Grouping method for disease diagnosis and treatment

Abstract

The invention belongs to the technical field of medical charging grouping, and particularly provides a grouping method for disease diagnosis and treatment, which comprises the following steps of: judging obtained data by combining a relationship between an average number and a median; then the data is divided into reasonable data, temporary data and non-grouping data through main cluster coding and other cluster coding, and more reasonable grouping can be calculated. The algorithm can be used for payment, medical management and other environments suitable for the algorithm, a good grouping result can be obtained by combining ICD-11 cluster coding, and the algorithm tests whether the cost of the same diagnosis group or similar diagnosis groups is reasonable or not by using the relationship between the median and the average number, so that the algorithm can be applied to the medical management and other environments. The method is suitable for all ICD (International Disease Classification) related fields and other environments suitable for the algorithm, and has practical value. In addition, whether the cost is reasonable or not can be calculated, and meanwhile, the priority of grouping is added, so that a more accurate grouping result is obtained.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical billing grouping, and in particular to a grouping method for disease diagnosis and treatment. Background Art

[0002] DRG (Diagnosis Related Groups, DRG) and DIP (full name: Diagnosis-Intervention Packet, referring to the regional point method total budget and payment by disease type score) are both used for payment and management, but in the process of operation, they have some irreconcilable problems.

[0003] Among them, the main disadvantages of DIP include its inadequacy in clinical judgment and the difficulty in supervising coding errors. The problems of DRG are also prominent, mainly including the following points: First, it may result in the transfer of outpatient and inpatient expenses rather than actual savings in medical expenses.

[0004] Second, it may slow down the pace of investment in medical technology, affect the advancement of medical technology, and indirectly reduce the quality of medical care.

[0005] Third, during the implementation of the DRG system, some hospitals may select patients and cases to reduce hospital costs, while those hospitals that were originally willing to care for inpatients may need to adjust the number of beds to save costs. This may directly affect the rights and interests of patients in hospitalization and indirectly cause a decline in medical quality.

[0006] Fourth, after the implementation of the DRG system, some hospitals may adopt improper means to save costs, which directly leads to some diseases having nowhere to be cured. No hospital is willing to provide inpatient medical services for patients with high complications, which in turn causes a "passing the buck" situation. Summary of the invention

[0007] The present disclosure aims to solve at least one of the technical problems existing in the prior art and proposes a grouping method for disease diagnosis and treatment.

[0008] In a first aspect, the present disclosure provides a grouping method for disease diagnosis and treatment, comprising: S1, form an ICD-11 cluster code for the diagnosis scheme of the same treatment method; S2, calculate the median, mean, maximum, minimum, and count of ICD-11 cluster codes; S3, recalculate the detail position, sub-position position, and category position of all ICD-11 cluster codes and make special identification marks for them respectively; S4, the deviation between the median and the mean needs to be less than a ratio, the default is 15%, the number of adjacent medians is less than a ratio, the default is 5%, the ratio that meets the above conditions is qualified data, the non-compliant is temporary data, and the data less than the preset number of cases is not included in the group, the default is 3 cases; S5, after calculation, the corresponding cluster code is brought in as conforming data, and the data of other cluster codes is calculated; when the subsequent case costs are brought in to the existing grouping costs, if the impact on the costs exceeds the threshold, the way of converting temporary data to conforming data and converting conforming data to temporary data is added, and the deviation ratio between the current data and the original data is set; after sorting by discharge time, if the number of consecutive cases exceeds the specified number of cases, the default is 6 cases, or the deviation ratio exceeds a certain ratio, the default is 30%, then the original data of the cluster code is discarded, and the data after this time node is used to recalculate the new value; in medical insurance payment, it can cope with the impact of centralized procurement and changes in mainstream treatment methods; S6, when grouping, the main cluster code and other cluster codes are calculated separately, and then further grouped in combination with the treatment method. The chapter to which the cluster code is applied, the first digit of the grouping number is the chapter of the cluster code; the second digit is the numerical value corresponding to the treatment method; the third digit is the median or mean interval; the conforming data are divided into 10 parts, expressed in 0-9, and the temporary data are divided into 24 parts, expressed in AZ, excluding o and i; the fourth digit is the influencing element, the first and second digit values ​​are taken to calculate the age data, and the median and average are taken as the value of the fourth digit age. For every increase or decrease of 5 years, combined with different treatment methods, the corresponding cost ratio is increased or decreased; specifically, for the oncology internal medicine treatment group, for every increase of 5 years, the benchmark cost is increased by 1%, for every increase of 1 day in hospitalization, the benchmark cost is increased by 5%, and for every increase in a serious diagnosis disease code, the corresponding treatment difficulty is increased.

[0009] Beneficial effects: The scheme of the present invention is the first of its kind. It has been tested and compared with the grouping algorithms of DRG and DIP. This algorithm can be used for payment and medical management, and combined with ICD-11 (International Classification of Diseases, 11th Revision), it can obtain fair and just grouping results. This algorithm uses the relationship between the median and the mean to test whether the costs of the same or similar diagnoses are reasonable. It is applicable to all areas that can be involved in ICD (International Classification of Diseases) and other environments that are applicable to this algorithm, and has practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a grouping method for disease diagnosis and treatment provided in an embodiment of the present disclosure; Figure 2 The collected information graphs provided for the embodiments of the present disclosure; Figure 3 A summary diagram of the collected information provided by the embodiment of the present disclosure; Figure 4 A diagram of group setting information provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0012] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure are not any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" are not limited to quantity, but are at least one. "Including" or "including" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used for relative positional relationships. When the absolute position of the described target changes, the relative positional relationship may also change accordingly.

[0013] In each of the accompanying drawings, the same elements are represented by similar reference numerals. For the sake of clarity, the various parts in the accompanying drawings are not all drawn to scale. In addition, some well-known parts may not be shown in the drawings.

[0014] Many specific details of the present disclosure are described below, such as component structures, materials, dimensions, processing techniques, and technologies, in order to more clearly understand the present disclosure. However, as those skilled in the art will appreciate, the present disclosure may be implemented without following these specific details.

[0015] like Figure 1 As shown, an embodiment of the present invention provides a grouping method for disease diagnosis and treatment, comprising: S1, an ICD-11 cluster code is formed for the diagnostic scheme of the same treatment method to form an initial grouping; S2, calculate the median, mean, maximum, minimum, and count of ICD-11 cluster codes and treatment methods; S3, remove the maximum and minimum values ​​of the main cluster codes when calculating the initial grouping. The maximum value defaults to 3 times the median and mean, and the minimum value defaults to 30% of the median and mean. After removal, re-determine the maximum, minimum, median, mean, and number of cases of the ICD-11 cluster codes. Other cluster codes are not removed because of the special algorithm; S4, the deviation between the median and the mean needs to be less than a ratio, the default is 15%, the number of adjacent medians is less than a ratio, the default is 5%, the ratio that meets the above conditions is qualified data, the non-qualified data is temporary data, and the data less than the preset number of cases is non-grouped data, the default is 3 cases; non-grouped data can decide whether to use it as temporary data. Even if the non-grouped data meets the conditions of qualified data, it cannot be used as qualified data for subsequent calculations; S5, after calculation, the corresponding cluster code is brought in as conforming data, and the data of other cluster codes is calculated; when the subsequent case costs are brought in to the existing grouping costs, if the impact on the costs exceeds the threshold, the way of converting temporary data to conforming data and converting conforming data to temporary data is added, and the deviation ratio between the current data and the original data is set; after sorting by discharge time, if the number of consecutive cases exceeds the specified number of cases, the default is 6 cases, or the deviation ratio exceeds a certain ratio, the default is 30%, then the original data of the cluster code is discarded, and the data after this time node is used to recalculate the new value; in medical insurance payment, it can cope with the impact of centralized procurement and changes in mainstream treatment methods; S6, when grouping, the initial grouping is further grouped, the main cluster code and other cluster codes are calculated separately, and further grouping is performed in combination with the treatment method. The chapter to which the cluster code is applied, the first digit of the grouping number is the chapter of the cluster code; the second digit is the numerical value corresponding to the treatment method; the third digit is the median or average; the conforming data is divided into 10 parts, expressed in 0-9, and the temporary data is divided into 24 parts, expressed in AZ, excluding o and i; the fourth digit is the influencing element, the first and second digit values ​​are taken to calculate the age data, the median and average are taken as the value of the fourth digit age, for every increase or decrease of 5 years, combined with different treatment methods, the corresponding cost ratio is increased or decreased, specifically, for the oncology internal medicine treatment group, for every increase of 5 years, the benchmark cost is increased by 1%, for every increase of 1 day in hospitalization, the benchmark cost is increased by 5%, and for every increase in a serious diagnosis disease code, the corresponding treatment difficulty is increased.

[0016] It should be noted that the technical solution of the present disclosure does not limit the sequence of the above steps, that is, the execution order of the steps can be arranged arbitrarily.

[0017] The scheme of the present invention is used for disease grouping. The research project was applied for in 2023. The project has been completed (basic research). The project number is JSY-2023G010. The basic research has been completed. Currently, we continue to apply for the second phase, applied basic research. After the basic research test, combined with the grouping principles of the grouper, satisfactory results have been achieved.

[0018] For the specific scheme, S101, a cluster code is formed for all diagnostic schemes with the same treatment modality; S102, for the cluster codes obtained in S101, excluding the first trunk code, sort the other trunk codes of the same treatment method; S103, removing duplicates and merging the same trunk code, general trunk code and specific trunk code that exist at the same time, retaining the additional code after the corresponding trunk code, and sorting the additional code of each trunk code to form the final ICD-11 cluster code for measurement.

[0019] Specifically, the scheme divides the diagnoses into main cluster codes and other cluster codes respectively, combined with the treatment methods; When the main cluster codes or other cluster codes correspond to different treatment methods, they cannot be combined into one cluster code; After grouping, primary data of the treatment methods with the same main diagnosis are generated. When there are other diagnoses, secondary data are generated, that is, other diagnoses and other surgeries are also included in the payment; When there are other diagnoses, the other diagnostic costs are manually calculated and grouped after being reviewed and verified to be reasonable; Among them, the first-level data is the main diagnostic data; the second-level data is other diagnostic data obtained through calculation; the third-level data is the diagnostic data obtained by manually estimating the cost; the first-level and second-level data are obtained by system calculation, and the third-level data is the estimated data. As shown in the following table: Main cluster code generation Other cluster code generation A Primary Data B Level 3 Data C Primary data calculated using secondary data D First-level data calculated using third-level data E Level 3 Data F Secondary data calculated using primary data G Secondary data calculated using tertiary data The preferred solution, S1 specifically includes: Combined with the treatment modalities, the diagnoses were divided into main cluster codes and other cluster codes; When the main cluster codes or other cluster codes correspond to different treatment methods, they cannot be merged into one cluster code; After grouping, primary data with the same main diagnosis and treatment method are generated. When there are other diagnoses, secondary data are generated. Certain special cases are manually calculated to generate tertiary data. The secondary data that matches the primary data are calculated with the tertiary data to produce initial grouping.

[0020] When there are other diagnoses, the other diagnostic costs are manually calculated and grouped after being reviewed and verified to be reasonable; Among them, the first-level data is the main diagnostic data; the second-level data is other diagnostic data obtained by calculation; the third-level data is the diagnostic data obtained by manually estimating the cost; the first- and second-level data are obtained by system calculation, and the third-level data is the estimated data.

[0021] When enrolling in the group, the following items are included: For the main cluster codes and other cluster codes with the same treatment mode, at different stages of calculation, the reasonable data are entered first, then the tertiary data, and the remaining cluster codes are entered into the temporary data, and finally the case grouping is completed; the rest are cluster coded, and the order of cluster code retention details, cluster code retention sub-items, cluster code retention categories, and trunk codes is obtained; The cluster codes, details, sub-items, categories of reasonable data and the cluster codes, details, sub-items, categories of temporary data are prioritized for preservation, with the cluster codes of reasonable data given priority, followed by the cluster codes of the details of reasonable data, and so on; after grouping based on the influence of multiple factors such as temporary data, reasonable data, median, mean, age, and length of hospital stay, even if the principle is made public, the grouping results cannot be directly inferred from existing cases.

[0022] The present invention operates based on some data on the front page of the medical record, including age, hospitalization days, diagnosis name, treatment method, whether there is rescue, and other information that has a greater impact on medical treatment. The diagnosis name includes the main diagnosis and other diagnostic information, and the treatment method includes medical treatment, surgical treatment, operation treatment, or no treatment. Using the above information, the following steps are performed: Step 1: First, all diagnostic schemes for the same treatment method are formed into an ICD-11 cluster code. Then, except for the first trunk code, the other trunk codes are sorted, and the same trunk codes are de-duplicated and merged; finally, the additional codes are retained to the corresponding trunk codes, and the additional codes of each trunk code are sorted to form a new ICD-11 cluster code.

[0023] Step 2: Calculate the median, mean, maximum, minimum, and count of all ICD-11 cluster codes.

[0024] Step 3: For all ICD-11 cluster codes, only the detail digits, only the sub-item digits, and only the category digits are taken, and the calculation is performed in the same manner as in step 2, that is, a special identification marking algorithm is performed on the detail digits, sub-item digits, and category digits of all ICD-11 cluster codes. The special identification marking algorithm is as follows: (1) The median, average, maximum, minimum, and count of the detail digits of the ICD-11 cluster codes are calculated. (2) The median, average, maximum, minimum, and count of the sub-item digits of the ICD-11 cluster codes are calculated. (3) The median, average, maximum, minimum, and count of the category digits of the ICD-11 cluster codes are calculated.

[0025] Step 4: Change step 1 to not remove the first trunk code, and repeat the operations of step 2 and step 3. That is, sort all trunk codes (including the first trunk code), remove duplicates and merge the same trunk codes, retain the additional codes to the corresponding trunk codes, sort the additional codes of each trunk code, and form all ICD-11 cluster codes. Then perform the operations of step 2 and step 3.

[0026] Step 5: Change step 1 to only keep the main code of the main diagnosis, and repeat the operations of step 2 and step 3. That is, when a patient has multiple diagnosis results, that is, when there are multiple sub-diagnosis schemes, only the main diagnosis main code is sorted, the same main code is de-duplicated and merged, the additional code is retained to the corresponding main code, and the additional code of each main code is sorted to form all ICD-11 cluster codes. Then perform the operations of step 2 and step 3.

[0027] Step 6: Step 1 is changed to only the main cluster code, and the calculations of steps 2 and 3 are performed. That is, the ICD-11 cluster codes are divided into main cluster codes and other cluster codes, and then all the main cluster codes in these different ICD-11 cluster codes are installed with the calculations of steps 2 and 3 for unified calculation.

[0028] Step 7: When the main cluster code and other cluster codes have different treatment methods, they are not merged. When there are other cluster codes with different treatment methods, the cases of the disease diagnosis scheme are not included in the calculation, but when other cluster codes have values, they can be subtracted before calculation.

[0029] Step 8, distinguish between conforming data and temporary data, and the method for excluding data: the deviation between the median and the mean needs to be less than a ratio, the default is 15%, the median and the adjacent number are less than a ratio, the default is 5%, the data that meets the conditional ratio is conforming data, the data that does not meet the ratio is temporary data, and the data less than a certain number of cases is excluded data, the default is 3 cases.

[0030] Step 9, the temporary data calculated by the above steps need to be removed, and the cases that meet the data are brought into the diagnosis plan. The data of other cluster codes are calculated specifically including: ① The data formed by two or more main cluster codes are calculated by binary or ternary linear equations; ② The single main cluster code that meets the requirements is brought into the source data, and other cluster codes of the same treatment method are merged; ③ Multiple cluster codes are combined and calculated by binary or ternary linear equations. When other cluster codes are consistent data, they can be further used to calculate the main cluster code. Similarly, steps 2 and 3 are performed to obtain the median, mean, maximum value, minimum value, count of different combinations of other cluster codes, and calculate the consistent data and temporary data. It should be pointed out that the values ​​obtained in steps ①②③ and the previous steps 2 and 3 under this step are specially marked in the algorithm. Among them, the maximum value is retained as the maximum value before and after the calculation, and the minimum value is retained as the minimum value before and after the calculation.

[0031] Step 10, using manual aggregation, treat certain ICD-11 cluster codes as compliant data and perform special identification and marking algorithms, that is, calculate the median, average, maximum, minimum, and count of the compliant data. You can also add values ​​1-11 to the results of the special identification and marking algorithm to finally form compliant data.

[0032] Step 11, after the conforming data is formed, the calculated values ​​are locked, that is, the median, average, maximum, minimum, and count values ​​of the conforming data are locked. Since the subsequent costs will change to form the current data with additional conditions, the previous conforming data will become the original data. Calculate the deviation ratio between the current data and the original data. If the number of consecutive cases exceeds the default 6 cases, or the deviation ratio exceeds the default by 30%, the original data will be discarded, starting from the default number of cases, and the calculation of the conforming data and temporary data will be repeated.

[0033] Step 12, when the main cluster code has the same treatment method as other cluster codes, in the calculation links of different stages, the conforming data shall be included first, and the rest shall be saved in the order of cluster code, cluster code retaining details, cluster code retaining sub-items, cluster code retaining categories, and trunk code, and the conforming data shall be included first.

[0034] Step 13, grouping: the median or mean can be used as the benchmark value, which is determined by the user. When the main cluster code has the same treatment method as other cluster codes, check the chapter of the ICD-11 cluster code. The first digit of the grouping number is the chapter of the code; the second digit is the single value represented by the treatment method; the third digit is the median, mean, maximum or minimum value. The data that meet the requirements are divided into 10 parts, expressed in 0-9, and the temporary data are divided into 24 parts, expressed in AZ, and o and i are excluded; the fourth digit is the score obtained by the influencing elements, treatment days, patient age, severe main code or additional code, etc. The chapters with little influence are expressed in 0-9, the chapters with greater influence are expressed in AZ, and o and i are excluded. The chapters with great influence are expressed in AZ and 0-9.

[0035] The Medical Insurance, National Health and Family Planning Commission, or other departments can set their own scores based on influencing factors. For example, if the person is over 60 years old, the benchmark will be raised by 1% for every additional 5 years; if the number of treatment days is less than 4 days, the benchmark will be lowered by 10% for every day less.

[0036] This algorithm can be used for hospitalization, to deduct all expenses, and to calculate certain hospitalization expenses, such as consumables and antibiotics. It can also be used for outpatient care, and can total and calculate all expenses for the same patient within a year.

[0037] In a specific implementation scenario, combined with Figure 2-Figure 4As shown, an operation interface of an APP based on the solution of the present invention is shown, wherein the benchmark value setting 1 setting includes four items: 1. Use the median to form the benchmark value, 2. Use the average to form the benchmark value, 3. Use the median to form the benchmark value for temporary data, and use the average to form the benchmark value for conforming data, 4. Use the median to form the benchmark value for conforming data, and use the average to form the benchmark value for temporary data Benchmark value setting 2 is set to use total cost to form the benchmark value, drug cost to form the benchmark value, consumables cost to form the benchmark value, etc. The ratio of median to mean is set, and the ratio of median to adjacent values ​​is set to meet the judgment criteria of the data. The ratio can be changed When the deviation ratio between the current data and the original data reaches a certain ratio, the matching data will be withdrawn. The condition for generating groups is to encode at least the same clusters into one group. The content not captured in the screenshot below is the summary interface of each calculation content.

[0038] When grouping, data that meet the requirements will be grouped first, followed by temporary data. The order can be adjusted through identification.

[0039] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A grouping method for disease diagnosis and treatment, characterized in that: include: S1, an ICD-11 cluster code is formed for the diagnostic scheme of the same treatment method to form an initial grouping; S2, calculate the median, mean, maximum, minimum, and count of ICD-11 cluster codes and treatment methods; S3, remove the maximum and minimum values ​​of the main cluster codes when calculating the initial grouping. The maximum value defaults to 3 times the median and mean, and the minimum value defaults to 30% of the median and mean. After removal, re-determine the maximum, minimum, median, mean, and number of cases of the ICD-11 cluster codes. Other cluster codes are not removed because of the special algorithm; S4, the deviation between the median and the mean needs to be less than a ratio, the default is 15%, the number of adjacent medians is less than a ratio, the default is 5%, the ratio that meets the above conditions is qualified data, the non-qualified data is temporary data, and the data less than the preset number of cases is non-grouped data, the default is 3 cases; non-grouped data can decide whether to use it as temporary data. Even if the non-grouped data meets the conditions of qualified data, it cannot be used as qualified data for subsequent calculations; S5, after calculation, the corresponding cluster code is brought in as conforming data, and the data of other cluster codes is calculated; when the subsequent case costs are brought in to the existing grouping costs, if the impact on the costs exceeds the threshold, the way of converting temporary data to conforming data and converting conforming data to temporary data is added, and the deviation ratio between the current data and the original data is set; after sorting by discharge time, if the number of consecutive cases exceeds the specified number of cases, the default is 6 cases, or the deviation ratio exceeds a certain ratio, the default is 30%, then the original data of the cluster code is discarded, and the data after this time node is used to recalculate the new value; in medical insurance payment, it can cope with the impact of centralized procurement and changes in mainstream treatment methods; S6, when grouping, the main cluster code and other cluster codes are calculated separately, and then further grouped in combination with the treatment method. The chapter to which the cluster code is applied, the first digit of the grouping number is the chapter of the cluster code; the second digit is the numerical value corresponding to the treatment method; the third digit is the median or mean interval; the conforming data are divided into 10 parts, expressed in 0-9, and the temporary data are divided into 24 parts, expressed in AZ, excluding o and i; the fourth digit is the influencing element, the first and second digit values ​​are taken to calculate the age data, and the median and average are taken as the value of the fourth digit age. For every increase or decrease of 5 years, combined with different treatment methods, the corresponding cost ratio is increased or decreased; specifically, for the oncology internal medicine treatment group, for every increase of 5 years, the benchmark cost is increased by 1%, for every increase of 1 day in hospitalization, the benchmark cost is increased by 5%, and for every increase in a serious diagnosis disease code, the corresponding treatment difficulty is increased.

2. The grouping method for disease diagnosis and treatment according to claim 1, characterized in that: The grouping method specifically includes: S101, all diagnostic schemes for the same treatment modality form a cluster code; S102, for the cluster codes obtained in S101, excluding the first trunk code, sort the other trunk codes of the same treatment method; S103, removing duplicates and merging the same trunk code, general trunk code and specific trunk code that exist at the same time, retaining the additional code after the corresponding trunk code, and sorting the additional code of each trunk code to form the final ICD-11 cluster code for measurement.

3. The grouping method for disease diagnosis and treatment according to claim 1, characterized in that: The S1 specifically includes: Combined with the treatment modalities, the diagnoses were divided into main cluster codes and other cluster codes; When the main cluster codes or other cluster codes correspond to different treatment methods, they cannot be combined into one cluster code; After grouping, primary data with the same main diagnosis and treatment method are generated. When there are other diagnoses, secondary data are generated. Some special cases are manually calculated to generate tertiary data. The secondary data that matches the data and the primary data are calculated with the tertiary data to produce the initial grouping; Among them, the first-level data is the main diagnostic data; the second-level data is other diagnostic data obtained by calculation; the third-level data is the diagnostic data obtained by manually estimating the cost; the first- and second-level data are obtained by system calculation, and the third-level data is the estimated data.

4. The grouping method for disease diagnosis and treatment according to claim 3, characterized in that: When enrolling in the group, the following items are included: For the main cluster codes and other cluster codes with the same treatment mode, at different stages of calculation, the reasonable data are entered first, then the tertiary data, and the remaining cluster codes are entered into the temporary data, and finally the case grouping is completed; the rest are cluster coded, and the order of cluster code retention details, cluster code retention sub-items, cluster code retention categories, and trunk codes is obtained; The cluster codes, details, sub-items, categories of reasonable data and the cluster codes, details, sub-items, categories of temporary data are prioritized for preservation, with the cluster codes of reasonable data given priority, followed by the cluster codes of the details of reasonable data, and so on; after grouping based on the influence of multiple factors such as temporary data, reasonable data, median, mean, age, and length of hospital stay, even if the principle is made public, the grouping results cannot be directly inferred from existing cases.

5. The grouping method for disease diagnosis and treatment according to claim 2, characterized in that: The S4 specifically includes: The enrollment number and the grouping number are divided into two independent related numbers, two or more reasonable data, a single reasonable data and temporary data, other cluster coded initial groupings and cluster coded initial groupings or canceled treatment method data, and the obtained values ​​are directly calculated by subtraction or two-variable linear equations or three-variable linear equations in accordance with S2 and S3 claims 2 and claim 3.

Images