A method, system and storage medium based on digital visualization of pain data

Abstract

The present invention relates to the field of data visualization, and in particular to a method, system and storage medium based on digital visualization of pain data. The method comprises the following steps: obtaining multi-dimensional pain data of target patients and performing potential pain pattern recognition analysis to obtain the patient's potential pain pattern; extracting pain types and mining potential trigger factors based on the patient's potential pain pattern, and simultaneously performing synchronous division of pain types to obtain the pain intensity, pain site and pain occurrence time corresponding to each patient's pain type; generating a pain intensity time series change additional trigger factor curve and a pain site intensity thermal distribution map corresponding to each patient's pain type by drawing, and uploading the pain intensity time series change additional trigger factor curve and the pain site intensity thermal distribution map corresponding to each patient's pain type to a user interactive visualization interface for digital visualization display processing. The present invention can improve the management and analysis efficiency of pain data.

Description

Technical Field

[0001] The present invention relates to the field of data visualization, and in particular to a method, system and storage medium based on digital visualization of pain data. Background Art

[0002] In recent years, the development of digital technology has provided new opportunities for the management and visualization of pain data. Through mobile applications and wearable devices, patients can record pain data in real time and connect to the medical system. By building an integrated data platform, multi-dimensional data such as patients' pain scores, emotional changes and physiological indicators are gathered, and big data analysis technology is used to deeply mine the collected pain data to identify pain patterns and trends. In addition, in terms of visualization, a set of user-friendly interfaces is designed to display complex data to clinicians and patients in an intuitive way through charts, heat maps, etc. This visualization tool can not only help medical staff quickly understand the patient's pain status, but also promote communication with patients and improve patients' participation and satisfaction. However, traditional pain assessment methods often lack systematicity and standardization, and are easily affected by patients' subjective factors, making it difficult for doctors to accurately grasp the cause of patients' pain triggers, and also limiting the visualization of pain types, locations and intensity. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method, system and storage medium based on digital visualization of pain data to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method based on digital visualization of pain data includes the following steps:

[0005] Step S1: Acquire multi-dimensional pain data of a target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time; perform potential pain pattern recognition analysis on the corresponding patient's pain nature based on the patient's pain frequency to obtain the patient's potential pain pattern;

[0006] Step S2: based on the potential pain pattern of the patient, the corresponding pain properties of the patient are subjected to pain type extraction and potential trigger factor mining and analysis, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are subjected to pain type synchronous classification, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type;

[0007] Step S3: based on the pain occurrence time corresponding to each patient's pain type, draw the corresponding pain intensity and the potential pain triggering factor intensity change trigger factor curve to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type; based on the pain intensity corresponding to each patient's pain type, draw the intensity thermal distribution map of the corresponding pain part to generate the intensity thermal distribution map of the pain part corresponding to each patient's pain type;

[0008] Step S4: Upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: Acquire multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time;

[0011] Step S12: performing quantitative and qualitative classification design according to the patient's pain properties to generate a standard classification table for the patient's pain properties;

[0012] Step S13: Based on the frequency of occurrence of the patient's pain, a frequency-nature correlation detection analysis is performed on each pain nature classification standard in the patient's pain nature standard classification table to obtain a correlation and mutual relationship map between the patient's pain frequency and each pain nature;

[0013] Step S14: Based on the correlation graph between the patient's pain occurrence frequency and each pain property, a potential pain pattern recognition analysis is performed on the corresponding patient's pain properties to obtain the patient's potential pain pattern.

[0014] Further, step S13 includes the following steps:

[0015] Step S131: Designing a property standard node for each pain property classification standard in the patient pain property standard classification table to obtain a patient pain property node corresponding to each pain property classification standard;

[0016] Step S132: performing node frequency matching division on the patient pain occurrence frequency based on the patient pain property node corresponding to each pain property classification standard, and obtaining the pain occurrence sub-frequency corresponding to each patient pain property node;

[0017] Step S133: calculating the frequency ratio between the patient pain property nodes corresponding to each pain property classification standard according to the pain occurrence sub-frequency corresponding to each patient pain property node, so as to obtain the pain occurrence frequency ratio between each patient pain property node;

[0018] Step S134: performing frequency-property correlation statistical calculations between the patient pain property nodes corresponding to each pain property classification standard based on the pain frequency ratio between each patient pain property node, and obtaining correlation coefficients between the patient pain frequency and each pain property;

[0019] Step S135: Compare and judge the correlation coefficients between the patient pain occurrence frequency and each pain property according to the preset correlation threshold value. If the corresponding correlation coefficient is greater than or equal to the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an explicit correlation relationship; if the corresponding correlation coefficient is less than the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an implicit correlation relationship; perform correlation detection connection generation on each of the above-mentioned patient pain property nodes that are determined as explicit correlation relationships and implicit correlation relationships, and obtain a correlation relationship map between the patient pain occurrence frequency and each pain property.

[0020] Further, step S2 includes the following steps:

[0021] Step S21: classifying and coding the corresponding pain characteristics of the patient to obtain a coding system for the pain characteristics of the patient;

[0022] Step S22: establishing pain type mapping rules for corresponding patient pain properties based on the patient pain property feature coding system, and obtaining a patient pain type mapping relationship rule document;

[0023] Step S23: performing pain type mapping and comparison processing on the corresponding patient pain properties based on the patient pain type mapping relationship rule document to obtain the patient pain type, wherein the patient pain type includes chronic pain, neuropathic pain, functional pain, inflammatory pain, physiological pain, recurrent pain and acute pain;

[0024] Step S24: performing potential trigger factor mining and analysis on each patient's pain type based on the patient's potential pain pattern to obtain the potential pain trigger factors corresponding to each patient's pain type;

[0025] Step S25: Based on the pain types of each patient, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are synchronously divided into pain types to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type.

[0026] Further, step S24 includes the following steps:

[0027] Step S241: constructing a classification system for the potential pain patterns of patients to obtain a classification system for potential pain patterns corresponding to different patients;

[0028] Step S242: constructing a preliminary identification framework of trigger factors for each patient's pain type based on the potential pain pattern classification system corresponding to different patients, so as to generate a preliminary identification framework of trigger factors corresponding to each patient's pain type;

[0029] Step S243: Obtain the corresponding pain environment changes and pain mood fluctuations of the patient, and perform pain type inducement statistical analysis on the corresponding pain environment changes and pain mood fluctuations based on the preliminary identification framework of trigger factors corresponding to each patient's pain type, to obtain the pain trigger inducement molecules corresponding to each patient's pain type;

[0030] Step S244: Based on the pain triggering molecules corresponding to each patient's pain type, potential triggering factor mining and analysis is performed on the corresponding patient's pain type to obtain the potential pain triggering factors corresponding to each patient's pain type.

[0031] Further, step S3 includes the following steps:

[0032] Step S31: Obtain the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type through the pain occurrence time corresponding to each patient's pain type, and divide the pain occurrence time period according to the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type, so as to obtain the pain occurrence time period corresponding to each patient's pain type;

[0033] Step S32: performing a statistical analysis of the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type based on the pain occurrence time periods, to obtain the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type;

[0034] Step S33: Preliminarily draw an intensity change curve for the amplitude of the time-series change of pain intensity corresponding to each patient's pain type, so as to generate a distribution curve of the time-series change of pain intensity corresponding to each patient's pain type;

[0035] Step S34: Based on the potential pain triggering factors corresponding to the pain types of each patient, the pain intensity time series change distribution curve corresponding to each patient's pain type is subjected to triggering factor accompanying additional annotation processing to generate a pain intensity time series change additional triggering factor curve corresponding to each patient's pain type;

[0036] Step S35: Based on the pain intensity corresponding to each patient's pain type, an intensity thermal distribution map of the corresponding pain site is drawn to generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

[0037] Further, step S34 includes the following steps:

[0038] Step S341: dividing the pain intensity time series change distribution curve corresponding to each patient's pain type into time series points to obtain the pain intensity distribution time series points corresponding to each patient's pain type;

[0039] Step S342: performing point trigger factor accompanying matching analysis on the corresponding potential pain trigger factors based on the pain intensity distribution time series points corresponding to the pain types of each patient, and obtaining the potential pain accompanying trigger factors at the time series points of the pain type distribution of each patient;

[0040] Step S343: perform additional annotation processing on the corresponding pain intensity time series change distribution curve according to the potential accompanying trigger factors of pain at the time series distribution points of each patient's pain type, so as to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type.

[0041] Further, step S35 includes the following steps:

[0042] Step S351: performing pain location matching analysis on the corresponding pain location based on the pain intensity corresponding to each patient's pain type, so as to obtain the specific magnitude of the pain intensity at the pain location corresponding to each patient's pain type;

[0043] Step S352: Performing spatial distribution statistical analysis on the specific magnitude of pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution characteristics of pain intensity at the pain site corresponding to each patient's pain type;

[0044] Step S353: performing a spatial distribution gradient quantification calculation based on the spatial distribution characteristics of the pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution gradient of the pain intensity at the pain site corresponding to each patient's pain type;

[0045] Step S354: based on the spatial distribution gradient of pain intensity at the pain site corresponding to each patient's pain type, draw an intensity thermal distribution map of the corresponding pain site, and generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

[0046] Furthermore, the present invention also provides a system based on digital visualization of pain data, which is used to execute the method based on digital visualization of pain data as described above, and the system based on digital visualization of pain data comprises:

[0047] The patient potential pain pattern analysis module is used to obtain multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency and the patient's pain occurrence time; based on the patient's pain frequency, the corresponding patient's pain nature is subjected to potential pain pattern recognition analysis to obtain the patient's potential pain pattern;

[0048] The patient pain type synchronous classification module is used to extract the pain type and mine the potential trigger factors of the corresponding patient pain properties based on the patient's potential pain mode, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are synchronously classified into pain types, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type;

[0049] The patient pain data curve drawing and analysis module is used to draw the intensity change trigger factor curve for the corresponding pain intensity and potential pain trigger factors based on the pain occurrence time corresponding to each patient pain type, so as to generate the additional trigger factor curve for the time series change of pain intensity corresponding to each patient pain type; draw the intensity thermal distribution map for the corresponding pain part based on the pain intensity corresponding to each patient pain type, so as to generate the intensity thermal distribution map for the pain part corresponding to each patient pain type;

[0050] The pain data digital visualization module is used to upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

[0051] Furthermore, the present invention also provides a computer storage medium having a computer program stored thereon, and when the computer program is executed, the method based on digital visualization of pain data as described above is implemented.

[0052] Beneficial effects of the present invention:

[0053] 1. Compared with the prior art, the method for digital visualization of pain data proposed in the present invention has the beneficial effect of obtaining multi-dimensional pain data of the target patient as the basis for understanding and evaluating pain data. This step not only includes pain intensity, location, nature, frequency and time of occurrence, but also provides a comprehensive perspective for subsequent analysis. By systematically collecting this information, a full picture of the patient's pain can be obtained, thereby identifying the specific characteristics of the pain, and providing basic data guarantee for the subsequent promotion of the pain data visualization process. At the same time, by performing potential pain pattern recognition analysis on the corresponding patient pain properties based on the frequency of patient pain, this analysis can not only identify the pattern of a specific pain type in a specific situation, but also reveal the potential cause or pathological mechanism, allowing the patient to understand the nature of their own pain and possible triggering factors, thereby achieving a higher level of pain data management process. Secondly, by identifying the pain type of the corresponding patient's pain properties, the patient's pain type can be identified more accurately, which can effectively correspond the patient's pain properties to the existing pain classification system, so as to quickly derive the patient's pain type, such as chronic pain, neuropathic pain, etc. By linking the patient's pain properties with standardized pain types, the patient's pain experience can be better understood, and personalized intervention measures can be formulated for their specific types. This process can provide strong support for subsequent data analysis. In addition, by mining and analyzing the potential trigger factors of each patient's pain type based on the patient's potential pain pattern, the relationship between different pain types and potential trigger factors can be analyzed to reveal the root cause and influencing factors of pain attacks. This analysis not only helps doctors better understand the patient's pain mechanism, but also provides a basis for clinical intervention, making it more proactive and effective in the process of managing pain data, so as to accurately grasp the pain trigger causes corresponding to various types of pain in patients. By synchronously dividing the pain types of each patient based on the intensity, location and time of pain, and combining the pain type with these key parameters, a more comprehensive pain portrait can be obtained, helping doctors to make a more accurate pain data visualization process. This synchronous division also helps to identify the common characteristics of certain types of pain, promote a deeper understanding of specific pain patterns, thereby promoting the continuous optimization of pain management strategies and providing a solid data foundation for subsequent pain data visualization processes.Then, by plotting the intensity change trigger factor curve based on the pain occurrence time corresponding to each patient's pain type, the corresponding pain intensity and potential pain trigger factors can be intuitively displayed to show the changing trend of each patient's pain intensity. This visualization method makes it possible to clearly see the fluctuations in pain, so as to better understand the potential trigger factors corresponding to pain, which can reveal the impact of trigger factors on pain. This process can not only help doctors identify factors that cause pain to worsen, but also provide patients with advice on how to avoid triggering pain. By labeling potential trigger factors, patients can better understand the development and changes of their own condition, and then actively participate in self-management. This process can also provide important data support for future research, promote a deeper understanding of pain mechanisms, and help develop more effective pain management strategies. By drawing the intensity thermal distribution map of the corresponding pain area based on the pain intensity corresponding to each patient's pain type, the distribution and intensity changes of pain in different parts can be intuitively displayed. This diagram not only helps to quickly identify the key areas of pain, but also provides a basis for subsequent image visualization. The use of thermal distribution maps helps to improve the accuracy of pain management. Patients can also understand the overall picture of their condition through such visualization tools, help identify the relationship between pain and other concurrent symptoms, and thus better enhance the visualization of the intensity of pain types and locations. Finally, by uploading the additional trigger factor curve of the pain intensity time series change of each patient and the thermal distribution map of the intensity of the pain location to the user interactive visualization interface for display, it can help to more intuitively understand their own pain conditions and their changing trends. Through easy-to-understand graphical displays, patients can better understand their health conditions and communicate effectively with medical staff. This not only improves the efficiency of information transmission, but also provides a good foundation for further clinical research and data accumulation, so as to provide patients with more accurate digital visualization management services for pain.

[0054] 2. The pain data digital visualization system proposed in the present invention is generally composed of a patient potential pain pattern analysis module, a patient pain type synchronous classification module, a patient pain data curve drawing and analysis module, and a pain data digital visualization module. It can implement any pain data digital visualization method described in the present invention, and is used to combine the operations between computer programs running on each module to implement the pain data digital visualization method. The internal structures of the system cooperate with each other, which can greatly reduce repetitive work and manpower investment, and can quickly and effectively provide a more accurate and efficient pain data digital visualization process, thereby simplifying the operation process of the pain data digital visualization system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0056] Figure 1 It is a schematic diagram of the steps of the method for digital visualization of pain data according to the present invention;

[0057] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0058] Figure 3 for Figure 2 Detailed step flow chart of step S13 in FIG. DETAILED DESCRIPTION

[0059] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0060] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0061] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0062] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for digital visualization of pain data, the method comprising the following steps:

[0063] Step S1: Acquire multi-dimensional pain data of a target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time; perform potential pain pattern recognition analysis on the corresponding patient's pain nature based on the patient's pain frequency to obtain the patient's potential pain pattern;

[0064] Step S2: based on the potential pain pattern of the patient, the corresponding pain properties of the patient are subjected to pain type extraction and potential trigger factor mining and analysis, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are subjected to pain type synchronous classification, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type;

[0065] Step S3: based on the pain occurrence time corresponding to each patient's pain type, draw the corresponding pain intensity and the potential pain triggering factor intensity change trigger factor curve to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type; based on the pain intensity corresponding to each patient's pain type, draw the intensity thermal distribution map of the corresponding pain part to generate the intensity thermal distribution map of the pain part corresponding to each patient's pain type;

[0066] Step S4: Upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

[0067] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the method for digitally visualizing pain data according to the present invention. In this example, the method for digitally visualizing pain data includes the following steps:

[0068] Step S1: Acquire multi-dimensional pain data of a target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time; perform potential pain pattern recognition analysis on the corresponding patient's pain nature based on the patient's pain frequency to obtain the patient's potential pain pattern;

[0069] In an embodiment of the present invention, multi-dimensional pain data of target patients are collected by using standardized questionnaires and electronic health record systems. The pain intensity is quantified using a numerical scoring method of 0 to 10. Patients are asked to report the degree of pain based on their own feelings. The location of the pain is shown by asking patients to mark the specific location through a body diagram to ensure the accuracy of the data. The nature of the pain is classified by asking the patient to describe the pain (such as tingling, dull pain, burning pain, etc.). The frequency of pain is recorded by the number of attacks per week, and the time of pain occurrence must be recorded as a specific date and time. All data are summarized through the patient management system to obtain multi-dimensional pain data of the target patient, including the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain time. By analyzing the collected patient pain properties, a standard classification table for patient pain properties is constructed. Quantitative methods, such as frequency analysis and descriptive statistics, are used to quantify the frequency of occurrence of different pain properties. At the same time, qualitative methods are combined with expert group discussions and literature reviews to determine the classification standards for pain properties. After integrating all information, a standardized classification table is formed. The correlation of each pain property standard in the standard classification table is detected and analyzed by combining the patient pain occurrence frequency obtained by previous real-time collection. The relationship between the pain occurrence frequency and various types of pain properties is evaluated through correlation tests (such as Pearson correlation or Spearman rank correlation). The analysis results are visualized to generate a correlation map to show the degree of correlation between different pain properties and their relationship with the occurrence frequency. Then, by combining the correlation map obtained by previous analysis, a machine learning algorithm (such as cluster analysis or decision tree analysis) is used to deeply explore the corresponding patient pain properties to identify potential pain patterns. The pain data of each patient is input into the model, similar pain features are automatically extracted, and pattern classification is performed on them. By comparing the patterns of different patients, common and individual characteristics are identified, and a description of the potential pain pattern is generated, and finally the patient's potential pain pattern is obtained.

[0070] Step S2: based on the potential pain pattern of the patient, the corresponding pain properties of the patient are subjected to pain type extraction and potential trigger factor mining and analysis, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are subjected to pain type synchronous classification, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type;

[0071] In the embodiment of the present invention, when classifying and coding the patient's pain properties, the patient's subjective pain description is first collected, including the intensity, location, and properties of the pain (such as tingling, dull pain, burning pain, etc.), and the pain is quantified using standardized questionnaires and scales (for example, visual analog rating scales, McGill pain questionnaires, etc.). Based on the collected data, the pain properties are classified according to a preset coding system. For example, using a digital coding system, tingling can be coded as "1", dull pain as "2", burning pain as "3", etc., to form a patient pain property characteristic coding system, and a mapping rule for the corresponding patient pain properties is established by combining the patient pain property characteristic coding system generated by previous coding, so as to formulate a pain classification system. The classification standard of the type is established, and the pain type corresponding to each pain property is determined through literature research and clinical expert consultation. For example, tingling and burning pain are mapped to neuropathic pain, and dull pain is mapped to chronic pain. After the mapping relationship is established, a rule document is generated. The corresponding patient pain properties are mapped and compared by combining the previously formulated mapping relationship rule document, so as to identify the corresponding pain type by matching the patient's code with the mapping rule, and generate a report on the patient's pain type. The classification includes chronic pain, neuropathic pain, functional pain, inflammatory pain, physiological pain, recurrent pain and acute pain, etc., to ensure that the pain type of each patient is accurately identified and recorded, so as to obtain the patient's pain type. At the same time, by combining the patient's potential pain pattern obtained by the previous identification analysis, the potential trigger factors of the patient's pain type obtained by the previous mapping comparison are mined and analyzed, so as to construct a data analysis framework, including data collection, organization and analysis modules, and use machine learning algorithms (such as decision trees, support vector machines, etc.) to conduct in-depth analysis of the patient's pain data, identify potential factors affecting the pain type, such as lifestyle habits, psychological state, environmental factors, etc., so as to obtain the potential trigger factors of pain corresponding to each patient's pain type. Then, by combining the pain types of each patient obtained from the previous mapping and comparison, the corresponding patient pain intensity, patient pain location and patient pain occurrence time are synchronously matched and divided into pain types, so as to divide the patient's pain data at different pain type time points, including pain intensity (using a scoring scale), pain location (through physical examination and graphic annotation) and the specific time of pain occurrence (recorded using the electronic medical record system), and finally the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type are obtained.

[0072] Step S3: based on the pain occurrence time corresponding to each patient's pain type, draw the corresponding pain intensity and the potential pain triggering factor intensity change trigger factor curve to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type; based on the pain intensity corresponding to each patient's pain type, draw the intensity thermal distribution map of the corresponding pain part to generate the intensity thermal distribution map of the pain part corresponding to each patient's pain type;

[0073] In an embodiment of the present invention, the corresponding pain start time and end time are obtained from the specific time period length of the pain occurrence time corresponding to each patient's pain type collected previously on the time axis, and the pain occurrence time period is divided on the corresponding time axis according to the corresponding start time point and end time point determined previously, so as to record the pain occurrence time period of each patient with different pain types, and the amplitude statistical calculation of the pain intensity in each time period is performed by combining the pain occurrence time period determined by the previous division, so as to extract the pain intensity data of each patient in the corresponding time period by writing a statistical analysis script, calculate the maximum and minimum pain intensity values ​​in each time period, and then calculate The amplitude is calculated (i.e., the maximum value minus the minimum value), and a bar graph or line graph is generated using a data visualization tool (such as Matplotlib) to intuitively display the intensity changes of each patient's pain type in different time periods. In addition, according to the potential pain triggers corresponding to each patient's pain type obtained in the previous analysis, different time points in the corresponding pain intensity time series change distribution curve are accompanied by additional annotation processing, so as to analyze the trigger factors in the patient's records (such as emotional changes, activity status, environmental factors, etc.), and annotate these trigger factors at different time points of the previously drawn pain intensity time series change distribution curve. Graphics processing tools (such as Adobe Illustrator or the annotation function in the visualization library) are used to add annotations at the corresponding positions of the curve, including the type of trigger factor, the time of occurrence and the degree of influence, so as to annotate and generate the additional trigger factor curve of the pain intensity time series change corresponding to each patient's pain type. Then, based on the pain intensity data corresponding to each patient's pain type, an intensity thermal distribution map of the corresponding pain site is drawn. By collating the intensity data of each patient at a specific pain site, a data set is constructed. A heat map generation tool (such as the Heatmap function in Python or GIS software) is used to map the pain intensity data to a two-dimensional plane. Different intensity levels are represented by color depth. The color corresponding to each pain site represents its pain intensity, ensuring that the high-intensity area is clearly distinguished from the low-intensity area. The generated thermal distribution map will intuitively reflect the intensity distribution of different pain sites of each patient, and finally generate a pain site intensity thermal distribution map corresponding to each patient's pain type.

[0074] Step S4: Upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

[0075] In an embodiment of the present invention, after completing the additional trigger factor curve of the time series change of pain intensity and the thermal distribution diagram of the intensity of the pain site, these graphics are uploaded to the user interactive visualization interface using a Web visualization framework (such as D3.js or Plotly). The interface is designed to be user-friendly and supports zooming, filtering and data export functions. Users can select data of specific patients for viewing according to their own needs, and analyze the changing trends and corresponding trigger factors of different pain types in real time. Through the interactive interface, medical personnel can dynamically adjust the observation time interval and pain type to improve the availability of data and support for clinical decision-making.

[0076] Further, step S1 includes the following steps:

[0077] Step S11: Acquire multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time;

[0078] Step S12: performing quantitative and qualitative classification design according to the patient's pain properties to generate a standard classification table for the patient's pain properties;

[0079] Step S13: Based on the frequency of occurrence of the patient's pain, a frequency-nature correlation detection analysis is performed on each pain nature classification standard in the patient's pain nature standard classification table to obtain a correlation and mutual relationship map between the patient's pain frequency and each pain nature;

[0080] Step S14: Based on the correlation graph between the patient's pain occurrence frequency and each pain property, a potential pain pattern recognition analysis is performed on the corresponding patient's pain properties to obtain the patient's potential pain pattern.

[0081] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0082] Step S11: Acquire multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time;

[0083] In an embodiment of the present invention, multi-dimensional pain data of target patients are collected by using standardized questionnaires and electronic health record systems. The pain intensity is quantified using a numerical scoring method of 0 to 10. Patients are asked to report the degree of pain based on their own feelings. The location of the pain is shown by asking patients to mark the specific location through a body diagram to ensure the accuracy of the data. The nature of the pain is classified by asking patients to describe the pain (such as tingling, dull pain, burning pain, etc.). The frequency of pain is recorded by the number of attacks per week, and the time of pain occurrence must be recorded as a specific date and time. All data are summarized through the patient management system to finally obtain the multi-dimensional pain data of the target patient, including the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain time.

[0084] Step S12: performing quantitative and qualitative classification design according to the patient's pain properties to generate a standard classification table for the patient's pain properties;

[0085] In an embodiment of the present invention, by analyzing the collected patient pain properties, a standard classification table of patient pain properties is constructed, and quantitative methods, such as frequency analysis and descriptive statistics, are used to quantify the frequency of occurrence of different pain properties. At the same time, in combination with qualitative methods, expert group discussion and literature review are used to determine the classification standards of pain properties. After integrating all information, a standardized classification table is formed. The classification table should include the name, definition and corresponding quantitative indicators of the pain property to provide a clear reference, and finally generate a standard classification table of patient pain properties.

[0086] Step S13: Based on the frequency of occurrence of the patient's pain, a frequency-nature correlation detection analysis is performed on each pain nature classification standard in the patient's pain nature standard classification table to obtain a correlation and mutual relationship map between the patient's pain frequency and each pain nature;

[0087] In an embodiment of the present invention, the correlation between each pain property standard in the patient pain property standard classification table is detected and analyzed by combining the patient pain occurrence frequency obtained by previous real-time collection, so as to evaluate the relationship between the pain occurrence frequency and various types of pain properties through correlation tests (such as Pearson correlation or Spearman rank correlation), and the analysis results are visualized to generate a correlation map to show the degree of correlation between different pain properties and their relationship with the occurrence frequency. This map will help to identify the potential patterns of patient pain characteristics, and finally obtain a correlation map between the patient pain occurrence frequency and each pain property.

[0088] Step S14: Based on the correlation graph between the patient's pain occurrence frequency and each pain property, a potential pain pattern recognition analysis is performed on the corresponding patient's pain properties to obtain the patient's potential pain pattern.

[0089] In an embodiment of the present invention, by combining the correlation map between the patient pain frequency and each pain property obtained by previous analysis, a machine learning algorithm (such as cluster analysis or decision tree analysis) is used to deeply explore the corresponding patient pain properties to identify potential pain patterns. The pain data of each patient is input into the model, similar pain features are automatically extracted, and the patterns are classified. By comparing the patterns of different patients, common and individual characteristics are identified, and a description of the potential pain pattern is generated, and finally the patient's potential pain pattern is obtained.

[0090] Further, step S13 includes the following steps:

[0091] Step S131: Designing a property standard node for each pain property classification standard in the patient pain property standard classification table to obtain a patient pain property node corresponding to each pain property classification standard;

[0092] Step S132: performing node frequency matching division on the patient pain occurrence frequency based on the patient pain property node corresponding to each pain property classification standard, and obtaining the pain occurrence sub-frequency corresponding to each patient pain property node;

[0093] Step S133: calculating the frequency ratio between the patient pain property nodes corresponding to each pain property classification standard according to the pain occurrence sub-frequency corresponding to each patient pain property node, so as to obtain the pain occurrence frequency ratio between each patient pain property node;

[0094] Step S134: performing frequency-property correlation statistical calculations between the patient pain property nodes corresponding to each pain property classification standard based on the pain frequency ratio between each patient pain property node, and obtaining correlation coefficients between the patient pain frequency and each pain property;

[0095] Step S135: Compare and judge the correlation coefficients between the patient pain occurrence frequency and each pain property according to the preset correlation threshold value. If the corresponding correlation coefficient is greater than or equal to the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an explicit correlation relationship; if the corresponding correlation coefficient is less than the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an implicit correlation relationship; perform correlation detection connection generation on each of the above-mentioned patient pain property nodes that are determined as explicit correlation relationships and implicit correlation relationships, and obtain a correlation relationship map between the patient pain occurrence frequency and each pain property.

[0096] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S13 in FIG. 1 . In this embodiment, step S13 includes the following steps:

[0097] Step S131: Designing a property standard node for each pain property classification standard in the patient pain property standard classification table to obtain a patient pain property node corresponding to each pain property classification standard;

[0098] In an embodiment of the present invention, each pain property classification standard listed in the patient pain property standard classification table is designed as a corresponding node, and these nodes will represent specific pain properties, such as sharp pain, dull pain, tingling, etc., and each pain property classification standard is converted into a node by using a professional graphic modeling tool, such as a UML tool or a network diagram building software. These nodes should have a unique identifier and description information to ensure that each node can be correctly identified and referenced during data processing and visualization. The node information is stored as structured data using a database management system (such as MySQL or MongoDB), and finally the patient pain property node corresponding to each pain property classification standard is obtained.

[0099] Step S132: performing node frequency matching division on the patient pain occurrence frequency based on the patient pain property node corresponding to each pain property classification standard, and obtaining the pain occurrence sub-frequency corresponding to each patient pain property node;

[0100] In an embodiment of the present invention, the frequency of occurrence of corresponding patient pain is matched and divided by combining the patient pain property node corresponding to each pain property classification standard previously determined, so as to achieve frequency statistics of the pain records of each patient under different pain property nodes, and generate a sub-data set containing the pain occurrence frequency. The data set matches each pain property node with the pain information in the patient record, divides the corresponding pain occurrence sub-frequencies, and finally obtains the pain occurrence sub-frequency corresponding to each patient pain property node.

[0101] Step S133: calculating the frequency ratio between the patient pain property nodes corresponding to each pain property classification standard according to the pain occurrence sub-frequency corresponding to each patient pain property node, so as to obtain the pain occurrence frequency ratio between each patient pain property node;

[0102] In an embodiment of the present invention, a statistical calculation of the frequency ratio is performed between the patient pain property nodes corresponding to each pain property classification standard by combining the pain occurrence sub-frequency corresponding to each patient pain property node obtained by previous matching and division, so as to calculate the occurrence frequency ratio between different pain property nodes. A statistical analysis software (such as R language or SPSS) is used to calculate the ratio of the frequency of each group of pain property nodes. The formula is: frequency ratio = node A frequency / node B frequency. The calculation results are organized into a data table for visualization and further analysis, and finally the pain occurrence frequency ratio between each patient pain property node is obtained.

[0103] Step S134: performing frequency-property correlation statistical calculations between the patient pain property nodes corresponding to each pain property classification standard based on the pain frequency ratio between each patient pain property node, and obtaining correlation coefficients between the patient pain frequency and each pain property;

[0104] In an embodiment of the present invention, a statistical calculation of the correlation between the patient pain property nodes corresponding to each pain property classification standard is performed by combining the pain occurrence frequency ratio between each patient pain property node obtained by previous quantitative calculation, so as to evaluate the correlation degree of each pair of pain property nodes by applying correlation analysis methods, such as Pearson correlation coefficient or Spearman rank correlation, and use a data analysis toolkit (such as SciPy library) to perform calculations, and output the correlation coefficient between each pair of nodes to generate a correlation matrix, which will help visualize the relationship between the patient pain occurrence frequency and each pain property, and finally obtain the correlation coefficient between the patient pain occurrence frequency and each pain property.

[0105] Step S135: Compare and judge the correlation coefficients between the patient pain occurrence frequency and each pain property according to the preset correlation threshold value. If the corresponding correlation coefficient is greater than or equal to the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an explicit correlation relationship; if the corresponding correlation coefficient is less than the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an implicit correlation relationship; perform correlation detection connection generation on each of the above-mentioned patient pain property nodes that are determined as explicit correlation relationships and implicit correlation relationships, and obtain a correlation relationship map between the patient pain occurrence frequency and each pain property.

[0106] In an embodiment of the present invention, the correlation coefficients between the patient's pain frequency and each pain property obtained by the previously quantitative calculation are compared and judged by using a preset correlation threshold, so as to determine the type of association between each pain property node. If the correlation coefficient is greater than or equal to the preset threshold, it is defined as an explicit association relationship; otherwise, it is defined as an implicit association relationship. For this purpose, it is necessary to write a logical judgment code and generate an association relationship map through a visualization tool (such as Tableau or D3.js) to show the connection relationship between the patient's pain frequency and the pain property. This map can be used for subsequent clinical analysis and decision support to improve the effectiveness of pain management, and finally connect to generate a correlation relationship map between the patient's pain frequency and each pain property.

[0107] Further, step S2 includes the following steps:

[0108] Step S21: classifying and coding the corresponding pain characteristics of the patient to obtain a coding system for the pain characteristics of the patient;

[0109] In an embodiment of the present invention, when classifying and coding the nature of the patient's pain, the patient's subjective pain description is first collected, including the intensity, location, and nature of the pain (such as tingling, dull pain, burning pain, etc.), and the pain is quantified using standardized questionnaires and scales (for example, a visual analog rating scale, a McGill pain questionnaire, etc.). Based on the collected data, the pain nature is classified according to a preset coding system. For example, using a digital coding system, tingling can be coded as "1", dull pain as "2", burning pain as "3", etc., to form a patient pain nature characteristic coding system, thereby ensuring the comparability of pain nature between different patients, and finally obtaining a patient pain nature characteristic coding system.

[0110] Step S22: establishing pain type mapping rules for corresponding patient pain properties based on the patient pain property feature coding system, and obtaining a patient pain type mapping relationship rule document;

[0111] In an embodiment of the present invention, a mapping rule for the corresponding patient pain properties is established by combining the patient pain property characteristic coding system generated by previous coding to formulate a pain type classification standard, and the pain type corresponding to each pain property is determined through literature research and clinical expert consultation. For example, tingling and burning pain are mapped to neuropathic pain, and dull pain is mapped to chronic pain, etc. After the mapping relationship is established, a rule document is generated, which includes the relationship between each code and the pain type and its definition. The document will serve as a guide to ensure that in the subsequent identification and analysis of pain types, a patient pain type mapping relationship rule document is finally obtained.

[0112] Step S23: performing pain type mapping and comparison processing on the corresponding patient pain properties based on the patient pain type mapping relationship rule document to obtain the patient pain type, wherein the patient pain type includes chronic pain, neuropathic pain, functional pain, inflammatory pain, physiological pain, recurrent pain and acute pain;

[0113] In an embodiment of the present invention, the corresponding patient pain properties are mapped and compared by combining the patient pain type mapping relationship rule document previously formulated, so as to identify the corresponding pain type by matching the patient's coding with the mapping rule. In specific implementation, a database management system can be used to store the patient's pain coding information and perform associated queries with the rule document to generate a report on the patient's pain type, which is classified into chronic pain, neuropathic pain, functional pain, inflammatory pain, etc., to ensure that each patient's pain type is accurately identified and recorded, and finally the patient's pain type is obtained, including chronic pain, neuropathic pain, functional pain, inflammatory pain, physiological pain, recurrent pain and acute pain.

[0114] Step S24: performing potential trigger factor mining and analysis on each patient's pain type based on the patient's potential pain pattern to obtain the potential pain trigger factors corresponding to each patient's pain type;

[0115] In an embodiment of the present invention, the potential triggering factors of the patient pain type obtained by the previous mapping comparison are mined and analyzed by combining the patient's potential pain pattern obtained by the previous identification analysis, so as to construct a data analysis framework, including data collection, organization and analysis modules, and use machine learning algorithms (such as decision trees, support vector machines, etc.) to conduct in-depth analysis of the patient's pain data, identify potential factors affecting the pain type, such as lifestyle habits, psychological state, environmental factors, etc., and analyze the patient's medical history and triggering factors through data mining tools (such as Pandas and Scikit-learn libraries in Python) to ensure that the correlation between the identified factors and the pain type is verified, clarify the potential triggering factors of each pain type, and finally obtain the potential pain triggering factors corresponding to each patient's pain type.

[0116] Step S25: Based on the pain types of each patient, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are synchronously divided into pain types to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type.

[0117] In an embodiment of the present invention, the corresponding patient pain intensity, patient pain site and patient pain occurrence time of each patient pain type obtained by combining the previous mapping comparison are synchronously matched and divided into pain types, so as to divide the patient's pain data at different pain type time points, including pain intensity (using a scoring scale), pain site (through physical examination and graphic annotation) and the specific time of pain occurrence (recorded using an electronic medical record system), and finally the pain intensity, pain site and pain occurrence time corresponding to each patient pain type are obtained.

[0118] Further, step S24 includes the following steps:

[0119] Step S241: constructing a classification system for the potential pain patterns of patients to obtain a classification system for potential pain patterns corresponding to different patients;

[0120] In an embodiment of the present invention, a classification system is constructed for the potential pain patterns of patients obtained by previous identification and analysis, so as to collect pain descriptions from different patients, including information such as pain location, nature, intensity and duration, and use the K-means algorithm to classify the data. The patient data is input into the analysis platform, and the appropriate number of clusters is determined. According to the data distribution, a classification of different potential pain patterns is formed. The generated classification system includes types such as acute pain, chronic pain and pain related to specific diseases, which provides a clear classification framework for subsequent analysis, and finally a classification system of potential pain patterns corresponding to different patients is obtained.

[0121] Step S242: constructing a preliminary identification framework of trigger factors for each patient's pain type based on the potential pain pattern classification system corresponding to different patients, so as to generate a preliminary identification framework of trigger factors corresponding to each patient's pain type;

[0122] In an embodiment of the present invention, by combining the previously established potential pain pattern classification system, a preliminary identification framework for trigger factors of different pain patterns is constructed. This process includes the collection of data such as patient medical records, living habits, environmental factors (such as climate change, activity level), etc., and the application of decision trees or random forest algorithms for analysis to identify potential trigger factors associated with each pain pattern. In specific implementation, data mining tools (such as RapidMiner or WEKA) are used to perform statistical analysis on the trigger factors to form a preliminary identification framework, so as to further confirm the specific trigger factors of each pain type, and finally construct a preliminary identification framework for trigger factors corresponding to each patient's pain type.

[0123] Step S243: Obtain the corresponding pain environment changes and pain mood fluctuations of the patient, and perform pain type inducement statistical analysis on the corresponding pain environment changes and pain mood fluctuations based on the preliminary identification framework of trigger factors corresponding to each patient's pain type, to obtain the pain trigger inducement molecules corresponding to each patient's pain type;

[0124] In an embodiment of the present invention, by obtaining the patient's pain environment changes and emotional fluctuations, real-time data is collected through the patient's questionnaire or wearable device, and the patient's pain perception under different environmental conditions is recorded. Subsequently, the corresponding pain environment changes and pain emotional fluctuations are integrated and analyzed in combination with the previously established trigger factor preliminary identification framework, and the relationship between different environmental factors and pain emotions is statistically analyzed by applying regression analysis or correlation analysis methods, so as to extract the pain triggering inducement molecules corresponding to each patient's pain type, ensure that the source and influence of each inducement are clearly defined, including physiological factors, psychological factors, environmental factors, and patient emotional and behavioral factors, etc., and finally obtain the pain triggering inducement molecules corresponding to each patient's pain type.

[0125] Step S244: Based on the pain triggering molecules corresponding to each patient's pain type, potential triggering factor mining and analysis is performed on the corresponding patient's pain type to obtain the potential pain triggering factors corresponding to each patient's pain type.

[0126] In an embodiment of the present invention, by combining the pain triggering molecules corresponding to each patient's pain type obtained in the previous analysis, a more in-depth potential triggering factor mining is carried out on the corresponding pain type, so as to screen out key factors from multiple triggers by adopting statistical methods such as principal component analysis (PCA) or factor analysis. The specific operations include constructing a multivariate linear regression model, analyzing the relationship between each trigger and pain intensity to determine the most influential potential triggering factor, and using data visualization tools (such as Tableau or Python's Matplotlib) to display the analysis results to ensure that the potential triggering factors of different patient pain types can be intuitively displayed, and finally the potential pain triggering factors corresponding to each patient pain type are obtained.

[0127] Further, step S3 includes the following steps:

[0128] Step S31: Obtain the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type through the pain occurrence time corresponding to each patient's pain type, and divide the pain occurrence time period according to the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type, so as to obtain the pain occurrence time period corresponding to each patient's pain type;

[0129] In an embodiment of the present invention, the corresponding pain start time and end time are obtained from the specific time period length of the pain occurrence time corresponding to each patient's pain type previously collected on the time axis, thereby obtaining the pain occurrence start time point and pain occurrence end time point corresponding to each patient's pain type. At the same time, the pain occurrence time period is divided on the corresponding time axis according to the pain occurrence start time point and pain occurrence end time point corresponding to each patient's pain type previously determined, so as to record the pain occurrence time period of each patient's different pain types, ensure that each patient's pain experience is accurately recorded, and finally obtain the pain occurrence time period corresponding to each patient's pain type.

[0130] Step S32: performing a statistical analysis of the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type based on the pain occurrence time periods, to obtain the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type;

[0131] In an embodiment of the present invention, by combining the pain occurrence time periods corresponding to the pain types of each patient determined previously, the amplitude of the pain intensity in each time period is statistically calculated, so as to extract the pain intensity data of each patient in the corresponding time period by writing a statistical analysis script, calculate the maximum and minimum pain intensity values ​​in each time period, and then calculate the amplitude (that is, the maximum value minus the minimum value), and use data visualization tools (such as Matplotlib) to generate a bar chart or line chart to intuitively display the intensity changes of each patient's pain type in different time periods. This analysis process can reveal the fluctuations of pain intensity within the time period, and finally obtain the amplitude of the time series changes of pain intensity corresponding to each patient's pain type.

[0132] Step S33: Preliminarily draw an intensity change curve for the amplitude of the time-series change of pain intensity corresponding to each patient's pain type, so as to generate a distribution curve of the time-series change of pain intensity corresponding to each patient's pain type;

[0133] In an embodiment of the present invention, the intensity change curve is initially drawn by combining the pain intensity time-series change amplitude corresponding to each patient's pain type obtained by previous quantitative calculation, so as to use a data visualization tool (such as the ggplot2 library in the R language or the Seaborn library in Python) to plot the amplitude data with time as the horizontal axis and the pain intensity amplitude as the vertical axis. The pain intensity change distribution curve of each patient will connect different time points by connecting lines to form a complete time-series change curve. In this process, it is ensured that the curve of each patient uses a different color or style to facilitate distinction and comparison, and finally the pain intensity time-series change distribution curve corresponding to each patient's pain type is drawn and generated.

[0134] Step S34: Based on the potential pain triggering factors corresponding to the pain types of each patient, the pain intensity time series change distribution curve corresponding to each patient's pain type is subjected to triggering factor accompanying additional annotation processing to generate a pain intensity time series change additional triggering factor curve corresponding to each patient's pain type;

[0135] In an embodiment of the present invention, additional annotation processing is performed on different time points in the corresponding pain intensity time series change distribution curve based on the potential pain triggering factors corresponding to each patient's pain type obtained by previous analysis, so as to annotate these triggering factors at different time points of the pain intensity time series change distribution curve previously drawn and generated by analyzing the triggering factors in the patient's records (such as emotional changes, activity status, environmental factors, etc.), and add annotations to the corresponding positions of the curve using graphic processing tools (such as Adobe Illustrator or the annotation function in the visualization library), including the type of triggering factor, the time of occurrence and the degree of influence. This can visualize the factors affecting pain, so that doctors and researchers can intuitively understand the potential causes behind the pain changes, and finally annotate and generate the additional triggering factor curve of the pain intensity time series change corresponding to each patient's pain type.

[0136] Step S35: Based on the pain intensity corresponding to each patient's pain type, an intensity thermal distribution map of the corresponding pain site is drawn to generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

[0137] In an embodiment of the present invention, an intensity thermal distribution map of the corresponding pain site is drawn based on the pain intensity data corresponding to the pain type of each patient, so as to construct a data set by collating the intensity data of each patient at a specific pain site, and use a heat map generation tool (such as the Heatmap function in Python or GIS software) to map the pain intensity data to a two-dimensional plane, and use color depth to represent different intensity levels. The color corresponding to each pain site represents its pain intensity, ensuring that the difference between high-intensity areas and low-intensity areas is obvious. The generated thermal distribution map will intuitively reflect the intensity distribution of different pain sites of each patient, and finally generate a pain site intensity thermal distribution map corresponding to each patient's pain type.

[0138] Further, step S34 includes the following steps:

[0139] Step S341: dividing the pain intensity time series change distribution curve corresponding to each patient's pain type into time series points to obtain the pain intensity distribution time series points corresponding to each patient's pain type;

[0140] In an embodiment of the present invention, the time series points of the pain intensity time series change distribution curve corresponding to each patient's pain type generated previously are divided, and time series analysis is performed by using data analysis software (such as Pandas and Matplotlib libraries in Python) to divide and extract the pain intensity value of each patient at a specific time point, and identify the key points on the pain intensity curve, including peak values ​​and valley values, thereby achieving the division of the time series points of the pain intensity change, ensuring that the pain intensity change of each patient at a specific time series point is clearly displayed in a visual manner, and finally obtaining the pain intensity distribution time series points corresponding to each patient's pain type.

[0141] Step S342: performing point trigger factor accompanying matching analysis on the corresponding potential pain trigger factors based on the pain intensity distribution time series points corresponding to the pain types of each patient, and obtaining the potential pain accompanying trigger factors at the time series points of the pain type distribution of each patient;

[0142] In an embodiment of the present invention, by combining the pain intensity distribution time series points obtained by previous positioning and division, an association rule mining method is used to perform accompanying matching analysis of the corresponding potential pain triggers, so as to cross-analyze the patient's pain intensity data with data such as his or her daily activities, psychological state, and external environment through data mining tools (such as R language or Weka). Specifically, the records of each trigger factor are matched with the pain intensity time series points, and the support and confidence indicators are used to identify the potential accompanying trigger factors that appear at the moment of pain intensity change. The goal of this process is to determine the accompanying trigger factors of each patient at different pain type distribution time series points, and finally obtain the potential accompanying trigger factors of pain at each patient's pain type distribution time series points.

[0143] Step S343: perform additional annotation processing on the corresponding pain intensity time series change distribution curve according to the potential accompanying trigger factors of pain at the time series distribution points of each patient's pain type, so as to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type.

[0144] In an embodiment of the present invention, the corresponding patient pain type distribution time series points on the pain intensity time series change distribution curve are additionally annotated based on the potential accompanying trigger factors of pain obtained by previous matching, so that the potential trigger factors are annotated at the corresponding time series point positions of the pain intensity curve through a visualization tool (such as Tableau or the Seaborn library in Python). In the specific operation, different colors or symbols are used to represent different trigger factors, and annotation information is added at the time series points to identify the specific type of trigger factors and the degree of influence of the trigger factors. The generated pain intensity time series change additional trigger factor curve provides a more intuitive diagram, which helps clinicians understand the potential cause of the problem corresponding to each pain type, and finally draws and generates the pain intensity time series change additional trigger factor curve corresponding to each patient pain type.

[0145] Further, step S35 includes the following steps:

[0146] Step S351: performing pain location matching analysis on the corresponding pain location based on the pain intensity corresponding to each patient's pain type, so as to obtain the specific magnitude of the pain intensity at the pain location corresponding to each patient's pain type;

[0147] In an embodiment of the present invention, by combining the pain assessment questionnaire and clinical records of the patient previously used in the electronic health record (EHR) system, the pain intensity (usually using a score of 0 to 10) corresponding to the pain type (such as chronic, neuropathic, functional, inflammatory, physiological, recurrent and acute, etc.) is extracted, and the corresponding pain site is matched and identified and analyzed to determine the specific pain intensity of the pain site, and a database is constructed to record the correspondence between each patient's pain type and pain site, and data mining technology is applied to analyze the intensity performance of different pain types in specific sites, forming a detailed pain intensity size for each patient, and finally obtaining the specific size of the pain intensity at the pain site corresponding to each patient's pain type.

[0148] Step S352: Performing spatial distribution statistical analysis on the specific magnitude of pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution characteristics of pain intensity at the pain site corresponding to each patient's pain type;

[0149] In an embodiment of the present invention, a spatial statistical method is used to perform spatial distribution statistical analysis on the specific magnitudes of pain intensity at the pain site corresponding to each patient's pain type determined by previous matching, so as to achieve spatial distribution analysis of pain intensity, and a spatial coordinate system of the pain site is established using a geographic information system (GIS) tool, and the pain intensity data is mapped to the spatial coordinates to form the spatial distribution of each pain site. The missing data is filled in space through interpolation technology (such as Kriging interpolation method) to facilitate observation of the spatial distribution characteristics of different pain types, and to obtain the spatial intensity distribution characteristics of each patient's pain site, and finally to obtain the spatial distribution characteristics of pain intensity at the pain site corresponding to each patient's pain type.

[0150] Step S353: performing a spatial distribution gradient quantification calculation based on the spatial distribution characteristics of the pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution gradient of the pain intensity at the pain site corresponding to each patient's pain type;

[0151] In an embodiment of the present invention, a spatial distribution gradient is quantitatively calculated based on the spatial distribution characteristics of pain intensity at the pain site corresponding to each patient's pain type obtained through previous statistical analysis, and a mathematical modeling method is used to calculate the gradient change of pain intensity based on the spatial distribution characteristics. A numerical analysis tool is used to perform derivative analysis on the spatial distribution diagram to identify the changing trend of pain intensity. By setting a certain threshold, the pain intensity gradients in different areas of the space are classified to form a set of quantitative standards, thereby outputting the corresponding pain intensity spatial distribution gradients, and finally obtaining the pain intensity spatial distribution gradients at the pain site corresponding to each patient's pain type.

[0152] Step S354: based on the spatial distribution gradient of pain intensity at the pain site corresponding to each patient's pain type, draw an intensity thermal distribution map of the corresponding pain site, and generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

[0153] In an embodiment of the present invention, an intensity thermal distribution map of the pain site of the corresponding pain type is drawn by combining the spatial distribution gradient of pain intensity at the pain site corresponding to each patient's pain type obtained by previous quantitative calculation, and using heat map generation software, the previously obtained pain intensity gradient data is input into the software, and according to the gradient value of the pain intensity, a color coding method is used to represent different intensities with different colors to form a heat map. By visualizing the pain site of each patient, the heat map can intuitively display the concentrated and dispersed areas of pain intensity, help clinicians quickly identify high-risk pain areas, ensure that the generated thermal distribution map has high readability and clinical application value, and finally draw and generate a thermal distribution map of the pain site intensity corresponding to each patient's pain type.

[0154] Furthermore, the present invention also provides a system based on digital visualization of pain data, which is used to execute the method based on digital visualization of pain data as described above, and the system based on digital visualization of pain data comprises:

[0155] The patient potential pain pattern analysis module is used to obtain multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency and the patient's pain occurrence time; based on the patient's pain frequency, the corresponding patient's pain nature is subjected to potential pain pattern recognition analysis to obtain the patient's potential pain pattern;

[0156] The patient pain type synchronous classification module is used to extract the pain type and mine the potential trigger factors of the corresponding patient pain properties based on the patient's potential pain mode, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are synchronously classified into pain types, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type;

[0157] The patient pain data curve drawing and analysis module is used to draw the intensity change trigger factor curve for the corresponding pain intensity and potential pain trigger factors based on the pain occurrence time corresponding to each patient pain type, so as to generate the additional trigger factor curve for the time series change of pain intensity corresponding to each patient pain type; draw the intensity thermal distribution map for the corresponding pain part based on the pain intensity corresponding to each patient pain type, so as to generate the intensity thermal distribution map for the pain part corresponding to each patient pain type;

[0158] The pain data digital visualization module is used to upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

[0159] Furthermore, the present invention also provides a computer storage medium having a computer program stored thereon, and when the computer program is executed, the method based on digital visualization of pain data as described above is implemented.

[0160] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0161] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for digital visualization of pain data, characterized in that: The following steps are involved: Step S1: Acquire multi-dimensional pain data of a target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time; Based on the frequency of the patient's pain, a potential pain pattern recognition analysis is performed on the corresponding patient's pain properties to obtain the patient's potential pain pattern; Step S2: based on the potential pain pattern of the patient, the corresponding pain properties of the patient are subjected to pain type extraction and potential trigger factor mining and analysis, so as to obtain the patient pain type and the potential pain trigger factors corresponding to each patient pain type; based on each patient pain type, the patient pain intensity, the patient pain site and the patient pain occurrence time are subjected to pain type synchronous classification, so as to obtain the pain intensity, the pain site and the pain occurrence time corresponding to each patient pain type; wherein, step S2 includes the following steps: Step S21: classifying and coding the corresponding pain characteristics of the patient to obtain a coding system for the pain characteristics of the patient; Step S22: establishing pain type mapping rules for corresponding patient pain properties based on the patient pain property feature coding system, and obtaining a patient pain type mapping relationship rule document; Step S23: performing pain type mapping and comparison processing on the corresponding patient pain properties based on the patient pain type mapping relationship rule document to obtain the patient pain type, wherein the patient pain type includes chronic pain, neuropathic pain, functional pain, inflammatory pain, physiological pain, recurrent pain and acute pain; Step S24: performing potential trigger factor mining and analysis on each patient's pain type based on the patient's potential pain pattern to obtain the potential pain trigger factors corresponding to each patient's pain type; Step S25: synchronously classifying the pain intensity, pain location and pain occurrence time of each patient based on the pain type of each patient, and obtaining the pain intensity, pain location and pain occurrence time corresponding to each patient pain type; Step S3: based on the pain occurrence time corresponding to each patient's pain type, draw the corresponding pain intensity and the potential pain triggering factor intensity change trigger factor curve to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type; based on the pain intensity corresponding to each patient's pain type, draw the intensity thermal distribution map of the corresponding pain part to generate the intensity thermal distribution map of the pain part corresponding to each patient's pain type; Step S4: Upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

2. The method for digital visualization of pain data according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency, and the patient's pain occurrence time; Step S12: performing quantitative and qualitative classification design according to the patient's pain properties to generate a standard classification table for the patient's pain properties; Step S13: Based on the frequency of occurrence of the patient's pain, a frequency-nature correlation detection analysis is performed on each pain nature classification standard in the patient's pain nature standard classification table to obtain a correlation and mutual relationship map between the patient's pain frequency and each pain nature; Step S14: Based on the correlation graph between the patient's pain occurrence frequency and each pain property, a potential pain pattern recognition analysis is performed on the corresponding patient's pain properties to obtain the patient's potential pain pattern.

3. The method for digital visualization of pain data according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: Designing a property standard node for each pain property classification standard in the patient pain property standard classification table to obtain a patient pain property node corresponding to each pain property classification standard; Step S132: performing node frequency matching division on the patient pain occurrence frequency based on the patient pain property node corresponding to each pain property classification standard, and obtaining the pain occurrence sub-frequency corresponding to each patient pain property node; Step S133: calculating the frequency ratio between the patient pain property nodes corresponding to each pain property classification standard according to the pain occurrence sub-frequency corresponding to each patient pain property node, so as to obtain the pain occurrence frequency ratio between each patient pain property node; Step S134: performing frequency-property correlation statistical calculations between the patient pain property nodes corresponding to each pain property classification standard based on the pain frequency ratio between each patient pain property node, and obtaining correlation coefficients between the patient pain frequency and each pain property; Step S135: Compare and judge the correlation coefficients between the patient pain occurrence frequency and each pain property according to the preset correlation threshold value. If the corresponding correlation coefficient is greater than or equal to the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an explicit correlation relationship; if the corresponding correlation coefficient is less than the preset correlation threshold value, the connection relationship between the patient pain occurrence frequency and each pain property at the corresponding patient pain property node is determined as an implicit correlation relationship; perform correlation detection connection generation on each of the above-mentioned patient pain property nodes that are determined as explicit correlation relationships and implicit correlation relationships, and obtain a correlation relationship map between the patient pain occurrence frequency and each pain property.

4. The method for digital visualization of pain data according to claim 1, characterized in that: Step S24 includes the following steps: Step S241: constructing a classification system for the potential pain patterns of patients to obtain a classification system for potential pain patterns corresponding to different patients; Step S242: constructing a preliminary identification framework of trigger factors for each patient's pain type based on the potential pain pattern classification system corresponding to different patients, so as to generate a preliminary identification framework of trigger factors corresponding to each patient's pain type; Step S243: Obtain the corresponding pain environment changes and pain mood fluctuations of the patient, and perform pain type inducement statistical analysis on the corresponding pain environment changes and pain mood fluctuations based on the preliminary identification framework of trigger factors corresponding to each patient's pain type, to obtain the pain trigger inducement molecules corresponding to each patient's pain type; Step S244: Based on the pain triggering molecules corresponding to each patient's pain type, potential triggering factor mining and analysis is performed on the corresponding patient's pain type to obtain the potential pain triggering factors corresponding to each patient's pain type.

5. The method for digital visualization of pain data according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Obtain the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type through the pain occurrence time corresponding to each patient's pain type, and divide the pain occurrence time period according to the pain occurrence start time point and the pain occurrence end time point corresponding to each patient's pain type, so as to obtain the pain occurrence time period corresponding to each patient's pain type; Step S32: performing a statistical analysis of the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type based on the pain occurrence time periods, to obtain the amplitude of the time series variation of the pain intensity corresponding to each patient's pain type; Step S33: Preliminarily draw an intensity change curve for the amplitude of the time-series change of pain intensity corresponding to each patient's pain type, so as to generate a distribution curve of the time-series change of pain intensity corresponding to each patient's pain type; Step S34: Based on the potential pain triggering factors corresponding to the pain types of each patient, the pain intensity time series change distribution curve corresponding to each patient's pain type is subjected to triggering factor accompanying additional annotation processing to generate a pain intensity time series change additional triggering factor curve corresponding to each patient's pain type; Step S35: Based on the pain intensity corresponding to each patient's pain type, an intensity thermal distribution map of the corresponding pain site is drawn to generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

6. The method for digital visualization of pain data according to claim 5, characterized in that: Step S34 includes the following steps: Step S341: dividing the pain intensity time series change distribution curve corresponding to each patient's pain type into time series points to obtain the pain intensity distribution time series points corresponding to each patient's pain type; Step S342: performing point trigger factor accompanying matching analysis on the corresponding potential pain trigger factors based on the pain intensity distribution time series points corresponding to the pain types of each patient, and obtaining the potential pain accompanying trigger factors at the time series points of the pain type distribution of each patient; Step S343: perform additional annotation processing on the corresponding pain intensity time series change distribution curve according to the potential accompanying trigger factors of pain at the time series distribution points of each patient's pain type, so as to generate the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type.

7. The method for digital visualization of pain data according to claim 5, characterized in that: Step S35 includes the following steps: Step S351: performing pain location matching analysis on the corresponding pain location based on the pain intensity corresponding to each patient's pain type, so as to obtain the specific magnitude of the pain intensity at the pain location corresponding to each patient's pain type; Step S352: Performing spatial distribution statistical analysis on the specific magnitude of pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution characteristics of pain intensity at the pain site corresponding to each patient's pain type; Step S353: performing a spatial distribution gradient quantification calculation based on the spatial distribution characteristics of the pain intensity at the pain site corresponding to each patient's pain type, to obtain the spatial distribution gradient of the pain intensity at the pain site corresponding to each patient's pain type; Step S354: based on the spatial distribution gradient of pain intensity at the pain site corresponding to each patient's pain type, draw an intensity thermal distribution map of the corresponding pain site, and generate an intensity thermal distribution map of the pain site corresponding to each patient's pain type.

8. A digital visualization system based on pain data, characterized in that: For executing the method for digital visualization of pain data as claimed in claim 1, the system for digital visualization of pain data comprises: The patient potential pain pattern analysis module is used to obtain multi-dimensional pain data of the target patient, wherein the multi-dimensional pain data of the target patient includes the patient's pain intensity, the patient's pain location, the patient's pain nature, the patient's pain frequency and the patient's pain occurrence time; based on the patient's pain frequency, the corresponding patient's pain nature is subjected to potential pain pattern recognition analysis to obtain the patient's potential pain pattern; The patient pain type synchronous classification module is used to extract the pain type and mine the potential trigger factors of the corresponding patient pain properties based on the patient's potential pain mode, so as to obtain the patient's pain type and the potential pain trigger factors corresponding to each patient's pain type; based on each patient's pain type, the patient's pain intensity, the patient's pain location and the patient's pain occurrence time are synchronously classified into pain types, so as to obtain the pain intensity, pain location and pain occurrence time corresponding to each patient's pain type; The patient pain data curve drawing and analysis module is used to draw the intensity change trigger factor curve for the corresponding pain intensity and potential pain trigger factors based on the pain occurrence time corresponding to each patient pain type, so as to generate the additional trigger factor curve for the time series change of pain intensity corresponding to each patient pain type; draw the intensity thermal distribution map for the corresponding pain part based on the pain intensity corresponding to each patient pain type, so as to generate the intensity thermal distribution map for the pain part corresponding to each patient pain type; The pain data digital visualization module is used to upload the pain intensity time series change additional trigger factor curve corresponding to each patient's pain type and the pain site intensity thermal distribution map to the user interactive visualization interface for digital visualization display processing.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for digital visualization of pain data as described in any one of claims 1 to 7 is implemented.

Images