obtain the prediction model, correct the parameters of the prediction model based on the reliability of the data at each monitoring time, and obtain the corrected prediction model.

[0104] The fourth data calculation module is used to take the patient's vital sign monitoring data as input to the corrected prediction model, obtain the predicted value of the patient's vital sign data, analyze the current health status of the patient based on the predicted value of the patient's vital sign data, and take corresponding measures based on the health status.

[0105] The terminal device of this invention includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the various method embodiments described above. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the various device embodiments described above.

[0106] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention.

[0107] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0108] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0109] The memory can be used to store the computer program and / or module. The processor implements various functions of the terminal device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.

[0110] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0111] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A clinical patient health management system based on smart healthcare, characterized in that, include: The data acquisition module is used to acquire real-time monitoring data of the patient's vital signs; The first data calculation module is used to calculate the instability of the patient's vital signs data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotions, based on the real-time monitoring data of the patient's vital signs. The calculation of the instability of the patient's vital signs data at each monitoring time includes: Calculate the probability that the data at each monitoring time point is abnormal equipment data: in, This indicates the probability that the data at the i-th monitoring time in the s-th type of vital sign data is data from an abnormal device. This represents the number of monitoring times included within the time period corresponding to the i-th monitoring time, including the i-th monitoring time. This represents the data value at the j-th monitoring time within the time period corresponding to the i-th monitoring time in the s-th type of vital sign data. This indicates the trend of the vital sign data between the (j+1)th monitoring time and the jth monitoring time. This indicates the degree of fluctuation in the s-th type of vital sign data within adjacent monitoring periods. Represents the normalization function; Calculate the probability of abnormal drug response at each monitoring time point: in, This indicates the probability of an abnormal drug response in the data at the i-th monitoring time point within the s-th type of vital signs data. This represents the monitored value of the data at the i-th monitoring time in the s-th type of vital sign data. This represents the fitted value of the i-th monitoring time on its corresponding fitted curve; Based on the probability that the data at each monitoring time point is from equipment malfunction and the probability that the data at each monitoring time point shows abnormal drug response, the degree of instability of the patient's vital signs data at each monitoring time point is calculated: in, This indicates the degree of instability of the data at the i-th monitoring time in the s-th type of vital sign data; The second data calculation module is used to calculate the reliability of the data at each monitoring time based on the degree of instability at each monitoring time and the possibility that the data at each monitoring time is affected by the patient's emotions. Calculate the likelihood that data at each monitoring time point is affected by the patient's emotions, including: in, This indicates the probability that the data at the i-th monitoring time point is affected by the patient's emotions. This indicates the total number of patient vital signs categories monitored. The number of vital sign categories other than category s. This represents the total number of monitoring times contained within the time period of the i-th monitoring time. This represents the difference between the s-th type of vital sign data at the j-th monitoring time and the previous monitoring time within the time period of the ith monitoring time. This represents the ratio of the change in the s-th type of vital sign data to the change in the t-th type of vital sign data at the j-th monitoring time. It represents the absolute value of the difference between the ratio of the changes in the s-th type of vital signs data and the t-th type of vital signs data at adjacent monitoring times; The calculation of the reliability of data at each monitoring time point includes: in, This indicates the reliability of the data at the i-th monitoring time in the s-th type of vital sign data; The third data calculation module is used to obtain the prediction model, correct the parameters of the prediction model based on the reliability of the data at each monitoring time, and obtain the corrected prediction model. The parameters of the prediction model, which are based on the reliability of data at each monitoring time, include: in, This represents the adjusted parameter value at the i-th monitoring time in the s-th type of vital sign data. Indicates the original parameter value; The fourth data calculation module is used to take the patient's vital sign monitoring data as input to the corrected prediction model, obtain the predicted value of the patient's vital sign data, analyze the current health status of the patient based on the predicted value of the patient's vital sign data, and take corresponding measures based on the health status.

2. The clinical patient health management system based on smart healthcare according to claim 1, characterized in that, The prediction model is an ARIMA model, based on the obtained adjusted parameter values. The ARIMA model is modified and optimized to obtain the modified prediction model ARIMA.

3. The clinical patient health management system based on smart healthcare according to claim 1, characterized in that, The process of analyzing the patient's current health status based on predicted values ​​of vital sign data and taking corresponding measures based on that health status includes: Set monitoring thresholds for each vital sign data. If the predicted value exceeds the set threshold, the current vital sign data is determined to be abnormal, and corresponding measures are taken based on the current abnormal data.

Images