Pain data processing system for tumor patients

Abstract

The present invention discloses a tumor patient pain data processing system, which relates to the technical field of health data processing, and includes a data acquisition module for collecting target physiological data and behavioral data; a physiological monitoring module for constructing a target heart rate abnormality index and a breathing abnormality index; a judgment module for judging the target physiological state; a behavior analysis module for analyzing the voice signal pitch fluctuation state and the voice signal strength abnormality, and analyzing the target behavior state according to the analysis results of the voice signal pitch fluctuation state and the voice signal strength abnormality within the management period; a pain assessment module for dividing the target pain level and outputting the pain level to the user; a data analysis module for analyzing the abnormality of the target skin conductance level and adjusting the division process of the target pain level according to the analysis results. The present invention improves the accuracy of pain assessment for tumor patients.

Description

Technical Field

[0001] The present invention relates to the technical field of health data processing, and in particular to a pain data processing system for tumor patients. Background Art

[0002] With the rapid development of medical technology, data-driven patient management systems are becoming an increasingly important component of modern healthcare. This is particularly true for pain management in cancer patients. Traditional assessment methods often rely on subjective physician judgment or patient self-reporting, making it difficult to fully and accurately reflect a patient's true pain status. Therefore, pain data processing systems have emerged, aiming to objectively assess a patient's pain status through multi-dimensional data collection and analysis, combined with physiological indicators and behavioral characteristics.

[0003] Chinese patent publication number CN114220543A discloses a method and system for assessing the physical and mental pain index of cancer patients, and the method is specifically as follows: S1. Collecting a video of the patient's observation period, intercepting the image to be analyzed, and extracting the facial image in the image to be analyzed; S2. Inputting the facial image into a pre-trained neural network physical pain and psychological pain recognition model for pain recognition, and obtaining a first physical pain level and a first psychological pain level; S3. Automatically detecting and tracking the trajectory of the patient's posture changes in the observation video, obtaining the posture change frequency and the second physical pain level; S4. The patient conducts self-assessment through psychological pain test questions and physical pain test questions, and obtains a second psychological pain level and a third physical pain level; S5. Calculating the physical pain assessment value and the psychological pain assessment value according to the preset weight coefficient; It can be seen that this scheme does not consider the influence of multiple factors when performing pain recognition based on facial features and posture changes, such as drug side effects, postoperative recovery status, etc., and there is a problem of low accuracy in pain assessment of cancer patients. Summary of the Invention

[0004] The object of the present invention is to provide a pain data processing system for tumor patients to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] Tumor patient pain data processing system, including:

[0007] Data acquisition module, used to collect target physiological data and behavioral data;

[0008] A physiological monitoring module is used to construct a target heart rate abnormality index and a target respiratory abnormality index based on the target heart rate and target respiratory rate collected during the monitoring period;

[0009] A judgment module is used to judge the target physiological state according to the results of constructing the target heart rate abnormality index and the breathing abnormality index during the monitoring period;

[0010] A behavior analysis module is used to analyze the pitch fluctuation state and the abnormality of the voice signal strength based on the target voice signal collected during the management period, and to analyze the target behavior state based on the analysis results of the pitch fluctuation state and the abnormality of the voice signal strength during the management period;

[0011] The pain assessment module is used to classify the target pain level based on the analysis results of the target physiological state and the target behavioral state during the management cycle, and output the pain level to the user;

[0012] The data analysis module is used to analyze the abnormality of the target skin conductance level based on the target skin conductance level collected during the management period, and adjust the target pain level classification process based on the analysis results.

[0013] Furthermore, the physiological monitoring module is provided with a heart rate monitoring unit and a respiratory monitoring unit. The heart rate monitoring unit is used to compare the target heart rate s1 collected during the monitoring period with the preset heart rate a1 to analyze the abnormality of the target heart rate. The abnormality of the target heart rate includes normal heart rate and abnormal heart rate. If the target heart rate in the current monitoring period is normal, the heart rate abnormality index is set to A1. If the target heart rate in the current monitoring period is abnormal, the heart rate abnormality index is set to A2.

[0014] Furthermore, the respiratory monitoring unit is used to compare the target respiratory frequency s2 collected during the monitoring period with the preset respiratory frequency a2 to analyze the abnormality of the target respiratory frequency. The abnormality of the target respiratory frequency includes normal respiratory frequency and abnormal respiratory frequency. If the target respiratory frequency in the current monitoring period is normal, the respiratory abnormality index is set to B1. If the target respiratory frequency in the current monitoring period is abnormal, the respiratory abnormality index is set to B2.

[0015] Furthermore, the judgment module judges the target physiological state based on the construction results of the target heart rate abnormality index and the breathing abnormality index within the monitoring period. If x1×heart rate abnormality index+x2×breathing abnormality index≤RT, the judgment module determines that the target physiological state of the current monitoring period is normal; if x1×heart rate abnormality index+x2×breathing abnormality index>RT, the judgment module determines that the target physiological state of the current monitoring period is abnormal, x1 is the heart rate weight, x2 is the breathing weight, and RT is the physiological index threshold.

[0016] Furthermore, the behavior analysis module is provided with a tone analysis unit, an intensity analysis unit and a behavior analysis unit. The tone analysis unit is used to extract the tone of each speech frame based on the speech signal collected during the management period, and analyze the pitch change rate B of the management period, and compare the pitch change rate B with the preset change rate B0 to analyze the pitch fluctuation state of the speech signal, and the pitch fluctuation state of the speech signal includes normal and abnormal.

[0017] Furthermore, the intensity analysis unit is used to calculate the voice signal intensity according to the signal amplitude of each voice frame of the collected voice signal, set the voice signal intensity of the i-th voice frame as Ei, and analyze the voice signal intensity E0 according to the analysis result of the signal intensity of each voice frame;

[0018] The strength analysis unit compares the speech signal strength E0 with a preset strength EY to analyze the abnormality of the speech signal strength. The abnormality of the speech signal strength includes normal and abnormal.

[0019] Furthermore, the behavior analysis unit is used to analyze the target behavior state based on the analysis results of the pitch fluctuation state of the voice signal within the management period and the analysis results of the abnormality of the voice signal intensity. If (w1×r1+w2×r2) / 2×r0≤u0, the behavior analysis unit determines that the target behavior state of the current management period is normal; if (w1×r1+w2×r2) / 2×r0>u0, the behavior analysis unit determines that the target behavior state of the current management period is abnormal, w1 is the fluctuation weight, w2 is the intensity weight, r1 is the number of voice signals with abnormal fluctuation state within the management period, r2 is the number of voice signals with abnormal intensity within the management period, r0 is the number of target voice signals collected within the management period, and u0 is the preset behavior threshold.

[0020] Furthermore, the pain assessment module divides the target pain level into mild pain, moderate pain and severe pain according to the analysis results of the target physiological state and the target behavioral state within the management period, and outputs the target pain level to the user.

[0021] Furthermore, the data analysis module is provided with an abnormality analysis unit and a fluctuation analysis unit; the abnormality analysis unit is used to calculate the target skin conductance level average value DP collected during the management period, and compare the target skin conductance level average value DP with the preset conductance level threshold d0 to analyze the abnormality of the target skin conductance level. The abnormality of the target skin conductance level includes normal and abnormal. If the target skin conductance level of the current management period is abnormal, the first pain threshold is adjusted to L1', and the second pain threshold is adjusted to L2'.

[0022] Furthermore, the fluctuation analysis unit is used to calculate the fluctuation coefficient BD of the target skin conductance level based on the target skin conductance level collected during the management period, and compare the fluctuation coefficient BD of the target skin conductance level with a preset fluctuation threshold YD to analyze the fluctuation state of the target skin conductance level. The fluctuation state of the target skin conductance level includes normal and abnormal. If the fluctuation state of the target skin conductance level in the current management period is abnormal, the preset conductance level threshold is adjusted to d0'.

[0023] The beneficial effects of the present invention are as follows: This system comprehensively covers the three key dimensions of physiological signals, behavioral signals and conductance signals, and conducts a holistic assessment of the pain status of cancer patients, which is more accurate and scientific than single-dimensional assessment. It also provides a dynamic adaptive adjustment mechanism. Through multiple dynamic adjustment mechanisms (threshold adjustment, fluctuation analysis, etc.), it can effectively respond to changes in patients at different times, environments and emotions, truly realizing personalized and intelligent pain monitoring and assessment. Moreover, through automated data processing and evaluation, it reduces the pressure of manual monitoring, improves the efficiency of pain management for cancer patients, and assists medical teams in making better decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 Schematic diagram of the structure of the pain data processing system for tumor patients in this embodiment.

[0026] Figure 2 Schematic diagram of the structure of the physiological monitoring module of this embodiment.

[0027] Figure 3 Schematic diagram of the behavior analysis module in this embodiment.

[0028] Figure 4 Schematic diagram of the structure of the data analysis module in this embodiment. DETAILED DESCRIPTION

[0029] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the following detailed description is illustrative rather than restrictive and should not be used to limit the scope of protection of the present invention.

[0030] It should be noted that, although the terms "first," "second," and "third" may be used to describe the embodiments of the present application, the description should not be limited to these terms. These terms are merely used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, "first" may also be referred to as "second," and similarly, "second" may also be referred to as "first."

[0031] See also Figure 1 As shown, it is a structural diagram of the pain data processing system for tumor patients in this embodiment, and the system includes: a data acquisition module for collecting target physiological data and behavioral data, the physiological data including heart rate and respiratory rate, the behavioral data including target voice signals, and the target is a tumor patient; in this embodiment, no specific limitation is made to the collection method of target physiological data and behavioral data, and those skilled in the art can freely set it, as long as the collection requirements of target physiological data and behavioral data are met, wherein the target physiological data can be collected by smart wearable devices, and the behavioral data can be collected by recording equipment; it should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant national and regional laws, regulations and standards.

[0032] Please continue reading Figure 1 As shown, the system includes a physiological monitoring module for constructing a target heart rate abnormality index and a respiratory abnormality index according to the target heart rate and respiratory rate collected during the monitoring period. The physiological monitoring module is connected to the data acquisition module.

[0033] See also Figure 2 As shown, the physiological monitoring module includes a heart rate monitoring unit, which is used to compare the target heart rate s1 collected during the monitoring period with the preset heart rate a1 to analyze the abnormality of the target heart rate and construct a heart rate abnormality index. If s1≤a1, the heart rate monitoring unit determines that the target heart rate of the current monitoring period is normal, and sets the heart rate abnormality index to A1, setting A1=0; if s1>a1, the heart rate monitoring unit determines that the target heart rate of the current monitoring period is abnormal, and sets the heart rate abnormality index to A2, setting A2=exp[lg(s1-a1) / a1]; by comparing with the preset heart rate, the heart rate abnormality can be quickly identified, and the quantitative analysis concretizes the degree of abnormality, making the assessment of the degree of heart rate abnormality more detailed.

[0034] Specifically, in this embodiment, there is no specific limitation on the setting of the preset heart rate, and those skilled in the art can set it freely, as long as the setting requirements of the preset heart rate are met. Among them, the optimal value of a1 is 75 beats / minute.

[0035] Please continue reading Figure 2 As shown, the physiological monitoring module includes a respiratory monitoring unit, which is connected to the heart rate monitoring unit. The respiratory monitoring unit compares the target respiratory frequency s2 collected during the monitoring period with the preset respiratory frequency a2 to analyze the abnormality of the target respiratory frequency and construct a respiratory abnormality index. If s2≤a2, the respiratory monitoring unit determines that the target respiratory frequency of the current monitoring period is normal, and sets the respiratory abnormality index to B1, setting B1=0; if s2>a2, the respiratory monitoring unit determines that the target respiratory frequency of the current monitoring period is abnormal, and sets the respiratory abnormality index to B2, setting B2=(s2-a2) / a2; through real-time monitoring of the respiratory frequency, it is helpful to timely detect physiological abnormalities, construct a respiratory abnormality index, and realize quantitative analysis of the physiological state.

[0036] Specifically, in this embodiment, there is no specific limitation on the setting of the preset respiratory frequency, and those skilled in the art can freely set it as long as the setting requirements of the preset respiratory frequency are met. Among them, the optimal value of a2 is 16 times / minute.

[0037] Specifically, the present embodiment does not impose any specific limitation on the setting of the monitoring period, and those skilled in the art can freely set it as long as the setting requirements of the monitoring period are met. The monitoring period can be set to 1 minute.

[0038] Please continue reading Figure 1 As shown, the system includes a judgment module, which is connected to the physiological monitoring module and is used to judge the target physiological state according to the construction results of the target heart rate abnormality index and the breathing abnormality index during the monitoring period to improve the accuracy of the target physiological state judgment, wherein:

[0039] If x1×heart rate abnormality index+x2×respiration abnormality index≤RT, the judgment module determines that the target physiological state of the current monitoring period is normal;

[0040] If x1×heart rate abnormality index+x2×respiration abnormality index>RT, the judgment module determines that the target physiological state of the current monitoring period is abnormal, x1 is the heart rate weight, x2 is the respiration weight, x1+x2=1, and RT is the physiological index threshold; by combining the heart rate and respiration abnormality index, an overall judgment of the physiological state is provided to enhance the accuracy of the judgment, thereby improving the accuracy of the target pain level classification.

[0041] Specifically, in this embodiment, there is no specific limitation on the setting of each weight and physiological index threshold. Those skilled in the art can set it freely as long as the setting requirements of each weight and physiological index threshold are met. Among them, the optimal value of x1 is 0.55, the optimal value of x2 is 0.45, and the optimal value of RT is 0.21.

[0042] Please continue reading Figure 1 As shown, the system includes a behavior analysis module, which is used to analyze the target behavior state according to the target voice signal collected during the management period. The behavior analysis module is connected to the data collection module.

[0043] Specifically, in this embodiment, there is no specific limitation on the setting of the management period, and those skilled in the art can set it freely, as long as the setting requirements of the management period are met. Among them, the setting of the management period should be greater than the setting of the monitoring period, and the management period can be set to 20 minutes, 30 minutes, etc.

[0044] See also Figure 3 As shown, the behavior analysis module includes a tone analysis unit, which extracts the tone of each voice frame based on the voice signal collected during the management period and analyzes the pitch change rate B of the management period, setting:

[0045] , F(i) is the pitch value of the i-th speech frame, F(i+1) is the pitch value of the i+1-th speech frame, and N is the total number of speech frames;

[0046] The tone analysis unit compares the tone change rate B with a preset change rate B0 to analyze the tone fluctuation state of the voice signal, thereby quickly identifying abnormal tone fluctuations of the patient, wherein:

[0047] When B≤B0, the tone analysis unit determines that the voice signal fluctuation is normal;

[0048] When B>B0, the tone analysis unit determines that the tone fluctuation state of the voice signal is abnormal; through the tone analysis of the voice frame, the fluctuation of the patient's emotions can be intuitively identified, which helps to discover the patient's emotional conditions such as anxiety, depression or excitement caused by pain.

[0049] Specifically, in this embodiment, the setting of the preset change rate is not specifically limited, and those skilled in the art can freely set it as long as the setting requirements of the preset change rate are met. Among them, the optimal value of B0 is 2 Hz.

[0050] Specifically, in this embodiment, there is no specific limitation on the division of speech frames and the extraction of speech frame pitch values. Those skilled in the art can freely set them as long as the division of speech frames and the extraction of speech frame pitch values ​​are met. The speech signal can be divided into a speech frame every 10 milliseconds, and the pitch value of each frame can be extracted through tools such as Librosa and Praat.

[0051] Please continue reading Figure 3As shown, the behavior analysis module includes an intensity analysis unit, which is connected to the tone analysis unit and is used to calculate the strength of the voice signal according to the signal amplitude of each voice frame of the collected voice signal and analyze the abnormality of the voice signal strength, wherein:

[0052] The intensity analysis unit sets the speech signal intensity of the i-th speech frame as Ei, and sets:

[0053] , x(i,m) is the signal amplitude of the mth sampling point in the i-th speech frame, and M is the number of sampling points in the i-th speech frame;

[0054] The intensity analysis unit analyzes the speech signal intensity E0 according to the analysis result of each speech frame signal intensity, and sets: ;

[0055] The intensity analysis unit compares the voice signal intensity E0 with the preset intensity EY to analyze the abnormality of the voice signal intensity, thereby objectively evaluating the abnormality of the voice signal intensity, wherein:

[0056] If E0≤EY, the intensity analysis unit determines that the voice signal intensity is normal; if E0>EY, the intensity analysis unit determines that the voice signal intensity is abnormal; by analyzing the amplitude of the voice signal, the emotional intensity of the patient's expression is directly perceived, the intensity of each voice frame is calculated and quantitative analysis is performed, thereby improving the accuracy of behavioral state analysis.

[0057] Specifically, in this embodiment, the method for collecting the signal amplitude of each speech frame of the speech signal is not specifically limited. Those skilled in the art can freely set it, as long as the collection requirements of the signal amplitude of each speech frame of the speech signal are met. Among them, Librosa in the Python library can be used for collection.

[0058] Specifically, the setting of the preset intensity is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset intensity are met. Among them, the optimal value of a1 is 0.9V.

[0059] Please continue reading Figure 3 As shown, the behavior analysis module includes a behavior analysis unit, which is connected to the intensity analysis unit and is used to analyze the target behavior state according to the analysis results of the voice signal pitch fluctuation state and the analysis results of the voice signal intensity abnormality within the management period, wherein:

[0060] If (w1×r1+w2×r2) / 2×r0≤u0, the behavior analysis unit determines that the target behavior state of the current management cycle is normal;

[0061] If (w1×r1+w2×r2) / 2×r0>u0, the behavior analysis unit determines that the target behavior state of the current management cycle is abnormal, w1 is the fluctuation weight, w2 is the intensity weight, w1+w2=1, r1 is the number of voice signals with abnormal fluctuation state within the management cycle, r2 is the number of voice signals with abnormal intensity within the management cycle, r0 is the number of target voice signals collected within the management cycle, and u0 is the preset behavior threshold; by comprehensively considering the analysis results of the fluctuation state and intensity of the voice, applying different weights for weighted averaging, the patient's current behavior state is fully reflected. This comprehensive multi-dimensional analysis improves the accuracy of the assessment.

[0062] Specifically, in this embodiment, there is no specific limitation on the setting of each weight and the preset behavior threshold. Those skilled in the art can set it freely, as long as the setting requirements of each weight and the preset behavior threshold are met. Among them, the optimal value of w1 is 0.52, the optimal value of w2 is 0.48, and the optimal value of u0 is 0.23.

[0063] Please continue reading Figure 1 As shown, the system includes a pain assessment module, which is connected to the judgment module and the behavior analysis module. The pain assessment module is used to classify the target pain level according to the analysis results of the target physiological state and the target behavioral state within the management period to improve the accuracy of the level classification and output the pain level to the user, wherein:

[0064] If the target behavior state is normal during the management cycle, when P1×k1 / k0≤L1, the pain assessment module determines that the target pain level of the current management cycle is mild pain; when L1<P1×k1 / k0<L2, the pain assessment module determines that the target pain level of the current management cycle is moderate pain; when P1×k1 / k0≥L2, the pain assessment module determines that the target pain level of the current management cycle is severe pain;

[0065] If the target behavior state is abnormal during the management cycle, when P1×k1 / k0+P2×(u1-u0) / u0≤L1, the pain assessment module determines that the target pain level of the current management cycle is mild pain; when L1<P1×k1 / k0+P2×(u1-u0) / u0<L2, the pain assessment module determines that the target pain level of the current management cycle is moderate pain; when P1×k1 / k0+P2×(u1-u0) / u0≥L2, the pain assessment module determines that the target pain level of the current management cycle is severe pain;

[0066] Wherein, P1 is the weight of physiological indicators, P2 is the weight of behavioral indicators, P1+P2=1, P1>P2, k1 is the number of monitoring periods in which the target physiological state is abnormal within the management period, k0 is the number of monitoring periods within the management period, L1 is the first pain threshold, L2 is the second pain threshold, L1<L2, u1 is the behavioral state parameter, u1=(w1×r1+w2×r2) / 2×r0;

[0067] The pain assessment module outputs the target pain level to the user; by integrating physiological and behavioral abnormality indices, the pain assessment is made more comprehensive and accurate, no longer relying on a single physiological indicator, but combining behavioral and psychological data, which can better reflect some pain information that is difficult to capture through traditional physiological data. By using an automatic grading method with specific thresholds (mild, moderate and severe pain grading), the patient's pain level can be given in real time, making it easier for doctors to quickly understand the patient's pain condition.

[0068] Specifically, in this embodiment, there is no specific limitation on the setting of each weight and each pain threshold. Those skilled in the art can set them freely as long as the setting requirements of each weight and each pain threshold are met. Among them, the optimal value of P1 is 0.7, the optimal value of P2 is 0.3, the optimal value of L1 is 0.12, and the optimal value of L2 is 0.36.

[0069] Specifically, the mild pain described in this embodiment is pain that is felt but does not affect daily activities, the moderate pain is obvious pain that affects daily activities but is still tolerable, and the severe pain is very severe and the patient cannot work or carry out normal activities and needs immediate treatment.

[0070] Please continue reading Figure 1 As shown, the system includes a data analysis module, which is connected to the pain assessment module. The data analysis module is used to analyze the abnormality of the target skin conductance level based on the target skin conductance level collected during the management period, and adjust the target pain level division process according to the analysis results.

[0071] Specifically, in this embodiment, there is no specific limitation on the method for collecting the target skin conductance level, and those skilled in the art can freely set it as long as the collection requirements of the target skin conductance level are met, among which, the target skin conductance level can be collected through a skin conductance sensor.

[0072] See also Figure 4 As shown, the data analysis module includes an abnormality analysis unit, which is used to calculate the target skin conductance level average DP collected during the management period, setting:

[0073] , Dj is the j-th target skin conductance level data collected during the management period, and J is the number of target skin conductance level data collected during the management period;

[0074] The abnormality analysis unit compares DP with a preset conductance level threshold d0 to analyze the abnormality of the target skin conductance level. If DP ≤ d0, the abnormality analysis unit determines that the skin conductance level of the current management cycle is normal and does not make any adjustments. If DP > d0, the abnormality analysis unit determines that the target skin conductance level of the current management cycle is abnormal, and adjusts the first pain threshold to L1', setting L1'=L1×exp[-(DP-d0) / (DP+d0)]; and adjusts the second pain threshold to L2', setting L2'=L2×exp[-(DP-d0) / (DP+d0)]; through the skin conductance level, a more sensitive physiological indicator, the accuracy of pain assessment is further improved, and by adjusting the pain thresholds (L1 and L2) in real time, the assessment mechanism is adjusted according to the actual monitoring situation, and dynamically adapts to the patient's physiological changes, the accuracy is higher, making the pain management strategy personalized.

[0075] Specifically, in this embodiment, the setting of the preset conductivity level threshold is not specifically limited, and those skilled in the art can freely set it as long as the setting requirements of the preset conductivity level threshold are met. Among them, the optimal value of d0 is 20 μS.

[0076] Please continue reading Figure 4 As shown, the data analysis module includes a fluctuation analysis unit, which is connected to the abnormality analysis unit and is used to calculate the fluctuation coefficient BD of the target skin conductance level based on the target skin conductance level collected during the management period, and set:

[0077] The fluctuation analysis unit compares BD with a preset fluctuation threshold value YD to analyze the fluctuation state of the target skin conductance level and adjusts the analysis process of the abnormality of the target skin conductance level according to the analysis result, wherein:

[0078] If BD≤YD, the fluctuation analysis unit determines that the fluctuation state of the target skin conductance level in the current management period is normal and does not make any adjustments; if BD>YD, the fluctuation analysis unit determines that the fluctuation state of the target skin conductance level in the current management period is abnormal, and adjusts the preset conductance level threshold to d0', setting: d0'=d0×[1-ln[9×(BD-YD)+1] / ln10]; by analyzing the skin conductance fluctuation coefficient, the overall fluctuation of the patient's emotions or stress changes within a certain period can be captured, helping to identify persistent pain or abnormal emotional states, and the threshold is adjusted in real time based on the characteristics of the conductance data fluctuation, thereby improving the stability and rationality of skin conductance data analysis.

[0079] Specifically, in this embodiment, there is no specific limitation on the setting of the preset fluctuation threshold, and those skilled in the art can set it freely, as long as the setting requirements of the preset fluctuation threshold are met. Among them, the optimal value of YD is 0.3.

[0080] Specifically, the system described in this embodiment is specifically used in the pain management department of a hospital. Doctors can use the system to monitor the physiological and behavioral data of cancer patients in real time, comprehensively assess the patient's pain level, and adjust the treatment plan in a timely manner.

[0081] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in this field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A tumor patient pain data processing system, characterized in that: include, Data collection module, used to collect target physiological data and behavioral data; A physiological monitoring module is used to construct a target heart rate abnormality index and a target breathing abnormality index according to the target heart rate and target breathing rate collected during the monitoring period; A judgment module is used to judge the target physiological state according to the construction results of the target heart rate abnormality index and the breathing abnormality index during the monitoring period; A behavior analysis module, for analyzing the pitch fluctuation state of the voice signal and the abnormality of the voice signal strength according to the target voice signal collected during the management period, and analyzing the target behavior state according to the analysis results of the pitch fluctuation state of the voice signal and the analysis results of the abnormality of the voice signal strength during the management period; The pain assessment module is used to classify the target pain level according to the analysis results of the target physiological state and the target behavioral state during the management cycle, and output the pain level to the user; A data analysis module, for analyzing the abnormality of the target skin conductance level according to the target skin conductance level collected during the management period, and adjusting the classification process of the target pain level according to the analysis results; The data analysis module is provided with an abnormality analysis unit and a fluctuation analysis unit; the abnormality analysis unit is used to calculate the target skin conductance level average DP collected during the management period, and compare the target skin conductance level average DP with the preset conductance level threshold d0 to analyze the abnormality of the target skin conductance level, the abnormality of the target skin conductance level includes normal and abnormal, if the target skin conductance level of the current management period is abnormal, the first pain threshold is adjusted to L1', L1'=L1×exp[-(DP-d0) / (DP+d0)] is set, and the second pain threshold is adjusted to L2', L2'=L2×exp[-(DP-d0) / (DP+d0)] is set, L1 is the first pain threshold, L2 is the second pain threshold; The fluctuation analysis unit is used to calculate the fluctuation coefficient BD of the target skin conductance level according to the target skin conductance level collected during the management period, and compare the fluctuation coefficient BD of the target skin conductance level with the preset fluctuation threshold value YD to analyze the fluctuation state of the target skin conductance level. The fluctuation state of the target skin conductance level includes normal and abnormal. If the fluctuation state of the target skin conductance level in the current management period is abnormal, the preset conductance level threshold is adjusted to d0', and d0'=d0×[1-ln[9×(BD-YD)+1] / ln10].

2. The tumor patient pain data processing system according to claim 1, characterized in that: The physiological monitoring module is provided with a heart rate monitoring unit and a respiratory monitoring unit. The heart rate monitoring unit is used to compare the target heart rate s1 collected during the monitoring period with the preset heart rate a1 to analyze the abnormality of the target heart rate. The abnormality of the target heart rate includes normal heart rate and abnormal heart rate. If the target heart rate in the current monitoring period is normal, the heart rate abnormality index is set to A1. If the target heart rate in the current monitoring period is abnormal, the heart rate abnormality index is set to A2.

3. The tumor patient pain data processing system according to claim 2, characterized in that: The respiratory monitoring unit is used to compare the target respiratory frequency s2 collected during the monitoring period with the preset respiratory frequency a2 to analyze the abnormality of the target respiratory frequency. The abnormality of the target respiratory frequency includes normal respiratory frequency and abnormal respiratory frequency. If the target respiratory frequency of the current monitoring period is normal, the abnormal respiratory index is set to B1. If the target respiratory frequency of the current monitoring period is abnormal, the abnormal respiratory index is set to B2.

4. The tumor patient pain data processing system according to claim 3, characterized in that: The judgment module judges the target physiological state according to the construction results of the target heart rate abnormality index and the breathing abnormality index within the monitoring period. If x1×heart rate abnormality index+x2×breathing abnormality index≤RT, the judgment module judges that the target physiological state of the current monitoring period is normal; if x1×heart rate abnormality index+x2×breathing abnormality index>RT, the judgment module judges that the target physiological state of the current monitoring period is abnormal, x1 is the heart rate weight, x2 is the breathing weight, and RT is the physiological index threshold.

5. The tumor patient pain data processing system according to claim 4, characterized in that: The behavior analysis module is provided with a tone analysis unit, an intensity analysis unit and a behavior analysis unit. The tone analysis unit is used to extract the tone of each speech frame according to the speech signal collected during the management period, and analyze the pitch change rate B of the management period, and compare the pitch change rate B with the preset change rate B0 to analyze the pitch fluctuation state of the speech signal, and the pitch fluctuation state of the speech signal includes normal and abnormal.

6. The tumor patient pain data processing system according to claim 5, characterized in that: The intensity analysis unit is used to calculate the intensity of the voice signal according to the signal amplitude of each voice frame of the collected voice signal, set the voice signal intensity of the i-th voice frame as Ei, and analyze the voice signal intensity E0 according to the analysis result of the signal intensity of each voice frame; The strength analysis unit compares the speech signal strength E0 with a preset strength EY to analyze the abnormality of the speech signal strength, where the abnormality of the speech signal strength includes normal and abnormal.

7. The tumor patient pain data processing system according to claim 6, characterized in that: The behavior analysis unit is used to analyze the target behavior state according to the analysis results of the voice signal pitch fluctuation state and the analysis results of the voice signal strength abnormality in the management period. If (w1×r1+w2×r2) / 2×r0≤u0, the behavior analysis unit determines that the target behavior state of the current management period is normal; If (w1×r1+w2×r2) / 2×r0>u0, the behavior analysis unit determines that the target behavior state of the current management cycle is abnormal, w1 is the fluctuation weight, w2 is the intensity weight, r1 is the number of voice signals with abnormal fluctuation state within the management cycle, r2 is the number of voice signals with abnormal intensity within the management cycle, r0 is the number of target voice signals collected within the management cycle, and u0 is the preset behavior threshold.

8. The tumor patient pain data processing system according to claim 7, characterized in that: The pain assessment module divides the target pain level into mild pain, moderate pain and severe pain according to the analysis results of the target physiological state and the target behavioral state in the management cycle, and outputs the target pain level to the user.

Images