A patient real-time monitoring management system based on a smart wristband

Abstract

The application discloses a kind of patient real-time monitoring management systems based on intelligent wristband, it is related to medical information technology field, including data acquisition sensing module, abnormality detection early warning module, health trend prediction module, data management module and user interaction module.The patient real-time monitoring management system based on intelligent wristband, through the method of dynamic anomaly detection, individualized health trend prediction, the accuracy of patient health monitoring and early warning reaction speed are significantly improved.Through abnormality detection and dynamic adjustment health trend modeling, sudden health problems can be identified in real time and future health risks can be predicted in advance, especially for chronic disease patients and elderly population, more accurate individualized health management solutions can be provided, thereby significantly improving the health management effect of patients, reducing medical costs and improving the quality of life of patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical information technology, in particular to a patient real-time monitoring management system based on a smart wristband. BACKGROUND

[0002] With the improvement of people's health management awareness and the rapid development of smart wearable devices, health monitoring systems based on smart wristbands have gradually become an important tool for personal health management and medical monitoring. Existing smart wristbands generally rely on real-time collection of physiological data (such as heart rate, blood oxygen, body temperature, etc.) by sensors, and perform health data analysis and display through simple algorithms. These devices can generally monitor the real-time health status of users and display and preliminarily analyze data through mobile applications and the like. However, the existing technology faces several important challenges and needs to be broken through to achieve more efficient and accurate patient real-time monitoring and health management.

[0003] Most existing smart wristband systems rely on traditional anomaly detection methods, mainly through fixed threshold values to determine whether the health status is abnormal. This method often does not take into account individual differences and dynamic changes of patients, which can easily lead to missed diagnosis or misdiagnosis, especially in chronic disease patients or elderly patient groups. In addition, the existing smart wristband system lacks the ability to predict health trends and can only reflect real-time health data, but cannot provide long-term trend analysis of health changes for patients, thereby affecting the effectiveness of prevention and intervention. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a patient real-time monitoring management system based on a smart wristband to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0006] In a first aspect, the present application provides a patient real-time monitoring management system based on a smart wristband, comprising:

[0007] S1, analyzing physiological indicators of the smart wristband;

[0008] S2, selecting sensor types carried by the smart wristband based on the analysis of physiological indicators of the smart wristband;

[0009] S3, determining the transmission path and communication protocol of the sensor data to ensure real-time collection of data from the sensor to the cloud or local server;

[0010] S4, performing anomaly detection and early warning based on the real-time collected sensor data;

[0011] S5, based on the real-time collected sensor data, analyzing the long-term health data and living habits of the patient, establishing a personalized health trend model, and predicting the future health status of the patient wearing the smart wristband.

[0012] Further optimize the technical solution, in steps S1 and S2, the physiological indicators of the smart wristband include heart rate, blood pressure, body temperature, blood oxygen saturation, and the sensor types include heart rate sensor, blood pressure sensor, temperature sensor, and blood oxygen sensor.

[0013] Further optimize the technical solution, in step S4, the abnormal detection and early warning model is constructed, the model combines various physiological indicators and individual differences of the patient to perform abnormal detection and intelligent early warning.

[0014] Define the physiological indicators monitored by the smart wristband:

[0015] Heart rate , blood oxygen saturation , blood pressure , body temperature , then:

[0016] represents the physiological indicator data collected at time point ;

[0017] represents the physiological indicator data sequence in the past period of time;

[0018] The abnormal detection and early warning model comprises:

[0019] Weighted abnormal score;

[0020] Overall abnormal score;

[0021] Dynamic adjustment threshold;

[0022] Trigger the early warning mechanism.

[0023] Further optimize the technical solution, when the abnormal detection and early warning model performs weighted abnormal scoring, define the abnormal score of each physiological indicator As follows:

[0024] ;

[0025] Wherein,

[0026] is the value of the th physiological indicator at the current time ;

[0027] And are the mean and standard deviation of the physiological indicator in the patient's historical data, representing the normal fluctuation range;

[0028] are the weight coefficients of the indicators, representing the importance of different indicators;

[0029] The overall abnormal score is obtained by weighted average of the abnormal scores of all physiological indicators :

[0030] ;

[0031] wherein,

[0032] is the number of monitored physiological indicators;

[0033] The overall abnormal score is used to measure the abnormality of each physiological indicator at the current time;

[0034] Due to the large difference in health baseline of different patients, a dynamic adjustment threshold is introduced to avoid false alarms, and the calculation method of the dynamic adjustment threshold is as follows:

[0035] ;

[0036] wherein,

[0037] is the basic threshold, determined based on the statistical characteristics of all patient data;

[0038] is an adjustment coefficient, representing the sensitivity of the model to the dynamic adjustment threshold, which is fine-tuned according to the patient's health history;

[0039] is the overall abnormal score at the previous time, and the threshold is dynamically adjusted according to the abnormal score at the previous time.

[0040] Further optimization of the technical solution, the overall abnormal score exceeds the threshold , it is determined as abnormal, triggering the warning mechanism, and the warning signal will be immediately pushed to the patient or medical personnel through the intelligent device or mobile application;

[0041] The emergency level of the warning is graded according to the size of , if the value higher than the threshold is high, an emergency alarm is issued; if the value higher than the threshold is low, a normal alarm is issued.

[0042] Further optimization of the technical solution, in step S5, the health trend model will physiological indicators: heart rate blood oxygen saturation blood pressure body temperature dynamically associated with the patient's health history, forming a personalized health trend, predicting the health status at a future time .

[0043] Further optimization of the technical solution, the health trend model defines the historical data of each physiological indicator as:

[0044] the heart rate, blood pressure, blood oxygen saturation and body temperature at time ;

[0045] the weight coefficient of each physiological indicator at time ;

[0046] Predict the future health status by weighting the historical data :

[0047] ;

[0048] wherein,

[0049] represents the predicted health status;

[0050] represents the change amount of the th physiological indicator, that is, the change compared with the previous day;

[0051] is the weight of the corresponding physiological indicator at time ;

[0052] is a regulation coefficient for controlling the influence of the change amount on the predicted health status, used to adjust the influence degree of the change trend.

[0053] Further optimization of the technical solution, in the health trend model, the weight is dynamically adjusted, so that the influence of each physiological indicator on health prediction is more flexible and personalized;

[0054] The weight dynamic adjustment formula is as follows:

[0055] ;

[0056] wherein,

[0057] is the weight of the corresponding physiological indicator at time ;

[0058] is an error measure of the prediction result, which is represented by the difference between the model prediction value and the actual value;

[0059] is the learning rate of each physiological indicator, used to control the sensitivity of weight update.

[0060] Further optimize the technical solution, the functional modules of the system include data acquisition sensing module, abnormality detection and early warning module, health trend prediction module, data management module and user interaction module.

[0061] Further optimize the technical solution, in the functional modules:

[0062] The data acquisition sensing module is used to collect the data of physiological indicators in real time and transmit them to the cloud or the local server.

[0063] The abnormality detection and early warning module is based on the collected data to perform abnormality detection and early warning.

[0064] The health trend prediction module is based on the collected data to predict the future health status of the patient wearing the smart wristband.

[0065] The data management module provides data storage and security management functions.

[0066] The user interaction module provides a user interaction interface to facilitate the viewing of health data and early warning information.

[0067] In the second aspect, the embodiments of the present application provide a computer device, including a memory and a processor, and the memory stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the patient real-time monitoring management system based on the smart wristband according to the first aspect of the present application.

[0068] In the third aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the patient real-time monitoring management system based on the smart wristband according to the first aspect of the present application.

[0069] Compared with the prior art, the present application provides a patient real-time monitoring management system based on a smart wristband, which has the following beneficial effects:

[0070] The patient real-time monitoring management system based on the smart wristband significantly improves the accuracy of patient health monitoring and the speed of early warning response through dynamic anomaly detection and personalized health trend prediction. Through anomaly detection and dynamic adjustment of health trend modeling, sudden health problems can be identified in real time and future health risks can be predicted in advance, especially for chronic disease patients and the elderly, more accurate personalized health management solutions can be provided, thereby significantly improving the health management effect of patients, reducing medical costs and improving the quality of life of patients. BRIEF DESCRIPTION OF DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0072] Figure 1 A construction process schematic diagram of a patient real-time monitoring management system based on a smart wristband is provided for the present application.

[0073] Figure 2 A function module schematic diagram of a patient real-time monitoring management system based on a smart wristband is provided for the present application. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings.

[0075] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from the description, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0076] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is separate or selectively excluded from other embodiments. Embodiment one

[0077] Reference Figure 1 For the first embodiment of the present application, the embodiment provides a patient real-time monitoring management system based on a smart wristband, comprising:

[0078] S1, analyzing the physiological indicators of the smart wristband.

[0079] In this embodiment, before developing a patient real-time monitoring management system based on a smart wristband, in-depth physiological indicator analysis is first needed. Through communication with medical experts, equipment manufacturers, and target users (patients), etc., the functions that the system needs to meet are determined. For example, the wristband needs to monitor physiological indicators such as heart rate, blood pressure, body temperature, and blood oxygen saturation in real time, and can issue an alarm in a timely manner when an anomaly occurs. In addition, it is also important to determine the goals of the system, for example, the system needs to have high-precision data acquisition capability, low-power design, powerful data analysis capability, and good user experience, etc. The requirement analysis stage should combine the characteristics of the target patient group, such as the elderly, chronic disease patients, etc., to ensure that the designed system can provide personalized health management services.

[0080] S2, physiological indicator analysis based on a smart wristband, selection of sensor types carried by the smart wristband.

[0081] In this embodiment, on the basis of physiological indicator analysis, it is crucial to select appropriate sensors. The wristband sensor needs to meet the requirements of high precision, low power consumption, and real-time performance, etc.

[0082] In steps S1 and S2, the physiological indicators of the smart wristband include heart rate, blood pressure, body temperature, and blood oxygen saturation, and the sensor types include heart rate sensors, blood pressure sensors, temperature sensors, and blood oxygen sensors.

[0083] For example, the heart rate sensor can be a sensor based on the photoplethysmography (PPG) technology, which can non-invasively measure heart rate and has relatively low power consumption. The data acquisition design should include the interface specification between the sensor and the smart wristband master chip.

[0084] S3, determination of the transmission path and communication protocol of the sensor data, to ensure real-time collection of data from the sensor to the cloud or local server.

[0085] In this embodiment, real-time transmission of data after collection is the key to ensuring that the system can intervene in a timely manner. The smart wristband needs to have stable wireless communication capability, and common communication methods include Bluetooth, Wi-Fi, LoRa, etc. According to the needs and use environment of the target patient group, the appropriate communication technology is selected. For example, Bluetooth is suitable for short-distance data transmission, Wi-Fi is suitable for scenarios that require real-time data transmission, and LoRa is suitable for long-distance and low-power application scenarios.

[0086] In addition, the communication protocol design should consider the reliability of data transmission, using lightweight protocols such as MQTT or CoAP to ensure smooth data transmission in various network environments. This step also needs to consider the battery life of the device, so it is necessary to optimize the frequency of data transmission and the size of the data packet, balancing the relationship between real-time performance and battery consumption.

[0087] S4, based on real-time collected sensor data, abnormality detection and early warning are performed.

[0088] Abnormality detection is one of the core functions of the system. In order to timely discover possible health problems of the patient, such as cardiac arrest and difficulty breathing, the system needs to design a model to analyze data in real time and make judgments.

[0089] In this embodiment, an abnormality detection and early warning model is constructed, which combines various physiological indicators and individual differences of the patient to perform abnormality detection and intelligent early warning.

[0090] Define the physiological indicators monitored by the intelligent wristband:

[0091] Heart rate , blood oxygen saturation , blood pressure , body temperature Therefore:

[0092] represents the physiological indicator data collected at time point

[0093] represents the physiological indicator data sequence in the past period of time.

[0094] The abnormality detection and early warning model comprises:

[0095] Weighted abnormality score

[0096] Overall abnormality score

[0097] Dynamic adjustment of threshold value

[0098] Triggering of early warning mechanism

[0099] Further, when performing the weighted abnormality score, the abnormality score of each physiological indicator is defined as as follows:

[0100]

[0101] wherein,

[0102] is the first ​​​a value of a physiological indicator (e.g. heart rate, blood oxygen, etc.);

[0103] and are the mean and standard deviation of the physiological indicator in the patient's historical data, representing the normal fluctuation range;

[0104] is the weight coefficient of the indicator, used to represent the importance of different indicators. Different physiological indicators are more sensitive to the warning of certain health risks, so their weight coefficients are different.

[0105] The overall abnormal score is obtained by weighted average of the abnormal scores of all physiological indicators

[0106]

[0107] wherein,

[0108] is the number of monitored physiological indicators;

[0109] The overall abnormal score is used to measure the abnormality of each physiological indicator at the current time.

[0110] In order to consider the individual differences and health history of the patient, since the health baseline of different patients is quite different, a dynamic adjustment threshold is introduced to avoid false alarms and ensure the accuracy of the warning, and the calculation method of the dynamic adjustment threshold is as follows:

[0111]

[0112] wherein,

[0113] is the basic threshold, determined based on the statistical characteristics of all patient data;

[0114] is an adjustment coefficient, representing the sensitivity of the model to the dynamic adjustment threshold, which is fine-tuned according to the patient's health history;

[0115] is the overall abnormal score at the previous time, and the threshold is dynamically adjusted according to the abnormal score at the previous time.

[0116] If the overall abnormal score exceeds the threshold , it is determined to be abnormal, triggering the warning mechanism, and the warning signal will be immediately pushed to the patient or medical personnel through the intelligent device or mobile application;

[0117] The urgency of the warning is determined according to ​​​The size of the value is graded, if the value above the threshold is high, an emergency alarm is sent out; if the value above the threshold is low, a normal alarm is sent out.

[0118] When the model is used, after a new round of data is obtained from the wristband each time, the system calculates the abnormal scores of each physiological indicator , and updates the overall abnormal score . The system dynamically adjusts the sensitivity of the early warning according to the patient's historical data and real-time health status, ensuring that there are not too many false alarms. Once the set threshold is exceeded, the system triggers an early warning to notify the patient or medical personnel, ensuring timely intervention.

[0119] The model can be adjusted according to the individual differences of patients to avoid false alarms and improve the accuracy of early warnings, and is a key component of the intelligent wristband patient real-time monitoring and management system.

[0120] S5, based on real-time collected sensor data, analyze the patient's long-term health data and living habits, establish a personalized health trend model, and predict the future health status of the patient wearing the intelligent wristband.

[0121] In this embodiment, the health trend model dynamically correlates the physiological indicators: heart rate , blood oxygen saturation , blood pressure , body temperature with the patient's health history to form a personalized health trend and predict the health status at a certain time in the future.

[0122] Further, the health trend model defines the historical data of each physiological indicator as:

[0123] the heart rate, blood pressure, blood oxygen saturation and body temperature at time ;

[0124] the weight coefficient of each physiological indicator at time , which is dynamically adjusted according to the individual situation of each patient (such as health status, medical history, etc.).

[0125] The future health status is predicted by weighting the historical data :

[0126] ;

[0127] wherein,

[0128] represents the predicted health status; ​

[0129] Indicates the first The change in a physiological indicator, that is, the change compared to the previous day;

[0130] It is a moment Corresponding physiological indicators The weights;

[0131] It is a moderating coefficient that controls the impact of changes on predicted health status, used to adjust the degree of influence of the trend of change.

[0132] In the aforementioned health trend model, the weights Dynamic adjustments are made to make the impact of each physiological indicator on health prediction more flexible and personalized; the weight of each physiological indicator is automatically adjusted based on historical health data and real-time monitoring feedback to adapt to changes in the patient's health. For example, during certain special periods (such as in the pre-heart attack phase for patients with heart disease), the weight of heart rate may be higher than usual.

[0133] The formula for dynamically adjusting the weights is as follows:

[0134] ;

[0135] in,

[0136] For a moment Corresponding physiological indicators The weights;

[0137] It is a measure of error in the prediction results, usually expressed as the difference between the model's predicted value and the actual value. Specifically, if the deviation in predicting health status is large, it indicates that the influence of that physiological indicator on the current prediction may need to be increased;

[0138] It is the learning rate of each physiological indicator, used to control the sensitivity of weight updates.

[0139] When in use, the model collects the patient's health data (heart rate, blood pressure, blood oxygen, body temperature, etc.) and environmental information (such as activity level, sleep status, etc.) from the smart wristband and other sensors. The model is trained using the patient's historical health data to obtain the initial weights for each physiological indicator. The system continuously monitors patients' health status using devices such as wristbands, and predicts future health status based on historical and real-time data. Weighting coefficients are adjusted according to real-time data and error feedback. Optimize prediction accuracy. Use the model to predict health status at a future point in time. and determine whether it exceeds the health risk threshold, thereby triggering an early warning.

[0140] According to the historical health data and real-time data of the individual patient, the weights of various physiological indicators are dynamically adjusted, and the future health trend is predicted. In this way, the system can not only identify sudden health problems in time, but also provide a scientific basis for long-term health management, and realize more personalized health prediction and early warning. Embodiment Two

[0141] Reference Figure 2 For the second embodiment of the present application, the embodiment provides a functional module of a patient real-time monitoring and management system, which includes a data acquisition and sensing module, an abnormality detection and early warning module, a health trend prediction module, a data management module, and a user interaction module.

[0142] In the functional module:

[0143] The data acquisition and sensing module is used to collect the data of physiological indicators (such as heart rate, blood pressure, blood oxygen, body temperature, etc.) in real time and transmit them to the cloud or local server;

[0144] The abnormality detection and early warning module performs abnormality detection and early warning based on the collected data;

[0145] The health trend prediction module predicts the future health status of the patient wearing the smart wristband based on the collected data;

[0146] The data management module provides data storage and security management functions, is responsible for storing the historical health data, real-time monitoring data, model parameters, and other information of the patient, and ensures the security, integrity, and accessibility of the data;

[0147] The user interaction module provides a user interaction interface for conveniently viewing health data and early warning information. Through the graphical interface, the user can conveniently view real-time health data, historical trends, health warnings, prediction results, and other information. Embodiment Three

[0148] The embodiment also provides a computer device suitable for the case of a patient real-time monitoring and management system based on a smart wristband, which includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize a patient real-time monitoring and management system based on a smart wristband as proposed in the above embodiment.

[0149] The embodiment also provides a storage medium having a computer program stored thereon, which is executed by a processor to realize a patient real-time monitoring and management system based on a smart wristband as proposed in the above embodiment.

[0150] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, a trackball or a touchpad arranged on the shell of the computer device, or can be an external keyboard, a touchpad or a mouse, etc.

[0151] If the functions are implemented in the form of software function units and sold or used as independent products, the functions can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer readable medium for use by an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from the instruction execution system, apparatus or device, or in conjunction with these instructions. For the purpose of this specification, the "computer readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, apparatus or device, or in conjunction with these instructions.

[0153] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via an optical scanner, then compiled, interpreted, or otherwise processed, as necessary, and stored in a computer memory.

[0154] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or combinations thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0155] It should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the present application. Even though the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced, without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A smart wristband based patient real time monitoring management system characterized in that, Comprise: S1, physiological indicators of smart wristband analysis; S2, based on the physiological indicators of smart wristband analysis, select the sensor type carried by the smart wristband; S3, determine the transmission path and communication protocol of the sensor data, ensure real-time collection of data from the sensor to the cloud or local server; S4, based on the real-time collected sensor data, abnormal detection and early warning; Build an abnormal detection and early warning model. The model combines various physiological indicators and individual differences of patients to detect abnormalities and provide intelligent early warning. Define the physiological indicators monitored by the smart wristband: heart rate , blood oxygen saturation , blood pressure , body temperature , then there is: representing a time point collected physiological indicator data; a sequence of physiological indicator data over a past period of time; The abnormal detection and early warning model includes: Weighted abnormal score; Overall abnormal score; Dynamic adjustment threshold; Trigger the early warning mechanism; S5, based on the real-time collected sensor data, analyze the patient's long-term health data and lifestyle, and establish a personalized health trend model to predict the future health status of the patient wearing the smart wristband. The abnormality detection early warning model defines an abnormality score of each physiological index when performing a weighted abnormality score As shown below: ； Wherein, is the current time the value of the first physiological indicator the value of the first physiological indicator and In particular, the physiological indicator is the mean and standard deviation of the patient's historical data, representing the normal fluctuation range. is a weight coefficient of the index, used to represent the importance of different indexes; The abnormal scores of all physiological indexes are weighted and averaged to obtain the overall abnormal score : ； Because the health baseline of different patients is quite different, the dynamic adjustment threshold is introduced to avoid false alarms. The dynamic adjustment threshold is calculated as follows: is the number of physiological indicators monitored; Overall abnormality score for measuring the abnormality degree of each physiological index at the current time Wherein, ； Wherein, is a basic threshold value determined based on statistical properties of the entire patient data; is an adjustment factor that represents the sensitivity of the model to dynamically adjust the threshold, fine-tuned according to the patient's health history; is the overall anomaly score of the previous time instant, threshold is dynamically adjusted according to the anomaly score of the previous time instant; The overall anomaly score Exceeding the threshold If this is detected, it is considered abnormal, triggering an early warning mechanism. The warning signal will be immediately pushed to the patient or medical personnel via smart devices or mobile applications; the urgency of the warning depends on... The values ​​are categorized into different levels. If the value is higher than the threshold, an emergency alarm is issued; if the value is lower than the threshold, a normal alarm is issued. In the aforementioned health trend model, the weights Dynamic adjustments are made to make the impact of each physiological indicator on health prediction more flexible and personalized; the dynamic adjustment formula for the weights is shown below: ； In steps S1 and S2, the physiological indicators of the smart wristband include heart rate, blood pressure, body temperature, and blood oxygen saturation, and the sensor types include heart rate sensor, blood pressure sensor, temperature sensor, and blood oxygen sensor. for the time being corresponding physiological indicators weight of the physiological indicator; is an error measure of the prediction result, expressed by the difference between the model prediction value and the actual value; is the learning rate of each physiological indicator, used to control the sensitivity of weight update.

2. The real time patient monitoring management system based on smart wristband as claimed in claim 1 wherein, The health trend model defines the historical data of each physiological indicator as:

3. The real time patient monitoring management system based on smart wristband as claimed in claim 1 wherein, In the step S5, the health trend model dynamically correlates the physiological indicators: heart rate , blood oxygen saturation , blood pressure , body temperature with the patient health history to form a personalized health trend to predict the health status at a future time .

4. The real time patient monitoring management system based on smart wristband as claimed in claim 3 wherein, Wherein, For a moment Heart rate, blood pressure, blood oxygen saturation, and body temperature; a weight coefficient for each physiological indicator at the time instant of the time instant Predicting future health status by weighting historical data : The functional modules of the system include data acquisition and sensing module, abnormal detection and early warning module, health trend prediction module, data management module, and user interaction module. represents a predicted health state; represents the change in the physiological indicator of item represents the change in the physiological indicator of item is the time corresponding to the physiological indicator weight; is a control change amount, and is a control change amount of the control variable, and is a control change amount of the control variable, and is a control change amount of the control variable, and is a control change amount of the control variable, and is a control change amount of the control 5. The real time patient monitoring management system based on smart wristband as claimed in claim 1 wherein, In the functional module:

6. The real time patient monitoring management system based on smart wristband as claimed in claim 5 wherein, The data acquisition and sensing module is used to collect real-time physiological indicator data and transmit it to the cloud or local server; The abnormal detection and early warning module is based on the collected data to detect abnormalities and provide early warning; The health trend prediction module is based on the collected data to predict the future health status of the patient wearing the smart wristband; The data management module provides data storage and security management functions; The user interaction module provides a user interaction interface for viewing health data and early warning information. ​

Images