A patient hyperbaric oxygen chamber recovery effect analysis system based on big data

Abstract

The present invention relates to the technical field of hyperbaric oxygen chamber recovery analysis, and in particular to a patient hyperbaric oxygen chamber recovery effect analysis system based on big data. The system includes: a physiological state grouping module, a body metabolic gain analysis module, a muscle elasticity recovery module, and a body function improvement module; used to extract blood oxygen saturation before the course of treatment according to the patient's physiological state data set before the course of treatment, and obtain blood oxygen saturation grouping data before the course of treatment; estimate the body metabolic gain intensity according to the blood oxygen saturation grouping data before the course of treatment, and obtain body metabolic gain intensity data; perform muscle elastic modulus recovery calculation between different muscle groups based on the body metabolic gain intensity data, and then evaluate the body function improvement effect to obtain body function improvement effect data. The present invention makes the technology more perfect by optimizing the hyperbaric oxygen chamber recovery effect analysis technology.

Description

Technical Field

[0001] The present invention relates to the technical field of hyperbaric oxygen chamber recovery analysis, and in particular to a patient hyperbaric oxygen chamber recovery effect analysis system based on big data. Background Art

[0002] In modern medicine, hyperbaric oxygen chambers are an effective treatment method widely used to treat a variety of conditions, including trauma repair, poisoning treatment, and adjunctive therapy for chronic diseases. Hyperbaric oxygen therapy, by increasing blood oxygen levels and promoting tissue repair and regeneration, has been shown to significantly improve patient recovery. With the development of big data technology, the analysis of patients' hyperbaric oxygen recovery outcomes has entered a new phase. Big data technology enables data integration, storage, and management, building a comprehensive patient database and providing rich data support for outcome analysis. Big data analysis can identify underlying patterns and trends in recovery outcomes, uncovering common success and failure factors. However, traditional big data-based systems for analyzing patients' hyperbaric oxygen recovery outcomes suffer from inaccurate analysis of patients' hyperbaric oxygen recovery outcomes and large errors in analyzing muscle recovery outcomes following hyperbaric oxygen intervention. Summary of the Invention

[0003] Based on this, it is necessary to provide a patient hyperbaric oxygen chamber recovery effect analysis system based on big data to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a big data-based hyperbaric oxygen chamber recovery effect analysis system for patients includes the following modules:

[0005] The physiological state grouping module is used to obtain the patient's pre-treatment physiological state data set and the hyperbaric oxygen chamber operation status data; group the patient's pre-treatment physiological state data set into physiological state samples to obtain pre-treatment physiological state grouping data; extract the pre-treatment blood oxygen saturation from the pre-treatment physiological state grouping data to obtain pre-treatment blood oxygen saturation grouping data;

[0006] The body metabolic gain analysis module is used to simulate the oxygen partial pressure increment difference of the blood oxygen saturation group data before the treatment based on the hyperbaric oxygen chamber operation status data to obtain the oxygen partial pressure increment difference simulation data; perform dynamic change analysis of the body oxygen concentration on the oxygen partial pressure increment difference simulation data to obtain the body oxygen concentration dynamic change data; and estimate the body metabolic gain intensity based on the body oxygen concentration dynamic change data to obtain the body metabolic gain intensity data;

[0007] The muscle elasticity recovery module is used to analyze the muscle strength recovery effect based on the body metabolic gain strength data to obtain muscle strength recovery effect data; the muscle elastic modulus recovery calculation between different muscle groups is performed on the muscle strength recovery effect data to obtain muscle elastic modulus recovery data;

[0008] The body function improvement module is used to evaluate the body function improvement effect based on the body metabolic gain intensity data and muscle elastic modulus recovery data based on the multi-layer perceptron to obtain the body function improvement effect data.

[0009] The present invention analyzes the patient's physiological state before treatment. This is achieved by collecting pre-treatment physiological state data and hyperbaric oxygen chamber operating status data. First, this data is grouped, meaning the patient's physiological state data is categorized and organized according to specific criteria. This grouping helps understand changes and trends in physiological state before treatment for different patients. Furthermore, the physiological state grouping module extracts pre-treatment blood oxygen saturation data from this grouped data. Blood oxygen saturation is an important indicator for assessing a patient's physical health, helping the system accurately acquire and analyze this data. The hyperbaric oxygen chamber operating status data is used to analyze pre-treatment changes in blood oxygen saturation. Specifically, it simulates differences in oxygen partial pressure increments—the increase in oxygen in the blood under different oxygen partial pressure conditions. This simulation helps understand the impact of hyperbaric oxygen treatment on blood oxygen saturation. Next, the metabolic gain analysis module conducts a detailed analysis of this simulated oxygen partial pressure increment data to understand the dynamic changes in oxygen concentration within the body. This dynamic change data is crucial for evaluating treatment efficacy and potential metabolic gain effects. Muscle strength recovery is assessed by analyzing metabolic gain strength data. First, it utilizes the metabolic gain strength data obtained in the previous stage, which reflects the changes in oxygen concentration in muscle tissue during treatment. By analyzing this data, the system is able to evaluate the effectiveness of muscle strength recovery. Furthermore, the muscle elasticity recovery module uses the muscle strength recovery effect data to calculate the recovery of muscle elastic modulus among different muscle groups. Muscle elastic modulus refers to the ability of muscle tissue to respond to external pressure or stretching. Its recovery reflects the health and elasticity of muscle tissue. In the body function improvement module, multilayer perceptron technology is used, which focuses on the comprehensive evaluation of body metabolic gain strength data and muscle elastic modulus recovery data. Through this comprehensive analysis, the module is able to evaluate the overall improvement effect of body function. Multilayer perceptron is an artificial neural network suitable for processing complex data patterns and relationships, which enables it to extract and understand important patterns from multiple data sources and then evaluate the improvement of body function.

[0010] Preferably, the physiological status grouping module includes the following functions:

[0011] Obtain the patient's pre-treatment physiological status data set and hyperbaric oxygen chamber operating status data;

[0012] Preprocessing the patient's physiological state data set before treatment to obtain preprocessed physiological state data before treatment;

[0013] Grouping physiological state samples of the patient's pre-treatment physiological state data set according to the pre-treatment physiological state preprocessing data to obtain pre-treatment physiological state grouping data;

[0014] The pre-treatment blood oxygen saturation is extracted from the pre-treatment physiological status grouping data to obtain the pre-treatment blood oxygen saturation grouping data.

[0015] This module of the present invention first collects the patient's physiological state data before receiving treatment. These data may include blood pressure, heart rate, body temperature, blood oxygen saturation and other physiological parameters. At the same time, it also obtains the status data of the hyperbaric oxygen chamber during operation. These data help to understand the impact of the treatment environment on the patient's physiological state. After obtaining the data, the module will pre-process the physiological state data before the treatment. This step includes data cleaning, denoising and standardization to ensure the quality and consistency of the data. The pre-treatment physiological state pre-processed data obtained after pre-processing is easier to analyze and process subsequently, which improves the availability and accuracy of the data. Next, the module groups the patient's physiological state samples according to the pre-treatment physiological state pre-processed data. This means that according to the physiological data characteristics shared by certain patients, the patient's data is divided into different groups or categories. Grouping helps to identify and understand data patterns and trends under different physiological states, provides a basis for subsequent analysis, and extracts blood oxygen saturation data from the pre-treatment physiological state grouped data. Blood oxygen saturation is a key physiological indicator that reflects the content and delivery of oxygen in the blood. The purpose of this step is to obtain accurate blood oxygen saturation data for each physiological status group to further analyze and compare blood oxygen levels in different physiological states.

[0016] Preferably, the body metabolic gain analysis module includes the following functions:

[0017] Performing oxygen concentration phase-increasing pattern recognition on the hyperbaric oxygen chamber operating status data to obtain oxygen concentration increasing pattern data;

[0018] The blood oxygen saturation differences between different groups were quantified based on the blood oxygen saturation grouping data before treatment to obtain the blood oxygen saturation grouping difference quantitative data;

[0019] Perform oxygen partial pressure increment difference simulation on the blood oxygen saturation group difference quantitative data according to the oxygen concentration increment mode data to obtain oxygen partial pressure increment difference simulation data;

[0020] The dynamic change of body oxygen concentration is analyzed on the simulated data of oxygen partial pressure increment difference to obtain the dynamic change data of body oxygen concentration;

[0021] The body's metabolic gain intensity is estimated based on the dynamic change data of the body's oxygen concentration to obtain the body's metabolic gain intensity data.

[0022] By identifying the phased pattern of oxygen concentration increase within a hyperbaric oxygen chamber, the present invention can understand how oxygen concentration changes over time. This helps optimize the chamber's operating strategy, ensuring the appropriate oxygen concentration is provided to support the desired physiological effects. Based on pre-treatment blood oxygen saturation group data, differences in blood oxygen saturation between groups can be quantified. This quantitative data provides a deeper understanding of changes in blood oxygen saturation under different physiological states, helping to assess the effectiveness of hyperbaric oxygen therapy and individual differences in response. Based on the oxygen concentration increase pattern data, the effects of varying oxygen partial pressure increments on blood oxygen saturation can be simulated. This simulation provides a prediction of blood oxygen saturation changes under different treatment conditions, facilitating adjustment of treatment parameters for optimal results. Analyzing the dynamic changes in oxygen concentration in the body provides a more comprehensive understanding of the effects of hyperbaric oxygen therapy on oxygen distribution within the body. This data provides key information for understanding oxygen delivery and utilization during treatment, helping to optimize treatment plans and enhance treatment effectiveness. Based on the dynamic changes in oxygen concentration in the body, the magnitude of the metabolic gain after treatment can be estimated. This estimation helps assess the physiological effects of treatment and individual physiological adaptability.

[0023] Preferably, the estimating of the body's metabolic gain intensity based on the body's oxygen concentration dynamic change data includes:

[0024] Calculate the stage-by-stage change rate difference of the dynamic change data of the body's oxygen concentration to obtain the oxygen concentration stage-by-stage change rate difference data;

[0025] The oxygen concentration dynamic change data of the body is used to calculate the oxygen molecule diffusion rate at each stage according to the oxygen concentration stage change rate difference data, and the oxygen molecule diffusion rate data at each stage is obtained;

[0026] The body cell activity is evaluated based on the periodic oxygen molecule diffusion rate data to obtain the periodic body cell activity data;

[0027] Based on the periodic oxygen molecule diffusion rate data and the periodic body cell activity data, the cell repair capacity is defined to obtain the periodic body cell repair capacity data;

[0028] Perform cell metabolism nonlinear regression analysis based on the staged body cell repair capacity data to obtain cell metabolism nonlinear regression data;

[0029] The nonlinear variance homogeneity calculation is performed on the cell metabolism nonlinear regression data to obtain the cell metabolism nonlinear variance homogeneity data;

[0030] The body metabolic gain strength is estimated based on the nonlinear variance homogeneity data of cell metabolism to obtain the body metabolic gain strength data.

[0031] By calculating the difference in the rate of change of oxygen concentration at different stages, the present invention can quantify the rate and trend of oxygen concentration changes at different treatment stages. This helps analyze the dynamic characteristics of oxygen distribution during treatment. Based on the data of the difference in the rate of change of oxygen concentration at different stages, the stage-by-stage diffusion rate of oxygen molecules in the body is calculated. This data reflects the efficiency of oxygen transmission at the tissue and cellular levels, providing an important basis for evaluating oxygen utilization efficiency. The stage-by-stage oxygen molecular diffusion rate data can be used to assess the activity of cells at different treatment stages. This data helps understand the changes in cellular metabolism during treatment. Based on the stage-by-stage oxygen molecular diffusion rate and cell activity data, the cell repair potential of the body at different treatment stages can be determined. This helps evaluate the impact of treatment on the potential for tissue repair and regeneration. Nonlinear regression analysis of the stage-by-stage cell metabolism data can provide a deeper understanding of the dynamic changes in cellular metabolism during treatment. This analysis helps reveal the complexity and nonlinear characteristics of cellular metabolic responses. By calculating the homogeneity of nonlinear variance of cellular metabolism, the consistency and stability of cellular metabolic responses under different treatment conditions can be assessed. Finally, based on the data obtained in the above steps, the magnitude of the treatment's metabolic gain can be estimated.

[0032] Preferably, performing nonlinear variance homogeneity calculation on the cell metabolism nonlinear regression data comprises:

[0033] Perform nonlinear regression variance calculation on cell metabolism nonlinear regression data to obtain metabolic nonlinear regression variance data;

[0034] Perform nonlinear group fitting on the cell metabolism nonlinear regression data according to the metabolic nonlinear regression variance data to obtain metabolic nonlinear variance group fitting data;

[0035] According to the metabolic nonlinear variance group fitting data, the variance group normal distribution analysis of the cell metabolic nonlinear regression data was performed to obtain the variance group normal distribution data;

[0036] Based on the variance grouped normal distribution data, the normal distribution structure Levene's test was performed on the metabolic nonlinear variance grouped fitting data to obtain the normal distribution structure test data;

[0037] Nonlinear variance homogeneity calculation was performed based on the normal distribution structure test data to obtain the nonlinear variance homogeneity data of cell metabolism.

[0038] The present invention performs variance calculation on the nonlinear regression data of cell metabolism. This step is intended to evaluate the degree of dispersion of each data point in the regression model to understand the variability of the data. Based on the metabolic nonlinear regression variance data obtained in the previous step, the data is subjected to nonlinear group fitting. This helps to group the data and establish a nonlinear model, better understand the characteristics of different data groups, and perform variance group normal distribution analysis based on the metabolic nonlinear variance group fitting data. This analysis can reveal the normal distribution of data between groups, further verify the statistical properties of the data, and use Levene's test to verify the normal distribution structure of the variance group normal distribution data. This helps to determine the equality or inequality of variance between different data groups. Finally, based on the normal distribution structure test data, the nonlinear variance homogeneity calculation of cell metabolism is performed. This step evaluates whether the variance of metabolic variables is equal between different data groups, thereby determining the stability and consistency of cell metabolism under different conditions.

[0039] Preferably, the muscle elasticity recovery module includes the following functions:

[0040] Calculate the energy consumption increment based on the body metabolic gain intensity data to obtain the body metabolic energy consumption increment data;

[0041] The muscle strength recovery effect is analyzed based on the body metabolic energy consumption increment data and the body metabolic gain strength data to obtain the muscle strength recovery effect data;

[0042] The muscle strength recovery effect data is analyzed for the recovery synergy relationship between muscle groups to obtain muscle strength recovery synergy relationship data;

[0043] The muscle elastic modulus recovery data of different muscle groups is calculated based on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data to obtain the muscle elastic modulus recovery data.

[0044] The present invention calculates the energy consumption increment of the body under different treatment or training conditions based on the body metabolic gain strength data. This helps to evaluate the impact of treatment or training on the body's energy metabolism, provides important data for understanding the efficiency of muscle activity, and analyzes the muscle strength recovery effect under different treatment or training conditions based on the body metabolic energy consumption increment data and the body metabolic gain strength data. These data help to quantify the actual effect of treatment or training on muscle strength recovery, analyze the muscle strength recovery effect data, and reveal the recovery synergistic relationship between different muscle groups. This analysis helps to understand the coordination and mutual influence of muscle groups in the recovery process, and provides information support for optimizing training or treatment strategies. Based on the muscle strength recovery synergistic relationship data, the muscle elastic modulus recovery situation between different muscle groups is calculated. These data evaluate the changes in elastic properties during the recovery process of muscle tissue and provide key information for evaluating muscle function and adaptability.

[0045] Preferably, the muscle strength recovery effect analysis based on the body metabolic energy consumption increment data and the body metabolic gain strength data includes:

[0046] Performing body sign factor analysis on the body metabolic energy consumption increment data to obtain the metabolic energy consumption sign factor;

[0047] Based on the metabolic energy consumption sign factors and the body metabolic gain strength data, the metabolic index correlation calculation is performed to obtain the body metabolic index correlation data;

[0048] The muscle lactate clearance effect is simulated based on the body metabolic index correlation data to obtain the muscle lactate clearance effect data;

[0049] The lactate clearance half-life was calculated for the muscle lactate clearance effect data to obtain the lactate clearance half-life data;

[0050] The muscle strength recovery effect was analyzed based on the lactate clearance half-life data to obtain the muscle strength recovery effect data.

[0051] The present invention obtains metabolic energy consumption sign factors by analyzing the incremental data of body metabolic energy consumption. These factors help to understand the characteristics and changing trends of body metabolism under different conditions. Based on the metabolic energy consumption sign factors and body metabolic gain intensity data, the correlation between body metabolic indicators is calculated. These data reveal the relationship between different metabolic parameters, help evaluate their role and influence in the muscle metabolic process, and simulate the muscle lactate clearance effect based on the body metabolic indicator correlation data. This process helps to understand the muscle's ability to handle lactate, and provides data support for evaluating the impact of lactate accumulation during exercise and recovery. Based on the simulated data, the half-life of muscle lactate clearance is calculated. The lactate clearance half-life is an important indicator for measuring muscle metabolic adaptability and recovery speed, and is of great significance for the evaluation of athletic performance and training effects. Combined with the lactate clearance half-life data, the recovery effect of muscle strength is analyzed. These data help to evaluate the actual impact of hyperbaric oxygen chamber treatment strategies on muscle strength recovery.

[0052] Preferably, analyzing the muscle strength recovery effect data to determine the recovery synergy relationship between muscle groups includes:

[0053] Performing similarity analysis on muscle group recovery behavior on muscle strength recovery effect data to obtain muscle group recovery behavior similarity data;

[0054] Based on the muscle group recovery behavior similarity data, non-parametric estimation of time-varying dynamic interaction is performed to obtain non-parametric time-varying dynamic interaction data;

[0055] Based on the non-parametric time-varying dynamic interaction data and the muscle group recovery behavior similarity data, a coordinated interaction causal chain analysis is performed to obtain the coordinated interaction causal chain data;

[0056] The coordinated interaction causal chain data is analyzed to analyze the recovery synergy relationship between muscle groups and obtain the muscle strength recovery synergy relationship data.

[0057] The present invention can identify the behavior patterns and similarities of muscle groups during the recovery process through similarity analysis of muscle strength recovery effect data, thereby understanding which muscle groups have similar recovery processes, which helps to reveal the common characteristics of different muscle groups during recovery. By using muscle group recovery behavior similarity data to perform time-varying dynamic interaction non-parametric estimation, the interaction between muscle groups can be dynamically captured, avoiding the limitations of data distribution assumptions in traditional methods and providing a more flexible and accurate interaction description. By analyzing non-parametric time-varying dynamic interaction data and muscle group recovery behavior similarity data, a coordinated interaction causal chain between muscle groups can be established. This analysis can reveal the causal relationship in the muscle group recovery process, identify which muscle groups have significant coordinated interactions, and help to understand the mechanism of muscle strength recovery. The analysis of the coordinated interaction causal chain data can reveal the synergistic relationship between muscle groups, that is, which muscle groups interact and recover synergistically during the recovery process. This analysis helps to more comprehensively understand the overall process of muscle recovery and the interaction between each muscle group, thereby optimizing the muscle strength recovery strategy.

[0058] Preferably, performing muscle elastic modulus recovery calculation between different muscle groups on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data comprises:

[0059] According to the muscle strength recovery synergy relationship data, the elastic response analysis between different muscle groups is performed on the muscle strength recovery effect data to obtain the muscle elastic response data;

[0060] Conduct synergistic effect multilevel regression analysis on muscle elastic response data to obtain elastic response synergistic multilevel regression data;

[0061] Performing weighted processing on the responses of different muscle groups on the muscle elastic response data according to the elastic response collaborative multi-level regression data to obtain muscle elastic response weighted data;

[0062] According to the muscle elastic response weighted data, a multi-level weighted elastic response matrix is ​​constructed by coordinating the elastic response multi-level regression data to obtain a multi-level weighted elastic response matrix;

[0063] Based on the multi-level weighted elastic response matrix, the elastic response collaborative multi-level regression data were analyzed for muscle elastic activation dependency to obtain muscle elastic activation dependency data;

[0064] The muscle elastic modulus recovery calculation between different muscle groups is performed based on the muscle elastic activation dependency data to obtain the muscle elastic modulus recovery data.

[0065] The present invention analyzes the elastic response of different muscle groups in response to the recovery process by analyzing the synergistic relationship data between muscle strength recovery groups. This analysis helps understand the dynamic adaptability of muscle groups to strength recovery. Performing a synergistic multi-level regression analysis of the muscle elastic response data can identify and quantify the synergistic effects of different muscle groups during the recovery process. This analysis reveals interactive effects at multiple levels, helping to understand the complex interactions during muscle recovery. Weighting the muscle elastic response data based on the elastic response synergistic multi-level regression data can more accurately assess the relative importance and contribution of each muscle group in the recovery process. This helps to accurately grasp the detailed characteristics of muscle recovery. Constructing a multi-level weighted elastic response matrix based on the weighted elastic response data helps to comprehensively integrate elastic response information at different levels. This matrix can reveal the overall elastic characteristics and interactions of muscle groups at different recovery stages. Using the multi-level weighted elastic response matrix to perform muscle elastic activation dependency analysis can provide a deeper understanding of the dependency of muscle activation patterns on elastic response during recovery. This helps to identify the key activation mechanisms of muscle groups in recovery. Calculating muscle elastic modulus recovery data based on muscle elastic activation-dependent data allows for quantitative assessment of changes in muscle elastic modulus during recovery. This calculation helps understand the structural and functional improvements of muscle during recovery.

[0066] Preferably, the body function improvement module includes the following functions:

[0067] Based on the multi-layer perceptron, the hyperbaric oxygen chamber recovery effect is perceived based on the body metabolic gain intensity data and muscle elastic modulus recovery data to obtain hyperbaric oxygen chamber recovery effect perception data;

[0068] Normalizing the hyperbaric oxygen chamber recovery effect perception data to obtain recovery effect perception normalized data;

[0069] The normalized data of recovery effect perception is used to evaluate the effect of improving body function, and the data of the effect of improving body function is obtained.

[0070] The present invention uses a multi-layer perceptron to analyze the body's metabolic gain intensity data and muscle elastic modulus recovery data, and can evaluate the effect of the hyperbaric oxygen chamber on the body's recovery. This analysis can comprehensively consider the changes in metabolic gain and muscle elastic modulus, thereby obtaining the overall recovery effect perception of the hyperbaric oxygen chamber, and normalizing the recovery effect perception data can eliminate the influence of different data scales and ranges, so that the data can be compared and analyzed under a unified standard. This helps to improve the accuracy and consistency of data analysis, and the body function improvement effect evaluation based on the normalized data can quantify the actual improvement degree of the hyperbaric oxygen chamber on the body's function. This evaluation can provide objective data on functional improvement and help understand the role of the hyperbaric oxygen chamber in functional recovery.

[0071] The beneficial effects of the present invention are as follows: the present invention provides a patient hyperbaric oxygen chamber recovery effect analysis system based on big data, which is an optimized processing of a traditional patient hyperbaric oxygen chamber recovery effect analysis system based on big data. It solves the problems of inaccurate analysis of patient hyperbaric oxygen chamber recovery effect and large error in analysis of muscle recovery effect under hyperbaric oxygen chamber intervention in the traditional patient hyperbaric oxygen chamber recovery effect analysis system based on big data, improves the accuracy of analysis of patient hyperbaric oxygen chamber recovery effect and reduces the problem of large error in analysis of muscle recovery effect under hyperbaric oxygen chamber intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a module flow diagram of a big data-based patient hyperbaric oxygen chamber recovery effect analysis system;

[0073] Figure 2 for Figure 1 Schematic diagram of the functional flow of the mid-body metabolic gain analysis module;

[0074] Figure 3 for Figure 1 Schematic diagram of the functional flow of the muscle elasticity recovery module.

[0075] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0076] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0077] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0078] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0079] To achieve this, please refer to Figures 1 to 3 , a patient hyperbaric oxygen chamber recovery effect analysis system based on big data, including the following modules:

[0080] The physiological state grouping module is used to obtain the patient's pre-treatment physiological state data set and the hyperbaric oxygen chamber operation status data; group the patient's pre-treatment physiological state data set into physiological state samples to obtain pre-treatment physiological state grouping data; extract the pre-treatment blood oxygen saturation from the pre-treatment physiological state grouping data to obtain pre-treatment blood oxygen saturation grouping data;

[0081] The body metabolic gain analysis module is used to simulate the oxygen partial pressure increment difference of the blood oxygen saturation group data before the treatment based on the hyperbaric oxygen chamber operation status data to obtain the oxygen partial pressure increment difference simulation data; perform dynamic change analysis of the body oxygen concentration on the oxygen partial pressure increment difference simulation data to obtain the body oxygen concentration dynamic change data; and estimate the body metabolic gain intensity based on the body oxygen concentration dynamic change data to obtain the body metabolic gain intensity data;

[0082] The muscle elasticity recovery module is used to analyze the muscle strength recovery effect based on the body metabolic gain strength data to obtain muscle strength recovery effect data; the muscle elastic modulus recovery calculation between different muscle groups is performed on the muscle strength recovery effect data to obtain muscle elastic modulus recovery data;

[0083] The body function improvement module is used to evaluate the body function improvement effect based on the body metabolic gain intensity data and muscle elastic modulus recovery data based on the multi-layer perceptron to obtain the body function improvement effect data.

[0084] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the module flow of a patient hyperbaric oxygen chamber recovery effect analysis system based on big data of the present invention. In this example, the patient hyperbaric oxygen chamber recovery effect analysis system based on big data includes:

[0085] S1: Physiological state grouping module, used to obtain the patient's pre-treatment physiological state data set and hyperbaric oxygen chamber operation status data; group the patient's pre-treatment physiological state data set into physiological state samples to obtain pre-treatment physiological state group data; extract the pre-treatment blood oxygen saturation from the pre-treatment physiological state group data to obtain pre-treatment blood oxygen saturation group data;

[0086] In an embodiment of the present invention, patient records are first obtained from a medical information system or from publicly available academic research websites such as HowNet, and pre-treatment physiological status data is extracted. This data typically includes physiological indicators such as heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation. This data is exported into a CSV or database table format using a medical database interface (such as the HL7 or FHIR standard). This data is historical data, and relevant hyperbaric chamber operating data during treatment, including chamber pressure, oxygen concentration, and operating time, is obtained from this historical data. Typically, hyperbaric chambers are equipped with data loggers that automatically record these parameters. This data is exported through a data interface, ensuring that the data format is consistent with other datasets to facilitate subsequent integration. The collected physiological status data is preprocessed. Missing values ​​and outliers are removed from the data to ensure data integrity and accuracy. This can be done using the Python Pandas library or a data processing package in the R language. Patients are grouped based on similarities in physiological status. Cluster analysis methods such as K-means or hierarchical clustering can be used. Cluster analysis is performed using the Python Scikit-learn library to group samples into groups based on physiological parameter characteristics. Data related to blood oxygen saturation is extracted from the grouped physiological status data. This typically requires filtering relevant records based on fields in the data table. Based on the extracted physiological data, blood oxygen saturation is calculated or extracted. This process can utilize the Python Pandas library for data manipulation, or statistical analysis tools can be used to calculate blood oxygen saturation.

[0087] S2: Body metabolic gain analysis module, used to simulate the oxygen partial pressure increment difference of the blood oxygen saturation group data before the treatment based on the hyperbaric oxygen chamber operation status data, to obtain oxygen partial pressure increment difference simulation data; perform body oxygen concentration dynamic change analysis on the oxygen partial pressure increment difference simulation data, to obtain body oxygen concentration dynamic change data; and estimate the body metabolic gain intensity based on the body oxygen concentration dynamic change data, to obtain body metabolic gain intensity data;

[0088] In this embodiment of the present invention, the oxygen dosage for each time period is extracted from the operating status data of the hyperbaric oxygen chamber. The oxygen partial pressure increment difference is simulated for the grouped blood oxygen saturation data before the treatment course. This incremental difference in oxygen partial pressure is simulated using a linear regression model. Using the linregress function in the Python SciPy library, a linear fit is performed on the oxygen partial pressure changes for each time period to calculate the differences in oxygen partial pressure under different physiological states. The simulated oxygen partial pressure increment difference data is then combined with the corresponding body oxygen concentration data to ensure that the data table includes the oxygen concentration change value at each time point. The Python Pandas library is used to integrate and organize the data, and the dynamic time warping (DTW) algorithm is applied to analyze the changing trends of body oxygen concentration. The DTW algorithm measures the similarity between time series and calculates the dynamic changes in body oxygen concentration. The fastdtw library in Python can implement this algorithm, generating dynamic oxygen concentration data. This data is organized into a table, recording the changing trends and analysis results at each time point. The Python Pandas library is used to save the data as a CSV file or store it in a database to ensure systematic and queryable data. Extract the required metrics from the oxygen concentration dynamics data, including the oxygen concentration change values ​​and their timestamps. This data will serve as the input for estimating the metabolic gain strength. A weighted linear regression model is used to estimate the metabolic gain strength. Specifically, the OLS function in the Python statsmodels library is used to perform a regression analysis using the oxygen concentration change data as the independent variable and the metabolic gain as the dependent variable to calculate the metabolic gain strength.

[0089] S3: Muscle elasticity recovery module, used to analyze muscle strength recovery effects based on body metabolic gain strength data to obtain muscle strength recovery effect data; calculate muscle elastic modulus recovery between different muscle groups based on muscle strength recovery effect data to obtain muscle elastic modulus recovery data;

[0090] In an embodiment of the present invention, relevant indicators are extracted from the metabolic gain strength data of the body, including the metabolic gain value and its corresponding timestamp. These data are combined with the muscle strength data to ensure that the timestamp and muscle strength value of each set of data are consistent. The data are merged using Python's Pandas library to ensure accurate alignment of the data, and the recovery effect of muscle strength is analyzed using a linear regression model. The metabolic gain strength is used as the independent variable and the muscle strength value as the dependent variable, and the OLS function in Python's statsmodels library is used for regression analysis. The changing trend of muscle strength with metabolic gain is calculated, and muscle strength recovery effect data is generated. The recovery effect index of each muscle group is extracted from the muscle strength recovery effect data. Ensure that the data includes the strength recovery value of each muscle group at different time points. Use Python's Pandas library for data processing and screening to ensure data integrity, apply the elastic modulus calculation formula to perform recovery calculation on the muscle elastic modulus of different muscle groups, and stress and strain can be estimated by the relationship between muscle strength recovery data and muscle volume data. Use the NumPy library in Python for calculation and data processing.

[0091] S4: Body function improvement module, used to evaluate the body function improvement effect based on the body metabolic gain intensity data and muscle elastic modulus recovery data based on the multi-layer perceptron, and obtain the body function improvement effect data.

[0092] In an embodiment of the present invention, relevant features are extracted from the body metabolic gain strength data and muscle elastic modulus recovery data. The specific operation includes integrating these two types of data to form a comprehensive data set. The integrated data should include body metabolic gain strength, muscle elastic modulus, corresponding timestamps and other relevant indicators. The Python Pandas library is used for data processing to ensure that all data are aligned in chronological order and to handle missing values ​​and outliers. The Python TensorFlow library is used to construct a multi-layer perceptron (MLP) model. The input layer of the model includes body metabolic gain strength data and muscle elastic modulus recovery data. The hidden layer is set to multiple fully connected layers, and each layer uses the ReLU activation function. The output layer uses a linear activation function to predict the effect of improving body function. During the model training process, the mean square error is selected as the loss function, and the gradient descent algorithm is used to optimize the model parameters. The optimal number of hidden layer nodes and learning rate are determined by cross-validation. The integrated data set is divided into a training set and a test set, usually with a ratio of 80% training set and 20% test set. The multi-layer perceptron model is trained using the training set data, and the model parameters are adjusted to minimize the loss function. After training, the performance of the model is evaluated using the test set data, and the model's prediction accuracy and error indicators, such as the root mean square error (RMSE) and the coefficient of determination (R2), are calculated. All training and evaluation processes are performed using the TensorFlow library. The trained multi-layer perceptron model is applied to new body metabolic gain intensity data and muscle elastic modulus recovery data to predict the effect of body function improvement. The generated prediction results are organized into a data table, including the body function improvement effect of each data point and its corresponding predicted value. Use Python's Pandas library to store the results as a CSV file or database table for subsequent analysis and use.

[0093] Preferably, the physiological status grouping module includes the following functions:

[0094] Obtain the patient's pre-treatment physiological status data set and hyperbaric oxygen chamber operating status data;

[0095] Preprocessing the patient's physiological state data set before treatment to obtain preprocessed physiological state data before treatment;

[0096] Grouping physiological state samples of the patient's pre-treatment physiological state data set according to the pre-treatment physiological state preprocessing data to obtain pre-treatment physiological state grouping data;

[0097] The pre-treatment blood oxygen saturation is extracted from the pre-treatment physiological status grouping data to obtain the pre-treatment blood oxygen saturation grouping data.

[0098] In this embodiment of the present invention, a massive dataset of pre-treatment patient physiological status is extracted from a hospital's electronic health record system. This dataset should include pre-treatment physiological indicators such as heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation. Data extraction is performed using HL7 or FHIR standard data interfaces to ensure a uniform data format. Relevant data, including chamber pressure, oxygen concentration, and operating time, is extracted from the hyperbaric oxygen chamber's operation monitoring system. This data can be automatically generated by the chamber's data recorder and exported through a data interface in CSV format or a database table. The extracted physiological status data is preprocessed, primarily by removing missing values ​​and outliers. The dropna function in the Python Pandas library is used to remove missing data, and the replace function is used to replace outliers. Numerical data is normalized to eliminate the influence of different dimensions. Features related to physiological status, such as heart rate variability and blood pressure fluctuations, are extracted. Statistical features are calculated using the Python SciPy library, and feature selection is performed on the data to retain the most influential features for analysis. The preprocessed data is stored as a structured data table in CSV file or database table format. Use the Python Pandas library to export the data to ensure data integrity and accuracy. Perform cluster analysis on the preprocessed data to divide the data into multiple groups. Select either the K-means clustering algorithm or the hierarchical clustering algorithm and implement it using the Python Scikit-learn library. Divide the samples into several groups based on the similarity of physiological status characteristics. Merge the grouping results with the original data to generate a data table containing group information. Each sample should be labeled with its group for subsequent analysis. Use the Python Pandas library to save the grouped data as a CSV file or a database table. Filter data related to blood oxygen saturation from the grouped physiological status data. Ensure that the extracted data includes the blood oxygen saturation value of each sample and its corresponding group information. Use the Python Pandas library to filter and organize the data. Based on the filtering results, extract the blood oxygen saturation data for each group. Calculate the mean blood oxygen saturation value and its standard deviation for each group to obtain the blood oxygen saturation distribution for each group. Organize the extracted blood oxygen saturation data into a data table, including the blood oxygen saturation value and related statistical information for each group. Use Python's Pandas library to save data as CSV files or database tables to ensure the systematic and queryable nature of the data.

[0099] Preferably, the body metabolic gain analysis module includes the following functions:

[0100] Performing oxygen concentration phase-increasing pattern recognition on the hyperbaric oxygen chamber operating status data to obtain oxygen concentration increasing pattern data;

[0101] The blood oxygen saturation differences between different groups were quantified based on the blood oxygen saturation grouping data before treatment to obtain the blood oxygen saturation grouping difference quantitative data;

[0102] Perform oxygen partial pressure increment difference simulation on the blood oxygen saturation group difference quantitative data according to the oxygen concentration increment mode data to obtain oxygen partial pressure increment difference simulation data;

[0103] The dynamic change of body oxygen concentration is analyzed on the simulated data of oxygen partial pressure increment difference to obtain the dynamic change data of body oxygen concentration;

[0104] The body's metabolic gain intensity is estimated based on the dynamic change data of the body's oxygen concentration to obtain the body's metabolic gain intensity data.

[0105] As an example of the present invention, refer to Figure 2 As shown, Figure 1 Schematic diagram of the functional flow of the metabolic gain analysis module in the body. In this example, the functions of the metabolic gain analysis module include:

[0106] S201: performing oxygen concentration phase-increasing pattern recognition on the hyperbaric oxygen chamber operating status data to obtain oxygen concentration increasing pattern data;

[0107] In an embodiment of the present invention, oxygen concentration data is extracted from the operation monitoring system of the hyperbaric oxygen chamber. The data should include the oxygen concentration at each time point and its timestamp. The data file is read using Python's Pandas library to ensure the integrity and consistency of the data, and the oxygen concentration data is analyzed using a temporal pattern recognition algorithm. The iind_peaks function in Python's SciPy library is used to detect the increasing stage in the oxygen concentration data. By calculating the rate of change of the oxygen concentration, the phased pattern of gradually increasing concentration is identified, and the starting and ending points of each stage are marked. The identified phased increasing pattern is organized into a data table, and the start time, end time and change amplitude of the oxygen concentration of each stage are recorded. The data is saved as a CSV file or a database table using Python's Pandas library for subsequent analysis.

[0108] S202: quantifying the blood oxygen saturation differences between different groups based on the blood oxygen saturation grouping data before the treatment, to obtain blood oxygen saturation grouping difference quantification data;

[0109] In an embodiment of the present invention, the blood oxygen saturation grouping data before the treatment is imported into Python's Pandas library, and the data is sorted according to the grouping information. Ensure that the blood oxygen saturation data of each group is included. The analysis of variance (ANOVA) or t-test method is used to quantify the differences in blood oxygen saturation between different groups. Use the f_oneway function in Python's Scipy library to perform ANOVA analysis, or the ttest ind function to perform a t-test to calculate the differences in blood oxygen saturation between different groups and their statistical significance. The difference quantification results are organized into a data table, including the average blood oxygen saturation value, standard deviation and significance level of each group. Use Python's Pandas library to save the data as a CSV file or database table for further analysis and use.

[0110] S203: performing oxygen partial pressure increment difference simulation on the blood oxygen saturation group difference quantified data according to the oxygen concentration increment mode data to obtain oxygen partial pressure increment difference simulation data;

[0111] In an embodiment of the present invention, oxygen concentration increment pattern data and quantitative data on grouped differences in blood oxygen saturation are extracted from the system. The oxygen concentration increment pattern data describes the changing pattern of oxygen concentration within the hyperbaric oxygen chamber during treatment, while the quantitative data on grouped differences in blood oxygen saturation reflect the differences in blood oxygen saturation between patients in different groups before treatment. A mathematical model is used to establish a simulation framework for differences in oxygen partial pressure increments. This model must consider the impact of the oxygen concentration increment pattern on changes in oxygen partial pressure. An appropriate mathematical or physical model (such as an exponential growth model or a linear regression model) is selected to simulate the specific impact of oxygen concentration on blood oxygen saturation. This ensures that the model accurately reflects the phased changes in oxygen partial pressure. The oxygen concentration increment pattern data is processed to calculate the oxygen concentration increment. This typically involves calculating the change in oxygen concentration at different time points to obtain the oxygen partial pressure increment. The calculated results are then combined with the quantitative data on grouped differences in blood oxygen saturation to obtain specific oxygen partial pressure increment difference data. By comparing the quantitative data of the differences between different groups, the specific impact of the oxygen concentration increment on blood oxygen saturation is determined, and the established model is used to simulate the differences in oxygen partial pressure increments. Use a simulation tool (such as MATLAB, the SciPy library in Python, or dedicated simulation software) to input data on the oxygen concentration ramp pattern and quantitative data on the differences in blood oxygen saturation between groups. The model will calculate the oxygen partial pressure increment at each stage and predict its impact on blood oxygen saturation. Conduct simulation experiments and adjust model parameters to ensure that the simulation results are consistent with reality. Record the difference in oxygen partial pressure increment at each time point or stage in the simulation. Perform a detailed analysis of the simulation results, including calculating statistics and trends for the oxygen partial pressure increment differences. Analyze the impact of different oxygen concentration stages on blood oxygen saturation to determine their contribution to the overall recovery effect.

[0112] S204: Analyzing the dynamic changes of body oxygen concentration based on the simulated data of the oxygen partial pressure increment difference to obtain dynamic changes of body oxygen concentration;

[0113] In an embodiment of the present invention, the oxygen partial pressure incremental difference simulation data is merged with the body oxygen concentration data to ensure that the data contains the oxygen partial pressure increment and the corresponding body oxygen concentration value at each time point. The Python Pandas library is used for data integration. The dynamic time warping (DTW) algorithm is applied to analyze the changes in body oxygen concentration. The DTW algorithm can calculate the similarity between time series and evaluate the dynamic changes in body oxygen concentration over time. The fastdtw library in Python is used for analysis to generate dynamic change data of body oxygen concentration. The analysis results are organized into a data table, recording the changes in body oxygen concentration at each time point and its corresponding incremental difference. The Python Pandas library is used to save the data as a CSV file or a database table to ensure the integrity and accessibility of the data.

[0114] S205: Estimate the metabolic gain strength of the body based on the dynamic change data of the body's oxygen concentration to obtain the metabolic gain strength data of the body.

[0115] In an embodiment of the present invention, the oxygen concentration change value and its corresponding timestamp are extracted from the dynamic change data of the body's oxygen concentration. Data is prepared for estimation of metabolic gain intensity. The body's metabolic gain intensity is estimated using a weighted linear regression model. The OLS function in the statsmodels library in Python is selected for linear regression analysis, and the body's oxygen concentration change value is used as the independent variable, and the metabolic gain intensity is used as the dependent variable to calculate the intensity of the metabolic gain. The estimated results of the metabolic gain intensity are organized into a data table, including the metabolic gain intensity value and its statistical information at each time point. Use Python's Pandas library to save the data as a CSV file or database table to ensure the systematicity and queryability of the data.

[0116] Preferably, the estimating of the body's metabolic gain intensity based on the body's oxygen concentration dynamic change data includes:

[0117] Calculate the stage-by-stage change rate difference of the dynamic change data of the body's oxygen concentration to obtain the oxygen concentration stage-by-stage change rate difference data;

[0118] The oxygen concentration dynamic change data of the body is used to calculate the oxygen molecule diffusion rate at each stage according to the oxygen concentration stage change rate difference data, and the oxygen molecule diffusion rate data at each stage is obtained;

[0119] The body cell activity is evaluated based on the periodic oxygen molecule diffusion rate data to obtain the periodic body cell activity data;

[0120] Based on the periodic oxygen molecule diffusion rate data and the periodic body cell activity data, the cell repair capacity is defined to obtain the periodic body cell repair capacity data;

[0121] Perform cell metabolism nonlinear regression analysis based on the staged body cell repair capacity data to obtain cell metabolism nonlinear regression data;

[0122] The nonlinear variance homogeneity calculation is performed on the cell metabolism nonlinear regression data to obtain the cell metabolism nonlinear variance homogeneity data;

[0123] The body metabolic gain strength is estimated based on the nonlinear variance homogeneity data of cell metabolism to obtain the body metabolic gain strength data.

[0124] In this embodiment of the present invention, oxygen concentration values ​​and their timestamps at each time point are extracted from the dynamic oxygen concentration data. The data is read using the Python Pandas library, ensuring that the data is arranged in chronological order. The oxygen concentration data is divided into several stages, and the start and end times of each stage are determined. The Python NumPy library is used to calculate the oxygen concentration change rate for each stage and the difference in change rates between adjacent stages. The Python Pandas library is used for data processing, calculating the rate difference between each two adjacent stages and organizing the results into a data table. The change rate difference values ​​for each stage are recorded, and the oxygen concentration stage change rate difference data are combined with the dynamic oxygen concentration data. The data ensures that the change rate difference for each stage and the corresponding oxygen concentration data are included. A diffusion model is used to calculate the stage-by-stage oxygen molecular diffusion rate. A classic diffusion equation, such as Fick's law, is used for calculation. The stage-by-stage oxygen molecular diffusion rate data is organized into a table, recording the diffusion rate values ​​and related statistical information for each stage. The diffusion rate values ​​for each stage are extracted from the stage-by-stage oxygen molecular diffusion rate data and correlated with indicators of cell activity. The data ensures that both the diffusion rate and cell activity data for each stage are included, and a biostatistical model is used to assess cell activity. A linear regression model was used, using oxygen diffusion rate as the independent variable and cell activity as the dependent variable, to calculate the trend of cell activity. Regression analysis was performed using the OLS function in the Python statsmodels library. The evaluation results were organized into a data table, recording the cell activity values ​​and statistical information for each stage. The stage-by-stage oxygen diffusion rate data and cell activity data were merged to ensure that data from each stage were included. Data were merged using the Python Pandas library, and multivariate regression models or machine learning algorithms were used to evaluate cell repair capacity. Models such as multilayer perceptrons or support vector machines were selected, using oxygen diffusion rate and cell activity as input features to predict cell repair capacity. These models can be implemented using the Python Scikit-Learn library. The repair capacity values ​​and their corresponding timestamps were extracted from the stage-by-stage cell repair capacity data as input data for nonlinear regression analysis. A nonlinear regression model, such as exponential or logarithmic regression, was applied to fit the relationship between cell metabolism and repair capacity. Nonlinear regression analysis was performed using the curve_fit function in the Python SciPy library. Regression residuals were extracted from the nonlinear regression data on cell metabolism, and the variance of each data point was calculated. The homogeneity of variance of the regression residuals was checked using the Levene test or the Brown-Forsythe test. The homogeneity of variance test was performed using the levene function in the Python SciPy library. The homogeneity of variance data for nonlinear cell metabolism were combined with the results of the nonlinear cell metabolism regression analysis to ensure that the data included homogeneity of variance values ​​for each stage and the relevant metabolic indices.Estimate metabolic gain using either a weighted regression model or a Bayesian regression model. Use the WLS function in the Python statsmodels library for weighted regression, or the pymc3 library for Bayesian regression analysis.

[0125] Preferably, performing nonlinear variance homogeneity calculation on the cell metabolism nonlinear regression data comprises:

[0126] Perform nonlinear regression variance calculation on cell metabolism nonlinear regression data to obtain metabolic nonlinear regression variance data;

[0127] Perform nonlinear group fitting on the cell metabolism nonlinear regression data according to the metabolic nonlinear regression variance data to obtain metabolic nonlinear variance group fitting data;

[0128] According to the metabolic nonlinear variance group fitting data, the variance group normal distribution analysis of the cell metabolic nonlinear regression data was performed to obtain the variance group normal distribution data;

[0129] Based on the variance grouped normal distribution data, the normal distribution structure Levene's test was performed on the metabolic nonlinear variance grouped fitting data to obtain the normal distribution structure test data;

[0130] Nonlinear variance homogeneity calculation was performed based on the normal distribution structure test data to obtain the nonlinear variance homogeneity data of cell metabolism.

[0131] In an embodiment of the present invention, nonlinear regression data of cell metabolism is extracted from the system, including the predicted values ​​and actual observed values ​​of the regression model. Ensure that the data set contains the residuals of the regression model, that is, the difference between the predicted values ​​and the actual values, use Python's NumPy library to calculate the variance of the regression residuals, organize the calculation results into a table, and record the variance data of each stage. Use Python's Scikit-learn library for nonlinear group fitting. Select an appropriate nonlinear regression model, such as polynomial regression or Gaussian process regression, and fit the regression model according to the variance data. Ensure that the model can handle the complexity of the grouped data and calculate the fitting effect of each group. Apply statistical analysis methods to perform a normal distribution test on the variance data of each group. Use the norm.fit function in Python's SciPy library to estimate the mean and standard deviation of each group data and draw a normal distribution graph. Calculate the goodness-of-fit index of the normal distribution, such as the Kolmogorov-Smirnov test result. Use the levene function in Python's SciPy library to perform a Levene's test on the variance data of each group. Levene's test was used to test whether the variances of different groups were equal. The test results, including the normal distribution goodness-of-fit and Levene's test results, were extracted from the normal distribution structure test data. The Levene's test results were combined to calculate the homogeneity of variance. The homogeneity of variance calculation aims to verify whether the variances of data from different groups are equal. The homogeneity of variance was reconfirmed using the levene function in the Python SciPy library.

[0132] Preferably, the muscle elasticity recovery module includes the following functions:

[0133] Calculate the energy consumption increment based on the body metabolic gain intensity data to obtain the body metabolic energy consumption increment data;

[0134] The muscle strength recovery effect is analyzed based on the body metabolic energy consumption increment data and the body metabolic gain strength data to obtain the muscle strength recovery effect data;

[0135] The muscle strength recovery effect data is analyzed for the recovery synergy relationship between muscle groups to obtain muscle strength recovery synergy relationship data;

[0136] The muscle elastic modulus recovery data of different muscle groups is calculated based on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data to obtain the muscle elastic modulus recovery data.

[0137] As an example of the present invention, refer to Figure 3 As shown, Figure 1 The functional flow diagram of the muscle elasticity recovery module in this example includes the following functions:

[0138] S301: Calculating energy consumption increment based on the body metabolic gain intensity data to obtain body metabolic energy consumption increment data;

[0139] In the embodiment of the present invention, the metabolic gain intensity data of the body is obtained from the system, including the metabolic gain data at each time point, and the increment of energy consumption is calculated. First, the difference in metabolic gain intensity between adjacent time points is calculated, and numerical calculations are performed using the Python NumPy library.

[0140] S302: Analyzing muscle strength recovery effect based on the body metabolic energy consumption increment data and the body metabolic gain strength data to obtain muscle strength recovery effect data;

[0141] In an embodiment of the present invention, the body metabolic energy consumption increment data is combined with the body metabolic gain strength data to form an analysis data set. Ensure that the data set contains the time point, metabolic energy consumption increment and metabolic gain strength, and use regression analysis or correlation analysis methods to analyze the muscle strength recovery effect. Select an appropriate statistical analysis model, such as linear regression or multivariate regression, to calculate the relationship between the metabolic energy consumption increment and the body metabolic gain strength. Use the LinearRegression class in the Scikit-learn library of Python or the statsmodels library to perform regression analysis, and organize the results of the muscle strength recovery effect analysis into a data table, including statistical indicators such as regression coefficient and determination coefficient.

[0142] S303: Analyzing the muscle strength recovery effect data for the recovery synergy relationship between muscle groups to obtain muscle strength recovery synergy relationship data;

[0143] In an embodiment of the present invention, the recovery data of each muscle group is extracted from the muscle strength recovery effect data to ensure that the data set contains the recovery index of each muscle group, and the recovery synergistic relationship between different muscle groups is analyzed using correlation analysis or factor analysis methods. Statistical analysis methods, such as Pearson correlation coefficient or principal component analysis, are selected to evaluate the recovery effect relationship between different muscle groups. The PCA class or corrcoef function in the Scikit-learn library of Python is used to perform correlation analysis, and the recovery synergistic relationship between muscle groups is organized into a data table, and statistical information such as correlation coefficients or factor loadings is recorded. The data is saved as a CSV file or a database table using the Pandas library of Python to ensure the accuracy and completeness of the data.

[0144] S304: Calculating muscle elastic modulus recovery between different muscle groups based on the muscle strength recovery synergy relationship data to obtain muscle elastic modulus recovery data.

[0145] In an embodiment of the present invention, the muscle strength recovery synergistic relationship data and the muscle strength recovery effect data are combined to create an analysis data set containing the synergistic relationship and recovery effect between different muscle groups. The elastic modulus calculation formula is applied to calculate the muscle elastic modulus in combination with the muscle strength recovery effect data and the synergistic relationship data. The results of the muscle elastic modulus recovery calculation are organized into a data table, including the elastic modulus value of each muscle group and related statistical information.

[0146] Preferably, the muscle strength recovery effect analysis based on the body metabolic energy consumption increment data and the body metabolic gain strength data includes:

[0147] Performing body sign factor analysis on the body metabolic energy consumption increment data to obtain the metabolic energy consumption sign factor;

[0148] Based on the metabolic energy consumption sign factors and the body metabolic gain strength data, the metabolic index correlation calculation is performed to obtain the body metabolic index correlation data;

[0149] The muscle lactate clearance effect is simulated based on the body metabolic index correlation data to obtain the muscle lactate clearance effect data;

[0150] The lactate clearance half-life was calculated for the muscle lactate clearance effect data to obtain the lactate clearance half-life data;

[0151] The muscle strength recovery effect was analyzed based on the lactate clearance half-life data to obtain the muscle strength recovery effect data.

[0152] Preferably, analyzing the muscle strength recovery effect data to determine the recovery synergy relationship between muscle groups includes:

[0153] Performing similarity analysis on muscle group recovery behavior on muscle strength recovery effect data to obtain muscle group recovery behavior similarity data;

[0154] Based on the muscle group recovery behavior similarity data, non-parametric estimation of time-varying dynamic interaction is performed to obtain non-parametric time-varying dynamic interaction data;

[0155] Based on the non-parametric time-varying dynamic interaction data and the muscle group recovery behavior similarity data, a coordinated interaction causal chain analysis is performed to obtain the coordinated interaction causal chain data;

[0156] The coordinated interaction causal chain data is analyzed to analyze the recovery synergy relationship between muscle groups and obtain the muscle strength recovery synergy relationship data.

[0157] In an embodiment of the present invention, variable data related to physical signs are extracted from a data set of metabolic energy expenditure increments. The data should include the metabolic energy expenditure increment data at each time point, ensuring that the data is complete and has no missing values. The principal component analysis (PCA) method is used to extract physical sign factors. The PCA class in the Python Scikit-learn library is selected for factor analysis, and the number of principal components to be extracted is set. By calculating the factor loading of each variable, the main physical sign factors affecting metabolic energy expenditure are identified, and the physical sign factors and their loadings are recorded in a data table to show the degree of influence of each factor on metabolic energy expenditure. The results are saved as a CSV file using the Python Pandas library for subsequent analysis; the metabolic energy expenditure physical sign factor data are combined with the body metabolic gain strength data to create a comprehensive data set containing physical sign factors and metabolic gain data, and the correlation between metabolic indicators is calculated using the Pearson correlation coefficient or the Spearman rank correlation coefficient. The pearsonr or spearmanr function in the Python Scipy library is selected for calculation. The correlation coefficient between each physical sign factor and the metabolic gain strength is calculated, and the metabolic indicator correlation data is organized into a table including the correlation coefficient and significance level. Use Python's Pandas library to save the results as CSV files or database tables to ensure data clarity and usability. Build a simulation model for lactate clearance based on metabolic marker correlation data. Select a kinetic model (such as a one-compartment model or a multicompartment model) to simulate the lactate clearance process. Use the odeint function in Python's SciPy library or other numerical solvers to simulate the lactate clearance effect. Input the metabolic marker correlation data as model parameters, run the simulation to obtain muscle lactate clearance effect data, extract the time-varying lactate concentration data from the muscle lactate clearance effect data, and determine the optimal lactate clearance half-life parameters using methods such as least squares or maximum likelihood estimation. These parameters account for not only the biological clearance characteristics of lactate but also the influence of variables present in the hyperbaric oxygen recovery environment, such as the effects of air pressure and oxygen concentration on lactate metabolism rate. Combine the lactate clearance half-life data with muscle strength recovery effect data to form an analytical dataset. Use linear regression or multivariate regression models to evaluate the impact of lactate clearance half-life on muscle strength recovery effect. Use the LinearRegression class in the Python Scikit-learn library for regression analysis. Organize the muscle strength recovery analysis results into a data table, including statistical indicators such as regression coefficients and coefficients of determination. Extract recovery data for each muscle group from the muscle strength recovery data. Ensure that the dataset includes recovery indicators for each muscle group. Use cluster analysis or similarity analysis methods, such as K-means clustering or hierarchical clustering, to assess the similarity of recovery behavior among different muscle groups.The KMeans or AgglomerativeClustering classes in the Python Scikit-learn library were used for analysis. The muscle group recovery behavior similarity data were organized into a data table, recording the similarity score or classification results for each muscle group. The muscle group recovery behavior similarity data were then used for time-varying dynamic interaction analysis. A dynamic interaction model was constructed using time-series data. Time-varying nonparametric estimation methods, such as locally weighted regression (LOWESS) or kernel density estimation, were used to analyze the dynamic interactions between muscle groups. Nonparametric estimation was performed using the lowess function in the Python Statsmodels library. The nonparametric estimates of time-varying dynamic interactions were organized into a table, including the estimated interaction values ​​at each time point. The data were saved as a CSV file using the Python Pandas library to ensure the accuracy and systematicity of the results. The nonparametric time-varying dynamic interaction data were combined with the muscle group recovery behavior similarity data to form a comprehensive dataset containing both interaction relationships and behavioral similarities. Causal chain analysis methods, such as the Granger Causality Test, were then applied to assess the causal chains of coordinated interactions between muscle groups. The grangercausalitytests function in Python's Statsmodels library was used to perform causal chain analysis. The results of the coordinated interaction causal chain analysis were organized into a data table, including the strength and significance level of the causal chain relationship. The data were saved as a CSV file using Python's Pandas library to ensure data accuracy and availability. The coordinated interaction causal chain data were used to analyze the recovery synergy relationship between muscle groups. The synergy relationship analysis method was used to combine the coordinated interaction causal chain data to evaluate the recovery synergy relationship between different muscle groups. The networkx function in Python's NetworkX library was used to construct and analyze the synergy relationship network. The muscle strength recovery synergy relationship data were organized into a data table, including the synergy relationship between muscle groups and a network diagram. The data were saved as a CSV file using Python's Pandas library to ensure data accuracy and systematicity.

[0158] Preferably, performing muscle elastic modulus recovery calculation between different muscle groups on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data comprises:

[0159] According to the muscle strength recovery synergy relationship data, the elastic response analysis between different muscle groups is performed on the muscle strength recovery effect data to obtain the muscle elastic response data;

[0160] Conduct synergistic effect multilevel regression analysis on muscle elastic response data to obtain elastic response synergistic multilevel regression data;

[0161] Performing weighted processing on the responses of different muscle groups on the muscle elastic response data according to the elastic response collaborative multi-level regression data to obtain muscle elastic response weighted data;

[0162] According to the muscle elastic response weighted data, a multi-level weighted elastic response matrix is ​​constructed by coordinating the elastic response multi-level regression data to obtain a multi-level weighted elastic response matrix;

[0163] Based on the multi-level weighted elastic response matrix, the elastic response collaborative multi-level regression data were analyzed for muscle elastic activation dependency to obtain muscle elastic activation dependency data;

[0164] The muscle elastic modulus recovery calculation between different muscle groups is performed based on the muscle elastic activation dependency data to obtain the muscle elastic modulus recovery data.

[0165] In an embodiment of the present invention, muscle strength recovery effect data and muscle strength recovery synergistic relationship data are extracted from the system. Data integrity is ensured, including the recovery effect indicators of each muscle group and the synergistic recovery between muscle groups. For each muscle group, the elastic response is calculated based on the recovery effect data. The elastic response is usually obtained by analyzing the rate at which the recovery effect changes over time, and a suitable mathematical model (such as a linear regression model or a nonlinear regression model) is selected to describe the elastic characteristics of the recovery process. Data analysis tools such as pandas and statsmodels in Python, or the lm function in R language are used to perform regression analysis to obtain the elastic response data of each muscle group. A synergistic effect multilevel regression model is used to analyze the elastic response data to evaluate the synergistic effect between different muscle groups. The process involves establishing a multilevel regression model in which each level represents the recovery of a different muscle group and the synergistic recovery relationship between these groups. A suitable regression model is selected to process these hierarchical data, for example, using stepwise regression analysis or a mixed effects model to process the hierarchical relationship of muscle groups. Based on the model output, the synergistic effect data of the elastic response are extracted. These data reflect the impact of the interaction and synergistic effect between muscle groups on the overall recovery effect. Record these synergy parameters for subsequent weighting. Weight the elastic response data based on the elastic response synergy multilevel regression data. Determine the importance of each muscle group in the recovery process and weight the response data for each muscle group using a weighting coefficient. The weighting coefficient is based on the synergy results from the multilevel regression model to ensure that each muscle group's contribution to the overall recovery calculation is accurately represented. Aggregate the weighted elastic response data into a structured dataset to provide a foundation for subsequent matrix construction. This data can be organized and stored using a spreadsheet or database system. Use the weighted elastic response data to construct a multilevel weighted elastic response matrix. Organize the data into a matrix format based on muscle group and recovery level. Each row of the matrix represents a muscle group, and each column represents the weighted elastic response value for a level. Ensure that the matrix accurately reflects the elastic response of each muscle group at different stages of recovery. Optimize the constructed matrix to improve data accuracy and consistency. Matrix decomposition or regularization may be required to ensure that the matrix accurately represents the elastic recovery between muscle groups. Analyze muscle elastic activation dependencies based on the multilevel weighted elastic response matrix. This involves calculating the relationship between the elastic response and activation level of each muscle group and assessing the effect of activation on the elastic response. Appropriate statistical analysis methods, such as regression or correlation analysis, are selected to determine activation dependency. The muscle elasticity activation dependency data are compiled into a report documenting the activation dependency of each muscle group and its effect on the elastic response. This data can help understand how different muscle groups interact and depend on each other during recovery. The muscle elastic modulus recovery between different muscle groups is calculated based on the muscle elasticity activation dependency data.The activation-dependent data is applied to the elastic response matrix, weighted and adjusted to derive final elastic modulus values ​​for each muscle group. The calculated muscle elastic modulus recovery data is organized into a structured format for reporting and analysis. This data provides a snapshot of the recovery of each muscle group, enabling the development of personalized recovery plans and further analysis of muscle recovery outcomes.

[0166] Preferably, the body function improvement module includes the following functions:

[0167] Based on the multi-layer perceptron, the hyperbaric oxygen chamber recovery effect is perceived based on the body metabolic gain intensity data and muscle elastic modulus recovery data to obtain hyperbaric oxygen chamber recovery effect perception data;

[0168] Normalizing the hyperbaric oxygen chamber recovery effect perception data to obtain recovery effect perception normalized data;

[0169] The normalized data of recovery effect perception is used to evaluate the effect of improving body function, and the data of the effect of improving body function is obtained.

[0170] In an embodiment of the present invention, metabolic gain strength data and muscle elastic modulus recovery data are extracted from the system. The data source is ensured to be accurate and complete, including metabolic gain data and elastic modulus recovery at each time point. The extracted data is trained using a multilayer perceptron (MLP). MLP is a deep learning model capable of complex pattern recognition and data processing through a multi-layer neural network. The training process involves taking the metabolic gain data and elastic modulus data as input and training the model to identify patterns and characteristics of the hyperbaric oxygen chamber recovery effect. An appropriate training algorithm (such as backpropagation) and loss function (such as mean squared error) are selected, and hyperparameters are adjusted to optimize model performance. The trained MLP model is used to predict newly input data to obtain hyperbaric oxygen chamber recovery effect perception data. This data reflects the comprehensive recovery effect of the hyperbaric oxygen chamber on the patient. The data generation process involves passing the input data through each layer of the MLP model, ultimately outputting a perception result of the hyperbaric oxygen chamber recovery effect. The obtained hyperbaric oxygen chamber recovery effect perception data is normalized. The purpose of normalization is to convert data of different scales to the same range to facilitate subsequent analysis. Select an appropriate normalization method, such as min-max normalization, to scale the data to a range of 0 to 1. Perform data normalization using data processing tools (such as the skleam.preprocessing library in Python or the normalize function in MATLAB). Ensure that all sensory data are properly normalized to prevent data range differences from affecting subsequent analysis. Select an appropriate evaluation model to analyze the normalized recovery effect sensory data. Common evaluation models include statistical analysis models (such as regression analysis) and machine learning models (such as support vector machines or decision trees). When selecting a model, consider the characteristics of the data and the target evaluation metric. Input the normalized data into the selected evaluation model to calculate the improvement in physical function. This process includes model training (if necessary) and then performing predictions for each data point to obtain physical function improvement data. The evaluation process can use statistical analysis tools (such as the lm function in SPSS or R) or machine learning tools (such as Scikit-learn or TensorFlow). Record the physical function improvement data and conduct detailed analysis. Generate a report summarizing the analysis results and evaluating the overall improvement in the patient's physical function after the hyperbaric oxygen chamber. The report should include statistical descriptions and graphical presentations of the improvement effects to facilitate further understanding and decision-making.

[0171] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0172] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A patient hyperbaric oxygen chamber recovery effect analysis system based on big data, characterized in that: Includes the following modules: The physiological state grouping module is used to obtain the patient's physiological state data set before the treatment and the hyperbaric oxygen chamber operation state data; group the physiological state samples of the patient's physiological state data set before the treatment to obtain the physiological state grouping data before the treatment; extract the blood oxygen saturation before the treatment from the physiological state grouping data before the treatment to obtain the blood oxygen saturation grouping data before the treatment; The body metabolic gain analysis module is used to simulate the oxygen partial pressure increment difference of the blood oxygen saturation grouping data before the treatment according to the hyperbaric oxygen chamber operation status data to obtain the oxygen partial pressure increment difference simulation data; and to analyze the dynamic change of body oxygen concentration on the oxygen partial pressure increment difference simulation data to obtain the dynamic change data of body oxygen concentration; The body metabolic gain intensity is estimated according to the dynamic change data of body oxygen concentration to obtain body metabolic gain intensity data; wherein the body metabolic gain analysis module includes: Performing oxygen concentration phase-increasing pattern recognition on the hyperbaric oxygen chamber operation status data to obtain oxygen concentration increasing pattern data; The blood oxygen saturation differences between different groups were quantified based on the blood oxygen saturation grouping data before the treatment, and the blood oxygen saturation grouping difference quantitative data were obtained; According to the oxygen concentration increasing mode data, the oxygen partial pressure increment difference is simulated for the blood oxygen saturation group difference quantitative data to obtain the oxygen partial pressure increment difference simulation data; The dynamic change of body oxygen concentration is analyzed on the simulated data of oxygen partial pressure increment difference to obtain the dynamic change data of body oxygen concentration; The body metabolic gain strength is estimated according to the body oxygen concentration dynamic change data to obtain the body metabolic gain strength data; wherein, the body metabolic gain strength is estimated according to the body oxygen concentration dynamic change data including: Calculate the stage-by-stage change rate difference of the dynamic change data of the body's oxygen concentration to obtain the oxygen concentration stage change rate difference data; The oxygen molecule diffusion rate of each stage is calculated based on the oxygen concentration stage change rate difference data for the dynamic change data of the oxygen concentration in the body, and the oxygen molecule diffusion rate of each stage is obtained; The activity of body cells is evaluated according to the periodic oxygen molecule diffusion rate data to obtain the periodic body cell activity data; Based on the periodic oxygen molecule diffusion rate data and the periodic body cell activity data, the cell repair capacity is defined to obtain the periodic body cell repair capacity data; According to the staged body cell repair ability data, nonlinear regression analysis of cell metabolism was performed to obtain nonlinear regression data of cell metabolism; The nonlinear variance homogeneity calculation is performed on the cell metabolism nonlinear regression data to obtain the cell metabolism nonlinear variance homogeneity data; wherein the nonlinear variance homogeneity calculation on the cell metabolism nonlinear regression data includes: Perform nonlinear regression variance calculation on cell metabolism nonlinear regression data to obtain metabolic nonlinear regression variance data; According to the metabolic nonlinear regression variance data, nonlinear group fitting is performed on the cell metabolic nonlinear regression data to obtain metabolic nonlinear variance group fitting data; According to the metabolic nonlinear variance grouping fitting data, the variance grouping normal distribution analysis was performed on the cell metabolic nonlinear regression data to obtain the variance grouping normal distribution data; Based on the variance grouping normal distribution data, the normal distribution structure Levene's test was performed on the metabolic nonlinear variance grouping fitting data to obtain the normal distribution structure test data; Nonlinear variance homogeneity calculation was performed based on the normal distribution structure test data to obtain nonlinear variance homogeneity data of cell metabolism; The body metabolic gain intensity is estimated based on the nonlinear variance homogeneity data of cell metabolism to obtain the body metabolic gain intensity data; The muscle elasticity recovery module is used to analyze the muscle strength recovery effect based on the body metabolic gain strength data to obtain muscle strength recovery effect data; perform muscle elastic modulus recovery calculations between different muscle groups on the muscle strength recovery effect data to obtain muscle elastic modulus recovery data; wherein the muscle elasticity recovery module includes: Calculate the energy consumption increment according to the body metabolic gain intensity data to obtain the body metabolic energy consumption increment data; The muscle strength recovery effect analysis is performed based on the body metabolic energy consumption increment data and the body metabolic gain intensity data to obtain the muscle strength recovery effect data; wherein, the muscle strength recovery effect analysis based on the body metabolic energy consumption increment data and the body metabolic gain intensity data includes: Perform body sign factor analysis on the body metabolic energy consumption increment data to obtain metabolic energy consumption sign factors; Based on the metabolic energy consumption sign factors and the body metabolic gain strength data, the metabolic index correlation calculation is performed to obtain the body metabolic index correlation data; The muscle lactate clearance effect is simulated according to the body metabolic index correlation data to obtain the muscle lactate clearance effect data; The lactate clearance half-life was calculated for the muscle lactate clearance effect data to obtain the lactate clearance half-life data; The muscle strength recovery effect was analyzed based on the lactate clearance half-life data to obtain the muscle strength recovery effect data; The muscle strength recovery effect data is analyzed for the recovery synergy relationship between muscle groups to obtain the muscle strength recovery synergy relationship data; wherein, the muscle strength recovery effect data is analyzed for the recovery synergy relationship between muscle groups includes: Conducting similarity analysis of recovery behaviors among muscle groups on muscle strength recovery effect data to obtain similarity data of muscle group recovery behaviors; According to the muscle group recovery behavior similarity data, non-parametric estimation of time-varying dynamic interaction is performed to obtain non-parametric time-varying dynamic interaction data; Conduct coordinated interaction causal chain analysis based on non-parametric time-varying dynamic interaction data and muscle group recovery behavior similarity data to obtain coordinated interaction causal chain data; The coordinated interaction causal chain data is analyzed for the recovery synergy relationship between muscle groups to obtain the muscle strength recovery synergy relationship data; The muscle elastic modulus recovery calculation between different muscle groups is performed on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data to obtain the muscle elastic modulus recovery data; wherein, the muscle elastic modulus recovery calculation between different muscle groups is performed on the muscle strength recovery effect data according to the muscle strength recovery synergy relationship data includes: According to the muscle strength recovery synergy relationship data, the elastic response analysis between different muscle groups is performed on the muscle strength recovery effect data to obtain the muscle elastic response data; Conduct synergistic effect multilevel regression analysis on muscle elastic response data to obtain elastic response synergistic multilevel regression data; According to the elastic response coordinated multi-level regression data, the muscle elastic response data is weighted for the responses of different muscle groups to obtain the muscle elastic response weighted data; According to the muscle elastic response weighted data, a multi-level weighted elastic response matrix is ​​constructed for the elastic response coordinated multi-level regression data to obtain a multi-level weighted elastic response matrix; Based on the multi-level weighted elastic response matrix, the elastic response coordinated multi-level regression data is analyzed for muscle elastic activation dependency to obtain muscle elastic activation dependency data; The muscle elastic modulus recovery calculation between different muscle groups is performed according to the muscle elastic activation dependency data to obtain the muscle elastic modulus recovery data; The body function improvement module is used to evaluate the body function improvement effect on the body metabolic gain intensity data and the muscle elastic modulus recovery data based on a multi-layer perceptron to obtain the body function improvement effect data; wherein the body function improvement module includes: Based on the multi-layer perceptron, the hyperbaric oxygen chamber recovery effect is perceived based on the body metabolic gain intensity data and the muscle elastic modulus recovery data to obtain the hyperbaric oxygen chamber recovery effect perception data; Normalizing the hyperbaric oxygen chamber recovery effect perception data to obtain recovery effect perception normalized data; The normalized data of recovery effect perception is used to evaluate the effect of improvement on body function, and the data of the effect of improvement on body function is obtained.

2. The patient hyperbaric oxygen chamber recovery effect analysis system based on big data according to claim 1 is characterized in that: The physiological state grouping module includes the following functions: Obtain the patient's physiological status data set before treatment and the hyperbaric oxygen chamber operation status data; Preprocessing the patient's physiological state data set before the treatment to obtain preprocessed physiological state data before the treatment; According to the pre-treatment physiological state pre-processing data, the patient's pre-treatment physiological state data set is grouped into physiological state samples to obtain pre-treatment physiological state grouping data; The pre-treatment blood oxygen saturation is extracted from the pre-treatment physiological status grouping data to obtain the pre-treatment blood oxygen saturation grouping data.

Images