Patient state intelligent monitoring system and method

Abstract

The invention discloses a patient state intelligent monitoring system and method, and relates to the technical field of medical data processing. Comprising the steps that physiological data and microenvironment parameters of a patient are collected through a multi-mode sensor, and an initial data set is formed; performing environmental error correction on the physiological data of the patient by using a dynamic compensation algorithm to generate a preliminary correction data set; calculating motion state characteristic parameters of the patient, and judging whether significant motion artifacts exist or not; for the detected artifact interference signal, correcting the physiological data in the preliminary correction data set by adopting a dynamic artifact removing algorithm to obtain a correction data set; and determining the priority of each physiological data, and combining the correction data set to form real-time output. The method can overcome monitoring data distortion caused by environmental noise, motion artifacts and other problems, improves the precision and reliability of a monitoring result, and has dynamic adaptability and convenience.

Description

Technical Field

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

[0002] With the rapid development of medical technology and sensor technology, non-invasive physiological monitoring has gradually become an important means of health management and disease diagnosis and treatment. Multimodal sensors can collect patients' physiological data in real time, such as heart rate, blood oxygen saturation, blood pressure and motion state parameters, to provide medical workers with accurate feedback on the patient's dynamic state. At the same time, the popularity of environmental sensors has enabled a more comprehensive recording and analysis of the impact of microenvironmental parameters (such as temperature, humidity, air pressure, etc.) on human physiological data. Based on this, many real-time monitoring systems use algorithms to process and correct physiological signals to improve data reliability.

[0003] Although some existing patient status monitoring systems use simple filtering algorithms to reduce the impact of noise or artifacts, these methods often ignore the combined interference of motion artifacts and microenvironmental factors, resulting in low accuracy of monitoring data. In addition, the fusion processing capabilities of multimodal data are weak, and the complementarity between different physiological parameters is not fully utilized to improve the monitoring effect. Especially in medical application scenarios with high real-time requirements, how to quickly and dynamically correct data and output reliable comprehensive monitoring results is still a problem that needs to be solved by existing technologies. Summary of the invention

[0004] In view of the problems existing in the above background technology, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to solve the problem of insufficient processing capability of environmental interference and motion artifacts by improving the dynamic correction capability and real-time performance of data.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an intelligent patient status monitoring method, which includes collecting patient physiological data, including heart rate data, blood oxygen saturation data and motion state parameters, through a multimodal sensor, and at the same time, obtaining microenvironment parameters, and the microenvironment parameters are bound to the physiological data in real time to form an initial data set; using a dynamic compensation algorithm to correct environmental errors of the patient's heart rate data and blood oxygen saturation data to generate a preliminary correction data set; calculating the patient's motion state characteristic parameters to determine whether there are significant motion artifacts; for the detected artifact interference signal, using a dynamic de-artifacting algorithm to correct the heart rate data and blood oxygen saturation data in the preliminary correction data set to obtain a correction data set; according to the patient's current state and microenvironment parameters, determine the priority of each physiological data, and combine the correction data set to form a real-time output.

[0007] As a preferred solution of the patient status intelligent monitoring method of the present invention, wherein: the patient's heart rate data and blood oxygen saturation data are corrected for environmental errors using a dynamic compensation algorithm to generate a preliminary correction data set, including the following steps: using an adaptive filtering method to correct the heart rate data and blood oxygen saturation data Preprocessing is performed to separate the effective fluctuation signal and the environmental interference components to obtain the denoised heart rate fluctuation characteristic value And the blood oxygen saturation fluctuation characteristic value after denoising ; According to the temperature data, humidity data and air pressure data in the microenvironment parameters, the multivariable compensation factor set is calculated through the dynamic mapping model ; Combined with heart rate data and blood oxygen saturation data The denoising fluctuation characteristics of the dynamic compensation factor set are analyzed by using the time series analysis method. Perform fine-tuning to eliminate the impact of transient environmental disturbances on the stability of the compensation model and obtain an updated set of compensation factors ; The compensation factor set to be updated Apply to heart rate data and blood oxygen saturation data , respectively, perform data correction through the error correction model to generate a preliminary correction data set .

[0008] As a preferred solution of the patient status intelligent monitoring method of the present invention, wherein: the multivariable compensation factor set The calculation formula is as follows: ; ; in, is the model coefficient, is the ambient temperature, is the ambient humidity, is the ambient air pressure, is the dynamic compensation factor for heart rate data, is the dynamic compensation factor for blood oxygen saturation data.

[0009] As a preferred solution of the patient status intelligent monitoring method of the present invention, wherein: the dynamic compensation factor set The calculation formula for fine correction is: The dynamic compensation factor is optimized by combining the original fluctuation characteristics of heart rate and blood oxygen through the time series analysis method to eliminate short-term disturbance errors. The optimized compensation factor is calculated as follows: ; ; in, is the optimized dynamic compensation factor for heart rate data, is the optimized dynamic compensation factor for blood oxygen saturation data.

[0010] As a preferred solution of the patient status intelligent monitoring method of the present invention, the process of determining whether there is a significant motion artifact is as follows: calculating the patient's motion state characteristics according to the acceleration data and angular velocity data in the motion state parameters, including the motion intensity and the rate of change of motion direction : ; ; in, is the patient’s three-dimensional acceleration data, The three-dimensional angular velocity data of the patient; According to the parameters of the motion state characteristics combined with heart rate data and blood oxygen saturation data The short-term change amplitude of the artifact interference judgment index is calculated : ; in, is the short-term fluctuation amplitude of heart rate, is the short-term fluctuation amplitude of blood oxygen saturation, is the weight coefficient, To preliminarily correct the heart rate data in the data set, The corrected blood oxygen saturation data in the preliminary correction data set; Will With setting threshold For comparison, When , it is determined that there is significant motion artifact.

[0011] As a preferred solution of the patient status intelligent monitoring method of the present invention, the method of correcting the heart rate data and blood oxygen saturation data in the preliminary correction data set using a dynamic artifact removal algorithm includes the following steps: according to the artifact detection result, when it is determined that there is a significant motion artifact, extracting artifact interference signal features; using the extracted artifact interference signal features, using a dynamic artifact removal algorithm based on weighted filtering to perform artifact correction on the heart rate and blood pressure data: ; ; in, is the heart rate data after artifact removal. is the blood oxygen saturation data after artifact removal. and is the dynamic weight factor, and They respectively represent the fluctuation values ​​of heart rate and blood oxygen signal caused by artifact interference.

[0012] As a preferred solution of the patient status intelligent monitoring method described in the present invention, the real-time output includes: the priority rules are set as follows: when all data are within the normal range, the core data is given priority, that is, heart rate, blood oxygen saturation and blood pressure are displayed first; if any abnormal data appears, the abnormal data will be displayed first.

[0013] In a second aspect, the present invention provides a patient status intelligent monitoring system, comprising: A multimodal data acquisition module, which is used to collect patient physiological data, including heart rate data, blood oxygen saturation data and motion state parameters, through a multimodal sensor, and simultaneously obtain microenvironment parameters, which are bound to the physiological data in real time to form an initial data set; A dynamic compensation correction module is used to perform environmental error correction on the patient's heart rate data and blood oxygen saturation data using a dynamic compensation algorithm to generate a preliminary correction data set; The motion artifact analysis module is used to calculate the characteristic parameters of the patient's motion state and determine whether there are significant motion artifacts; A dynamic artifact removal correction module is used to correct the detected artifact interference signal by using a dynamic artifact removal algorithm on the heart rate data and blood oxygen saturation data in the preliminary correction data set to obtain a correction data set; The data display module is used to determine the priority of each physiological data according to the patient's current state and microenvironment parameters, and form a real-time output in combination with the correction data set.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the patient status intelligent monitoring method as described in the first aspect of the present invention are implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the patient status intelligent monitoring method as described in the first aspect of the present invention are implemented.

[0016] The beneficial effects of the present invention are as follows: the dynamic compensation factor of the present invention fully combines the fluctuation characteristics of physiological data and the changes in microenvironment parameters, ensuring that the corrected data can more truly reflect the patient's physiological state, significantly improving the accuracy of physiological data in a dynamic environment; the dynamic artifact removal algorithm effectively eliminates the influence of artifact interference on heart rate and blood oxygen data by fusing motion feature parameters and artifact signal characteristics, ensuring that the corrected data is more credible, significantly improving the accuracy and availability of heart rate and blood oxygen data in the patient's active state; and through priority adjustment and layered display, the monitoring data is more intuitively presented to the user, which helps to quickly capture key health information and improve the ease of use and effectiveness of the monitoring system. The present invention can overcome the distortion of monitoring data caused by environmental noise, motion artifacts and other problems, improve the accuracy and reliability of monitoring results, and at the same time have dynamic adaptability and convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 Flow chart of the method for intelligent monitoring of patient status.

[0019] Figure 2 This is a structural diagram of the patient status intelligent monitoring system. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1: Reference Figure 1~Figure 2, which is the first embodiment of the present invention, provides a method for intelligently monitoring a patient's status, comprising: S1: Collect patient physiological data through multimodal sensors, including but not limited to heart rate data, blood oxygen saturation data and motion state parameters (acceleration data and angular velocity data), and at the same time, obtain microenvironment parameters (ambient temperature, humidity and air pressure data). The microenvironment parameters are bound to the physiological data in real time to form an initial data set.

[0024] Specifically, each sensor records with a unified timestamp to ensure the temporal consistency of multimodal data collection, and the microenvironment data and physiological data are synchronously bound during collection to form temporally continuous multidimensional data.

[0025] Furthermore, the collected raw data are filtered to remove obvious random noise, and the sensor data with different sampling rates are uniformly processed using an interpolation method to ensure the consistency of the sampling points.

[0026] The collected physiological data and microenvironmental parameters are combined into a multidimensional matrix form, which is defined as the initial data set.

[0027] S2: Use a dynamic compensation algorithm to correct environmental errors in the patient's heart rate data and blood oxygen saturation data.

[0028] The specific steps include: S2.1: Using adaptive filtering method to process heart rate data and blood oxygen saturation data Preprocessing is performed to separate the effective fluctuation signal and the environmental interference components to obtain the denoised heart rate fluctuation characteristic value And the blood oxygen saturation fluctuation characteristic value after denoising ; Furthermore, according to the temperature data, humidity data and air pressure data in the microenvironment parameters, the multivariable compensation factor set is calculated through the dynamic mapping model The calculation formula is as follows: ; ; in, is the model coefficient, is the ambient temperature, is the ambient humidity, is the ambient air pressure, is the dynamic compensation factor for heart rate data, is the dynamic compensation factor for blood oxygen saturation data.

[0029] in, Used for dynamic compensation of heart rate data, taking into account the nonlinear offset of photoplethysmography signals caused by temperature and humidity; Used for dynamic compensation of blood oxygen saturation data, taking into account the impact of air pressure changes on the near-infrared signal absorption rate.

[0030] S2.2: Combined with heart rate data and blood oxygen saturation data The denoising fluctuation characteristics of the dynamic compensation factor set are analyzed by using the time series analysis method. Perform fine-tuning to eliminate the impact of transient environmental disturbances on the stability of the compensation model and obtain an updated set of compensation factors .

[0031] Preferably, the dynamic compensation factor is optimized by combining the original fluctuation characteristics of heart rate and blood oxygen through a time series analysis method to eliminate short-term disturbance errors. The optimized compensation factor is calculated as follows: ; ; in, is the optimized dynamic compensation factor for heart rate data, is the optimized dynamic compensation factor for blood oxygen saturation data.

[0032] It should be noted that when the fluctuation characteristics of heart rate and blood oxygen are directly involved in the correction of compensation factors without being processed, they may be affected by interference signals, resulting in the compensation factor being incorrectly corrected, ultimately affecting the accuracy of the correction data. Therefore, a preprocessing step is introduced before the dynamic compensation factor is corrected. The error in the fluctuation characteristics is reduced through independent signal separation or filtering technology, thereby improving the accuracy of the compensation factor.

[0033] S2.3: Update the compensation factor set Apply to heart rate data and blood oxygen saturation data , respectively, to correct the data: ; ; in, and is the weight coefficient, To preliminarily correct the heart rate data in the data set, It is the corrected blood oxygen saturation data in the preliminary correction data set.

[0034] Get the heart rate data after preliminary correction and blood oxygen saturation data , generate a preliminary calibration data set .

[0035] It can be seen that the dynamic mapping model is used to perform nonlinear dynamic compensation on the environmental parameters, and the disturbance error introduced by short-term fluctuations is corrected by the time series analysis method, thereby improving the adaptability and correction accuracy of the compensation factor. The dynamic compensation factor of the microenvironmental parameters is optimized through the feedback of the original fluctuation data of heart rate and blood oxygen each time it is updated, realizing the deep correlation and adaptive correction of multi-source data.

[0036] S3: Use acceleration data and angular velocity data to calculate the patient's motion state characteristic parameters to determine whether there is significant motion artifact; for the detected artifact interference signal, use a dynamic artifact removal algorithm to perform preliminary correction on the data set. Correcting the heart rate data and blood oxygen saturation data in the embodiment includes the following steps: S3.1: Calculate patient motion characteristics, including motion intensity, based on acceleration and angular velocity data and the rate of change of motion direction : ; ; in, is the patient’s three-dimensional acceleration data, It is the three-dimensional angular velocity data of the patient.

[0037] It should be noted that the motion state features are used to determine whether there are significant motion artifacts. The linear acceleration and angular velocity are fused into two parameters: motion intensity and direction change rate, which are used to quantify the degree of artifact interference, facilitating the subsequent determination and removal of artifact signals.

[0038] S3.2: Based on motion state characteristic parameters and , combined with heart rate data and blood oxygen saturation data The short-term change amplitude of the artifact interference judgment index is calculated : ; Will With setting threshold For comparison, When , it is determined that there is significant motion artifact.

[0039] in, is the short-term fluctuation amplitude of heart rate, is the short-term fluctuation amplitude of blood oxygen saturation, is the weight coefficient.

[0040] S3.3: Based on the artifact detection result, when it is determined that there is a significant motion artifact, extract the artifact interference signal features, for example: ; ; in, is the current time point, is the time window length, used to capture short-term artifact fluctuation signals, and They represent the fluctuation values ​​of heart rate and blood oxygen signal caused by artifact interference, respectively. The fluctuation values ​​are used for dynamic artifact removal. For the current time point Heart rate data, For the current time point Blood oxygen saturation data.

[0041] S3.4: Using the extracted artifact signal features, a dynamic artifact removal algorithm based on weighted filtering is used to perform artifact correction on the heart rate and blood pressure data: ; ; in, is the heart rate data after artifact removal. is the blood oxygen saturation data after artifact removal. and is the dynamic weight factor.

[0042] The corrected data set is defined as the corrected data set .

[0043] S4: Determine the priority of each physiological data according to the patient's current state and microenvironment parameters, and combine it with the correction data set , forming real-time output.

[0044] The priority rules are set as follows, for example: When all data are within the normal range, core data are prioritized: heart rate, blood oxygen saturation, and blood pressure are displayed first; If any abnormal indicator increases, the data will be displayed first.

[0045] The output data is presented in a layered form through the display module. Under normal circumstances, core indicators such as heart rate data, blood oxygen saturation data, blood pressure data, etc. are displayed first, and environmental and exercise status data are used as background reference information; if there are abnormal conditions, the abnormal data will be displayed first, followed by the core indicators.

[0046] Furthermore, this embodiment also provides a patient status intelligent monitoring system, including: A multimodal data acquisition module, which is used to collect patient physiological data, including heart rate data, blood oxygen saturation data and motion state parameters, through a multimodal sensor, and simultaneously obtain microenvironment parameters, which are bound to the physiological data in real time to form an initial data set; A dynamic compensation correction module is used to perform environmental error correction on the patient's heart rate data and blood oxygen saturation data using a dynamic compensation algorithm to generate a preliminary correction data set; The motion artifact analysis module is used to calculate the characteristic parameters of the patient's motion state and determine whether there are significant motion artifacts; A dynamic artifact removal correction module is used to correct the detected artifact interference signal by using a dynamic artifact removal algorithm on the heart rate data and blood oxygen saturation data in the preliminary correction data set to obtain a correction data set; The data display module is used to determine the priority of each physiological data according to the patient's current state and microenvironment parameters, and form a real-time output in combination with the correction data set.

[0047] This embodiment also provides a computer device, including 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 implement the patient status intelligent monitoring method proposed in the above embodiment.

[0048] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used 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 the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0049] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for intelligently monitoring the patient's status as proposed in the above embodiment is implemented.

[0050] In summary, the dynamic compensation factor of the present invention fully combines the fluctuation characteristics of physiological data and the changes in microenvironment parameters, ensuring that the corrected data can more truly reflect the patient's physiological state and significantly improve the accuracy of physiological data in a dynamic environment; the dynamic artifact removal algorithm effectively eliminates the influence of artifact interference on heart rate and blood oxygen data by fusing motion feature parameters and artifact signal characteristics, ensuring that the corrected data is more credible, and significantly improving the accuracy and availability of heart rate and blood oxygen data when the patient is active; and through priority adjustment and layered display, the monitoring data is more intuitively presented to the user, which helps to quickly capture key health information and improve the ease of use and effectiveness of the monitoring system. The present invention can overcome the distortion of monitoring data caused by environmental noise, motion artifacts and other problems, improve the accuracy and reliability of monitoring results, and at the same time have dynamic adaptability and convenience.

[0051] Example 2: Referring to Table 1 and Table 2, this is the second example of the present invention. This example provides an intelligent monitoring method for patient status. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0052] In the embodiment, six patients with different physiological conditions (numbered as patient 001 to patient 006) were selected to verify the effectiveness of the patient status intelligent monitoring method proposed in the present invention.

[0053] During the experiment, multimodal sensors were used to collect various physiological data in real time, including heart rate, blood oxygen saturation, temperature, humidity, air pressure and other environmental parameters, as well as acceleration and angular velocity data. In order to ensure the time consistency of the data, all sensors record data with a unified timestamp to ensure the time alignment of data from different sensors. During the data collection process, the environmental temperature, humidity, and air pressure data are bound to the physiological data in real time to form an initial data set.

[0054] After data collection, the original data was first filtered to remove obvious random noise, and the sensor data with different sampling rates were uniformly processed through interpolation methods to ensure the consistency of data sampling points. Then, the heart rate data and blood oxygen saturation data were preprocessed based on the adaptive filtering method to separate the effective fluctuation signal and the environmental interference component, and the denoised heart rate fluctuation characteristic value and blood oxygen saturation fluctuation characteristic value were obtained.

[0055] Next, combined with the microenvironmental parameters (temperature, humidity, and air pressure data), the dynamic compensation factor set was calculated through the dynamic mapping model, and the compensation factor set was corrected through the time series analysis method to eliminate the impact of transient environmental disturbances on the stability of the compensation model. The refined and corrected compensation factor set was applied to the correction of heart rate data and blood oxygen saturation data. Finally, by monitoring the patient's movement status, it was determined whether there was significant motion artifact, and the dynamic artifact removal algorithm was used to further correct the preliminary correction data.

[0056] Based on the calibration data, combined with the patient's current status and microenvironment parameters, the priority of each physiological data is determined, and core data including heart rate and blood oxygen saturation are output in real time. In abnormal situations, abnormal data is output first, thereby providing accurate real-time monitoring data for medical staff. The following is some experimental data: Table 1 Physiological data collection Patient number Heart rate (bpm) Blood oxygen saturation (%) Temperature (°C) humidity(%) Air pressure (hPa) Movement level (m / s²) Patient 001 78 97 37.1 60 1015 0.3 Patient 002 85 96 37.0 55 1016 0.5 Patient 003 90 98 37.2 62 1014 0.4 Patient 004 82 95 37.0 63 1015 0.6 Patient 005 75 99 37.3 58 1014 0.3 Patient 006 88 97 37.1 59 1017 0.5 Table 2 Correction and compensation data Patient number Heart rate compensation factor Blood oxygen saturation compensation factor Corrected heart rate (bpm) Corrected blood oxygen saturation (%) Ambient temperature adjustment (°C) Motion compensation (%) Patient 001 1.02 1.03 78.546 97.621 0.1 0.3 Patient 002 1.05 1.04 86.61 96.828 0.1 0.5 Patient 003 1.03 1.02 91.503 98.294 0.2 0.4 Patient 004 1.01 1.01 82.413 95.583 0.1 0.6 Patient 005 1.02 1.02 75.546 99.294 0.1 0.3 Patient 006 1.04 1.03 88.704 97.621 0.1 0.5 Through comparative analysis of the above table data, firstly, the environmental error correction of heart rate and blood oxygen saturation data was performed by applying dynamic compensation factors. The compensation factors calculated based on microenvironmental parameters (temperature, humidity, air pressure) can effectively compensate for the data deviation caused by environmental changes. The optimized heart rate and blood oxygen saturation data have been significantly improved in multiple patients.

[0057] Furthermore, through the monitoring of the motion state and the detection of artifacts, the dynamic artifact removal algorithm effectively eliminates the interference signals caused by motion, especially when the motion intensity is large (such as patient 004 and patient 006), the data after artifact removal is more accurate, which reflects the advantages of the dynamic correction and artifact removal method of the present invention. In addition, the patient's motion state characteristics (such as acceleration and angular velocity) are combined with the dynamic adjustment of the compensation factor to improve the adaptability and accuracy of data correction.

[0058] Through these data, it can be concluded that the traditional static compensation method and simple environmental parameter compensation fail to fully consider the nonlinear effects of environmental changes and the interference of motion artifacts. The present invention greatly improves the real-time and accuracy of patient physiological data by combining multimodal data, dynamic compensation factor correction and motion artifact removal technology, effectively solves the data deviation problem in the prior art, and has significant practical value.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention 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 invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligently monitoring patient status, characterized in that: include: The patient's physiological data, including heart rate data, blood oxygen saturation data and motion state parameters, are collected through a multimodal sensor, and at the same time, microenvironment parameters are obtained, and the microenvironment parameters are bound to the physiological data in real time to form an initial data set; The patient's heart rate data and blood oxygen saturation data are corrected for environmental errors using a dynamic compensation algorithm to generate a preliminary correction data set; Calculate the patient's motion state characteristic parameters to determine whether there is significant motion artifact; for the detected artifact interference signal, use a dynamic artifact removal algorithm to correct the heart rate data and blood oxygen saturation data in the preliminary correction data set to obtain a correction data set; According to the patient's current state and microenvironment parameters, the priority of each physiological data is determined, and combined with the correction data set to form a real-time output.

2. The method for intelligently monitoring patient status according to claim 1, characterized in that: The method of using a dynamic compensation algorithm to perform environmental error correction on the patient's heart rate data and blood oxygen saturation data to generate a preliminary correction data set includes the following steps: Using adaptive filtering method to process heart rate data and blood oxygen saturation data Preprocessing is performed to separate the effective fluctuation signal and the environmental interference components to obtain the denoised heart rate fluctuation characteristic value And the blood oxygen saturation fluctuation characteristic value after denoising ; According to the temperature data, humidity data and air pressure data in the microenvironment parameters, the multivariable compensation factor set is calculated through the dynamic mapping model ; Combined with heart rate data and blood oxygen saturation data The denoising fluctuation characteristics of the dynamic compensation factor set are analyzed by using the time series analysis method. Perform fine-tuning to eliminate the impact of transient environmental disturbances on the stability of the compensation model and obtain an updated set of compensation factors ; The compensation factor set to be updated Apply to heart rate data and blood oxygen saturation data , respectively, perform data correction through the error correction model to generate a preliminary correction data set .

3. The method for intelligently monitoring patient status according to claim 2, characterized in that: The multivariable compensation factor set The calculation formula is as follows: ； ； in, is the model coefficient, is the ambient temperature, is the ambient humidity, is the ambient air pressure, is the dynamic compensation factor for heart rate data, is the dynamic compensation factor for blood oxygen saturation data.

4. The method for intelligently monitoring patient status according to claim 3, characterized in that: The dynamic compensation factor set The calculation formula for fine-tuning correction is: The dynamic compensation factor is optimized by combining the original fluctuation characteristics of heart rate and blood oxygen through the time series analysis method to eliminate short-term disturbance errors. The optimized compensation factor is calculated as follows: ； ； in, is the optimized dynamic compensation factor for heart rate data, is the optimized dynamic compensation factor for blood oxygen saturation data.

5. The method for intelligently monitoring patient status according to claim 4, characterized in that: The process of determining whether there is a significant motion artifact is as follows: Calculate the patient's motion state characteristics, including motion intensity, based on the acceleration data and angular velocity data in the motion state parameters and the rate of change of motion direction : ； ； in, is the patient’s three-dimensional acceleration data, The three-dimensional angular velocity data of the patient; According to the parameters of the motion state characteristics combined with the short-term change amplitude of the heart rate data and the blood oxygen saturation data, the artifact interference determination index is calculated : ； in, is the short-term fluctuation amplitude of heart rate, is the short-term fluctuation amplitude of blood oxygen saturation, is the weight coefficient, To preliminarily correct the heart rate data in the data set, The corrected blood oxygen saturation data in the preliminary correction data set; Will With setting threshold For comparison, When , it is determined that there is significant motion artifact.

6. The method for intelligently monitoring patient status according to claim 5, characterized in that: The method of correcting the heart rate data and blood oxygen saturation data in the preliminary correction data set by using a dynamic artifact removal algorithm comprises the following steps: According to the artifact detection result, when it is determined that there is a significant motion artifact, the artifact interference signal feature is extracted; By using the extracted artifact interference signal features, a dynamic artifact removal algorithm based on weighted filtering is adopted to perform artifact correction on the heart rate and blood pressure data: ； ； in, is the heart rate data after artifact removal. is the blood oxygen saturation data after artifact removal. and is the dynamic weight factor, and They respectively represent the fluctuation values ​​of heart rate and blood oxygen signal caused by artifact interference.

7. The method for intelligently monitoring patient status according to claim 6, characterized in that: The real-time output includes: The priority rules are set as follows: When all data are within the normal range, core data will be displayed first, that is, heart rate, blood oxygen saturation and blood pressure; If any abnormal data appears, it will be displayed first.

8. A patient status intelligent monitoring system, based on the patient status intelligent monitoring method according to any one of claims 1 to 7, characterized in that: include: A multimodal data acquisition module, which is used to collect patient physiological data, including heart rate data, blood oxygen saturation data and motion state parameters, through a multimodal sensor, and simultaneously obtain microenvironment parameters, which are bound to the physiological data in real time to form an initial data set; A dynamic compensation correction module is used to perform environmental error correction on the patient's heart rate data and blood oxygen saturation data using a dynamic compensation algorithm to generate a preliminary correction data set; The motion artifact analysis module is used to calculate the characteristic parameters of the patient's motion state and determine whether there are significant motion artifacts; A dynamic artifact removal correction module is used to correct the detected artifact interference signal by using a dynamic artifact removal algorithm on the heart rate data and blood oxygen saturation data in the preliminary correction data set to obtain a correction data set; The data display module is used to determine the priority of each physiological data according to the patient's current state and microenvironment parameters, and form a real-time output in combination with the correction data set.

Images