Calcium guard protein and slgA joint determination of children digestive state evaluation method and system

Abstract

The application provides a method and system for evaluating the digestive state of children by jointly determining calprotectin and slgA, and relates to the technical field of data detection. The method comprises the following steps: collecting the age of a target child, configuring baseline calprotectin and baseline slgA, and obtaining a baseline error coefficient; collecting the physical characteristics of the target child and an eating characteristic sequence within a preset time range, configuring a physical sign correction coefficient and an eating correction coefficient, and correcting to obtain a corrected baseline error coefficient; predicting the fluctuations of calprotectin and slgA according to the eating characteristic sequence, obtaining predicted fluctuation calprotectin and predicted fluctuation slgA, and calculating actual calprotectin and actual slgA; calculating the fluctuation coefficients of the predicted fluctuation calprotectin and the predicted fluctuation slgA and the baseline calprotectin and the baseline slgA, obtaining a data confidence, marking, and evaluating the digestive state of children. The technical problem of insufficient accuracy of the evaluation result of the digestive state of children in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of data detection, and in particular to a method and system for assessing the digestive status of children by combining calprotectin and slgA. Background Technology

[0002] Traditional assessments of children's digestive status often rely on single biomarker detection. However, children's intestinal development is not yet mature and their gastrointestinal function is less stable. Single biomarker detection is easily affected by multiple factors such as age and dietary structure, resulting in insufficient accuracy of children's digestive status assessment results and frequent false positives and false negatives. Summary of the Invention

[0003] This invention addresses the technical problem of insufficient accuracy in the assessment results of children's digestive status in the prior art by providing a method and system for assessing children's digestive status using a combination of calprotectin and slgA.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a method for assessing the digestive status of children by combining calprotectin and sIgA, including: Collect the age of the target children, configure baseline calprotectin and baseline slgA, and obtain the baseline error coefficient; Collect the physical characteristics and feeding characteristic sequences of the target child within the most recent preset time range, configure the vital sign correction coefficient and feeding correction coefficient, and correct the baseline error coefficient to obtain the corrected baseline error coefficient; The test obtains the calprotectin and slgA of the target child, and predicts the fluctuation of calprotectin and slgA based on the feeding characteristic sequence to obtain the predicted fluctuating calprotectin and predicted fluctuating slgA. Combining the calprotectin and slgA, the actual calprotectin and actual slgA are calculated. The fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA are calculated. Combined with the corrected baseline error coefficient, the data confidence level is calculated. The actual calprotectin and actual slgA are then labeled to assess the child's digestive status.

[0005] Secondly, the present invention provides a system for assessing the digestive status of children by combining calprotectin and sIgA, comprising: The data acquisition module is used to collect the age of the target children, configure baseline calprotectin and baseline slgA, and obtain the baseline error coefficient; The error correction module is used to collect the physical characteristics of the target child and the feeding characteristic sequence within the most recent preset time range, configure the vital sign correction coefficient and the feeding correction coefficient, correct the baseline error coefficient, and obtain the corrected baseline error coefficient. The fluctuation prediction module is used to test and obtain the calprotectin and slgA of the target child, predict the fluctuation of calprotectin and slgA based on the feeding characteristic sequence, obtain the predicted fluctuating calprotectin and predicted fluctuating slgA, and calculate the actual calprotectin and actual slgA by combining the calprotectin and slgA. The status assessment module is used to calculate the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA, and to calculate the data confidence level by combining the corrected baseline error coefficient, thereby labeling the actual calprotectin and actual slgA and assessing the digestive status of children.

[0006] The beneficial effects of this invention are: Compared to existing technologies, this application first collects the age of the target children, configures baseline calprotectin and baseline slgA, and obtains the baseline error coefficient. Through age matching, it determines the normal range of calprotectin and slgA indicators that conforms to the developmental stage of the target children, providing a reliable comparative standard for subsequent assessments. Secondly, it collects the target children's physical characteristics and recent feeding characteristic sequences within a preset time range, configures physical characteristic correction coefficients and feeding correction coefficients, and corrects the baseline error coefficient to obtain a corrected baseline error coefficient. This fully considers individual differences; by incorporating the target children's physical characteristics and recent feeding characteristics, the population-based baseline error coefficient is corrected to a more individualized corrected baseline error coefficient, thereby improving the accuracy of the assessment. Secondly, the test obtains calprotectin and slgA levels for the target children. Based on the feeding characteristic sequence, calprotectin and slgA fluctuations are predicted, yielding predicted fluctuating calprotectin and slgA. Combining these with the actual calprotectin and slgA, the test-obtained calprotectin and slgA are calculated. By comparing the target children's calprotectin and slgA levels with the model's predicted fluctuations, the actual calprotectin and slgA levels accurately reflect the children's digestive status. This eliminates interference from reversible factors such as short-term feeding characteristics, avoids misjudging physiological fluctuations as pathological conditions, and improves the accuracy of the assessment. Finally, the fluctuation coefficients of the predicted fluctuating calprotectin and slgA levels with the baseline calprotectin and slgA levels are calculated. Combined with the baseline error correction coefficient, the data confidence level is calculated. The actual calprotectin and slgA levels are then labeled for assessing the children's digestive status. This approach avoids missing reliable abnormalities and reduces misjudgments based on unreliable data, ensuring that the final digestive status assessment is based on objective data while considering data reliability, thus achieving a precise and scientific determination of the children's digestive status.

[0007] Through the above technical solution, this application fully considers key influencing factors such as the target child's age, physical characteristics, and eating habits. It establishes baseline calprotectin and baseline slgA values ​​that align with the developmental stage through age matching. Then, it calculates physical and eating correction coefficients based on physical and eating characteristics, individually correcting the baseline error coefficient to obtain a corrected baseline error coefficient that effectively adapts to individual differences in children. Furthermore, it quantifies short-term physiological fluctuations caused by interference from diet and physical characteristics using a fluctuation predictor constructed through machine learning, and calculates data confidence based on the corrected baseline error coefficient, thus achieving reliable labeling of actual test values. In this way, it reduces the interference of physiological fluctuations caused by the immaturity and poor functional stability of the child's intestines, improving the reliability of test results. Compared with traditional methods, it can more accurately distinguish between physiological fluctuations and pathological abnormalities, providing a scientific basis for children's intestinal inflammation, immune dysfunction, and other issues, and assisting in precise clinical intervention. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating the method for assessing the digestive status of children by combining calprotectin and slgA, as provided by the present invention. Figure 2 This is a schematic diagram of the structure of the pediatric digestive status assessment system for the combined determination of calprotectin and slgA provided by the present invention.

[0009] In the attached diagram, the components represented by each number are as follows: Data acquisition module 11, error correction module 12, fluctuation prediction module 13, and state assessment module 14. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0012] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0013] Example 1, as Figure 1 As shown, embodiments of the present invention provide a method for assessing the digestive status of children by combining calprotectin and sIgA, including: S10: Collect the age of the target children, configure baseline calprotectin and baseline slgA, and obtain the baseline error coefficient; Calprotectin is a calcium-binding protein synthesized and released by immune cells such as neutrophils (the main inflammatory response cells in the human body) and macrophages. It is widely present in bodily fluids such as blood, saliva, and feces. Fecal calprotectin is a commonly used indicator for clinical assessment of intestinal inflammation. When the intestinal mucosa is inflamed (such as by infection, injury, or autoimmune response), neutrophils gather at the site of inflammation and release calprotectin, leading to an increase in the level of calprotectin in the intestine, which is then excreted in the feces. Therefore, the activity of intestinal inflammation can be assessed by detecting the concentration of calprotectin in feces.

[0014] sIgA is a secretory form of immunoglobulin A (IgA), mainly synthesized by plasma cells in the mucosal tissues of the intestines, respiratory tract, and digestive tract. During intestinal infection, intestinal mucosal immunity is activated, and plasma cells synthesize large amounts of sIgA to enhance defense. At this time, the level of sIgA may increase, reflecting that the intestine is initiating an immune response to fight damage.

[0015] Children's intestinal development is not yet mature. For example, the mucosal barrier function, immune regulation capacity, and gut microbiota homeostasis are all in the process of being perfected. Digestive function is easily affected by factors such as infection, dietary stimulation, and immune abnormalities. Calprotectin and sIgA can reflect abnormalities in children's digestive status from two dimensions: inflammatory response and immune defense. Specifically, when inflammation occurs in children's intestines, neutrophils in the intestines are activated and release calprotectin, leading to a significant increase in fecal calprotectin levels. Abnormal sIgA directly reflects the imbalance between intestinal mucosal immune defense and digestive homeostasis. Decreased sIgA indicates low intestinal mucosal immune function, making children more susceptible to intestinal infections, food allergies, or gut microbiota dysbiosis. Elevated sIgA suggests that the intestines may be initiating an immune response to fight damage.

[0016] To address the aforementioned issues, this application collects the age of the target children, sets baseline calprotectin and baseline slgA, and obtains the baseline error coefficient.

[0017] Specifically, step S10 in the method includes: Collect the age of the target children; Obtain the average calprotectin and average slgA of children of the same age under normal digestive conditions; The average calprotectin and average slgA were used as baseline calprotectin and baseline slgA. Based on the baseline calprotectin and baseline slgA, the baseline error coefficient is obtained through processing.

[0018] In this embodiment, the specific age of the target child is first collected, such as 5 years old, 6 years old, etc. For infants and young children, it is necessary to further refine the age to the month or even day, such as 65 days. The specific age of the target child is collected because the younger the child is, the stronger the fluctuation of digestive-related indicators, and the digestive function (such as intestinal development maturity and immune regulation ability) changes significantly with age. There are clear differences in the normal reference levels of calprotectin and sIgA in different age groups. Therefore, accurate age collection is the basis for subsequent configuration of baseline indicators and ensuring the accuracy of the assessment.

[0019] Secondly, several calprotectin and slgA levels were collected from children of the same age as the target children under normal digestive conditions, and the mean values ​​were calculated to obtain the average calprotectin and average slgA. Normal digestive condition refers to a healthy state without intestinal inflammation (e.g., no diarrhea, abdominal pain, mucosal damage), immune dysfunction (e.g., no recurrent infections, allergic reactions), or digestive disorders (e.g., no chronic constipation, indigestion), ensuring that the data reflects the physiological levels under healthy conditions. For example, sufficient test data from children of the same age as the target children under normal digestive conditions can be collected from a historical database to obtain several calprotectin and slgA levels, and the mean values ​​are calculated to obtain the average calprotectin and average slgA. The average calprotectin and average slgA can reflect the general characteristics of normal digestive function in children of the same age as the target children.

[0020] Secondly, the mean calprotectin and mean slgA are used as baseline calprotectin and baseline slgA. Baseline calprotectin and baseline slgA are the average physiological levels of the target child under normal digestive conditions, and serve as the original reference lines for judging whether the indicators of the target child are abnormal.

[0021] Finally, baseline error coefficients were obtained based on baseline calprotectin and baseline slgA. This is because factors such as individual constitution, gut microbiota, and daily diet can affect the calprotectin and slgA levels of children of the same age with normal digestion. These levels will not be completely identical to the fixed baseline values, but will exhibit physiological fluctuations around the baseline. The baseline error coefficient is a parameter used to quantify this range of normal fluctuations. It provides an important basis for subsequent assessment: when the target child's test values ​​fall within this range, it can be determined as normal physiological fluctuation; if they exceed this range, it suggests a possible pathological abnormality, thus effectively avoiding misjudging normal fluctuations caused by individual differences as pathological conditions.

[0022] Specifically, the step of "processing to obtain baseline error coefficients based on the baseline calprotectin and baseline slgA" includes: Several children of the same age were randomly selected, and multiple samples of calprotectin and slgA were obtained through testing. The baseline error coefficient is obtained by calculating the average deviation of calprotectin and slgA from baseline calprotectin and slgA in multiple samples.

[0023] In this embodiment, several children of the same age are first randomly selected, and multiple samples of calprotectin and slgA are obtained. For example, several children of the same age as the target child are randomly selected as samples, and standardized detection methods, such as fecal calprotectin detection and saliva or fecal slgA detection, are used to detect calprotectin and slgA in these samples, obtaining multiple samples of calprotectin and slgA data.

[0024] Secondly, the deviations of multiple sample calprotectin and multiple sample slgA from baseline calprotectin and baseline slgA are calculated. The average deviation is then calculated as the baseline error coefficient. The deviation can be calculated using relative deviations. For example, the deviation of calprotectin is calculated as |sample calprotectin - baseline calprotectin| / baseline calprotectin × 100%, and the deviation of slgA is calculated as |sample slgA - baseline slgA| / baseline slgA × 100%. Relative deviations can eliminate the influence of differences in the absolute values ​​of the indicators and facilitate the standardized quantification of the degree of fluctuation. The baseline error coefficient can reflect the range of fluctuation of calprotectin and slgA indicators in children of the same age on the baseline calprotectin and baseline slgA. For example, if the average deviation of calprotectin from baseline calprotectin in 100 3-year-old children is 12%, and the average deviation of slgA from baseline slgA is 10%, then the baseline error coefficient = (12% + 10%) / 2 = 11%. This means that the fluctuation range of calprotectin and slgA in children of the same age is ±11% above baseline calprotectin and baseline slgA. For example, if the baseline calprotectin is 100 μg / g and the baseline error coefficient is 11%, it means that the calprotectin of normal children in this age group usually fluctuates within the range of 89~111 μg / g (100 ± 100 × 15%). This range is the initial reasonable range for judging whether the indicators are abnormal, avoiding misjudging normal physiological fluctuations as pathological problems.

[0025] In summary, compared to existing technologies, this application collects the age of the target children, establishes baseline calprotectin and baseline slgA, and obtains the baseline error coefficient. Thus, by age matching, it determines the normal range of calprotectin and slgA indicators that conforms to the developmental stage of the target children, providing a reliable comparative standard for subsequent assessment.

[0026] S20: Collect the physical characteristics of the target child and the feeding characteristic sequence within the most recent preset time range, configure the vital sign correction coefficient and the feeding correction coefficient, correct the baseline error coefficient, and obtain the corrected baseline error coefficient; Physical characteristics of the target children, such as weight deviating from the age-average, a history of food allergies, or weak constitution; and dietary characteristics, such as recent frequent consumption of spicy or raw / cold foods, an excessively high proportion of meat in their diet, and irregular eating frequency, can all lead to significant differences in the fluctuation patterns of individual calprotectin and slgA compared to the population average. In other words, the baseline error coefficient derived from population data may not accurately reflect the true fluctuation patterns of the target children. Therefore, it is necessary to collect these individual characteristics and calculate corresponding correction coefficients to individually adjust the baseline error coefficient to suit the actual physiological characteristics of the target children.

[0027] To address the aforementioned issues, this application collects the physical characteristics of the target child and the feeding characteristic sequence within the most recent preset time range, configures a physical characteristic correction coefficient and a feeding correction coefficient, and corrects the baseline error coefficient to obtain a corrected baseline error coefficient.

[0028] Specifically, step S20 in the method includes: Collect the target child's physical characteristics and the sequence of eating characteristics within the most recent preset time range; Obtain the average physical characteristics and average eating characteristics sequences of children of the same age; The deviation of the physical characteristics and feeding characteristics sequence from the average physical characteristics and average feeding characteristics sequence is calculated and used as the physical characteristics correction coefficient and feeding correction coefficient. The baseline error coefficient is corrected by using the vital sign correction coefficient and the feeding correction coefficient to obtain the corrected baseline error coefficient.

[0029] In this embodiment, the physical characteristics of the target child and the sequence of eating characteristics within the most recent preset time range are first collected. The physical characteristics refer to weight, height, BMI, history of allergies, history of digestive diseases, etc. The preset time can be set according to actual needs, such as 3 days, 1 week, etc. The eating characteristics include the number of meals, food type (meat / vegetables / dairy products, etc.), intake of special foods (such as spicy, cold, allergenic foods, etc.), and amount of food consumed. This is to capture individual-specific factors that may affect the levels of calprotectin and slgA. For example, in terms of physical characteristics, obese children may experience greater fluctuations in calprotectin baseline due to their unique gut microbiota, and children with a history of milk allergy may have different responses to dairy products in terms of slgA compared to ordinary children. In terms of eating characteristics, recent high intake of red meat may temporarily increase calprotectin, and continuous consumption of probiotics may affect slgA secretion levels. These individual characteristics may make the baseline error coefficient unable to accurately reflect the true fluctuation pattern of the target child. For example, physical characteristics of the target child, such as height 80cm, weight 18kg, and history of milk allergy, and eating characteristics sequence of the most recent 3 days, such as eating 4 times a day and consuming 80g of vegetables per day, could be collected.

[0030] Secondly, obtain the average physical characteristics and average eating habits of children of the same age. For example, obtain the average physical characteristics and average eating habits of children of the same age as the target child from historical databases or health statistics. These include average weight, average BMI, average daily meal frequency, food intake, typical dietary structure, and types of common foods. These average characteristics represent the general state of children of the same age. By comparing them with the individual characteristics of the target child, the degree to which an individual deviates from the group average can be quantified. This establishes a benchmark for comparing the target child with the same age group, providing a reference scale for subsequent calculation of correction coefficients. For example, collect the average physical characteristics of children of the same age as the target child, such as an average weight of 15 kg and an average height of 75 cm, as well as the average eating habits, such as an average of 4 meals per day and an average daily intake of 200 g of vegetables.

[0031] Next, the deviations of the physical characteristics and eating characteristics sequences from the average physical characteristics and average eating characteristics sequences are calculated as the physical characteristic correction coefficient and the eating correction coefficient, respectively. Specifically, the deviations of the target child's physical characteristics from the average physical characteristics of the same age are calculated, and the mean is calculated as the physical characteristic correction coefficient. Similarly, the deviations of the target child's eating characteristics sequence from the average eating characteristics sequence of the same age are calculated, and the mean is calculated as the eating correction coefficient. For example, for numerical characteristics such as weight and food intake, the deviation can be calculated using relative deviation. For instance, the physical characteristic correction coefficient (weight) = (target child's weight - average weight) / average weight × 100%. If the target child's weight is 18 kg and the average weight of children of the same age is 15 kg, then the weight-related physical characteristic correction coefficient = (18 - 15) / 15 × 100% = +20%, indicating that the weight is 20% higher than the average level. For example, for non-numerical characteristics, such as a history of allergies, the deviation range can be quantified by preset rules. For instance, children with a history of milk allergy may experience greater fluctuations in slgA due to their allergic constitution, so the physical characteristic correction coefficient can be set to +15%. In this way, the positive and negative values ​​and absolute values ​​of the physical characteristic correction coefficient and the feeding correction coefficient reflect the direction and degree of individual characteristics deviating from the group average level, providing a quantitative basis for adjusting the error range.

[0032] Finally, the baseline error coefficient is corrected using a vital signs correction factor and a feeding correction factor to obtain the corrected baseline error coefficient. The corrected baseline error coefficient is calculated as: Baseline Error Coefficient × (1 + Vital Signs Correction Factor × w1 + Feeding Correction Factor × w2), where w1 + w2 = 1. This value can be dynamically set according to the target child's actual situation; for example, w1 = 0.6, w2 = 0.4. For instance, if the baseline error coefficient is 11%, the target child's vital signs correction factor is +15%, the feeding correction factor is +10%, w1 = 0.6, and w2 = 0.4, then the corrected baseline error coefficient = 11% × (1 + 15% × 0.6 + 10% × 0.4) = 12.43%. This is because the target child is obese and has recently had unusual dietary habits, resulting in greater fluctuations in calprotectin levels. The corrected baseline error coefficient is larger than the baseline error coefficient, avoiding misjudging normal fluctuations as abnormal.

[0033] Thus, the modified baseline error coefficient corrects the baseline error coefficient, making it more consistent with the individual's actual situation. For example, obese children with unusual recent diets have greater fluctuations in calprotectin, and the modified baseline error coefficient expands the baseline error coefficient, avoiding misjudging normal fluctuations as abnormalities. On the other hand, for children with stable physical condition and regular diets, the modified baseline error coefficient may shrink, increasing the sensitivity to pathological abnormalities.

[0034] In summary, compared to existing technologies, this application collects the target child's physical characteristics and recent feeding characteristic sequences within a preset time range, configures physical characteristic correction coefficients and feeding correction coefficients, and corrects the baseline error coefficient to obtain a corrected baseline error coefficient. Thus, by fully considering individual differences and incorporating the target child's physical characteristics and recent feeding characteristics, the group-based baseline error coefficient is corrected to a more individualized correction baseline error coefficient, thereby improving the accuracy of the assessment.

[0035] S30: Test to obtain the calprotectin and slgA of the target child, predict the fluctuation of calprotectin and slgA based on the feeding characteristic sequence, obtain the predicted fluctuation of calprotectin and the predicted fluctuation of slgA, and calculate the actual calprotectin and the actual slgA by combining the calprotectin and slgA. The eating characteristics of the target children, such as recent dietary structure, intake of special foods, and eating frequency, may cause physiological fluctuations in calprotectin and slgA. These fluctuations are normal responses of the body to dietary stimuli and are not caused by actual pathological conditions (such as intestinal inflammation or abnormal immune function). If the original test values ​​are used for evaluation directly, these physiological fluctuations are easily misjudged as pathological abnormalities. Therefore, it is necessary to predict the fluctuations of calprotectin and slgA based on the eating characteristic sequence to eliminate the interference of short-term eating characteristics.

[0036] To address the aforementioned issues, this application tests and obtains the calprotectin and slgA of the target child, predicts the fluctuations of calprotectin and slgA based on the feeding characteristic sequence, obtains the predicted fluctuating calprotectin and predicted fluctuating slgA, and calculates the actual calprotectin and actual slgA by combining the calprotectin and slgA.

[0037] Specifically, step S30 in the method includes: Using sample extraction solution and fecal sampling tubes, fecal samples from the target children were pre-processed for analysis. The fecal samples of the target substances were collected and quantitatively extracted in advance, and the calprotectin and slgA of the target children were tested and obtained. The age, physical characteristics, and eating characteristics sequence are input into the fluctuation predictor, and the predicted fluctuation calprotectin and predicted fluctuation slgA are output. Based on the calprotectin and slgA, combined with the predicted fluctuating calprotectin and predicted fluctuating slgA, the actual calprotectin and actual slgA are calculated.

[0038] In this embodiment, a sample extraction solution and a fecal sampling tube are first used to pre-process the fecal sample from the target child before analysis. The fecal sample containing the analyte is collected and quantitatively extracted in advance to obtain calprotectin and sIgA from the target child. Exemplarily, a sample extraction solution and a matching fecal sampling tube can be used to pre-process the fecal sample before analysis, allowing for the collection and quantitative extraction of the analyte from the fecal sample to obtain calprotectin and sIgA. This avoids the influence of interfering substances on the detection results. The extracted solution can be directly detected on a fully automated chemiluminescence analyzer. For high-concentration samples, the fully automated chemiluminescence analyzer can automatically dilute and perform data back-calculation.

[0039] Secondly, the age, physical characteristics, and dietary characteristics sequence are input into the fluctuation predictor, which outputs predicted fluctuation calprotectin and predicted fluctuation slgA. The fluctuation predictor is built based on machine learning and can predict predicted fluctuation calprotectin and predicted fluctuation slgA based on the target child's age, physical characteristics, and dietary characteristics sequence. Predicted fluctuation calprotectin represents the temporary change in calprotectin due to dietary characteristics and individual physiological factors, while predicted fluctuation slgA represents the temporary change in slgA due to dietary characteristics and individual physiological factors. For example, inputting a 3-year-old child weighing 18kg who has consumed 100g of red meat daily for the past 3 days into the fluctuation predictor results in a predicted fluctuation calprotectin of +15μg / g and a predicted fluctuation slgA of +10μg / g. This is because calprotectin temporarily increases due to red meat intake, and slgA temporarily increases due to dietary stimulation.

[0040] Finally, based on the calprotectin and slgA levels obtained from the test for the target child, and combined with the predicted fluctuations in calprotectin and slgA, the actual calprotectin and slgA are calculated. The actual calprotectin = calprotectin - predicted fluctuations in calprotectin, and the actual slgA = slgA - predicted fluctuations in slgA. For example, if the tested calprotectin level is 115 μg / g and the predicted fluctuation in calprotectin is +15 μg / g, then the actual calprotectin = 115 - 15 = 100 μg / g. This eliminates the interference of reversible factors such as short-term feeding characteristics, obtaining actual calprotectin and slgA levels that more closely approximate the true physiological state, avoiding misjudging physiological fluctuations as pathological conditions, and improving the accuracy of the assessment.

[0041] Specifically, the "fluctuation predictor" is trained using the following steps: Based on machine learning, a fluctuation predictor is constructed, wherein the input data of the fluctuation predictor are age, body characteristics and food intake characteristic sequences, and the output data are fluctuation calprotectin and fluctuation slgA. Based on the false positive detection data of calprotectin and slgA in children, we collected sample age sets, sample body characteristic sets, and sample food intake characteristic sequence sets, and labeled and obtained sample fluctuating calprotectin sets and sample fluctuating slgA sets. The fluctuation predictor is iteratively supervised and trained using the sample age set, sample body feature set, sample food intake feature sequence set, sample fluctuation calprotectin set, and sample fluctuation slgA set.

[0042] In this embodiment, a fluctuation predictor is first constructed based on machine learning. The input data of the fluctuation predictor are age, body characteristics, and feeding feature sequences, and the output data are fluctuation calprotectin and fluctuation slgA. Fluctuation calprotectin refers to the short-term fluctuation amplitude of calprotectin, and fluctuation slgA refers to the short-term fluctuation amplitude of slgA. For example, the fluctuation predictor can adopt a neural network architecture, which captures the mapping relationship between the input data (age, body characteristics, and feeding feature sequences) and the output data (fluctuation calprotectin and fluctuation slgA) through multi-layer nonlinear transformation. It mainly consists of an input layer, a hidden layer (which can contain 1-3 layers, adjusted according to feature complexity), and an output layer. The number of neurons in the input layer is consistent with the total dimension of the input features. For example, if there is 1 feature (age), 5 indicators (body characteristics), and 8 parameters (feeding feature sequences), for a total of 14 dimensions of parameters, then the number of neurons in the input layer is 14. The hidden layer performs feature extraction and association learning by setting an appropriate number of neurons (such as 64 or 32). The output layer has 2 neurons, corresponding to the output values ​​of predicted fluctuation calprotectin and predicted fluctuation slgA, respectively.

[0043] Secondly, based on the false-positive test data of calprotectin and slgA in children, sample age sets, sample physical characteristic sets, and sample dietary characteristic sequence sets were collected. Additionally, sample fluctuation sets of calprotectin and slgA were obtained through annotation. False-positive test data refers to cases with abnormal test data but confirmed by clinical follow-up to have no pathological problems such as intestinal inflammation or immune dysfunction. For example, false-positive test data of calprotectin and slgA in children were screened from historical clinical data, and key information was extracted to form sample sets: sample age sets (e.g., age data of 200 children), sample physical characteristic sets (e.g., corresponding children's weight, allergy history, etc.), and sample dietary characteristic sequence sets (e.g., dietary structure and special food intake records for the 3 days prior to testing, etc.). Simultaneously, normal calprotectin and slgA reference values ​​for these samples after excluding short-term interference were determined through clinical evaluation, such as test values ​​under stable physical conditions without dietary stimulation, combined with the test results from false-positive cases. The fluctuation values ​​of calprotectin and slgA are calculated. For example, if the clinically tested calprotectin of a sample is 120 μg / g and its normal reference value is 75 μg / g, then the fluctuation value of calprotectin for this sample is 120 - 75 = +45 μg / g. Similarly, the fluctuation value of slgA is calculated. In this way, the fluctuation sets of calprotectin and slgA for the sample are obtained, providing a true label for short-term fluctuations for the model. This enables the fluctuation predictor to learn the correlation between different combinations of age, physical characteristics, and eating characteristics and the fluctuation of calprotectin and slgA.

[0044] Finally, the fluctuation predictor is iteratively supervised and trained using the sample age set, sample body feature set, sample food intake feature sequence set, sample fluctuation calprotectin set, and sample fluctuation slgA set. For example, the training process of the fluctuation predictor can be implemented through the following technical path: 1. Data preparation: The sample age set, sample body feature set, sample food intake feature sequence set, and the corresponding sample fluctuation calprotectin set and sample fluctuation slgA set are divided into a training set (for model parameter learning), a validation set (for adjusting hyperparameters during training), and a test set (for final evaluation of the model's generalization ability) in a 7:1.5:1.5 ratio. 2. Model Training: Using the age, body characteristics, and food intake sequence corresponding to the training set as input features, and sample fluctuation calprotectin and sample fluctuation slgA as supervision labels, the Adam optimizer is used to iteratively adjust model parameters, such as the weights and biases of the neural network. Mean squared error is used as the loss function to continuously reduce the prediction error. During the training process, the model performance is monitored through the validation set to avoid overfitting. When the model's prediction accuracy on the test set is >95%, it is considered to have converged, and the fluctuation predictor is obtained.

[0045] In summary, compared to existing technologies, this application obtains calprotectin and slgA from the target child through testing, predicts fluctuations in calprotectin and slgA based on the feeding characteristic sequence, and obtains predicted fluctuating calprotectin and predicted fluctuating slgA. Combining these calprotectin and slgA, the actual calprotectin and actual slgA are calculated. Thus, by combining the tested calprotectin and slgA of the target child with the fluctuation prediction results output by the model, the actual calprotectin and actual slgA that accurately reflect the child's digestive state are obtained. This eliminates the interference of reversible factors such as short-term feeding characteristics, avoids misjudging physiological fluctuations as pathological states, and improves the accuracy of the assessment.

[0046] S40: Calculate the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA, combine them with the corrected baseline error coefficient, calculate the data confidence level, label the actual calprotectin and actual slgA, and conduct a digestive status assessment for children.

[0047] Children's digestive indicators, such as calprotectin and sIgA, are easily affected by factors such as age, diet, and individual constitution, resulting in physiological fluctuations. Traditional assessment methods often directly use raw test values ​​for judgment without quantitatively assessing the reliability of the data (such as whether it is affected by short-term interference or whether it conforms to individual physiological patterns). This can easily lead to misjudging physiological fluctuations as pathological abnormalities or missing true lesions due to ignoring data errors, ultimately affecting the accuracy of assessing children's digestive status.

[0048] To address the aforementioned issues, this application calculates the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA, and combines these with the corrected baseline error coefficient to calculate the data confidence level. The actual calprotectin and actual slgA are then labeled to assess the digestive status of children.

[0049] Specifically, step S40 in the method includes: The fluctuation coefficient is obtained by calculating the average fluctuation amplitude of the predicted fluctuating calprotectin and the predicted fluctuating slgA with that of the baseline calprotectin and the baseline slgA. Based on the corrected baseline error coefficient and fluctuation coefficient, the detection error degree is calculated, and the data confidence degree is calculated. Using the aforementioned data confidence level, actual calprotectin and actual slgA were labeled to assess the digestive status of children.

[0050] In this embodiment of the application, the average fluctuation amplitude of the predicted fluctuating calprotectin and the predicted fluctuating slgA is first calculated with respect to the baseline calprotectin and the baseline slgA to obtain the fluctuation coefficient. The fluctuation amplitude of the predicted fluctuating calprotectin and the baseline calprotectin is calculated as |predicted fluctuating calprotectin - baseline calprotectin| / baseline calprotectin, and the fluctuation amplitude of the predicted fluctuating slgA and the baseline slgA is calculated as |predicted fluctuating slgA - baseline slgA| / baseline slgA. For example, if the predicted fluctuation of calprotectin is +15 μg / g, the predicted fluctuation of slgA is +10 μg / g, the baseline calprotectin is 50 μg / g, and the baseline slgA is 60 μg / g, then the fluctuation amplitude of the predicted fluctuation of calprotectin and the baseline calprotectin is |15-50| / 50=0.7, and the fluctuation amplitude of the predicted fluctuation of slgA and the baseline slgA is |10-60| / 60=0.83. Then, the mean is calculated to obtain the fluctuation coefficient = (0.7+0.83) / 2=0.767. The fluctuation coefficient can quantify the degree of deviation between the predicted fluctuation of calprotectin and the predicted fluctuation of slgA and the baseline calprotectin and the baseline slgA. The larger the fluctuation coefficient, the stronger the temporary interference caused by feeding characteristics or individual physiological factors.

[0051] Secondly, based on the corrected baseline error coefficient and the fluctuation coefficient, the detection error degree and data confidence degree are calculated. The detection error degree = corrected baseline error coefficient + fluctuation coefficient, and the data confidence degree = 1 / (1 + detection error degree). The corrected baseline error coefficient reflects systematic errors caused by individual developmental differences in children, while the fluctuation coefficient reflects situational errors caused by feeding characteristics or temporary physiological disturbances. The detection error degree combines systematic and situational errors. The data confidence degree decreases non-linearly with increasing detection error degree, reflecting the reliability of the detection data. For example, if the corrected baseline error coefficient is 12.43% and the fluctuation coefficient is 0.767, then the detection error degree = 12.43% + 0.767 = 0.8913, and the data confidence degree = 1 / (1 + 0.8913) = 0.53. This indicates that the data reliability is generally low. A judgment threshold can be dynamically set, for example, 0.5. If the value is below the judgment threshold, a forced retesting mechanism is triggered. In this way, the reliability of the actual test data for calprotectin and multiple slgA is quantified.

[0052] Finally, data confidence levels were used to label the actual calprotectin and actual slgA to assess the digestive status of children. For example, actual calprotectin was 100 μg / g with data confidence level, and actual slgA was 65 μg / g with data confidence level. The digestive status was then assessed based on the labeling results. For example, the following method can be used to assess a child's digestive status: If the actual calprotectin and actual slgA are within the range of baseline calprotectin ± corrected baseline error coefficient and baseline slgA ± corrected baseline error coefficient, and the data confidence level (e.g., ≥80%), the digestive status is considered normal, and the fluctuation is within the normal physiological range for the individual; if the actual calprotectin exceeds the above range, and the data confidence level is high, it suggests possible intestinal inflammation (e.g., infection, mucosal damage, etc.); if the actual slgA exceeds the above range, and the data confidence level is high, it suggests possible intestinal immune dysfunction (e.g., susceptibility to infection, flora imbalance). Combining both, it is judged as digestive dysfunction (e.g., inflammation combined with immune abnormalities); if the actual calprotectin and actual slgA exceed the above range, but the data confidence level is low (e.g., <60%), it suggests that the data may be affected by uncaptured factors and is unreliable. Data needs to be collected again or combined with clinical symptoms for comprehensive judgment to avoid misjudgment.

[0053] In summary, compared to existing technologies, this application calculates the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA, and combines this with the corrected baseline error coefficient to calculate the data confidence level. The actual calprotectin and actual slgA are then labeled for assessing the child's digestive status. This approach avoids missing reliable anomalies and reduces misjudgments based on unreliable data, ensuring that the final digestive status assessment is based on objective data while also considering data reliability, thereby achieving an accurate and scientific determination of the child's digestive status.

[0054] In summary, the embodiments of this application have at least the following technical effects: Compared to existing technologies, this application first collects the age of the target children, sets baseline calprotectin and baseline slgA, and obtains the baseline error coefficient. In this way, by age matching, the normal range of calprotectin and slgA indicators corresponding to the developmental stage of the target children is determined, providing a reliable comparative standard for subsequent assessment.

[0055] Secondly, this application collects the physical characteristics and recent eating characteristic sequences of the target children within a preset time range, configures physical characteristic correction coefficients and eating correction coefficients, and corrects the baseline error coefficient to obtain a corrected baseline error coefficient. In this way, by fully considering individual differences and incorporating the physical characteristics and recent eating characteristics of the target children, the group-based baseline error coefficient is corrected to a more individualized correction baseline error coefficient, thereby improving the accuracy of the assessment.

[0056] Furthermore, this application obtains calprotectin and slgA from the target child through testing. Based on the feeding characteristic sequence, fluctuations in calprotectin and slgA are predicted to obtain predicted fluctuating calprotectin and predicted fluctuating slgA. Combining the calprotectin and slgA, the actual calprotectin and actual slgA are calculated. Thus, by combining the calprotectin and slgA obtained from the test with the fluctuation prediction results output by the model, the actual calprotectin and actual slgA that accurately reflect the child's digestive state are obtained. This eliminates the interference of reversible factors such as short-term feeding characteristics, avoids misjudging physiological fluctuations as pathological states, and improves the accuracy of the assessment.

[0057] Finally, this application calculates the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA. Combining this with the corrected baseline error coefficient, a data confidence level is calculated. The actual calprotectin and actual slgA are then labeled for assessing the child's digestive status. This approach avoids missing reliable abnormalities and reduces misjudgments based on unreliable data, ensuring that the final digestive status assessment is based on objective data while also considering data reliability, thereby achieving an accurate and scientific determination of the child's digestive status.

[0058] Through the above technical solution, this application fully considers key influencing factors such as the target child's age, physical characteristics, and eating habits. It establishes baseline calprotectin and baseline slgA values ​​that align with the developmental stage through age matching. Then, it calculates physical and eating correction coefficients based on physical and eating characteristics, individually correcting the baseline error coefficient to obtain a corrected baseline error coefficient that effectively adapts to individual differences in children. Furthermore, it quantifies short-term physiological fluctuations caused by interference from diet and physical characteristics using a fluctuation predictor constructed through machine learning, and calculates data confidence based on the corrected baseline error coefficient, thus achieving reliable labeling of actual test values. In this way, it reduces the interference of physiological fluctuations caused by the immaturity and poor functional stability of the child's intestines, improving the reliability of test results. Compared with traditional methods, it can more accurately distinguish between physiological fluctuations and pathological abnormalities, providing a scientific basis for children's intestinal inflammation, immune dysfunction, and other issues, and assisting in precise clinical intervention.

[0059] Example 2, as Figure 2 As shown, based on the same inventive concept as the method for assessing children's digestive status using the combined determination of calprotectin and sIgA provided in Example 1, this embodiment of the invention also provides a system for assessing children's digestive status using the combined determination of calprotectin and sIgA, comprising: The data acquisition module 11 is used to collect the age of the target children, configure the baseline calprotectin and baseline slgA, and obtain the baseline error coefficient; Error correction module 12 is used to collect the physical characteristics of the target child and the feeding characteristic sequence within the most recent preset time range, configure the physical characteristic correction coefficient and the feeding correction coefficient, correct the baseline error coefficient, and obtain the corrected baseline error coefficient. The fluctuation prediction module 13 is used to test and obtain the calprotectin and slgA of the target child, predict the fluctuation of calprotectin and slgA based on the feeding characteristic sequence, obtain the predicted fluctuation of calprotectin and the predicted fluctuation of slgA, and calculate the actual calprotectin and the actual slgA by combining the calprotectin and slgA. The status assessment module 14 is used to calculate the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating slgA with the baseline calprotectin and baseline slgA, and to calculate the data confidence level by combining the corrected baseline error coefficient, and to label the actual calprotectin and actual slgA to assess the digestive status of children.

[0060] Specifically, the data acquisition module 11 is used for: Collect the age of the target children; Obtain the average calprotectin and average slgA of children of the same age under normal digestive conditions; The average calprotectin and average slgA were used as baseline calprotectin and baseline slgA. Based on the baseline calprotectin and baseline slgA, the baseline error coefficient is obtained through processing.

[0061] Specifically, the step of "processing to obtain baseline error coefficients based on the baseline calprotectin and baseline slgA" includes: Several children of the same age were randomly selected, and multiple samples of calprotectin and slgA were obtained through testing. The baseline error coefficient is obtained by calculating the average deviation of calprotectin and slgA from baseline calprotectin and slgA in multiple samples.

[0062] Specifically, the error correction module 12 is used for: Collect the target child's physical characteristics and eating characteristic sequences within the most recent preset time range; Obtain the average physical characteristics and average eating characteristics sequences of children of the same age; The deviation of the physical characteristics and feeding characteristics sequence from the average physical characteristics and average feeding characteristics sequence is calculated and used as the physical characteristics correction coefficient and feeding correction coefficient. The baseline error coefficient is corrected by using the vital sign correction coefficient and the feeding correction coefficient to obtain the corrected baseline error coefficient.

[0063] Specifically, the fluctuation prediction module 13 is used for: Using sample extraction solution and fecal sampling tubes, fecal samples from the target children were pre-processed for analysis. The fecal samples of the target substances were collected and quantitatively extracted in advance, and the calprotectin and slgA of the target children were tested and obtained. The age, physical characteristics, and eating characteristics sequence are input into the fluctuation predictor, and the predicted fluctuation calprotectin and predicted fluctuation slgA are output. Based on the calprotectin and slgA, combined with the predicted fluctuating calprotectin and predicted fluctuating slgA, the actual calprotectin and actual slgA are calculated.

[0064] Specifically, the "fluctuation predictor" is trained using the following steps: Based on machine learning, a fluctuation predictor is constructed, wherein the input data of the fluctuation predictor are age, body characteristics and food intake characteristic sequences, and the output data are fluctuation calprotectin and fluctuation slgA. Based on the false positive detection data of calprotectin and slgA in children, we collected sample age sets, sample body characteristic sets, and sample food intake characteristic sequence sets, and labeled and obtained sample fluctuating calprotectin sets and sample fluctuating slgA sets. The fluctuation predictor is iteratively supervised and trained using the sample age set, sample body feature set, sample food intake feature sequence set, sample fluctuation calprotectin set, and sample fluctuation slgA set.

[0065] Specifically, the state evaluation module 14 is used for: The fluctuation coefficient is obtained by calculating the average fluctuation amplitude of the predicted fluctuating calprotectin and the predicted fluctuating slgA with that of the baseline calprotectin and the baseline slgA. Based on the corrected baseline error coefficient and fluctuation coefficient, the detection error degree is calculated, and the data confidence degree is calculated. Using the aforementioned data confidence level, actual calprotectin and actual slgA were labeled to assess the digestive status of children.

[0066] In summary, the embodiments of this application have at least the following technical effects: Compared to existing technologies, this application first uses a data acquisition module to collect the age of the target children, configure baseline calprotectin and baseline slgA, and obtain a baseline error coefficient. By age matching, it determines the normal range of calprotectin and slgA indicators that conforms to the developmental stage of the target children, providing a reliable comparative standard for subsequent assessments. Secondly, through an error correction module, it collects the target children's physical characteristics and recent feeding characteristic sequences within a preset time range, configures physical characteristic correction coefficients and feeding correction coefficients, and corrects the baseline error coefficient to obtain a corrected baseline error coefficient. This fully considers individual differences; by incorporating the target children's physical characteristics and recent feeding characteristics, the population-based baseline error coefficient is corrected to a more individualized corrected baseline error coefficient, thereby improving the accuracy of the assessment. Furthermore, through the fluctuation prediction module, the calprotectin and slgA of the target child are obtained through testing. Based on the feeding characteristic sequence, the fluctuation of calprotectin and slgA is predicted to obtain the predicted fluctuating calprotectin and predicted fluctuating slgA. Combining calprotectin and slgA, the actual calprotectin and actual slgA are calculated. By combining the calprotectin and slgA of the target child obtained through testing with the fluctuation prediction results output by the model, the actual calprotectin and actual slgA that can accurately reflect the child's digestive state are obtained. This eliminates the interference of reversible factors such as short-term feeding characteristics, avoids misjudging physiological fluctuations as pathological states, and improves the accuracy of the assessment. Finally, the status assessment module calculates the fluctuation coefficients of predicted fluctuating calprotectin and predicted fluctuating slgA compared to baseline calprotectin and baseline slgA. Combined with the corrected baseline error coefficient, the data confidence level is calculated, and the actual calprotectin and actual slgA are labeled for assessing the child's digestive status. This approach avoids missing reliable abnormalities and reduces misjudgments based on unreliable data, ensuring that the final digestive status assessment is based on both objective and reliable data, thus achieving a precise and scientific determination of the child's digestive status. This reduces the interference of physiological fluctuations caused by the immaturity and poor functional stability of the child's intestines, improving the reliability of the test results. Compared to traditional methods, it can more accurately distinguish between physiological fluctuations and pathological abnormalities, providing a scientific basis for addressing issues such as intestinal inflammation and immune dysfunction in children, and supporting precise clinical intervention.

[0067] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0073] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for assessing the digestive status of children by combining calprotectin and sIgA, characterized in that, The method includes: Collect the age of the target children, configure baseline calprotectin and baseline sIgA, and obtain the baseline error coefficient; Collect the physical characteristics and feeding characteristic sequences of the target child within the most recent preset time range, configure the vital sign correction coefficient and feeding correction coefficient, and correct the baseline error coefficient to obtain the corrected baseline error coefficient; The test obtains the calprotectin and sIgA of the target child. Based on the feeding characteristic sequence, the fluctuation of calprotectin and sIgA is predicted to obtain the predicted fluctuation of calprotectin and sIgA. Combined with the calprotectin and sIgA of the target child obtained by the test, the actual calprotectin and actual sIgA are calculated. The fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating sIgA with the baseline calprotectin and baseline sIgA are calculated. Combined with the corrected baseline error coefficient, the data confidence level is calculated. The actual calprotectin and actual sIgA are labeled to assess the digestive status of children. Collect the age of the target children, configure baseline calprotectin and baseline sIgA, and obtain the baseline error coefficient, including: Collect the age of the target children; Obtain the average calprotectin and average sIgA of children of the same age under normal digestive conditions; The average calprotectin and average sIgA were used as baseline calprotectin and baseline sIgA, respectively. Several children of the same age were randomly selected, and multiple samples of calprotectin and sIgA were obtained through testing. Calculate the average deviation of multiple samples of calprotectin and multiple samples of sIgA from baseline calprotectin and baseline sIgA to obtain the baseline error coefficient; Collect the physical characteristics and feeding characteristic sequences of the target child within the most recent preset time range, configure vital sign correction coefficients and feeding correction coefficients, and correct the baseline error coefficient to obtain the corrected baseline error coefficient, including: Collect the target child's physical characteristics and eating characteristic sequences within the most recent preset time range; Obtain the average physical characteristics and average eating characteristics sequences of children of the same age; The deviation of the physical characteristics and feeding characteristics sequence from the average physical characteristics and average feeding characteristics sequence is calculated and used as the physical characteristics correction coefficient and feeding correction coefficient. The baseline error coefficient is corrected by using the vital sign correction coefficient and the feeding correction coefficient to obtain the corrected baseline error coefficient. The test obtains the calprotectin and sIgA of the target child. Based on the feeding characteristic sequence, the fluctuation of calprotectin and sIgA is predicted to obtain the predicted fluctuating calprotectin and sIgA. Combining the calprotectin and sIgA of the target child obtained from the test, the actual calprotectin and actual sIgA are calculated, including: Using sample extraction solution and fecal sampling tubes, fecal samples from the target children were pre-processed for analysis, and the substances to be tested were collected and quantitatively extracted in advance to obtain calprotectin and sIgA from the target children. The age, physical characteristics, and eating characteristics sequence are input into the fluctuation predictor, and the predicted fluctuation calprotectin and predicted fluctuation sIgA are output. Based on the calprotectin and sIgA of the target child obtained from the test, combined with the predicted fluctuating calprotectin and predicted fluctuating sIgA, the actual calprotectin and actual sIgA are calculated. The fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating sIgA with the baseline calprotectin and baseline sIgA are calculated. Combined with the corrected baseline error coefficient, a data confidence level is calculated. The actual calprotectin and actual sIgA are then labeled, and a child's digestive status is assessed, including: The fluctuation coefficient is obtained by calculating the average fluctuation amplitude of the predicted fluctuating calprotectin and predicted fluctuating sIgA with that of the baseline calprotectin and baseline sIgA. Based on the corrected baseline error coefficient and the fluctuation coefficient, the detection error degree is calculated, and the data confidence degree is calculated; where, the detection error degree = corrected baseline error coefficient + fluctuation coefficient, and the data confidence degree = 1 / (1 + detection error degree). Using the aforementioned data confidence level, actual calprotectin and actual sIgA were labeled to assess the digestive status of children.

2. The method for assessing children's digestive status by combining calprotectin and sIgA according to claim 1, characterized in that, The volatility predictor is trained using the following steps: Based on machine learning, a fluctuation predictor is constructed, wherein the input data of the fluctuation predictor are age, body characteristics and food intake characteristic sequences, and the output data are fluctuation calprotectin and fluctuation sIgA. Based on false positive detection data of calprotectin and sIgA in children, we collected sample age sets, sample body characteristic sets, and sample food intake characteristic sequence sets, and labeled and obtained sample fluctuating calprotectin sets and sample fluctuating sIgA sets. The fluctuation predictor is iteratively supervised and trained using the sample age set, sample body feature set, sample food intake feature sequence set, sample fluctuation calprotectin set, and sample fluctuation sIgA set.

3. A system for assessing the digestive status of children by combining the determination of calprotectin and sIgA, used to implement the method for assessing the digestive status of children by combining the determination of calprotectin and sIgA as described in claim 1, characterized in that, include: The data acquisition module is used to collect the age of the target children, configure baseline calprotectin and baseline sIgA, and obtain the baseline error coefficient; The error correction module is used to collect the physical characteristics of the target child and the feeding characteristic sequence within the most recent preset time range, configure the vital sign correction coefficient and the feeding correction coefficient, correct the baseline error coefficient, and obtain the corrected baseline error coefficient. The fluctuation prediction module is used to test and obtain the calprotectin and sIgA of the target child, predict the fluctuation of calprotectin and sIgA based on the feeding characteristic sequence, obtain the predicted fluctuation of calprotectin and the predicted fluctuation of sIgA, and calculate the actual calprotectin and the actual sIgA by combining the calprotectin and sIgA. The status assessment module is used to calculate the fluctuation coefficients of the predicted fluctuating calprotectin and predicted fluctuating sIgA with the baseline calprotectin and baseline sIgA, and to calculate the data confidence level by combining the corrected baseline error coefficient, thereby labeling the actual calprotectin and actual sIgA and assessing the digestive status of children.

Images