Diet management method and system based on inflammatory dietary assessment and anti-inflammatory dietary recipe pushing

Abstract

The application provides a dietary management method and system based on inflammatory dietary assessment and anti-inflammatory dietary plan pushing, which comprises the following steps: step 1, obtaining the intake amount of food of a surveyee each time; step 2, combining food categories and intake frequency, calculating the average daily intake amount of various foods of the surveyee; step 3, based on the dietary intake data of the surveyee, adopting principal component analysis for statistical analysis, obtaining a personalized food combination which can best represent the favorite of the surveyee; step 4, according to the full literature retrieval result, creating an inflammation score CDII of Chinese food, which is used to measure the dietary inflammation degree of Chinese people; and step 5, combining the inflammation effect score in the CDII and the personalized food combination, providing food replacement suggestions which can meet the dietary favorite of the surveyee and reduce dietary inflammation to the surveyee. The application can more easily reduce the chronic inflammation of the body on the basis of not changing the dietary habits, and from the inflammatory mechanism, the most fundamental and effective result of reducing the risk of chronic diseases is achieved.

Description

Technical Field

[0001] This invention relates to the field of dietary management technology, specifically to a dietary management method and system based on inflammatory dietary assessment and anti-inflammatory recipe recommendations. Background Technology

[0002] A growing body of scientific evidence links dietary intake to inflammatory processes in the development of chronic noncommunicable diseases. The Dietary Inflammatory Index (DII), designed by Shivappa et al. at the University of South Carolina (the “DII Design and Development Methods” were published in the August 2014 issue of the journal *Public Health Nutrition*, pp. 1689-1696), has been demonstrated in numerous epidemiological studies to reflect the overall inflammatory potential of diet. Therefore, the DII can serve as a tool for assessing the degree of dietary inflammation in an individual.

[0003] Patent document CN113963776A (application number: CN202111267062.5) discloses a method for health monitoring and dietary management. The method includes: acquiring multiple health standard values ​​and multiple dietary standard values ​​to construct a corresponding healthy dietary standard database; acquiring multiple human body indicators for monitoring user health and multiple dietary indicators for monitoring dietary health; determining the user's comprehensive health risk level based on the multiple human body indicators and the healthy dietary standard database; and evaluating the user's dietary nutrition quality (health) level by integrating the multiple dietary indicators and the healthy dietary standard database, and determining a scientific dietary plan.

[0004] However, the current application of DII is limited to the scientific research field. By calculating the DII of a population and linking it to diseases, it can be analyzed to predict the degree of disease. However, DII suitable for the diet of the general population has not been developed, nor has DII been linked with dietary survey questionnaires to conduct real-time assessment of the dietary quality of the population and push personalized dietary pattern suggestions aimed at reducing inflammation. A dietary inflammation index suitable for the dietary characteristics of the Chinese population has not been developed or applied to real-world research. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the purpose of this invention is to provide a dietary management method and system based on inflammatory dietary assessment and anti-inflammatory recipe recommendation.

[0006] The dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendation provided by the present invention includes: Step 1: Based on the images of standard food portions on the client side, obtain the respondents' food intake for each meal in the form of a questionnaire; Step 2: On the system computing platform, based on the amount of food consumed by the respondents each time, combined with the types of food and the frequency of intake, calculate the average daily intake of various foods for each individual, link to the food composition table database, and construct a database of the average daily intake of dietary nutrients for each individual. Step 3: Based on individual dietary intake data, principal component analysis is used for statistical analysis to obtain the personalized food combination that best represents individual preferences; Step 4: Based on the full literature search results, create the Chinese food inflammation score CDII to measure the degree of dietary inflammation in Chinese people; Step 5: Combining the inflammation effect score in CDII with personalized food combinations, provide users with food substitution suggestions that match their personal dietary preferences and reduce dietary inflammation.

[0007] Preferably, step 3 includes: Based on individual dietary intake data, principal component analysis was used for statistical analysis, with the average daily intake of N types of food as N statistical variables, forming X= Given a dataset, first calculate the mean, then subtract the mean from each feature, and then sequentially construct mutually orthogonal coordinate axes in the original space to achieve dimensionality reduction for the N variables, and finally calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained using eigenvalue decomposition. A set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest, and the k largest eigenvalues ​​are selected. Then, the k corresponding eigenvectors are used as column vectors to form an eigenvector matrix. The column vectors are the independent personalized dietary patterns to be extracted. For a multiple linear equation with each dietary pattern score as the dependent variable and each food in the equation as the independent variable, the stepwise regression method is used to obtain foods whose statistical p-value is always less than 0.05 when introducing a new variable into the linear equation and testing each of the old variables already included in the regression model. The food groups composed of these foods are taken as the foods with the strongest association with the dietary pattern (i.e., the dependent variable of the multiple linear regression). This is the personalized food combination that best represents personal preferences.

[0008] Preferably, step 4 includes: Based on the validated Dietary Inflammation Index (DII), this paper modifies the original DII by incorporating literature on the relationship between foods / nutrients and six major blood inflammatory markers that were not included in the original DII. Following the original DII's method of obtaining inflammatory effect scores, the paper retrieves literature since 1950 that associates foods or nutrients with the six major inflammatory factors. It considers different study designs, the number of articles, and conclusions regarding anti-inflammatory, inflammatory, and no-association relationships to calculate the inflammatory scores of various foods, thus establishing the Dietary Inflammation Index (CDII). The system's computing platform integrates the average daily dietary nutrient intake data of all questionnaire participants, forming a progressively accumulating database of average dietary intake for the population. This database serves as a standardized database for calculating individual CDII scores. The average daily intake of each individual's dietary element in the CDII is standardized, converted to a normal distribution percentile, and then multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows:

[0009] The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation in a person: the higher the absolute value of the score, the stronger the inflammatory effect of the diet.

[0010] Preferably, step 5 includes: The system's computing platform divides the cumulative CDII scores into quartiles, sorts the CDII data from smallest to largest, and obtains the 25th percentile P of this data set. 25 50th percentile P 50 75th percentile P 75 The population was sorted and classified using these three CDII quantiles: less than P 25 , between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75 These four score ranges correspond to the risk level of an individual's inflammatory diet, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. They also correspond to the color bars on the client page, ranging from green (most anti-inflammatory), light yellow (most inflammatory), yellow (most inflammatory), and red (most inflammatory), with corresponding risk definitions. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in CDII and previously obtained personalized food combinations, it provides food substitution suggestions that meet the individual dietary preferences of all people except the most anti-inflammatory diet group and can reduce dietary inflammation. This is directly pushed back to the client page, generating a color chart of the risk level, its interpretation, personalized dietary patterns and related food groups, as well as textual dietary nutrition advice.

[0011] Preferably, clinical indicators of the population are obtained, including blood inflammation indicators. Statistical correlation is performed between the blood inflammation indicators and the calculated CDII dietary inflammation score to verify whether CDII can effectively reflect the human body's inflammation level. The stronger the correlation, the more valid the population applicability of CDII is verified.

[0012] The dietary management system based on inflammatory dietary assessment and anti-inflammatory recipe recommendation provided by the present invention includes: Module M1: Based on images of standard food portions, the client obtains the amount of food consumed by the respondents each time in the form of a questionnaire; Module M2: On the system computing platform, based on the amount of food consumed by the respondents each time, combined with the types of food and the frequency of intake, the average daily intake of various foods is calculated, and linked to the food composition table database to construct an average daily intake database of personal dietary nutrition. Module M3: Based on personal dietary intake data, principal component analysis is used for statistical analysis to obtain personalized food combinations that best represent personal preferences; Module M4: Based on the full literature search results, an inflammation score CDII for Chinese foods is created to measure the degree of dietary inflammation in Chinese people. The CDII is a numerical range from negative to positive, with a larger absolute value indicating a stronger anti-inflammatory or pro-inflammatory ability. Specifically, a larger absolute negative value indicates a stronger anti-inflammatory effect, while a larger absolute positive value indicates a stronger pro-inflammatory effect, and vice versa. Module M5: Combining the inflammation effect score in CDII with personalized food combinations, it provides users with food substitution suggestions that match their personal dietary preferences and reduce dietary inflammation.

[0013] Preferably, the module M3 includes: Based on individual dietary intake data, principal component analysis was used for statistical analysis, with the average daily intake of N types of food as N statistical variables, forming X= Given a dataset, first calculate the mean, then subtract the mean from each feature, and then sequentially construct mutually orthogonal coordinate axes in the original space to achieve dimensionality reduction for the N variables, and finally calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained using eigenvalue decomposition. A set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest, and the k largest eigenvalues ​​are selected. Then, the k corresponding eigenvectors are used as column vectors to form an eigenvector matrix. The column vectors are the independent personalized dietary patterns to be extracted. For a multiple linear equation with each dietary pattern score as the dependent variable and each food in the equation as the independent variable, the stepwise regression method is used to obtain foods whose statistical p-value is always less than 0.05 when introducing a new variable into the linear equation and testing each of the old variables already included in the regression model. The food groups composed of these foods are taken as the foods with the strongest association with the dietary pattern (i.e., the dependent variable of the multiple linear regression), thus selecting the personalized food combination that best represents personal preferences.

[0014] Preferably, the module M4 includes: Based on the validated Dietary Inflammation Index (DII), this paper modifies the original DII by incorporating literature on the relationship between foods / nutrients and six major blood inflammatory markers that were not included in the original DII. Following the original DII's method of obtaining inflammatory effect scores, the paper retrieves literature since 1950 that associates foods or nutrients with the six major inflammatory factors. It considers the scoring of different study designs, the number of articles, and the literature's conclusions regarding anti-inflammatory, inflammatory, and no association, calculating the inflammatory scores of various foods to establish the Dietary Inflammation Index (CDII). The system's computing platform integrates the average daily dietary nutrient intake data of all questionnaire participants, forming a progressively accumulating database of average dietary intake for the population. This database serves as a standardized database for calculating individual CDII scores. The average daily intake of each individual's dietary element in the CDII is standardized, then converted to a normal distribution percentile and multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows:

[0015] The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation. The CDII is a numerical range from negative to positive, with a larger absolute value indicating a stronger anti-inflammatory or anti-inflammatory effect. Specifically, a larger absolute negative value indicates a stronger anti-inflammatory effect, while a larger absolute positive value indicates a stronger inflammatory effect, and vice versa.

[0016] Preferably, the module M5 includes: The system's computing platform divides the cumulative CDII scores into quartiles, sorts the CDII data from smallest to largest, and obtains the 25th percentile P of this data set. 25 50th percentile P 5075th percentile P 75 The population was sorted and classified using these three CDII quantiles: less than P 25 , between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75 These four score ranges correspond to the risk level of an individual's inflammatory diet, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. They also correspond to the color bars on the client page, ranging from green (most anti-inflammatory) to light yellow (most inflammatory) and red (most inflammatory), with corresponding risk definitions. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in CDII and previously obtained personalized food combinations, it provides food substitution suggestions that meet the individual dietary preferences of all people except the most anti-inflammatory diet group and can reduce dietary inflammation. This is directly pushed back to the client page, generating a color chart of the risk level, its interpretation, personalized dietary patterns and related food groups, as well as textual nutritional advice.

[0017] Preferably, clinical indicators of the population are obtained, including blood inflammation indicators. Statistical correlation is performed between the blood inflammation indicators and the calculated CDII dietary inflammation score to verify whether CDII can effectively reflect the human body's inflammation level. The stronger the correlation, the more valid the population applicability of CDII is verified.

[0018] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention solves the problem that the previous paper-based dietary questionnaires were difficult for respondents to understand and accurately assess food intake by using a food reference system and a standard intake of each food. It also saves a lot of manpower and resources to conduct on-site nutrition surveys, and assesses personal dietary habits more efficiently and accurately. (2) This invention has developed a new method for calculating the dietary inflammation index and inflammation score that is suitable for the dietary characteristics of the Chinese population by conducting a full literature search of published dietary and inflammatory marker associations and reformulating the total dietary intake database used for dietary data standardization. This solves the scientific limitation that the previous DII could not be applied to the assessment of the degree of dietary inflammation in the Chinese population. (3) This invention obtains personalized dietary patterns and corresponding food types through statistical methods, and uses the equal energy food exchange method to provide foods that satisfy personal preferences and reduce the inflammatory nature of food to replace the original highly inflammatory foods. This makes it easier to reduce chronic inflammation of the body without changing dietary habits. Starting from the inflammatory mechanism, it achieves the most fundamental and effective result of reducing the risk of chronic diseases. It solves the problem that the original dietary recommendations do not take into account personal dietary preferences and the design method does not take into account the pathogenic mechanism, thus lacking scientific accuracy and making it difficult to truly prevent and treat diseases. (4) This invention, by directly inputting personal dietary intake data from the customer's page to the background, automatically calculates and presents the DII score and inflammation level assessment in real time, and pushes personalized anti-inflammatory diet suggestions in real time, solves the problem of an integrated dietary health management system from quantitative dietary nutrient intake to accurate assessment of dietary quality and personalized dietary suggestions from the scientific mechanism of dietary inflammation. In the real world, it realizes the goal of being able to scientifically and accurately assess one's own dietary quality in real time rather than just dietary intake. At the same time, it provides diet suggestions that are in line with personal dietary characteristics from the perspective of reducing inflammation, so that the public can truly reduce the occurrence of a series of diet-related chronic diseases from the mechanism. Attached Figure Description

[0019] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart of the dietary management method of the present invention; Figure 2 A framework diagram of a dietary inflammation index database system; Figure 3 A flowchart for calculating and classifying dietary inflammation scores based on collected dietary data; Figure 4 A framework diagram for a personalized anti-inflammatory diet recommendation system based on dietary inflammation level assessment; Figure 5 A diagram illustrating the calculation of the inflammatory effect score for each CDII food. Detailed Implementation

[0020] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0021] Example 1: like Figure 1This invention provides a dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendation, comprising the following steps: Step 1: Based on the unique dietary behaviors of the modern Yangtze River Delta population and considering various intake scenarios, the dietary questionnaire in the system consists of 75 kinds of daily foods that are most representative of the Yangtze River Delta residents. The questionnaire uses a question format that includes subcategories of foods within major categories. For each food, the online questionnaire provides one or more pictures with a food reference system, using the normal adult's intake as the standard serving size, to ask the respondents how many servings they consume each time, thus accurately identifying the intake amount.

[0022] Step 2: The system backend automatically captures and updates the dietary intake data entered by the individual. Using the weight data of the stored food images, the dietary portions and intake frequency selected by the respondents, the backend automatically calculates the individual's average daily intake of various foods, links to the food composition table database in the backend, constructs a database of the individual's average daily dietary nutrient intake, and stores it in the system's database module.

[0023] Step 3: Based on individual dietary intake data, principal component analysis was used for statistical analysis, with the daily average intake of 75 foods as 75 statistical variables, forming X= For the dataset, first calculate the mean, then subtract the mean from each feature, and then construct mutually orthogonal coordinate axes in the original space sequentially to achieve dimensionality reduction for the 75 variables, and calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained using eigenvalue decomposition. Specifically, a set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest, and the k largest eigenvalues ​​are selected. The corresponding k eigenvectors are then used as column vectors to form an eigenvector matrix. These column vectors represent the independent personalized dietary patterns to be extracted. This is a multiple linear regression equation composed of multiple dietary variables (for example, a plant-based dietary pattern = a × green vegetables + b × root vegetables + c × aquatic vegetables + d × other foods). For a multiple linear equation where each dietary pattern score is the dependent variable and each food in the equation is the independent variable, stepwise regression is used. Foods whose p-value remains less than 0.05 regardless of whether a new variable is introduced into the linear equation or each existing variable in the regression model is tested are identified. These food groups are then used as the dietary pattern, thus selecting the food combination that best represents individual preferences. Figure 3 .

[0024] Step 4: Based on the only internationally validated Dietary Inflammation Index (DII), this model is modified to suit the dietary characteristics of the Chinese population. A full-Chinese literature search is conducted to include literature on the relationship between foods / nutrients not included in the original DII and the six major blood inflammatory markers. Following the method for obtaining inflammatory effect scores in the original DII, literature on the association between foods or nutrients (not included in the DII's dietary elements) and the six major inflammatory factors since 1950 is retrieved. This is combined with the scoring of different study designs, the number of articles, and the conclusions regarding anti-inflammatory, inflammatory, and no association in the literature to calculate the inflammation scores of various foods, thereby establishing the Dietary Inflammation Index (CDI). I. The system's computing platform integrates the average daily dietary intake data of all participants who completed the questionnaire, forming a progressively accumulating database of average dietary intake for the population. This database serves as a standardized database for calculating individual CDII scores (this database contains the mean and standard deviation of the total population's intake across various dietary factors, hereinafter referred to as the "dietary database"). Based on this database, the average daily intake of each individual for each CDII dietary element is standardized, then converted to a normally distributed percentile, and multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows:

[0025] The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation in a person: the larger the positive score, the stronger the inflammatory effect of the diet; conversely, the larger the absolute value of the negative score, the stronger the anti-inflammatory effect of the diet.

[0026] Step 5: The system's computing platform performs quartile division of the cumulative CDII scores, that is, sorts the CDII data from smallest to largest to obtain the 25th percentile P of this data set. 25 50th percentile (median, P) 50 ), 75th percentile P 75 The population was sorted and classified using these three CDII quantiles (less than P). 25 Between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75These four score ranges correspond to the individual's risk level of inflammatory diets, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. This also corresponds to the "green, light yellow, yellow, and red color bars" displayed on the client page, representing the most anti-inflammatory to the most inflammatory levels. The risk is defined accordingly. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in the CDII and previously obtained personalized food combinations, food substitution suggestions are provided to all individuals except the most anti-inflammatory diet group, offering recommendations that match their personal dietary preferences and reduce dietary inflammation. This information is directly pushed back to the client page, generating a color chart of the risk levels, explanations, personalized dietary patterns and related food groups, as well as textual dietary and nutritional advice, such as... Figure 4 .

[0027] Risk Definition: The colors from most anti-inflammatory to most pro-inflammatory are green, light yellow, yellow, and red, respectively. Under this color bar chart, the individual's dietary patterns and representative foods are extracted from the "Personal Dietary Characteristics Database." By linking to the inflammatory effect scores of foods in the CDII database, foods with strong pro-inflammatory properties in the individual's diet are identified and marked. This constitutes the first part of the information seen by the respondents—the assessment conclusion of their personal dietary inflammation. Literature has reported a significant relationship between higher dietary inflammation and the occurrence of various chronic diseases, including diabetes, cardiovascular disease, and cancer. Therefore, the red, light yellow, and yellow groups all need to increase their intake of anti-inflammatory foods to reduce the future risk of developing chronic diseases. For the risk of chronic disease development, red represents a high-risk diet, and green represents a low-risk diet.

[0028] This invention provides a dietary management system based on inflammatory dietary assessment and anti-inflammatory recipe recommendations, comprising: Module M1: On the client side, based on images of standard food portions, the system obtains the respondents' daily food intake in the form of a questionnaire; Module M2: On the system's computing platform, based on the respondents' daily food intake, combined with food types and intake frequency, the system calculates the individual's average daily intake of various foods, links to a food composition database, and constructs a database of the individual's average daily intake of dietary nutrients; Module M3: Based on the individual's dietary intake data, the system performs statistical analysis using principal component analysis to obtain personalized food combinations that best represent the individual's preferences; Module M4: Based on the results of a full literature search, the system creates a Chinese food inflammation score CDII to measure the degree of dietary inflammation in Chinese people; Module M5: Combining the inflammatory effect score in the CDII with personalized food combinations, the system provides users with food replacement suggestions that match their personal dietary preferences and reduce dietary inflammation.

[0029] Module M3 includes: based on individual dietary intake data, using principal component analysis for statistical analysis, taking the average daily intake of N kinds of food as N statistical variables, forming X= Given a dataset, first calculate the mean, then subtract the mean from each feature, and then sequentially construct mutually orthogonal coordinate axes in the original space to achieve dimensionality reduction for the N variables, and finally calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained using eigenvalue decomposition. A set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest, and the k largest eigenvalues ​​are selected. Then, the k corresponding eigenvectors are used as column vectors to form an eigenvector matrix. The column vectors are the independent personalized dietary patterns to be extracted. For a multiple linear equation with each dietary pattern score as the dependent variable and each food in the equation as the independent variable, the stepwise regression method is used to obtain foods whose statistical p-value is always less than 0.05 when introducing a new variable into the linear equation and testing each of the old variables already included in the regression model. The food groups composed of these foods are considered to be the foods most strongly associated with the dietary pattern, that is, the personalized food combinations that best represent personal preferences.

[0030] Module M4 includes: An improved version of the validated Dietary Inflammation Index (DII) is created by incorporating literature on the relationship between foods / nutrients not included in the original DII and six major blood inflammatory markers through a literature search. Following the original DII's method of obtaining inflammatory effect scores, literature on the association between foods or nutrients and the six major inflammatory factors since 1950 is retrieved. This is combined with different study designs, the number of articles, and conclusions regarding anti-inflammatory, inflammatory, and no association conclusions to calculate the inflammatory scores of various foods, thus establishing the Dietary Inflammation Index (CDII). The system's computing platform integrates the average daily dietary nutrient intake data of all questionnaire participants to form a progressively accumulating database of average dietary intake, serving as a standardized database for calculating individual CDII scores. The average daily intake of each individual for each CDII dietary element is standardized, then converted to a normal distribution percentile and multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows:

[0031] The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation in a person: the larger the positive score, the stronger the inflammatory effect of the diet; conversely, the larger the absolute value of the negative score, the stronger the anti-inflammatory effect of the diet.

[0032] The module M5 includes: the system's computing platform performs quartile division of the cumulative population based on the CDII scores, and obtains the 25th percentile P of this data set after sorting the CDII data from smallest to largest. 25 50th percentile P 50 75th percentile P75 The population was sorted and classified using these three CDII quantiles: less than P 25 Between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75 These four score ranges correspond to the risk level of an individual's inflammatory diet, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. They also correspond to the color bars on the client page, ranging from green (most anti-inflammatory) to light yellow (most inflammatory) and red (most inflammatory), and provide corresponding risk definitions. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in CDII and previously obtained personalized food combinations, we provide food substitution suggestions that meet the individual dietary preferences of all people except the most anti-inflammatory diet group and can reduce dietary inflammation. These suggestions are directly pushed back to the client page, generating a color chart of the risk level, its interpretation, personalized dietary patterns and related food groups, as well as textual dietary nutrition advice.

[0033] Clinical indicators of the population, including blood inflammation indicators, are obtained. Statistical correlations are then performed between the blood inflammation indicators and the calculated CDII dietary inflammation scores to verify whether CDII can effectively reflect the human body's inflammation level. The stronger the correlation, the more valid the population applicability of CDII is.

[0034] Example 2: Example 2 is a preferred example of Example 1.

[0035] This invention provides a dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendations, comprising: Step 1: By comprehensively integrating the unique dietary intake characteristics of the contemporary Yangtze River Delta population, a pre-developed integrated dietary health management system (hereinafter referred to as the "System") dietary questionnaire platform presented 75 common foods in the Yangtze River Delta region, reflecting the characteristics of combining Chinese and Western styles, diverse cooking methods, and the combination of takeout and home cooking. It covered 10 categories of breakfast (such as multigrain pancakes, pan-fried buns, Western-style bread and toast), 45 categories of Chinese or Western-style main meals, 5 categories of snacks, and 15 categories of takeout food (non-main meals such as milk tea, coffee, and barbecue). The questionnaire set two types of questions for each type of food: 1) the frequency of intake in the past three months, and adopted a folded question format with food categories (such as sweets or leafy green vegetables) nested within food subcategories, allowing subjects to continue answering questions only for the most frequently eaten subcategories within the main category, saving the total questionnaire time. 2) To accurately quantify the average intake of each food item, the system's dietary questionnaire presents a color image on the client interface showing the most commonly consumed form of the food or the one that best conveys its weight. Each image represents approximately the amount of the food consumed by a normal adult in one sitting (e.g., one medium-sized apple, a 250ml glass of orange juice, 10 grapes, a bowl of 16 large wontons, a medium-sized cooked chicken breast weighing about 50g, or a bag of Lay's potato chips). The questionnaire directly informs respondents that such a food image represents "one standard intake serving," thus asking them how many servings of the food they consume each time. The images are presented using a "food reference system": the food is placed on a table covered with a 2*2cm black checkered tablecloth (except for a few items, all food is placed on a 10-inch white household plate), with a 250ml red standard Coca-Cola can placed next to the plate as a reference to help respondents more accurately understand the size of the food. For example, when asking about seafood (ribbonfish, large yellow croaker, small yellow croaker, salmon), the questionnaire presented a piece of fried ribbonfish weighing about 25g-50g on a standard 10-inch plate; chopped vegetables or cooked meat were presented in the usual way of preparing dishes (such as potatoes and carrots cut into shreds, and bamboo shoots cut into cubes); when asking about cakes, a small square cream cake bought from "Jing'an Bakery" was presented (these takeout foods are easier for respondents to understand in terms of size and weight); and dried beans or nuts were presented as a "handful" in the hand of a normal adult. The system backend pre-stores a composite database (hereinafter referred to as the "food image database") containing the weight of each food image. When the respondents select the intake frequency and the standard number of servings per intake on the page, the system backend's calculation module will multiply the selected food intake frequency by the number of servings, and then call the corresponding food weight data from the food image database. The product of these three factors serves as the person's average daily intake of a certain food. This average intake of all foods for each individual constitutes the personal dietary database stored on the system backend database platform.

[0036] Step 2: The 2017 version of the Chinese Food Composition Table database stored in the system backend links with the personal dietary database by using food as ID / object. It multiplies the intake value of all nutrients for each food by the individual's daily intake of that food, and finally sums up the intake values ​​of all foods for a certain nutrient to obtain the individual's average daily intake of all nutrients. These nutrient intake values ​​are then merged into the personal dietary database to obtain a complete "personal dietary nutrition database" and stored in the database platform in the backend.

[0037] Step 3: After summarizing the daily dietary intake values ​​from the individual dietary nutrition database, the system backend uses principal component analysis to construct several "dietary patterns" that best represent the intake characteristics of this group. Each dietary pattern is expressed by a linear equation with weights based on the loading factors of the various foods included. The larger the value of this equation, the more closely the individual's diet conforms to this pattern. Based on the individual's tertiary ranking in each dietary pattern, the system platform labels the top 1-3 dietary patterns (if none are in the top 1 / 3, then the top 1 / 2) as the "personal dietary pattern" that best matches the individual's dietary habits. Further, multiple linear regression equations are used to correlate the individual's dietary pattern score with various foods, selecting foods with significant p-values ​​or those with the top 5 weights in the dietary pattern (choosing the method that obtains the largest number of foods). These foods are then summarized to form personalized food combinations. The links between the text-based dietary patterns and personalized food combinations form a new "personal dietary characteristics" database, which is stored on the database platform.

[0038] Step 4: Based on the inflammatory mechanisms of diet, develop the Chinese dietary inflammatory index (CDII) to assess the degree of inflammation in the diet of the Chinese population, and embed this CDII into the system database platform in the form of a database. Currently, the DII developed by the University of South Carolina in 2016 is widely used in scientific research. It is a database of 45 dietary inflammatory indices obtained by statistical algorithms after searching all literature on the association between dietary nutrients and 6 major blood inflammatory indicators. Using this inflammatory index database and individual standardized dietary intake data (standardized by comparing with the average of the world dietary database from 22 countries), the total DII score on 45 diets is obtained, which is the total score of the degree of dietary inflammation. The higher the score, the greater the inflammatory effect, and the lower the score, the greater the anti-inflammatory effect. Because Chinese food differs significantly from that of other countries, we developed a CDII based on the Dietary Influence Index (DII): Building upon the existing 45 dietary factors in the DII, we created inflammatory effect scores for Chinese-specific foods. To continue using the inflammatory effect scores of the 45 dietary factors in the DII, we followed the original DII design, utilizing the Wanfang Database and CNKI to obtain all published articles since 1950 on the association between Chinese-specific foods or nutrients (not included in the DII's dietary elements) and the six major inflammatory factors, such as shiitake mushrooms, chili peppers, ribbonfish, Chinese green vegetables, and cabbage. Based on the research design... These studies were assigned scores of 3-10 based on their strength (ranked from lowest to highest: cell experiments (3), animal experiments (5), cross-sectional studies (6), case-control studies (7), cohort studies (8), and clinical studies (10)). Then, based on the three types of literature conclusions—anti-inflammatory, pro-inflammatory, and no-association—statistics were calculated. The total score obtained by multiplying the number of articles by the corresponding study design score was divided by the total score of all studies, thus yielding the proportions of anti-inflammatory, pro-inflammatory, and irrelevant articles. Finally, the proportion of anti-inflammatory articles was subtracted from the proportion of pro-inflammatory articles to obtain the final food inflammation effect score (see Table 1 for details). Figure 2 According to a preliminary search of qualified Chinese literature, CDII contains approximately 55-65 dietary factors.

[0039] Step 5: Integrate the cumulative average and standard deviation of each CDII dietary element from the individual dietary nutrition database to construct the "Chinese Population Daily Dietary Intake Average Database" (hereinafter referred to as the "Chinese Dietary Database") and store it on the system's database platform. This database is used to standardize individual dietary data. A minimum of 200 individuals is used as the starting population for accumulation, and a new cumulative average is calculated each time 200 individuals are added. If an individual's data does not reach a multiple of 200 in the ranking, the previously accumulated average is still used as the comparison value. Using the following formula, the system's computing platform calls upon individual nutritional dietary data, the Chinese Dietary Database, and the CDII database to calculate the individual's CDII score, which is used to assess the degree of dietary inflammation and form the "Chinese CDII Score Database."

[0040]

[0041] Table 1. Design Scores for Each Type of Research Design

[0042] Figure 5 The two-step process for calculating the inflammatory effect of saturated fatty acids can be extrapolated to other dietary factors.

[0043] Step 6: The system's computing center, based on individual CDII scores in the "Chinese CDII Score Database," uses a cumulative calculation method to form the quartiles (P0) of the population's CDII, starting with 200 individuals. 25 P 50 P 75 Furthermore, the CDII quartiles of the entire population are recalculated for every additional 100 participants. Based on these quartile cutoffs, participants are divided into the most anti-inflammatory diet group (CDII values ​​less than P0.05). 25 The anti-inflammatory group (CDII value between P) 25 and P 50 (intermediate), more inflammatory group (CDII value between P) 50 and P 75 (interval), most inflammatory diet group (CDII value between P) 75 and P 100The data processing center added this level as a new variable to the "Chinese CDII Score Database." Simultaneously, the center pushed an individual's CDII level to the client in the form of a visually appealing color-coded risk level bar chart (green, light yellow, yellow, and red for the most anti-inflammatory group, respectively). Under this color-coded bar chart, the individual's dietary patterns and representative foods were extracted from the "Personal Dietary Characteristics Database." By linking to the inflammatory effect scores of foods in the CDII database, foods with strong pro-inflammatory properties in the individual's diet were identified and marked. This constituted the first part of the information seen by the respondents—the assessment conclusion of their individual dietary inflammation. Literature has reported a significant relationship between higher dietary inflammation and the occurrence of various chronic diseases, including diabetes, cardiovascular disease, and cancer. Therefore, those in the red, light yellow, and yellow groups should increase their intake of anti-inflammatory foods to reduce the risk of developing chronic diseases in the future. As dietary recommendations, to simultaneously align with individual dietary preferences, while maintaining an adult's total daily energy intake of 1800-2500 kcal, the platform in CDII first selects foods with strong anti-inflammatory properties (i.e., low inflammatory effect value) belonging to the personalized food category or those that meet the personalized dietary pattern. Alternatively, if no food can satisfy both anti-inflammatory and personal preference criteria, a secondary option is to recommend an additional personalized food that is also more anti-inflammatory than the substituted food, or a food containing the main antioxidant nutrients (such as vitamins A, D, E, and various minerals) found in the personalized food and thus possessing strong anti-inflammatory properties. When substituting, a one-to-one substitution method with equal energy is used (i.e., one food is replaced by another). For the pale yellow dietary group, 1-2 foods from the pro-inflammatory food list can be substituted; for the dark yellow dietary group, 4-5 foods can be substituted; and for the red group, half should be substituted if possible. After the system computing platform retrieves the "personal nutrition and diet database", it calculates the intake of the food to be replaced. Through the calculation of equal energy, it obtains the intake of the recommended alternative food. Finally, the list of this alternative food (anti-inflammatory diet mode) is pushed to the front end in the form of alternative food name + intake, such as replacing 20g of beef with 100g of seafood per day. This information forms the second part of the information pushed to the client, namely the anti-inflammatory diet mode recommendation.

[0044] Those skilled in the art will understand that, in addition to implementing the system, apparatus, and their modules provided by this invention in purely computer-readable program code, the same program can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system, apparatus, and their modules provided by this invention can be considered a hardware component, and the modules included therein for implementing various programs can also be considered structures within the hardware component; alternatively, modules for implementing various functions can be considered both software programs implementing the method and structures within the hardware component.

[0045] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendation, characterized in that, include: Step 1: Based on the images of standard food portions in the client, obtain the respondents' food intake for each meal in the form of a questionnaire; Step 2: On the system computing platform, based on the amount of food consumed by the respondents each time, combined with the types of food and the frequency of intake, calculate the average daily intake of various foods for each individual, link to the food composition table database, and construct a database of the average daily intake of dietary nutrients for each individual. Step 3: Based on individual dietary intake data, principal component analysis is used for statistical analysis to obtain the personalized food combination that best represents individual preferences; Step 4: Based on the full literature search results, create the Chinese food inflammation score CDII to measure the degree of dietary inflammation in Chinese people; Step 5: Combining the inflammatory effect scores of various foods in CDII with personal food preferences, provide users with food substitution suggestions that match their personal dietary preferences and can reduce dietary inflammation; Step 3 includes: Based on individual dietary intake data, principal component analysis was used for statistical analysis, with the average daily intake of N types of food as N statistical variables, forming X= Given a dataset, first calculate the mean, then subtract the mean from each feature, and then sequentially construct mutually orthogonal coordinate axes in the original space to achieve dimensionality reduction for the N variables, and finally calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained by eigenvalue decomposition. A set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest. The k largest eigenvalues ​​are selected, and their corresponding k eigenvectors are used as column vectors to form an eigenvector matrix. The column vectors are the independent personalized dietary patterns to be extracted. For a multiple linear equation with each dietary pattern score as the dependent variable and each food in the equation as the independent variable, the stepwise regression method is used to obtain foods whose statistical P-value is always less than 0.05 when a new variable is introduced into the linear equation and each of the old variables already included in the regression model is tested. The food group composed of these foods is the food with the strongest association with the dietary pattern. This is the personalized food combination that best represents personal preferences. Step 4 includes: Based on the validated Dietary Inflammation Index (DII), this paper modifies the original DII by incorporating literature on the relationship between foods / nutrients and six major blood inflammatory markers that were not included in the original DII. Following the original DII's method of obtaining inflammatory effect scores, the paper retrieves literature since 1950 that associates foods or nutrients with the six major inflammatory factors. It considers the scoring of different study designs, the number of articles, and the literature's conclusions regarding anti-inflammatory, inflammatory, and no association, calculating the inflammatory scores of various foods to establish the Dietary Inflammation Index (CDII). The system's computing platform integrates the average daily dietary nutrient intake data of all questionnaire participants, forming a progressively accumulating database of average dietary intake for the population. This database serves as a standardized database for calculating individual CDII scores. The average daily intake of each individual's dietary element in the CDII is standardized, then converted to a normal distribution percentile and multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows: The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation in a person. The CDII is a numerical range from negative to positive. The larger the absolute value of the score, the stronger the anti-inflammatory or inflammatory ability. Specifically, the larger the absolute value of the negative value, the stronger the anti-inflammatory effect, and the larger the absolute value of the positive value, the stronger the inflammatory effect of the diet, and vice versa.

2. The dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendation according to claim 1, characterized in that, Step 5 includes: The system's computing platform divides the cumulative CDII scores into quartiles, sorts the CDII data from smallest to largest, and obtains the 25th percentile P of this data set. 25 50th percentile P 50 75th percentile P 75 The population was sorted and classified using these three CDII quantiles: less than P 25 , between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75 These four score ranges correspond to the risk level of an individual's inflammatory diet, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. They also correspond to the color bars on the client page, ranging from green (most anti-inflammatory) to light yellow (most inflammatory) and red (most inflammatory), and provide corresponding risk definitions. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in CDII and previously obtained personalized food combinations, a food substitution suggestion that matches the individual dietary preferences and reduces dietary inflammation is provided to all groups except the most anti-inflammatory diet group. This suggestion is directly pushed back to the client page, generating a color chart of the risk level, its interpretation, personalized dietary patterns and related food groups, as well as textual dietary nutrition advice.

3. The dietary management method based on inflammatory dietary assessment and anti-inflammatory recipe recommendation according to claim 1, characterized in that, Clinical indicators of the population, including blood inflammation indicators, are obtained. Statistical correlations are then performed between the blood inflammation indicators and the calculated CDII dietary inflammation scores to verify whether CDII can effectively reflect the human body's inflammation level. The stronger the correlation, the more valid the population applicability of CDII is.

4. A dietary management system based on inflammatory dietary assessment and anti-inflammatory recipe recommendation, characterized in that, include: Module M1: Based on images of standard food portions, the client obtains the amount of food consumed by the respondents each time in the form of a questionnaire; Module M2: On the system computing platform, based on the amount of food consumed by the respondents each time, combined with the types of food and the frequency of intake, the average daily intake of various foods is calculated, and linked to the food composition table database to construct a database of the average daily intake of dietary nutrients for each individual. Module M3: Based on personal dietary intake data, principal component analysis is used for statistical analysis to obtain personalized food combinations that best represent personal preferences; Module M4: Based on the full literature search results, create the Chinese food inflammation score CDII to measure the degree of dietary inflammation in Chinese people; Module M5: Combining the inflammatory effect scores of various foods in CDII with personal food preferences, it provides users with food substitution suggestions that match their personal dietary preferences and reduce dietary inflammation; The module M3 includes: Based on individual dietary intake data, principal component analysis was used for statistical analysis, with the average daily intake of N types of food as N statistical variables, forming X= Given a dataset, first calculate the mean, then subtract the mean from each feature, and then sequentially construct mutually orthogonal coordinate axes in the original space to achieve dimensionality reduction for the N variables, and finally calculate the covariance matrix. Where J is the sample size, the eigenvectors and eigenvalues ​​of the covariance matrix are obtained by eigenvalue decomposition. A set of orthogonal unit vectors is found to decompose the covariance matrix into Q∑Q-1. The eigenvalues ​​on the diagonal matrix ∑ are sorted from largest to smallest. The k largest eigenvalues ​​are selected, and their corresponding k eigenvectors are used as column vectors to form an eigenvector matrix. The column vectors are the independent personalized dietary patterns to be extracted. For a multiple linear equation with each dietary pattern score as the dependent variable and each food in the equation as the independent variable, the stepwise regression method is used to obtain foods whose statistical P-value is always less than 0.05 when a new variable is introduced into the linear equation and each of the old variables already included in the regression model is tested. The food group composed of these foods is the food with the strongest association with the dietary pattern. This is the personalized food combination that best represents personal preferences. The module M4 includes: Based on the validated Dietary Inflammation Index (DII), this paper modifies the original DII by incorporating literature on the relationship between foods / nutrients and six major blood inflammatory markers that were not included in the original DII. Following the original DII's method of obtaining inflammatory effect scores, the paper retrieves literature since 1950 that associates foods or nutrients with the six major inflammatory factors. It considers the scoring of different study designs, the number of articles, and the literature's conclusions regarding anti-inflammatory, inflammatory, and no association, calculating the inflammatory scores of various foods to establish the Dietary Inflammation Index (CDII). The system's computing platform integrates the average daily dietary nutrient intake data of all questionnaire participants, forming a progressively accumulating database of average dietary intake for the population. This database serves as a standardized database for calculating individual CDII scores. The average daily intake of each individual's dietary element in the CDII is standardized, then converted to a normal distribution percentile and multiplied by the inflammatory effect score of each dietary factor. Finally, the products of all dietary elements are summed to obtain the individual's CDII score. The calculation formula is as follows: The CDII score is a participant's dietary inflammation score, used to measure the degree of dietary inflammation in a person. The CDII is a numerical range from negative to positive. The larger the absolute value of the score, the stronger the anti-inflammatory or inflammatory ability. Specifically, the larger the absolute value of the negative value, the stronger the anti-inflammatory effect, and the larger the absolute value of the positive value, the stronger the inflammatory effect of the diet, and vice versa.

5. The dietary management system based on inflammatory dietary assessment and anti-inflammatory recipe recommendation according to claim 4, characterized in that, The module M5 includes: The system's computing platform divides the cumulative CDII scores into quartiles, sorts the CDII data from smallest to largest, and obtains the 25th percentile P of this data set. 25 50th percentile P 50 75th percentile P 75 The population was sorted and classified using these three CDII quantiles: less than P 25 , between P 25 and P 50 Between, between P 50 and P 75 Between, greater than P 75 These four score ranges correspond to the risk level of an individual's inflammatory diet, from low to high: anti-inflammatory, moderately anti-inflammatory, moderately inflammatory, and highly inflammatory. They also correspond to the color bars on the client page, ranging from green (most anti-inflammatory) to light yellow (most inflammatory) and red (most inflammatory), and provide corresponding risk definitions. Using the principle of iso-energy food substitution, combined with the inflammatory effect score in CDII and previously obtained personalized food combinations, a food substitution suggestion that matches the individual dietary preferences and reduces dietary inflammation is provided to all groups except the most anti-inflammatory diet group. This suggestion is directly pushed back to the client page, generating a color chart of the risk level, its interpretation, personalized dietary patterns and related food groups, as well as textual dietary nutrition advice.

6. The dietary management system based on inflammatory dietary assessment and anti-inflammatory recipe recommendation according to claim 4, characterized in that, Clinical indicators of the population, including blood inflammation indicators, are obtained. Statistical correlations are then performed between the blood inflammation indicators and the calculated CDII dietary inflammation scores to verify whether CDII can effectively reflect the human body's inflammation level. The stronger the correlation, the more valid the population applicability of CDII is.

Images