A dual-mode active triggered pain assessment and assisted management system

Abstract

The application discloses a dual-mode active trigger pain assessment and auxiliary management system, and relates to the technical field of pain assessment, and the technical scheme points of the application include the following steps: a rule base containing a physiological index and a medication control linkage constraint relationship is constructed, and a medication benchmark for different scenes is built according to the rule base; wherein the medication benchmark includes an evaluation control type and a standard physiological component element; a characteristic node resource library is established; wherein the characteristic node resource library includes a control type characteristic; a benchmark physiological characteristic node including a node control category and a node component element is generated based on the matching result of the medication benchmark and the characteristic node resource library; a comprehensive pain medication risk coefficient is obtained by analyzing a measured physiological characteristic node, the benchmark physiological characteristic node and a link correlation track; and an auxiliary medication control strategy is output according to the comprehensive pain medication risk coefficient, and the effect is to drive whole-process control relying on physiological data.

Description

Technical Field

[0001] This invention relates to the field of pain assessment technology, and more specifically, to a dual-mode active triggering pain assessment and auxiliary management system. Background Technology

[0002] Traditional management systems are ill-suited to the refined management needs of both in-hospital care and home-based chronic disease follow-up. Existing technologies have significant limitations in utilizing physiological indicators. Healthcare professionals mostly rely on patients' verbal descriptions of pain to determine medication regimens. Even with the addition of physiological monitoring equipment such as heart rate and electrodermal conductivity, the collected physiological data are mostly scattered and isolated values. There is a lack of standardized linkage and constraint rules between changes in physiological indicators and analgesic dosages. It is impossible to objectively anchor medication management standards based on fluctuations in physiological data. Differences in clinical experience among different healthcare professionals can easily lead to differentiated medication treatments for the same pain symptoms, making it difficult to ensure the uniformity of medication management. Summary of the Invention

[0003] To address the shortcomings of existing technologies, the present invention aims to provide a dual-mode active triggering pain assessment and auxiliary management system.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A dual-mode active-triggered pain assessment and assistance management system includes:

[0006] Construction module: Construct a rule base containing the linkage and constraint relationship between physiological indicators and medication control, and build medication benchmarks for different scenarios based on the rule base; wherein, the medication benchmarks include assessment and control types and standard physiological components;

[0007] Establishment Module: Establish a feature node resource library; wherein, the feature node resource library includes control type features;

[0008] Processing module: Based on the matching results between medication benchmarks and feature node resource library, it generates benchmark physiological feature nodes including node control categories and node components, and constructs link association trajectories between benchmark physiological feature nodes based on linkage constraint relationships;

[0009] Matching module: Obtains measured control types and measured physiological elements, and matches the feature node resource library based on measured control types and measured physiological elements to obtain measured physiological feature nodes including measured control categories;

[0010] Analysis module: Analyzes measured physiological characteristic nodes, baseline physiological characteristic nodes, and link-related trajectories to obtain a comprehensive pain medication risk coefficient;

[0011] Output module: Outputs auxiliary medication management strategies based on the comprehensive pain medication risk coefficient.

[0012] Preferably, the standard physiological components include heart rate and skin electrophysiological signal data.

[0013] Preferably, the comprehensive pain medication risk coefficient is obtained by analyzing the measured physiological characteristic nodes, the baseline physiological characteristic nodes, and the link-related trajectories, specifically including the following steps:

[0014] Abnormal measured feature nodes are obtained by matching the measured physiological feature nodes with the benchmark physiological feature nodes;

[0015] The first-level pain medication risk coefficient is obtained based on the abnormal measured feature nodes;

[0016] Based on the link association trajectory of abnormal measured feature nodes, the baseline physiological feature nodes are obtained, and the second-layer pain medication risk coefficient is obtained based on the baseline physiological feature nodes.

[0017] The comprehensive pain medication risk coefficient is obtained based on the first-level pain medication risk coefficient and the second-level pain medication risk coefficient.

[0018] Preferably, the abnormal measured feature nodes are obtained by matching the measured physiological feature nodes with the baseline physiological feature nodes, specifically including the following steps:

[0019] The measured physiological elements are compared item by item with the node components of the target benchmark feature nodes to obtain the abnormal deviation elements within the measured physiological elements.

[0020] Measured physiological feature nodes that include abnormal deviations are marked as abnormal measured feature nodes.

[0021] Preferably, the first-layer pain medication risk coefficient is obtained based on the abnormal measured feature nodes, specifically including the following steps:

[0022] Determine the anomaly category and the total number of anomaly deviation elements in the abnormal measured feature nodes;

[0023] Set the anomaly weight of elements according to the anomaly classification;

[0024] The node deviation anomaly coefficient is obtained based on the total number of abnormally deviating elements and the corresponding abnormal weights of the elements.

[0025] Configure the basic control weight of the node according to the actual control type corresponding to the abnormal actual measured feature node;

[0026] The first-level pain medication risk coefficient is obtained based on the node basic control weight and the node deviation anomaly coefficient.

[0027] Preferably, the second-layer pain medication risk coefficient is obtained based on the baseline physiological characteristic nodes, specifically including the following steps:

[0028] Match the associated baseline physiological feature nodes based on the node association tags of the abnormal measured feature nodes;

[0029] The first association control coefficient is obtained based on the total association of the associated baseline physiological characteristic nodes;

[0030] Extract the node control category of the associated baseline physiological feature nodes, and configure the category control weight according to the node control category;

[0031] The second association control coefficient is obtained based on the total number of associated node categories and the corresponding category control weights;

[0032] The second-level pain medication risk coefficient is obtained based on the first and second association control coefficients.

[0033] Preferably, the comprehensive pain medication risk coefficient is obtained based on the first-level pain medication risk coefficient and the second-level pain medication risk coefficient, specifically including the following steps:

[0034] Preset the first weighting coefficient and the second weighting coefficient;

[0035] The comprehensive pain medication risk coefficient is obtained by using the first weighting coefficient, the first-level pain medication risk coefficient, the second weighting coefficient, and the second-level pain medication risk coefficient.

[0036] Preferably, the medication benchmarks for different scenarios are built based on the rule base, specifically including the following steps:

[0037] Based on the linkage and constraint relationship between physiological indicators and medication management in the rule base, the pain diagnosis and treatment management needs for each scenario are determined.

[0038] Based on the needs of pain diagnosis and management, appropriate physiological assessment dimensions and medication management dimensions for corresponding scenarios are selected to form a set of benchmark assessment elements;

[0039] Based on the linkage and constraint relationship between physiological indicators and medication control, the physiological elements and medication control elements within the benchmark assessment element set are correlated and matched to establish the control standards between physiological elements and medication control elements.

[0040] Medication benchmarks adapted to different diagnosis and treatment scenarios are formed by integrating control standards.

[0041] Preferably, a baseline physiological feature node, including node control category and node component elements, is generated based on the matching results between the medication baseline and the feature node resource library. This specifically includes the following steps:

[0042] Extract the assessment and control types and standard physiological components of medication use benchmarks;

[0043] Traverse the control type features of the feature node resource library, compare and filter the evaluation control type with the control type features to obtain matching and adaptation results;

[0044] Based on the matching and adaptation results, the feature resource content adapted to the current medication benchmark scenario is determined;

[0045] Define the corresponding data control category based on the content of the characteristic resources;

[0046] Based on the data control category and standard physiological components, a baseline physiological feature node is generated.

[0047] Preferably, constructing the link association trajectory between benchmark physiological feature nodes based on linkage constraint relationships specifically includes the following steps:

[0048] Based on the linkage constraint relationship, identify the associated features between the benchmark physiological feature nodes;

[0049] The order of action and the hierarchy of mutual influence of different benchmark physiological feature nodes are defined based on the linkage constraint relationship, and the correlation and coupling characteristics of each benchmark physiological feature node are clarified based on the order of action and the hierarchy of mutual influence.

[0050] Construct the correlation transmission path between benchmark physiological feature nodes based on correlation features and correlation coupling features;

[0051] Based on the associated transmission path, the characteristics of state linkage change are determined to obtain the link association trajectory.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] This invention relies on a construction module to build a rule base and scenario-specific medication benchmarks. The rule base binds physiological indicators and medication control to a linkage constraint relationship. A feature node resource library built by the module includes features of all categories of control types, providing a unified resource carrier for the standardized generation of benchmark nodes and measured nodes. The processing module generates benchmark physiological feature nodes based on bidirectional matching, and then builds node link correlation trajectories based on linkage constraints. This not only completes the standardized filing of physiological indicators but also quantifies the linkage influence patterns between various physiological parameters, enabling the capture of potential medication risks caused by abnormalities in a single indicator. The matching module captures on-site measured control types and physiological data in real time, automatically matching and generating standardized measured physiological feature nodes, improving data processing efficiency. The analysis module calculates two layers of risk coefficients layer by layer and weights them to obtain a comprehensive risk value. Relying on quantitative values ​​to replace subjective experience judgment, it enables digital measurement of pain medication risks. Finally, the output module automatically outputs appropriate control strategies according to the comprehensive risk coefficient, forming a closed-loop control chain from physiological data collection, data comparison, risk calculation to medication guidance. By relying on physiological data to drive the entire process of control, it optimizes the medication safety of pain diagnosis and treatment throughout the entire cycle. Attached Figure Description

[0054] Fig. 1 This is a schematic diagram of a dual-mode active triggering pain assessment and auxiliary management system provided in an embodiment of the present invention;

[0055] Fig. 2 This is a schematic diagram of a dual-mode active triggering pain assessment and auxiliary management system provided in an embodiment of the present invention. Detailed Implementation

[0056] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0059] Reference Figs. 1-2 As shown.

[0060] The embodiments further illustrate the dual-mode active triggering pain assessment and auxiliary management system proposed in this invention.

[0061] A dual-mode active-triggered pain assessment and assistance management system includes:

[0062] Construction module: Constructs a rule base containing the linkage and constraint relationship between physiological indicators and medication management;

[0063] The process of building medication benchmarks for different scenarios based on a rule base includes the following steps:

[0064] Based on the linkage and constraint relationship between physiological indicators and medication management in the rule base, the pain diagnosis and treatment management needs for each scenario are determined.

[0065] Based on the needs of pain diagnosis and management, appropriate physiological assessment dimensions and medication management dimensions for corresponding scenarios are selected to form a set of benchmark assessment elements;

[0066] Based on the linkage and constraint relationship between physiological indicators and medication control, the physiological elements and medication control elements within the benchmark assessment element set are correlated and matched to establish the control standards between physiological elements and medication control elements.

[0067] Medication benchmarks adapted to different diagnosis and treatment scenarios are integrated based on control standards;

[0068] The medication criteria include the assessment of the control type and standard physiological components;

[0069] Standard physiological components include heart rate and skin electrophysiological signal data.

[0070] The rule base contains all the linkage and constraint relationships between physiological indicators and medication control. These linkage and constraint relationships are derived from the corresponding logic of physiological changes and analgesic drug use guidelines in the clinical pain diagnosis and treatment process. For example, if a patient's heart rate is persistently elevated during the resting phase and the skin conductance signal is abnormally elevated during clinical diagnosis and treatment, the usable dosage of analgesic drugs for a single administration needs to be adjusted accordingly. These clinically validated corresponding logics are entered into the rule base one by one.

[0071] By leveraging the linkage and constraint relationship between physiological indicators and medication management in the rule base, the pain management and control needs corresponding to each type of diagnosis and treatment scenario are clearly defined. In clinical practice, the scenarios of in-hospital postoperative bed rest and home chronic pain follow-up can be divided. The diagnosis and treatment environment, patient physical condition, and medical intervention conditions of the two scenarios are different. Based on the constraint logic of the rule base, differentiated management and control needs are obtained. The management and control needs of the in-hospital postoperative bed rest scenario focus on the control of analgesic drug dosage after the physiological indicators are abnormal due to postoperative wound stress. The management and control needs of the home chronic pain follow-up scenario focus on the control of the frequency of oral analgesics corresponding to physiological fluctuations under daily medical and nursing supervision.

[0072] Physiological assessment dimensions and medication control dimensions suitable for the current scenario are selected. All the selected dimensions are summarized and aggregated to form the benchmark assessment element set for the corresponding scenario. Taking the in-hospital postoperative bed rest scenario as an example, the selected physiological assessment dimensions include the resting heart rate assessment dimension and the resting skin conductance signal assessment dimension. The selected medication control dimensions include the single dose control dimension of intravenous analgesics and the maximum number of doses per day control dimension. The above four dimensions constitute the benchmark assessment element set for this scenario.

[0073] Based on the linkage constraint relationship, the physiological elements and medication control elements of the benchmark assessment element set are correlated and matched. After the element matching is completed, the corresponding control standards between the physiological elements and medication control elements are determined. Calculation formulas can be set for the resting heart rate element and the intravenous single dose element. In abnormal conditions, the single dose = benchmark single dose - the dose reduction corresponding to the heart rate exceeding the standard. Calculation formulas can be set for the skin conductance signal element and the daily dosing frequency element. When the skin conductance is abnormal, the maximum daily dosing frequency = benchmark dosing frequency - 1. After summarizing the corresponding quantitative rules of all physiological and medication elements, a complete control standard is formed.

[0074] All control standards were integrated and summarized, categorized and integrated according to different treatment scenarios, and finally, medication benchmarks adapted to each independent treatment scenario were generated. Medication benchmarks include assessment control types and standard physiological components. The standard physiological components include heart rate physiological signal data and skin conductance physiological signal data. Using the in-hospital postoperative bed rest scenario as an example, the assessment control type for this scenario is postoperative acute pain intravenous administration control. The corresponding standard physiological components are the calibrated baseline heart rate and baseline skin conductance values ​​for this scenario. All comparisons of measured physiological data and the generation of feature nodes must be based on the medication benchmarks as the judgment criteria.

[0075] Establishment Module: Establish a feature node resource library; the feature node resource library includes control type features;

[0076] The assessment and control types are extracted from medication baselines, and various medication control attributes are summarized by combining massive amounts of past clinical pain management data. These attributes are then refined into standardized control type features, which are hierarchically categorized and stored in a feature node resource library based on differences in control attributes. Taking the scenarios of intravenous administration control for acute postoperative pain in hospitals and oral administration control control for chronic home pain as examples, corresponding control type features are extracted for each scenario. One type of control type feature corresponds to the attributes of intravenous administration for acute postoperative pain, while the other corresponds to the attributes of oral administration for chronic home pain. These two types of features are stored independently in different classification partitions of the resource library to avoid data confusion between different control type features.

[0077] Each control type feature comes with detailed attribute parameters, including matching weight values ​​for the corresponding control type. These matching weight values ​​differ between control types. The baseline matching score for a single control feature is calculated as follows: Baseline matching value + Scenario adaptation bonus score. The baseline matching value is determined by the inherent attributes of the control type. The scenario adaptation bonus score is adjusted based on whether the control type falls within or outside the hospital setting. For example, the baseline matching value for the control type feature corresponding to intravenous administration of acute postoperative pain is set to 8, and the scenario adaptation bonus score from falling within the hospital setting is set to 2. Substituting these values ​​into the calculation formula, we get the baseline matching score for this control feature as 8 + 2 = 10. Similarly, the baseline matching value for the control type feature corresponding to oral administration of chronic pain at home is set to 6, and the scenario adaptation bonus score from falling outside the hospital setting is set to 1. Substituting these values ​​into the calculation formula, we get the baseline matching score for this control feature as 6 + 1 = 7. These quantitative matching scores are entered into the resource library along with the control type features to facilitate comparison and screening of control types.

[0078] Processing module: Based on the matching results between medication baselines and the feature node resource library, it generates baseline physiological feature nodes including node control categories and node component elements, specifically including the following steps:

[0079] Extract the assessment and control types and standard physiological components of medication use benchmarks;

[0080] Traverse the control type features of the feature node resource library, compare and filter the evaluation control type with the control type features to obtain matching and adaptation results;

[0081] Based on the matching and adaptation results, the feature resource content adapted to the current medication benchmark scenario is determined;

[0082] Define the corresponding data control category based on the content of the characteristic resources;

[0083] Based on the data control category and standard physiological components, a baseline physiological feature node is generated.

[0084] The assessment and control types and standard physiological components corresponding to the treatment scenario are extracted from the medication baseline. These standard physiological components include heart rate data and skin conductance data. Taking the in-hospital postoperative acute pain treatment scenario as an example, the assessment and control type extracted from the medication baseline for this scenario is postoperative intravenous analgesia administration control, and the extracted standard physiological components include the baseline heart rate value and baseline skin conductance signal value calibrated for this scenario.

[0085] The system iterates through all control type features stored in the feature node resource library, comparing each control type with each control type feature. Based on preset matching rules, it filters out content that matches each other, thus forming the final matching and adaptation result. The control feature matching score = inherent base score + scenario matching bonus. Different control type features are configured with independent inherent base scores. For example, the inherent base score for the control type feature corresponding to postoperative intravenous analgesia is set to 9, and the scenario matching bonus for in-hospital scenarios is set to 1, resulting in a matching score of 9 + 1 = 10. The inherent base score for the control type feature corresponding to home oral analgesia is set to 7, and the scenario matching bonus for out-of-hospital scenarios is set to 1, resulting in a matching score of 7 + 1 = 8. A pre-defined threshold of 9 is set for a qualified matching score. Control type features with a final score greater than or equal to 9 are included in the matching and adaptation result; features below the threshold are directly filtered out.

[0086] The system obtains all feature resources that are compatible with the current medication benchmark scenario from the feature node resource library. Irrelevant resource data is masked and shelved. Postoperative intravenous analgesia-related features that meet the scoring criteria are selected from the matching and adaptation results. Then, all feature resources in the resource library that belong to this control direction are locked.

[0087] Based on the content of the feature resources, a unique data control category is defined. The data control category is used to define the medication control scope corresponding to the baseline node. Different feature resources correspond to a unique control category. The control category corresponding to the feature resources related to postoperative intravenous analgesia is defined as the postoperative intravenous administration control category. This category is bound to the control attribute parameters of the generated node.

[0088] The defined data control categories and standard physiological components are combined to generate complete baseline physiological feature nodes. The generated baseline physiological feature nodes carry node control categories and node components. The node control categories are selected from the defined data control categories, and the node components are taken from the extracted baseline heart rate and baseline skin conductance data. The generated baseline physiological feature nodes serve as standard reference samples, and all anomaly judgments and risk assessments are based on the content of these nodes as the benchmark.

[0089] The process of constructing the link-related trajectories between benchmark physiological feature nodes based on linkage constraints includes the following steps:

[0090] Based on the linkage constraint relationship, identify the associated features between the benchmark physiological feature nodes;

[0091] The order of action and the hierarchy of mutual influence of different benchmark physiological feature nodes are defined based on the linkage constraint relationship, and the correlation and coupling characteristics of each benchmark physiological feature node are clarified based on the order of action and the hierarchy of mutual influence.

[0092] Construct the correlation transmission path between benchmark physiological feature nodes based on correlation features and correlation coupling features;

[0093] Based on the associated transmission path, the characteristics of state linkage change are determined to obtain the link association trajectory;

[0094] Based on the linkage constraint relationship, the corresponding correlation features between all benchmark physiological characteristic nodes are sorted out. The correlation features are used to define the inherent linkage logic between two benchmark physiological characteristic nodes at the level of physiological changes and medication control. According to the clinical linkage constraint rules, it can be clearly seen that when the heart rate value deviates from the benchmark range, it causes regular fluctuations in the skin conductance signal. Abnormal changes in the skin conductance signal form a fine-tuning constraint on the heart rate control threshold. The objective law of bidirectional linkage is sorted into the exclusive correlation features between two types of nodes. The linkage logic between all pairs of nodes is sorted and archived one by one to form a complete correlation feature. The basic score of a single node correlation = basic fixed value + physiological linkage correlation score. The basic fixed value corresponding to the heart rate and skin conductance nodes is set to 5, and the bidirectional physiological linkage correlation score is set to 3. Substituting into the calculation formula, we get the basic score of the node correlation = 5 + 3 = 8. Different paired nodes are configured with differentiated physiological linkage correlation scores according to their own linkage strength. The stronger the linkage effect, the higher the corresponding additional score value.

[0095] The order of action and mutual influence levels of each benchmark physiological characteristic node are defined. Based on the order of action and mutual influence levels, the correlation and coupling characteristics of each benchmark physiological characteristic node are clarified. The order of action is used to distinguish the sequential triggering order of abnormal physiological indicators, the mutual influence level is used to classify the strength of the influence between nodes, and the correlation and coupling characteristics are used to quantify the magnitude of mutual interference between nodes. According to the clinical physiological change pattern, pain stimulation first causes abnormalities in heart rate indicators, which then lead to changes in skin conductance signals. Thus, the heart rate node is determined to be at the first level of action, and the skin conductance node is at the second level of action. Based on the level and sequence of action, the correlation and coupling characteristics of the two are extracted. These coupling characteristics can clarify that for every fixed amplitude of abnormal heart rate change, the benchmark control threshold of skin conductance needs to be lowered accordingly. The coupling weight of a single node = the hierarchical baseline value + the order correction value. The hierarchical baseline value corresponding to the first-level node is 4, the hierarchical baseline value corresponding to the second-level node is 2, the order correction value of heart rate first is 2, and the order correction value of skin conductance second is 1. The overall coupling weight of the two groups of nodes = 4 + 2 + 2 + 1 = 9. Different combinations of nodes at different levels and in different orders of action will generate different coupling weight values.

[0096] The correlation and conduction path between various benchmark physiological characteristic nodes is established. The correlation and conduction path shows the propagation route of physiological abnormality from one node to the other related nodes layer by layer. Based on the correlation and coupling characteristics of heart rate and skin conductance nodes, a forward conduction path from the heart rate benchmark node to the skin conductance benchmark node is established. At the same time, a reverse conduction path is established from the skin conductance benchmark node to fine-tune the heart rate control standard. The two types of paths together form the complete correlation and conduction path.

[0097] The state linkage change features of each node following the physiological data change are extracted by the associated transmission path. Based on all state linkage change features, the link association trajectory of the entire set of benchmark physiological feature nodes is finally generated. The state linkage change features record the parameter change pattern of the other nodes on the entire path after the value of a single node changes. The link association trajectory completely preserves the linkage change context of all nodes.

[0098] Matching module: Obtains measured control types and measured physiological elements, and matches the feature node resource library based on measured control types and measured physiological elements to obtain measured physiological feature nodes including measured control categories;

[0099] The device obtains the measured control type and measured physiological elements corresponding to the diagnosis and treatment scenario from the terminal physiological data acquisition device. The measured physiological elements include the real-time collected heart rate value and skin conductance signal value. Taking a bedridden patient after surgery in the hospital as an example, the device collects the measured control type corresponding to the patient as postoperative acute pain intravenous drug administration control in real time, and simultaneously collects the measured heart rate data of 89 beats per minute and the corresponding amplitude measured skin conductance data. Both types of collected data are stored in a temporary cache space.

[0100] The complete score of the measured data = the complete score of the control type + the complete score of the physiological element. The complete score of the control type is fixed at 5, the complete score of heart rate is 3, and the complete score of skin conductance is 2. The complete score of a single qualified data collection is 5 + 3 + 2 = 10. The system preset passing score is 8.

[0101] Using the measured control type as the primary search keyword, the system traverses all control type features within the resource library, filters out resource entries that match the measured control type attributes, and combines the parameter ranges of two physiological elements—measured heart rate and measured skin conductance—to identify characteristic resource content within the resource library that is suitable for the current measured conditions. The measured control matching score = basic control type score + physiological element adaptation bonus. The basic control type score for postoperative acute pain intravenous administration control is set to 9, the physiological element adaptation bonus for heart rate values ​​falling within the scenario baseline fluctuation range is set to 2, and the physiological element adaptation bonus for skin conductance values ​​falling within the scenario baseline fluctuation range is set to 1. Substituting these values ​​into the calculation formula, the overall measured control matching score for this data is 9 + 2 + 1 = 12. The effective matching score threshold is set to 8, and resource content with a matching score higher than the threshold participates in the generation of measured nodes.

[0102] Analysis module: This module analyzes the measured physiological characteristic nodes, baseline physiological characteristic nodes, and link-related trajectories to obtain a comprehensive pain medication risk coefficient. Specifically, it includes the following steps:

[0103] The abnormal measured feature nodes are obtained by matching the measured physiological feature nodes with the baseline physiological feature nodes. The specific steps include:

[0104] The measured physiological elements are compared item by item with the node components of the target benchmark feature nodes to obtain the abnormal deviation elements within the measured physiological elements.

[0105] Measured physiological feature nodes that include abnormal deviations are marked as abnormal measured feature nodes.

[0106] The measured physiological elements and the constituent elements of the target baseline feature node are compared item by item. The target baseline feature node that matches the current measured control category is pre-locked. The constituent elements of the baseline node include the baseline heart rate value and the baseline skin conductance value of the scene calibration. Then, the measured heart rate and measured skin conductance stored in the measured physiological feature node are extracted. The values ​​are compared item by item according to the element type. Physiological elements whose measured values ​​deviate from the baseline preset fluctuation range are judged as abnormal deviation elements. Taking the scenario of acute postoperative pain in a hospital as an example, the baseline physiological characteristic node in this scenario is set with a baseline heart rate range of 60 to 75 beats per minute and a baseline skin conductance signal amplitude of 20 units. When the terminal collects a measured heart rate of 86 beats per minute and a measured skin conductance amplitude of 19 units, after comparing each item, it can be determined that the measured heart rate exceeds the baseline range. The heart rate data is marked as an abnormal deviation element, while the skin conductance value is within the baseline fluctuation range and is judged as a normal element. The deviation amplitude of a single physiological element = measured element value - baseline element standard value. The heart rate deviation amplitude = 86 - 75 = 11 beats per minute, and the skin conductance deviation amplitude = 19 - 20 = -1 unit. The qualified deviation thresholds for various physiological elements are defined in advance. The qualified deviation upper limit for heart rate is 15 beats per minute, and the qualified deviation range for skin conductance is -5 units to +5 units. After numerical verification, the deviation amplitude of heart rate exceeds the limit standard, while the deviation amplitude of skin conductance falls within the qualified range. Thus, the heart rate is identified as the only abnormal deviation element.

[0107] Based on the abnormal deviation elements, the node marking work is completed. The element composition of all measured physiological feature nodes is retrieved. As long as the measured physiological feature node contains any abnormal deviation element that has been determined, it is uniformly marked as an abnormal measured feature node. If the measured physiological feature node contains the abnormal deviation element of heart rate, the node is classified as an abnormal measured feature node. If the measured elements of heart rate and skin conductance of a certain measured physiological feature node are both within the baseline control range and there are no abnormal deviation elements, then the node retains its original normal node attributes and is not marked as abnormal.

[0108] The first-level pain medication risk coefficient is obtained based on abnormal measured feature nodes, specifically including the following steps:

[0109] Determine the anomaly category and the total number of anomaly deviation elements in the abnormal measured feature nodes;

[0110] Set the anomaly weight of elements according to the anomaly classification;

[0111] The node deviation anomaly coefficient is obtained based on the total number of abnormally deviating elements and the corresponding abnormal weights of the elements.

[0112] Configure the basic control weight of the node according to the actual control type corresponding to the abnormal actual measured feature node;

[0113] The first-level pain medication risk coefficient is obtained based on the node basic control weight and the node deviation anomaly coefficient.

[0114] The abnormality category corresponding to all abnormal deviation elements within a node is identified one by one, and the total number of abnormal deviation elements under that node is counted. Physiological abnormalities are pre-classified into two fixed categories: elevated heart rate belongs to the first category, and deviations in skin conductance values ​​belong to the second category. Taking the abnormal measured feature node corresponding to postoperative pain in hospital as an example, if both elevated heart rate and deviation in skin conductance occur within the node, the total number of abnormal deviation elements is counted to be 2, with one element corresponding to the first category and the other to the second category.

[0115] For each type of abnormality, a corresponding element abnormality weight value is matched. Different abnormality categories are configured with different fixed weights. The higher the severity of the abnormality, the larger the corresponding weight value. The element abnormality weight corresponding to the first type of heart rate abnormality is set to 3, and the element abnormality weight corresponding to the second type of skin conductance abnormality is set to 2. Combining the total number of abnormal deviation elements and the element abnormality weights corresponding to each type of element, the node deviation abnormality coefficient is obtained. The node deviation abnormality coefficient = weight of the first abnormal element + weight of the second abnormal element + weights of the remaining abnormal elements. After substituting the values, we can get the node deviation abnormality coefficient = 3 + 2 = 5. If the node has only a single heart rate abnormality element, the node deviation abnormality coefficient = 3. The more abnormal elements there are or the higher the weight of a single abnormality, the larger the final node deviation abnormality coefficient value will be, which directly reflects the severity of the physiological deviation of the node itself.

[0116] Based on the measured control type bound to the abnormal measured feature nodes, a basic control weight is assigned to each node. Different treatment scenarios correspond to specific basic control weights for different control types. For example, the level of medication supervision for in-hospital postoperative intravenous medication control is higher, therefore the configured basic control weight value for the node is larger. Conversely, the basic control weight value for home-based chronic pain oral medication control is relatively lower. The basic control weight for this control type is set to 4, while for a home-based oral medication control scenario, the basic control weight is set to 2. The strength of the medication constraint for the control type directly determines the specific value of the weight.

[0117] The risk coefficient for pain medication at the first level = the basic control weight of the node + the deviation anomaly coefficient of the node.

[0118] The baseline physiological feature nodes are obtained based on the link association trajectory of the abnormal measured feature nodes;

[0119] The second-layer pain medication risk coefficient is obtained based on the baseline physiological characteristic nodes, specifically including the following steps:

[0120] Match the associated baseline physiological feature nodes based on the node association tags of the abnormal measured feature nodes;

[0121] The first association control coefficient is obtained based on the total association of the associated baseline physiological characteristic nodes;

[0122] Extract the node control category of the associated baseline physiological feature nodes, and configure the category control weight according to the node control category;

[0123] The second association control coefficient is obtained based on the total number of associated node categories and the corresponding category control weights;

[0124] The second-level pain medication risk coefficient is obtained based on the first and second association control coefficients.

[0125] The comprehensive pain medication risk coefficient is obtained based on the first-level and second-level pain medication risk coefficients, specifically including the following steps:

[0126] Preset the first weighting coefficient and the second weighting coefficient;

[0127] The comprehensive pain medication risk coefficient is obtained by using the first weighting coefficient, the first-level pain medication risk coefficient, the second weighting coefficient, and the second-level pain medication risk coefficient.

[0128] Based on the link association trajectory, all reference physiological feature nodes corresponding to the current abnormal measured feature node are located. The link association trajectory records the transmission relationship between the physiological parameters of each reference physiological feature node. It can retrieve all the reference physiological feature nodes involved by following the connecting artery network of the abnormal node. Based on the node association mark of the abnormal measured feature node, all related reference physiological feature nodes are matched and filtered. The node association mark is pre-bound in each node, and the mark content corresponds one-to-one with the link association trajectory built in the early stage. Taking the abnormal measured node of acute postoperative pain in the hospital as an example, based on the node association mark, the heart rate reference node and the skin conductance reference node can be matched, a total of 2 related reference physiological feature nodes.

[0129] The total number of associated baseline physiological characteristic nodes is used to calculate the first association control coefficient, which is set to equal the total number of associated baseline physiological characteristic nodes. For example, if the total number of associated nodes is 2, the first association control coefficient is 2. The more associated nodes there are, the more baseline items can be affected by the physiological abnormality, and the corresponding first association control coefficient value increases accordingly.

[0130] Extract the node control category inherent to each associated baseline physiological feature node, and configure category control weights differently according to the risk level of the control category. Different control categories correspond to different fixed weight values. The control category corresponding to postoperative intravenous administration has a higher risk level, and the configured category control weight is 3. The control category for routine home oral administration is configured with a weight of 2. In the example, both associated nodes belong to the postoperative intravenous administration control category, and the category control weight values ​​corresponding to the two nodes are both equal to 3.

[0131] The total number of associated node categories is counted. The second association control coefficient is calculated by combining the category control weights matched by each category. The second association control coefficient = the category control weight of the first associated node + the category control weight of the second associated node + the category control weights of the remaining associated nodes. Substituting the weight values ​​of the instance, we can get the second association control coefficient = 3 + 3 = 6.

[0132] The second-level pain medication risk coefficient = the first correlation control coefficient + the second correlation control coefficient. Substituting the case values, we get the second-level pain medication risk coefficient = 2 + 6 = 8. This value fully reflects the secondary medication risk caused by abnormal physiological data being transmitted through the link and resulting in changes in related nodes.

[0133] The comprehensive pain medication risk coefficient is calculated by combining the first-level and second-level pain medication risk coefficients. Fixed first and second weighting coefficients are configured in advance. The first weighting coefficient applies to the first-level risk coefficient, and the second weighting coefficient applies to the second-level risk coefficient. The comprehensive pain medication risk coefficient = first-level pain medication risk coefficient × first weighting coefficient + second-level pain medication risk coefficient × second weighting coefficient. If the first-level pain medication risk coefficient is 9, the first weighting coefficient is set to 0.6 and the second weighting coefficient is set to 0.4. The second-level pain medication risk coefficient is 8. The final comprehensive pain medication risk coefficient = 9 × 0.6 + 8 × 0.4 = 5.4 + 3.2 = 8.6.

[0134] Output module: Outputs auxiliary medication management strategies based on the comprehensive pain medication risk coefficient.

[0135] Based on the linkage and constraint relationship between physiology and medication within the rule base, multiple risk level intervals are divided. Each risk level interval corresponds to a set of auxiliary medication management plans, and the critical values ​​for different intervals are determined by clinical diagnosis and treatment data. Reference values ​​are set for risk grading boundaries. Taking the division of three commonly used management intervals as an example, the first interval is a comprehensive pain medication risk coefficient greater than or equal to 1 and less than or equal to 3; the second interval is a comprehensive pain medication risk coefficient greater than 3 and less than or equal to 7; and the third interval is a comprehensive pain medication risk coefficient greater than 7. The three intervals are respectively matched with a low-risk routine maintenance medication strategy, a medium-risk dose reduction and adjustment strategy, and a high-risk strategy of suspending medication and re-examination.

[0136] First, the risk values ​​and classification intervals were compared and matched. The comprehensive analgesia medication risk coefficient was calculated to be 8.6, which falls within the range of the third interval. The corresponding high-risk management strategy for the third interval was then retrieved. The management strategy includes specific medication adjustment rules and follow-up procedures. The management rules for high-risk patients include immediately suspending the current analgesic medication administration, simultaneously reminding medical staff to re-measure the patient's heart rate and skin conductance, recalculating the risk value based on the re-measured physiological data, and then determining the new dosage.

[0137] The adjusted single-dose dosage = baseline single-dose dosage - dosage reduction value corresponding to the risk level. If the baseline single-dose dosage is set at 20 mg, and the dosage reduction value corresponding to the high-risk level is also set at 20 mg, substituting these values ​​into the calculation formula yields the adjusted single-dose dosage = 20 - 20 = 0 mg, thus meeting the control requirement of suspending medication. If the comprehensive pain medication risk coefficient calculation result is equal to 2, this value falls into the first interval, and the corresponding dosage reduction value is 0 mg. Substituting this value into the calculation formula yields the adjusted single-dose dosage = 20 - 0 = 20 mg, and routine medication administration can continue using the original baseline dosage.

[0138] After completing physiological data collection, risk quantification analysis, and outputting medication management strategies, this system ensures that all dosing regimens strictly adhere to the five core clinical dosing principles corresponding to the WHO three-step analgesia guidelines, achieving standardized and regulated full-process control of analgesia dosing. Oral administration is the preferred route of analgesia due to its advantages of being non-invasive, convenient, cost-effective, and maintaining stable blood drug concentrations, significantly improving long-term patient adherence. When the system detects abnormal physiological indicators such as vomiting, swallowing dysfunction, or intestinal obstruction that prevent oral intake, it automatically switches to an appropriate dosing route, matching transdermal patches, rectal suppositories, subcutaneous injections, or intravenous infusions to meet pain intervention needs in scenarios where oral administration is not possible.

[0139] The standardized management logic of timely drug administration abandons the delayed intervention model of on-demand post-pain medication. It sets a fixed dosing cycle according to the corresponding half-life of various analgesics, continuously and stably maintaining the effective blood drug concentration in the patient's body, and preventing sudden pain outbreaks in advance from the root cause. When the patient's physiological indicators match the characteristics of breakthrough pain and the comprehensive medication risk coefficient corresponds to the level of sudden pain, it automatically pushes an immediate-release short-acting analgesic as a rescue dosing plan to relieve sudden severe pain in a timely manner.

[0140] When the system identifies a patient's pain score as mild (1-3), a first-step dosing regimen is used, combining basic medication with corresponding adjunctive analgesics. It is noted that these medications are not addictive but carry risks of gastrointestinal, renal, and cardiovascular damage, limiting overdose and long-term continuous administration. When a patient's NRS score is determined to be moderate (4-6), a second-step dosing strategy is activated, combining a first-step nonsteroidal anti-inflammatory drug (NSAID) with adjunctive medications. It is also noted that the analgesic effect of these medications has an upper limit, and clinicians can directly recommend low-dose strong opioid alternatives based on patient tolerance. When the system identifies a patient's NRS score as severe (7-10), a third-step dosing regimen is activated, combining an NSAID with adjunctive analgesics. It is noted that these medications do not have an analgesic ceiling effect and, when used under standardized management, carry an extremely low risk of addiction, ensuring the professionalism, safety, and consistency of pain management in both in-hospital and home follow-up settings.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dual-mode active-triggered pain assessment and auxiliary management system, characterized in that, include: Construction module: Construct a rule base containing the linkage and constraint relationship between physiological indicators and medication control, and build medication benchmarks for different scenarios based on the rule base; wherein, the medication benchmarks include assessment and control types and standard physiological components; Establishment Module: Establish a feature node resource library; wherein, the feature node resource library includes control type features; Processing module: Based on the matching results between medication benchmarks and feature node resource library, it generates benchmark physiological feature nodes including node control categories and node components, and constructs link association trajectories between benchmark physiological feature nodes based on linkage constraint relationships; Matching module: Obtains measured control types and measured physiological elements, and matches the feature node resource library based on measured control types and measured physiological elements to obtain measured physiological feature nodes including measured control categories; Analysis module: Analyzes measured physiological characteristic nodes, baseline physiological characteristic nodes, and link-related trajectories to obtain a comprehensive pain medication risk coefficient; Output module: Outputs auxiliary medication management strategies based on the comprehensive pain medication risk coefficient.

2. The dual-mode active triggering pain assessment and auxiliary management system according to claim 1, characterized in that, The standard physiological components include heart rate and skin electrophysiological signal data.

3. The dual-mode active triggering pain assessment and auxiliary management system according to claim 1, characterized in that, The comprehensive pain medication risk coefficient is obtained by analyzing the measured physiological characteristic nodes, the baseline physiological characteristic nodes, and the link-related trajectories. The specific steps include: Abnormal measured feature nodes are obtained by matching the measured physiological feature nodes with the benchmark physiological feature nodes; The first-level pain medication risk coefficient is obtained based on the abnormal measured feature nodes; Based on the link association trajectory of abnormal measured feature nodes, the baseline physiological feature nodes are obtained, and the second-layer pain medication risk coefficient is obtained based on the baseline physiological feature nodes. The comprehensive pain medication risk coefficient is obtained based on the first-level pain medication risk coefficient and the second-level pain medication risk coefficient.

4. The dual-mode active triggering pain assessment and auxiliary management system according to claim 3, characterized in that, The abnormal measured feature nodes are obtained by matching the measured physiological feature nodes with the baseline physiological feature nodes. The specific steps include: The measured physiological elements are compared item by item with the node components of the target benchmark feature nodes to obtain the abnormal deviation elements within the measured physiological elements. Measured physiological feature nodes that include abnormal deviations are marked as abnormal measured feature nodes.

5. The dual-mode active triggering pain assessment and auxiliary management system according to claim 3, characterized in that, The first-level pain medication risk coefficient is obtained based on abnormal measured feature nodes, specifically including the following steps: Determine the anomaly category and the total number of anomaly deviation elements in the abnormal measured feature nodes; Set the anomaly weight of elements according to the anomaly classification; The node deviation anomaly coefficient is obtained based on the total number of abnormally deviating elements and the corresponding abnormal weights of the elements. Configure the basic control weight of the node according to the actual control type corresponding to the abnormal actual measured feature node; The first-level pain medication risk coefficient is obtained based on the node basic control weight and the node deviation anomaly coefficient.

6. The dual-mode active triggering pain assessment and auxiliary management system according to claim 3, characterized in that, The second-layer pain medication risk coefficient is obtained based on the baseline physiological characteristic nodes, specifically including the following steps: Match the associated baseline physiological feature nodes based on the node association tags of the abnormal measured feature nodes; The first association control coefficient is obtained based on the total association of the associated baseline physiological characteristic nodes; Extract the node control category of the associated baseline physiological feature nodes, and configure the category control weight according to the node control category; The second association control coefficient is obtained based on the total number of associated node categories and the corresponding category control weights.

7. The dual-mode active triggering pain assessment and auxiliary management system according to claim 3, characterized in that, The comprehensive pain medication risk coefficient is obtained based on the first-level and second-level pain medication risk coefficients, specifically including the following steps: Preset the first weighting coefficient and the second weighting coefficient; The comprehensive pain medication risk coefficient is obtained by using the first weighting coefficient, the first-level pain medication risk coefficient, the second weighting coefficient, and the second-level pain medication risk coefficient.

8. The dual-mode active triggering pain assessment and auxiliary management system according to claim 1, characterized in that, The process of building medication benchmarks for different scenarios based on a rule base includes the following steps: Based on the linkage and constraint relationship between physiological indicators and medication management in the rule base, the pain diagnosis and treatment management needs for each scenario are determined. Based on the needs of pain diagnosis and management, appropriate physiological assessment dimensions and medication management dimensions for corresponding scenarios are selected to form a set of benchmark assessment elements; Based on the linkage and constraint relationship between physiological indicators and medication control, the physiological elements and medication control elements within the benchmark assessment element set are correlated and matched to establish the control standards between physiological elements and medication control elements. Medication benchmarks adapted to different diagnosis and treatment scenarios are formed by integrating control standards.

9. The dual-mode active triggering pain assessment and auxiliary management system according to claim 1, characterized in that, Based on the matching results between medication baselines and the feature node resource library, baseline physiological feature nodes are generated, including node control categories and node component elements. The specific steps include: Extract the assessment and control types and standard physiological components of medication use benchmarks; Traverse the control type features of the feature node resource library, compare and filter the evaluation control type with the control type features to obtain matching and adaptation results; Based on the matching and adaptation results, the feature resource content adapted to the current medication benchmark scenario is determined; Define the corresponding data control category based on the content of the characteristic resources; Based on the data control category and standard physiological components, a baseline physiological feature node is generated.

10. A dual-mode active triggering pain assessment and auxiliary management system according to claim 9, characterized in that, The process of constructing the link-related trajectories between benchmark physiological feature nodes based on linkage constraints includes the following steps: Based on the linkage constraint relationship, identify the associated features between the benchmark physiological feature nodes; The order of action and the hierarchy of mutual influence of different benchmark physiological feature nodes are defined based on the linkage constraint relationship, and the correlation and coupling characteristics of each benchmark physiological feature node are clarified based on the order of action and the hierarchy of mutual influence. Construct the correlation transmission path between benchmark physiological feature nodes based on correlation features and correlation coupling features; Based on the associated transmission path, the characteristics of state linkage change are determined to obtain the link association trajectory.

Images