Clinical patient health management method and system based on smart medical treatment

Abstract

The invention discloses a clinical patient health management method and system based on wisdom medical treatment, and the method comprises the steps: calculating the influence degree of the interference of equipment data transmission abnormality, patient medication response, patient emotion fluctuation and other factors on historical data according to the stability degree of historical vital sign data of a patient and the relevance of different vital sign data changes; therefore, the influence of the historical data which cannot reflect the real health condition of the patient on the prediction result can be effectively reduced, the accuracy of the prediction result is improved, a doctor can take effective measures in time according to the current health condition of the patient, and the accuracy of the prediction result is improved. According to the method, the abnormal condition of the vital sign data of the patient can be predicted, and the timeliness is better.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and relates to a clinical patient health management method and system based on intelligent healthcare. Background Art

[0002] Clinical patient health management refers to a management process that, throughout the entire process of patient consultation, treatment, hospitalization, rehabilitation, and follow-up after discharge, based on multi-source health data and clinical information, combines modern information technology means to dynamically monitor, risk-assess, and provide personalized interventions for the patient's physiological state, disease progression, treatment compliance, and health behaviors. With the development of science and technology, clinical patient health management has gradually become an important part of hospital management, playing a key role in improving the diagnosis and treatment efficiency, improving the patient's prognosis, and reducing the incidence of complications.

[0003] Existing clinical patient health management methods mainly rely on electronic medical record systems (EMRs), clinical pathways, remote monitoring devices, and manual follow-up, etc., and are mainly used for risk warnings for postoperative rehabilitation patients, critically ill patients, chronic disease patients, etc. However, existing management methods are mainly rule-driven, lacking analysis of patient individual differences and disease evolution characteristics, making it difficult to provide effective personalized intervention strategies. Moreover, the data integration degree of existing methods is not high, and some systems will increase the burden on medical staff during use, resulting in insufficient practicality and promotion. Summary of the Invention

[0004] The purpose of the present invention is to solve the problem in the prior art that existing health management methods lack analysis and judgment of the evolution of patients' diseases and only alarm after the patient's vital sign data shows abnormalities, with poor timeliness, and to provide a clinical patient health management method and system based on intelligent healthcare.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A clinical patient health management method based on intelligent healthcare, comprising the following steps: Obtain real-time monitoring data of the patient's vital signs; Based on the real-time monitoring data of the patient's vital signs, calculate the instability degree of the patient's vital sign data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion; Based on the instability degree at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion, calculate the credibility of the data at each monitoring moment; Obtain a prediction model, and based on the credibility of the data at each monitoring moment, correct the parameters of the prediction model to obtain a corrected prediction model; Use the monitoring data of the patient's vital signs as the input of the corrected prediction model to obtain the predicted values of the patient's vital signs data, analyze the health status of the current patient based on the predicted values of the patient's vital signs data, and take corresponding measures according to the health status.

[0006] A further improvement of the present invention lies in: Calculating the instability degree of the vital signs data of the patient at each monitoring moment, including: Calculating the possibility that the data at each monitoring moment is abnormal data of the device:

[0007] Wherein, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital signs data is abnormal data of the device, represents the number of monitoring moments included in the time period corresponding to the i-th monitoring moment. If , including the i-th monitoring moment, represents the data value at the j-th monitoring moment in the time period corresponding to the i-th monitoring moment in the s-th type of vital signs data, represents the change trend of the vital signs data between the (j + 1)-th monitoring moment and the j-th monitoring moment, represents the fluctuation degree of the s-th type of vital signs data within adjacent monitoring periods, that is, if the fluctuation degree of this vital signs data is small, the data at different monitoring moments shows the same change trend, represents a normalization function; Calculating the possibility that the data at each monitoring moment shows abnormal drug reaction:

[0008] Wherein, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital signs data shows abnormal drug reaction, represents the monitoring value of the data at the i-th monitoring moment in the s-th type of vital signs data, represents the fitted value of the i-th monitoring moment on its corresponding fitted curve, represents a normalization function; Based on the possibility that the data at each monitoring moment is abnormal data of the device and the possibility that the data at each monitoring moment shows abnormal drug reaction, calculate the instability degree of the vital signs data of the patient at each monitoring moment:

[0009] Wherein, represents the instability degree of the data at the i-th monitoring moment in the s-th type of vital signs data, Indicates the possibility that the data at the $i$-th monitoring moment in the $s$-th type of vital sign data is abnormal data of the device. Indicates the possibility of abnormal drug reaction in the data at the $i$-th monitoring moment in the $s$-th type of vital sign data.

[0010] The calculated possibility that the data at each monitoring moment is affected by the patient's emotion, including:

[0011] Among them, Indicates the possibility that the data at the $i$-th monitoring moment is affected by the patient's emotion. Indicates the total number of types of the patient's monitored vital signs. Is the number of types of vital signs other than the $s$-th type. Indicates the total number of monitoring moments included in the time period where the $i$-th monitoring moment is located. Indicates the difference between the $s$-th type of vital sign data of the $j$-th monitoring moment and its previous monitoring moment in the time period where the $i$-th monitoring moment is located. Indicates the ratio relationship of the change amount between the $s$-th type of vital sign data and the $t$-th type of vital sign data at the $j$-th monitoring moment. Indicates the absolute value of the difference in the ratio of the change amounts of the $s$-th type of vital sign data and the $t$-th type of vital sign data between adjacent monitoring moments. Indicates that the smaller the absolute value of the difference in the ratio of the change amounts of the $s$-th type of vital sign data and the $t$-th type of vital sign data between adjacent monitoring moments, the more the two types of vital sign data change according to a fixed ratio relationship, that is, the stronger the correlation between the two types of vital sign data. Indicates the normalization function.

[0012] The calculation of the credibility of the data at each monitoring moment includes:

[0013] Among them, Indicates the credibility of the data at the $i$-th monitoring moment in the $s$-th type of vital sign data. Indicates the instability degree of the data at the $i$-th monitoring moment in the $s$-th type of vital sign data. Indicates the possibility that the data at the $i$-th monitoring moment is affected by the patient's emotion. Indicates the normalization function.

[0014] The modification of the parameters of the prediction model based on the credibility of the data at each monitoring moment includes:

[0015] Among them, Indicates the adjusted parameter value at the $i$-th monitoring moment in the $s$-th type of vital sign data. denotes the original parameter value, denotes the data credibility of the i-th monitoring moment in the s-th type of vital sign data.

[0016] The prediction model is an ARIMA model. Based on the obtained adjusted parameter value , the ARIMA model is corrected and optimized to obtain the corrected prediction model ARIMA.

[0017] Analyze the current patient's health status based on the predicted value of the patient's vital sign data, and take corresponding measures according to the health status, including: Set the monitoring threshold for each vital sign data. If the predicted value exceeds the set threshold, it is determined that the current vital sign data is abnormal data, and corresponding measures are taken according to the current abnormal data.

[0018] A clinical patient health management system based on intelligent healthcare, including: A data acquisition module for acquiring real-time monitoring data of the patient's vital signs; A first data calculation module for calculating the instability degree of the patient's vital sign data at each monitoring moment and the possibility of the data at each monitoring moment being affected by the patient's emotion based on the real-time monitoring data of the patient's vital signs; A second data calculation module for calculating the credibility of the data at each monitoring moment based on the instability degree at each monitoring moment and the possibility of the data at each monitoring moment being affected by the patient's emotion; A third data calculation module for obtaining a prediction model, correcting the parameters of the prediction model based on the credibility of the data at each monitoring moment, and obtaining a corrected prediction model; A fourth data calculation module for using the monitoring data of the patient's vital signs as the input of the corrected prediction model, obtaining the predicted value of the patient's vital sign data, analyzing the current patient's health status based on the predicted value of the patient's vital sign data, and taking corresponding measures according to the health status.

[0019] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any method described in the present invention are implemented.

[0020] A computer-readable storage medium stores a computer program, characterized in that when the computer program is executed by a processor, the steps of any method described in the present invention are implemented.

[0021] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a clinical patient health management method based on intelligent healthcare. According to the stability of the patient's historical vital sign data and the correlation of changes in different vital sign data, the influence degree of the historical data being interfered by factors such as abnormal device data transmission, patient medication response, and patient mood fluctuations is calculated, and based on this, the influence weight of each historical data in the prediction model is adjusted. This can effectively reduce the influence of historical data that cannot reflect the patient's true health status on the prediction result, improve the accuracy of the prediction result, and is beneficial for doctors to take effective measures in a timely manner according to the current patient's health status. This method can predict the situation where the patient's vital sign data is abnormal, and has better timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use 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 therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of a clinical patient health management method based on intelligent healthcare disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0026] It should be noted that: similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0027] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper", "lower", "horizontal", "inner", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invention product is usually placed during use, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0028] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but it can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but it can be slightly inclined.

[0029] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, if terms such as "set", "installed", "connected", "connected" are understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] The following further describes the present invention in detail with reference to the drawings: See Figure 1 , the present invention discloses a clinical patient health management method based on intelligent healthcare. This method uses the historical monitoring data of clinical patients to predict the vital sign data of patients, and based on the abnormal degree of the predicted values of various vital sign data and the reflection of different vital sign abnormalities on the patient's health status, targeted abnormal warnings are carried out, which can effectively improve the timeliness of patient risk warnings. And different warning information is provided for different abnormal manifestations, which can greatly reduce the management burden of medical staff on patients.

[0031] This method first continuously monitors the vital sign data of clinical patients, then predicts the patient's health status according to the changes in the patient's historical monitoring data, and finally takes corresponding treatment measures according to the abnormal conditions of the predicted values of the patient's various vital sign data. The specific steps are as follows: Step 1: Continuously monitor the vital sign data of clinical patients through clinical monitoring instruments.

[0032] Specifically include: Clinical patient health management mainly targets critically ill patients and postoperative patients. These patients have unstable health conditions and are prone to abnormal phenomena such as complications, so it is necessary to continuously monitor the vital sign data of the patients. This method uses a bedside detector to monitor the vital sign data of the patients, including heart rate, respiratory rate, blood pressure, blood oxygen saturation, etc. The monitoring instrument obtains the relevant data of the patient every 1 second.

[0033] Step 2: According to the patient's historical monitoring data, use the ARIMA model to calculate the predicted values of the patient's vital sign data.

[0034] For clinical patients who need continuous monitoring, such as critically ill patients and postoperative patients, ensuring the stability of their vital sign data and maintaining it within the normal range is an important goal of treatment. Therefore, when the patient's health status is relatively good, all their vital signs should be relatively stable and within the abnormal threshold. Therefore, by predicting whether there are abnormal manifestations in the patient's vital sign data, corresponding measures can be taken for the patient's abnormal risks in a timely manner. However, the patient's vital sign data may be affected by equipment abnormalities, patient drug use, and patient emotions, resulting in obvious fluctuations. These fluctuations are temporary and do not reflect the patient's true health status, which will affect the accuracy of the predicted values of the patient's vital sign data. Therefore, according to the stability of the data at each monitoring moment of the patient and the possibility of being affected by emotions, the credibility of each monitoring data is calculated, and thus the influence weight of each monitoring data on the predicted value is adjusted.

[0035] Furthermore, the present invention analyzes the patient's historical vital sign monitoring data to predict the patient's health status, specifically including the following steps: Step 2.1: According to the fluctuations of each vital sign of the patient, calculate the stability of each vital sign data within its corresponding time period respectively.

[0036] Step 2.2: According to the correlation of the fluctuations of different vital sign data of the patient within the same time period, calculate the possibility that the data at each monitoring moment is affected by the patient's emotions.

[0037] Step 2.3: According to the stability and the possibility of being affected by emotions of each monitoring data, calculate the credibility of each monitoring data, and calculate the predicted values of the patient's vital sign data.

[0038] Specifically, it is expanded as follows: Step 2.1: According to the fluctuations of each vital sign of the patient, calculate the stability of each vital sign data within its corresponding time period respectively.

[0039] In the normal state, the vital sign data of a patient should be relatively stable. Even during the recovery process, it should show a relatively gentle change trend. However, when the monitoring device is in unstable contact, data errors occur during data transmission, or the patient has corresponding drug reactions after taking medicine, etc., the vital sign data of the patient may show short-term violent fluctuations. At this time, the monitoring data cannot reflect the patient's true health condition and will cause certain interference to the prediction results of the patient's health. Therefore, it is necessary to calculate the stability of each vital sign data according to the fluctuation of the patient's vital sign data.

[0040] Specifically, it includes: First, because the data errors caused by abnormalities in the device monitoring and transmission processes usually only affect the data at a few monitoring moments, the unstable data caused by device abnormalities can be obtained by checking whether there are obvious fluctuations in each monitoring data within a short time period. Therefore, for the data at each monitoring moment, calculate the possibility that the data at this monitoring moment is abnormal data caused by device abnormalities based on the fluctuation degree of the data at the 10 monitoring moments closest to it:

[0041] Among them, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital sign data is abnormal data caused by the device, represents the number of monitoring moments included in the corresponding time period of the i-th monitoring moment ( , including the i-th monitoring moment), represents the data value at the j-th monitoring moment in the corresponding time period of the i-th monitoring moment in the s-th type of vital sign data, represents the change trend of the vital sign data between the (j + 1)-th monitoring moment and the j-th monitoring moment, represents the fluctuation degree of the s-th type of vital sign data within adjacent monitoring periods, that is, if the fluctuation degree of this vital sign data is small, the data at different monitoring moments should show the same change trend. represents the normalization function.

[0042] Further, when the patient uses a short-acting drug, the vital sign data will show a significant increase or decrease within a few minutes. At this time, the monitored data may show a change in the same trend within a short period, but it will quickly return to normal after the drug is stopped. Therefore, this type of data should also be considered unstable data that cannot accurately reflect the patient's health status. Because the vital sign data of the patient changes significantly during the drug reaction and recovery process, according to the drug reaction time, taking each monitoring moment as the central moment, the monitoring data within its corresponding 10 minutes (empirical value) is obtained. The coordinate graph of each type of vital sign data is plotted according to "time - monitored value". The least squares method is used to fit it, and according to the difference between the monitored value at the central monitoring moment and the fitted value on the fitted curve, the possibility of abnormal drug reaction at the central monitoring moment is calculated:

[0043] wherein, represents the possibility of abnormal drug reaction of the data at the i-th monitoring moment in the s-th type of vital sign data, represents the monitored value of the data at the i-th monitoring moment in the s-th type of vital sign data, represents the fitted value of the i-th monitoring moment on its corresponding fitted curve, represents the normalization function.

[0044] Further, according to the possibility that the monitoring data is abnormal data of the device and the possibility of abnormal drug reaction, the instability degree of each monitoring data is calculated.

[0045]

[0046] wherein, represents the instability degree of the data at the i-th monitoring moment in the s-th type of vital sign data, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital sign data is abnormal data of the device, represents the possibility of abnormal drug reaction of the data at the i-th monitoring moment in the s-th type of vital sign data.

[0047] Step 2.2. According to the correlation of the fluctuations of different vital sign data of the patient within the same period, calculate the possibility that the data at each monitoring moment is affected by the patient's emotion.

[0048] Since the vital sign data of a patient is greatly affected by the patient's emotions. For example, when the patient is emotionally excited, data such as heart rate, respiratory rate, and blood pressure will persistently remain at a high level. However, the patient is not always in a state affected by emotions. Therefore, the data affected by the patient's emotions has a relatively low degree of reflection for predicting the patient's health status. The drug treatment of a patient usually targets only one aspect, that is, the correlation between different vital sign data during the treatment process is relatively weak. However, the impact of emotional changes on the patient is often comprehensive. That is, when the patient's emotions change, it often causes large changes in multiple vital sign data simultaneously. Therefore, according to the correlation of changes in different vital sign data of the patient, calculate the possibility that the data at each monitoring moment is affected by the patient's emotions.

[0049] Specifically include: First, because the response speed of emotional changes in vital sign data is relatively fast, for each monitoring moment, centered on this monitoring moment, obtain the monitoring data within 1 minute of it, which is used to calculate the possibility that the data at this monitoring moment is affected by the patient's emotions. Since the ranges and units of different vital sign data are different and cannot be directly compared, it is necessary to first perform normalization processing on all monitoring data. All the data mentioned in the following steps are the normalized data values.

[0050] Since the patient's emotional changes will cause correlated changes in multiple vital sign data, first calculate the change amount of each type of vital sign data at each monitoring moment and its previous monitoring moment during the monitoring period (the difference between the vital sign data of the s-th type at the i-th monitoring moment and its previous monitoring moment). If the changes between different vital sign data are correlated, then the changes in different vital sign data should always follow a fixed ratio. Thus, calculate the possibility that the data at each monitoring moment is affected by the patient's emotions:

[0051] Among them, represents the possibility that the data at the i-th monitoring moment is affected by the patient's emotions, represents the total number of types of vital signs monitored for the patient, is the number of types of vital signs other than the s-th type, represents the total number of monitoring moments included in the time period (1 min) where the i-th monitoring moment is located, represents the difference between the vital sign data of the s-th type at the j-th monitoring moment and its previous monitoring moment within the time period where the i-th monitoring moment is located. represents the ratio relationship between the change amounts of the vital sign data of the s-th type and the t-th type at the j-th monitoring moment, Denote the absolute value of the difference between the ratios of the changes in the vital sign data of the s-th type and the t-th type at adjacent monitoring times. The smaller the absolute value of the difference between the ratios of the changes in the vital sign data of the s-th type and the t-th type at adjacent monitoring times, the more the two types of vital sign data change according to a fixed proportional relationship, that is, the stronger the correlation between the two types of vital sign data. Denote the normalization function.

[0052] Step 2.3. Calculate the credibility of each monitoring data according to the stability of each monitoring data and the possibility of being affected by emotions, and calculate the predicted value of the patient's vital sign data.

[0053] According to the stability of the monitoring data in the above steps and the stability of the patient's emotional state during monitoring, which are important factors affecting the degree to which the vital sign data reflects the patient's health status. Unstable data and data greatly affected by the patient's emotions will lead to a decrease in the accuracy of the predicted value of the patient's vital sign data, that is, the credibility of these data in the prediction process is relatively low. Therefore, combining the stability of each monitoring data and the possibility of being affected by emotions, calculate the credibility of each monitoring data, and adjust the parameters in the ARIMA model accordingly:

[0054] Among them, Denote the credibility of the data at the i-th monitoring time in the vital sign data of the s-th type, Denote the degree of instability of the data at the i-th monitoring time in the vital sign data of the s-th type, Denote the possibility that the data at the i-th monitoring time is affected by the patient's emotions, Denote the normalization function.

[0055] Furthermore, obtain the autoregressive coefficient in the ARIMA model using maximum likelihood estimation , and then correct this parameter according to the credibility of each historical data.

[0056]

[0057] Among them, Denote the adjusted parameter value at the i-th monitoring time in the vital sign data of the s-th type, Denote the original parameter value, Denote the credibility of the data at the i-th monitoring time in the vital sign data of the s-th type.

[0058] Furthermore, substitute the historical monitoring data of the patient's vital signs into the ARIMA model with adjusted parameters respectively to obtain the predicted value of each item of the patient's vital sign data.

[0059] Step 3: Analyze the current health status of the patient and implement corresponding measures according to the degree of abnormality of the predicted values of the patient's vital sign data.

[0060] Specifically, it includes: Set the threshold for each piece of vital sign data monitoring data; Compare the adjusted predicted values of the patient's vital sign data with the monitoring thresholds of each piece of vital sign data: When there is a predicted value exceeding the threshold warning line, it is considered that there is an abnormal risk for the predicted value of this vital sign. By comprehensively considering the abnormal risk situations of multiple predicted values, since the predicted value represents the development of the subsequent health status monitoring data of the patient, the possible health status risks of the patient in the future can be judged based on the predicted value, so as to intervene in clinical treatment in advance and improve the timeliness of patient health management.

[0061] The method disclosed in the embodiment of the present invention calculates the influence degree of historical data being interfered by factors such as abnormal device data transmission, patient medication reaction, and patient mood fluctuation according to the stability degree of the patient's historical vital sign data and the relevance of changes in different vital sign data, and adjusts the influence weight of each historical data in the prediction model accordingly, which can effectively reduce the influence of historical data that cannot reflect the true health status of the patient on the prediction result, improve the accuracy of the prediction result, and is beneficial for doctors to take effective measures in a timely manner for the current health status of the patient.

[0062] This embodiment also discloses a clinical patient health management system based on intelligent healthcare, including: A data acquisition module for acquiring real-time monitoring data of the patient's vital signs; A first data calculation module for calculating the instability degree of the patient's vital sign data at each monitoring moment and the possibility of the data being affected by the patient's mood based on the real-time monitoring data of the patient's vital signs; A second data calculation module for calculating the credibility of the data at each monitoring moment based on the instability degree at each monitoring moment and the possibility of the data being affected by the patient's mood; A third data calculation module for obtaining a prediction model, modifying the parameters of the prediction model based on the credibility of the data at each monitoring moment, and obtaining a modified prediction model; A fourth data calculation module for using the monitoring data of the patient's vital signs as the input of the modified prediction model, obtaining the predicted values of the patient's vital sign data, analyzing the current health status of the patient according to the predicted values of the patient's vital sign data, and taking corresponding measures according to the health status.

[0063] The terminal device according to an embodiment of the present 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, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0064] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention.

[0065] The terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0066] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0067] The memory may be used to store the computer program and / or modules, and the processor realizes various functions of the terminal device by running or executing the computer program and / or modules stored in the memory, and by calling the data stored in the memory.

[0068] If the modules / units integrated in the terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0069] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A clinical patient health management method based on intelligent healthcare, characterized in that, Including the following steps: Obtain real-time monitoring data of the patient's vital signs; Based on the real-time monitoring data of the patient's vital signs, calculate the instability degree of the patient's vital sign data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion; Based on the instability degree at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion, calculate the credibility of the data at each monitoring moment; Obtain a prediction model, modify the parameters of the prediction model based on the credibility of the data at each monitoring moment, and obtain a modified prediction model; Use the monitoring data of the patient's vital signs as the input of the modified prediction model, obtain the predicted value of the patient's vital sign data, analyze the current health condition of the patient according to the predicted value of the patient's vital sign data, and take corresponding measures according to the health condition.

2. The clinical patient health management method based on intelligent healthcare according to claim 1, characterized in that, The calculation of the instability degree of the patient's vital sign data at each monitoring moment includes: Calculate the possibility that the data at each monitoring moment is abnormal data of the device: Among them, represents the possibility that the data at the $i$-th monitoring moment in the $s$-th type of vital sign data is abnormal data of the device. represents the number of monitoring moments included in the corresponding time period of the $i$-th monitoring moment. If , including the $i$-th monitoring moment, represents the data value of the $j$-th monitoring moment in the corresponding time period of the $i$-th monitoring moment in the $s$-th type of vital sign data. represents the change trend of the vital sign data at the $(j + 1)$-th monitoring moment and the $j$-th monitoring moment. represents the fluctuation degree of the $s$-th type of vital sign data in adjacent monitoring periods, that is, if the fluctuation degree of the vital sign data is small, the data at different monitoring moments shows the same change trend. represents a normalization function; Calculate the possibility that the data at each monitoring moment has an abnormal drug reaction: Among them, represents the possibility of an abnormal drug reaction occurring in the data at the $i$-th monitoring moment in the $s$-th type of vital sign data, represents the monitored value of the data at the $i$-th monitoring moment in the $s$-th type of vital sign data, represents the fitted value of the $i$-th monitoring moment on its corresponding fitted curve, represents the normalization function; Based on the possibility that the data at each monitoring moment is abnormal data of the device and the possibility that the data at each monitoring moment has an abnormal drug reaction, calculate the instability degree of the patient's vital sign data at each monitoring moment: Among them, represents the instability degree of the data at the i-th monitoring moment in the s-th type of vital sign data, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital sign data is abnormal data of the device, represents the possibility that the data at the i-th monitoring moment in the s-th type of vital sign data has an abnormal drug reaction.

3. The clinical patient health management method based on intelligent healthcare according to claim 1, characterized in that, The calculation of the possibility that the data at each monitoring moment is affected by the patient's emotion includes: Among them, represents the possibility that the data at the i-th monitoring moment is affected by the patient's emotion, represents the total number of categories of the patient's vital signs to be monitored, is the number of categories of vital signs other than the s-th category, represents the total number of monitoring moments included in the time period where the i-th monitoring moment is located, represents the difference between the vital sign data of the s-th category at the j-th monitoring moment and its previous monitoring moment within the time period where the i-th monitoring moment is located, represents the ratio relationship between the change amounts of the vital sign data of the s-th category and the t-th category at the j-th monitoring moment, represents the absolute value of the difference between the ratios of the change amounts of the vital sign data of the s-th category and the t-th category at adjacent monitoring moments, It indicates that the smaller the absolute value of the difference between the ratios of the change amounts of the vital sign data of the s-th category and the t-th category at adjacent monitoring moments, the more the two types of vital sign data change according to a fixed proportional relationship, that is, the stronger the correlation between the two types of vital sign data, represents a normalization function.

4. A clinical patient health management method based on intelligent healthcare according to claim 1, characterized in that, The calculation of the credibility of the data at each monitoring moment includes: Among them, represents the data credibility of the i-th monitoring moment in the s-th type of vital sign data, represents the instability degree of the i-th monitoring moment data in the s-th type of vital sign data, represents the possibility that the data of the i-th monitoring moment is affected by the patient's emotion, represents a normalization function.

5. The clinical patient health management method based on intelligent healthcare according to claim 4, characterized in that The modification of the parameters of the prediction model based on the credibility of the data at each monitoring moment includes: Among them, represents the adjusted parameter value at the i-th monitoring moment in the s-th type of vital sign data, represents the original parameter value, represents the data credibility at the i-th monitoring moment in the s-th type of vital sign data.

6. The clinical patient health management method based on intelligent healthcare according to claim 5, characterized in that, The prediction model is an ARIMA model, and based on the obtained adjusted parameter values , the ARIMA model is corrected and optimized to obtain the corrected prediction model ARIMA.

7. A clinical patient health management method based on intelligent healthcare according to claim 1, characterized in that, The analysis of the current health condition of the patient according to the predicted value of the patient's vital sign data and the taking of corresponding measures according to the health condition include: Set the monitoring threshold for each item of vital sign data. If the predicted value exceeds the set threshold, determine that the current vital sign data is abnormal data, and take corresponding measures according to the current abnormal data.

8. A clinical patient health management system based on intelligent healthcare, characterized in that, Including: A data acquisition module for obtaining real-time monitoring data of the patient's vital signs; A first data calculation module for calculating the instability degree of the patient's vital sign data at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion based on the real-time monitoring data of the patient's vital signs; A second data calculation module for calculating the credibility of the data at each monitoring moment based on the instability degree at each monitoring moment and the possibility that the data at each monitoring moment is affected by the patient's emotion; A third data calculation module for obtaining a prediction model, modifying the parameters of the prediction model based on the credibility of the data at each monitoring moment, and obtaining a modified prediction model; A fourth data calculation module for using the monitoring data of the patient's vital signs as the input of the modified prediction model, obtaining the predicted value of the patient's vital sign data, analyzing the current health condition of the patient according to the predicted value of the patient's vital sign data, and taking corresponding measures according to the health condition.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method described in any one of claims 1-7 are implemented.

Images