Traditional Chinese medicine internal medicine case data processing method and system based on cloud computing

Abstract

The invention discloses a traditional Chinese medicine internal medicine case data processing method and system based on cloud computing, and relates to the technical field of intelligent management, and the method comprises the following steps: setting keywords and traditional Chinese medicine syndrome differentiation types, recognizing synonyms, synonyms and derivative words of the keywords, obtaining diagnosis data and test data corresponding to case data, and storing the diagnosis data and the test data in a database; screening an effective typing index and an effective age index, calculating the correlation degree between the keyword and the diagnosis data, constructing a first mapping relation and a second mapping relation, calling an expert platform, and obtaining an expert decision. By automatically acquiring and processing case data, the working efficiency is improved, multi-dimensional data are integrated together, a complete patient portrait is formed, keywords, synonyms and synonyms are recognized and processed, the consistency and comparability of the data are enhanced, the effectiveness of different types is objectively evaluated, the accuracy of treatment based on syndrome differentiation is improved, and the patient experience is improved. And more accurate dialectical treatment is carried out by combining the specific conditions of the patient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traditional Chinese medicine, and particularly relates to a traditional Chinese medicine internal medicine case data processing method and system based on cloud computing. BACKGROUND

[0002] In recent years, the traditional Chinese medicine internal medicine case data processing technology is expected to continue to improve the application value in clinical practice, scientific research and education and the like with the progress of technology and the deepening of research, and to provide strong data support for the development of traditional Chinese medicine. Valuable information such as disease regularity and treatment effect is extracted from traditional Chinese medicine case data by using data mining technology. Machine learning and artificial intelligence are applied to traditional Chinese medicine case analysis to help identify patient characteristics, predict disease development and optimize treatment plans. With the help of big data analysis, clinical research of traditional Chinese medicine internal medicine is carried out, and the scientificity and clinical guidance of traditional Chinese medicine theory are improved.

[0003] At present, a traditional Chinese medicine case data processing method and system for sudden acute infectious diseases are disclosed in Chinese patent application CN 104866979 B. The method can effectively improve the evidence level of the scheme by using data mining and appropriate application of artificial intelligence technologies such as case-based reasoning, combining the “five syndrome groups” of traditional Chinese medicine diagnosis and treatment rules and extensive expert consensus. The method is beneficial to improving the scientificity, feasibility and generalizability of the scheme. However, the related art does not perform standardized analysis on the disease to be tested according to the patient's own data, the patient's medical data and the patient's physical symptoms. The method lacks comprehensiveness in grasping the characteristics of the disease and lacks comprehensiveness in data analysis. The method does not uniformly process data in multiple formats, which is not conducive to the clarity and specificity of the analysis, and has certain limitations. SUMMARY

[0004] The technical problem solved by the present application is that the related art does not perform standardized analysis on the disease to be tested according to the patient's own data, the patient's medical data and the patient's physical symptoms. The method lacks comprehensiveness in grasping the characteristics of the disease and lacks comprehensiveness in data analysis. The method does not uniformly process data in multiple formats, which is not conducive to the clarity and specificity of the analysis, and has certain limitations.

[0005] To solve the above technical problems, the present application provides the following technical solutions: in a first aspect, a traditional Chinese medicine internal medicine case data processing method based on cloud computing, comprising the following steps:

[0006] Step S100, acquiring case data and patient information, and calculating the BMI index of the patient according to the patient information;

[0007] Step S200, setting keywords and TCM syndrome differentiation type, identifying synonyms, near synonyms and derivative words of the keywords, extracting sentences corresponding to the keywords, synonyms, near synonyms and derivative words in the case data, and segmenting the sentences to obtain effective sentences, obtaining diagnosis data and test data corresponding to the case data;

[0008] Step S300, counting the number of times of TCM syndrome differentiation type appearing in the diagnosis data, denoted as the first number, filtering effective type indicators according to the first number, setting age stages, counting the number of times of patient information appearing in the age stages, denoted as the second number, filtering effective age indicators, first assigning different age stages according to the effective age indicators, setting a BMI index threshold, second assigning BIM index according to the BMI index threshold, respectively counting the number of times of keywords appearing in the diagnosis data, denoted as the third number, and calculating the association degree of the keywords and the diagnosis data according to the third number;

[0009] Step S400, constructing a first mapping relationship between the assigned age indicators, BIM indicators and association degrees and the diagnosis data, assigning the test data, constructing a second mapping relationship between the assigned test data and the diagnosis data, obtaining first current diagnosis data according to the first mapping relationship, obtaining second current diagnosis data according to the second mapping relationship, and calling an expert platform to obtain expert decision.

[0010] As a preferred scheme of the cloud computing-based TCM internal medicine case data processing method, the step S100 comprises the following sub-steps:

[0011] Step S101, obtaining patient information, wherein the patient information comprises patient number, age, weight and height;

[0012] Step S102, calling a case database, inputting the patient number into the case database, matching the case data corresponding to the patient number, calculating the BMI index of the patient according to the patient weight and the patient height, wherein the BMI index is calculated by a BMI index formula, and the case database comprises patient information, case data, case data number, diagnosis data corresponding to the case data number and test data.

[0013] As a preferred scheme of the cloud computing-based TCM internal medicine case data processing method, the step S200 comprises the following sub-steps:

[0014] Step S201, setting keywords and TCM syndrome differentiation type, identifying synonyms, near synonyms and derivative words of the keywords by Synonyms Chinese near synonym tool;

[0015] The keywords comprise medical history, tongue color, moss quality, spirit, smoking, defecation, drinking, stomach and sweat.

[0016] Synonyms and near-synonyms for the keywords include: surgical history, history of osteoporosis, history of obesity, history of hypertension, history of hyperlipidemia, cardiovascular disease, history of cerebrovascular disease, family history of hereditary diseases, mental fatigue, mental exhaustion, constipation, dark yellow urine, smoking, drinking alcohol, poor appetite, good appetite, thin tongue coating, yellow tongue coating, pale white tongue coating, pale white tongue color, dark tongue color, sweating, and little sweating.

[0017] The TCM syndrome differentiation includes spleen and kidney qi deficiency, dampness and turbidity stagnation, liver stagnation and spleen deficiency, qi deficiency and blood stasis, water and dampness stagnation, yin deficiency and heat excess, qi deficiency and dampness heat accumulation, and spleen deficiency and dampness stagnation transforming into heat.

[0018] Step S202: The sentence is segmented using a string segmentation method. The segmented sentences are traversed, and keywords, synonyms, and near-synonyms are compared with the segmented sentences. Segmented sentences containing keywords, synonyms, and near-synonyms are retained and set as valid sentences. Segmented sentences that do not contain keywords, synonyms, and near-synonyms are deleted.

[0019] Step S203: Obtain the diagnostic data and laboratory data corresponding to the case data, wherein the diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage;

[0020] The test data included fasting blood glucose, triglycerides, and uric acid.

[0021] As a preferred embodiment of the cloud computing-based method for processing TCM internal medicine case data according to the present invention, the method for acquiring the diagnostic data and laboratory data includes:

[0022] Obtain the case data number, retrieve the case database, input the case data number into the case database, match the diagnostic data and laboratory data corresponding to the case data number, and assign numbers to the case data to indicate that the patient had an initial visit or follow-up visit at different times, and performed corresponding laboratory tests, thus obtaining different case data and laboratory data.

[0023] As a preferred embodiment of the cloud computing-based method for processing TCM internal medicine case data according to the present invention, step S300 includes the following sub-steps:

[0024] Step S301: Count the number of times each TCM syndrome differentiation occurs in the diagnostic data, and record it as the first count. The first count includes the first count of the first diagnostic data and the first count of the second diagnostic data.

[0025] Step S302: Filter effective classification indicators based on the first set of data. The filtering logic for the effective classification indicators includes:

[0026] Obtain diagnostic data corresponding to the early stage of metabolic syndrome and diagnostic data corresponding to the confirmed stage of metabolic syndrome. Record the diagnostic data corresponding to the early stage of metabolic syndrome and the diagnostic data corresponding to the confirmed stage of metabolic syndrome as the first diagnostic data and the second diagnostic data, respectively. Count the number of times each TCM syndrome differentiation occurs in the first diagnostic data and the number of times each TCM syndrome differentiation occurs in the second diagnostic data.

[0027] The number of times each TCM syndrome differentiation type appears in the first diagnostic data is recorded as the first frequency of the first diagnostic data.

[0028] The number of times each TCM syndrome differentiation type appears in the second diagnostic data is recorded as the first count of the second diagnostic data.

[0029] Step S303: Set age stages, which include adolescence, youth, middle age and old age. Set 0-14 years old as adolescence, 15-35 years old as youth, 36-60 years old as middle age, and 60-120 years old as old age.

[0030] The age groups are numbered, and the number is represented as X. i , where i is a natural number and i∈[1,4];

[0031] The childhood stage is represented by X1, the youth stage by X2, the middle age stage by X3, and the old age stage by X4;

[0032] Step S304: Compare the patient's age with the age group, count the number of times the patient's age appears in the age group, and record it as the second count;

[0033] Step S305: Filter valid age indicators. The filtering logic for valid age indicators includes:

[0034] Iterate through the second number, sort the second number in descending order, select the second number with the largest value, and set the age stage corresponding to the second number with the largest value as the effective age indicator.

[0035] Step S306: Assign a first value to different age groups based on the effective age index, set the first value as the BMI index threshold, and assign a second value to the BMI index based on the BMI index threshold.

[0036] Step S307: Count the number of times the keyword appears in the diagnostic data, denoted as the third occurrence count. The third occurrence count includes the third occurrence count of the first diagnostic data and the third occurrence count of the second diagnostic data. Calculate the correlation degree between the keyword and the diagnostic data based on the third occurrence count. The correlation degree includes the correlation degree of the first diagnostic data and the correlation degree of the second diagnostic data. The calculation logic for the correlation degree includes:

[0037] Obtain the third count of the first diagnostic data or the third count of the second diagnostic data, and correspondingly obtain the total number of cases corresponding to the first diagnostic data or the total number of cases corresponding to the second diagnostic data. Calculate the ratio of the third count of the first diagnostic data to the total number of cases corresponding to the first diagnostic data, and record it as the correlation degree of the first diagnostic data. Alternatively, calculate the ratio of the third count of the second diagnostic data to the total number of cases corresponding to the second diagnostic data, and record it as the correlation degree of the second diagnostic data.

[0038] As a preferred embodiment of the cloud computing-based method for processing TCM internal medicine case data according to the present invention, the comparison logic between patient age and age group includes:

[0039] The process involves obtaining the patient's age, acquiring any age segment and its number, determining whether the patient's age falls within that age segment, obtaining a determination result (including distribution and non-distribution), and performing a first operation based on the determination result. The first operation includes either acquiring the next age segment or assigning a first mark to the patient's age and counting the number of occurrences of the first mark (referred to as the second count). The first mark corresponds to the age segment number and is represented as NX. i Where N is a natural number, and N represents the second number;

[0040] The logic for the first and second assignments includes:

[0041] Obtain the effective age index and BMI index threshold, obtain the age stage to be assigned and the BMI index to be assigned, and assign the effective age index and BMI index threshold to 1 respectively.

[0042] Calculate the ratio of the upper limit of the age stage to be assigned to the upper limit of the effective age indicator, and record it as the first ratio. Calculate the ratio of the lower limit of the age stage to be assigned to the lower limit of the effective age indicator, and record it as the second ratio. Calculate the average of the first ratio and the second ratio. Calculate the product of the average of the first ratio and the second ratio and 1, and record it as the first product. Set the first product as the first assignment corresponding to the age stage to be assigned.

[0043] Calculate the ratio of the BMI index to be assigned to the BMI index threshold, and record it as the third ratio. Calculate the product of the third ratio and 1, and record it as the second product. Set the second product as the second assignment corresponding to the BMI index to be assigned.

[0044] As a preferred embodiment of the cloud computing-based method for processing TCM internal medicine case data according to the present invention, wherein:

[0045] Secondly, step S400 includes the following sub-steps:

[0046] Step S401: Construct the first mapping relationship between the assigned age index, BIM index, correlation degree and diagnostic data; obtain self-test diagnostic data based on the first mapping relationship; and calculate the sum of each assigned value in the first mapping relationship, denoted as the first sum.

[0047] Set standardized test data, which includes standard fasting blood glucose, standard triglycerides, and standard uric acid. Assign the value 1 to each of the standardized test data. Set the second value to standard fasting blood glucose, the third value to standard triglycerides, and the fourth value to standard uric acid. Obtain test data, calculate the ratio of the test data to the corresponding standardized test data, calculate the product of the ratio of the test data to the corresponding standardized test data and 1, and record it as the fourth product. Set the fourth product as the assigned value of the test data.

[0048] Construct a second mapping relationship between the assigned test data and diagnostic data, obtain the test and diagnostic data based on the second mapping relationship, and calculate the sum of each assigned value in the second mapping relationship, denoted as the second sum.

[0049] Calculate the average of the first and second sums, and record it as the third sum. Set the third sum as the risk value for both self-test diagnostic data and laboratory diagnostic data.

[0050] Step S402: Obtain current patient information, calculate the assigned current age index, current BIM index and current correlation degree based on the current patient information, and obtain the current self-test diagnostic data according to the first mapping relationship;

[0051] The current patient information is entered by the patient themselves, including current age, current height, current weight, current medical history, current tongue color, current tongue coating, current mental state, current smoking status, current bowel movements, current alcohol consumption, and current appetite. The system automatically calculates the values ​​of the current age index, the current BIM index, and the current correlation degree based on the first mapping relationship, and obtains the current self-test diagnostic data and the corresponding first sum value. The current self-test diagnostic data includes the current self-test pre-metabolic syndrome stage and the current self-test diagnosed metabolic syndrome stage.

[0052] Step S403: Obtain the current test data. According to the second mapping relationship, obtain the current test diagnosis data and the corresponding second sum value. The current test diagnosis data includes the current test pre-metabolic syndrome and the current test metabolic syndrome diagnosis period. Compare the current self-test diagnosis data with the current test diagnosis data. Retrieve the expert platform according to the comparison results.

[0053] The current laboratory diagnostic data is generated by the hospital testing the patient's fasting blood glucose, triglycerides, and uric acid, and obtaining a test report. The patient then inputs the current fasting blood glucose, triglyceride, and uric acid values ​​according to the test report. The second mapping relationship automatically calculates the assigned values ​​for the current fasting blood glucose, triglycerides, and uric acid, and obtains the second sum value corresponding to the current laboratory diagnostic data. The current laboratory diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage.

[0054] Automatically calculate the current self-test diagnostic data and obtain the current risk value by combining the corresponding first sum and the corresponding second sum of the current laboratory diagnostic data;

[0055] The comparison results include cases where the current self-test diagnostic data is the same as the current laboratory diagnostic data, and cases where the current self-test diagnostic data is different from the current laboratory diagnostic data.

[0056] When the comparison result shows that the current self-test diagnostic data is different from the current laboratory diagnostic data, the current laboratory diagnostic data will be entered into the expert platform. When the comparison result shows that the current self-test diagnostic data is the same as the current laboratory diagnostic data, either the current self-test diagnostic data or the current laboratory diagnostic data will be entered into the expert platform.

[0057] Step S404: Input the current self-test diagnostic data or current laboratory data, current age index and current BIM index, current correlation degree and current risk value into the expert platform to obtain expert decisions. The expert decisions include dietary decisions and lifestyle decisions. Then, output the current laboratory diagnostic data, the expert decisions and the current risk value to the patient.

[0058] Thirdly, the present invention provides an electronic device, including a storage device, a processor, and computer-readable instructions stored in the storage device. When the computer-readable instructions are executed by the processor, the steps in the cloud computing-based method for processing TCM internal medicine case data described above are performed.

[0059] Fourthly, the present invention provides a storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, it performs the steps of the cloud computing-based method for processing TCM internal medicine case data as described above.

[0060] The beneficial effects of this invention are as follows: By using cloud computing technology, case data is automatically acquired and processed, reducing manual intervention and improving work efficiency. Patient information, case data, diagnostic data, and laboratory data are integrated to form a complete patient profile. The identification and processing of keywords, synonyms, and near-synonyms enhance the consistency and comparability of the data. By statistically analyzing the frequency of TCM syndrome differentiation in diagnostic data, the effectiveness of different differentiations can be objectively evaluated, improving the accuracy of syndrome differentiation and treatment. By setting different age groups and BMI thresholds, combined with the patient's specific condition, more precise syndrome differentiation and treatment can be carried out. By calculating the frequency of keywords in diagnostic data and their correlation with diagnostic results, doctors can identify important symptoms and treatment effects. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of the basic process of a cloud computing-based method for processing medical case data in traditional Chinese medicine, provided as an embodiment of the present invention. Detailed Implementation

[0062] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0063] Example, refer to Figure 1 As an embodiment of the present invention, a method for processing TCM internal medicine case data based on cloud computing is provided, comprising the following steps:

[0064] Step S100: Obtain case data and patient information, and calculate the patient's BMI index based on the patient information;

[0065] Step S200: Set keywords and TCM syndrome differentiation, identify synonyms, near-synonyms and derivatives of the keywords, extract sentences corresponding to the keywords, synonyms, near-synonyms and derivatives in the case data, segment the sentences to obtain valid sentences, and obtain the diagnostic data and laboratory data corresponding to the case data;

[0066] Step S300: Count the number of times TCM syndrome differentiation appears in the diagnostic data, and record it as the first count. Filter effective differentiation indicators based on the first count. Set age stages and count the number of times patient information appears in the age stages, and record it as the second count. Filter effective age indicators and assign first values ​​to different age stages based on the effective age indicators. Set a BMI index threshold and assign a second value to the BMI index based on the BMI index threshold. Count the number of times keywords appear in the diagnostic data, and record it as the third count. Calculate the correlation between keywords and diagnostic data based on the third count.

[0067] Step S400: Construct a first mapping relationship between the assigned age index, BIM index, and correlation degree and the diagnostic data; assign values ​​to the test data; construct a second mapping relationship between the assigned test data and the diagnostic data; obtain the first current diagnostic data based on the first mapping relationship; obtain the second current diagnostic data based on the second mapping relationship; and retrieve the expert platform to obtain expert decisions.

[0068] This invention utilizes cloud computing technology to automatically acquire and process case data, reducing manual intervention and improving work efficiency. It integrates patient information, case data, diagnostic data, and laboratory data to form a complete patient profile. The identification and processing of keywords, synonyms, and near-synonyms enhance data consistency and comparability. By statistically analyzing the frequency of TCM syndrome differentiation in diagnostic data, the effectiveness of different differentiations can be objectively evaluated, improving the accuracy of syndrome differentiation and treatment. By setting different age groups and BMI thresholds, combined with the patient's specific condition, more precise syndrome differentiation and treatment can be carried out. By calculating the frequency of keywords in diagnostic data and their correlation with diagnostic results, it helps doctors identify important symptoms and treatment effects.

[0069] Step S100 includes the following sub-steps:

[0070] Step S101: Obtain patient information, which includes patient number, age, weight, and height;

[0071] Step S102: Call the case database, input the patient number into the case database, match the case data corresponding to the patient number, calculate the patient's BMI index based on the patient's weight and height, the BMI index is calculated using the BMI index formula, the case database includes patient information, case data, case data number, diagnostic data and laboratory data corresponding to the case data number.

[0072] In practice, by obtaining patient ID, age, weight, and height, a complete patient file can be established, providing necessary basic data for subsequent case analysis. Standardizing the acquisition and storage of patient information facilitates subsequent data processing and analysis, improving data usability. The integrated design of the case database enables the association and access of patient information, case data, diagnostic data, and laboratory data, enhancing the convenience of information retrieval. Complete patient information and case data provide a foundation for subsequent data analysis and mining, helping to discover potential disease patterns and treatment effects.

[0073] Step S200 includes the following sub-steps:

[0074] Step S201: Set keywords and TCM syndrome differentiation, and use the Synonyms Chinese synonym tool to identify synonyms, near-synonyms and derivatives of the keywords;

[0075] The keywords include medical history, tongue color, tongue coating, mental state, smoking, bowel movements, alcohol consumption, appetite, and sweating;

[0076] Synonyms and near-synonyms for the keywords include: surgical history, history of osteoporosis, history of obesity, history of hypertension, history of hyperlipidemia, cardiovascular disease, history of cerebrovascular disease, family history of hereditary diseases, mental fatigue, mental exhaustion, constipation, dark yellow urine, smoking, drinking alcohol, poor appetite, good appetite, thin tongue coating, yellow tongue coating, pale white tongue coating, pale white tongue color, dark tongue color, sweating, and little sweating.

[0077] The TCM syndrome differentiation includes spleen and kidney qi deficiency, dampness and turbidity stagnation, liver stagnation and spleen deficiency, qi deficiency and blood stasis, water and dampness stagnation, yin deficiency and heat excess, qi deficiency and dampness heat accumulation, and spleen deficiency and dampness stagnation transforming into heat.

[0078] Step S202: The sentence is segmented using a string segmentation method. The segmented sentences are traversed, and keywords, synonyms, and near-synonyms are compared with the segmented sentences. Segmented sentences containing keywords, synonyms, and near-synonyms are retained and set as valid sentences. Segmented sentences that do not contain keywords, synonyms, and near-synonyms are deleted.

[0079] Step S203: Obtain the diagnostic data and laboratory data corresponding to the case data, wherein the diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage;

[0080] The test data included fasting blood glucose, triglycerides, and uric acid.

[0081] The methods for obtaining the diagnostic data and laboratory data include:

[0082] Obtain the case data number, retrieve the case database, input the case data number into the case database, match the diagnostic data and laboratory data corresponding to the case data number, and assign numbers to the case data to indicate that the patient had an initial visit or follow-up visit at different times, and performed corresponding laboratory tests, thus obtaining different case data and laboratory data.

[0083] In practice, by setting keywords (such as medical history, tongue color, and tongue coating) and combining them with the Synonyms Chinese synonym tool, it is possible to comprehensively identify synonyms, near-synonyms, and derivatives related to these keywords. When processing case data, it can not only accurately capture directly related words but also cover other similar expressions, improving the coverage of data processing. By comparing the segmented sentences with keywords, synonyms, and near-synonyms, it is possible to efficiently filter out effective sentences related to patient symptoms and eliminate irrelevant information, thus improving the efficiency of effective data extraction. Through statistical analysis of TCM syndrome differentiation (such as spleen and kidney qi deficiency and dampness and stagnation), it is possible to accurately identify the patient's disease type based on specific patient symptoms and signs, providing a reliable basis for personalized treatment plan formulation. Combined with the patient's specific medical history, signs, and laboratory data, it is possible to tailor a personalized treatment plan for each patient, thereby improving efficacy.

[0084] Step S300 includes the following sub-steps:

[0085] Step S301: Count the number of times each TCM syndrome differentiation occurs in the diagnostic data, and record it as the first count. The first count includes the first count of the first diagnostic data and the first count of the second diagnostic data.

[0086] Step S302: Filter effective classification indicators based on the first set of data. The filtering logic for the effective classification indicators includes:

[0087] Obtain diagnostic data corresponding to the early stage of metabolic syndrome and diagnostic data corresponding to the confirmed stage of metabolic syndrome. Record the diagnostic data corresponding to the early stage of metabolic syndrome and the diagnostic data corresponding to the confirmed stage of metabolic syndrome as the first diagnostic data and the second diagnostic data, respectively. Count the number of times each TCM syndrome differentiation occurs in the first diagnostic data and the number of times each TCM syndrome differentiation occurs in the second diagnostic data.

[0088] The number of times each TCM syndrome differentiation type appears in the first diagnostic data is recorded as the first frequency of the first diagnostic data.

[0089] The number of times each TCM syndrome differentiation type appears in the second diagnostic data is recorded as the first count of the second diagnostic data.

[0090] Step S303: Set age stages, which include adolescence, youth, middle age and old age. Set 0-14 years old as adolescence, 15-35 years old as youth, 36-60 years old as middle age, and 60-120 years old as old age.

[0091] The age groups are numbered, and the number is denoted as Xi, where i is a natural number and i∈[1,4];

[0092] The childhood stage is represented by X1, the youth stage by X2, the middle age stage by X3, and the old age stage by X4;

[0093] Step S304: Compare the patient's age with the age group, count the number of times the patient's age appears in the age group, and record it as the second count;

[0094] Step S305: Filter valid age indicators. The filtering logic for valid age indicators includes:

[0095] Iterate through the second number, sort the second number in descending order, select the second number with the largest value, and set the age stage corresponding to the second number with the largest value as the effective age indicator.

[0096] Step S306: Assign a first value to different age groups based on the effective age index, set the first value as the BMI index threshold, and assign a second value to the BMI index based on the BMI index threshold.

[0097] Step S307: Count the number of times the keyword appears in the diagnostic data, denoted as the third occurrence count. The third occurrence count includes the third occurrence count of the first diagnostic data and the third occurrence count of the second diagnostic data. Calculate the correlation degree between the keyword and the diagnostic data based on the third occurrence count. The correlation degree includes the correlation degree of the first diagnostic data and the correlation degree of the second diagnostic data. The calculation logic for the correlation degree includes:

[0098] Obtain the third count of the first diagnostic data or the third count of the second diagnostic data, and correspondingly obtain the total number of cases corresponding to the first diagnostic data or the total number of cases corresponding to the second diagnostic data. Calculate the ratio of the third count of the first diagnostic data to the total number of cases corresponding to the first diagnostic data, and record it as the correlation degree of the first diagnostic data. Alternatively, calculate the ratio of the third count of the second diagnostic data to the total number of cases corresponding to the second diagnostic data, and record it as the correlation degree of the second diagnostic data.

[0099] In practice, by statistically analyzing the frequency of each TCM syndrome differentiation in diagnostic data, we can provide basic data for the subsequent screening of effective differentiation indicators, enhancing the objectivity and accuracy of syndrome differentiation. By comparing the frequency of TCM syndrome differentiation in the pre-metabolic syndrome and confirmed syndrome stages, we can screen out more meaningful effective differentiation indicators for clinical diagnosis, providing doctors with more accurate disease analysis basis. Reasonably classifying patients by age—setting four stages: adolescence, youth, middle age, and old age—can more intuitively reflect the age characteristics of patients. Comprehensive analysis of the correlation between patient age stages, BMI index, and keywords increases the applicability of the method. Combining TCM syndrome differentiation with modern medical indicators (such as BMI) helps promote the clinical practice of integrating TCM and Western medicine, improving overall medical outcomes.

[0100] The logic for comparing the patient's age with age groups includes:

[0101] Obtain the patient's age, obtain any age stage and its number, determine whether the patient's age is distributed within the age stage, obtain a determination result, the determination result includes distribution and non-distribution, and perform a first operation based on the determination result, the first operation includes obtaining the next age stage or marking the patient's age with a first mark, and counting the number of times the first mark appears, recorded as the second number, the first mark corresponds to the age stage number, the first mark is represented as NXI, where N is a natural number, N represents the second number;

[0102] The logic for the first and second assignments includes:

[0103] Obtain the effective age index and BMI index threshold, obtain the age stage to be assigned and the BMI index to be assigned, and assign the effective age index and BMI index threshold to 1 respectively.

[0104] Calculate the ratio of the upper limit of the age stage to be assigned to the upper limit of the effective age indicator, and record it as the first ratio. Calculate the ratio of the lower limit of the age stage to be assigned to the lower limit of the effective age indicator, and record it as the second ratio. Calculate the average of the first ratio and the second ratio. Calculate the product of the average of the first ratio and the second ratio and 1, and record it as the first product. Set the first product as the first assignment corresponding to the age stage to be assigned.

[0105] Calculate the ratio of the BMI index to be assigned to the BMI index threshold, and record it as the third ratio. Calculate the product of the third ratio and 1, and record it as the second product. Set the second product as the second assignment corresponding to the BMI index to be assigned.

[0106] In practice, by determining whether patients' ages fall into different age groups (distributed or not), the age group to which patients belong can be accurately identified, ensuring the scientific nature and accuracy of data classification and avoiding improper classification due to incorrect age judgment. Using a first label (NXi) corresponding to the age group number can clearly record the distribution of patients in each age group, thus providing a reliable basis for subsequent data analysis and processing. The entire logical process significantly improves the efficiency of patient data processing through automated comparison and calculation, reduces the need for manual intervention, and lowers the error rate.

[0107] Step S400 includes the following sub-steps:

[0108] Step S401: Construct the first mapping relationship between the assigned age index, BIM index, correlation degree and diagnostic data; obtain self-test diagnostic data based on the first mapping relationship; and calculate the sum of each assigned value in the first mapping relationship, denoted as the first sum.

[0109] Set standardized test data, which includes standard fasting blood glucose, standard triglycerides, and standard uric acid. Assign the value 1 to each of the standardized test data. Set the second value to standard fasting blood glucose, the third value to standard triglycerides, and the fourth value to standard uric acid. Obtain test data, calculate the ratio of the test data to the corresponding standardized test data, calculate the product of the ratio of the test data to the corresponding standardized test data and 1, and record it as the fourth product. Set the fourth product as the assigned value of the test data.

[0110] Construct a second mapping relationship between the assigned test data and diagnostic data, obtain the test and diagnostic data based on the second mapping relationship, and calculate the sum of each assigned value in the second mapping relationship, denoted as the second sum.

[0111] Calculate the average of the first and second sums, and record it as the third sum. Set the third sum as the risk value for both self-test diagnostic data and laboratory diagnostic data.

[0112] Step S402: Obtain current patient information, calculate the assigned current age index, current BIM index and current correlation degree based on the current patient information, and obtain the current self-test diagnostic data according to the first mapping relationship;

[0113] The current patient information is entered by the patient themselves, including current age, current height, current weight, current medical history, current tongue color, current tongue coating, current mental state, current smoking status, current bowel movements, current alcohol consumption, and current appetite. The system automatically calculates the values ​​of the current age index, the current BIM index, and the current correlation degree based on the first mapping relationship, and obtains the current self-test diagnostic data and the corresponding first sum value. The current self-test diagnostic data includes the current self-test pre-metabolic syndrome stage and the current self-test diagnosed metabolic syndrome stage.

[0114] Step S403: Obtain the current test data. According to the second mapping relationship, obtain the current test diagnosis data and the corresponding second sum value. The current test diagnosis data includes the current test pre-metabolic syndrome and the current test metabolic syndrome diagnosis period. Compare the current self-test diagnosis data with the current test diagnosis data. Retrieve the expert platform according to the comparison results.

[0115] The current laboratory diagnostic data is generated by the hospital testing the patient's fasting blood glucose, triglycerides, and uric acid, and obtaining a test report. The patient then inputs the current fasting blood glucose, triglyceride, and uric acid values ​​according to the test report. The second mapping relationship automatically calculates the assigned values ​​for the current fasting blood glucose, triglycerides, and uric acid, and obtains the second sum value corresponding to the current laboratory diagnostic data. The current laboratory diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage.

[0116] Automatically calculate the current self-test diagnostic data and obtain the current risk value by combining the corresponding first sum and the corresponding second sum of the current laboratory diagnostic data;

[0117] The comparison results include cases where the current self-test diagnostic data is the same as the current laboratory diagnostic data, and cases where the current self-test diagnostic data is different from the current laboratory diagnostic data.

[0118] When the comparison result shows that the current self-test diagnostic data is different from the current laboratory diagnostic data, the current laboratory diagnostic data will be entered into the expert platform. When the comparison result shows that the current self-test diagnostic data is the same as the current laboratory diagnostic data, either the current self-test diagnostic data or the current laboratory diagnostic data will be entered into the expert platform.

[0119] Step S404: Input the current self-test diagnostic data or current laboratory data, current age index and current BIM index, current correlation degree and current risk value into the expert platform to obtain expert decisions. The expert decisions include dietary decisions and lifestyle decisions. Then, output the current laboratory diagnostic data, the expert decisions and the current risk value to the patient.

[0120] In practice, by establishing a mapping relationship between assigned age, BMI, and correlation values ​​and diagnostic data, it facilitates the systematic management and analysis of patients' health information. This improves the efficiency and accuracy of data integration, quantifies patients' health status into risk values, and enables doctors and patients to more intuitively understand patients' health conditions, facilitating subsequent health management and intervention. By comparing self-tested diagnostic data with laboratory diagnostic data, potential health risks and discrepancies can be effectively identified. When self-tested data differs from laboratory data, it is promptly input into the expert platform to ensure patients receive professional medical advice. Patients participate in the diagnostic process by inputting personal information, enhancing their sense of participation and responsibility in their own health management, which helps improve health awareness. By dynamically calculating patients' risk values ​​and health indicators, doctors and patients can monitor their health status in real time and adjust treatment plans accordingly, ensuring optimal health management for patients. Through systematic data analysis and expert decision-making, the scientific basis for clinicians in formulating treatment plans can be enhanced, improving treatment effectiveness and patient satisfaction.

[0121] This invention utilizes cloud computing technology to automatically acquire and process case data, reducing manual intervention and improving work efficiency. It integrates patient information, case data, diagnostic data, and laboratory data to form a complete patient profile. The identification and processing of keywords, synonyms, and near-synonyms enhance data consistency and comparability. By statistically analyzing the frequency of TCM syndrome differentiation in diagnostic data, the effectiveness of different differentiations can be objectively evaluated, improving the accuracy of syndrome differentiation and treatment. By setting different age groups and BMI thresholds, combined with the patient's specific condition, more precise syndrome differentiation and treatment can be carried out. By calculating the frequency of keywords in diagnostic data and their correlation with diagnostic results, it helps doctors identify important symptoms and treatment effects.

[0122] 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 implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. 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.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A cloud computing-based method for processing medical case data in Traditional Chinese Medicine (TCM) internal medicine, characterized in that: Includes the following steps: Step S100: Obtain case data and patient information, and calculate the patient's BMI index based on the patient information; Step S200: Set keywords and TCM syndrome differentiation, identify synonyms, near-synonyms and derivatives of the keywords, extract sentences corresponding to the keywords, synonyms, near-synonyms and derivatives in the case data, segment the sentences to obtain valid sentences, and obtain the diagnostic data and laboratory data corresponding to the case data; Step S300: Count the number of times TCM syndrome differentiation appears in the diagnostic data, and record it as the first count. Filter effective differentiation indicators based on the first count. Set age stages and count the number of times patient information appears in the age stages, and record it as the second count. Filter effective age indicators and assign first values ​​to different age stages based on the effective age indicators. Set a BMI index threshold and assign a second value to the BMI index based on the BMI index threshold. Count the number of times keywords appear in the diagnostic data, and record it as the third count. Calculate the correlation between keywords and diagnostic data based on the third count. Step S400: Construct a first mapping relationship between the assigned age index, BIM index, and correlation degree and the diagnostic data; assign values ​​to the test data; construct a second mapping relationship between the assigned test data and the diagnostic data; obtain the first current diagnostic data based on the first mapping relationship; obtain the second current diagnostic data based on the second mapping relationship; and retrieve the expert platform to obtain expert decisions.

2. The method for processing TCM internal medicine case data based on cloud computing as described in claim 1, characterized in that: Step S100 includes the following sub-steps: Step S101: Obtain patient information, which includes patient number, age, weight, and height; Step S102: Call the case database, input the patient number into the case database, match the case data corresponding to the patient number, calculate the patient's BMI index based on the patient's weight and height, the BMI index is calculated using the BMI index formula, the case database includes patient information, case data, case data number, diagnostic data and laboratory data corresponding to the case data number.

3. The method for processing TCM internal medicine case data based on cloud computing as described in claim 1, characterized in that: Step S200 includes the following sub-steps: Step S201: Set keywords and TCM syndrome differentiation, and use the Synonyms Chinese synonym tool to identify synonyms, near-synonyms and derivatives of the keywords; The keywords include medical history, tongue color, tongue coating, mental state, smoking, bowel movements, alcohol consumption, appetite, and sweating; Synonyms and near-synonyms for the keywords include: surgical history, history of osteoporosis, history of obesity, history of hypertension, history of hyperlipidemia, cardiovascular disease, history of cerebrovascular disease, family history of hereditary diseases, mental fatigue, mental exhaustion, constipation, dark yellow urine, smoking, drinking alcohol, poor appetite, good appetite, thin tongue coating, yellow tongue coating, pale white tongue coating, pale white tongue color, dark tongue color, sweating, and little sweating. The TCM syndrome differentiation includes spleen and kidney qi deficiency, dampness and turbidity stagnation, liver stagnation and spleen deficiency, qi deficiency and blood stasis, water and dampness stagnation, yin deficiency and heat excess, qi deficiency and dampness heat accumulation, and spleen deficiency and dampness stagnation transforming into heat. Step S202: The sentence is segmented using a string segmentation method. The segmented sentences are traversed, and keywords, synonyms, and near-synonyms are compared with the segmented sentences. Segmented sentences containing keywords, synonyms, and near-synonyms are retained and set as valid sentences. Segmented sentences that do not contain keywords, synonyms, and near-synonyms are deleted. Step S203: Obtain the diagnostic data and laboratory data corresponding to the case data, wherein the diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage; The test data included fasting blood glucose, triglycerides, and uric acid.

4. The method for processing TCM internal medicine case data based on cloud computing as described in claim 3, characterized in that: The methods for obtaining the diagnostic data and laboratory data include: Obtain the case data number, retrieve the case database, input the case data number into the case database, match the diagnostic data and laboratory data corresponding to the case data number, and assign numbers to the case data to indicate that the patient had an initial visit or follow-up visit at different times, and performed corresponding laboratory tests, thus obtaining different case data and laboratory data.

5. The method for processing TCM internal medicine case data based on cloud computing as described in claim 1, characterized in that: Step S300 includes the following sub-steps: Step S301: Count the number of times each TCM syndrome differentiation occurs in the diagnostic data, and record it as the first count. The first count includes the first count of the first diagnostic data and the first count of the second diagnostic data. Step S302: Filter effective classification indicators based on the first set of data. The filtering logic for the effective classification indicators includes: Obtain diagnostic data corresponding to the early stage of metabolic syndrome and diagnostic data corresponding to the confirmed stage of metabolic syndrome. Record the diagnostic data corresponding to the early stage of metabolic syndrome and the diagnostic data corresponding to the confirmed stage of metabolic syndrome as the first diagnostic data and the second diagnostic data, respectively. Count the number of times each TCM syndrome differentiation occurs in the first diagnostic data and the number of times each TCM syndrome differentiation occurs in the second diagnostic data. The number of times each TCM syndrome differentiation type appears in the first diagnostic data is recorded as the first frequency of the first diagnostic data. The number of times each TCM syndrome differentiation type appears in the second diagnostic data is recorded as the first count of the second diagnostic data. Step S303: Set age stages, which include adolescence, youth, middle age and old age. Set 0-14 years old as adolescence, 15-35 years old as youth, 36-60 years old as middle age, and 60-120 years old as old age. The age groups are numbered, and the number is represented as X. i , where i is a natural number and i∈[1,4]; The childhood stage is represented by X1, the youth stage by X2, the middle age stage by X3, and the old age stage by X4; Step S304: Compare the patient's age with the age group, count the number of times the patient's age appears in the age group, and record it as the second count; Step S305: Filter valid age indicators. The filtering logic for valid age indicators includes: Iterate through the second number, sort the second number in descending order, select the second number with the largest value, and set the age stage corresponding to the second number with the largest value as the effective age indicator. Step S306: Assign a first value to different age groups based on the effective age index, set the first value as the BMI index threshold, and assign a second value to the BMI index based on the BMI index threshold. Step S307: Count the number of times the keyword appears in the diagnostic data, denoted as the third occurrence count. The third occurrence count includes the third occurrence count of the first diagnostic data and the third occurrence count of the second diagnostic data. Calculate the correlation degree between the keyword and the diagnostic data based on the third occurrence count. The correlation degree includes the correlation degree of the first diagnostic data and the correlation degree of the second diagnostic data. The calculation logic for the correlation degree includes: Obtain the third count of the first diagnostic data or the third count of the second diagnostic data, and correspondingly obtain the total number of cases corresponding to the first diagnostic data or the total number of cases corresponding to the second diagnostic data. Calculate the ratio of the third count of the first diagnostic data to the total number of cases corresponding to the first diagnostic data, and record it as the correlation degree of the first diagnostic data. Alternatively, calculate the ratio of the third count of the second diagnostic data to the total number of cases corresponding to the second diagnostic data, and record it as the correlation degree of the second diagnostic data.

6. The method for processing TCM internal medicine case data based on cloud computing as described in claim 5, characterized in that: The logic for comparing the patient's age with age groups includes: The process involves obtaining the patient's age, acquiring any age segment and its number, determining whether the patient's age falls within that age segment, obtaining a determination result (including distribution and non-distribution), and performing a first operation based on the determination result. The first operation includes either acquiring the next age segment or assigning a first mark to the patient's age and counting the number of occurrences of the first mark (referred to as the second count). The first mark corresponds to the age segment number and is represented as NX. i Where N is a natural number, and N represents the second number; The logic for the first and second assignments includes: Obtain the effective age index and BMI index threshold, obtain the age stage to be assigned and the BMI index to be assigned, and assign the effective age index and BMI index threshold to 1 respectively. Calculate the ratio of the upper limit of the age stage to be assigned to the upper limit of the effective age indicator, and record it as the first ratio. Calculate the ratio of the lower limit of the age stage to be assigned to the lower limit of the effective age indicator, and record it as the second ratio. Calculate the average of the first ratio and the second ratio. Calculate the product of the average of the first ratio and the second ratio and 1, and record it as the first product. Set the first product as the first assignment corresponding to the age stage to be assigned. Calculate the ratio of the BMI index to be assigned to the BMI index threshold, and record it as the third ratio. Calculate the product of the third ratio and 1, and record it as the second product. Set the second product as the second assignment corresponding to the BMI index to be assigned.

7. The method for processing TCM internal medicine case data based on cloud computing as described in claim 1, characterized in that: Step S400 includes the following sub-steps: Step S401: Construct the first mapping relationship between the assigned age index, BIM index, correlation degree and diagnostic data; obtain self-test diagnostic data based on the first mapping relationship; and calculate the sum of each assigned value in the first mapping relationship, denoted as the first sum. Set standardized test data, which includes standard fasting blood glucose, standard triglycerides, and standard uric acid. Assign the value 1 to each of the standardized test data. Set the second value to standard fasting blood glucose, the third value to standard triglycerides, and the fourth value to standard uric acid. Obtain test data, calculate the ratio of the test data to the corresponding standardized test data, calculate the product of the ratio of the test data to the corresponding standardized test data and 1, and record it as the fourth product. Set the fourth product as the assigned value of the test data. Construct a second mapping relationship between the assigned test data and diagnostic data, obtain the test and diagnostic data based on the second mapping relationship, and calculate the sum of each assigned value in the second mapping relationship, denoted as the second sum. Calculate the average of the first and second sums, and record it as the third sum. Set the third sum as the risk value for both self-test diagnostic data and laboratory diagnostic data. Step S402: Obtain current patient information, calculate the assigned current age index, current BIM index and current correlation degree based on the current patient information, and obtain the current self-test diagnostic data according to the first mapping relationship; The current patient information is entered by the patient themselves, including current age, current height, current weight, current medical history, current tongue color, current tongue coating, current mental state, current smoking status, current bowel movements, current alcohol consumption, and current appetite. The system automatically calculates the values ​​of the current age index, the current BIM index, and the current correlation degree based on the first mapping relationship, and obtains the current self-test diagnostic data and the corresponding first sum value. The current self-test diagnostic data includes the current self-test pre-metabolic syndrome stage and the current self-test diagnosed metabolic syndrome stage. Step S403: Obtain the current test data. According to the second mapping relationship, obtain the current test diagnosis data and the corresponding second sum value. The current test diagnosis data includes the current test pre-metabolic syndrome and the current test metabolic syndrome diagnosis period. Compare the current self-test diagnosis data with the current test diagnosis data. Retrieve the expert platform according to the comparison results. The current laboratory diagnostic data is generated by the hospital testing the patient's fasting blood glucose, triglycerides, and uric acid, and obtaining a test report. The patient then inputs the current fasting blood glucose, triglyceride, and uric acid values ​​according to the test report. The second mapping relationship automatically calculates the assigned values ​​for the current fasting blood glucose, triglycerides, and uric acid, and obtains the second sum value corresponding to the current laboratory diagnostic data. The current laboratory diagnostic data includes the pre-metabolic syndrome stage and the confirmed metabolic syndrome stage. Automatically calculate the current self-test diagnostic data and obtain the current risk value by combining the corresponding first sum and the corresponding second sum of the current laboratory diagnostic data; The comparison results include cases where the current self-test diagnostic data is the same as the current laboratory diagnostic data, and cases where the current self-test diagnostic data is different from the current laboratory diagnostic data. When the comparison result shows that the current self-test diagnostic data is different from the current laboratory diagnostic data, the current laboratory diagnostic data will be entered into the expert platform. When the comparison result shows that the current self-test diagnostic data is the same as the current laboratory diagnostic data, either the current self-test diagnostic data or the current laboratory diagnostic data will be entered into the expert platform. Step S404: Input the current self-test diagnostic data or current laboratory data, current age index and current BIM index, current correlation degree and current risk value into the expert platform to obtain expert decisions. The expert decisions include dietary decisions and lifestyle decisions. Then, output the current laboratory diagnostic data, the expert decisions and the current risk value to the patient.

8. A cloud-based TCM internal medicine case data processing system, the system being used to execute the cloud-based TCM internal medicine case data processing method as described in claim 1, characterized in that, It includes a data acquisition module, an analysis module, and a decision-making module; The acquisition module is used to acquire case data and patient information, calculate the patient's BMI index based on the patient information, set keywords and TCM syndrome differentiation, identify synonyms, near-synonyms and derivatives of the keywords, extract sentences corresponding to the keywords, synonyms, near-synonyms and derivatives in the case data, segment the sentences to obtain valid sentences, and acquire the diagnostic data and laboratory data corresponding to the case data. The analysis module is used to count the number of times TCM syndrome differentiation occurs in the diagnostic data, recorded as the first count. Based on the first count, effective syndrome differentiation indicators are selected. An age range is set, and the number of times patient information occurs in the age range is counted as the second count. Effective age indicators are selected, and a first value is assigned to different age ranges based on the effective age indicators. A BMI index threshold is set, and a second value is assigned to the BMI index based on the BMI index threshold. The number of times keywords occur in the diagnostic data is counted as the third count, and the correlation between keywords and diagnostic data is calculated based on the third count. The decision-making module is used to construct a first mapping relationship between the assigned age index, BIM index, and correlation degree and the diagnostic data, assign values ​​to the test data, construct a second mapping relationship between the assigned test data and the diagnostic data, obtain the first current diagnostic data based on the first mapping relationship, obtain the second current diagnostic data based on the second mapping relationship, and retrieve the expert platform to obtain expert decisions.

9. An electronic device comprising a storage device, a processor, and a computer program stored in the storage device and executable on the processor, characterized in that, When the processor executes the computer program, it implements the cloud computing-based method for processing TCM internal medicine case data as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the cloud computing-based method for processing TCM internal medicine case data as described in any one of claims 1-7.

Images