Quantitative analysis method for kidney transplantation reexamination result data based on artificial intelligence

Abstract

The invention belongs to the technical field of review result quantitative analysis, and discloses a quantitative analysis method for kidney transplantation review result data based on artificial intelligence. First patient reexamination result data are collected and preprocessed, second patient reexamination result data are obtained, and the first patient reexamination result data comprise biochemical index data, image result data and pathological report data; analyzing the second patient review result data to obtain a patient state reference value, and classifying the patient state reference value to obtain a classification result; storing the first patient review result data and the patient state reference value; in general, the method has the remarkable advantages that the auxiliary decision making effect is good, the patient information confidentiality is high, and the ability of assisting doctors in analyzing conditions is high.

Description

Technical Field

[0001] The present invention relates to the technical field of quantitative analysis of review results, and more specifically, to a quantitative analysis method for renal transplantation review result data based on artificial intelligence. Background Art

[0002] Kidney transplantation is commonly known as kidney replacement, which is the process of transplanting a healthy kidney to a patient with kidney disease and loss of kidney function. The human body has two kidneys, and usually one kidney can support normal metabolic needs. When both kidneys lose function, kidney transplantation is recognized as the best treatment for end-stage renal disease.

[0003] Regular postoperative review and close follow-up are crucial to the long-term health and survival of transplant recipients and transplanted kidneys. In current clinical work, there is a lack of systematic, standardized, and comprehensive quantitative standards for analyzing follow-up review data of kidney transplant recipients. This makes different kidney transplant doctors often make subjective and volatile decisions based on their personal experience and cognition when following up on patients. Such a follow-up model is not only inefficient, but also easily leads to large and frequent fluctuations in the indicators of kidney transplant recipients, which is not conducive to kidney transplant recipients maintaining a stable and good health state.

[0004] Therefore, how to quickly organize the review result data and conduct scientific, systematic and effective normative analysis has become a problem that doctors need to solve. In view of this, the present invention proposes a quantitative analysis method for follow-up review data monitoring and prognosis evaluation of kidney transplant recipients based on artificial intelligence to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising:

[0006] A data acquisition module is used to acquire the first patient's review result data and perform preprocessing to obtain the second patient's review result data, wherein the first patient's review result data includes biochemical index data, imaging result data and pathology report data;

[0007] Furthermore, the method of collecting the first patient's review result data includes:

[0008] Through the patient's biochemical index report, the concentration values ​​of creatinine, urea nitrogen and immunosuppressant obtained by the changes in electrical signals generated when creatinine, urea nitrogen and immunosuppressant in the patient's body react with specific reagents are collected to obtain a biochemical index value set, thereby obtaining biochemical index data;

[0009] By connecting to the hospital information system, the patient's X-ray, CT or MRI images are collected to obtain imaging result data;

[0010] By connecting to the hospital laboratory information system, the biopsy tissue processing data is collected, and the pathology report data is obtained based on the doctor's analysis of the lesions in cell morphology and structure;

[0011] The preprocessing method includes data cleaning and data denoising to obtain the second patient review result data;

[0012] A data analysis module is used to analyze the second patient's review result data, obtain a patient status reference value, and classify the patient status to obtain a classification result;

[0013] Further, the analysis methods include:

[0014] Obtain the second patient's reexamination result data and preset the biochemical index threshold interval group Substitute the concentration values ​​of creatinine, urea nitrogen and immunosuppressants in the biochemical index value set into the biochemical index threshold interval group for comparison. When the creatinine concentration value is less than Q1 or greater than Q2, the value is 1; when the creatinine concentration value is greater than Q1 and less than Q2, the value is 2; when the urea nitrogen concentration value is less than W1 or greater than W2, the value is 1; when the urea nitrogen concentration value is greater than W1 and less than W2, the value is 2; when the immunosuppressant concentration value is less than E1 or greater than E2, the value is 1; when the immunosuppressant concentration value is greater than E1 and less than E2, the value is 2;

[0015] The biochemical index data values ​​are obtained by substituting into the calculation formula: Aa = Ca × L1 + Cb × L2 + Cc × L3, where Ca is the creatinine concentration value, Cb is the urea nitrogen concentration value, Cc is the immunosuppressant concentration value, and L1, L2 and L3 are the weight factors corresponding to the creatinine concentration value, urea nitrogen concentration value and immunosuppressant concentration value respectively;

[0016] Collect the historical second patient review result data of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P;

[0017] Based on the training set, a clustering model is established, and the historical image result data in the training set is obtained. The normal value cluster J and the abnormal value cluster H are preset, and two data points J and H are selected as the initial cluster centers. By substituting into the calculation formula: Get the distance between data points, calculate the distance between the sub-data items and the preliminary cluster center in the training set, assign the sub-data items to the nearest preliminary cluster center, and recalculate the mean of the two preliminary cluster centers as the new preliminary cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points, xi and yi are the values ​​of the two data points on the i sub-data items respectively, and n is the number of sub-data items;

[0018] After U rounds of iterations, the output results of the clustering model tend to be stable, and an intelligent allocation model is obtained;

[0019] The image result data is input into the intelligent allocation model to check whether the output value is in the normal value cluster or the abnormal value cluster, and the image result data value is obtained. The image result data value is 0 or 1. When the output value is in the normal value cluster, the image result data value is 0, and when the output value is in the abnormal value cluster, the image result data value is 1;

[0020] The patient status reference value is obtained by substituting into the calculation formula: As = Aa × A1 + Ab × A2 + Ac × A3, where Aa is the biochemical index data value, Ab is the imaging result data value, Ac is the pathology report data, and A1, A2 and A3 are the corresponding preset weight factors respectively;

[0021] Further, the classification methods include:

[0022] A patient health threshold interval (B1, B2) is preset. When the patient status reference value is less than B1, poor status information is generated. When the patient status reference value is greater than B1 and less than B2, better status information is generated. When the patient status reference value is greater than B2, good status information is generated.

[0023] Bad condition information includes indicating that the patient's physical condition is very bad and requiring the doctor to take immediate treatment measures for the patient; good condition information includes indicating that the patient's physical condition is average and requiring the doctor to observe the patient's physical condition several times; good condition information includes indicating that the patient's physical condition is good and requiring the doctor to give necessary medical advice based on the patient's physical condition;

[0024] Packing bad status information, better status information and good status information to obtain classification results;

[0025] A data storage module, used for storing the first patient's review result data and the patient's status reference value;

[0026] Furthermore, the step of storing includes:

[0027] Z1: Based on the preset time unit, the first patient's review result data and the patient status reference value are packaged to obtain a patient status data set;

[0028] Z2: Encrypt the patient status data set based on the SM4 encryption algorithm to obtain the status ciphertext, calculate the status ciphertext based on the hash algorithm, obtain the hash value of the status ciphertext, and upload the status ciphertext and the hash value to the data storage module for storage;

[0029] Z3: Encrypted storage of SM4 key based on SM2 asymmetric encryption algorithm;

[0030] Z4: When the patient or doctor needs to access or modify the first patient review result data and the patient status reference value, the private key of SM2 is used to decrypt the key of SM4, and then the key of SM4 is used to decrypt the status ciphertext stored in the data storage module to obtain the first patient review result data and the patient status reference value;

[0031] A report display module is used to display the first patient's review result data and classification results to obtain a review result report;

[0032] Further, the steps of obtaining the review result report include:

[0033] X1: Obtain the reexamination result data and classification result of the first patient, and generate the reexamination result data and classification result of the first patient in the form of a report based on the Excel statistical report system to obtain a reexamination result table;

[0034] X2: Based on the review result table, the doctor provides the patient with a condition assessment, physical condition assessment, and treatment recommendations to obtain a clinical decision table;

[0035] X3: Package the review result table and clinical decision table, and print them to obtain the review result report;

[0036] Further, S1: collecting the reexamination result data of the first patient and performing preprocessing to obtain the reexamination result data of the second patient, the reexamination result data of the first patient including biochemical index data, imaging result data and pathology report data;

[0037] S2: Analyze the reexamination result data of the second patient to obtain a patient status reference value, and classify the patient status to obtain a classification result;

[0038] S3: storing the first patient's review result data and the patient's status reference value;

[0039] S4: Display the reexamination result data and classification results of the first patient, and obtain a reexamination result report.

[0040] The technical effects and advantages of the present invention are as follows:

[0041] The present invention obtains the second patient review result data by preprocessing the collected first patient review result data, so that it can be better used for subsequent data analysis. By analyzing the second patient review result data, the patient status reference value obtained can intuitively display the patient's physical status in a numerical form, which is convenient for doctors to use and greatly reduces the time required for doctors to read, understand and think when facing the review result data. Through the classification results, it can effectively assist doctors in making decisions when facing patients and provide doctors with a variety of options when dealing with patients' conditions. Through the data storage module, the security of patient condition information can be greatly enhanced to prevent patient information leakage. Generally speaking, the present invention has the significant advantages of good auxiliary decision-making effect, strong confidentiality of patient information and high ability to assist doctors in analyzing situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a quantitative analysis system for renal transplantation review result data based on artificial intelligence of the present invention;

[0043] Figure 2 Schematic diagram of the quantitative analysis method of renal transplantation review result data based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] Example 1

[0046] See also Figure 1 As shown, the quantitative analysis method of renal transplantation review result data based on artificial intelligence in this embodiment includes:

[0047] A data acquisition module is used to acquire the first patient's review result data and perform preprocessing to obtain the second patient's review result data, wherein the first patient's review result data includes biochemical index data, imaging result data and pathology report data;

[0048] Furthermore, the method of collecting the first patient's reexamination result data includes:

[0049] Through the patient's biochemical index report, the concentration values ​​of creatinine, urea nitrogen and immunosuppressant obtained by the changes in electrical signals generated when creatinine, urea nitrogen and immunosuppressant in the patient's body react with specific reagents are collected to obtain a biochemical index value set, thereby obtaining biochemical index data;

[0050] By connecting to the hospital information system, the patient's X-ray, CT or MRI images are collected to obtain imaging result data;

[0051] By connecting to the hospital laboratory information system, the biopsy tissue processing data is collected, and the pathology report data is obtained based on the doctor's analysis of the lesions in cell morphology and structure;

[0052] It should be explained that the analysis results are based on the doctor's classification of the pathological conditions of cell morphology and structure, and a natural number is obtained based on the classification. The larger the natural number, the better the patient's physical condition.

[0053] The preprocessing method includes data cleaning and data denoising to obtain the second patient review result data;

[0054] A data analysis module is used to analyze the second patient's review result data, obtain a patient status reference value, and classify the patient status to obtain a classification result;

[0055] Further, the analysis methods include:

[0056] Obtain the second patient's reexamination result data and preset the biochemical index threshold interval group Substitute the concentration values ​​of creatinine, urea nitrogen and immunosuppressants in the biochemical index value set into the biochemical index threshold interval group for comparison. When the creatinine concentration value is less than Q1 or greater than Q2, the value is 1; when the creatinine concentration value is greater than Q1 and less than Q2, the value is 2; when the urea nitrogen concentration value is less than W1 or greater than W2, the value is 1; when the urea nitrogen concentration value is greater than W1 and less than W2, the value is 2; when the immunosuppressant concentration value is less than E1 or greater than E2, the value is 1; when the immunosuppressant concentration value is greater than E1 and less than E2, the value is 2;

[0057] The biochemical index data values ​​are obtained by substituting into the calculation formula: Aa = Ca × L1 + Cb × L2 + Cc × L3, where Ca is the creatinine concentration value, Cb is the urea nitrogen concentration value, Cc is the immunosuppressant concentration value, and L1, L2 and L3 are the weight factors corresponding to the creatinine concentration value, urea nitrogen concentration value and immunosuppressant concentration value respectively;

[0058] It should be noted that biochemical indicators are not limited to creatinine, urea nitrogen and immunosuppressants, but can also be other biochemical indicators, such as uric acid, alanine aminotransferase (ALT), aspartate aminotransferase (AST), albumin, globulin, hemoglobin, platelet count, white blood cell count, urine BKV, etc. All are judged according to the preset threshold range. Specifically, if the value of a biochemical indicator exceeds or falls below its normal threshold range, it is marked as abnormal, otherwise it is marked as normal. These thresholds are set by medical standards and adjusted according to individual differences of patients.

[0059] Collect the historical second patient review result data of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P;

[0060] Based on the training set, a clustering model is established, and the historical image result data in the training set is obtained. The normal value cluster J and the abnormal value cluster H are preset, and two data points J and H are selected as the initial cluster centers. By substituting into the calculation formula: Get the distance between data points, calculate the distance between the sub-data items and the preliminary cluster center in the training set, assign the sub-data items to the nearest preliminary cluster center, and recalculate the mean of the two preliminary cluster centers as the new preliminary cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points, xi and yi are the values ​​of the two data points on the i sub-data items respectively, and n is the number of sub-data items;

[0061] After U rounds of iterations, the output results of the clustering model tend to be stable, and an intelligent allocation model is obtained;

[0062] The image result data is input into the intelligent allocation model to check whether the output value is in the normal value cluster or the abnormal value cluster, and the image result data value is obtained. The image result data value is 0 or 1. When the output value is in the normal value cluster, the image result data value is 0, and when the output value is in the abnormal value cluster, the image result data value is 1;

[0063] The patient status reference value is obtained by substituting into the calculation formula: As = Aa × A1 + Ab × A2 + Ac × A3, where Aa is the biochemical index data value, Ab is the imaging result data value, Ac is the pathology report data, and A1, A2 and A3 are the corresponding preset weight factors respectively;

[0064] Further classification methods include:

[0065] A patient health threshold interval (B1, B2) is preset. When the patient status reference value is less than B1, poor status information is generated. When the patient status reference value is greater than B1 and less than B2, better status information is generated. When the patient status reference value is greater than B2, good status information is generated.

[0066] Bad condition information includes indicating that the patient's physical condition is very bad and requiring the doctor to take immediate treatment measures for the patient; good condition information includes indicating that the patient's physical condition is average and requiring the doctor to observe the patient's physical condition several times; good condition information includes indicating that the patient's physical condition is good and requiring the doctor to give necessary medical advice based on the patient's physical condition;

[0067] Packing bad status information, better status information and good status information to obtain classification results;

[0068] A data storage module, used for storing the first patient's review result data and the patient's status reference value;

[0069] Furthermore, the step of storing includes:

[0070] Z1: Based on the preset time unit, the first patient's review result data and the patient status reference value are packaged to obtain a patient status data set;

[0071] It should be explained that the preset time unit is set based on a week, month or quarter, or based on an inspection cycle;

[0072] Z2: Encrypt the patient status data set based on the SM4 encryption algorithm to obtain the status ciphertext, calculate the status ciphertext based on the hash algorithm, obtain the hash value of the status ciphertext, and upload the status ciphertext and the hash value to the data storage module for storage;

[0073] Z3: Encrypted storage of SM4 key based on SM2 asymmetric encryption algorithm;

[0074] Z4: When the patient or doctor needs to access or modify the first patient review result data and the patient status reference value, the private key of SM2 is used to decrypt the key of SM4, and then the key of SM4 is used to decrypt the status ciphertext stored in the data storage module to obtain the first patient review result data and the patient status reference value;

[0075] A report display module is used to display the first patient's review result data and classification results to obtain a review result report;

[0076] Further, the steps of obtaining the review result report include:

[0077] X1: Obtain the reexamination result data and classification result of the first patient, and generate the reexamination result data and classification result of the first patient in the form of a report based on the Excel statistical report system to obtain a reexamination result table;

[0078] X2: Based on the review result table, the doctor provides the patient with a condition assessment, physical condition assessment, and treatment recommendations to obtain a clinical decision table;

[0079] X3: Package the review result table and clinical decision table, and print them to obtain the review result report;

[0080] The present embodiment has the beneficial effect of preprocessing the collected review result data of the first patient to obtain the review result data of the second patient, so that it can be better used for subsequent data analysis; by analyzing the review result data of the second patient, the patient status reference value is obtained, and the patient's physical status can be intuitively displayed in a numerical form, which is convenient for doctors to use, and greatly reduces the time required for doctors to read, understand and think when facing the review result data; through the classification results, it can effectively assist doctors in making decisions when facing patients, and provide doctors with a variety of options when dealing with patients' conditions; through the data storage module, the security of patient condition information can be greatly enhanced to prevent patient information leakage. Generally speaking, the present invention has the significant advantages of good auxiliary decision-making effect, strong confidentiality of patient information and high ability to assist doctors in analyzing situations.

[0081] Example 2

[0082] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a quantitative analysis method for renal transplantation review result data based on artificial intelligence is provided, including: S1: collecting the review result data of the first patient, and preprocessing it to obtain the review result data of the second patient, the review result data of the first patient includes biochemical index data, imaging result data and pathology report data;

[0083] S2: Analyze the reexamination result data of the second patient to obtain a patient status reference value, and classify the patient status to obtain a classification result;

[0084] S3: storing the first patient's review result data and the patient's status reference value;

[0085] S4: Display the reexamination result data and classification results of the first patient, and obtain a reexamination result report.

[0086] Example 3

[0087] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the quantitative analysis method of renal transplantation review result data based on artificial intelligence provided above is implemented.

[0088] Since the electronic device introduced in this embodiment is an electronic device used for implementing the quantitative analysis method of renal transplantation review result data based on artificial intelligence in the embodiment of the present application, based on the quantitative analysis method of renal transplantation review result data based on artificial intelligence introduced in the embodiment of the present application, the technical personnel of the field can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as the technical personnel of the field implement the electronic device used for the quantitative analysis method of renal transplantation review result data based on artificial intelligence in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0089] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0090] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical patients in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A quantitative analysis system for renal transplantation review result data based on artificial intelligence, characterized in that: include: A data acquisition module is used to acquire the first patient's review result data and perform preprocessing to obtain the second patient's review result data, wherein the first patient's review result data includes biochemical index data, imaging result data and pathology report data; A data analysis module is used to analyze the second patient's review result data, obtain a patient status reference value, and classify the patient status to obtain a classification result; A data storage module, used for storing the first patient's review result data and the patient's status reference value; The report display module is used to display the review result data and classification results of the first patient and obtain a review result report.

2. The artificial intelligence-based quantitative analysis system for renal transplantation review result data according to claim 1, characterized in that: Methods for collecting the first patient review result data include: Through the patient's biochemical index report, the concentration values ​​of creatinine, urea nitrogen and immunosuppressant obtained by the changes in electrical signals generated when creatinine, urea nitrogen and immunosuppressant in the patient's body react with specific reagents are collected to obtain a biochemical index value set, thereby obtaining biochemical index data; By connecting to the hospital information system, the patient's X-ray, CT or MRI images are collected to obtain imaging result data; By connecting to the hospital laboratory information system, the biopsy tissue processing data is collected, and the pathology report data is obtained based on the doctor's analysis of the lesions in cell morphology and structure; The preprocessing method includes data cleaning and data denoising to obtain the second patient review result data.

3. The artificial intelligence-based quantitative analysis system for renal transplantation review result data according to claim 2, characterized in that: The analysis can be done by: Obtain the second patient's reexamination result data and preset the biochemical index threshold interval group Substitute the concentration values ​​of creatinine, urea nitrogen and immunosuppressants in the biochemical index value set into the biochemical index threshold interval group for comparison. When the creatinine concentration value is less than Q1 or greater than Q2, the value is 1; when the creatinine concentration value is greater than Q1 and less than Q2, the value is 2; when the urea nitrogen concentration value is less than W1 or greater than W2, the value is 1; when the urea nitrogen concentration value is greater than W1 and less than W2, the value is 2; when the immunosuppressant concentration value is less than E1 or greater than E2, the value is 1; when the immunosuppressant concentration value is greater than E1 and less than E2, the value is 2; The biochemical index data values ​​are obtained by substituting into the calculation formula: Aa = Ca × L1 + Cb × L2 + Cc × L3, where Ca is the creatinine concentration value, Cb is the urea nitrogen concentration value, Cc is the immunosuppressant concentration value, and L1, L2 and L3 are the weight factors corresponding to the creatinine concentration value, urea nitrogen concentration value and immunosuppressant concentration value respectively; Collect the historical second patient review result data of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P; Based on the training set, a clustering model is established, and the historical image result data in the training set is obtained. The normal value cluster J and the abnormal value cluster H are preset, and two data points J and H are selected as the initial cluster centers. By substituting into the calculation formula: Get the distance between data points, calculate the distance between the sub-data items and the preliminary cluster center in the training set, assign the sub-data items to the nearest preliminary cluster center, and recalculate the mean of the two preliminary cluster centers as the new preliminary cluster center for secondary calculation, where x and y are the coordinate values ​​of the data points, xi and yi are the values ​​of the two data points on the i sub-data items respectively, and n is the number of sub-data items; After U rounds of iterations, the output results of the clustering model tend to be stable, and an intelligent allocation model is obtained; The image result data is input into the intelligent allocation model to check whether the output value is in the normal value cluster or the abnormal value cluster, and the image result data value is obtained. The image result data value is 0 or 1. When the output value is in the normal value cluster, the image result data value is 0, and when the output value is in the abnormal value cluster, the image result data value is 1; The patient status reference value is obtained by substituting into the calculation formula: As=Aa×A1+Ab×A2+Ac×A3, where Aa is the biochemical indicator data value, Ab is the imaging result data value, Ac is the pathology report data, and A1, A2 and A3 are the corresponding preset weight factors.

4. The artificial intelligence-based quantitative analysis system for renal transplantation review result data according to claim 3, characterized in that: The classification methods include: A patient health threshold interval (B1, B2) is preset. When the patient status reference value is less than B1, poor status information is generated. When the patient status reference value is greater than B1 and less than B2, better status information is generated. When the patient status reference value is greater than B2, good status information is generated. Bad condition information includes indicating that the patient's physical condition is very bad and requiring the doctor to take immediate treatment measures for the patient; good condition information includes indicating that the patient's physical condition is average and requiring the doctor to observe the patient's physical condition several times; good condition information includes indicating that the patient's physical condition is good and requiring the doctor to give necessary medical advice based on the patient's physical condition; The bad state information, the better state information and the good state information are packaged to obtain the classification result.

5. The artificial intelligence-based quantitative analysis system for renal transplantation review result data according to claim 4, characterized in that: The steps to store include: Z1: Based on the preset time unit, the first patient's review result data and the patient status reference value are packaged to obtain a patient status data set; Z2: Encrypt the patient status data set based on the SM4 encryption algorithm to obtain the status ciphertext, calculate the status ciphertext based on the hash algorithm, obtain the hash value of the status ciphertext, and upload the status ciphertext and the hash value to the data storage module for storage; Z3: Encrypted storage of SM4 key based on SM2 asymmetric encryption algorithm; Z4: When the patient or doctor needs to access or modify the first patient review result data and the patient status reference value, use the private key of SM2 to decrypt the key of SM4, and then use the key of SM4 to decrypt the status ciphertext stored in the data storage module to obtain the first patient review result data and the patient status reference value.

6. The artificial intelligence-based quantitative analysis system for renal transplantation review result data according to claim 5, characterized in that: The steps to obtain a review report include: X1: Obtain the review result data and classification result of the first patient, and generate the review result data and classification result of the first patient in the form of a report based on the Excel statistical report system to obtain a review result table; X2: Based on the review result table, the doctor provides the patient with a condition assessment, physical condition assessment, and treatment recommendations to obtain a clinical decision table; X3: Package the review result table and clinical decision table, and print them to obtain the review result report.

7. A method for quantitative analysis of renal transplantation review result data based on artificial intelligence, implemented by a system for quantitative analysis of renal transplantation review result data based on artificial intelligence according to claims 1-6, characterized in that: S1: Collect the reexamination result data of the first patient and perform preprocessing to obtain the reexamination result data of the second patient, the reexamination result data of the first patient includes biochemical index data, imaging result data and pathology report data; S2: Analyze the reexamination result data of the second patient to obtain a patient status reference value, and classify the patient status to obtain a classification result; S3: storing the first patient's review result data and the patient's status reference value; S4: Display the reexamination result data and classification results of the first patient, and obtain a reexamination result report.

Images