Physiological signal real-time monitoring and intervention system for pain management

Abstract

The present application relates to the technical field of medical informatics, and in particular to a physiological signal real-time monitoring and intervention system for pain management, which comprises: a determination module configured to determine the abnormal tendency of a real-time updated stimulation window at each update time to obtain an abnormal tendency sequence; the determination module is further configured to determine similar fluctuation segments in the abnormal tendency sequence; the determination module is further configured to determine an abnormal progress factor of the physiological sensing signal at the current time based on the abnormal tendency difference and the length of each similar fluctuation segment; the determination module is further configured to determine a trigger factor for evaluating the abnormal pain state at the current time according to the abnormal progress factors of each physiological sensing signal at the current time and the last time, and to normalize the trigger factor to obtain a normalized trigger factor; and an intervention module configured to visualize and intervene in the pain degree of a target user based on the normalized trigger factor. The present application improves the accuracy and sensitivity of physiological signal anomaly recognition.

Description

Technical Field

[0001] This invention relates to the field of medical informatics technology, specifically to a real-time physiological signal monitoring and intervention system for pain management. Background Technology

[0002] Pain is a common subjective discomfort symptom in clinical practice, affecting not only patients' physiological comfort and quality of life but also potentially delaying disease recovery. Scientific and effective pain management has become an important component of modern medicine. Its core objective is to achieve precise pain control through appropriate intervention, maximizing pain relief while minimizing adverse reactions, thus balancing efficacy and safety. With the integration of biomedical engineering and artificial intelligence technologies, pain management is gradually transforming towards intelligentization, with intelligent monitoring systems based on biosignal sensing becoming a core area of ​​research and development. These systems continuously collect multidimensional physiological signals such as heart rate, blood pressure, and electromyography (EMG), electroencephalography (EEG), and electrodermal activity through wearable devices and other hardware. AI algorithms analyze massive amounts of data in real time, constructing a mapping relationship between physiological signals and pain intensity to achieve automatic pain level assessment. When pain intensity exceeds the threshold, personalized intervention measures can be automatically triggered, significantly improving management efficiency and effectiveness.

[0003] However, in some scenarios, the technical bottlenecks caused by individual patient differences become apparent in clinical applications. Different patients exhibit significantly different physiological signal changes during pain due to variations in age, physical condition, underlying diseases, and pain tolerance thresholds; even the same patient may show altered signal response patterns at different disease stages and with different pain types. Current mainstream intelligent monitoring systems mostly employ standardized models, training general algorithms based on large-scale population samples to identify signal anomalies using fixed logic. When faced with individuals exhibiting significant differences in characteristics, such models are prone to misjudgment or missed detection, making it difficult to accurately capture the pain-related signal characteristics of different patients. Therefore, the above methods lack sufficient accuracy and sensitivity in identifying physiological signal anomalies in patients with highly differentiated physiological signal change characteristics. Summary of the Invention

[0004] To address the technical problem of insufficient accuracy and sensitivity in identifying abnormal physiological signals in individual patients with highly differentiated physiological signal characteristics, the present invention aims to provide a real-time physiological signal monitoring and intervention system for pain management.

[0005] To solve the above technical problems, the specific technical solution adopted is as follows:

[0006] In a first aspect, embodiments of the present invention provide a real-time monitoring and intervention system for physiological signals for pain management, comprising: a determination module, configured to determine the abnormal tendency of a real-time updated stimulation window at each update time based on the real-time curves and historical curves of each physiological sensor signal of a target user, thereby obtaining an abnormal tendency sequence; the determination module is further configured to determine similar fluctuation segments in the abnormal tendency sequence based on the abnormal tendency difference between the subsequent data and the preceding data in the abnormal tendency sequence; the determination module is further configured to determine the abnormal process factor of the physiological sensor signal at the current time based on the abnormal tendency difference and the length of each similar fluctuation segment; the determination module is further configured to determine the triggering factor for assessing the abnormal pain state at the current time based on the abnormal process factor of each physiological sensor signal at the current time and the previous time, and to normalize the triggering factor to obtain a normalized triggering factor; and an intervention module, configured to visualize and intervene in the pain level of the target user based on the normalized triggering factor.

[0007] Optionally, the determining module is further configured to: determine the waveform segment corresponding to a pair of minimum values ​​at adjacent positions of the real-time curve of the physiological sensor signal as the current local stimulus behavior; determine the stimulation effectiveness of the current local stimulus behavior based on the first difference between any two points in the local sensor signal curve segment corresponding to the current local stimulus behavior, the second difference between the historical maximum value and the historical mean of the historical curve, the duration of the current local stimulus behavior, and the average of the duration of the historical local stimulus behavior corresponding to the physiological sensor signal; and determine the abnormal tendency of the real-time updated stimulation window at each update time according to the stimulation effectiveness of each local stimulus behavior in the real-time updated stimulation window, thereby obtaining an abnormal tendency sequence.

[0008] Optionally, the determining module is further configured to: determine the maximum difference among the first differences between any two points in the local sensor signal curve segment corresponding to the current local stimulus behavior; calculate a first ratio between the maximum difference and a second difference between the historical maximum value and the historical mean of the historical curve, and a second ratio between the duration of the current local stimulus behavior and the average duration of the historical local stimulus behavior corresponding to the physiological sensor signal; and determine the stimulation effectiveness of the current local stimulus behavior based on the first ratio and the second ratio.

[0009] Optionally, the determination module is also used to: calculate the third difference between the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window and the mean effectiveness of the stimulus effectiveness of each local stimulus behavior; and determine the abnormal tendency based on the third difference and the standard deviation of the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window to obtain an abnormal tendency sequence.

[0010] Optionally, the determining module is also used to: calculate the abnormal tendency difference between the next data point and the previous data point in the abnormal tendency sequence to obtain an abnormal tendency difference sequence; compare the signs of adjacent abnormal tendency differences in the abnormal tendency difference sequence, and continuously mark the abnormal tendencies corresponding to the abnormal tendency differences with the same sign in the abnormal tendency difference sequence to obtain similar fluctuation segments in the abnormal tendency sequence.

[0011] Optionally, the determining module is further configured to: superimpose the abnormal tendency difference values ​​in the abnormal tendency difference sequence that are greater than a threshold to obtain a first superimposed value; superimpose the abnormal tendency difference values ​​in the abnormal tendency difference sequence that are less than a threshold to obtain a second superimposed value; and determine the abnormal process factor of the physiological sensing signal at the current moment based on the first superimposed value, the second superimposed value, and the length of each similar fluctuation segment.

[0012] Optionally, the determining module is further configured to: calculate the absolute value of the third ratio between the first superposition value and the second superposition value, and the fourth difference between the maximum length of each similar fluctuation segment and the average length of each similar fluctuation segment; and determine the abnormal process factor of the physiological sensing signal at the current moment based on the absolute value of the third ratio, the fourth difference, and the standard deviation of the length of each similar fluctuation segment.

[0013] Optionally, the determining module is further configured to: calculate a fourth ratio between the third superposition value of the abnormal process factor of each physiological sensor signal at the current time and the fourth superposition value of the abnormal process factor of each physiological sensor signal at the previous time; calculate a fifth difference between the abnormal process factors of each physiological sensor signal at the current time and the previous time, and a fifth ratio between the difference and the average process factor of the abnormal process factors of each physiological sensor signal at the current time; and determine the triggering factor for assessing the abnormal pain state at the current time based on the fourth ratio and the fifth ratio.

[0014] Optionally, the intervention module is also used to: map normalized triggering factors to corresponding colors using false colors and perform corresponding intervention actions based on the colors, where different colors represent different levels of pain for the target user.

[0015] Secondly, embodiments of the present invention provide a real-time physiological signal monitoring and intervention system for pain management, comprising: a processor and a memory; wherein the memory is used to store a computer program that can run on the processor; the processor is used to execute the program stored in the memory to implement the following steps:

[0016] Based on the real-time and historical curves of the target user's physiological sensor signals, the abnormal tendencies of the real-time updated stimulation window at each update time are determined, and an abnormal tendency sequence is obtained.

[0017] Based on the difference in abnormal trends between the next data point and the previous data point in the abnormal trend sequence, similar fluctuation segments in the abnormal trend sequence are determined.

[0018] Based on the abnormal tendency difference and the length of each of the similar fluctuation segments, the abnormal process factor of the physiological sensing signal at the current moment is determined.

[0019] Based on the abnormal process factors of each physiological sensor signal at the current time and the previous time, the triggering factor for assessing the abnormal pain state at the current time is determined, and the triggering factor is normalized to obtain the normalized triggering factor. The pain level of the target user is visualized based on the normalized triggering factor.

[0020] The present invention has the following beneficial effects: The determination module in the embodiments of the present invention can determine abnormal tendencies based on the real-time and historical curves of the target user's physiological sensor signals, and then determine abnormal process factors based on the difference in abnormal tendencies. This method can capture the pain-related signal characteristics of different patients, solving the problem of insufficient accuracy and sensitivity of traditional methods when facing individual differences, and achieving more accurate identification and judgment of the patient's pain state. After generating the abnormal tendency sequence, the determination module identifies similar fluctuation segments based on the difference in abnormal tendencies, and calculates the abnormal process factor accordingly. From the perspective of dynamic change, it comprehensively grasps the abnormal change process of physiological sensor signals over a period of time, and can capture the changing trend and fluctuation characteristics of signals in signal fluctuations. By determining the normalized trigger factor through the abnormal process factors of each physiological sensor signal at the current moment and the previous moment, this process transforms complex physiological signal characteristics into unified and standardized evaluation indicators. Normalization processing enables pain data of different patients and different types to be compared on the same scale, greatly improving the accuracy and comparability of the evaluation. Medical staff only need to rely on the normalized trigger factor to quickly and accurately judge the patient's pain level, and then promptly carry out visual analysis and implement corresponding intervention measures. Therefore, the above-mentioned approach not only improves the efficiency of pain management, but also enhances the accuracy and sensitivity of identifying abnormal physiological signals. Attached Figure Description

[0021] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a real-time physiological signal monitoring and intervention system for pain management, as provided in one embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of another physiological signal real-time monitoring and intervention system for pain management provided in one embodiment of the present invention. Detailed Implementation

[0024] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a real-time physiological signal monitoring and intervention system for pain management proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0026] The following description, in conjunction with the accompanying drawings, details the specific scheme of a real-time physiological signal monitoring and intervention system for pain management provided by the present invention.

[0027] Example 1:

[0028] Please see Figure 1 This document illustrates a schematic diagram of a real-time physiological signal monitoring and intervention system for pain management according to an embodiment of the present invention. The system includes: a determination module 101, configured to determine the abnormal tendency of a real-time updated stimulation window at each update time based on the real-time and historical curves of each physiological sensor signal of the target user, thereby obtaining an abnormal tendency sequence; the determination module 101 is further configured to determine similar fluctuation segments in the abnormal tendency sequence based on the abnormal tendency difference between the subsequent and preceding data in the abnormal tendency sequence; the determination module 101 is further configured to determine the abnormal process factor of the physiological sensor signal at the current time based on the abnormal tendency difference and the length of each similar fluctuation segment; the determination module 101 is further configured to determine the triggering factor for assessing the abnormal pain state at the current time based on the abnormal process factors of each physiological sensor signal at the current and previous times, and to normalize the triggering factor to obtain a normalized triggering factor; and an intervention module 102, configured to visualize and intervene in the pain level of the target user based on the normalized triggering factor.

[0029] Specifically, the physiological sensing signals in this embodiment of the invention include, but are not limited to, electroencephalogram (EEG) signals, electrocardiogram (ECG) signals, and photoplethysmography (PPG) waves. In this embodiment, the EEG signals are recorded using a dedicated EEG instrument, connected to four electrode patches placed on the patient's forehead via a dedicated sensor. During acquisition, a notch filter is used to filter 50Hz public network noise, and the sampling rate is set to 125Hz, thereby transmitting the output waveform to a central computer in real time. ECG signals and PPG waves are continuously collected and recorded using a multi-functional patient monitor, with a sampling frequency of 125Hz. ECG signals are acquired by connecting three electrode patches to the patient's chest, while PPG waves are acquired by connecting a finger probe to the tip of the patient's index finger. Similarly, the acquired data is transmitted back to the central computer to obtain the sensing signal corresponding to the current location. After acquiring the raw sensing signals, high-frequency interference and baseline drift removal are performed to obtain the acquired sensing data.

[0030] Furthermore, the analysis addresses the variations in physiological sensory signals across different patients: pain responses result from various noxious stimuli generating electrical signals in the sensory neuronal pathways. These signals are captured by corresponding sensors and converted into output level signals. The states of these electrical signals vary depending on the location of the stimulus, leading to different output levels after sensor capture. Therefore, this invention first analyzes the real-time fluctuation characteristics of the physiological signals generated by the system deployed on the patient's limbs. This establishes an initial model of the system's specific physiological signal fluctuation characteristics for the current patient. The model's evolution across different time segments is then analyzed to determine the degree of abnormal evolution. Finally, the abnormal state of the model is assessed based on the abnormal evolution process, enabling real-time perception of sensory signals and providing accurate data for intervention plans.

[0031] Furthermore, this embodiment of the invention judges the fluctuation characteristics of the patient's physiological sensor signals: the patient's pain status is not simply a sparse switching between two states of no pain and pain in time, but fluctuates continuously over time. Therefore, it is necessary to first distinguish the different states of change in the patient's physiological sensor signals. First, for the collected individual physiological sensor signals, the local influence of an effective stimulus signal is represented by a local peak and the fluctuation within its surrounding range in the waveform of the physiological sensor signal. Therefore, the distribution of peaks and valleys in the curve of the physiological sensor signal is analyzed. In one optional embodiment of the present invention, the determining module 101 is further configured to: determine the waveform segment corresponding to a pair of minimum values ​​at adjacent positions of the real-time curve of the physiological sensor signal as the current local stimulation behavior; determine the stimulation effectiveness of the current local stimulation behavior based on the first difference between any two points in the local sensor signal curve segment corresponding to the current local stimulation behavior, the second difference between the historical maximum value and the historical mean of the historical curve, the duration of the current local stimulation behavior, and the average of the duration of the historical local stimulation behavior corresponding to the physiological sensor signal; and determine the abnormal tendency of the real-time updated stimulation window at each update time according to the stimulation effectiveness of each local stimulation behavior in the real-time updated stimulation window, thereby obtaining an abnormal tendency sequence.

[0032] Specifically, in this embodiment of the invention, the waveform curve of the physiological sensing signal returned by a single sensor is processed using an Automatic Multiscale-based Peak Detection (AMPD) algorithm to extract the maximum positions of the waveform. The waveform is then axially symmetric along the x-axis, and the maximum values ​​are extracted again using AMPD. These maximum positions are recorded as the minimum positions of the original waveform. The original waveform segment intercepted between adjacent pairs of minimum positions is recorded as a local stimulus behavior B, further evaluating the effectiveness of the single stimulus behavior.

[0033] Furthermore, the historical curve can be a curve representing historical physiological sensor signals collected up to the current moment. Specifically, it can be a curve representing a single historical physiological sensor signal collected up to the current moment.

[0034] Furthermore, as an optional embodiment of the present invention, the determining module 101 is further configured to: determine the maximum difference among the first differences between any two points in the local sensor signal curve segment corresponding to the current local stimulation behavior; calculate a first ratio between the maximum difference and a second difference between the historical maximum value and the historical mean of the historical curve, and a second ratio between the duration of the current local stimulation behavior and the average duration of the historical local stimulation behavior corresponding to the physiological sensor signal; and determine the stimulation effectiveness of the current local stimulation behavior based on the first ratio and the second ratio.

[0035] Specifically, the first difference between any two points can be the difference between the next data point and the previous data point in the local sensing signal curve segment. In this embodiment of the invention, the following formula is used to calculate the stimulation effectiveness of the current local stimulation behavior:

[0036]

[0037] In the above formula, This indicates the effectiveness of the local stimulus behavior B. It represents the maximum difference among the first differences between any two points in the local sensor signal curve segment corresponding to the current local stimulus behavior. Indicates the first The historical maximum value of the historical curve of a physiological sensor signal. Indicates the first Historical average values ​​of physiological sensor signals. This indicates the duration of the current local stimulus behavior B. Indicates the first The average duration of the historical local stimulus behavior B of a physiological sensor signal.

[0038] in, This formula compares the intensity of the stimulus in the current local stimulus behavior B with the fluctuations reflected in historical data. The larger the formula, the more effective the stimulus signal represented by the current local stimulus behavior B is. The duration of stimulation of the current local stimulus behavior B is reflected in the proportion of the stimulation time. A higher proportion indicates that the stimulus signal monitored by the sensor occupies a longer period of time. Thus, the stimulation intensity of the stimulus signal is combined to accurately evaluate the current stimulus behavior B. This indicates the fluctuation of stimulus intensity in the current local stimulus behavior B compared to historical data responses. The relatively uniform concentration of these fluctuations at different times suggests that the stimulus function is operating normally.

[0039] Furthermore, this embodiment of the invention analyzes the abnormal state scale obtained by combining the dynamic process of the physiological sensing signal a monitored by the current sensor a, thereby accurately extracting the signal segments with abnormalities, and extracting the degree of abnormality based on the abnormal evolution process between signal segments. This embodiment of the invention judges the abnormal scale of a single physiological sensing signal a: However, the similarity between the stimulation behaviors B of physiological sensing signal a represents the anti-interference ability of the current physiological sensing signal a, that is, the influence of pain stimulation on the currently monitored physiological sensing signal a is relatively limited, thus indicating that the current physiological sensing signal a is less likely to cause significant stimulation changes. Therefore, when the current physiological sensing signal a shows a low-signal fluctuation, it actually indicates that the current physiological sensing signal a has already produced a relatively obvious abnormality. Therefore, this embodiment of the invention establishes a real-time window based on the effectiveness of the fluctuation to judge the monitoring sensitivity of physiological sensing signal a. In one optional embodiment of the present invention, the determining module 101 is further configured to: calculate a third difference between the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window and the mean effectiveness of the stimulus effectiveness of each local stimulus behavior; and determine the abnormal tendency based on the third difference and the standard deviation of the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window to obtain an abnormal tendency sequence.

[0040] Specifically, in this embodiment of the invention, the current moment is used as the starting point of the window (the current moment can be at different locations, but generally the starting moment is used when the sensor begins to acquire data), and the window expansion speed is set to the sensor's acquisition frequency, thereby obtaining the real-time updated stimulation window corresponding to the current physiological sensing signal a. Real-time updated stimulation window During the expansion process, the stimulation window is updated in real time. The overall distribution of stimulus effectiveness in the data represents the direction of fluctuations in anomalous situations, thereby altering the stimulus window through cumulative tendency changes. The sensitivity of anomaly detection is judged. In this embodiment of the invention, the following formula is used to calculate the anomaly tendency:

[0041]

[0042] In the above formula, Indicates a stimulus window that updates in real time. Abnormal tendencies. Indicates a stimulus window that updates in real time. The number of localized stimulus behaviors. Indicates a stimulus window that updates in real time. The effectiveness of local stimulus behavior B. Indicates a stimulus window that updates in real time. The mean effectiveness of stimulus effectiveness for each local stimulus behavior. Indicates a stimulus window that updates in real time. The standard deviation of the stimulus effectiveness of each local stimulus behavior. Showing the current, real-time updated stimulus window The acquired local stimulus behaviors are displayed in a real-time updated stimulus window. The outlier effect generated in the process; thus, the difference value of the fraction is amplified by cubing while preserving the sign of the numerical fluctuation, and finally, the stimulus window is updated in real time. Various stimuli behaviors This results in a stimulus window that is updated in real time. The effectiveness of stimuli changes in real time during the real-time expansion process.

[0043] Furthermore, as the real-time updated stimulus window expands accordingly after the sensor acquires new monitoring data, the abnormal tendency of the real-time updated stimulus window is updated. The real-time abnormal progress of the real-time updated stimulus window is determined based on the cumulative proportion of the real-time changing abnormal tendency in each direction. Furthermore, the sensitivity of the current physiological sensor signal to the abnormal pain stimulus signal, as shown by the changing trend of the abnormal progress rate, is combined to determine the sensitivity of attribute monitoring. Therefore, this embodiment of the invention determines the abnormal progress of the window based on the degree of change in the cumulative tendency of the abnormal tendency during the real-time expansion of the window. At each time the window's range is updated, the updated abnormal tendency calculated based on the updated range is placed at the current position, thereby obtaining the corresponding abnormal tendency sequence based on the real-time expansion of the window. .

[0044] Furthermore, as an optional embodiment of the present invention, the determining module 101 is also used to: calculate the abnormal tendency difference between the next data item and the previous data item in the abnormal tendency sequence to obtain an abnormal tendency difference sequence; compare the signs of adjacent abnormal tendency differences in the abnormal tendency difference sequence, and continuously mark the abnormal tendencies corresponding to the abnormal tendency differences with the same signs in the abnormal tendency difference sequence to obtain similar fluctuation segments in the abnormal tendency sequence.

[0045] Specifically, the embodiments of the present invention address abnormal tendency sequences. By subtracting the first difference from the previous data point for the next data point, multiple abnormal tendency differences are obtained. Then compare adjacent ones. By comparing the symbols of the two pairs, those with the same symbol are continuously labeled with the corresponding anomalous tendencies, thereby identifying anomalous tendencies in the sequence. Extract the current abnormal tendency sequence Each similar fluctuation segment Q' in the data.

[0046] Furthermore, as an optional embodiment of the present invention, the determining module 101 is also used to: superimpose the abnormal tendency difference values ​​in the abnormal tendency difference sequence that are greater than a threshold to obtain a first superimposed value; superimpose the abnormal tendency difference values ​​in the abnormal tendency difference sequence that are less than a threshold to obtain a second superimposed value; and determine the abnormal process factor of the physiological sensing signal at the current moment based on the first superimposed value, the second superimposed value, and the length of each similar fluctuation segment.

[0047] Specifically, in this embodiment of the invention, the threshold value can be 0. To determine the direction of change: , The values ​​are superimposed separately to obtain the first superimposed value. Second superposition value The length of the similar fluctuation segment can be the length of time. Further, as an optional embodiment of the present invention, the determining module 101 is also used to: calculate the absolute value of a third ratio between the first superposition value and the second superposition value, and a fourth difference between the maximum length of each similar fluctuation segment and the average length of each similar fluctuation segment; and determine the abnormal process factor of the physiological sensing signal at the current moment based on the absolute value of the third ratio, the fourth difference, and the standard deviation of the lengths of each similar fluctuation segment.

[0048] Specifically, the embodiments of the present invention use the following formula to calculate the abnormal process factor at the current time t:

[0049]

[0050] In the above formula, This represents the abnormal process factor of the real-time updated stimulus window at the current time t. This represents the first superposition value. This represents the second superimposed value. This represents the longest length among the lengths of similar fluctuation segments. It represents the average length of the lengths of the similar fluctuation segments. This represents the standard deviation of the lengths of each similar fluctuation segment. It reflects the overall abnormal tendency and corresponding degree of tendency in the stimulus window as of the current time t, in real time. The explanation states that the anomaly at a later time step is more severe than that at the previous time step, thus the numerical value of the formula is differentiated with 1 as the center, representing the real-time growth of the anomaly. Furthermore, by combining the real-time growth of the anomaly with the cumulative deviation of the real-time updated stimulus window, the current stimulus situation represented by the current real-time updated stimulus window can be accurately assessed at different time scales. Therefore, this embodiment of the invention achieves this through... The difference between the scale of the current continuous fluctuations and the steady discrete fluctuations of the stimulus signal indicates that at the current time t, the stimulus behavior has already produced a relatively significant anomaly.

[0051] It should be noted that if the second superposition value is 0, then to prevent the denominator from being 0, a zero-prevention parameter of 0.001 is added to the denominator of the abnormal progress factor calculation formula, that is... .

[0052] Thus, the abnormal process factor c of each physiological sensor signal a at each time t was determined, and the abnormal state period was finally extracted by combining the changes between different physiological sensor signals.

[0053] Furthermore, the determining module 101 is also used to: calculate a fourth ratio between the third superposition value of the abnormal process factor of each physiological sensor signal at the current time and the fourth superposition value of the abnormal process factor of each physiological sensor signal at the previous time; calculate a fifth difference between the abnormal process factors of each physiological sensor signal at the current time and the previous time, and a fifth ratio between the fifth difference between the fifth difference and the fifth difference between the fifth difference and the average process factor of the abnormal process factors of each physiological sensor signal at the current time; and determine the triggering factor for assessing the abnormal pain state at the current time based on the fourth ratio and the fifth ratio.

[0054] Specifically, the embodiments of the present invention employ the following formula to calculate the triggering factor for abnormal pain states:

[0055]

[0056] In the above formula, This represents the triggering factor for the abnormal pain state at the current time t. This represents the third superposition value of the abnormal process factors of each physiological sensor signal at the current time t, that is, the third superposition value is the sum of the abnormal process factors of all types of physiological sensor signals at the current time t. This indicates the time preceding each physiological sensor signal at the current time t. The fourth superposition value of the abnormal process factor, that is, the fourth superposition value is the previous time of the current time t. The sum of abnormal process factors of all types of physiological sensor signals. This represents the abnormal process factor of the real-time updated stimulus window at the current time t. This represents the time before the current time t. The abnormal process factor of the corresponding real-time updated stimulus window. This represents the average process factor of the abnormal process factors of each physiological sensor signal at the current moment. This indicates the number of types of physiological sensory signals. The ratio reflects the triggering of abnormal situations in the current overall environment. This reflects the anomalous scale of a single physiological sensor signal at the current time t, thereby traversing the total number of physiological sensor signals. The completed changes are obtained, thus revealing the overall scale of the anomaly.

[0057] Finally, the triggering factor is normalized using a normalization function. Normalization is performed to obtain a normalized trigger factor with a range of [-1, 1]. .

[0058] Furthermore, as an optional embodiment of the present invention, the intervention module 102 is also used to: map the normalized triggering factor to the corresponding color through false color and perform corresponding intervention behaviors according to the color, wherein different colors represent different pain levels of the target user.

[0059] Specifically, in this embodiment of the invention, false color is used. Specifically, in the RGB space, the path connecting the points (255,0,0) and (0,255,0) from red to green is selected, and the normalized triggering factor with a value range of [-1,1] is used. Point-to-point mapping with the connection line is used to visualize the patient's pain level. For example, green (-1) represents low pain abnormality and red (1) represents high pain abnormality. The visualization is displayed through the patient's electronic records and other visual GUIs to notify professional medical personnel to intervene.

[0060] The determination module in this embodiment of the invention can determine abnormal tendencies based on real-time and historical curves of the target user's physiological sensor signals, and then determine abnormal process factors based on the difference in abnormal tendencies. This method can capture the pain-related signal characteristics of different patients, solving the problem of insufficient accuracy and sensitivity of traditional methods when facing individual differences, and achieving more accurate identification and judgment of the patient's pain state. After generating the abnormal tendency sequence, the determination module identifies similar fluctuation segments based on the difference in abnormal tendencies, and calculates the abnormal process factor accordingly. From the perspective of dynamic changes, it comprehensively grasps the abnormal change process of physiological sensor signals over a period of time, and can capture the changing trend and fluctuation characteristics of signals. By determining the normalization trigger factor through the abnormal process factors of each physiological sensor signal at the current moment and the previous moment, this process transforms complex physiological signal characteristics into unified and standardized evaluation indicators. Normalization processing enables pain data from different patients and different types to be compared on the same scale, greatly improving the accuracy and comparability of the evaluation. Medical staff only need to rely on the normalized trigger factor to quickly and accurately judge the patient's pain level, and then promptly carry out visual analysis and implement corresponding intervention measures. Therefore, the above-mentioned approach not only improves the efficiency of pain management, but also enhances the accuracy and sensitivity of identifying abnormal physiological signals.

[0061] Example 2:

[0062] Corresponding to the real-time physiological signal monitoring and intervention system for pain management provided in the above embodiments, based on the same technical concept, this invention also provides another real-time physiological signal monitoring and intervention system for pain management. Figure 2 This is a schematic diagram of another physiological signal real-time monitoring and intervention system for pain management provided in one embodiment of the present invention, as shown below. Figure 2 As shown. Real-time physiological signal monitoring and intervention systems for pain management can vary considerably due to differences in configuration or performance. They may include one or more processors 201 and memory 202. The memory 202 stores computer programs that can run on the processor 201. The processor 201 executes the programs stored in the memory 202 to achieve the following steps:

[0063] Based on the real-time and historical curves of the target user's physiological sensor signals, the abnormal tendencies of the real-time updated stimulation window at each update time are determined, and an abnormal tendency sequence is obtained.

[0064] Based on the difference in abnormal trends between the next data point and the previous data point in the abnormal trend sequence, similar fluctuation segments in the abnormal trend sequence are determined.

[0065] Based on the difference in abnormal tendencies and the length of each similar fluctuation segment, the abnormal process factor of the physiological sensing signal at the current moment is determined.

[0066] Based on the abnormal process factors of each physiological sensor signal at the current time and the previous time, the triggering factors for assessing the abnormal pain state at the current time are determined, and the triggering factors are normalized to obtain normalized triggering factors. The pain level of the target user is visualized based on the normalized triggering factors.

[0067] The memory 202 can be either temporary or persistent storage. The applications stored in the memory 202 may include one or more modules (not shown in the figure), each module including a series of computer-executable instructions for a real-time monitoring and intervention system for physiological signals oriented towards pain management.

[0068] Furthermore, the processor 201 can be configured to communicate with the memory 202 and execute a series of computer-executable instructions stored in the memory 202 on the real-time physiological signal monitoring and intervention system for pain management. The real-time physiological signal monitoring and intervention system for pain management may also include one or more power supplies 203, one or more wired or wireless network interfaces 204, one or more input / output interfaces 205, and one or more keyboards 206.

[0069] Specifically, in this embodiment, the real-time physiological signal monitoring and intervention system for pain management includes a processor, a communication interface, a memory, and a communication bus; wherein, the processor, communication interface, and memory communicate with each other via the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the following steps:

[0070] Based on the real-time and historical curves of the target user's physiological sensor signals, the abnormal tendencies of the real-time updated stimulation window at each update time are determined, and an abnormal tendency sequence is obtained.

[0071] Based on the difference in abnormal trends between the next data point and the previous data point in the abnormal trend sequence, similar fluctuation segments in the abnormal trend sequence are determined.

[0072] Based on the abnormal tendency difference and the length of each of the similar fluctuation segments, the abnormal process factor of the physiological sensing signal at the current moment is determined.

[0073] Based on the abnormal process factors of each physiological sensor signal at the current and previous times, the triggering factors for assessing the abnormal pain state at the current time are determined, and the triggering factors are normalized to obtain normalized triggering factors. The pain level of the target user is visualized based on the normalized triggering factors. This method possesses the beneficial effects of the above-described embodiments, and to avoid repetition, the embodiments of this invention will not be elaborated upon here.

[0074] It should be noted that the other physiological signal real-time monitoring and intervention system for pain management provided in this embodiment of the invention is based on the same application concept as the physiological signal real-time monitoring and intervention system for pain management provided in the above embodiment of the invention. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned physiological signal real-time monitoring and intervention system for pain management, and has the same or similar beneficial effects. Repeated parts will not be repeated.

[0075] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0077] This invention also proposes a computer-readable storage medium storing one or more programs, which, when executed by a real-time physiological signal monitoring and intervention system for pain management that includes multiple applications, cause the real-time physiological signal monitoring and intervention system for pain management to perform... Figure 1 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods in the preceding method embodiments, and will not be repeated here.

[0078] The computer-readable storage media include read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A real-time physiological signal monitoring and intervention system for pain management, characterized in that, include: The determination module is used to determine the abnormal tendencies of the real-time updated stimulation window at each update time based on the real-time curves and historical curves of the target user's various physiological sensor signals, and to obtain the abnormal tendency sequence. The determining module is further configured to determine similar fluctuation segments in the abnormal trend sequence based on the abnormal trend difference between the subsequent data and the preceding data in the abnormal trend sequence. The determining module is further configured to determine the abnormal process factor of the physiological sensing signal at the current moment based on the abnormal tendency difference and the length of each of the similar fluctuation segments. The determining module is further configured to determine the triggering factor for assessing the abnormal pain state at the current moment based on the abnormal process factors of each physiological sensor signal at the current moment and the previous moment, and to normalize the triggering factor to obtain the normalized triggering factor. An intervention module is used to visualize and intervene in the pain level of the target user based on the normalized triggering factor.

2. The real-time physiological signal monitoring and intervention system for pain management according to claim 1, characterized in that, The determining module is further configured to: The waveform segments corresponding to a pair of minimum values ​​at adjacent positions of the real-time curve of the physiological sensing signal are determined as the current local stimulation behavior; The effectiveness of the current local stimulation behavior is determined based on the first difference between any two points in the local sensor signal curve segment corresponding to the current local stimulation behavior, the second difference between the historical maximum value and the historical mean value of the historical curve, the duration of the current local stimulation behavior, and the average of the duration of the historical local stimulation behavior corresponding to the physiological sensor signal. Based on the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window, the abnormal tendency of the real-time updated stimulus window at each update time is determined, and an abnormal tendency sequence is obtained.

3. The real-time physiological signal monitoring and intervention system for pain management according to claim 2, characterized in that, The determining module is further configured to: Determine the maximum difference among the first differences between any two points in the local sensor signal curve segment corresponding to the current local stimulus behavior; Calculate a first ratio between the maximum difference and a second difference between the historical maximum value and the historical mean of the historical curve, and a second ratio between the duration of the current local stimulation behavior and the average duration of the historical local stimulation behavior corresponding to the physiological sensing signal; The effectiveness of the current local stimulus behavior is determined based on the first ratio and the second ratio.

4. The real-time physiological signal monitoring and intervention system for pain management according to claim 2, characterized in that, The determining module is further configured to: Calculate the third difference between the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window and the mean effectiveness of the stimulus effectiveness of each local stimulus behavior; Based on the third difference and the standard deviation of the stimulus effectiveness of each local stimulus behavior in the real-time updated stimulus window, the abnormal tendency is determined, and an abnormal tendency sequence is obtained.

5. The real-time physiological signal monitoring and intervention system for pain management according to claim 1, characterized in that, The determining module is further configured to: Calculate the difference in anomalous tendency between the next data point and the previous data point in the anomalous tendency sequence to obtain the anomalous tendency difference sequence; By comparing the signs of adjacent abnormal tendency differences in the abnormal tendency difference sequence, the abnormal tendencies corresponding to the abnormal tendency differences with the same sign in the abnormal tendency difference sequence are continuously marked to obtain similar fluctuation segments in the abnormal tendency sequence.

6. The real-time physiological signal monitoring and intervention system for pain management according to claim 5, characterized in that, The determining module is further configured to: The abnormal tendency difference values ​​in the abnormal tendency difference sequence that are greater than a threshold are superimposed to obtain a first superimposed value, and the abnormal tendency difference values ​​in the abnormal tendency difference sequence that are less than a threshold are superimposed to obtain a second superimposed value. Based on the first superposition value, the second superposition value, and the length of each of the similar fluctuation segments, the abnormal process factor of the physiological sensing signal at the current moment is determined.

7. The real-time physiological signal monitoring and intervention system for pain management according to claim 6, characterized in that, The determining module is further configured to: Calculate the absolute value of the third ratio between the first superimposed value and the second superimposed value, and the fourth difference between the maximum length of each of the similar fluctuation segments and the average length of each of the similar fluctuation segments; The abnormal process factor of the physiological sensing signal at the current moment is determined based on the absolute value of the third ratio, the fourth difference, and the standard deviation of the length of each of the similar fluctuation segments.

8. The real-time physiological signal monitoring and intervention system for pain management according to claim 1, characterized in that, The determining module is further configured to: Calculate the fourth ratio between the third superposition value of the abnormal process factor of each physiological sensor signal at the current time and the fourth superposition value of the abnormal process factor of each physiological sensor signal at the previous time. Calculate the fifth difference between the abnormal process factors of each of the physiological sensing signals at the current time and the previous time, and the fifth ratio between the average process factor of the abnormal process factors of each of the physiological sensing signals at the current time. Based on the fourth ratio and the fifth ratio, the triggering factor for assessing the abnormal pain state at the current moment is determined.

9. The real-time physiological signal monitoring and intervention system for pain management according to claim 1, characterized in that, The intervention module is also used for: The normalized triggering factor is mapped to a corresponding color using false color, and corresponding intervention actions are performed based on the color. Different colors represent different levels of pain for the target user.

10. A real-time physiological signal monitoring and intervention system for pain management, characterized in that, include: A processor and memory; wherein the memory stores computer programs that can run on the processor; and the processor executes the programs stored in the memory to perform the following steps: Based on the real-time and historical curves of the target user's physiological sensor signals, the abnormal tendencies of the real-time updated stimulation window at each update time are determined, and an abnormal tendency sequence is obtained. Based on the difference in abnormal trends between the next data point and the previous data point in the abnormal trend sequence, similar fluctuation segments in the abnormal trend sequence are determined. Based on the abnormal tendency difference and the length of each of the similar fluctuation segments, the abnormal process factor of the physiological sensing signal at the current moment is determined. Based on the abnormal process factors of each physiological sensor signal at the current time and the previous time, the triggering factor for assessing the abnormal pain state at the current time is determined, and the triggering factor is normalized to obtain the normalized triggering factor. The pain level of the target user is visualized based on the normalized triggering factor.

Images