Energy metabolism analysis and patient information integration method and system

Abstract

The invention relates to the technical field of health information processing, in particular to an energy metabolism analysis and patient information integration method and system.The energy metabolism analysis and patient information integration method comprises the following steps that on the basis of metabolic rate data and blood detection indexes, classification matching is conducted on local deviation of the metabolic rate and distribution characteristics of biochemical indexes in blood detection; and extracting statistical characteristics in the local abnormal region, and analyzing the correlation change between the metabolic migration and the biochemical indexes. According to the method, potential health risks are revealed through dynamic correlation analysis of metabolic migration characteristic values and blood detection indexes, accurate capture of dynamic physiological changes is achieved in combination with correlation evaluation of vital sign fluctuation data and exercise intensity in the time period, and the dynamic physiological changes are accurately captured through stratified analysis of causal paths and high-frequency health risk parameter adjustment. The accuracy and layering of health risk identification are improved, the nutritional ingredient proportion is optimized to match metabolic requirements, the food intake range is adjusted, personalized diet recommendation is generated through data comparison, and the individual health management requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of health information processing, and in particular to a method and system for integrating energy metabolism analysis and patient information. Background Art

[0002] The field of health information processing technology includes technical methods for managing, storing, analyzing and exchanging medical and health data using information technology. The core content of this technology field includes the efficient management and processing of medical data to support medical decision-making and health service optimization. Its overall technical field mainly covers the establishment and management of electronic medical records, the implementation of health information exchange technology, the application of big data technology in the medical field, and the application of artificial intelligence technology in diagnosis, prediction and treatment. Through the systematic collection and analysis of patient data, this technology field has played an important role in improving medical quality, optimizing medical efficiency and rationally allocating medical resources.

[0003] Among them, the energy metabolism analysis and patient information integration method refers to a technical method that integrates patient energy metabolism data with other patient information. This method mainly targets the specific technical matter of energy metabolism analysis, covering the collection, standardization, dynamic change analysis of patient energy metabolism data, and the correlation and integration with patient medical history, diagnostic data, and vital signs data. Based on the collected energy metabolism data, the metabolic characteristics are associated with the patient's health information through classification, filtering and analysis of the data to build a comprehensive health assessment model. This method is usually completed through the application technology in the field of health information processing, including the storage, dynamic monitoring and processing of health data, and the integrated analysis of multidimensional data, ultimately achieving a comprehensive assessment and application support for the patient's metabolic health.

[0004] Existing technologies for analyzing energy metabolism data mostly remain at a static and isolated level, lacking dynamic associations with blood tests and physiological parameters, making it difficult to accurately identify potential risks. In vital sign monitoring, the dynamic relationship between time periods and exercise status is often ignored, which may lead to the omission of key health information. Dietary optimization is mostly based on universal recommendations, which are not combined with individual metabolic needs and are difficult to support personalized health management. The above shortcomings limit the depth of health assessments and the accuracy of medical services, affecting decision-making effectiveness and the rational allocation of resources. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an energy metabolism analysis and patient information integration method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for energy metabolism analysis and patient information integration, comprising the following steps:

[0007] S1: Based on metabolic rate data and blood test indicators, the local deviation of metabolic rate and the distribution characteristics of biochemical indicators in blood tests are classified and matched, the statistical characteristics in the local abnormal area are extracted, the correlation changes between metabolic deviation and biochemical indicators are analyzed, and the metabolic deviation characteristic value is generated;

[0008] S2: Based on the metabolic shift characteristic value, the heart rate and blood pressure in the vital sign parameters are analyzed for a time period, the fluctuation data at key time points are extracted, the correlation between exercise intensity and heart rate data is evaluated, the weight of the fluctuation data is adjusted, and the dynamic trend value of the vital sign is generated;

[0009] S3: Based on the dynamic trend value of the vital signs, the metabolic deviation characteristic value and the distribution value of the health risk causal node are matched and analyzed, the causal node value between the dynamic data of the vital signs and the metabolic rate characteristics is extracted, the frequency distribution of the key risk parameters in the causal path is hierarchically evaluated, the weight data of the high-frequency risk causal path is range-adjusted, and the health risk causal path coefficient is generated;

[0010] S4: Based on the health risk causal path coefficient, adjust the proportion of dietary ingredients, match the nutritional ingredients with metabolic needs, analyze the correlation between nutritional distribution and health risks, optimize the dietary structure intake data into a segmented recommended value range, and generate a nutritional recommendation distribution ratio;

[0011] S5: Based on the recommended nutritional distribution ratio, adjust the recommended range of food intake, analyze the matching of food data with health status, adjust the upper and lower limits of intake, compare the dietary intake data with the metabolic requirement value, and generate personalized dietary intake recommendation values.

[0012] The metabolic deviation characteristic values ​​specifically include the statistical characteristics of local abnormal areas, the associated changes of biochemical indicators, and the metabolic rate distribution characteristics. The dynamic trend values ​​of vital signs include heart rate fluctuation data, blood pressure fluctuation data, and exercise intensity correlation assessment. The health risk causal path coefficient specifically refers to the frequency distribution of key risk parameters, high-frequency risk path weight adjustment, and health risk stratification assessment. The nutritional recommendation distribution ratio includes the matching degree of nutritional components, the correlation between nutritional distribution and health risks, and the adjustment range of dietary components. The personalized dietary intake recommendation value specifically includes the recommended range of food intake, the matching of health status and food data, and the comparison of metabolic demand parameters.

[0013] As a further solution of the present invention, the step of obtaining the metabolic deviation characteristic value is specifically as follows:

[0014] S101: extracting local offset regions based on metabolic rate data, determining whether the local change amplitude in the metabolic rate data exceeds a dynamic threshold, calculating the change rate interval within the dynamic threshold, and marking the local offset regions to obtain distribution characteristics of the local metabolic offset regions;

[0015] S102: calling the local metabolic deviation regional distribution characteristics, combining the biochemical data of the blood test index, calculating the characteristic change interval of the biochemical index according to the distribution mean and variance of each biochemical index, and judging whether the biochemical data in the local metabolic deviation region deviates from the characteristic change interval, and extracting the characteristic data of the local abnormal region by matching the local regional characteristics and the biochemical index distribution deviation characteristics;

[0016] S103: calling the characteristic data of the local abnormal area, setting the distribution function of the correlation change between the metabolic rate and the biochemical index, and fitting the deviation value of the biochemical index and the metabolic rate, using the formula:

[0017]

[0018] Calculate and generate metabolic shift characteristic values;

[0019] Among them, C f Represents the metabolic shift characteristic value, ΔM i is the local offset of the ith metabolic rate, ΔB i is the deviation value of the i-th blood test index, W i is the weight factor of the i-th data, and n is the number of statistical samples in the local abnormal area.

[0020] As a further solution of the present invention, the step of obtaining the dynamic trend value of the vital signs is specifically as follows:

[0021] S201: Using the metabolic shift characteristic value, marking the key time points of the heart rate and blood pressure of the vital sign data, identifying the time points when the fluctuation value exceeds the dynamic threshold by analyzing the time series distribution law of the heart rate and blood pressure, and classifying and marking the key points according to the fluctuation characteristics to obtain the key fluctuation data of the heart rate and blood pressure;

[0022] S202: calling the key fluctuation data of the heart rate and blood pressure, combining the correlation between the exercise intensity data and the heart rate data, calculating the correlation coefficient between the exercise intensity and the heart rate, and screening the heart rate fluctuation characteristics within the differentiated exercise intensity range, and obtaining an adjusted fluctuation data weight set by adjusting the fluctuation characteristic weight matching data to show the mutual change trend;

[0023] S203: Using the adjusted volatility data weight set and combining it with the time series analysis model, the formula is:

[0024]

[0025] Calculate and obtain dynamic trend values ​​of vital signs;

[0026] Among them, T d Represents the dynamic trend value of vital signs, w t Represents the weight adjustment coefficient at time point t, HR t Represents the heart rate data at time point t, BP t Represents the blood pressure data at time point t, numerator | HR t -BP t | is the absolute difference between heart rate and blood pressure at time point t, the denominator (HR t +BP t ) is the sum of heart rate and blood pressure at time point t, which is used for normalization, and T represents the total time step of the time series.

[0027] As a further solution of the present invention, the steps for obtaining the health risk causal path coefficient are specifically as follows:

[0028] S301: Based on the dynamic trend value of the vital signs, the metabolic deviation characteristic value is matched with the distribution value of the health risk causal node, the causal node between the dynamic trend value and the metabolic rate characteristic is extracted, and the causal association node of the health risk is located by identifying the characteristic value range of multiple causal associations in the node distribution, and the preliminary matching causal node data is obtained;

[0029] S302: calling the preliminary matched causal node data, screening the causal nodes through statistical analysis, using partial correlation analysis between nodes to determine the correlation between metabolic rate and dynamic vital signs, and calculating the correlation coefficient between the causal nodes, re-ordering the screened nodes according to the correlation size, and establishing a causal node value distribution map;

[0030] S303: using the causal node numerical distribution diagram, extracting key risk parameters, statistically analyzing the frequency distribution of multiple parameters, clustering the key risk parameters of the frequency distribution using hierarchical evaluation technology, and generating preliminary weight data of high-frequency risk causal paths;

[0031] S304: Call the preliminary weight data of the high-frequency risk causal path, and adjust the range according to the causal node weight distribution, using the formula:

[0032]

[0033] Calculate and generate health risk causal path coefficients;

[0034] Among them, R c represents the causal path coefficient of health risk, w i represents the weight of the ith risk factor, x irepresents the value of the i-th causal node, μ represents the mean value of the causal node, σ represents the standard deviation of the causal node value, n represents the total number of causal nodes, and exp is an exponential function used to dynamically adjust the weight distribution.

[0035] As a further solution of the present invention, the step of obtaining the recommended nutrition distribution ratio is specifically as follows:

[0036] S401: using the health risk causal path coefficient, preliminarily adjusting the dietary component ratio, analyzing the correlation between the nutritional components and the health risk according to the matching degree between the nutritional components and the metabolic requirements, and determining the dietary component range that needs to be adjusted by comparing the nutritional component intake standard with the correlation data of the health risk factors, and obtaining the adjusted dietary component data;

[0037] S402: calling the adjusted dietary component data, analyzing the correlation between multiple components and health risks, calculating the risk contribution of multiple nutritional components through statistical analysis methods, and iteratively adjusting the dietary component ratio based on the risk contribution, determining the recommended intake of each component, and generating refined dietary component recommendation data;

[0038] S403: Using the refined dietary component recommendation data, the distribution of multiple nutrients is optimized through a nutritional model using the formula:

[0039]

[0040] Optimize the intake data of dietary structure and generate the recommended distribution ratio of nutrition;

[0041] Among them, P n represents the recommended distribution ratio of nutrition, α i is the adjustment factor for the ith nutrient, taking into account the criticality of the risk factor and the variability of the nutrient content in the food, v i is the target intake of the ith nutrient, s i is the standard intake and m is the total number of nutrients.

[0042] As a further solution of the present invention, the steps for obtaining the personalized dietary intake recommendation value are specifically as follows:

[0043] S501: Analyze and adjust the recommended range of food intake based on the recommended nutritional distribution ratio, match the nutritional components with the metabolic needs, identify the food data most related to the health status, and obtain an adjusted recommended range of food intake by dynamically adjusting the upper and lower limits of food intake;

[0044] S502: calling the adjusted recommended food intake range, analyzing the matching of multiple nutrients with health status, determining the suitability of the intake by comparing the actual intake of nutrients with the recommended intake, and generating optimized dietary intake data;

[0045] S503: Compare the optimized dietary intake data with the metabolic demand value using the formula:

[0046]

[0047] Adjust the upper and lower limits of intake, combine the intake deviation of each ingredient with the standard deviation of the recommended amount, and calculate the personalized dietary intake recommendation value;

[0048] Among them, R d represents the recommended value of personalized dietary intake, c j is the adjustment coefficient of the jth food component, taking into account its sensitivity and individual differences in metabolic effects, Δm j is the intake deviation of the jth food component, s j is the standard deviation of the recommended intake to reflect the differences in intake between individuals, ∈ is a small constant to avoid the situation where the denominator is zero, and k is the total number of food ingredients.

[0049] An energy metabolism analysis and patient information integration system, the energy metabolism analysis and patient information integration system is used to perform the above energy metabolism analysis and patient information integration method, the system comprises:

[0050] The metabolic shift analysis module is based on metabolic rate data and blood test indicators. It extracts local shift information from metabolic rate data, extracts biochemical distribution characteristics from blood test indicators, calculates the correlation between the two, analyzes the statistical characteristics in the local abnormal area, and generates metabolic shift characteristic values.

[0051] The vital signs trend analysis module analyzes the volatility of differentiated time periods based on the metabolic shift characteristic value and combines the heart rate and blood pressure data, and adjusts the weight of the fluctuation data through the correlation evaluation between the heart rate data and the exercise intensity to generate the dynamic trend value of the vital signs;

[0052] The health risk causal assessment module matches the distribution of metabolic deviation characteristic values ​​and health risk causal nodes based on the dynamic trend values ​​of the vital signs, analyzes the causal node values ​​between the vital signs and the metabolic rate characteristics, performs a hierarchical assessment of the key risk parameters in the causal path, adjusts the weight data, and generates a health risk causal path coefficient;

[0053] The nutrition optimization distribution module analyzes the matching between the dietary component ratio and the metabolic demand based on the health risk causal path coefficient, adjusts the dietary component ratio to the optimal range, and generates a nutrition recommendation distribution ratio;

[0054] The dietary intake recommendation module analyzes the relationship between food intake and health status based on the recommended nutrient distribution ratio, adjusts the upper and lower limits of food intake, compares and matches parameters with the metabolic demand value, and generates personalized dietary intake recommendation values.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are:

[0056] In the present invention, through the dynamic correlation analysis of metabolic deviation characteristic values ​​and blood test indicators, potential health risks can be revealed, and combined with the correlation evaluation of vital sign fluctuation data and exercise intensity in time periods, accurate capture of dynamic physiological changes can be achieved. Through hierarchical analysis of causal paths and adjustment of high-frequency health risk parameters, the accuracy and hierarchy of health risk identification are improved. The proportion of nutrients is optimized to match metabolic needs, and the range of food intake is adjusted. Personalized diet recommendations are generated through data comparison to meet individual health management needs. Multi-dimensional dynamic data integration and in-depth analysis enhance the scientific nature of health assessment and promote the precision and comprehensiveness of health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0058] Figure 2 A flow chart of the steps for obtaining the metabolic deviation characteristic value of the present invention;

[0059] Figure 3 This is a flow chart of the steps for obtaining the dynamic trend value of vital signs of the present invention;

[0060] Figure 4 A flowchart of steps for obtaining the causal path coefficient of health risk of the present invention;

[0061] Figure 5 A flow chart of the steps for obtaining the recommended nutrient distribution ratio of the present invention;

[0062] Figure 6 This is a flow chart of the steps for obtaining the personalized dietary intake recommendation value of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0064] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0065] Embodiment 1

[0066] See also Figure 1 The present invention provides a technical solution: a method for integrating energy metabolism analysis and patient information, comprising the following steps:

[0067] S1: Based on metabolic rate data and blood test indicators, the local deviation of metabolic rate and the distribution characteristics of biochemical indicators in blood tests are classified and matched, the statistical characteristics in the local abnormal area are extracted, the correlation changes between metabolic deviation and biochemical indicators are analyzed, and the metabolic deviation characteristic value is generated;

[0068] S2: Based on the metabolic shift characteristic value, the heart rate and blood pressure in the vital sign parameters are analyzed for a certain period of time, the fluctuation data at key time points are extracted, the correlation between exercise intensity and heart rate data is evaluated, the weight of the fluctuation data is adjusted, and the dynamic trend value of the vital sign is generated;

[0069] S3: Based on the dynamic trend values ​​of vital signs, match and analyze the distribution values ​​of metabolic deviation characteristic values ​​and health risk causal nodes, extract the causal node values ​​between the dynamic data of vital signs and metabolic rate characteristics, conduct hierarchical evaluation on the frequency distribution of key risk parameters in the causal path, adjust the range of weight data of high-frequency risk causal paths, and generate health risk causal path coefficients;

[0070] S4: Based on the causal path coefficient of health risk, adjust the proportion of dietary ingredients, match the nutritional ingredients with metabolic needs, analyze the correlation between nutritional distribution and health risks, optimize the dietary structure intake data into a segmented recommended value range, and generate the recommended nutritional distribution ratio;

[0071] S5: Based on the recommended nutrient distribution ratio, adjust the recommended range of food intake, analyze the matching between food data and health status, adjust the upper and lower limits of intake, compare the dietary intake data with the metabolic requirement value, and generate personalized dietary intake recommendation values.

[0072] The characteristic values ​​of metabolic deviation specifically include the statistical characteristics of local abnormal areas, the correlation changes of biochemical indicators, and the distribution characteristics of metabolic rate. The dynamic trend values ​​of vital signs include heart rate fluctuation data, blood pressure fluctuation data, and exercise intensity correlation assessment. The health risk causal path coefficient specifically refers to the frequency distribution of key risk parameters, high-frequency risk path weight adjustment, and health risk stratification assessment. The nutritional recommendation distribution ratio includes the matching degree of nutritional components, the correlation between nutritional distribution and health risks, and the adjustment range of dietary components. The personalized dietary intake recommendation value specifically includes the recommended range of food intake, the matching of health status and food data, and the comparison of metabolic demand parameters.

[0073] See also Figure 2 , the specific steps for obtaining the metabolic shift characteristic value are:

[0074] S101: extracting local offset regions based on metabolic rate data, determining whether the local change amplitude in the metabolic rate data exceeds a dynamic threshold, calculating the change rate interval within the dynamic threshold, and marking the local offset regions to obtain distribution characteristics of the local metabolic offset regions;

[0075] Analyze the local variation range in the metabolic rate data. By sampling the metabolic rate data in segments, calculate the variation range in each segment as the offset index. The specific implementation process is to first divide the metabolic rate time series into multiple equal-length intervals, and calculate the differential data in each interval in a sliding window manner. The sliding window length is dynamically adjusted according to the metabolic rate time resolution. The standard deviation of the differential value in the interval is calculated as the variation range, which is further compared with the dynamically set threshold. The dynamic threshold is constructed using the full sample mean and twice the standard deviation, that is, the threshold formula is: in is the mean of the entire sample, σ M is the standard deviation of the whole sample. When the change amplitude exceeds the threshold, it is marked as an offset area. The marking method is based on the indicative function x i Indicates that if |ΔM i |>T, then x i =1, otherwise x i =0, the local metabolic deviation regional distribution characteristics are generated according to the distribution characteristics of the deviation region.

[0076] S102: calling the local metabolic deviation regional distribution characteristics, combining the biochemical data of the blood test index, calculating the characteristic change interval of the biochemical index according to the distribution mean and variance of each biochemical index, and judging whether the biochemical data in the local metabolic deviation region deviates from the characteristic change interval, and extracting the characteristic data of the local abnormal region by matching the local regional characteristics and the biochemical index distribution deviation characteristics;

[0077] Analyze the distribution characteristics of biochemical indicators in the metabolic deviation area. First, classify the sample values ​​of each biochemical indicator into normal range and abnormal range according to the biochemical data of blood test indicators. The specific steps are to calculate the mean and standard deviation of each indicator and set its normal range according to the formula The abnormal interval is not in B norm The deviation degree of the distribution of biochemical indicators of each sample is calculated by calculating the distance from the sample value to the upper and lower limits of the interval. The formula is: The distribution deviation values ​​of all biochemical indicators are matched with the marker values ​​of the local metabolic deviation area, and the characteristic data of the local abnormal area are extracted through the matching results.

[0078] S103: calling the characteristic data of the local abnormal area, setting the distribution function of the correlation change between the metabolic rate and the biochemical index, and fitting the deviation value of the biochemical index and the metabolic rate, using the formula:

[0079]

[0080] Calculate and generate metabolic shift characteristic values;

[0081] Among them, C f Represents the metabolic shift characteristic value, ΔM i is the local offset of the ith metabolic rate, ΔB i is the deviation value of the i-th blood test index, W i is the weight factor of the i-th data, and n is the number of statistical samples in the local abnormal area.

[0082] formula:

[0083]

[0084] The benefit of the formula is that, by introducing the combined effects of metabolic rate offset value, biochemical index deviation value and weight factor, it realizes the joint evaluation of local metabolic abnormality area and abnormal distribution of biochemical index, and at the same time improves the flexibility and accuracy of calculation by adjusting the weight factor.

[0085] Detailed explanation of the formula and the process of formula calculation and derivation:

[0086] ΔM i represents the local offset of the ith metabolic rate, which is calculated by the above steps and is the sliding window difference result. Assume that ΔM1 = 0.8, ΔM2 = 1.2, ΔM3 = 0.6, and the unit is the change of a certain metabolic rate;

[0087] ΔB iIt represents the deviation value of the i-th blood test index, which is calculated by the biochemical index distribution deviation formula, assuming that ΔB1=0.9, ΔB2=0.7, ΔB3=1.1, and the unit is the deviation of a specific biochemical index;

[0088] W i is the weight factor of the i-th data, which is set according to the historical correlation between biochemical indicators and metabolic rate in the local abnormal area. The weight setting is based on the degree of historical correlation, assuming that W1 = 0.5, W2 = 0.3, and W3 = 0.2;

[0089] Substituting the above values ​​into the formula:

[0090]

[0091] C f =0.744;

[0092] The results show that the metabolic deviation characteristic value is 0.744, which represents the comprehensive degree of deviation of local metabolic rate and biochemical index distribution. This value is related to the result in the step in that it provides a joint evaluation result, providing a quantifiable basis for subsequent analysis.

[0093] See also Figure 3 ,The specific steps for obtaining the dynamic trend value of vital signs are:

[0094] S201: Using metabolic shift characteristic values, marking key time points of the heart rate and blood pressure of the vital signs data, identifying time points when the fluctuation value exceeds the dynamic threshold by analyzing the time series distribution law of the heart rate and blood pressure, and classifying and marking key points according to the fluctuation characteristics to obtain key fluctuation data of the heart rate and blood pressure;

[0095] Based on the heart rate and blood pressure collected values ​​at each time point in the metabolic rate data, point-by-point screening is performed to determine whether the fluctuations in heart rate and blood pressure exceed the dynamic threshold of the historical distribution. The threshold is set to the interval of the mean within the normal range of heart rate and blood pressure plus or minus 3 times the standard deviation. The time point when the fluctuation exceeds the threshold is determined through point-by-point analysis, and the absolute value and change trend of the fluctuation amplitude are calculated. These time points are marked as key fluctuation points, and the change data of heart rate and blood pressure are recorded within the key time points. At the same time, the change in fluctuation amplitude in different time intervals is calculated in segments, and the locations where peaks and troughs appear in the data are marked as significant change points. According to the marking results, the time positions of the key fluctuation points and their corresponding heart rate and blood pressure data characteristics are summarized to obtain the key fluctuation data of heart rate and blood pressure.

[0096] S202: calling the key fluctuation data of heart rate and blood pressure, combining the correlation between exercise intensity data and heart rate data, calculating the correlation coefficient between exercise intensity and heart rate, and screening the heart rate fluctuation characteristics within the differentiated exercise intensity range, and obtaining an adjusted fluctuation data weight set by adjusting the fluctuation characteristic weight to match the mutual change trend between the data;

[0097] Extract the correlation between exercise intensity data and heart rate data, calculate the correlation coefficient between exercise intensity and heart rate point by point, first calculate the time series distribution trend of exercise intensity, divide it into different intervals according to the time period of exercise intensity change, and then calculate the linear correlation coefficient between heart rate and exercise intensity in each time interval, using the formula in is the mean exercise intensity, is the mean of heart rate, the numerator is the covariance of the two, and the denominator is the product of their standard deviations. The correlation strength in different intervals is calculated, and then the correlation results of each interval are used to adjust the fluctuation weights of heart rate and blood pressure. The weight ratio of key fluctuation points is dynamically adjusted according to the high and low range of exercise intensity, and the time period corresponding to the fluctuation data and exercise intensity data after weight adjustment is recalibrated to obtain the adjusted fluctuation data weight set.

[0098] S203: Using the adjusted volatility data weight set, combined with the time series analysis model, the formula is:

[0099]

[0100] Calculate and obtain dynamic trend values ​​of vital signs;

[0101] Among them, T d Represents the dynamic trend value of vital signs, w t Represents the weight adjustment coefficient at time point t, HR t Represents the heart rate data at time point t, BP t Represents the blood pressure data at time point t, numerator | HR t -BP t | is the absolute difference between heart rate and blood pressure at time point t, the denominator (HR t +BP t ) is the sum of heart rate and blood pressure at time point t, which is used for normalization, and T represents the total time step of the time series.

[0102] formula:

[0103]

[0104] The benefit of the formula is that by introducing the absolute difference and normalization calculation of the heart rate and blood pressure fluctuations at the time point, the fluctuation intensity can be adjusted within the dynamic range, and the time point weight adjustment factor wt The introduction of increases the flexible control over the importance distribution of data in different time periods, so that the overall calculation can more accurately reflect the dynamic trend of vital signs.

[0105] Detailed explanation of the formula and the process of formula calculation and derivation:

[0106] Set the time series range T = 5, weight adjustment factor w t They are [1.2, 0.8, 1.0, 1.1, 0.9] respectively, and the heart rate HR t The data is [80,85,90,95,88], blood pressure BP t The data is [120, 125, 118, 130, 122]. Substitute it into the formula and calculate step by step as follows:

[0107] Time point 1: After adjusting the weight, w1×0.447=1.2×0.447=0.5364;

[0109] Time point 2: After adjusting the weights, w2×0.4364=0.8×0.4364=0.3491;

[0110] Time point 3: After adjusting the weight, w3×0.3669=1.0×0.3669=0.3669;

[0111] Time point 4: After adjusting the weight, w4×0.3945=1.1×0.3945=0.4339;

[0112] Time point 5: After adjusting the weight, w5×0.4024=0.9×0.4024=0.3622;

[0113] Sum up the results at all time points:

[0114] T d =0.5364+0.3491+0.3669+0.4339+0.3622=2.0485.

[0115] The results show that the dynamic trend value of vital signs T d =2.0485 reflects the overall trend strength of heart rate and blood pressure fluctuations in the current time series. Combined with the adjusted weight factor, a dynamic distribution evaluation of the changes in different time periods is performed.

[0116] See also Figure 4 , the specific steps for obtaining the causal path coefficient of health risk are:

[0117] S301: Based on the dynamic trend value of the vital signs, match the metabolic deviation characteristic value with the distribution value of the health risk causal node, extract the causal node between the dynamic trend value and the metabolic rate characteristic, locate the causal association node of the health risk by identifying the characteristic value range of multiple causal associations in the node distribution, and obtain preliminary matching causal node data;

[0118] By analyzing the time series characteristics of the dynamic trend values ​​of vital signs, the dynamic trend values ​​are decomposed into daily fluctuation change sequences and weekly fluctuation change sequences. The heart rate and blood pressure data are used as key factors for the daily fluctuation characteristics. By comparing the deviation rate between the daily fluctuation maximum value and the average value, the time nodes corresponding to the abnormal values ​​are screened to obtain the daily key causal nodes. For the weekly fluctuation change sequence, the repeated distribution within the fluctuation range of heart rate and blood pressure is analyzed to determine the periodicity of high-frequency change nodes. Combining the above-mentioned daily key causal nodes with the weekly fluctuation change law, these causal nodes are classified, and causal nodes with consistency or significant abnormalities are extracted. Finally, combined with the metabolic offset characteristic value, the distribution characteristics of the causal nodes are analyzed to determine whether these nodes are associated with the health risk causal nodes. By judging whether the offset direction of the metabolic rate characteristic value between nodes is consistent with the change direction of the dynamic trend value of the causal node, the qualified nodes are screened and marked as preliminary matching causal nodes to obtain preliminary matching causal node data.

[0119] S302: calling the preliminary matched causal node data, screening the causal nodes through statistical analysis, using the partial correlation analysis between nodes to determine the correlation between the metabolic rate and the dynamic vital signs, and calculating the correlation coefficient between the causal nodes, re-ordering the screened nodes according to the correlation size, and establishing a causal node value distribution map;

[0120] By calculating the correlation of the heart rate and blood pressure characteristic data of all preliminary matched causal nodes, the fluctuation amplitude and change rate of the heart rate and blood pressure characteristics at different time points are analyzed, and the fluctuation characteristics of the causal nodes are compared with the change characteristics of the metabolic offset characteristic values ​​through partial correlation analysis. The nodes with larger correlation coefficients in the causal nodes are screened out as high-correlation causal nodes, and these high-correlation causal nodes are further stratified. According to the concentration of key time periods in the node distribution, the time distribution characteristics of the high-correlation nodes are analyzed, and the concentrated distribution segments in the causal nodes are extracted. The correlation weight of each causal node is calculated based on the statistical data of the concentrated segments, and the weight values ​​are sorted. The correlation distribution diagram of the causal nodes is generated and the screened high-correlation nodes are marked to establish the causal node numerical distribution diagram.

[0121] S303: Using the causal node numerical distribution diagram, extracting key risk parameters, statistically analyzing the frequency distribution of multiple parameters, clustering the key risk parameters of the frequency distribution using hierarchical evaluation technology, and generating preliminary weight data of high-frequency risk causal paths;

[0122] The highly correlated node information in the distribution map is called to extract the key risk parameters in the causal path, and the frequency distribution of the key risk parameters is statistically analyzed. Based on the data concentration in the statistical distribution, a hierarchical evaluation is performed on the high-frequency distribution points of each key risk parameter to screen out key parameters with high frequency values ​​and narrow fluctuation ranges. Cluster analysis is performed on the screened key parameters to analyze the fluctuation characteristics of each high-frequency distribution key parameter. According to the distribution position and fluctuation range of these key parameters, a frequency distribution matrix of each risk causal path is established, and the key distribution areas in the matrix are marked as high-frequency risk causal paths. At the same time, weighted calculations are performed on the key parameters in these paths. The weight values ​​are calculated based on the high-frequency occurrence value of each parameter in the risk path and its fluctuation characteristics. The weight values ​​are adjusted in range to generate preliminary weight data for high-frequency risk causal paths.

[0123] S304: Call the preliminary weight data of the high-frequency risk causal path, and adjust the range according to the weight distribution of the causal nodes, using the formula:

[0124]

[0125] Calculate and generate health risk causal path coefficients;

[0126] Among them, R c represents the causal path coefficient of health risk, w i represents the weight of the ith risk factor, x i represents the value of the i-th causal node, μ represents the mean value of the causal node, σ represents the standard deviation of the causal node value, n represents the total number of causal nodes, and exp is an exponential function used to dynamically adjust the weight distribution.

[0127] formula:

[0128]

[0129] The benefit of the formula is that it dynamically adjusts the weight parameters by introducing the normal distribution function, combines the distribution characteristics of each causal node, and processes it through a dynamic smoothing function, so that the weight distribution is more in line with the actual situation of the node value, reducing the impact of extreme values ​​on the results.

[0130] Detailed explanation of the formula and the process of formula calculation and derivation:

[0131] First, define and obtain all parameter values ​​in the formula. i is the weight of the ith risk factor, calculated by the high-frequency distribution characteristics of the causal node, x iis the value of the i-th causal node, which is determined by monitoring the dynamic trend value of vital signs and the changing characteristics of metabolic rate characteristics, μ is the average value of the causal node, which is obtained by calculating the mean of all node values, σ is the standard deviation of the causal node value, which is obtained by calculating the standard deviation of all node values, and n is the total number of causal nodes, which is obtained by counting all the screened causal nodes;

[0132] Assume that the total number of monitored causal nodes is 5, namely 30, 35, 40, 45, and 50, and the weight w i They are 0.2, 0.25, 0.15, 0.3, and 0.1, respectively. The average value μ is 40, and the standard deviation σ is 7.07. Then substitute it into the formula for calculation:

[0133]

[0134] Calculate each term in turn:

[0135]

[0136] R c =0.2·e -1 +0.25 e -0.25 +0.15·1+0.3·e -0.25 +0.1 e -1 ;

[0137] R c =0.2 0.3679 + 0.25 0.7788 + 0.15 1 + 0.3 0.7788 + 0.1 0.3679;

[0138] R c =0.0736+0.1947+0.15+0.2336+0.0368;

[0139] R c =0.6887;

[0140] The results show that the coefficient of the health risk causal path is 0.6887, indicating that the comprehensive risk level of the high-frequency risk causal path is relatively high. According to this value, the weight parameter distribution can be further optimized or the response strategy of health risks can be adjusted.

[0141] See also Figure 5 , the specific steps for obtaining the recommended nutritional distribution ratio are:

[0142] S401: Using the health risk causal path coefficient, make a preliminary adjustment to the dietary component ratio, analyze its association with health risks based on the matching degree between nutrients and metabolic needs, and determine the dietary component range that needs to be adjusted by comparing the intake standard of nutrients with the association data of health risk factors, and obtain the adjusted dietary component data;

[0143] The influence range of each nutrient in the health risk causal path coefficient was analyzed. By matching the data of nutrient intake and metabolic demand ratio, the dietary components were divided into multiple detailed indicators. According to the metabolic demand contribution corresponding to each indicator, the current dietary component intake ratio was adjusted. The weight parameters in the health risk causal path were called to calculate the risk impact of different components on the overall dietary structure. The nutrient range for priority adjustment was extracted through the risk impact stratified screening method, and the initial dietary component intake ratio was re-optimized according to its distribution value in each interval. The nutrient intake adjustment value was recalculated based on the above-screened component range and the weight parameter of health risk to obtain the adjusted dietary component data.

[0144] S402: calling the adjusted dietary component data, analyzing the correlation between multiple components and health risks, calculating the risk contribution of multiple nutritional components through statistical analysis methods, and iteratively adjusting the dietary component ratio based on the risk contribution, determining the recommended intake of each component, and generating refined dietary component recommendation data;

[0145] By extracting the matching data of nutrients and metabolic requirements (such as the coefficient of difference, calculated by the ratio of the intake of each ingredient to the required amount), combined with the high-risk node values ​​marked in the health risk causal path, the contribution of nutrients is analyzed, and the formula is calculated. Where R i is the nutrient risk contribution value, v i is the nutrient intake, s i Its standard demand, β i is the causal weight of nutrients and health risks. The risk contribution of each nutrient is calculated through this calculation. The nutrients are re-ranked according to the risk contribution, and the top nutrients with high risk contribution are selected. The nutrients are further refined and adjusted in combination with health needs. The corrected value C of each nutrient is calculated. i =s i ·δ i (where δ i To adjust the coefficient, which is jointly affected by the associated weights in the health risk pathway and the differences in demand), the corrected value is used to optimize the nutrient ratio and generate refined dietary composition recommendation data.

[0146] S403: Using the refined dietary ingredient recommendation data, the distribution of multiple nutrients is optimized through a nutritional model using the formula:

[0147]

[0148] Optimize the intake data of dietary structure and generate the recommended distribution ratio of nutrition;

[0149] Among them, P n represents the recommended distribution ratio of nutrition, α i is the adjustment factor for the ith nutrient, taking into account the criticality of the risk factor and the variability of the nutrient content in the food, v i is the target intake of the ith nutrient, s i is the standard intake and m is the total number of nutrients.

[0150] formula:

[0151]

[0152] The benefit of the formula is that, by introducing logarithmic operations and absolute values, it can dynamically balance the nonlinear deviation between nutrient intake and requirement, further enhancing sensitivity to outliers. At the same time, the denominator is normalized to ensure the adaptability and flexibility of each nutrient in the recommended distribution ratio.

[0153] Detailed explanation of the formula and the process of formula calculation and derivation:

[0154] P n represents the recommended distribution ratio of nutrition, α i represents the adjustment coefficient of the ith nutrient component, which is obtained based on the causal path coefficient analysis of health risk and indicates the contribution of the ith component to health risk. i represents the target intake of the ith nutrient, which is determined experimentally or adjusted based on the difference between the actual intake and the required amount. i represents the standard requirement of the ith nutrient, obtained through authoritative nutrition guidelines or metabolic requirement formulas, and m represents the total number of nutrients. When using this formula, the number of parameters can be determined according to the classification of actual nutrients;

[0155] Assignment:

[0156] Assume that the target analysis includes three macronutrients: carbohydrates, proteins, and fats, where the carbohydrate target intake v1 = 250, the standard requirement s1 = 300, the adjustment coefficient α1 = 0.8, the protein target intake v2 = 80, the standard requirement s2 = 70, the adjustment coefficient α2 = 0.9, the fat target intake v3 = 60, the standard requirement s3 = 65, and the adjustment coefficient α3 = 0.7;

[0157] Calculation process:

[0158] For the carbohydrates:

[0159]

[0160] For the protein:

[0161]

[0162] For the fat:

[0163]

[0164] Total recommended distribution ratio:

[0165] P n =P1+P2+P3=0.002468+0.006+0.003919=0.012387;

[0166] The results show that in nutritional optimization, the total value of the current recommended nutrient distribution ratio is 0.012387, indicating that the overall intake is low. By adjusting the intake, the dietary structure can be optimized to meet the level of health needs.

[0167] See also Figure 6 , the specific steps for obtaining personalized dietary intake recommendations are:

[0168] S501: Analyze and adjust the recommended range of food intake based on the recommended nutritional distribution ratio, match the nutritional components with the metabolic needs, identify the food data most related to the health status, and obtain the adjusted recommended range of food intake by dynamically adjusting the upper and lower limits of food intake;

[0169] Analyze the relationship between the recommended range of current food intake and metabolic needs, divide the nutritional components of each food into two categories: macronutrients and micronutrients, extract the specific content data of each category of ingredients and match them with the recommended intake. The intake range of macronutrients such as protein, fat and carbohydrates is calculated by the unit energy intake ratio. Set a target intake value range for each macronutrient and make dynamic adjustments based on the deviation between intake and demand. For example, through the formula Calculate target protein intake c , where C m is the total mass of protein, E d is the metabolic energy corresponding to protein, T dThe total energy metabolism requirement is then optimized according to the adjusted results. The upper and lower limits of micronutrient intake, such as vitamins and minerals, are adjusted according to the standard range that matches the health status indicators (such as blood test results). For example, the deficiency of a certain vitamin is used as the target amount, and the intake correction formula V is used to adjust the intake. r =V t -V c ) Calculate the adjusted recommended intake V r , where V t is the target value of health needs, V c For the current intake level, the recommended range of the target value is calculated to obtain the adjusted recommended range of food intake.

[0170] S502: calling the adjusted recommended food intake range, analyzing the matching of multiple nutrients with health status, determining the suitability of the intake by comparing the actual intake of nutrients with the recommended intake, and generating optimized dietary intake data;

[0171] By comparing the actual intake of nutrients with the recommended intake item by item, the data of insufficient nutrients are extracted as a supplement priority list, and the data of excessive nutrients are extracted as a restriction priority list, so as to screen and stratify the priorities, and calculate the deviation ratio formula between the intake and the target value. Determine the priority, where ΔC is the difference between the actual intake and the target recommended value, C t The target recommended value is used to adjust the intake order. The analysis results are used to obtain the matching weight with the health status through context information. For example, the increase in the demand for certain nutrients in patients with certain chronic diseases in the health status can introduce a dynamic weight adjustment factor through the nutritional supplement demand formula. Among them, H d is the change in health demand, N d Based on the standard requirement, weighting factors are used to increase the importance of specific nutrients in the recommendation, optimizing the results to generate adjusted dietary intake data.

[0172] S503: Parameter comparison of the optimized dietary intake data with the metabolic demand value is performed using the formula:

[0173]

[0174] Adjust the upper and lower limits of intake, combine the intake deviation of each ingredient with the standard deviation of the recommended amount, and calculate the personalized dietary intake recommendation value;

[0175] Among them, R d represents the recommended value of personalized dietary intake, c jis the adjustment coefficient of the jth food component, taking into account its sensitivity and individual differences in metabolic effects, Δm j is the intake deviation of the jth food component, s j is the standard deviation of the recommended intake to reflect the differences in intake between individuals, ∈ is a small constant to avoid the situation where the denominator is zero, and k is the total number of food ingredients.

[0176] formula:

[0177]

[0178] The benefit of the formula is that by combining the intake deviation of food components, the standard deviation of the recommended amount, and the dynamic weighting of the adjustment coefficient, it can optimize dietary intake, accurately match individual metabolic needs and health status, and improve the scientificity and practicality of personalized dietary plans.

[0179] Detailed explanation of the formula and the process of formula calculation and derivation:

[0180] Δm j =v j -s j , assuming that the actual intake of a certain nutrient is v1 = 50g, and the recommended intake is s1 = 60g, so the intake deviation is Δm1 = 50-60 = -10g;

[0181] Adjustment coefficient c j The basis for setting this nutrient is the metabolic demand sensitivity. Assuming that c1=1.2 is obtained through health data, the standard deviation is s j =5g;

[0182] Introduce a small constant ∈=0.01 to prevent the denominator from being zero, and calculate the weighted deviation term:

[0183]

[0184] Assuming that the total number of food ingredients k = 3, and bringing in the relevant parameters of other nutrients, the calculation results are The result is:

[0185]

[0186] The results showed that the recommended value of personalized dietary intake R d =-0.1972, indicating that the deviation between the current actual intake and metabolic demand needs to be further optimized by adjusting the intake of each nutrient to meet the recommended range, which is further used to generate personalized dietary intake recommendations.

[0187] An energy metabolism analysis and patient information integration system, which is used to perform the above energy metabolism analysis and patient information integration method, and the system includes:

[0188] The metabolic shift analysis module is based on metabolic rate data and blood test indicators. It extracts local shift information from metabolic rate data, extracts biochemical distribution characteristics from blood test indicators, calculates the correlation between the two, analyzes the statistical characteristics in the local abnormal area, and generates metabolic shift characteristic values.

[0189] The vital signs trend analysis module analyzes the volatility of differentiated time periods based on metabolic shift characteristic values, combined with heart rate and blood pressure data. It adjusts the weight of the fluctuation data through the correlation evaluation between heart rate data and exercise intensity to generate dynamic trend values ​​of vital signs.

[0190] The health risk causal assessment module matches the distribution of metabolic deviation characteristic values ​​and health risk causal nodes based on the dynamic trend values ​​of vital signs, analyzes the causal node values ​​between vital signs and metabolic rate characteristics, conducts hierarchical assessment of key risk parameters in the causal path, adjusts weight data, and generates health risk causal path coefficients;

[0191] The nutrition optimization distribution module analyzes the matching between the dietary component ratio and metabolic demand based on the health risk causal path coefficient, adjusts the dietary component ratio to the optimal range, and generates the recommended nutrition distribution ratio;

[0192] The dietary intake recommendation module analyzes the relationship between food intake and health status based on the recommended nutrient distribution ratio, adjusts the upper and lower limits of food intake, compares and matches parameters with metabolic demand values, and generates personalized dietary intake recommendation values.

[0193] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for integrating energy metabolism analysis and patient information, characterized in that: The following steps are involved: S1: Based on metabolic rate data and blood test indicators, the local deviation of metabolic rate and the distribution characteristics of biochemical indicators in blood tests are classified and matched, the statistical characteristics in the local abnormal area are extracted, the correlation changes between metabolic deviation and biochemical indicators are analyzed, and the metabolic deviation characteristic value is generated; S2: Based on the metabolic shift characteristic value, the heart rate and blood pressure in the vital sign parameters are analyzed for a time period, the fluctuation data at key time points are extracted, the correlation between exercise intensity and heart rate data is evaluated, the weight of the fluctuation data is adjusted, and the dynamic trend value of the vital sign is generated; S3: Based on the dynamic trend value of the vital signs, the metabolic deviation characteristic value and the distribution value of the health risk causal node are matched and analyzed, the causal node value between the dynamic data of the vital signs and the metabolic rate characteristics is extracted, the frequency distribution of the key risk parameters in the causal path is hierarchically evaluated, the weight data of the high-frequency risk causal path is range-adjusted, and the health risk causal path coefficient is generated; S4: Based on the health risk causal path coefficient, adjust the proportion of dietary ingredients, match the nutritional ingredients with metabolic needs, analyze the correlation between nutritional distribution and health risks, optimize the dietary structure intake data into a segmented recommended value range, and generate a nutritional recommendation distribution ratio; S5: Based on the recommended nutritional distribution ratio, adjust the recommended range of food intake, analyze the matching of food data with health status, adjust the upper and lower limits of intake, compare the dietary intake data with the metabolic requirement value, and generate personalized dietary intake recommendation values.

2. The method for energy metabolism analysis and patient information integration according to claim 1, characterized in that: The metabolic deviation characteristic values ​​specifically include the statistical characteristics of local abnormal areas, the associated changes of biochemical indicators, and the metabolic rate distribution characteristics. The dynamic trend values ​​of vital signs include heart rate fluctuation data, blood pressure fluctuation data, and exercise intensity correlation assessment. The health risk causal path coefficient specifically refers to the frequency distribution of key risk parameters, high-frequency risk path weight adjustment, and health risk stratification assessment. The nutritional recommendation distribution ratio includes the matching degree of nutritional components, the correlation between nutritional distribution and health risks, and the adjustment range of dietary components. The personalized dietary intake recommendation value specifically includes the recommended range of food intake, the matching of health status and food data, and the comparison of metabolic demand parameters.

3. The method for energy metabolism analysis and patient information integration according to claim 2, characterized in that: The steps for obtaining the metabolic deviation characteristic value are specifically as follows: S101: extracting local offset regions based on metabolic rate data, determining whether the local change amplitude in the metabolic rate data exceeds a dynamic threshold, calculating the change rate interval within the dynamic threshold, and marking the local offset regions to obtain distribution characteristics of the local metabolic offset regions; S102: calling the local metabolic deviation regional distribution characteristics, combining the biochemical data of the blood test index, calculating the characteristic change interval of the biochemical index according to the distribution mean and variance of each biochemical index, and judging whether the biochemical data in the local metabolic deviation region deviates from the characteristic change interval, and extracting the characteristic data of the local abnormal region by matching the local regional characteristics and the biochemical index distribution deviation characteristics; S103: calling the characteristic data of the local abnormal area, setting the distribution function of the correlation change between the metabolic rate and the biochemical index, and fitting the deviation value of the biochemical index and the metabolic rate, using the formula: Calculate and generate metabolic shift characteristic values; Among them, C f Represents the metabolic shift characteristic value, ΔM i is the local offset of the ith metabolic rate, ΔB i is the deviation value of the i-th blood test index, W i is the weight factor of the ith data, and n is the number of statistical samples in the local abnormal area.

4. The method for energy metabolism analysis and patient information integration according to claim 3, characterized in that: The steps for obtaining the dynamic trend value of the vital signs are specifically as follows: S201: Using the metabolic shift characteristic value, marking the key time points of the heart rate and blood pressure of the vital sign data, identifying the time points when the fluctuation value exceeds the dynamic threshold by analyzing the time series distribution law of the heart rate and blood pressure, and classifying and marking the key points according to the fluctuation characteristics to obtain the key fluctuation data of the heart rate and blood pressure; S202: calling the key fluctuation data of the heart rate and blood pressure, combining the correlation between the exercise intensity data and the heart rate data, calculating the correlation coefficient between the exercise intensity and the heart rate, and screening the heart rate fluctuation characteristics within the differentiated exercise intensity range, and obtaining an adjusted fluctuation data weight set by adjusting the fluctuation characteristic weight matching data to show the mutual change trend; S203: Using the adjusted volatility data weight set and combining it with the time series analysis model, the formula is: Calculate and obtain dynamic trend values ​​of vital signs; Among them, T d Represents the dynamic trend value of vital signs, w t Represents the weight adjustment coefficient at time point t, HR t Represents the heart rate data at time point t, BP t Represents the blood pressure data at time point t, numerator | HR t -BP t | is the absolute difference between heart rate and blood pressure at time point t, the denominator (HR t +BP t ) is the sum of heart rate and blood pressure at time point t, which is used for normalization, and T represents the total time step of the time series.

5. The method for energy metabolism analysis and patient information integration according to claim 4, characterized in that: The steps for obtaining the health risk causal path coefficient are specifically as follows: S301: Based on the dynamic trend value of the vital signs, the metabolic deviation characteristic value is matched with the distribution value of the health risk causal node, the causal node between the dynamic trend value and the metabolic rate characteristic is extracted, and the causal association node of the health risk is located by identifying the characteristic value range of multiple causal associations in the node distribution, and the preliminary matching causal node data is obtained; S302: calling the preliminary matched causal node data, screening the causal nodes through statistical analysis, using partial correlation analysis between nodes to determine the correlation between metabolic rate and dynamic vital signs, and calculating the correlation coefficient between the causal nodes, re-ordering the screened nodes according to the correlation size, and establishing a causal node value distribution map; S303: using the causal node numerical distribution diagram, extracting key risk parameters, statistically analyzing the frequency distribution of multiple parameters, clustering the key risk parameters of the frequency distribution using hierarchical evaluation technology, and generating preliminary weight data of high-frequency risk causal paths; S304: Call the preliminary weight data of the high-frequency risk causal path, and adjust the range according to the causal node weight distribution, using the formula: Calculate and generate health risk causal path coefficients; Among them, R c represents the causal path coefficient of health risk, w i represents the weight of the ith risk factor, x i represents the value of the i-th causal node, μ represents the mean value of the causal node, σ represents the standard deviation of the causal node value, n represents the total number of causal nodes, and exp is an exponential function used to dynamically adjust the weight distribution.

6. The method for energy metabolism analysis and patient information integration according to claim 5, characterized in that: The steps for obtaining the recommended nutritional distribution ratio are specifically as follows: S401: using the health risk causal path coefficient, preliminarily adjusting the dietary component ratio, analyzing the correlation between the nutritional components and the health risk according to the matching degree between the nutritional components and the metabolic requirements, and determining the dietary component range that needs to be adjusted by comparing the nutritional component intake standard with the correlation data of the health risk factors, and obtaining the adjusted dietary component data; S402: calling the adjusted dietary component data, analyzing the correlation between multiple components and health risks, calculating the risk contribution of multiple nutritional components through statistical analysis methods, and iteratively adjusting the dietary component ratio based on the risk contribution, determining the recommended intake of each component, and generating refined dietary component recommendation data; S403: Using the refined dietary component recommendation data, the distribution of multiple nutrients is optimized through a nutritional model, using the formula: Optimize the intake data of dietary structure and generate the recommended distribution ratio of nutrition; Among them, P n represents the recommended distribution ratio of nutrition, α i is the adjustment factor for the ith nutrient, taking into account the criticality of the risk factor and the variability of the nutrient content in the food, v i is the target intake of the ith nutrient, s i is the standard intake and m is the total number of nutrients.

7. The method for energy metabolism analysis and patient information integration according to claim 6, characterized in that: The steps for obtaining the personalized dietary intake recommended value are specifically as follows: S501: Analyze and adjust the recommended range of food intake based on the recommended nutritional distribution ratio, match the nutritional components with the metabolic needs, identify the food data most related to the health status, and obtain an adjusted recommended range of food intake by dynamically adjusting the upper and lower limits of food intake; S502: calling the adjusted recommended food intake range, analyzing the matching of multiple nutrients with health status, determining the suitability of the intake by comparing the actual intake of nutrients with the recommended intake, and generating optimized dietary intake data; S503: Compare the optimized dietary intake data with the metabolic demand value using the formula: Adjust the upper and lower limits of intake, combine the intake deviation of each ingredient with the standard deviation of the recommended amount, and calculate the personalized dietary intake recommendation value; Among them, R d represents the recommended value of personalized dietary intake, c j is the adjustment coefficient of the jth food component, taking into account its sensitivity and individual differences in metabolic effects, Δm j is the intake deviation of the jth food component, s j is the standard deviation of the recommended intake to reflect the differences in intake between individuals, ∈ is a small constant to avoid the situation where the denominator is zero, and k is the total number of food ingredients.

8. An energy metabolism analysis and patient information integration system, characterized in that: According to any one of claims 1 to 7, the method for integrating energy metabolism analysis and patient information comprises: The metabolic shift analysis module is based on metabolic rate data and blood test indicators. It extracts local shift information from metabolic rate data, extracts biochemical distribution characteristics from blood test indicators, calculates the correlation between the two, analyzes the statistical characteristics in the local abnormal area, and generates metabolic shift characteristic values. The vital signs trend analysis module analyzes the volatility of differentiated time periods based on the metabolic shift characteristic value and combines the heart rate and blood pressure data, and adjusts the weight of the fluctuation data through the correlation evaluation between the heart rate data and the exercise intensity to generate the dynamic trend value of the vital signs; The health risk causal assessment module matches the distribution of metabolic deviation characteristic values ​​and health risk causal nodes based on the dynamic trend values ​​of the vital signs, analyzes the causal node values ​​between the vital signs and the metabolic rate characteristics, performs a hierarchical assessment of the key risk parameters in the causal path, adjusts the weight data, and generates a health risk causal path coefficient; The nutrition optimization distribution module analyzes the matching between the dietary component ratio and the metabolic demand based on the health risk causal path coefficient, adjusts the dietary component ratio to the optimal range, and generates a nutrition recommendation distribution ratio; The dietary intake recommendation module analyzes the relationship between food intake and health status based on the recommended nutrient distribution ratio, adjusts the upper and lower limits of food intake, compares and matches parameters with the metabolic demand value, and generates personalized dietary intake recommendation values.

Images