Lymphedema disease screening system based on big data

Abstract

The invention relates to the technical field of disease screening, and discloses a big data-based lymphedema disease screening system which overcomes the defects of singleness, subjectivity and low efficiency of a traditional screening means by integrating multi-source data, optimizing a processing flow, accurately calculating a screening index and automatically generating an analysis result. According to the method, the accuracy, efficiency and operability of screening are remarkably improved, doctors are helped to quickly identify high-risk patients, meanwhile, the dependence of the patients on expensive detection means is reduced, optimal configuration of medical resources is achieved, comprehensive and reliable technical support is provided for early screening and intervention of lymphedema, and through multi-dimensional collection of patient information, the screening accuracy, efficiency and operability are improved. High-quality input is provided for intelligent calculation and analysis, operation of subsequent modules is more efficient and accurate, high adaptability of data in the screening process is guaranteed through the targeted design, and the problems of misdiagnosis and missed diagnosis caused by data incompleteness or deviation are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of disease screening, and in particular to a lymphedema disease screening system based on big data. Background Art

[0002] Lymphedema is a chronic disease that is common in patients after cancer surgery, lymph node resection or trauma. Early detection and intervention are of great significance to the patient's prognosis.

[0003] Traditional screening methods mainly rely on a single data source and lack the ability to integrate and analyze multi-source data, making it difficult to comprehensively and accurately assess patient risks. Secondly, existing diagnostic methods are highly dependent on the physician's experience and judgment, and are limited by subjectivity and technical level, which can easily lead to missed or misdiagnosed conditions. Thirdly, large-scale screening usually requires imaging examinations or complex laboratory tests, which not only increases costs, but also puts greater pressure on the allocation of medical resources. The above problems significantly reduce the efficiency and accuracy of lymphedema screening, especially the identification and intervention of early patients.

[0004] Therefore, we proposed a lymphedema disease screening system based on big data to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a lymphedema disease screening system based on big data to solve the problem that the existing diagnostic methods proposed in the above background technology are highly dependent on the doctor's experience and judgment, are limited by subjectivity and technical level, and are prone to missed diagnosis or misdiagnosis.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a lymphedema disease screening system based on big data, comprising a data acquisition module, a data integration module, a data calculation module, a data analysis module and an execution module;

[0007] The data acquisition module is used to collect patient data and standard data, and integrate them into a multi-source data set;

[0008] The data integration module is used to pre-process the multi-source data sets and generate a first data set, a second data set and a third data set;

[0009] The data calculation module is used to integrate the first data set, the second data set and the third data set to calculate the screening abnormality coefficient.

[0010] The data analysis module is used to compare the screening abnormality coefficient with a preset first threshold value, so as to determine whether the current patient has physiological abnormalities;

[0011] The execution module is used to feed back the comparison result to the doctor.

[0012] Preferably, the data acquisition module includes a first acquisition unit, a second acquisition unit and a third acquisition unit; the first acquisition unit is used to collect basic information of the patient, including age, weight and BMI;

[0013] The second acquisition unit is used to collect the patient's physical sign data, including limb circumference difference, skin thickness and edema score;

[0014] The third acquisition unit is used to collect the patient's physiological data, including lymph flow rate, C-reactive protein and lymphatic vessel diameter;

[0015] Age, weight, BMI, limb circumference difference, skin thickness, edema score, lymphatic flow velocity, C-reactive protein, and lymphatic vessel diameter constituted the multi-source data set.

[0016] Preferably, the data integration module includes a data preprocessing unit and a data sorting unit, the data preprocessing unit is used to preprocess and dimensionlessly transform the multi-source data, and the data sorting unit is used to sort the processed multi-source data set into a first multi-source data set, a second multi-source data set and a third multi-source data set.

[0017] Preferably, the first data set includes age A, weight B and BMIC;

[0018] The second data set includes limb circumference difference D, skin thickness E, and edema score F;

[0019] The third data set includes lymphatic flow velocity G, C-reactive protein H, and lymphatic vessel diameter I.

[0020] Preferably, the data calculation module is calculated and obtained by the following formula:

[0021] SLY=a1×S1+a2×S2+a3×S3;

[0022] Wherein: S1 is the first reference coefficient, which is obtained by calculating the first data set; S2 is the second reference coefficient, which is obtained by calculating the second data set; S3 is the third reference coefficient, which is obtained by calculating the third data set.

[0023] Preferably, the data calculation module calculates S1, S2 and S3 respectively by the following formulas:

[0024] S1=b1×A+b2×B+b3×C;

[0025] S2=c1×D+c2×E+c3×F;

[0026] S3=d1×G+d2×H+d3×I;

[0027] Where: A is age, B is weight, C is BMI, D is the difference in limb circumference, E is skin thickness, F is the edema score, G is lymphatic flow rate, H is C-reactive protein, I is the lymphatic vessel diameter, b1, b2, b3, c1, c2, c3, d1, d2, and d3 are weight values, and the values of b1, b2, b3, c1, c2, c3, d1, d2, and d3 are adjusted and set by the user.

[0028] Preferably, the data analysis module includes a first analysis unit and a second analysis unit. The first analysis unit is used to generate a first comparison result, and the second analysis unit is used to generate a second comparison result.

[0029] Preferably, the first comparison result is specifically as follows:

[0030] When SLY < Y, it means that the current patient does not have lymphedema disease. When SLY ≥ Y, it means that the current patient has lymphedema disease.

[0031] Preferably, the second comparison result is specifically as follows:

[0032] When Y ≤ SLY < R, it means that the current patient has a first-level abnormality. When R ≤ SLY < R × 110%, it means that the current patient has a second-level abnormality. When SLY ≥ R × 110%, it means that the current patient has a third-level abnormality.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] 1. The lymphedema screening system based on big data realizes the full-process intelligence and high efficiency from data collection to diagnostic feedback. By integrating multi-source data, optimizing the processing flow, accurately calculating screening indicators, and automatically generating analysis results, the system overcomes the deficiencies of traditional screening methods such as single nature, subjectivity, and low efficiency. The final effect is: significantly improving the accuracy, efficiency, and operability of screening, helping doctors quickly identify high-risk patients, while reducing patients' dependence on expensive detection methods, realizing the optimal allocation of medical resources, and providing comprehensive and reliable technical support for the early screening and intervention of lymphedema.

[0035] 2. Through the multi-dimensional collection of patient information, it provides high-quality input for intelligent calculation and analysis, making the operation of subsequent modules more efficient and accurate. Its targeted design ensures the high adaptability of data in the screening process, reduces misdiagnosis and missed diagnosis problems caused by incomplete or deviated data, and significantly improves the overall efficiency of the system. Through comprehensive multi-dimensional data collection, the system can capture early symptoms or potential risks of lymphedema, overcoming the limitation of traditional screening methods in the insufficient ability to identify early patients. This improvement not only shortens the time cycle of disease identification but also provides doctors with a more scientific diagnostic basis, promoting the implementation of precision medicine in the field of lymphedema screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a system flow chart of the present invention.

[0037] In the figure: 1. Data acquisition module; 11. First acquisition unit; 12. Second acquisition unit; 13. Third acquisition unit; 2. Data integration module; 21. Data preprocessing unit; 22. Data sorting unit; 3. Data calculation module; 4. Data analysis module; 41. First analysis unit; 42. Second analysis unit; 5. Execution module. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1: Please refer to Figure 1 , a lymphedema disease screening system based on big data, comprising a data acquisition module 1, a data integration module 2, a data calculation module 3, a data analysis module 4 and an execution module 5;

[0040] The data collection module 1 is used to collect patient data and standard data and integrate them into a multi-source data set;

[0041] The data integration module 2 is used to pre-process the multi-source data sets and generate a first data set, a second data set and a third data set;

[0042] The data calculation module 3 is used to integrate the first data set, the second data set and the third data set to calculate the screening abnormality coefficient;

[0043] The data analysis module 4 is used to compare the screening abnormality coefficient with a preset first threshold value, so as to determine whether the current patient has physiological abnormalities;

[0044] The execution module 5 is used to feed back the comparison result to the doctor.

[0045] In this embodiment: Data acquisition module 1 forms a multi-source data set by integrating patient data and standard data, laying a data foundation for the screening system. Patient data includes basic information, physical sign data, and physiological data; standard data provides a comparison basis for the model. The role of this module is to build a comprehensive and reliable database covering multi-dimensional information, thereby avoiding the limitations of a single data source in traditional screening methods and providing high-quality input for subsequent processing and analysis.

[0046] Data integration module 2 non-dimensionalizes, standardizes and cleanses multi-source data through data preprocessing and organization, and generates three types of data sets. The key role of this module is to eliminate inconsistencies or noise in the original data and ensure the standardization and comparability of the data. At the same time, this module optimizes the data structure so that information of different dimensions can be efficiently integrated and analyzed, thereby improving the accuracy and consistency of model processing.

[0047] The data calculation module 3 performs a comprehensive analysis on the preprocessed data set, and generates the screening abnormality coefficient through weight assignment and formula calculation. It quantifies the values ​​of each dimension of the patient, combines the first data set, the second data set, and the third data set, and calculates the corresponding reference coefficients respectively, and finally forms a comprehensive abnormal screening index. The task of this module is to realize the quantification and comprehensive processing of complex data, reduce subjective judgment errors, and improve the scientificity and objectivity of the screening results.

[0048] The data analysis module 4 compares the screening abnormality coefficient with the preset first threshold value to determine whether the patient has physiological abnormalities and the level of abnormality. By setting reasonable thresholds and classification criteria, the module can quickly locate high-risk patients or clarify the stage of disease development. The effect is to improve the accuracy and efficiency of screening, ensure that patients can get intervention advice as soon as possible, and reduce the possibility of missed diagnosis and misdiagnosis.

[0049] Execution module 5 feeds back the analysis results to doctors in an intuitive way to support clinical decision-making. Doctors can conduct further examinations or formulate intervention plans based on the results. Through visualization and result delivery, execution module 5 shortens the time chain of screening-diagnosis-intervention and improves the convenience and operability of the screening process. Its role is to achieve seamless connection between system output and clinical practice and improve doctors' control over disease risks.

[0050] The lymphedema screening system based on big data realizes the intelligence and efficiency of the whole process from data collection to diagnostic feedback. By integrating multi-source data, optimizing processing procedures, accurately calculating screening indicators, and automatically generating analysis results, the system overcomes the defects of the singleness, subjectivity, and inefficiency of traditional screening methods. The final effect is: significantly improving the accuracy, efficiency, and operability of screening, helping doctors to quickly identify high-risk patients, while reducing patients' dependence on expensive testing methods, achieving optimal allocation of medical resources, and providing comprehensive and reliable technical support for early screening and intervention of lymphedema.

[0051] Example 2: Please refer to Figure 1 , the data acquisition module 1 includes a first acquisition unit 11, a second acquisition unit 12 and a third acquisition unit 13; the first acquisition unit 11 is used to collect basic information of the patient, including age, weight and BMI;

[0052] The second acquisition unit 12 is used to collect the patient's physical sign data, including limb circumference difference, skin thickness and edema score;

[0053] The third acquisition unit 13 is used to collect the patient's physiological data, including lymph flow rate, C-reactive protein and lymphatic vessel diameter;

[0054] Age, weight, BMI, limb circumference difference, skin thickness, edema score, lymphatic flow velocity, C-reactive protein, and lymphatic vessel diameter constituted the multi-source data set.

[0055] In this embodiment, by including the patient's basic information, vital signs and physiological data in the collection scope, the data collection module 1 achieves multi-dimensional and multi-level information coverage. This design makes up for the deficiency of relying on a single data source in traditional screening methods, enables the screening process to comprehensively reflect the various pathological characteristics of the disease, and improves the reliability and integrity of the data basis.

[0056] By dividing into the first acquisition unit 11, the second acquisition unit 12 and the third acquisition unit 13, the system can collect different types of data by classification. This structured design not only improves the efficiency of data collection, but also ensures the pertinence and accuracy of each type of data. In particular, the introduction of physiological data provides an important basis for in-depth analysis of the pathogenesis of lymphedema and broadens the perspective of traditional screening.

[0057] Integrating the above collected data into a multi-source data set lays a solid foundation for subsequent preprocessing, analysis and calculation. This multi-source integration breaks the data silos, can provide richer information dimensions for disease screening, and enable the system to have stronger comprehensive analysis capabilities. Compared with traditional methods, the screening method that relies solely on a single indicator appears one-sided and cannot fully reflect the disease risk; the collection and integration of multi-source data can significantly improve the comprehensiveness and scientificity of screening.

[0058] Through the multi-dimensional collection of patient information, high-quality input is provided for intelligent calculation and analysis, making the operation of subsequent modules more efficient and accurate. Its targeted design ensures the high adaptability of data in the screening process, reduces the problems of misdiagnosis and missed diagnosis caused by incomplete or biased data, and significantly improves the overall efficiency of the system. Through comprehensive multi-dimensional data collection, the system can capture the early symptoms or potential risks of lymphedema, overcoming the limitations of traditional screening methods in their ability to identify early patients. This improvement not only shortens the time period for disease identification, but also provides doctors with a more scientific basis for diagnosis, promoting the implementation of precision medicine in the field of lymphedema screening.

[0059] Example 3: Please refer to Figure 1The data integration module 2 includes a data preprocessing unit 21 and a data sorting unit 22. The data preprocessing unit 21 is used to preprocess and dimensionlessly transform the multi-source data. The data sorting unit 22 is used to sort the processed multi-source data set into a first multi-source data set, a second multi-source data set and a third multi-source data set.

[0060] The first data set includes age A, weight B, and BMIC;

[0061] The second data set includes limb circumference difference D, skin thickness E, and edema score F;

[0062] The third data set includes lymphatic flow velocity G, C-reactive protein H, and lymphatic vessel diameter I.

[0063] In this embodiment: the data preprocessing unit 21 solves the unit inconsistency, dimension difference or noise problems that may exist in the original data by preprocessing and dimensionless processing of multi-source data. After dimensionless processing, all data can be unified within a standard range, which helps to avoid certain indicators from having too much impact on the screening results due to scale differences, thereby improving the accuracy of subsequent data analysis and calculation. This improvement effectively reduces the errors caused by data inconsistency or deviation, and ensures that each data dimension contributes equally and reliably to the overall analysis.

[0064] The data sorting unit 22 divides the processed multi-source data set into the first, second and third data sets according to different data dimensions. This classification and sorting method can perform more sophisticated processing and analysis on different types of data. For example, the first data set focuses on basic information, the second data set focuses on vital sign data, and the third data set focuses on physiological data. Through reasonable division and sorting, not only the operability of the data is improved, but also a clearer structure is provided for subsequent calculation and analysis, so that the system can more efficiently identify potential abnormalities.

[0065] Segmenting multi-source data into three different data sets helps to deeply analyze the patient's health status from different dimensions. For example, the first data set can focus on analyzing the potential impact of basic physical parameters on lymphedema, the second data set can help identify signs related to edema, and the third data set provides support for physiological mechanisms. This hierarchical processing not only improves the pertinence of data analysis, but also improves the hierarchical diagnostic capabilities of the entire screening system. Doctors can judge the different stages of development of the disease based on different data sets, and achieve more accurate early screening and intervention.

[0066] Data integration module 2 pre-processes and sorts the data, allowing the system to flexibly adapt to different types of patient data, not just fixed parameters or data dimensions. This flexibility allows the system to be widely used in different clinical settings and meet the needs of different patient groups. Especially when facing patients with different stages of lymphedema, the data sorting and pre-processing module can quickly adjust the analysis focus and provide personalized screening results.

[0067] By collating multi-source data into three independent data sets, the data integration module 2 can achieve efficient data flow and analysis support. The independence of each data set improves processing efficiency and provides clear input for subsequent data calculation and analysis modules. This design avoids data mixing and interference, allowing the entire system to quickly process large amounts of patient data, thereby increasing screening speed and meeting efficient clinical needs.

[0068] Example 4: Please refer to Figure 1 , the data calculation module 3 obtains it by calculating through the following formula;

[0069] SLY=a1×S1+a2×S2+a3×S3;

[0070] Wherein: S1 is the first reference coefficient, which is obtained by calculating the first data set; S2 is the second reference coefficient, which is obtained by calculating the second data set; S3 is the third reference coefficient, which is obtained by calculating the third data set.

[0071] The data calculation module 3 calculates S1, S2 and S3 respectively through the following formulas:

[0072] S1=b1×A+b2×B+b3×C;

[0073] S2=c1×D+c2×E+c3×F;

[0074] S3=d1×G+d2×H+d3×I;

[0075] Wherein: A is age, B is weight, C is BMI, D is limb circumference difference, E is skin thickness, F is edema score, G is lymph flow velocity, H is C-reactive protein, I is lymphatic vessel diameter, b1, b2, b3, c1, c2, c3, d1, d2 and d3 are weight values, and the values ​​of b1, b2, b3, c1, c2, c3, d1, d2 and d3 are adjusted and set by the user.

[0076] In this embodiment: Data calculation module 3 introduces weight values ​​so that the system can be flexibly adjusted according to user needs. This improvement provides customized screening capabilities for different patient groups, different clinical environments or different screening stages. Doctors or researchers can adjust the weights of various data according to actual conditions to make screening more accurate. Traditional screening systems are often difficult to adapt to individual differences, and this module provides personalized screening results through dynamic weight settings, improving the adaptability and flexibility of the system.

[0077] By comprehensively calculating multiple key parameters such as age, weight, BMI, limb circumference difference, skin thickness, edema score, lymphatic flow rate, C-reactive protein, lymphatic vessel diameter, etc., the data calculation module 3 can comprehensively evaluate the patient's pathological condition from multiple dimensions. This comprehensive calculation capability improves the accuracy of the screening results and avoids the diagnostic bias caused by relying on a single indicator. Each reference coefficient is calculated and weighted based on the relevant data set, effectively integrating information from different dimensions, making the disease screening process more scientific and rigorous.

[0078] Users can adjust the weight value according to different clinical needs, and the system can automatically calculate different reference coefficients based on the weight setting. This automated calculation not only improves the efficiency of screening, but also reduces the occurrence of human errors. Doctors can further adjust the weights for detailed screening based on the preliminary screening results, thereby optimizing the screening process and reducing the risk of misdiagnosis and missed diagnosis.

[0079] By inputting all data into a comprehensive calculation formula, the data calculation module 3 automates complex data processing and calculation, greatly simplifying the entire screening process. Doctors only need to focus on the calculation results, without having to manually analyze a large amount of raw data or manually process the relationship between various parameters. This improvement improves the efficiency of diagnosis, especially when facing a large number of patients, which can greatly save time and improve clinical efficiency.

[0080] The improvement of data calculation module 3 can quickly determine whether the patient is at risk of lymphedema through the calculated reference coefficient and provide accurate screening results. This not only supports early diagnosis, but also provides doctors with more scientific data support so that intervention measures can be taken as early as possible. This improvement is of great significance for reducing the progression of the patient's disease and improving the treatment effect.

[0081] Example 5: Please refer to Figure 1 The data analysis module 4 includes a first analysis unit 41 and a second analysis unit 42. The first analysis unit 41 is used to generate a first comparison result, and the second analysis unit 42 is used to generate a second comparison result.

[0082] The first comparison results are as follows:

[0083] When SLY < Y, it indicates that the current patient does not have lymphedema disease. When SLY ≥ Y, it indicates that the current patient has lymphedema disease.

[0084] The specific second comparison result is as follows:

[0085] When Y ≤ SLY < R, it indicates that the current patient has a first-level abnormality. When R ≤ SLY < R × 110%, it indicates that the current patient has a second-level abnormality. When SLY ≥ R × 110%, it indicates that the current patient has a third-level abnormality.

[0086] In this embodiment: The data analysis module 4, through the dual analysis mechanism of the first analysis unit 41 and the second analysis unit 42, enables the screening result to not only distinguish whether the patient has lymphedema, but also grade the patient's condition. This improvement significantly enhances the meticulousness of the screening. The first analysis unit 41 clearly distinguishes the preliminary judgment of whether the patient is ill by generating the first comparison result, while the second analysis unit 42 subdivides the patient's condition into different abnormal levels by generating the second comparison result. This grading method provides doctors with a clearer disease progression, enabling them to adopt more personalized and precise treatment plans.

[0087] Through hierarchical screening, the data analysis module 4 provides doctors with multi-level decision-making support. The first comparison result helps doctors quickly understand whether the patient has lymphedema, facilitating preliminary intervention; while the second comparison result provides a refined grading of the condition, enabling doctors to judge the severity of the condition. For patients with a first-level abnormality, minor intervention measures can be taken, while for patients with a third-level abnormality, a more aggressive treatment plan is required. In this way, the system can greatly improve the pertinence and effectiveness of treatment, while reducing the possibility of misdiagnosis and missed diagnosis.

[0088] The abnormal level division of the second analysis unit 42 enables the system to capture the patient's condition changes more meticulously, especially in the early stage of the disease. When the patient's condition is detected as a first-level abnormality, the system can prompt doctors to conduct more frequent monitoring and necessary early intervention, thereby avoiding the aggravation of the condition. This ability of early identification and grading greatly improves the early detection rate of lymphedema disease, provides patients with earlier treatment opportunities, and reduces the harm caused by disease progression.

[0089] By generating hierarchical comparison results, the data analysis module 4 enables the patient's condition to be more clearly classified and managed. Patients of different levels can be automatically classified and enter different treatment processes, which not only improves the screening efficiency but also provides a clear basis for subsequent treatment. Doctors can quickly formulate targeted treatment plans according to the condition grading and optimize resource allocation.

[0090] The data analysis module 4 combines the first comparison result and the second comparison result, so that the screening process can not only quickly determine whether the patient is ill, but also accurately assess the severity of the patient's condition. Compared with the traditional screening system, the method of simply judging whether the patient is ill is relatively rough and lacks in-depth understanding of the patient's condition. Through hierarchical analysis, the system can provide doctors with more accurate screening results, thereby improving the accuracy and efficiency of the entire screening process.

[0091] Data analysis module 4 significantly improves the meticulousness and accuracy of the lymphedema screening system by comparing the results by grading. Compared with the traditional simple diagnosis method, this grading mechanism can not only help doctors determine whether the patient is sick, but also accurately reflect the severity of the disease, thereby providing personalized and accurate treatment plans. This improvement not only improves the ability of early diagnosis, but also optimizes patient classification and resource management, providing more efficient and scientific decision-making support for the treatment of lymphedema.

[0092] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0093] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A lymphedema disease screening system based on big data, characterized by: It includes a data collection module (1), a data integration module (2), a data calculation module (3), a data analysis module (4) and an execution module (5); The data acquisition module (1) is used to collect patient data and standard data, and integrate them into a multi-source data set; The data integration module (2) is used to pre-process the multi-source data sets and generate a first data set, a second data set and a third data set; The data calculation module (3) is used to integrate the first data set, the second data set and the third data set to calculate the screening abnormality coefficient. The data analysis module (4) is used to compare the screening abnormality coefficient with a preset first threshold value, so as to determine whether the current patient has physiological abnormalities; The execution module (5) is used to feed back the comparison result to the doctor.

2. The lymphedema disease screening system based on big data according to claim 1, characterized in that: The data acquisition module (1) comprises a first acquisition unit (11), a second acquisition unit (12) and a third acquisition unit (13); the first acquisition unit (11) is used to acquire basic information of the patient, including age, weight and BMI; The second acquisition unit (12) is used to collect the patient's physical sign data, including limb circumference difference, skin thickness and edema score; The third acquisition unit (13) is used to acquire physiological data of the patient, including lymph flow rate, C-reactive protein and lymphatic vessel diameter; Age, weight, BMI, limb circumference difference, skin thickness, edema score, lymphatic flow velocity, C-reactive protein, and lymphatic vessel diameter constituted the multi-source data set.

3. The lymphedema disease screening system based on big data according to claim 2, characterized in that: The data integration module (2) comprises a data preprocessing unit (21) and a data sorting unit (22), wherein the data preprocessing unit (21) is used to preprocess and dimensionlessly transform the multi-source data, and the data sorting unit (22) is used to sort the processed multi-source data set into a first multi-source data set, a second multi-source data set, and a third multi-source data set.

4. The lymphedema disease screening system based on big data according to claim 3, characterized in that: The first data set includes age A, weight B, and BMIC; The second data set includes limb circumference difference D, skin thickness E, and edema score F; The third data set includes lymphatic flow velocity G, C-reactive protein H, and lymphatic vessel diameter I.

5. The lymphedema disease screening system based on big data according to claim 4, characterized in that: The data calculation module (3) is calculated and obtained by the following formula: SLY=a1×S1+a2×S2+a3×S3; Wherein: S1 is the first reference coefficient, which is obtained by calculating the first data set; S2 is the second reference coefficient, which is obtained by calculating the second data set; S3 is the third reference coefficient, which is obtained by calculating the third data set.

6. The lymphedema disease screening system based on big data according to claim 5, characterized in that: The data calculation module (3) calculates S1, S2 and S3 respectively by the following formulas: S1=b1×A+b2×B+b3×C; S2=c1×D+c2×E+c3×F; S3=d1×G+d2×H+d3×I; Where: A is age, B is weight, C is BMI, D is the difference in limb circumference, E is skin thickness, F is the edema score, G is lymphatic flow rate, H is C-reactive protein, I is the lymphatic vessel diameter, b1, b2, b3, c1, c2, c3, d1, d2, and d3 are weight values, and the values of b1, b2, b3, c1, c2, c3, d1, d2, and d3 are adjusted and set by the user.

7. The lymphedema disease screening system based on big data according to claim 6, characterized in that: The data analysis module (4) includes a first analysis unit (41) and a second analysis unit (42). The first analysis unit (41) is used to generate a first comparison result, and the second analysis unit (42) is used to generate a second comparison result.

8. The lymphedema disease screening system based on big data according to claim 7, characterized in that: The first comparison result is specifically as follows: When SLY < Y, it means that the current patient does not have lymphedema disease. When SLY ≥ Y, it means that the current patient has lymphedema disease.

9. The lymphedema disease screening system based on big data according to claim 8, characterized in that: The second comparison result is specifically as follows: When Y ≤ SLY < R, it means that the current patient has a first-level abnormality. When R ≤ SLY < R × 110%, it means that the current patient has a second-level abnormality. When SLY ≥ R × 110%, it means that the current patient has a third-level abnormality.

Images