Pain grading assessment system based on multimodal physiological signal fusion

Abstract

The present invention discloses a pain grading assessment system based on multimodal physiological signal fusion, which relates to data processing related fields, including: obtaining a time-series muscle contraction distribution by capturing the muscle tissue contraction of the target area. Calculating the initial temperature field distribution based on the thermal imaging of the target area, performing temperature compensation based on the basic time-series body temperature, and outputting the time-series temperature field distribution. Calling real-time physiological data for analysis, and outputting coupled fluctuation correlation features. After aligning the time-series muscle contraction distribution and the time-series temperature field distribution, extracting dynamic features, outputting ORI correlation features and regional thermodynamic features, and combining the coupled fluctuation correlation features to input the physiological stress grading space, matching and locating the initial stress grading. Performing dynamic threshold compensation on the initial stress grading based on the basic time-series body temperature, and outputting a real-time physiological pain grading. This solves the technical problem of low accuracy of pain assessment in traditional pain assessment methods.

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a pain grading assessment system based on multimodal physiological signal fusion. Background Art

[0002] In medicine and biology, pain assessment often relies on the monitoring and analysis of physiological signals. Traditional pain grading methods typically focus on subjective clinical assessments and lack real-time dynamic monitoring and quantitative analysis of physiological responses. With the continuous advancement of biomedical technology, research on pain grading using multimodal physiological signals is becoming increasingly popular. By combining different physiological characteristics, it is possible to more accurately reflect an individual's physiological stress response and pain status.

[0003] Therefore, the existing pain assessment methods lack accurate real-time physiological data analysis and dynamic update mechanisms, and are unable to fully consider the impact of environmental factors, resulting in technical problems such as low accuracy of pain assessment. Summary of the Invention

[0004] This application provides a pain grading assessment system based on multimodal physiological signal fusion, addressing the technical issues in existing pain assessment methods, which lack accurate real-time physiological data analysis and dynamic update mechanisms, and fail to fully consider the impact of environmental factors, resulting in low accuracy in pain assessment. By combining multimodal physiological signals and using a dynamic stress vector update mechanism, this method can monitor an individual's physiological stress response in real time and visualize changes in stress status through a physiological trajectory sphere model, thereby achieving more accurate and reliable pain grading.

[0005] The present application provides a pain grading assessment system based on multimodal physiological signal fusion, the system comprising: a contraction distribution acquisition module for capturing muscle tissue contraction in a target area to obtain a time-series muscle contraction distribution; a temperature field distribution acquisition module for calculating an initial temperature field distribution based on thermal imaging of the target area, performing temperature compensation based on a basic time-series body temperature transmitted back by an ear temperature sensor, and outputting a time-series temperature field distribution; a correlation feature acquisition module for docking with standard medical equipment to call real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features; a dynamic feature acquisition module for spatially registering the time-series muscle contraction distribution and the time-series temperature field distribution, performing dynamic feature extraction, and outputting ORI correlation features and regional thermodynamic features; a stress grading module for inputting the ORI correlation features, regional thermodynamic features, and coupled fluctuation correlation features into a physiological stress grading space to match and locate the initial stress grading; and a pain grading module for performing dynamic threshold compensation on the initial stress grading based on the basic time-series body temperature, and outputting a real-time physiological pain grading.

[0006] In a possible implementation, the pain grading module is further used to: construct a real-time stress vector based on the ORI association characteristics, regional thermodynamic characteristics and coupled fluctuation association characteristics; preset a stress monitoring window, and dynamically update the real-time stress vector through the stress monitoring window, and output multiple incremental stress vectors; construct a physiological trajectory sphere model based on the multiple incremental stress vectors, and use multiple incremental stress grades to perform visual rendering of the physiological trajectory sphere model.

[0007] In a possible implementation, the correlation feature acquisition module is also used to: acquire respiratory rate and blood pressure parameters in real time through a standard medical equipment interface to obtain respiratory rate time series data and blood pressure parameter time series data; perform phase synchronization analysis on the respiratory rate time series data and blood pressure parameter time series data to construct a respiratory-blood pressure coupling sequence; perform sliding window cross-correlation analysis on the respiratory-blood pressure coupling sequence to output the coupled fluctuation correlation feature.

[0008] In a possible implementation, the correlation feature acquisition module is further used to: construct sliding window parameters based on the standard respiratory cycle, wherein the sliding window parameters include a window length and a sliding step, the window length is H standard respiratory cycles, and the sliding step is 1 / M standard respiratory cycles; based on the sliding window parameters, the respiratory-blood pressure coupling sequence is slidingly divided to output multiple window coupling sequences; using a normalized cross-correlation function, multiple cross-correlation coefficients and multiple coupling delays of the multiple window coupling sequences are calculated; the multiple cross-correlation coefficients are arranged in ascending order, the maximum cross-correlation coefficient is extracted, and the target coupling delay is called accordingly, wherein the maximum cross-correlation coefficient and the target coupling delay constitute the coupling fluctuation correlation feature.

[0009] In a possible implementation, the contraction distribution acquisition module is also used to: when using an 850nm near-infrared light source and a 520nm visible light light source to irradiate the target area in a pulse alternating mode, synchronously capture the dual-wavelength reflected light intensity distribution through a shutter sensor to generate a reflected light intensity alternating sequence; calculate an output light intensity difference sequence based on the reflected light intensity alternating sequence; input the light intensity difference sequence into a tissue deformation association model to perform local deformation inversion to obtain a local deformation variable sequence; perform elastic modulus inversion on the local deformation variable sequence to output an instantaneous elastic modulus sequence; perform sliding window change rate calculation on the instantaneous elastic modulus sequence to output an elastic modulus time series change curve as the time series muscle contraction distribution.

[0010] In a possible implementation, the temperature field distribution acquisition module is further used to: configure a far-infrared thermal imager according to the spatial characteristics of the target area, wherein the target area is located at the center of the field of view of the far-infrared thermal imager; and capture the original temperature of the target area based on the far-infrared thermal imager to obtain a multi-frame original temperature matrix.

[0011] In a possible implementation, the temperature field distribution acquisition module is further used to: collect continuous resting state data of the target user through the ear temperature sensor to construct the basic time-series body temperature; locate the vascular bifurcation point matrix in the target area; after spatially aligning the multiple frames of original temperature matrices with the vascular bifurcation point matrix as a reference feature, calculate the gradient distribution of the original temperature matrices of adjacent frames and output the initial temperature field distribution; perform dynamic temperature compensation on the initial temperature field distribution according to the basic time-series body temperature and output the time-series temperature field distribution.

[0012] In a possible implementation, the dynamic feature acquisition module is also used to: use the vascular bifurcation point matrix as a reference feature to perform cross-modal spatial registration of the temporal muscle contraction distribution and the temporal temperature field distribution, and output the registered muscle contraction distribution and the registered temperature field distribution; calculate the elastic modulus change rate of the registered muscle contraction distribution, locate the peak point of the change rate, and use it as the instantaneous extreme value of muscle contraction; perform peak attenuation tracking starting from the peak point of the change rate, and output a contraction recovery delay window, wherein the contraction recovery delay window and the instantaneous extreme value of muscle contraction constitute the ORI association feature; starting from the regional center of the target area, traverse the registered temperature field distribution to calculate and output the regional temperature difference gradient; perform metabolic heat production prediction on the registered temperature field distribution, and output the regional heat production rate, wherein the regional temperature difference gradient and the regional heat production rate constitute the regional thermodynamic feature.

[0013] In a possible implementation, the stress grading module is further configured to: locally de-privacy-enable multiple sample multimodal physiological features and multiple sample stress ratings; establish the physiological stress grading space based on the standard indicator structure of the sample multimodal physiological features; locate multiple sample particle points in the physiological stress grading space based on the multiple sample multimodal physiological features, and then use the multiple sample stress ratings to identify the multiple sample particle points, thereby completing data filling in the physiological stress grading space; input the ORI association features, regional thermodynamic features, and coupled fluctuation association features into the physiological stress grading space to locate virtual particle points; perform spatial matching of the virtual particle points with the goal of minimizing distance, locate the nearest particle point, and use the sample stress rating of the nearest particle point as the initial stress rating. The sample multimodal physiological features include sample ORI features, sample thermodynamic features, and sample coupling features.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0015] The present application provides a pain grading assessment system based on multimodal physiological signal fusion, comprising: a contraction distribution acquisition module for capturing muscle tissue contraction in a target area and obtaining a time-series muscle contraction distribution; a temperature field distribution acquisition module for calculating an initial temperature field distribution based on thermal imaging of the target area, performing temperature compensation based on the base time-series body temperature transmitted by an ear temperature sensor, and outputting a time-series temperature field distribution; a correlation feature acquisition module for interfacing with standard medical equipment to access real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features; a dynamic feature acquisition module for spatially registering the time-series muscle contraction distribution and the time-series temperature field distribution, performing dynamic feature extraction, and outputting ORI correlation features and regional thermodynamic features; a stress grading module for inputting the ORI correlation features, regional thermodynamic features, and coupled fluctuation correlation features into a physiological stress grading space to match and locate the initial stress grading; and a pain grading module for performing dynamic threshold compensation on the initial stress grading based on the base time-series body temperature and outputting a real-time physiological pain grading. This system solves the technical problem that existing pain assessment methods lack accurate real-time physiological data analysis and dynamic update mechanisms, fail to fully consider the influence of environmental factors, and thus result in low accuracy in pain assessment. By combining multimodal physiological signals and using a dynamic stress vector update mechanism, this method can monitor an individual's physiological stress response in real time and visualize changes in stress state through a physiological trajectory sphere model, thereby achieving more accurate and reliable pain grading. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A schematic diagram of the structure of a pain grading assessment system based on multimodal physiological signal fusion provided in an embodiment of the present application;

[0018] Figure 2 This is a flow chart of the process of determining the temporal muscle contraction distribution by the contraction distribution acquisition module in the pain grading assessment system based on multimodal physiological signal fusion in this application.

[0019] Explanation of the accompanying symbols: contraction distribution acquisition module 11, temperature field distribution acquisition module 12, correlation feature acquisition module 13, dynamic feature acquisition module 14, stress grading module 15, pain grading module 16. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, systems, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The present application embodiment provides a pain grading assessment system based on multimodal physiological signal fusion, such as Figure 1 As shown, the system includes:

[0024] The contraction distribution acquisition module 11 is used to capture the contraction of muscle tissue in the target area and obtain the time-series muscle contraction distribution; the temperature field distribution acquisition module 12 is used to calculate the initial temperature field distribution based on the thermal imaging of the target area, and perform temperature compensation based on the basic time-series body temperature sent back by the ear temperature sensor, and output the time-series temperature field distribution; the correlation feature acquisition module 13 is used to connect to standard medical equipment to call real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features.

[0025] By deploying an 850nm near-infrared light source and a 520nm visible light source in a pulsed alternating pattern to illuminate the target area, the contraction distribution acquisition module 11 is used to capture muscle tissue contraction in the target area to obtain a temporal muscle contraction distribution, which is a temporal curve of the muscle elastic modulus. Subsequently, the temperature field distribution acquisition module 12 is used to obtain a thermal image by capturing infrared radiation from the target area and calculate the initial temperature field distribution based on the thermal imaging of the target area. Body temperature data is collected using an ear temperature sensor and combined with the thermal imaging data for temperature compensation. Specifically, the temperature gradient between the center and edge of the wound is used to detect the local temperature rise caused by the inflammatory response. The user's basal body temperature is then simultaneously measured using a forehead or ear temperature sensor for whole-body temperature compensation, eliminating ambient temperature interference and thus obtaining a more accurate temporal temperature field distribution. Furthermore, the correlation feature acquisition module 13 is used to connect to standard medical equipment to access real-time physiological data, including respiratory cycle and blood pressure, construct real-time physiological data for physiological fluctuation correlation analysis, and output coupled fluctuation correlation features.

[0026] Furthermore, the correlation feature acquisition module 13 is also used to obtain respiratory rate and blood pressure parameters in real time through a standard medical equipment interface to obtain respiratory rate time series data and blood pressure parameter time series data; perform phase synchronization analysis on the respiratory rate time series data and blood pressure parameter time series data to construct a respiratory-blood pressure coupling sequence; perform sliding window cross-correlation analysis on the respiratory-blood pressure coupling sequence to output the coupled fluctuation correlation feature.

[0027] The method involves interfacing with standard medical equipment to access real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features. The method includes: acquiring respiratory rate and blood pressure parameters in real time through a standard medical equipment interface to obtain respiratory rate time series data and blood pressure parameter time series data. Subsequently, phase synchronization analysis is performed on the respiratory rate time series data and the blood pressure parameter time series data, such as aligning peaks or troughs of the respiratory rate time series data and the blood pressure parameter time series data to construct a respiratory-blood pressure coupled sequence. Sliding window cross-correlation analysis is performed on the respiratory-blood pressure coupled sequence to output the coupled fluctuation correlation features.

[0028] Furthermore, the correlation feature acquisition module 13 is also used to: construct a sliding window parameter based on a standard respiratory cycle, wherein the sliding window parameter includes a window length and a sliding step, the window length is H standard respiratory cycles, and the sliding step is 1 / M standard respiratory cycles; based on the sliding window parameter, the respiratory-blood pressure coupling sequence is slidingly divided to output multiple window coupling sequences; using a normalized cross-correlation function, multiple cross-correlation coefficients and multiple coupling delays of the multiple window coupling sequences are calculated; the multiple cross-correlation coefficients are arranged in ascending order, the maximum cross-correlation coefficient is extracted, and the target coupling delay is called accordingly, wherein the maximum cross-correlation coefficient and the target coupling delay constitute the coupling fluctuation correlation feature.

[0029] A sliding window cross-correlation analysis is performed on the respiratory-blood pressure coupling sequence to output the coupling fluctuation correlation characteristics. The method includes: constructing sliding window parameters based on a standard respiratory cycle, wherein the standard respiratory cycle is the time required to complete H complete respiratory cycles under normal conditions. The sliding window parameters include a window length and a sliding step length, wherein the window length is H standard respiratory cycles, and the sliding step length is 1 / M standard respiratory cycles. H and M are positive integers greater than 1. Further, the respiratory-blood pressure coupling sequence is segmented based on the sliding window parameters, and a respiratory-blood pressure coupling sequence is segmented into multiple window lengths and data under corresponding sliding steps under each window length, and multiple window coupling sequences are output. Further, a normalized cross-correlation function is used to calculate multiple cross-correlation coefficients and multiple coupling delays of the multiple window coupling sequences. The normalized cross-correlation function is:

[0030]

[0031] Among them, R(t) is the respiratory signal time series data, B(t) is the blood pressure signal time series data, τ is the delay offset, The mean of the respiratory signal time series data, is the mean of the blood pressure signal time series data. Finally, the maximum cross-correlation coefficient is extracted from the cross-correlation coefficients calculated from multiple windows. The maximum cross-correlation coefficient indicates the strongest synchronization between respiration and blood pressure during the entire analysis process. The multiple cross-correlation coefficients are arranged in ascending order, and the maximum cross-correlation coefficient is extracted. The target coupling delay is called accordingly. The target coupling delay is the coupling delay corresponding to the maximum cross-correlation coefficient, which indicates the optimal phase synchronization point between respiration and blood pressure. The maximum cross-correlation coefficient and the target coupling delay constitute the coupling fluctuation correlation feature, which is used for subsequent pain grading analysis.

[0032] Further, such as Figure 2As shown, the contraction distribution acquisition module 11 is also used for: when using an 850nm near-infrared light source and a 520nm visible light source to irradiate the target area in a pulse alternating mode, synchronously capturing the dual-wavelength reflected light intensity distribution through a shutter sensor to generate a reflected light intensity alternating sequence; calculating an output light intensity difference sequence based on the reflected light intensity alternating sequence; inputting the light intensity difference sequence into a tissue deformation association model to perform local deformation inversion to obtain a local deformation variable sequence; performing elastic modulus inversion on the local deformation variable sequence to output an instantaneous elastic modulus sequence; performing sliding window change rate calculation on the instantaneous elastic modulus sequence to output an elastic modulus time series change curve as the time series muscle contraction distribution.

[0033] Capturing muscle tissue contraction in a target area to obtain a time-series muscle contraction distribution, the method includes: using an 850nm near-infrared light source and a 520nm visible light source, illuminating the target area in a pulsed alternating mode, i.e., alternating emission of the near-infrared light source and the visible light source, and synchronously capturing the dual-wavelength reflected light intensity distribution through a shutter sensor, ensuring that the intensity of the reflected light in the target area can be accurately recorded each time the light source switches, thereby generating an alternating reflected light intensity sequence. Subsequently, based on the alternating reflected light intensity sequence, an output light intensity difference sequence is calculated, wherein the light intensity difference sequence is the difference between adjacent alternating reflected light intensity sequences, such as the difference between the first and second reflected light intensities, the difference between the third and fourth reflected light intensities, and the difference between the fifth and sixth reflected light intensities. Reflected light intensities that have already been calculated are not calculated a second time, thereby obtaining a light intensity difference sequence. A tissue deformation association model is constructed based on a neural network model, and the construction data is the light intensity difference sequence and the corresponding local deformation variable parameters in the historical muscle tissue contraction monitoring data. For example, a light intensity difference sequence of 50 units and a local deformation variable of 0.2 mm represent the local deformation of the muscle surface during contraction. The neural network model is supervised and trained by constructing data until the accuracy of the model output meets the requirements, thereby completing the training and obtaining a tissue deformation association model. Furthermore, the light intensity difference sequence is input into the tissue deformation association model, and local deformation inversion is performed to obtain a local deformation variable sequence. The elastic modulus inversion of the local deformation variable sequence is performed by means of an experiment or calibration through the local deformation variable and the corresponding applied stress, thereby outputting an instantaneous elastic modulus sequence. Finally, a sliding window change rate calculation is performed on the instantaneous elastic modulus sequence, wherein the sliding window is a preset time window, which has the same interval length as each parameter of the instantaneous elastic modulus sequence. The change rate of adjacent parameters of the instantaneous elastic modulus sequence is calculated through the sliding window, and according to the calculated change rate, the elastic modulus time series change curve is output as the time series muscle contraction distribution.

[0034] Furthermore, the temperature field distribution acquisition module 12 is also used to: configure a far-infrared thermal imager according to the spatial characteristics of the target area, wherein the target area is located at the center of the field of view of the far-infrared thermal imager; and capture the original temperature of the target area based on the far-infrared thermal imager to obtain a multi-frame original temperature matrix.

[0035] The far-infrared thermal imager is configured based on the spatial characteristics of the target area so that the target area is centered in the camera's field of view. Once configured, the far-infrared thermal imager captures the target area's raw temperature, generating a multi-frame raw temperature matrix that displays the temperature data corresponding to the imaging pixels at the target area's location.

[0036] Furthermore, the temperature field distribution acquisition module 12 is also used to: collect continuous resting state data of the target user through the ear temperature sensor to construct the basic time-series body temperature; locate the vascular bifurcation point matrix in the target area; after spatially aligning the multiple frames of original temperature matrices with the vascular bifurcation point matrix as the reference feature, calculate the gradient distribution of the original temperature matrices of adjacent frames and output the initial temperature field distribution; perform dynamic temperature compensation on the initial temperature field distribution according to the basic time-series body temperature and output the time-series temperature field distribution.

[0037] The initial temperature field distribution is calculated based on the thermal imaging of the target area, and temperature compensation is performed based on the basic time-series body temperature transmitted back by the ear temperature sensor, and the time-series temperature field distribution is output. The method includes: collecting continuous resting state data of the target user through the ear temperature sensor, wherein the resting state is the body temperature measurement data obtained when the user is not subject to other interference conditions, and the measured temperature is closer to . The basic time-series body temperature is constructed based on the continuous resting state data. Furthermore, the vascular bifurcation point matrix is ​​located in the target area, and the vascular bifurcation point matrix is ​​the spatial coordinates of the vascular bifurcation position in the target area. Based on the vascular bifurcation point matrix as the reference feature, the spatial alignment of the multiple frames of the original temperature matrix is ​​performed, that is, the spatial position of the vascular bifurcation point matrix is ​​aligned with the original temperature matrix. The alignment process includes translation, rotation, or scaling to ensure that the target area corresponding to the multiple frames of data remains consistent. The gradient distribution of the original temperature matrices of adjacent frames is calculated, and the initial temperature field distribution is output. The initial temperature field distribution is the temperature difference gradient between the center and edge of the wound of each original temperature matrix. Finally, a linear regression formula is established between the body temperature data and the thermal imaging temperature data. The linear regression formula is constructed by finding the linear relationship between the basic time-series body temperature and the initial temperature field distribution, so that the thermal imaging temperature can be corrected using the body temperature data. The linear regression formula can be constructed by professional technicians. The initial temperature field distribution is dynamically temperature compensated using the linear regression formula based on the basic time-series body temperature, and the time-series temperature field distribution is output.

[0038] The dynamic feature acquisition module 14 is used to spatially align the temporal muscle contraction distribution and the temporal temperature field distribution, perform dynamic feature extraction, and output ORI-related features and regional thermodynamic features. The stress grading module 15 is used to input the ORI-related features, regional thermodynamic features, and coupled fluctuation-related features into the physiological stress grading space to match and locate the initial stress grading. The pain grading module 16 is used to perform dynamic threshold compensation on the initial stress grading based on the basal temporal body temperature and output a real-time physiological pain grading.

[0039] The dynamic feature acquisition module 14 performs spatial registration of the temporal muscle contraction distribution and the temporal temperature field distribution. After completion, dynamic feature extraction is performed, outputting ORI-related features and regional thermodynamic features. Subsequently, the stress grading module 15 inputs the ORI-related features, regional thermodynamic features, and coupled fluctuation-related features into the physiological stress grading space, locates the virtual points of the ORI-related features, regional thermodynamic features, and coupled fluctuation-related features in the physiological stress grading space, determines the closest particle point, and uses the sample stress grade of the closest particle point as the initial stress grade. Finally, the pain grading module 16 performs dynamic threshold compensation on the initial stress grade based on the basal temporal body temperature. Based on the temperature variation trend, such as a slight increase or decrease in basal body temperature, the module obtains a preset stress grade adjustment corresponding to the increase or decrease in body temperature. This module then outputs a real-time physiological pain grade to account for potential errors caused by temperature fluctuations, thereby ensuring more accurate pain assessment. For example, an elevated body temperature may indicate a high level of stress, necessitating an increased stress grade. For example, for every 1°C increase in temperature, the preset stress level is increased by 0.5. The preset parameter value can be adjusted according to the actual data. This solves the technical problem that the existing pain assessment method lacks accurate real-time physiological data analysis and dynamic update mechanism, cannot fully consider the influence of environmental factors, and leads to low accuracy of pain assessment. By combining multimodal physiological signals and using a dynamic stress vector update mechanism, this method can monitor the individual's physiological stress response in real time, and visualize the changes in stress state through a physiological trajectory sphere model, thereby achieving more accurate and reliable pain grading. This solves the technical problem that the existing pain assessment method lacks accurate real-time physiological data analysis and dynamic update mechanism, cannot fully consider the influence of environmental factors, and leads to low accuracy of pain assessment. By combining multimodal physiological signals and using a dynamic stress vector update mechanism, this method can monitor the individual's physiological stress response in real time, and visualize the changes in stress state through a physiological trajectory sphere model, thereby achieving more accurate and reliable pain grading.

[0040] Furthermore, the dynamic feature acquisition module 14 is also used to: use the vascular bifurcation point matrix as a reference feature to perform cross-modal spatial registration of the temporal muscle contraction distribution and the temporal temperature field distribution, and output the registered muscle contraction distribution and the registered temperature field distribution; calculate the elastic modulus change rate of the registered muscle contraction distribution, locate the peak point of the change rate, and use it as the instantaneous extreme value of muscle contraction; perform peak attenuation tracking starting from the peak point of the change rate, and output the contraction recovery delay window, wherein the contraction recovery delay window and the instantaneous extreme value of muscle contraction constitute the ORI association feature; starting from the regional center of the target area, traverse the registered temperature field distribution to calculate and output the regional temperature difference gradient; perform metabolic heat production prediction on the registered temperature field distribution, and output the regional heat production rate, wherein the regional temperature difference gradient and the regional heat production rate constitute the regional thermodynamic feature.

[0041] After spatially registering the temporal muscle contraction distribution and the temporal temperature field distribution, dynamic feature extraction is performed to output ORI-related features and regional thermodynamic features. The method includes: using the vascular bifurcation point matrix as a reference feature, performing cross-modal spatial registration of the temporal muscle contraction distribution and the temporal temperature field distribution, aligning the temporal muscle contraction distribution and the temporal temperature field distribution data in spatial coordinates, and then outputting the registered muscle contraction distribution and the registered temperature field distribution. Furthermore, the elastic modulus change rate of the registered muscle contraction distribution is calculated, and the peak point of the change rate is located as the instantaneous extreme value of muscle contraction. These peak points can be used to measure the intensity of pain or stress. Assume that during monitoring, the elastic modulus of the muscle changes from 10 kPa to 25 kPa in 0.5 seconds, with an elastic modulus change rate of 30 kPa / second. The instantaneous extreme peak point is calculated and represented as the maximum muscle tension at a given moment. Peak decay tracking is performed starting from the peak point of the change rate. Peak decay refers to the recovery process after the muscle contraction reaches its maximum value, which can be used to obtain recovery time and intensity. Output the contraction recovery delay window, which refers to the time required from the instantaneous extreme value of muscle contraction to the time it takes for muscle contraction to recover to a certain threshold. This window can reflect the muscle's recovery ability and thus provide a basis for pain assessment. The contraction recovery delay window and the instantaneous extreme value of muscle contraction constitute the ORI association feature. Starting from the center of the target area, the registered temperature field distribution is traversed to calculate and output the regional temperature gradient. The temperature gradient is calculated by obtaining the temperature difference between adjacent points and reflects the speed and direction of heat transfer. Based on the registered temperature field data and the calculated temperature gradient, a thermodynamic model is applied to predict metabolic heat production. The thermodynamic model is constructed based on a neural network model. The temperature gradient corresponding to the registered temperature field data obtained from historical acquisition and the metabolic heat production identification results are input into an untrained model to perform supervised model training. When the model converges, the thermodynamic model is obtained. The registered temperature field data and the calculated temperature gradient are input into the thermodynamic model. The model predicts the heat production rate of the region to obtain the regional thermodynamic characteristics. The regional temperature gradient and the regional heat production rate constitute the regional thermodynamic characteristics.

[0042] Furthermore, the stress grading module 15 is also used to: locally de-privacy call multiple sample multimodal physiological features and multiple sample stress grades; establish the physiological stress grading space according to the standard indicator composition of the sample multimodal physiological features; after locating multiple sample particle points in the physiological stress grading space based on the multiple sample multimodal physiological features, use the multiple sample stress grades to identify the multiple sample particle points to complete the data filling of the physiological stress grading space; input the ORI association features, regional thermodynamic features and coupled fluctuation association features into the physiological stress grading space to locate virtual particle points; perform spatial matching of the virtual particle points with the goal of minimizing distance, locate the nearest particle point, and use the sample stress grade of the nearest particle point as the initial stress grade.

[0043] By locally implementing privacy protection measures to call upon multiple sample multimodal physiological features and multiple sample stress ratings, the security of the user's biometric data and personal information is ensured. The sample multimodal physiological features include sample ORI features, sample thermodynamic features, and sample coupling features. The sample stress rating is the stress level of the reference sample under the conditions corresponding to the sample multimodal physiological features. Stress ratings are generally divided into different levels based on the intensity of the physiological response, for example, mild corresponds to levels 0-3, moderate corresponds to levels 4-6, and severe stress response corresponds to levels 7-10. Based on the standard indicators of the sample multimodal physiological features, the physiological stress rating space is established based on the sample ORI features, sample thermodynamic features, and sample coupling features, and the physiological characteristics of each individual are converted into a point in the stress rating space. After locating multiple sample particle points in the physiological stress rating space based on the multiple sample multimodal physiological features, the multiple sample stress ratings are used to identify the multiple sample particle points, completing the data filling of the physiological stress rating space. Furthermore, the acquired ORI-related features, regional thermodynamic features, and coupled fluctuation-related features of the target user are input into the physiological stress classification space to locate virtual particle points. Spatial matching of the virtual particle points is performed with the goal of minimizing distance. The nearest particle point in the physiological stress classification space is obtained, and the sample stress rating of the nearest particle point is used as the initial stress rating.

[0044] Furthermore, the pain grading module 16 is also used to: construct a real-time stress vector based on the ORI correlation characteristics, regional thermodynamic characteristics and coupled fluctuation correlation characteristics; preset a stress monitoring window, and dynamically update the real-time stress vector through the stress monitoring window, and output multiple incremental stress vectors; construct a physiological trajectory sphere model based on the multiple incremental stress vectors, and use multiple incremental stress grades to perform visual rendering of the physiological trajectory sphere model.

[0045] A real-time stress vector is constructed based on the ORI correlation features, regional thermodynamic features, and coupled fluctuation correlation features, with the corresponding characteristic parameters represented by vectors. Subsequently, a pre-set stress monitoring window (i.e., a fixed time monitoring window) is established, and the real-time stress vector is dynamically updated within this window. Stress vectors that have undergone vector updates are obtained, and multiple incremental stress vectors are output. Finally, a physiological trajectory sphere model is constructed based on these multiple incremental stress vectors. This physiological trajectory sphere model is used to represent the dynamic changes in the stress state along the time axis. Each incremental stress vector is represented as a point in the three-dimensional space of the sphere model, and the lines connecting the points represent the trajectory of the stress state. The physiological trajectory sphere model is visualized using multiple incremental stress levels, mapping the incremental stress levels to different regions of the sphere model to intuitively display the changes in the stress state. In the sphere model, different stress levels are represented by different colors or sphere sizes: low stress is represented by green, medium stress is represented by yellow, and high stress is represented by red.

[0046] The embodiment of the present application includes a contraction distribution acquisition module for capturing muscle tissue contraction in a target area to obtain a time-series muscle contraction distribution; a temperature field distribution acquisition module for calculating an initial temperature field distribution based on thermal imaging of the target area, performing temperature compensation based on the basic time-series body temperature transmitted back by the ear temperature sensor, and outputting a time-series temperature field distribution; a correlation feature acquisition module for interfacing with standard medical equipment to call real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features; a dynamic feature acquisition module for spatially registering the time-series muscle contraction distribution and the time-series temperature field distribution, performing dynamic feature extraction, and outputting ORI correlation features and regional thermodynamic features; a stress grading module for inputting the ORI correlation features, regional thermodynamic features, and coupled fluctuation correlation features into a physiological stress grading space to match and locate the initial stress grading; and a pain grading module for performing dynamic threshold compensation on the initial stress grading based on the basic time-series body temperature and outputting a real-time physiological pain grading. This solves the technical problem that the existing pain assessment methods lack accurate real-time physiological data analysis and dynamic update mechanisms, fail to fully consider the influence of environmental factors, and thus result in low accuracy of pain assessment. By combining multimodal physiological signals and using a dynamic stress vector update mechanism, this method can monitor an individual's physiological stress response in real time and visualize changes in stress state through a physiological trajectory sphere model, thereby achieving more accurate and reliable pain grading.

[0047] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A pain grading assessment system based on multimodal physiological signal fusion, characterized by: The system comprises: Contraction distribution acquisition module, used to capture the muscle tissue contraction in the target area and obtain the time-series muscle contraction distribution; The temperature field distribution acquisition module is used to calculate the initial temperature field distribution based on the thermal imaging of the target area, perform temperature compensation based on the basic time-series body temperature returned by the ear temperature sensor, and output the time-series temperature field distribution; The correlation feature acquisition module is used to connect to standard medical equipment to call real-time physiological data, perform physiological fluctuation correlation analysis, and output coupled fluctuation correlation features; A dynamic feature acquisition module is used to perform dynamic feature extraction after spatially registering the temporal muscle contraction distribution and the temporal temperature field distribution, and output ORI-related features and regional thermodynamic features. The ORI-related features include the muscle contraction recovery delay window and the instantaneous extreme value of muscle contraction, and the regional thermodynamic features include the regional temperature gradient and the regional heat production rate. A stress classification module is used to input the ORI correlation feature, regional thermodynamic feature and coupled fluctuation correlation feature into the physiological stress classification space, locate the virtual points of the ORI correlation feature, regional thermodynamic feature and coupled fluctuation correlation feature in the physiological stress classification space, determine the closest particle point, and use the sample stress classification of the closest particle point as the initial stress classification; The pain grading module is used to perform dynamic threshold compensation on the initial stress grading according to the basal temporal body temperature, obtain the preset adjustment amplitude of the stress grading corresponding to the increase or decrease of the body temperature according to the changing trend of the body temperature, such as a slight increase or decrease of the basal body temperature, and output the real-time physiological pain grade.

2. The pain grading assessment system based on multimodal physiological signal fusion according to claim 1, characterized in that: The pain rating module is also used to: Constructing a real-time stress vector based on the ORI correlation characteristics, regional thermodynamic characteristics, and coupled fluctuation correlation characteristics; Presetting a stress monitoring window, and dynamically updating the real-time stress vector through the stress monitoring window to output a plurality of incremental stress vectors; A physiological trajectory spherical model is constructed according to the multiple incremental stress vectors, and a plurality of incremental stress levels are used to perform visual rendering of the physiological trajectory spherical model.

3. The pain grading assessment system based on multimodal physiological signal fusion according to claim 1, characterized in that: The associated feature acquisition module is further used for: Acquire respiratory rate and blood pressure parameters in real time through a standard medical equipment interface to obtain respiratory rate time series data and blood pressure parameter time series data; Performing phase synchronization analysis on the respiratory frequency time series data and the blood pressure parameter time series data to construct a respiratory-blood pressure coupling sequence; Perform sliding window cross-correlation analysis on the respiration-blood pressure coupling sequence and output the coupling fluctuation correlation feature.

4. The pain grading assessment system based on multimodal physiological signal fusion according to claim 3, characterized in that: The associated feature acquisition module is further used for: Constructing sliding window parameters according to the standard breathing cycle, wherein the sliding window parameters include a window length and a sliding step length, the window length is H standard breathing cycles, and the sliding step length is 1 / M standard breathing cycles; Sliding and segmenting the respiration-blood pressure coupling sequence based on the sliding window parameter, and outputting a plurality of window coupling sequences; Using a normalized cross-correlation function, calculating a plurality of cross-correlation coefficients and a plurality of coupling delays of the plurality of window coupling sequences; The multiple mutual correlation coefficients are arranged in ascending order, a maximum mutual correlation coefficient is extracted, and a target coupling delay is called accordingly, wherein the maximum mutual correlation coefficient and the target coupling delay constitute the coupling fluctuation correlation feature.

5. The pain grading assessment system based on multimodal physiological signal fusion according to claim 1, characterized in that: The shrinkage distribution acquisition module is further used for: During the process of irradiating the target area with an 850nm near-infrared light source and a 520nm visible light light source in a pulse alternating mode, a shutter sensor is used to synchronously capture the dual-wavelength reflected light intensity distribution to generate an alternating reflected light intensity sequence; Calculating an output light intensity difference sequence based on the reflected light intensity alternating sequence; Inputting the light intensity difference sequence into a tissue deformation correlation model to perform local deformation inversion to obtain a local deformation quantity sequence; Performing elastic modulus inversion on the local deformation sequence to output an instantaneous elastic modulus sequence; The sliding window change rate of the instantaneous elastic modulus sequence is calculated, and a time series change curve of the elastic modulus is output as the time series muscle contraction distribution.

6. The pain grading assessment system based on multimodal physiological signal fusion according to claim 1, characterized in that: The temperature field distribution acquisition module is also used for: Configuring a far-infrared thermal imager according to the spatial characteristics of the target area, wherein the target area is located at the center of the field of view of the far-infrared thermal imager; The original temperature of the target area is captured based on the far-infrared thermal imager to obtain a multi-frame original temperature matrix.

7. The pain grading assessment system based on multimodal physiological signal fusion according to claim 6, characterized in that: The temperature field distribution acquisition module is also used for: Collecting continuous resting state data of the target user through the ear temperature sensor to construct the basic time series body temperature; locating a matrix of vascular bifurcation points in the target area; After spatially aligning the multiple frames of original temperature matrices using the vascular bifurcation point matrix as a reference feature, the gradient distribution of the original temperature matrices of adjacent frames is calculated to output an initial temperature field distribution; Dynamic temperature compensation is performed on the initial temperature field distribution according to the basal time-series body temperature, and the time-series temperature field distribution is output.

8. The pain grading assessment system based on multimodal physiological signal fusion according to claim 7, characterized in that: The dynamic feature acquisition module is further used for: Using the vascular bifurcation point matrix as a reference feature, performing cross-modal spatial registration of the time-series muscle contraction distribution and the time-series temperature field distribution, and outputting the registered muscle contraction distribution and the registered temperature field distribution; Calculating the elastic modulus change rate of the registered muscle contraction distribution and locating the peak point of the change rate as the instantaneous extreme value of the muscle contraction; Perform peak decay tracking starting from the peak point of the rate of change, and output a contraction recovery delay window, wherein the contraction recovery delay window and the instantaneous extreme value of muscle contraction constitute the ORI correlation feature; Taking the center of the target area as the starting point, traverse the registered temperature field distribution to calculate the output regional temperature difference gradient; Metabolic heat production is predicted for the registered temperature field distribution, and a regional heat production rate is output, wherein the regional temperature difference gradient and the regional heat production rate constitute the regional thermodynamic characteristics.

9. The pain grading assessment system based on multimodal physiological signal fusion according to claim 1, characterized in that: The stress rating module is further configured to: Local privacy removal calls multiple sample multimodal physiological features and multiple sample stress ratings; Establishing the physiological stress classification space according to the standard index composition of the multimodal physiological characteristics of the sample; After locating a plurality of sample particle points in the physiological stress classification space based on the plurality of multimodal physiological characteristics of the samples, the plurality of sample particle points are labeled using the plurality of sample stress classifications to complete data filling in the physiological stress classification space; Inputting the ORI correlation features, regional thermodynamic features, and coupled fluctuation correlation features into the physiological stress classification space to locate virtual particle points; The virtual particle points are spatially matched with the goal of minimizing the distance, the nearest particle point is located, and the sample stress rating of the nearest particle point is used as the initial stress rating.

10. The pain grading assessment system based on multimodal physiological signal fusion according to claim 9, characterized in that: The multimodal physiological characteristics of the sample include sample ORI characteristics, sample thermodynamic characteristics and sample coupling characteristics.

Images