A method and system for monitoring patient physiological state data

Abstract

The application discloses a kind of methods, systems, equipment, medium and program for monitoring patient physiological state data, belong to data processing technical field.Method includes obtaining patient physiological state monitoring data, and identify missing value in patient physiological state monitoring data, obtain missing data;According to the physiological state data of patient and influence relationship, data interpolation is carried out to missing data, and the physiological state monitoring data after interpolation is obtained;According to the physiological state monitoring data after interpolation, the health status of patient is evaluated.The application can provide personalized data interpolation result according to the influence relationship between different physiological state data of patient, improve the accuracy of patient physiological state data.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, system, device, medium, and program for monitoring patient physiological status data. Background Technology

[0002] Real-time monitoring of patients' physiological status data is crucial for doctors to assess patients' post-operative recovery and manage the health of patients with chronic diseases. With the development of medical technology and artificial intelligence, various wearable intelligent monitoring devices for patients' physiological status data, such as smartwatches, are increasingly widely used in the healthcare field. These wearable devices collect patients' physiological status data in real time through their sensors and utilize transmission modules such as Bluetooth and Wi-Fi for remote monitoring, enabling telemedicine and home monitoring for the elderly and patients with chronic diseases. However, wearable devices are susceptible to interference from factors such as patient wearing procedures, signal transmission stability, and patient sweating, which may lead to partial data loss and affect the accuracy of patient health assessments.

[0003] Traditional methods for imputing missing values ​​in monitoring data involve averaging the acquired monitoring data before and after the missing value, or predicting the missing value based on the trend of changes in the acquired monitoring data. Traditional imputation methods can obtain relatively accurate results when the patient's physiological state data is relatively stable and has few missing values. However, when the patient's physiological state data fluctuates, or when multiple consecutive data points are missing, traditional imputation methods cannot combine the analysis of the different physiological state data change characteristics of different patients, and the results obtained are often less accurate. Summary of the Invention

[0004] To address the problem of low accuracy in imputation results obtained in existing technologies when patient physiological state data fluctuates significantly or contains multiple missing values, this invention provides a method for monitoring patient physiological state data. This method can provide personalized data imputation results based on the influence relationships between different physiological state data points, thereby improving the accuracy of patient physiological state data.

[0005] To achieve the above objectives, the present invention provides the following technical solution.

[0006] In a first aspect, the present invention provides a method for monitoring patient physiological state data, comprising: obtaining patient physiological state monitoring data and identifying missing values ​​in the patient physiological state monitoring data to obtain missing data; imputing the missing data according to the performance and influence relationship of the patient's physiological state data to obtain imputed physiological state monitoring data; and assessing the patient's health status based on the imputed physiological state monitoring data.

[0007] As a further improvement of the present invention, the step of obtaining patient physiological state monitoring data and identifying missing values ​​in the patient physiological state monitoring data to obtain missing data includes: real-time monitoring of patient physiological state data through a smart wearable device to obtain patient physiological state monitoring data, including: identifying undetected missing values ​​in the patient physiological state monitoring data to obtain missing data.

[0008] As a further improvement of the present invention, the real-time monitoring of the patient's physiological state data includes: real-time monitoring of the patient's heart rate and blood oxygen data, and calculating the patient's blood pressure data in combination with pulse wave transmission time; real-time monitoring of the patient's exercise status; real-time monitoring of the patient's body temperature; and real-time monitoring of the patient's cardiac electrical activity to generate an electrocardiogram.

[0009] As a further improvement of the present invention, the step of imputing missing data based on the patient's physiological state data performance and influence relationships to obtain imputed physiological state monitoring data includes: selecting data with similar motion states to the missing values ​​at the time corresponding to the motion states in the patient's historical data to obtain the physiological state data change performance in the patient's historical data; analyzing the influence relationships between several physiological state data based on the physiological state data change performance in the patient's historical data; calculating the interpolation results corresponding to the missing values ​​based on the patient's physiological state data performance and influence relationships; and imputing the missing data based on the interpolation results to obtain imputed physiological state monitoring data.

[0010] As a further improvement of the present invention, the missing interpolation result includes: In the formula: This represents the interpolation result for the current missing value; This represents the total number of historical data points to be analyzed. This represents the weight of the influence of the j-th historical data point on the interpolation result in terms of the correlation between physiological state data; This indicates the degree of similarity between the p-th type of physiological state data in the j-th historical data point and the corresponding value at the current missing value monitoring time; Represents the maximum value function; This represents the number of data points used to calculate the similarity of physiological state change trends corresponding to missing values. This represents the value of the physiological state data corresponding to the missing value at the t-th monitoring time before the j-th historical data point; This represents the value of the physiological state data at the t-th monitoring time before the current missing value; This indicates the degree of similarity between historical data and the current monitoring time in terms of the changing trend of physiological state data corresponding to the current missing value; This represents the value of the j-th historical data point to be analyzed in the physiological state data corresponding to the current missing value.

[0011] As a further improvement of the present invention, the step of assessing the patient's health status based on the interpolated physiological state monitoring data includes: performing threshold monitoring and assessment on multidimensional physiological state data to obtain a threshold for each dimension; determining whether there are any data in the interpolated physiological state monitoring data that exceed the threshold for that dimension; and considering that the current health status of the patient is at risk if there are any data in the monitoring data that exceed the threshold.

[0012] Secondly, the present invention provides a system for monitoring patient physiological state data, comprising: a missing data module for obtaining patient physiological state monitoring data and identifying missing values ​​in the patient physiological state monitoring data to obtain missing data; an imputation processing module for imputing the missing data according to the patient's physiological state data performance and influence relationship to obtain imputed physiological state monitoring data; and an assessment module for assessing the patient's health status based on the imputed physiological state monitoring data.

[0013] Thirdly, the present invention provides an electronic device including 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 the method for monitoring patient physiological state data.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for monitoring patient physiological state data.

[0015] Fifthly, the present invention provides a computer program product including computer instructions that, when executed by a processor, implement the steps of the method for monitoring patient physiological state data.

[0016] Compared with existing technologies, this invention has the following advantages: This method effectively solves the problem of low accuracy in imputation results when patient physiological state data fluctuates greatly or has multiple missing values. By combining the influence relationships between patient physiological state data, personalized imputation results are achieved, thereby improving the accuracy of data imputation. Specifically, this method analyzes the patient's historical physiological state monitoring data, identifies the mutual influence and dependence relationships between various physiological state data, and when data is missing, comprehensively considers the performance of other physiological states of the patient, imputing the missing data based on these relationships. In this process, the imputation results not only conform to the individual physiological characteristics of the patient, but also overcome the problems of excessive data fluctuation or inaccuracy that may occur in traditional imputation methods. Compared with traditional single imputation methods, the imputation scheme of this invention is more flexible and targeted. It can provide imputation data that conforms to the individual characteristics of different patients based on their physiological state differences, thereby more accurately reflecting the patient's physiological state. In addition, this method particularly emphasizes considering the data performance of other related physiological states of the patient when data is missing, making the imputation data more consistent and reasonable, avoiding the situation in traditional methods where the imputation values ​​may not conform to the actual physiological fluctuation patterns. This imputation method, based on the interaction between personalized patient data and physiological status, not only improves the accuracy of data imputation but also effectively reduces the negative impact of missing data on patient health assessment. In the process of monitoring patient health status, missing data may lead to incorrect assessments or delayed diagnoses. The imputation method provided by this invention can fill the information gaps caused by missing data, thereby more accurately assessing the patient's health status and improving the quality and efficiency of medical services. Attached Figure Description

[0017] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way. In the drawings: Figure 1 This is a flowchart illustrating a method for monitoring patient physiological status data according to the present invention. Figure 2 This is a time-acceleration coordinate graph in a method for monitoring patient physiological state data according to the present invention; Figure 3 This is a "body temperature-blood pressure" coordinate graph in a method for monitoring patient physiological status data according to the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] To address the problem of low accuracy in imputation results obtained from existing technologies when patient physiological state data fluctuates significantly or contains multiple missing values, this invention provides a method for monitoring patient physiological state data, such as... Figure 1 As shown, the method includes: S100: obtaining patient physiological state monitoring data and identifying missing values ​​in the patient physiological state monitoring data to obtain missing data; S200: performing data imputation on the missing data based on the patient's physiological state data performance and influence relationship to obtain imputed physiological state monitoring data; S300: assessing the patient's health status based on the imputed physiological state monitoring data.

[0021] This method analyzes the influence relationship between different physiological state data in the patient's historical monitoring data, and calculates the interpolated data value at the monitoring time corresponding to the missing data by combining the patient's other physiological state data. This ensures that the interpolated data can meet the physiological state data change characteristics of different patients, and can effectively solve the problem of reduced accuracy of interpolation results due to multiple missing data, thereby reducing the impact of missing data on the assessment of the patient's health status.

[0022] The present invention will be further explained and described below with reference to the accompanying drawings.

[0023] The present invention discloses a method for monitoring patient physiological state data, specifically comprising the following: The system uses sensors in smart wearable devices to monitor patients' physiological status data in real time and obtains such data.

[0024] Smartwatches are wearable devices that monitor patients' physiological data and play an extremely important role in telemedicine, chronic disease management, and health monitoring. This method uses smartwatches to monitor patients' physiological data in real time.

[0025] The smartwatch primarily uses a PPG sensor to monitor the patient's heart rate and blood oxygen data, and combines this with pulse wave transit time (PWTT) to estimate the patient's blood pressure; it uses an accelerometer to monitor the patient's movement status; an infrared temperature sensor to monitor the patient's body temperature; and electrodes to detect the heart's electrical activity, generating an electrocardiogram (ECG). The sensors collect the patient's corresponding physiological data once per second.

[0026] Because sensor monitoring data may be affected by sensor contact stability and data transmission stability, certain data may not be detected at certain monitoring times. These undetected data are the missing values ​​that need to be interpolated.

[0027] step Based on the influence relationship between different physiological state data of the patient, and combined with the current movement state of the patient, the interpolation result of the monitoring time corresponding to the missing data is calculated.

[0028] Because the patterns of physiological state data changes in patients may vary under different exercise states, the motion state of patients during the time period corresponding to the missing value is obtained based on the patient's acceleration data within that period. Data from historical periods that are similar to the patient's motion state during the current period are then selected for further analysis of the interpolation result corresponding to the missing value. Since changes in a patient's health status affect multiple physiological state data, there are certain correlations between different physiological state data. Therefore, by analyzing the correlations between changes in different physiological state data, the influence patterns between them are obtained. Finally, combined with the patient's other physiological state data at the monitoring time corresponding to the current missing value, the interpolation result corresponding to that missing value is calculated.

[0029] Therefore, the present invention performs data imputation for missing values ​​by analyzing the influence relationship between different physiological state data as follows: a. Based on the patient's historical data of motion state, select data with similar motion state to the time corresponding to the missing value.

[0030] b. Analyze the influence relationships between different physiological state data based on the changes in different physiological state data in the patient's historical data.

[0031] c. Calculate the interpolation results corresponding to missing values ​​based on the influence relationship between data of different physiological states.

[0032] Specifically, the steps are as follows: a. Based on the patient's historical motion state, filter out data that have similar motion states to the time corresponding to the missing values.

[0033] Patients' physiological state data are closely related to their motor state. The patterns of change in patients' physiological state data also differ under different motor states. Therefore, by selecting data with similar motor states to the time corresponding to the missing values ​​and analyzing the influence relationship between different physiological state data, the results obtained can better match the patterns of physiological state data at the time corresponding to the missing values.

[0034] Because the impact of a patient's movement state on physiological state data is lagging, physiological state data at a given moment is generated after continuous movement, and is therefore often influenced by the movement state in the preceding period. Therefore, a 1-minute time window is used here, and the movement state corresponding to the physiological state data at each monitoring moment represents the movement performance within the preceding 1-minute period.

[0035] The patient's motion status is mainly reflected by the patient's acceleration data. Therefore, based on the acceleration change within the time period corresponding to each historical data point (the time period 1 minute before the monitoring time) and the acceleration change trend within the time period corresponding to the current missing value, the similarity of the motion status between the historical data and the time period of the current missing value is calculated.

[0036] Plot the acceleration data for each time period as a time-acceleration coordinate graph. To facilitate comparison of the similarity of different fitted curves, the time on the horizontal axis represents the i-th data point within that time period. ),like Figure 2 As shown: Based on the proximity of the acceleration of the corresponding data point within the time period corresponding to each historical data point and the current missing value, the similarity of the motion state within the time period corresponding to the historical data and the current missing value is calculated. Since the motion state is usually continuous, that is, the frequency and amplitude of acceleration changes are small, and the influence of the motion state on the patient's physiological state data also has a certain degree of continuity, if an acceleration value is missing within a time period, the acceleration value at the moment before the missing value is used as the acceleration value at the moment corresponding to that missing value.

[0037] Construction formula: In the formula: This indicates the similarity of the motion state between the u-th historical data point and the current missing value. This indicates the number of monitoring moments within the time period corresponding to the motion state. This represents the acceleration value at the ith monitoring moment within the time period corresponding to the u-th historical data point. This represents the acceleration value at the i-th monitoring moment within the time period corresponding to the currently missing value. This represents the sum of the acceleration differences between the u-th historical data point and the current missing value within the corresponding time period. The more similar the patient's motion state is between historical data and the time period corresponding to the current missing value, the closer the acceleration difference is to 0. This indicates that the smaller the absolute value of the sum of acceleration differences at each moment within the corresponding time period, the more similar the historical data is to the motion state of the current missing value. Ensure that the fraction is meaningful. This represents the normalization function.

[0038] when If the historical data is considered to be similar to the motion state of the current missing value, then these historical data are used as the historical data to be analyzed, and the influence relationship between different physiological state data is further obtained based on the historical data to be analyzed.

[0039] b. Analyze the influence relationships between different physiological state data based on the changes in different physiological state data in the patient's historical data.

[0040] Different physiological state data may change due to the same influencing factor, so there is a certain correlation between the changes in different physiological state data. Furthermore, because different patients have different patterns of physiological state data change due to differences in age, physical condition, etc., data imputation using only methods such as averaging cannot meet the individual differences of different patients. Therefore, it is necessary to analyze the influence relationship between different physiological state data of the current patient based on the historical data to be analyzed, and use this as the basis for data imputation of missing values.

[0041] Because the numerical ranges of data from different physiological states are different, it is not possible to directly analyze the correlation between data from different physiological states. Therefore, all physiological state data are first normalized: in, This represents the normalized value of the p-th physiological state data corresponding to the j-th historical data to be analyzed. This represents the original monitoring value of the p-th physiological state data corresponding to the j-th historical data to be analyzed. This represents the maximum value of the p-th physiological state data in the historical data. This represents the minimum value of the p-th physiological state data in the historical data.

[0042] If a certain physiological state data (let's call it type A physiological state data) has a strong correlation with a missing physiological state data (let's call it type B physiological state data), then when the historical data matches the physiological state data (type A physiological state data) at the monitoring time corresponding to the current missing value, data imputation can be performed on the current missing value based on the corresponding physiological state data (type B physiological state data). Therefore, the stronger the correlation between other physiological state data and the current missing value, the greater their influence weight during data imputation. Thus, it is necessary to calculate the correlation between other physiological state data and the current missing value to obtain the influence weight of each physiological state data on the data imputation result.

[0043] First, the normalized physiological state data are placed into their respective coordinate systems, such as... Figure 3As shown, taking body temperature (physiological state data to be analyzed) and blood pressure (physiological state corresponding to missing values) data as examples: the least squares method is used to fit the data points in the coordinate system to obtain the fitted curve. The coefficient of determination of the fitted curve is then calculated. This is used to indicate the degree of correlation between the two physiological state data: in, This represents the true value of the ordinate of the i-th data point in the coordinate system. This represents the fitted ordinate value of the i-th data point in the coordinate system. This represents the average of the true values ​​on the vertical axis of all data (here, the average of the body temperature data).

[0044] Therefore, the correlation between each physiological state data and the physiological state data corresponding to the current missing value is calculated.

[0045] c. Calculate the interpolation results corresponding to missing values ​​based on the influence relationship between data of different physiological states.

[0046] If the physiological state data at a given historical data point is close to the value of the current missing value at a given monitoring time, and the correlation between this physiological state data and the missing value is high, then the physiological state data corresponding to the current missing value at that historical data point should also be close to the true value of the missing value. Therefore, firstly, based on the difference between the corresponding value at the monitoring time of the current missing value and the physiological state data at each historical data point to be analyzed, the degree of closeness between each physiological state data at that historical data point and the current corresponding value is calculated: In the formula, This indicates the degree of similarity between the p-th type of physiological state data in the j-th historical data point and the corresponding value at the current missing value monitoring time. This represents the value of the p-th physiological state data in the j-th historical data point. This represents the p-th type of physiological state data value at the current missing value monitoring time. This indicates that the smaller the absolute value of the difference between corresponding values, the closer the two values ​​are. Ensure that the fraction is meaningful.

[0047] For the j-th historical data to be analyzed, according to The correlation of the maximum value with respect to physiological state data As a weighting factor for the influence of historical data on the interpolation results in different physiological states. .

[0048] Furthermore, changes in a patient's physiological state data are typically gradual rather than abrupt. Therefore, historical data with similar trends to the current missing value over a previous period are closer to the true value the current missing value should represent. Thus, the influence weight of each historical data point is adjusted based on its proximity to the 10 monitoring points preceding the missing value in terms of that physiological state data.

[0049] Therefore, the interpolation result of the current missing value is calculated based on the weighted average of historical data.

[0050] Construction formula: In the formula: This represents the interpolation result for the current missing value. This indicates the total number of historical data points to be analyzed. This represents the weight of the j-th historical data point in terms of its correlation with physiological state data on the interpolation result. This indicates the degree of similarity between the p-th type of physiological state data in the j-th historical data point and the corresponding value at the current missing value monitoring time. This represents the maximum value function. This represents the number of data points used to calculate the similarity of physiological state change trends corresponding to missing values. This represents the value of the physiological state data corresponding to the missing value at the t-th monitoring time before the j-th historical data point. This represents the value of the physiological state data at the t-th monitoring time before the current missing value. This indicates the degree of similarity between historical data and the current monitoring time in terms of the changing trend of physiological state data corresponding to the current missing value. This represents the value of the j-th historical data point to be analyzed in the physiological state data corresponding to the current missing value.

[0051] Based on the physiological state data after data interpolation, assess the patient's current health status.

[0052] The interpolated physiological state monitoring data is obtained through S2 described above, and threshold monitoring and evaluation are performed on the multidimensional physiological state data. The threshold for each dimension is the corresponding indicator threshold for abnormal physiological signs in that dimension. When any data in the monitoring data exceeds the threshold, the patient's current health status is considered to be at risk. Therefore, interpolation improves the accuracy and completeness of the monitoring data, thereby obtaining more precise results for monitoring the patient's physiological state.

[0053] In summary, this method utilizes the correlation between data from different physiological states, combined with the changing trends of the data types corresponding to the missing values, to calculate the true values ​​that the missing values ​​should correspond to. This makes the interpolation results more consistent with the changing patterns of the patient's own physiological state data, effectively improving the accuracy of data imputation results. Furthermore, before analyzing the correlation between data from different physiological states, this invention first performs preliminary screening of historical data based on the patient's movement state, analyzing historical data similar to the current patient's movement state. This effectively reduces the interference of differences in the changing patterns of physiological data under different movement states on the final data imputation results. Therefore, this method can provide personalized imputation results by analyzing the relationships between data from different physiological states, solving the problem of insufficient accuracy in existing imputation methods. Secondly, it effectively overcomes the challenge of reduced accuracy in imputation results when multiple missing data points are present, ensuring that the imputed data better matches the individual physiological fluctuation characteristics of the patient. Moreover, it reduces the impact of missing data on the assessment of the patient's health status, improving the accuracy and reliability of health monitoring.

[0054] The second objective of this invention is to provide a system for monitoring patient physiological status data, comprising: a missing data module for obtaining patient physiological status monitoring data and identifying missing values ​​in the patient physiological status monitoring data to obtain missing data; an imputation processing module for imputing the missing data based on the patient's physiological status data performance and influence relationships to obtain imputed physiological status monitoring data; and an assessment module for assessing the patient's health status based on the imputed physiological status monitoring data.

[0055] A third objective of this invention is to provide an electronic device comprising a processor, a memory, and a display screen. The memory and display screen are both connected to the processor, such as via a bus. Optionally, the electronic device may further include a transceiver. It should be noted that in practical applications, the transceiver is not limited to a single unit, and the structure of this electronic device does not constitute a limitation on the embodiments of this application.

[0056] The processor can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP (Digital Signal Processor) and a microprocessor, etc.

[0057] A bus can include a pathway for transmitting information between the aforementioned components. The bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc.

[0058] The memory may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited to these.

[0059] The memory stores the application code that executes the solution of this application, and its execution is controlled by the processor. The processor executes the application code stored in the memory to implement the content shown in the foregoing method embodiments.

[0060] The electronic device in this embodiment is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0061] A fourth objective of this invention is to provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the aforementioned functions. Figure 1 The illustrated method embodiments include various processes. For example, a memory may include instructions that can be executed by a processor of an electronic device to perform the described method.

[0062] A computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), staging random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0063] A fifth objective of this invention is to provide a computer program product comprising computer instructions that, when executed by a processor, implement the above-described... Figure 1 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0064] Many embodiments and applications beyond the examples provided will be apparent to those skilled in the art upon reading the foregoing description. Therefore, the scope of this teaching should not be determined by reference to the foregoing description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

[0065] The above content provides a further detailed description of the present invention. It should not be construed that the specific embodiments of the present invention are limited to this. For those skilled in the art, several simple deductions or substitutions can be made without departing from the concept of the present invention, and all such deductions or substitutions should be considered to fall within the scope of protection of the present invention as defined by the submitted claims.

Claims

1. A method for monitoring patient physiological state data, characterized in that, include: Obtain patient physiological status monitoring data and identify missing values ​​in the patient physiological status monitoring data to obtain missing data; Based on the patient's physiological status data and their influencing relationships, missing data are imputed to obtain imputed physiological status monitoring data; the patient's health status is then assessed based on the imputed physiological status monitoring data.

2. A method for monitoring patient physiological state data according to claim 1, characterized in that, The process of obtaining patient physiological state monitoring data and identifying missing values ​​in the patient physiological state monitoring data to obtain missing data includes: real-time monitoring of patient physiological state data through a smart wearable device to obtain patient physiological state monitoring data, including: identifying undetected missing values ​​in the patient physiological state monitoring data to obtain missing data.

3. A method for monitoring patient physiological state data according to claim 2, characterized in that, The real-time monitoring of the patient's physiological status data includes: real-time monitoring of the patient's heart rate and blood oxygen data, and calculating the patient's blood pressure data by combining pulse wave transmission time; real-time monitoring of the patient's exercise status; real-time monitoring of the patient's body temperature; and real-time monitoring of the patient's cardiac electrical activity to generate an electrocardiogram.

4. A method for monitoring patient physiological state data according to claim 1, characterized in that, The process of imputing missing data based on the patient's physiological state data and their influencing relationships to obtain imputed physiological state monitoring data includes: selecting data with similar motion states to the missing values ​​at the time corresponding to the motion states in the patient's historical data to obtain the physiological state data change patterns in the patient's historical data; analyzing the influencing relationships between several physiological state data based on the physiological state data change patterns in the patient's historical data; calculating the interpolation results corresponding to the missing values ​​based on the patient's physiological state data and their influencing relationships; and imputing the missing data based on the interpolation results to obtain the imputed physiological state monitoring data.

5. A method for monitoring patient physiological state data according to claim 4, characterized in that, The interpolation results corresponding to the missing values ​​include: In the formula: This represents the interpolation result for the current missing value; This represents the total number of historical data points to be analyzed. This represents the weight of the influence of the j-th historical data point on the interpolation result in terms of the correlation between physiological state data; This indicates the degree of similarity between the p-th type of physiological state data in the j-th historical data point and the corresponding value at the current missing value monitoring time; Represents the maximum value function; This represents the number of data points used to calculate the similarity of physiological state change trends corresponding to missing values. This represents the value of the physiological state data corresponding to the missing value at the t-th monitoring time before the j-th historical data point; This represents the value of the physiological state data at the t-th monitoring time before the current missing value; This indicates the degree of similarity between historical data and the current monitoring time in terms of the changing trend of physiological state data corresponding to the current missing value; This represents the value of the j-th historical data point to be analyzed in the physiological state data corresponding to the current missing value.

6. A method for monitoring patient physiological state data according to claim 1, characterized in that, The assessment of the patient's health status based on the interpolated physiological state monitoring data includes: performing threshold monitoring and assessment on multidimensional physiological state data to obtain a threshold for each dimension; determining whether any data in the interpolated physiological state monitoring data exceeds the threshold for that dimension; and considering the current health status of the patient to be at risk if any data in the monitoring data exceeds the threshold.

7. A system for monitoring patient physiological state data, characterized in that, include: Missing data module: Used to obtain patient physiological status monitoring data and identify missing values ​​in the patient physiological status monitoring data to obtain missing data; The imputation processing module is used to imput missing data based on the patient's physiological status data and its influence, and to obtain imputed physiological status monitoring data. The assessment module is used to assess the patient's health status based on the imputed physiological status monitoring data.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method for monitoring patient physiological state data as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for monitoring patient physiological state data as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes computer instructions that, when executed by a processor, implement the steps of a method for monitoring patient physiological state data as described in any one of claims 1-6.

Images