Traditional Chinese medicine use data analysis system for pediatric department

Abstract

The invention provides a pediatric traditional Chinese medicine medication data analysis system. The pediatric traditional Chinese medicine medication data analysis system comprises a data acquisition and preprocessing module, a medication effect recovery module and a data analysis and decision module. The data acquisition and preprocessing module is used for acquiring, preprocessing and classifying traditional Chinese medicine use data and extracting medicine types, medicine doses and medicine use frequencies. The medication effect recovery module recovers the medication effect curve of the medicine in the patient based on the medication dosage. And the data analysis and decision-making module compares the current patient medication data with the effective medication model and the medication model to be observed, updates model data, identifies abnormal data, transfers stable data into the effective model, and discards invalid data. According to the system, accurate analysis of traditional Chinese medicine medication is achieved through multi-dimensional data analysis, medication decision is optimized, and the safety and effectiveness of pediatric traditional Chinese medicine medication are improved. The scientificity and the safety of pediatric traditional Chinese medicine medication can be effectively improved, the abnormal condition of medication is reduced, and the treatment effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data analysis, and more specifically, to a traditional Chinese medicine medication data analysis system for pediatrics. Background Art

[0002] In the field of pediatric medicine, the application of traditional Chinese medicine has a long history and unique advantages. However, there are still many deficiencies in the management and analysis of pediatric traditional Chinese medicine. Traditional Chinese medicine mainly relies on clinical experience and the subjective judgment of doctors, lacking systematic and data-based analysis methods. Especially in terms of dosage, frequency of use and evaluation of medication effects, due to the large individual differences among children and the rapid changes in their condition, it is difficult to achieve accurate medication based on experience alone. In addition, most of the existing medication data are scattered and have not been effectively integrated, making it difficult to conduct large-scale analysis and model building.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: there is a lack of systematic analysis tools for pediatric Chinese medicine medication data, and the medication data cannot be effectively preprocessed, classified and accurately analyzed; it is difficult to accurately evaluate the actual medication effect of the drug in patients, and the medication model cannot be dynamically updated and optimized; the ability to identify and process abnormal medication data is insufficient, which can easily lead to deviations in medication decisions, affecting treatment effects and patient safety. Summary of the invention

[0004] The present invention provides a Chinese medicine medication data analysis system for pediatrics, comprising: A data acquisition and preprocessing module is used to acquire the Chinese medicine medication data of pediatric patients, and preprocess and classify the data to obtain the drug type, dosage and frequency of medication; A medication effect recovery module, used for recovering the medication effect curve of the drug in the patient based on the medication dosage; The data analysis and decision-making module is used to realize accurate analysis of Chinese medicine based on the medication effect curve, drug type, dosage and frequency of medication by using multi-dimensional data analysis: compare the current patient's medication data with the data in the effective medication model and the medication model to be observed, and update the data in the effective medication model and the medication model to be observed when there is a feature match between the two; the current data that does not have a feature match in the effective medication model and the medication model to be observed is regarded as abnormal data; check the medication model to be observed, move the stably updated data therein to the effective medication model, and regard the data that cannot be updated for multiple consecutive times as invalid data and discard it; check the effective medication model, and for the data that has not been updated, find its change trend according to the medication dosage, and if there is no result, continue to retain the current data and change trend, and use the data in the effective medication model as the medication analysis result of this stage. Furthermore, the data acquisition and preprocessing module also includes: An average dose calculation unit, used to calculate the average dose of the medicine in the traditional Chinese medicine medication data and record it as an average dose graph; A dosage fluctuation calculation unit, used to calculate the dosage fluctuation range of the medicine in the traditional Chinese medicine medication data, recorded as a dosage fluctuation graph; The data optimization unit is used for weighted superposition of the average dose map and the dose fluctuation map as optimization data. Furthermore, the data acquisition and preprocessing module also includes: A drug significance analysis unit, used for analyzing the Chinese medicine medication data using a drug analysis model group, and taking the maximum value of a component at each data position in the obtained analysis data group to obtain a drug significance map; The data fusion unit is used for weighted superposition of the average dose map, the dose fluctuation map and the drug significance map as optimization data. Furthermore, in the average dose calculation unit, a normal distribution model is used to represent the drug dose distribution of the traditional Chinese medicine medication data, and the normal distribution model is:

[0005] In the formula, Indicates drug dosage, represents the standard deviation of the dose, Indicates the mean dose. Furthermore, in the dosage fluctuation calculation unit, the dosage fluctuation range of the drug in the traditional Chinese medicine medication data is:

[0006] In the formula, Indicates drug dosage, Indicates the maximum dose value, Indicates the minimum dose value. Furthermore, in the dosage fluctuation calculation unit, the dosage fluctuation range of the drug in the traditional Chinese medicine medication data is calculated as follows: the traditional Chinese medicine medication data is processed using a sliding average filter and a median filter and the absolute value of the difference between the two filtered data is taken as the dosage fluctuation range of the drug in the traditional Chinese medicine medication data. Furthermore, in the data acquisition and preprocessing module, the dynamic threshold is:

[0007] In the formula, is the dynamic threshold, For range The threshold coefficient represents the linear position of the dynamic threshold from the mean to the maximum value. To optimize the average dose value of the data, is the maximum dose value for the optimization data.

[0008] Furthermore, in the medication effect recovery module, the boundary threshold is:

[0009] In the formula, is the boundary threshold of drug dosage, The dosage strength of the drug. Furthermore, in the data analysis and decision-making module, the features include drug dosage and medication frequency, and if the dosage difference between the current patient's medication data and the data in the effective medication model and the medication model to be observed is within the dosage fluctuation range and the difference between the medication frequencies does not exceed the frequency threshold, the features are considered to be consistent. Furthermore, in the data analysis and decision-making module, if abnormal data appears at the high-dose end of the current patient's medication data, it is considered to be abnormal data of overdose and is added to the medication model to be observed; otherwise, it is considered to be invalid data and is discarded.

[0010] The above-mentioned embodiments of the present invention have at least the following beneficial effects: the system can effectively improve the accuracy and scientificity of pediatric Chinese medicine medication. The Chinese medicine medication data is classified and optimized by the data acquisition and preprocessing module, and the medication effect recovery module is combined to accurately restore the medication effect curve of the drug in the patient. The system can provide clinicians with a more comprehensive and accurate medication reference, thereby improving the treatment effect and reducing the risk of medication.

[0011] In addition, the system can dynamically update effective medication models and medication models to be observed, intelligently identify and classify abnormal data, and ensure the accuracy and timeliness of medication data. This dynamic optimization mechanism can better adapt to the characteristics of pediatric patients with large individual differences and rapid changes in their conditions, provide strong support for clinical decision-making, and further improve the safety and effectiveness of pediatric Chinese medicine. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram of the structure of a traditional Chinese medicine data analysis system for pediatrics provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0013] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0014] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0015] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0016] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of a pediatric Chinese medicine medication data analysis system provided by one embodiment of the present invention. Figure 1 As shown, a pediatric Chinese medicine medication data analysis system 100 includes: The data acquisition and preprocessing module 101 is used to acquire the Chinese medicine medication data of pediatric patients, and preprocess and classify the data to obtain the drug type, dosage and frequency of medication; A medication effect recovery module 102, configured to recover the medication effect curve of the drug in the patient based on the medication dosage; The data analysis and decision-making module 103 is used to realize accurate analysis of Chinese medicine based on the medication effect curve, drug type, dosage and frequency of medication by using multi-dimensional data analysis: compare the current patient's medication data with the data in the effective medication model and the medication model to be observed, and update the data in the effective medication model and the medication model to be observed when there is a feature match between the two; the current data that does not have a feature match in the effective medication model and the medication model to be observed is regarded as abnormal data; check the medication model to be observed, move the data that is stably updated therein to the effective medication model, and regard the data that cannot be updated for multiple consecutive times as invalid data and discard it; check the effective medication model, and for the data that has not been updated, find its change trend according to the medication dosage, and if there is no result, continue to retain the current data and change trend, and use the data in the effective medication model as the medication analysis result of this stage. It should be noted that one of the core modules of this system is the data acquisition and preprocessing module, whose main function is to obtain the Chinese medicine medication data of pediatric patients and preprocess and classify these data. Data acquisition here refers to collecting patients' Chinese medicine medication information from hospital information systems, electronic medical records or clinician records, including drug types, dosages and frequency of use. Preprocessing is to clean, filter and format these raw data so that subsequent modules can process them more efficiently. For example, the type of drug refers to the name of the Chinese medicine used by the patient, the dosage refers to the amount of Chinese medicine used each time, and the frequency of use refers to the number of times the medicine is used per unit time.

[0017] Specifically, the data acquisition and preprocessing module also includes an average dose calculation unit and a dose fluctuation calculation unit. The average dose calculation unit is used to calculate the average dose of drugs in the Chinese medicine medication data, that is, by statistically analyzing a large number of patient dosage data, the average dosage of a certain drug in a specific age group or condition is obtained. The dose fluctuation calculation unit is used to calculate the fluctuation range of the drug dose, that is, by analyzing the difference between the maximum dose value and the minimum dose value, the stability of the drug dose is evaluated. For example, for a commonly used Chinese medicine, its average dose may be 10 grams per dose, and the dose fluctuation range may be 5 grams to 15 grams, which indicates that in the actual medication process, the dose of the drug fluctuates between 5 grams and 15 grams.

[0018] Preferably, the average dose calculation unit can use a normal distribution model to represent the drug dose distribution. The normal distribution model is a commonly used statistical model used to describe the central tendency and dispersion of data. In this system, the parameters of the normal distribution model include the mean value of the dose ( ) and standard deviation ( ), these parameters can be used to more accurately calculate the average dosage of a drug. For example, for a certain traditional Chinese medicine, by collecting a large amount of sample data, the mean of its dosage is calculated to be 10 grams and the standard deviation is 2 grams, which means that the dosage of most patients is concentrated between 6 grams and 14 grams.

[0019] Furthermore, the dosage fluctuation calculation unit can process the data using sliding average filtering and median filtering to reduce the impact of outliers, and determine the dosage fluctuation range by calculating the difference of the filtered data. This processing method can more accurately reflect the actual fluctuation of the drug dosage and provide more reliable data support for subsequent drug effect analysis.

[0020] In some embodiments, the data acquisition and preprocessing module further includes: An average dose calculation unit, used to calculate the average dose of the medicine in the traditional Chinese medicine medication data and record it as an average dose graph; A dosage fluctuation calculation unit, used to calculate the dosage fluctuation range of the medicine in the traditional Chinese medicine medication data, recorded as a dosage fluctuation graph; The data optimization unit is used for weighted superposition of the average dose map and the dose fluctuation map as optimization data. It should be noted that the data acquisition and preprocessing module further includes an average dose calculation unit and a dose fluctuation calculation unit, which are the key parts for a more in-depth analysis of the TCM medication data. The function of the average dose calculation unit is to calculate the average dose of the drug in the TCM medication data and present the result in the form of an average dose graph. The average dose graph here refers to the drug dose distribution graph obtained through statistical analysis, which can intuitively show the average dosage of a certain drug in different patients. The dose fluctuation calculation unit is used to calculate the fluctuation range of the drug dose and display it in the form of a dose fluctuation graph. The dose fluctuation graph here refers to the range of changes in drug doses in different patients or at different time points, which can reflect the stability of the drug dose.

[0021] Specifically, the average dose calculation unit can collect medication data from a large number of patients and calculate the average dose of a certain drug in a specific age group or condition. For example, for a traditional Chinese medicine commonly used to treat children's cough, statistical analysis found that its average dose is 10 grams per dose. The dose fluctuation calculation unit can determine the dose fluctuation range by calculating the difference between the maximum dose value and the minimum dose value. For example, for the above-mentioned traditional Chinese medicine, the maximum dose value is 15 grams and the minimum dose value is 5 grams, then the dose fluctuation range is 10 grams. In actual applications, the settings of these parameters can be adjusted according to factors such as the characteristics of the specific drug, the patient's age, weight, and the severity of the disease. For example, for younger children, the dose may be appropriately reduced, while for patients with more serious conditions, the dose may be appropriately increased.

[0022] Preferably, the average dose calculation unit can use a normal distribution model to represent the drug dose distribution. The normal distribution model is a commonly used statistical model, and its formula is:

[0023] In the formula, Indicates drug dosage, represents the standard deviation of the dose, Indicates the mean dose. Through this model, the average dose of the drug can be calculated more accurately. For example, for a certain Chinese medicine, by collecting a large amount of sample data, the mean of its dose is calculated to be 10 grams and the standard deviation is 2 grams. This means that the dosage of most patients is concentrated between 6 grams and 14 grams. In addition, the dose fluctuation calculation unit can use sliding average filtering and median filtering to process the data to reduce the impact of outliers, and determine the dose fluctuation range by calculating the difference of the filtered data. For example, the original data can be first processed by sliding average filtering, then by median filtering, and finally the absolute value of the difference between the two sets of filtered data is calculated as the dose fluctuation range. This processing method can more accurately reflect the actual fluctuation of the drug dosage and provide more reliable data support for subsequent analysis of the effect of medication.

[0024] In some embodiments, the data acquisition and preprocessing module further includes: A drug significance analysis unit, used for analyzing the Chinese medicine medication data using a drug analysis model group, and taking the maximum value of a component at each data position in the obtained analysis data group to obtain a drug significance map; The data fusion unit is used for weighted superposition of the average dose map, the dose fluctuation map and the drug significance map as optimization data. It should be noted that the data acquisition and preprocessing module further includes a drug significance analysis unit and a data fusion unit. The function of the drug significance analysis unit is to use the drug analysis model group to analyze the Chinese medicine medication data, and take the maximum value of the component at each data position in the obtained analysis data group to obtain a drug significance map. The drug significance map here refers to a visual chart reflecting the significance of the drug generated by analyzing the efficacy and importance of the drug in different patients. The function of the data fusion unit is to weightedly superimpose the average dose map, the dose fluctuation map and the drug significance map to generate optimized data. The optimized data here refers to the data after comprehensive analysis and processing, which can more comprehensively reflect the use and effect of the drug.

[0025] Specifically, the drug significance analysis unit can process the TCM medication data through a variety of drug analysis models. For example, a statistically based model, such as analysis of variance (ANOVA) or regression analysis, can be used to evaluate the difference in the efficacy of drugs in different patients. In the analysis process, the maximum value of the component at each data position refers to selecting the largest value at that position in the analysis results of multiple models to highlight the significance of the drug in this regard. For example, for a traditional Chinese medicine for treating children's colds, by analyzing multiple indicators such as its fever-reducing effect and cough-relieving effect in different patients, the maximum value of each indicator is selected to generate a drug significance map. The data fusion unit comprehensively processes the average dose map, the dose fluctuation map, and the drug significance map by weighted superposition. The weighted superposition here means assigning different weight coefficients according to the importance of each chart, and then merging them into a comprehensive data. For example, the weight of the average dose map can be set to 0.4, the weight of the dose fluctuation map can be set to 0.3, and the weight of the drug significance map can be set to 0.3, and the optimized data can be generated by weighted summation.

[0026] Preferably, the drug significance analysis unit can use a variety of analysis methods to improve the accuracy of the results. For example, in addition to statistical models, machine learning algorithms such as support vector machines (SVM) or random forests (RandomForest) can be combined to evaluate the efficacy and importance of drugs. These algorithms can automatically learn the performance patterns of drugs in different patients based on a large amount of clinical data, thereby generating drug significance maps more accurately. In the data fusion unit, the distribution of weights can be adjusted according to the specific application scenario and analysis objectives. For example, in some cases, if the dose fluctuation has a greater impact on the treatment effect, the weight of the dose fluctuation map can be appropriately increased.

[0027] Furthermore, a dynamic adjustment mechanism can be introduced to automatically adjust the weight according to the changes in real-time data to ensure the timeliness and accuracy of the optimized data. For example, when it is found that the dosage fluctuation of a certain drug has a significant impact on the treatment effect, the system can automatically increase the weight of the dosage fluctuation graph to more accurately reflect the actual use of the drug.

[0028] In some embodiments, in the average dose calculation unit, a normal distribution model is used to represent the drug dose distribution of the traditional Chinese medicine medication data, and the normal distribution model is:

[0029] In the formula, Indicates drug dosage, represents the standard deviation of the dose, Indicates the mean dose. It should be noted that the average dose calculation unit uses the normal distribution model to represent the drug dose distribution of traditional Chinese medicine data. The normal distribution model is a commonly used statistical model used to describe the central tendency and dispersion of data. In this system, the normal distribution model uses a mathematical formula to express the distribution of drug doses, where the parameters in the formula include drug dose ( ), the mean of the dose ( ) and the standard deviation of the dose ( ). Through this model, the average dosage of the drug can be calculated more accurately, thus providing basic data support for subsequent drug analysis.

[0030] In practical applications, the mean It can be calculated by taking the average value of a large number of sample data, while the standard deviation It indicates the degree of dispersion of the data, which can be calculated by statistical methods. For example, for a traditional Chinese medicine commonly used to treat children's cough, suppose the collected dosage data is: 5 grams, 10 grams, 12 grams, 8 grams, 9 grams, etc. By performing statistical analysis on these data, the mean can be calculated. 9 grams, standard deviation This means that the dosage of most patients is concentrated between 5 grams and 13 grams, and is normally distributed with 9 grams as the center. This model can help the system more accurately evaluate the reasonable range of drug dosage and provide a reference for subsequent dosage optimization.

[0031] Preferably, in order to further improve the accuracy and applicability of the model, the normal distribution model can be adjusted and optimized in practical applications. For example, the mean can be adjusted according to factors such as the characteristics of the drug, the age and weight of the patient, etc. and standard deviation Dynamic adjustment. For pediatric patients, due to their different physiological characteristics and drug metabolism ability from adults, it may be necessary to calculate the mean and standard deviation according to age and weight. For example, for children under 3 years old, the mean can be adjusted to 7 grams and the standard deviation to 1.5 grams; for children over 6 years old, the mean can be adjusted to 10 grams and the standard deviation can be adjusted to 2.5 grams.

[0032] Furthermore, other statistical models or machine learning algorithms, such as Bayesian estimation or neural networks in deep learning, can be introduced to further optimize the modeling process of dose distribution. These methods can automatically learn the distribution law of drug doses based on a large amount of clinical data, thereby more accurately reflecting the actual use of drugs.

[0033] In some embodiments, in the dosage fluctuation calculation unit, the dosage fluctuation range of the drug in the traditional Chinese medicine medication data is:

[0034] In the formula, Indicates drug dosage, Indicates the maximum dose value, Indicates the minimum dose value. It should be noted that the dose fluctuation calculation unit is used to calculate the fluctuation range of drug doses in TCM medication data. The dose fluctuation range here refers to the difference between the maximum and minimum values ​​of drug doses in different patients or at different time points. This indicator can be used to evaluate the stability of drug doses. For example, for a certain TCM, if its dose fluctuation range is large, it may mean that the dose control is not accurate enough in actual use and needs further optimization.

[0035] Specifically, the calculation formula for the dosage fluctuation range is:

[0036] in, Indicates drug dosage, Indicates the maximum dose value, Indicates the minimum dose value. In practical applications, the maximum and minimum dose values ​​can be obtained by statistically analyzing a large amount of medication data collected. For example, for a Chinese medicine used to treat children's colds, it is found through analysis that its maximum dose is 15 grams and its minimum dose is 5 grams, so its dose fluctuation range is 10 grams. This range can help doctors understand the fluctuation of doses in the actual medication process, so as to better adjust the medication plan.

[0037] Preferably, in order to more accurately calculate the dosage fluctuation range, the original data can be preprocessed by sliding average filtering and median filtering. The sliding average filter can smooth the short-term fluctuations in the data, while the median filter can effectively remove the outliers in the data. The specific operation steps are as follows: First, the original data is subjected to sliding average filtering, and the window size can be set according to the sampling frequency of the data and the frequency of use of the drug. For example, for daily medication data, the window size can be set to 7 days. Then the filtered data is subjected to median filtering, and the window size can also be adjusted according to the characteristics of the data. Finally, the absolute value of the difference between the data after the two filtering processes is calculated as the dosage fluctuation range. This method can effectively reduce the influence of noise and outliers in the data on the calculation of the dosage fluctuation range and improve the reliability of the results. In addition, other filtering methods or data processing techniques, such as Gaussian filtering or wavelet transform, can be selected according to the characteristics of the drug or clinical needs to further optimize the calculation process of the dosage fluctuation range.

[0038] In some embodiments, in the dosage fluctuation calculation unit, the dosage fluctuation range of the drug in the traditional Chinese medicine medication data is calculated as follows: the traditional Chinese medicine medication data is processed using a sliding average filter and a median filter and the absolute value of the difference between the two filtered data is taken as the dosage fluctuation range of the drug in the traditional Chinese medicine medication data. It should be noted that the dosage fluctuation calculation unit uses sliding average filtering and median filtering to process the Chinese medicine data, and calculates the fluctuation range of the drug dosage by taking the absolute value of the difference between the two filtered data. The sliding average filter mentioned here is a commonly used data smoothing technology, which reduces the impact of short-term fluctuations by taking the average of continuous data points in the data sequence; while the median filter is a nonlinear filtering technology that removes outliers by taking the median of the data sequence. The combination of these two filtering methods can effectively improve the accuracy and reliability of the dosage fluctuation range calculation.

[0039] Specifically, the window size of the sliding average filter can be set according to the sampling frequency of the data and the frequency of drug use. For example, for daily recorded medication data, the window size can be set to 7 days, which means that data from 7 consecutive days will be considered each time the average value is calculated. The window size of the median filter can also be adjusted according to the characteristics of the data, and is usually consistent with the window size of the sliding average filter. In actual operation, the sliding average filter is first applied to the original medication data to obtain a smoothed data sequence; then the median filter is applied to the same data sequence to obtain a data sequence after removing outliers. Finally, the absolute value of the difference between the corresponding points of the two filtered data sequences is calculated as the fluctuation range of the drug dosage. For example, assuming that the dosage of a certain Chinese medicine in 7 consecutive days is 10 grams, 12 grams, 8 grams, 11 grams, 9 grams, 13 grams and 7 grams respectively, the sequence obtained after the sliding average filter may be 10 grams, 10.3 grams, 10 grams, 10 grams, 10.3 grams, 10 grams, and the sequence obtained after the median filter may be 10 grams, 10 grams, 10 grams, 10 grams, 10 grams, 10 grams, 10 grams. By calculating the absolute value of the difference between the two sequences, the specific value of the dosage fluctuation range can be obtained.

[0040] Preferably, in order to further improve the accuracy of the dosage fluctuation range calculation, the parameters of the sliding average filter and the median filter can be optimized. For example, different window sizes can be tried, and the optimal window size can be selected by cross-validation and other methods to ensure that the filtered data can better reflect the actual fluctuation of the drug dosage.

[0041] Furthermore, other filtering techniques can be introduced as alternatives, such as Gaussian filtering or wavelet transform. Gaussian filtering is a smoothing filtering method based on Gaussian function, which can process data more smoothly; wavelet transform can analyze data in both time and frequency domains, and is suitable for processing medication data with complex fluctuation patterns. Through these optimizations and alternatives, the fluctuation of drug dosage can be evaluated more comprehensively, providing a more scientific basis for clinical medication.

[0042] In some embodiments, in the data acquisition and preprocessing module, the dynamic threshold is:

[0043] In the formula, is the dynamic threshold, For range The threshold coefficient represents the linear position of the dynamic threshold from the mean to the maximum value. To optimize the average dose value of the data, is the maximum dose value for the optimization data.

[0044] It should be noted that the data acquisition and preprocessing module also includes the calculation of dynamic thresholds. Dynamic thresholds refer to thresholds that are dynamically adjusted according to data changes and are used to determine the validity and abnormality of data. Specifically, the calculation formula for dynamic thresholds is:

[0045] in, represents the dynamic threshold, is the threshold coefficient in the range of [0,1], indicating the linear position of the dynamic threshold from the mean to the maximum value, To optimize the average dose value of the data, To optimize the maximum dose value of the data. In this way, the threshold can be dynamically adjusted according to the actual situation of the data to improve the accuracy of the judgment.

[0046] Specifically, the calculation of the dynamic threshold requires first determining the average dose value and the maximum dose value of the optimized data. The average dose value of the optimized data can be obtained by statistically analyzing a large amount of sample data. For example, for a certain Chinese medicine, statistical analysis shows that its average dose is 10 grams. The maximum dose value of the optimized data refers to the maximum dose value that appears in all sample data. For example, for the above Chinese medicine, the maximum dose value is 15 grams. Threshold coefficient The choice can be adjusted according to the specific application scenario. For example, for a scene that requires higher sensitivity, a larger value, so that the dynamic threshold is closer to the maximum dose value; for scenes that require higher stability, a smaller value, making the dynamic threshold closer to the average dose value.

[0047] Preferably, in order to further improve the applicability of dynamic thresholds, multiple calculation methods and adjustment mechanisms can be introduced. For example, the threshold can be dynamically adjusted according to the changing trend of historical data. The dynamic threshold can be better adapted to the changes in data by adjusting the value. In addition, the dynamic threshold can be optimized by combining other statistical models or machine learning algorithms, such as Bayesian estimation or neural networks in deep learning. For example, the threshold coefficient can be dynamically adjusted according to the distribution of historical data through Bayesian estimation. ; or through deep learning algorithms, automatically learn the change pattern of data to more accurately calculate the dynamic threshold. These methods can further improve the accuracy and applicability of dynamic thresholds and provide a more scientific basis for judging the validity of data.

[0048] In some embodiments, in the medication effect recovery module, the boundary threshold is:

[0049] In the formula, is the boundary threshold of drug dosage, The dosage strength of the drug. It should be noted that the concept of boundary threshold is introduced in the medication effect recovery module. The boundary threshold refers to a key parameter used to determine whether the drug dosage reaches an effective treatment level. Its calculation formula is:

[0050] in, represents the boundary threshold of drug dosage, Indicates the dosage strength of the drug. Through this boundary threshold, it is possible to more scientifically evaluate whether the drug dosage is within the effective range, thereby providing a basis for restoring the effect of the medication.

[0051] Specifically, the calculation of the boundary threshold depends on the dosage intensity parameter of the drug. The dosage intensity refers to the intensity of the therapeutic effect that a drug can exert at a unit dose, which is usually obtained through clinical trials or pharmacological studies. For example, for a certain traditional Chinese medicine, its dosage intensity may be determined through pharmacodynamic experiments as the specific therapeutic effect that can be produced per gram of the drug. The coefficient of the boundary threshold of 0.707 is an empirical coefficient used to convert the dosage intensity into a reasonable boundary threshold. For example, if the dosage intensity of a certain traditional Chinese medicine is 20 units of efficacy per gram, then its boundary threshold is:

[0052] This means that only when the drug dose reaches or exceeds 14.14 units is it considered to have a sufficient therapeutic effect. In this way, it is possible to effectively distinguish whether the drug dose is within the effective range, thereby providing a scientific basis for the recovery of the medication effect.

[0053] Preferably, the coefficient of the boundary threshold can be adjusted according to the characteristics of the specific drug and clinical needs. For example, for some drugs with strong efficacy but large side effects, the coefficient can be appropriately lowered to ensure the safety of medication; and for some drugs with weaker efficacy but smaller side effects, the coefficient can be appropriately increased to ensure the therapeutic effect. In addition, a dynamic adjustment mechanism can be introduced to dynamically adjust the boundary threshold according to the individual differences of patients (such as age, weight, severity of illness, etc.). For example, for pediatric patients, the coefficient can be adjusted to 0.6, and for adult patients, the coefficient can be adjusted to 0.8. This dynamic adjustment mechanism can better adapt to the needs of different patients and improve the accuracy of drug effect evaluation.

[0054] In some embodiments, in the data analysis and decision-making module, the features include drug dosage and medication frequency, and if the dosage difference between the current patient's medication data and the data in the effective medication model and the medication model to be observed is within the dosage fluctuation range and the difference between the medication frequencies does not exceed the frequency threshold, the features are considered to be consistent. It should be noted that the data analysis and decision-making module will consider two key features, drug dosage and medication frequency, when comparing medication data. When the current patient's medication data meets specific conditions in terms of dosage difference and medication frequency difference with the data in the effective medication model and the medication model to be observed, the characteristics of the two are considered to be consistent. The dosage difference here refers to the difference between the current patient's medication dosage and the dosage in the model, while the medication frequency difference refers to the difference between the current patient's medication frequency and the frequency in the model. In this way, the system can determine whether the current medication data matches the existing effective or to-be-observed model, thereby updating the model or identifying abnormal data.

[0055] Specifically, the calculation formula for the dose difference is:

[0056] in, Indicates the current patient's medication dosage. Represents the dosage of medication in the model. The calculation formula for the difference in medication frequency is:

[0057] in, Indicates the current frequency of medication for the patient. Indicates the frequency of medication in the model. The system sets a dose fluctuation range and a frequency threshold. When the dose difference is within the dose fluctuation range and the medication frequency difference does not exceed the frequency threshold, the feature is considered to be consistent. For example, the dose fluctuation range can be set to 5 grams, and the frequency threshold can be set to once a day. This means that if the current patient's medication dose does not differ from the dose in the model by more than 5 grams, and the medication frequency difference does not exceed once a day, the current data is considered to be consistent with the model features.

[0058] Preferably, the dose fluctuation range and frequency threshold can be adjusted according to the characteristics of the specific drug and clinical needs. For example, for some drugs with strong efficacy but large side effects, the dose fluctuation range can be appropriately narrowed to ensure the safety and accuracy of medication; and for some drugs with weaker efficacy but smaller side effects, the dose fluctuation range can be appropriately expanded to improve the applicability of the model. The frequency threshold can also be adjusted according to the frequency of drug use. For example, for drugs that require frequent use, the frequency threshold can be set to twice a day; and for drugs that do not require frequent use, the frequency threshold can be set to once a week.

[0059] Furthermore, a dynamic adjustment mechanism can be introduced to dynamically adjust the dosage fluctuation range and frequency threshold according to individual differences of patients (such as age, weight, severity of illness, etc.). For example, for pediatric patients, the dosage fluctuation range can be set to 3 grams, and the frequency threshold can be set to 0.5 times per day; while for adult patients, the dosage fluctuation range can be set to 7 grams, and the frequency threshold can be set to 1.5 times per day. This dynamic adjustment mechanism can better meet the needs of different patients and improve the accuracy and reliability of drug data comparison.

[0060] In some embodiments, in the data analysis and decision-making module, if abnormal data appears at the high-dose end of the current patient's medication data, it is considered to be abnormal data of overdose and is added to the medication model to be observed; otherwise, it is considered to be invalid data and is discarded.

[0061] It should be noted that when processing abnormal data, the data analysis and decision-making module will classify and process the abnormal data according to the location where the abnormal data appears. If the abnormal data appears at the high-dose end of the current patient's medication data, it is considered to be abnormal data of overdose and is added to the medication model to be observed; otherwise, it is considered invalid data and discarded. The high-dose end here refers to the part where the drug dose exceeds the upper limit of the normal medication range, which is usually related to the safety and potential side effects of the drug. Through this classification and processing method, the system can effectively identify and manage abnormal medication situations to ensure the safety and rationality of medication.

[0062] Specifically, the definition of the high-dose end can be achieved by setting a dose threshold. For example, for a certain Chinese medicine, the normal dosage range is 5 grams to 15 grams, so the part exceeding 15 grams can be regarded as the high-dose end. When the data analysis and decision-making module detects that the current patient's medication dosage exceeds this threshold, it will be marked as abnormal data of overdose. At this time, the system will add these abnormal data to the medication model to be observed for further analysis and observation of their possible impact. On the contrary, if the abnormal data appears at the lower end of the dosage range or within the normal range, but does not match the effective medication model and the medication model to be observed, the data is considered invalid and discarded to avoid interference with subsequent analysis.

[0063] Preferably, the dose threshold can be dynamically adjusted according to the characteristics of the specific drug and clinical needs. For example, for some drugs with strong efficacy but large side effects, the threshold at the high dose end can be set lower to more strictly control the dosage; while for some drugs with weak efficacy and small side effects, the threshold at the high dose end can be appropriately increased.

[0064] Furthermore, individual patient differences, such as age, weight, and severity of illness, can be introduced to personalize the dose threshold. For example, for pediatric patients, the high-dose threshold can be set to 12 grams, while for adult patients, it can be set to 18 grams. This dynamic and personalized adjustment mechanism can more accurately identify abnormal data of overdose, while avoiding misjudgment due to one-size-fits-all threshold settings.

[0065] The above-mentioned embodiments of the present invention have the following beneficial effects: the system can accurately obtain the Chinese medicine medication data of pediatric patients through the data acquisition and preprocessing module, and classify and optimize the processing, so as to extract key information such as drug type, dosage and frequency of medication. The medication effect recovery module can accurately restore the medication effect curve of the drug in the patient based on the medication dosage, provide clinicians with a more comprehensive medication reference, improve the treatment effect and reduce the risk of medication. The data analysis and decision-making module can realize the accurate analysis and dynamic optimization of Chinese medicine medication through multi-dimensional data analysis, and ensure the accuracy and timeliness of medication data.

[0066] In addition, the system can dynamically update effective medication models and medication models to be observed, intelligently identify and classify abnormal data, and ensure the scientificity and safety of medication decisions. Through functions such as average dose calculation, dose fluctuation calculation, and drug significance analysis, the system can comprehensively analyze and optimize medication data to adapt to the characteristics of large individual differences and rapid changes in the condition of pediatric patients, provide strong support for clinical decision-making, and further improve the safety and effectiveness of pediatric Chinese medicine.

[0067] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0068] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A Chinese medicine medication data analysis system for pediatrics, characterized in that: Includes the following modules: A data acquisition and preprocessing module is used to acquire the Chinese medicine medication data of pediatric patients, and preprocess and classify the data to obtain the drug type, dosage and frequency of medication; A medication effect recovery module, used for recovering the medication effect curve of the drug in the patient based on the medication dosage; The data analysis and decision-making module is used to realize accurate analysis of Chinese medicine based on the medication effect curve, drug type, dosage and frequency of medication by multi-dimensional data analysis: compare the current patient's medication data with the data in the effective medication model and the medication model to be observed, and update the data in the effective medication model and the medication model to be observed when there is a feature match between the two; the current data that does not have a feature match in the effective medication model and the medication model to be observed is regarded as abnormal data; check the medication model to be observed, move the stably updated data therein to the effective medication model, and regard the data that cannot be updated for multiple consecutive times as invalid data and discard it; check the effective medication model, and for the data that has not been updated, find its change trend according to the medication dosage, and if there is no result, continue to retain the current data and change trend, and use the data in the effective medication model as the medication analysis result of this stage.

2. The Chinese medicine medication data analysis system for pediatrics according to claim 1, characterized in that: The data acquisition and preprocessing module also includes: An average dose calculation unit, used to calculate the average dose of the medicine in the traditional Chinese medicine medication data and record it as an average dose graph; A dosage fluctuation calculation unit, used to calculate the dosage fluctuation range of the medicine in the traditional Chinese medicine medication data, recorded as a dosage fluctuation graph; The data optimization unit is used for weighted superposition of the average dose map and the dose fluctuation map as optimization data.

3. The Chinese medicine data analysis system for pediatrics according to claim 2, characterized in that: The data acquisition and preprocessing module also includes: A drug significance analysis unit, used for analyzing the Chinese medicine medication data using a drug analysis model group, and taking the maximum value of a component at each data position in the obtained analysis data group to obtain a drug significance map; The data fusion unit is used for weighted superposition of the average dose map, the dose fluctuation map and the drug significance map as optimization data.

4. The Chinese medicine data analysis system for pediatrics according to claim 2 or 3, characterized in that: In the average dose calculation unit, a normal distribution model is used to represent the drug dose distribution of the traditional Chinese medicine medication data, and the normal distribution model is: In the formula, Indicates drug dosage, represents the standard deviation of the dose, Indicates the mean dose.

5. The Chinese medicine medication data analysis system for pediatrics according to claim 4, characterized in that: In the dosage fluctuation calculation unit, the dosage fluctuation range of the medicine in the traditional Chinese medicine medication data is: In the formula, Indicates drug dosage, Indicates the maximum dose value, Indicates the minimum dose value.

6. The Chinese medicine data analysis system for pediatrics according to claim 5, characterized in that: In the dosage fluctuation calculation unit, the dosage fluctuation range of the drugs in the traditional Chinese medicine medication data is calculated as follows: the traditional Chinese medicine medication data is processed using a sliding average filter and a median filter and the absolute value of the difference between the two filtered data is taken as the dosage fluctuation range of the drugs in the traditional Chinese medicine medication data.

7. The Chinese medicine data analysis system for pediatrics according to claim 6, characterized in that: In the data acquisition and preprocessing module, the dynamic threshold is: In the formula, is the dynamic threshold, For range The threshold coefficient represents the linear position of the dynamic threshold from the mean to the maximum value. To optimize the average dose value of the data, is the maximum dose value for the optimization data.

8. The Chinese medicine data analysis system for pediatrics according to claim 7, characterized in that: In the medication effect recovery module, the boundary threshold is: In the formula, is the boundary threshold of drug dosage, The dosage strength of the drug.

9. The Chinese medicine data analysis system for pediatrics according to claim 8, characterized in that: In the data analysis and decision-making module, the features include drug dosage and medication frequency, and if the dosage difference between the current patient's medication data and the data in the effective medication model and the medication model to be observed is within the dosage fluctuation range and the difference between the medication frequencies does not exceed the frequency threshold, the features are considered to be consistent.

10. The Chinese medicine data analysis system for pediatrics according to claim 9, characterized in that: In the data analysis and decision-making module, if abnormal data appears at the high-dose end of the current patient's medication data, it is considered to be abnormal data of overdose and is added to the medication model to be observed; otherwise, it is considered to be invalid data and is discarded.

Images