Tumor intervention postoperative auxiliary nursing system based on real-time health data

Abstract

The invention discloses a tumor intervention postoperative auxiliary nursing system based on real-time health data, and particularly relates to the technical field of medical nursing, and the system comprises the following modules: a data collection module obtains physiological parameters, behavior data and equipment states of a patient in real time; the data processing module cleans, formats and stores the collected data; the efficacy evaluation module evaluates the treatment cooperation efficacy of the patient; the matching evaluation module evaluates the matching degree of the equipment and the physiological state of the patient; the classification model construction module performs classification according to the evaluation result and determines a nursing type; and the nursing intervention module executes a corresponding intervention strategy according to the classification result. The system realizes intelligent and personalized postoperative care; according to the physiological data, the treatment adaptability and the equipment adaptability of the patients, personalized nursing strategies are intelligently matched, and it is ensured that each patient is nursed most suitable for the health condition of the patient after an operation. The personalized nursing scheme is beneficial to accelerating the recovery of the patient and reducing postoperative complications and adverse reactions.

Description

Technical Field

[0001] The present invention relates to the field of medical care technology, and more particularly, to a post-operative auxiliary care system for tumor intervention based on real-time health data. Background Art

[0002] Cancer treatment typically involves multiple approaches, including surgery, radiotherapy, and chemotherapy. Postoperative care is crucial for patient recovery and treatment effectiveness. Postoperative patients often face physical weakness and decreased immunity, and the quality of postoperative care directly impacts their recovery and quality of life.

[0003] Traditional nursing care often relies on the subjective judgment and experience of caregivers, which can be untimely and inaccurate. Furthermore, manual care for complex or specialized patients is sometimes difficult to personalize and accurately. Different patients have different adaptations to treatment equipment, and the equipment may be uncomfortable to wear or incompatible with the patient's physiological characteristics, which can lead to device failure or unsatisfactory treatment results. Therefore, the present invention proposes an auxiliary nursing system for post-operative tumor intervention based on real-time health data to address the above-mentioned issues. Summary of the Invention

[0004] To achieve the above object, the present invention provides the following technical solutions: The auxiliary nursing system for post-operative tumor intervention based on real-time health data includes data acquisition module, data processing module, effectiveness evaluation module, matching evaluation module, classification model construction module, and nursing intervention module; The data acquisition module is used to collect the patient's physiological parameters, behavioral data and equipment usage status data in real time; The data processing module is used to clean, format and store the collected multi-source heterogeneous data; The effectiveness evaluation module is used to evaluate the patient's treatment cooperation effectiveness based on the patient's behavior data and the device usage time, and obtain evaluation result 1; The matching evaluation module is used to evaluate the bio-interaction matching of the device based on the device wearing status data and physiological parameter changes, and obtain the second evaluation result; The classification model construction module is used to construct a classification model based on the evaluation result 1 and the evaluation result 2 in the historical records. The constructed classification model is used to perform classification operations based on the current evaluation result 1 and the evaluation result 2, and output the result of the type of auxiliary care to be performed; The nursing intervention module is used to match the corresponding preset intervention strategy according to the output results of the constructed classification model.

[0005] In a preferred embodiment, the patient's treatment compliance efficacy is evaluated, and the first evaluation result obtained is the treatment compliance efficacy index. The biointeraction matching of the device is evaluated, and the second evaluation result obtained is the biointeraction matching index.

[0006] In a preferred embodiment, the constructed classification model is a fuzzy logic model.

[0007] In a preferred embodiment, the logic for obtaining the treatment compliance efficacy index is: Obtain the total time the patient actually wears the device each day (device usage time T1), the cumulative time when the device is interrupted (device interruption time T2), and the daily target usage time set according to the patient's preset care plan (expected usage time T3). Then calculate the usage rate as follows: ; Indicates the utilization rate; Introducing discontinuity penalty factor: ; Indicates the preset adjustment coefficient, represents the discontinuity penalty factor; Represents a constant set to prevent the denominator from being zero; Introducing behavioral stability enhancement factors: ; Indicates the preset enhancement coefficient, represents the behavioral stability enhancement factor, Indicates behavioral stability value; The calculation formula of treatment cooperation efficacy index is: ; Represents the preset nonlinear control coefficient, It represents the treatment cooperation efficacy index.

[0008] In a preferred embodiment, the logic for obtaining the behavior stability value is: The device usage window is divided into m sub-windows, each sub-window corresponds to a stage of data collection by the device, and the wearing time, wearing status, and shedding frequency of each sub-window are obtained. When the wearing status is 1, it indicates full-time wearing, and a preset value of one corresponding to the sub-window is generated. When the wearing status is 0, it indicates partial wearing, the product value obtained by multiplying the wearing time by the preset weight coefficient one is subtracted from the product value obtained by multiplying the shedding frequency by the preset weight coefficient two to obtain the behavior value corresponding to the sub-window. The sum of the weight coefficient one and the weight coefficient two is one, and the preset value one or the behavior value is used as the statistical value of the sub-window; Arrange all statistical values in chronological order of the subwindow to obtain the actual behavior vector. Then calculate the Euclidean distance between the actual behavior vector and the preset standard vector. Map the Euclidean distance to the numerical range [0,1]. Subtract the Euclidean distance mapping value from the value 1 and the result is used as the behavior stability value.

[0009] In a preferred embodiment, the logic for obtaining the biological interaction matching index is: First calculate the wearing status matching degree: ; Indicates the corresponding data of the i-th wearing matching type, represents the preset influence coefficient of the data corresponding to the i-th wearing matching type, Indicates the total number of matching types worn. Indicates the matching degree of wearing status; Then obtain the ratio of the standard deviation of each physiological parameter measurement value to the preset standard fluctuation threshold, and take the maximum value of the ratio as the physiological parameter disorder coefficient ; Then obtain the signal quality value Q of data transmission during the measurement process of wearing the device and calculate the signal reliability enhancement factor: ; represents the signal reliability enhancement factor; The biological interaction matching index calculation formula is: ; represents the preset trade-off coefficient, represents the biological interaction matching index.

[0010] In a preferred embodiment, the signal quality value is an average signal-to-noise ratio of data transmission during the measurement process of wearing the device.

[0011] In a preferred embodiment, the fuzzy logic logic is: The biological interaction matching index and treatment cooperation effectiveness index corresponding to the day are taken as input variables, and the type of auxiliary care to be performed is taken as the output variable. The input variables are fuzzified and the values of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of each auxiliary care type under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the type of auxiliary care to be performed.

[0012] In a preferred embodiment, when the integrity of the patient's physiological parameter measurement data is lower than a preset data reference threshold, the efficacy evaluation module, the matching evaluation module, the classification model construction module, and the nursing intervention module are all activated and used.

[0013] Technical effects and advantages of the present invention: This system intelligently matches personalized care strategies based on the patient's physiological data, treatment compliance, and device compatibility, ensuring that each patient receives the care best suited to their health status after surgery. This personalized care plan helps accelerate patient recovery and reduce postoperative complications and adverse reactions. By collecting and analyzing real-time health data, the system continuously monitors the patient's physiological condition and device usage, identifying anomalies and making adjustments promptly to maximize treatment effectiveness.

[0014] This invention uses an efficacy evaluation module to assess a patient's treatment compliance index in real time and, based on this data, accurately evaluates their compliance during treatment. This assessment not only identifies low patient compliance but also enables timely intervention based on the results, improving patient compliance and ensuring effective implementation of treatment plans. Through intelligent analysis of patient compliance and device compatibility, it provides clinicians with accurate data support, aiding decision-making and avoiding treatment deviations caused by subjective judgment.

[0015] This invention uses a matching assessment module to evaluate the compatibility between the patient and the treatment device. If the device does not match the patient's physiological characteristics, the system provides timely optimization suggestions to ensure that the patient receives the most appropriate treatment device, thereby improving treatment effectiveness. If anomalies occur during treatment (such as interruptions in device use or decreased treatment compliance), the system intelligently adjusts the nursing strategy to provide more targeted interventions, thereby ensuring the continuity and stability of the treatment plan.

[0016] By automating data collection and analysis, this invention reduces the need for manual patient records and assessments in traditional nursing care, significantly reducing the workload for nursing staff. This allows nursing staff to focus more on areas requiring human intervention, improving nursing efficiency. Through the system's real-time monitoring, patients can clearly understand their health status and treatment progress. This not only improves patient awareness of treatment but also enhances treatment compliance, encouraging active participation in treatment and rehabilitation.

[0017] Through real-time monitoring and personalized care, this system can promptly identify and address potential risks in patients' health conditions, reducing complications caused by untimely or inappropriate treatment, thereby reducing hospital stays and subsequent treatment costs. By intelligently analyzing patients' needs, the system can rationally allocate nursing resources, avoid unnecessary manual intervention, optimize hospital resource allocation, and reduce medical operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings; Figure 1This is a schematic diagram of the auxiliary nursing system for post-operative tumor intervention based on real-time health data in the present invention. DETAILED DESCRIPTION

[0019] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] Example 1: Patients undergoing interventional tumor treatment typically require long-term postoperative monitoring and care. During their recovery, their physical condition and recovery rate can vary significantly from patient to patient, making traditional nursing methods difficult to meet the individual needs of all patients. Traditional nursing methods often rely on manual monitoring and empirical judgment, lacking real-time data support and making it difficult to adjust nursing strategies in a timely manner. Patient compliance with treatment and device compatibility are also difficult to quantify, making it difficult to guarantee effective care.

[0021] With the development of the Internet of Things and artificial intelligence (AI), real-time data collection and intelligent analysis have become crucial tools for improving treatment outcomes and quality of care. Postoperative patients require personalized care through intelligent approaches, timely monitoring of treatment effectiveness, and automated adjustments to care plans to ensure that every step of the recovery process is addressed. By collecting patients' physiological and behavioral data in real time and performing intelligent analysis based on this data, dynamic assessments of their health status can be achieved. Based on these assessments, the need for supplementary care can be automatically determined, and personalized interventions can be provided to patients.

[0022] The present invention proposes an auxiliary nursing system for post-operative tumor intervention based on real-time health data, including a data acquisition module, a data processing module, an effectiveness evaluation module, a matching evaluation module, a classification model construction module, and a nursing intervention module; the data acquisition module, the data processing module, the effectiveness evaluation module, the matching evaluation module, the classification model construction module, and the nursing intervention module are communicatively connected.

[0023] The data acquisition module is used to collect patients' physiological parameters, behavioral data, and device usage data in real time. This module's primary function is to collect these data in real time. This serves as the foundation of the entire system, ensuring the accuracy and timeliness of subsequent analysis. By collecting real-time data, patients' health status and treatment progress can be tracked. This ensures the system has a comprehensive understanding of patients' physiological changes (such as heart rate, body temperature, and blood oxygen saturation), behavioral characteristics (such as device wearing status), and treatment compliance (such as device usage duration).

[0024] The data processing module cleans, formats, and stores collected, heterogeneous data from multiple sources. This module is responsible for cleaning, formatting, and storing collected data. This is crucial for eliminating noise, filling missing values, and unifying data from different sources and formats, thereby providing high-quality data for subsequent analysis modules. Cleaning and formatting data ensures data quality and consistency, improving the accuracy and reliability of analysis. Furthermore, data can be stored as needed to facilitate subsequent querying and analysis.

[0025] The effectiveness assessment module evaluates the effectiveness of treatment compliance based on patient behavioral data and device usage time, generating Assessment Result 1. This module assesses the treatment compliance effectiveness index (Assessment Result 1) based on patient behavioral data and device usage time. This assessment helps understand the patient's level of compliance with the treatment plan and ensures the effectiveness of the treatment process. Patient compliance is assessed by measuring the time the patient actually wears the device, device interruption time, and device stability. If compliance is insufficient, timely identification and intervention are implemented.

[0026] The match assessment module evaluates the device's bio-interaction compatibility based on device wear status data and physiological parameter changes, producing the second evaluation result. This module evaluates the device's bio-interaction compatibility (evaluation result 2) based on device wear status data and physiological parameter changes. This helps ensure that the device matches the patient's health status and avoids poor treatment outcomes due to device incompatibility or improper configuration. The device-patient compatibility is assessed to ensure that the device is functioning properly and effectively supporting the patient's treatment needs. If a mismatch is detected, timely intervention is identified and implemented.

[0027] The classification model construction module constructs a classification model based on historically recorded Assessment Results 1 and 2. This model then performs classification operations based on the current Assessment Results 1 and 2, outputting the type of supplementary care required. By learning from historical data, this module constructs a classification model based on Assessment Results 1 (Therapeutic Compatibility Index) and 2 (Biological Interaction Matching Index). This model can classify patients based on real-time assessment results, determine whether supplementary care is needed, and output the corresponding type of care. Based on both historical and real-time patient data, the classification model can identify patients' health status and make intelligent decisions.

[0028] The Nursing Intervention Module matches and executes pre-set intervention strategies based on the output of the constructed classification model. This module automatically matches and executes pre-set nursing strategies based on the classification model's output. This significantly improves the efficiency and accuracy of nursing care, ensuring that patients' needs are promptly addressed. Based on the classification model's output, the Nursing Intervention Module automatically selects appropriate intervention strategies, such as increasing treatment compliance or adjusting device wear. This module ensures personalized and precise nursing care.

[0029] The treatment compliance effectiveness of patients is assessed, resulting in the Treatment Compliance Effectiveness Index (TCI). The bio-interaction compatibility of the device is assessed, resulting in the Bio-Interaction Compatibility Index (BCI). The TCI reflects the patient's level of compliance with the treatment plan (e.g., device wear duration, intermittent wear time, and consistency of wear behavior). This index allows healthcare professionals to understand patient compliance throughout treatment, promptly identify interruptions or low compliance, and adjust treatment plans to ensure optimal patient outcomes. Treatment outcomes are often closely correlated with patient compliance. If patients do not wear the device as expected or experience extended interruptions, treatment outcomes may be impacted. The TCI provides a quantitative tool to help assess whether patients are experiencing poor treatment compliance, thereby optimizing care strategies and improving treatment outcomes. This index allows healthcare professionals to dynamically monitor patient compliance and provide real-time feedback on compliance and behavioral changes, helping to identify issues early and implement timely interventions to prevent adverse events. Through this clear index assessment, patients can more clearly understand their own treatment compliance and adjust their behavior based on this feedback, thereby increasing their ownership and responsibility for their treatment.

[0030] The Biointeraction Match Index assesses the compatibility between a device and a patient's physiological characteristics. This helps ensure that the therapeutic device being used is functionally compatible with the patient's physiological state. For example, if the device is not worn properly or its operating mode does not align with the patient's physiological changes, treatment effectiveness may be affected. This index can identify potential mismatches between the device and the patient and enable timely adjustments. Ensuring that the device matches the patient's physiological state allows the device to more effectively support the patient's treatment needs. If the device is not well adapted to the patient's physiological characteristics, it may fail or provide suboptimal results. By assessing device compatibility, the Biointeraction Match Index helps improve device efficiency and accuracy. When the device's compatibility with the patient's physiological characteristics is poor, compatibility issues such as discomfort and poor treatment effectiveness may occur. The Biointeraction Match Index can help identify these issues and provide a basis for device adjustment or replacement. The Biointeraction Match Index provides data support for personalized treatment, helping to recommend the most appropriate device or treatment plan for each patient to maximize device effectiveness.

[0031] The Treatment Compliance Index and the Biointeraction Match Index are important tools for evaluating patient treatment outcomes. The former focuses on patient behavior and compliance during treatment, while the latter assesses the compatibility and effectiveness of treatment devices. The combination of these two indices provides healthcare professionals with a comprehensive understanding of a patient's treatment status, improving not only treatment outcomes but also patient comfort and experience, ultimately enabling more efficient and precise personalized treatment and care plans.

[0032] The logic for obtaining the treatment cooperation effectiveness index is: Obtain the total time the patient actually wears the device each day (device usage time T1), the cumulative time when the device is interrupted (device interruption time T2), and the daily target usage time set according to the patient's preset care plan (expected usage time T3). Then calculate the usage rate as follows: ; Indicates the utilization rate; through this ratio, the degree to which patients actually cooperate with treatment is calculated.

[0033] Introducing discontinuity penalty factor: ; Indicates the preset adjustment coefficient, Represents the interruption penalty factor; the interruption penalty factor is calculated by exponential decay, penalizing longer interruptions. Control the intensity of punishment. Represents a constant set to prevent the denominator from being zero. The purpose is to ensure that mathematical calculations make sense, and the constant is usually set to a very small positive number.

[0034] Introducing behavioral stability enhancement factors: ; Indicates the preset enhancement coefficient, represents the behavioral stability enhancement factor, Indicates the behavioral stability value; the higher the behavioral stability, the greater the behavioral stability enhancement factor, which reflects the patient's stability and consistency in treatment.

[0035] The calculation formula of treatment cooperation efficacy index is: ; Represents the preset nonlinear control coefficient, which is used to control the weight of utilization rate and interruption penalty. It represents the treatment cooperation efficacy index. It reflects the usage of the device and the penalty for interruption. The combination of device usage and interruption penalty determines the degree of patient treatment compliance. This index reflects the stability of the patient's behavior, which can enhance treatment effectiveness and reflect the patient's continued engagement in treatment. A higher Treatment Compliance Effectiveness Index indicates greater patient compliance, more stable device use during treatment, lower discontinuation penalties, and more consistent patient behavior. This indicates that the patient adheres to the treatment plan, and the duration and status of device use are more consistent with expectations, thereby improving treatment effectiveness and rehabilitation efficiency.

[0036] The logic for obtaining the behavioral stability value is: The device usage window is divided into m sub-windows, each sub-window corresponds to a stage of data collection by the device, and the wearing time, wearing status, and shedding frequency of each sub-window are obtained. When the wearing status is 1, it indicates full-time wearing, and a preset value of one corresponding to the sub-window is generated. When the wearing status is 0, it indicates partial wearing, the product value obtained by multiplying the wearing time by the preset weight coefficient one is subtracted from the product value obtained by multiplying the shedding frequency by the preset weight coefficient two to obtain the behavior value corresponding to the sub-window. The sum of the weight coefficient one and the weight coefficient two is one, and the preset value one or the behavior value is used as the statistical value of the sub-window; Arrange all statistical values in chronological order of the subwindow to obtain the actual behavior vector. Then calculate the Euclidean distance between the actual behavior vector and the preset standard vector. Map the Euclidean distance to the numerical range [0,1]. Subtract the Euclidean distance mapping value from the value 1 and the result is used as the behavior stability value.

[0037] The device usage window (i.e., the monitoring period during a patient's treatment) is divided into m subwindows, each corresponding to a phase of device data collection. Data from each phase (such as wear duration, wear status, and frequency of removal) is calculated separately and used to assess the patient's behavioral stability during that phase.

[0038] Wearing status (1 or 0): The wearing status is 1, which means it is worn throughout the entire process; 0, which means it is not worn throughout the entire process.

[0039] Preset weight coefficients one and two: weight coefficient one represents the importance of wearing time, and weight coefficient two represents the impact of shedding frequency on behavioral stability.

[0040] Sub-window behavior value: The behavior value corresponding to the sub-window is calculated by subtracting the product of the wearing time and the preset weight coefficient 1 from the product of the shedding frequency and the preset weight coefficient 2, reflecting the patient's treatment cooperation during this stage.

[0041] Generation of statistical values: Arrange the statistical values (behavior values or preset values) of each sub-window in chronological order to obtain the actual behavior vector. This vector reflects the patient's behavior pattern throughout the treatment process.

[0042] Calculate Euclidean distance: This quantifies the deviation between the patient's actual behavior and the expected standard by calculating the Euclidean distance between the actual behavior vector and the preset standard vector. The smaller the Euclidean distance, the more consistent the patient's behavior is with the expected standard and the higher the patient's compliance with treatment.

[0043] Mapping to the numerical interval [0,1]: Map the Euclidean distance to the interval [0,1] and subtract the Euclidean distance from 1 to obtain the final behavioral stability value. The closer this value is to 1, the more stable the patient's behavior during treatment and the higher their compliance with treatment.

[0044] This method converts a patient's behavioral stability during treatment into a quantitative indicator—a behavioral stability value. This value effectively reflects whether the patient wears the device on time, whether the device is worn consistently, and whether there are frequent device removals or irregular behavior. This method allows for a quantitative assessment of whether the patient's behavior meets treatment requirements. The behavioral stability value takes into account not only the duration of wear but also the frequency of device removal and wear status, comprehensively assessing the patient's compliance and stability during treatment. Frequent device removal or incomplete device wear will result in a corresponding decrease in the behavioral stability value, providing real-time feedback on treatment issues. Using the behavioral stability value, healthcare professionals can promptly identify behavioral issues during treatment, such as failure to wear the device regularly or unstable wear. By monitoring this value in real time, personalized interventions can be provided to patients, such as reminders to wear the device and increased nursing support, thereby improving treatment compliance and effectiveness.

[0045] The logic for obtaining the biological interaction matching index is: First calculate the wearing status matching degree: ; The i-th represents the corresponding data of the wearing matching type, such as skin fit strength, etc. represents the preset influence coefficient of the data corresponding to the i-th wearing matching type, Indicates the total number of matching types worn. Indicates the matching degree of wearing status; It represents the attenuation effect of biological matching as the degree of adaptation decreases. The entire formula reflects the degree of interaction matching between the device and the patient through weighted summation, and obtains a comprehensive biological interaction matching index.

[0046] Then obtain the ratio of the standard deviation of each physiological parameter measurement value to the preset standard fluctuation threshold, and take the maximum value of the ratio as the physiological parameter disorder coefficient The standard deviation indicates the fluctuation of a physiological parameter over a specific period of time. Significant fluctuations in physiological parameters (such as heart rate and body temperature) indicate an unstable or abnormal patient's physiological state. By comparing this value with a preset standard fluctuation threshold, the volatility of physiological parameters can be quantitatively assessed. If the fluctuation of a physiological parameter exceeds the preset fluctuation threshold, it may indicate a disturbance in the patient's physiological state, potentially affecting treatment effectiveness. This is often related to factors such as disease progression and treatment inadequacy. Expressing this value using the maximum ratio can quickly identify physiological abnormalities and provide a basis for treatment adjustments.

[0047] Then obtain the signal quality value Q of data transmission during the measurement process of wearing the device and calculate the signal reliability enhancement factor: ; Represents the signal reliability enhancement factor. By taking into account the nonlinear effects of signal quality through logarithmic and square root operations, it can more accurately reflect changes in signal quality. This calculation method helps smooth out the effects of small changes in signal quality, especially when the signal quality does not change much.

[0048] The biological interaction matching index calculation formula is: ; represents the preset trade-off coefficient, The Biointeraction Match Index (BICI) is a comprehensive measure of the aforementioned factors, quantifying the degree of compatibility between the device and the patient's physiology while also accounting for the impact of signal quality. A higher BICI value indicates a greater degree of physiological compatibility between the device and the patient. This means the device closely matches the patient's physiological state and can provide better treatment outcomes. A higher BICI value indicates a more consistent treatment with the patient's physiological needs, potentially supporting the patient's treatment process more effectively and reducing discomfort or adverse reactions. The BICI incorporates signal quality; a higher BICI value indicates more reliable signal quality, potentially less interference during transmission, and more stable interaction between the device and the patient. A higher BICI value indicates a more pronounced therapeutic effect, improved patient compliance and comfort, and accelerated recovery. Highly compatible devices can improve patient treatment adherence and reduce interruptions or discomfort caused by device incompatibility or inappropriateness.

[0049] The signal quality value is the average signal-to-noise ratio (SNR) of data transmitted while the device is worn for measurement. The signal quality value (SNR) reflects the stability of signal transmission between the device and the patient. Higher SNR values indicate clearer signal transmission, less interference, and greater accuracy and stability in data collection. The signal quality value directly impacts data collection accuracy. Poor signal quality and excessive noise can lead to inaccurate data collected by the device, impacting treatment efficacy assessment and decision-making. Higher SNR values indicate more reliable data transmission, helping the medical system make informed decisions and adjustments.

[0050] The constructed classification model is a fuzzy logic controller, and the usage logic of the fuzzy logic controller is: The biological interaction matching index and treatment cooperation effectiveness index corresponding to the day are taken as input variables, and the type of auxiliary care to be performed is taken as the output variable. The input variables are fuzzified and the values of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of each auxiliary care type under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the type of auxiliary care to be performed.

[0051] The basic concept of a fuzzy logic controller is to transform uncertain or ambiguous variables in a real-world problem into fuzzy sets, then perform reasoning based on fuzzy rules to ultimately output a clear conclusion. In this invention, a fuzzy logic controller is used to determine the need for auxiliary care and the specific type of care based on the patient's bio-interaction compatibility and treatment compliance.

[0052] Using logic: Fuzzification of input variables: Biointeraction Match Index: This metric measures the degree of match between the device and the patient's physiological state. If the device and the patient's physiological characteristics match, the Biointeraction Match Index is high; if not, it is low. Because this metric is a continuous value and cannot be used directly in reasoning, it needs to be converted into a fuzzy set. For example, the Biointeraction Match Index value can be converted into three fuzzy sets: "High Match," "Medium Match," and "Low Match."

[0053] Treatment Compliance Index: This metric reflects the patient's treatment compliance. Highly compliant patients have a higher compliance index, while low-compliant patients have a lower index. Similar to the Biological Interaction Match Index, this metric needs to be fuzzified into three fuzzy sets: "high compliance," "medium compliance," and "low compliance."

[0054] Fuzzification of the output variable: Supplementary care type: This is often the desired outcome of fuzzy inference. It represents the type of care a patient dynamically requires, such as "basic care," "moderate care," and "intensive care." These types also require fuzzification so they can be combined with the fuzzy sets of the input variables.

[0055] Formulating fuzzy rules: Fuzzy rules are the core of fuzzy logic, describing the relationship between input variables and output variables. For example, if the biological interaction match index is "high match" and the treatment coordination effectiveness index is "high coordination," then the output type of auxiliary care is "basic care." If the biological interaction match index is "low match" and the treatment coordination effectiveness index is "low coordination," then the required auxiliary care type is "heavy care." If the biological interaction match index is "moderate match" and the treatment coordination effectiveness index is "moderate coordination," then the required auxiliary care type is "moderate care." These rules clarify the relationship between input variables and output variables through a fuzzy inference system. Rules are typically formulated by experts based on experience or historical data.

[0056] Fuzzy Inference: Once the input variables (biological interaction match index and treatment cooperation effectiveness index) are converted into fuzzy sets, the fuzzy logic engine performs inference based on the rule base. The inference process "matches" the input fuzzy set with the rules based on the relationship between the input values and the rules, and then outputs a fuzzy result. For example, if the input is "high match" and "high cooperation," the rules may output the fuzzy set of "basic care." The inference process is to map the fuzzy input information to the appropriate output result through logical inference.

[0057] Defuzzification: Finally, the fuzzy output is converted into a specific value or decision, a process known as "defuzzification." This process transforms the fuzzy output into a specific type of supplemental care. For example, a fuzzy set of "basic care" output from fuzzy inference is converted into a clear "basic care" decision.

[0058] For example, suppose a patient has a biological interaction match index of 0.8 (high) and a treatment compliance index of 0.9 (very high). Converting these values into fuzzy sets: a biological interaction match index of 0.8 can be converted to "high match." A treatment compliance index of 0.9 can be converted to "high compliance."

[0059] According to the preset fuzzy rule: if the biological interaction match is "high match" and the treatment coordination efficacy is "high coordination", then the auxiliary care type is "basic care". Therefore, the output result is "basic care".

[0060] If another patient's biological interaction match index is 0.2 (low) and the treatment coordination effectiveness index is 0.4 (low), then: A biological interaction match index of 0.2 is converted to "low match." A treatment coordination effectiveness index of 0.4 is converted to "low coordination." According to the rule: If the biological interaction match is "low match" and the treatment coordination effectiveness is "low coordination," then the auxiliary care type is "intensive care." The final output is "intensive care."

[0061] The nursing intervention module is used to match the output results of the constructed classification model with the corresponding preset intervention strategy and execute it. For example, if the patient's treatment compliance is low (the treatment compliance efficacy index is low) and the biological interaction matching index is low, the system will use the classification model to determine that the patient needs intensive care. In this case, the nursing intervention module will take the following measures: Increased monitoring frequency: Caregivers may check patients' vital signs, especially blood pressure and blood sugar, every hour to ensure that the patient's health status is always under control.

[0062] Equipment adjustment: Based on the patient's unstable wearing of the device, the nursing staff will provide the patient with a more suitable device and adjust the wearing method to ensure that the patient can continue to wear the device.

[0063] Psychological support: Nursing staff communicate with patients regularly to understand their psychological conditions and provide appropriate psychological counseling to help patients reduce postoperative anxiety.

[0064] When the integrity of the patient's physiological parameter measurement data is lower than the preset data reference threshold, the effectiveness evaluation module, matching evaluation module, classification model construction module, and nursing intervention module are all activated and used.

[0065] When the integrity of a patient's physiological parameter measurement data falls below the preset data reference threshold, the system activates multiple modules (efficacy assessment module, matching assessment module, classification model building module, and nursing intervention module). This mechanism is designed to ensure that even with incomplete data, the system can still assess and judge the patient's health status and make necessary interventions. The specific meanings are as follows: The significance of activating the effectiveness assessment module: Promptly identifying potential treatment compliance issues: When physiological parameter data integrity is low, it may be due to the patient not wearing the device on time, device interruption, or data transmission issues. By activating the effectiveness assessment module, the system can still assess the patient's treatment compliance and promptly identify signs of poor treatment compliance, avoiding missing important intervention opportunities due to missing data. This module can analyze existing data and calculate the Treatment Effectiveness Index (TPEI). Even if some data is missing, the patient's compliance level can be inferred from other relevant data, avoiding the impact of insufficient data on the evaluation of treatment effectiveness.

[0066] Dynamically adjust treatment strategies: Even with incomplete data, the system can output a treatment compliance index based on the currently available data, allowing adjustments to the patient's treatment plan. For example, the system can strengthen patient education and reminders, encourage them to wear the device on time, and increase monitoring of patients with low treatment compliance.

[0067] The significance of activating the Match Assessment Module: Ensuring device compatibility: Even when physiological data is incomplete, the Match Assessment Module assesses the compatibility between the device and the patient based on the available data. A mismatch between the device and the patient's physiological state can affect treatment effectiveness and patient comfort. By activating the Match Assessment Module, the system can promptly identify any device mismatches with the patient's needs and make appropriate adjustments.

[0068] Improve device usage: When the integrity of physiological data is low, this module still evaluates the device's compatibility through existing data (such as wearing status, signal quality, etc.), thereby ensuring that the patient's treatment device is optimally configured and used, reducing discomfort caused by the device or unsatisfactory treatment effects.

[0069] The significance of activating the classification model building module: Intelligent decision support: Even when physiological data is incomplete, the classification model building module can still build a classification model and perform inference by analyzing existing partial data (such as the treatment compliance index and device compatibility). This enables the system to output whether the patient requires auxiliary care and recommend the most appropriate type of care based on the assessment results.

[0070] Reduce judgment bias caused by missing data: This module can effectively use limited data for intelligent reasoning, ensuring that even if data is missing, the classification model can still make inferences and judgments through the input of other variables, reducing misjudgments of patients' health status.

[0071] The significance of activating the nursing intervention module: Timely intervention in patient treatment issues: The nursing intervention module provides patients with personalized nursing plans in a timely manner by analyzing the results output by the classification model. Even if the data is incomplete, the system can still determine whether the patient needs intensive care based on the existing data. For example, if the physiological parameter measurement data is not complete enough, but the treatment compliance is low, the system will automatically adjust the nursing plan and increase the frequency of nursing intervention. Improve the quality of care and response speed: In the case of incomplete data, the system can still provide targeted nursing intervention. For example, increase the inspection of the patient's wearing of the device, strengthen psychological support, adjust the nursing plan, etc. This timely intervention can help patients solve potential health problems and avoid ignoring unstable factors in treatment due to missing data.

[0072] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0073] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0074] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0076] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A post-operative auxiliary nursing system for tumor intervention based on real-time health data, characterized by: It includes data collection module, data processing module, effectiveness evaluation module, matching evaluation module, classification model construction module and nursing intervention module; The data acquisition module is used to collect the patient's physiological parameters, behavioral data and equipment usage status data in real time; The data processing module is used to clean, format and store the collected multi-source heterogeneous data; The effectiveness evaluation module is used to evaluate the patient's treatment cooperation effectiveness based on the patient's behavior data and the device usage time, and obtain evaluation result 1; The matching evaluation module is used to evaluate the bio-interaction matching of the device based on the device wearing status data and physiological parameter changes, and obtain the second evaluation result; The classification model construction module is used to construct a classification model based on the evaluation result 1 and the evaluation result 2 in the historical records. The constructed classification model is used to perform classification operations based on the current evaluation result 1 and the evaluation result 2, and output the result of the type of auxiliary care to be performed; The nursing intervention module is used to match the corresponding preset intervention strategy according to the output results of the constructed classification model.

2. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 1 is characterized in that: The patient's treatment cooperation effectiveness is evaluated, and the evaluation result obtained is the treatment cooperation effectiveness index. The bio-interaction matching of the equipment is evaluated, and the evaluation result obtained is the bio-interaction matching index.

3. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 2 is characterized in that: The constructed classification model is a fuzzy logic device.

4. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 3 is characterized in that: The logic for obtaining the treatment cooperation effectiveness index is: Obtain the total time the patient actually wears the device each day (device usage time T1), the cumulative time when the device is interrupted (device interruption time T2), and the daily target usage time set according to the patient's preset care plan (expected usage time T3). Then calculate the usage rate as follows: ; Indicates the utilization rate; Introducing discontinuity penalty factor: ; Indicates the preset adjustment coefficient, represents the discontinuity penalty factor; Represents a constant set to prevent the denominator from being zero; Introducing behavioral stability enhancement factors: ; Indicates the preset enhancement coefficient, represents the behavioral stability enhancement factor, Indicates behavioral stability value; The calculation formula of treatment cooperation efficacy index is: ; Represents the preset nonlinear control coefficient, It represents the treatment cooperation efficacy index.

5. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 4 is characterized in that: The logic for obtaining the behavioral stability value is: The device usage window is divided into m sub-windows, each sub-window corresponds to a stage of data collection by the device, and the wearing time, wearing status, and shedding frequency of each sub-window are obtained. When the wearing status is 1, it indicates full-time wearing, and a preset value of one corresponding to the sub-window is generated. When the wearing status is 0, it indicates partial wearing, the product value obtained by multiplying the wearing time by the preset weight coefficient one is subtracted from the product value obtained by multiplying the shedding frequency by the preset weight coefficient two to obtain the behavior value corresponding to the sub-window. The sum of the weight coefficient one and the weight coefficient two is one, and the preset value one or the behavior value is used as the statistical value of the sub-window; Arrange all statistical values in chronological order of the subwindow to obtain the actual behavior vector. Then calculate the Euclidean distance between the actual behavior vector and the preset standard vector. Map the Euclidean distance to the numerical range [0,1]. Subtract the Euclidean distance mapping value from the value 1 and the result is used as the behavior stability value.

6. The tumor intervention post-operative auxiliary nursing system based on real-time health data according to claim 5 is characterized in that: The logic for obtaining the biological interaction matching index is: First calculate the wearing status matching degree: ; Indicates the corresponding data of the i-th wearing matching type, represents the preset influence coefficient of the data corresponding to the i-th wearing matching type, Indicates the total number of matching types worn. Indicates the matching degree of wearing status; Then obtain the ratio of the standard deviation of each physiological parameter measurement value to the preset standard fluctuation threshold, and take the maximum value of the ratio as the physiological parameter disorder coefficient ; Then obtain the signal quality value of data transmission during the measurement process of the device wearing , calculate the signal reliability enhancement factor: ; represents the signal reliability enhancement factor; The biological interaction matching index calculation formula is: ; represents the preset trade-off coefficient, represents the biological interaction matching index.

7. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 6 is characterized in that: The signal quality value is the average signal-to-noise ratio of data transmission during the measurement process of wearing the device.

8. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 7 is characterized in that: The usage logic of the fuzzy logic device is: The biological interaction matching index and treatment cooperation effectiveness index corresponding to the day are taken as input variables, and the type of auxiliary care to be performed is taken as the output variable. The input variables are fuzzified and the values of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of each auxiliary care type under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the type of auxiliary care to be performed.

9. The tumor intervention postoperative auxiliary nursing system based on real-time health data according to claim 8 is characterized in that: When the integrity of the patient's physiological parameter measurement data is lower than the preset data reference threshold, the effectiveness evaluation module, matching evaluation module, classification model construction module, and nursing intervention module are all activated and used.

Images