A method and system for determining high-risk medical insurance settlement list under DRG payment

Abstract

The present invention provides a method and system for determining a high-risk medical insurance settlement list under DRG payment. The method mainly performs determination through four steps. Step one, the collected basic data is calculated; Step two, based on the calculation result, the regulatory high-risk rule library is screened; Step three, the regulatory high-risk liquidation list is determined; Step four, when the determination result meets the preset requirements, the regulatory high-risk liquidation list is output. Through the above method, the workload of manual determination is greatly reduced, and the detection rate of illegal medical insurance settlement lists is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of determining a high-risk medical insurance settlement list under DRG payment, and specifically relates to a method and system for determining a high-risk medical insurance settlement list under DRG payment. Background Art

[0002] Diagnosis Related Groups (DRGs) are an important tool for measuring the quality and efficiency of medical services and for medical insurance payment. DRG payment is an important means to achieve a win-win situation for "medical-insurance-patient" and promote tiered diagnosis and treatment to promote the transformation of service models. That is, payment is made according to disease diagnosis-related groups, that is, related diseases are divided into a group and paid in a package, instead of paying item by item.

[0003] However, under DRG payment, medical institutions may engage in behaviors such as "low code and high coding", "special disease list abnormalities", "fragmented hospitalization", "low standard admission", "physical examination admission", etc. At present, there is a lack of effective judgment methods or application software for the above-mentioned violations on the market, and the suspected violation cases captured are prone to clinical disputes. If the expert discussion method is used, each medical institution is required to provide the original medical records corresponding to the medical insurance settlement list, which is difficult to collect, takes a long time to study the data, and has low judgment efficiency. Summary of the invention

[0004] Based on this, an embodiment of the present invention provides a method and system for determining a high-risk medical insurance settlement list under DRG payment, aiming to solve the problem in the prior art that violations in medical insurance settlement rely on time-consuming and labor-intensive manual analysis.

[0005] A first aspect of an embodiment of the present invention provides a method for determining a high-risk medical insurance settlement list under DRG payment, the method comprising:

[0006] Set up a violation feature library for the medical insurance settlement list, where the violation feature library includes MDC type, type of treatment method for this hospitalization, type of comparison with the last treatment method, CC type, type of total hospitalization cost, type of special disease single negotiation, type of interval with the last hospitalization, profit type, and type of proportion of inspection and testing;

[0007] According to each type in the violation feature library, corresponding violation label sub-libraries are established;

[0008] Putting several medical insurance settlement lists uploaded to the medical insurance settlement platform in preset regions and preset time periods into the DRG grouper, determining the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library;

[0009] A regulatory risk category library is set up, and violations are defined for each regulatory risk category in the regulatory risk category library, and corresponding violation label sub-libraries are extracted from the violation label library, and the Cartesian product between the extracted violation label sub-libraries is calculated to form a regulatory risk rule library, wherein the regulatory risk rule library includes a number of elements that have undergone Cartesian product;

[0010] Calculate the first occurrence rate of the regulatory risk rule base in the violation tag base of a single settlement list;

[0011] Calculate the first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate;

[0012] According to the four-part method and the total incidence rate, the regulatory risk rule base is screened to determine each target element, and each target element is sorted to form a target regulatory risk rule base;

[0013] Calculate the second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list;

[0014] According to the second occurrence rate, calculate the second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists;

[0015] Calculate the risk weight coefficient of each regulatory risk category based on the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule base based on the second total incidence rate and the risk weight coefficient;

[0016] Calculate the total amount of violation information of each medical insurance settlement list according to the amount of violation information and the second incidence rate, and calculate the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list;

[0017] According to the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists, calculate the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list;

[0018] Calculate the risk factor of each medical insurance settlement list violation based on the standard deviation of all medical insurance settlement list violation information and the standard deviation of each medical insurance settlement list violation information;

[0019] Determine whether there is a single medical insurance settlement list with a total amount of illegal information greater than the average amount of illegal information in all medical insurance settlement lists;

[0020] If so, determine whether the corresponding medical insurance settlement list violation risk coefficient is greater than the threshold;

[0021] If so, it is determined to be a high regulatory risk and the corresponding high regulatory risk settlement list is output.

[0022] Furthermore, in the step of calculating the risk weight coefficient of each regulatory risk category based on the second total incidence rate, the calculation formula is:

[0023] C i =∑ i＝1 p it ;

[0024] Among them, C i It is expressed as the risk weight coefficient of the ith regulatory risk category library, p it Expressed as the second overall incidence.

[0025] Furthermore, in the step of calculating the amount of violation information of each target regulatory risk rule base according to the second total incidence rate and the risk weight coefficient, the calculation formula is:

[0026] K it =C i ×(-log2p it );

[0027] Among them, K it The amount of violation information represented as the target regulatory risk rule base.

[0028] Furthermore, in the step of calculating the total amount of violation information of each medical insurance settlement list according to the violation information amount and the second incidence rate, the calculation formula is:

[0029] R n =∑ n＝1 (K it ×p nit );

[0030] Among them, p nit Expressed as the second incidence rate, R n Represents the total amount of violation information in the medical insurance settlement list.

[0031] Furthermore, in the step of calculating the average amount of illegal information in all medical insurance settlement lists based on the total amount of illegal information in each medical insurance settlement list, the calculation formula is:

[0032]

[0033] in, It is represented by the average amount of violation information in all medical insurance settlement lists, and N is represented by the total number of medical insurance settlement lists.

[0034] Further, in the step of calculating the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list based on the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists, the calculation formula for the standard deviation of the amount of illegal information in all medical insurance settlement lists is:

[0035]

[0036] Among them, σ represents the standard deviation of the amount of illegal information in all medical insurance settlement lists;

[0037]

[0038] Among them, σ n It is expressed as the standard deviation of the amount of illegal information in the nth medical insurance settlement list.

[0039] Furthermore, in the step of calculating the risk coefficient of violation of each medical insurance settlement list according to the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list, the calculation formula is:

[0040] K n =σ n / σ;

[0041] Among them, K n It is expressed as the risk coefficient of violation of the nth medical insurance settlement list.

[0042] A second aspect of an embodiment of the present invention provides a system for determining a high-risk medical insurance settlement list under DRG payment, the system comprising:

[0043] A setting module is used to set a violation feature library of the medical insurance settlement list, wherein the violation feature library includes MDC type, type of this hospitalization treatment method, type of comparison with the last treatment method, CC type, total hospitalization cost type, special disease single negotiation type, interval type with the last hospitalization, profit type, and inspection and test proportion type;

[0044] An establishment module, used for establishing each violation label sub-library corresponding to each type in the violation feature library;

[0045] A violation label library determination module is used to put a number of medical insurance settlement lists uploaded to the medical insurance settlement platform in a preset region and a preset time period into a DRG grouper, and determine the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library;

[0046] The first calculation module is used to set up a regulatory risk category library, define violations for each regulatory risk category in the regulatory risk category library, extract corresponding violation label sub-libraries from the violation label library, and calculate the Cartesian product between the extracted violation label sub-libraries to form a regulatory risk rule library, wherein the regulatory risk rule library includes a number of elements that have undergone Cartesian products;

[0047] A second calculation module is used to calculate a first occurrence rate of the regulatory risk rule base in the violation tag base of a single settlement list;

[0048] A third calculation module is used to calculate a first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate;

[0049] The screening module is used to screen the regulatory risk rule base according to the four-part method and the total incidence rate, determine each target element, and organize each target element to form a target regulatory risk rule base;

[0050] A fourth calculation module, used to calculate a second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list;

[0051] A fifth calculation module, configured to calculate a second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists according to the second occurrence rate;

[0052] a sixth calculation module, configured to calculate the risk weight coefficient of each regulatory risk category library according to the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule library according to the second total incidence rate and the risk weight coefficient;

[0053] a seventh calculation module, configured to calculate the total amount of violation information of each medical insurance settlement list according to the amount of violation information and the second incidence rate, and calculate the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list;

[0054] An eighth calculation module, for calculating the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list according to the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists;

[0055] A ninth calculation module, for calculating the risk coefficient of violation of each medical insurance settlement list according to the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list;

[0056] The first judgment module is used to judge whether the total amount of illegal information in a single medical insurance settlement list is greater than the average amount of illegal information in all medical insurance settlement lists;

[0057] The second judgment module is used to judge whether the corresponding medical insurance settlement list violation risk coefficient is greater than a threshold value when it is judged that the total amount of violation information in a single medical insurance settlement list is greater than the average amount of violation information in all medical insurance settlement lists;

[0058] The output module is used to determine that when the risk coefficient of violation of the corresponding medical insurance settlement list is greater than a threshold, it is considered as a high regulatory risk and output the corresponding high-risk regulatory settlement list.

[0059] A third aspect of an embodiment of the present invention provides a computer-readable storage medium, including:

[0060] The readable storage medium stores one or more programs, which, when executed by the processor, implement the method for determining a high-risk medical insurance settlement list under DRG payment as described in the first aspect.

[0061] A fourth aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising a memory and a processor, wherein:

[0062] The memory is used to store computer programs;

[0063] When the processor is used to execute the computer program stored in the memory, it implements the method for determining the high-risk medical insurance settlement list under DRG payment as described in the first aspect.

[0064] A method and system for determining a high-risk medical insurance settlement list under DRG payment is provided in an embodiment of the present invention. By setting a violation feature library of the medical insurance settlement list, each violation label sub-library is established according to each type in the violation feature library; a number of medical insurance settlement lists uploaded to the medical insurance settlement platform in a preset area and a preset time period are put into a DRG grouper to determine the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library; a regulatory risk category library is set, and violation behaviors are defined for each regulatory risk category in the regulatory risk category library, and the corresponding violation label sub-library is extracted from the violation label library, and the extracted violation label sub-library is calculated. Cartesian products of the violation label sub-libraries are used to form a regulatory risk rule base, which includes several elements that have undergone Cartesian products; a first occurrence rate of the regulatory risk rule base in the violation label base of a single settlement list is calculated; based on the first occurrence rate, a first total occurrence rate of the regulatory risk rule base in the violation label base of all settlement lists is calculated; based on the four-part method and the total occurrence rate, the regulatory risk rule base is screened to determine each target element, and each target element is sorted to form a target regulatory risk rule base; a second occurrence rate of the target regulatory risk rule base in the violation label base of a single settlement list is calculated; based on the second occurrence rate, a first total occurrence rate of the regulatory risk rule base in the violation label base of all settlement lists is calculated; The second total incidence rate is calculated for the target regulatory risk rule base in the violation label base of all settlement lists; the risk weight coefficient of each regulatory risk category library is calculated according to the second total incidence rate, and the violation information volume of each target regulatory risk rule base is calculated according to the second total incidence rate and the risk weight coefficient; the total amount of violation information of each medical insurance settlement list is calculated according to the violation information volume and the second incidence rate, and the average amount of violation information of all medical insurance settlement lists is calculated according to the total amount of violation information of each medical insurance settlement list; the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list are calculated according to the total amount of violation information of each medical insurance settlement list and the average amount of violation information of all medical insurance settlement lists; the violation risk coefficient of each medical insurance settlement list is calculated according to the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list; it is determined whether there is a single medical insurance settlement list with a total amount of violation information greater than the average amount of violation information of all medical insurance settlement lists; if so, it is determined whether the corresponding medical insurance settlement list violation risk coefficient is greater than the threshold; if so, it is determined to be a high regulatory risk, and the corresponding high regulatory risk settlement list is output, which effectively solves the problem of time-consuming and labor-intensive manual judgment of violations in medical insurance settlement. DETAILED DESCRIPTION

[0065] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0067] Embodiment 1

[0068] A method for determining a high-risk medical insurance settlement list under DRG payment provided in Embodiment 1 of the present invention specifically includes steps S01 to S06.

[0069] Step S01, setting a violation feature library of the medical insurance settlement list, wherein the violation feature library includes MDC type, type of this hospitalization treatment method, type of comparison with the last treatment method, CC type, total hospitalization cost type, special disease single negotiation type, interval type with the last hospitalization, profit type, and examination and testing ratio type.

[0070] Specifically, set up the violation feature library S of the medical insurance settlement list i , where S1 is "MDC type", S2 is "this hospitalization treatment method type", S3 is "comparison type with the last treatment method", S4 is "CC type", S5 is "total hospitalization cost type", S6 is "special disease single negotiation type", S7 is "interval type with the last hospitalization", S8 is "profit type", and S9 is "inspection and testing ratio type". It should be noted that the calculation method of each type definition in the violation feature library is as follows:

[0071] (1) S1 refers to the classification of "MDC type" obtained by calculation after a settlement list is uploaded to the medical insurance settlement platform and then passed through the DRG grouper, which represents the anatomical and physiological system to which the settlement list belongs in medicine. According to the DRG grouping scheme, the first letter of the DRG group code is classified according to AZ, and each English letter represents a different anatomical and physiological system in medicine. For example, after a settlement list is grouped by the grouper, it is classified into the DRG group code "CB39", the DRG name is "lens surgery", and the first letter of the DRG group is "C". Then the S1 of the settlement list is "MDCC", which means that it belongs to eye diseases and functional disorders in medicine;

[0072] (2) S2 refers to the classification of "treatment means" obtained after a settlement list is uploaded to the medical insurance settlement platform and then passed through the DRG grouper, which represents the medical treatment measures taken in the settlement list. According to the DRG grouping scheme, the second letter of the DRG group code "A, B, C, D, E, F, G, H, J" represents the "surgical group", the second letter of the DRG group code "K, L, M, N, P, Q" represents the "operation group", and the second letter of the DRG group code "R, S, T, U, V, W, X, Y, Z" represents the "internal medicine group". For example, after a settlement list is grouped by the grouper, it is divided into the DRG group "CB39", the DRG name is "lens surgery", and the second letter of the DRG group code is "B", then the S2 of the settlement list is the "surgical group";

[0073] (3) S3 refers to the classification of "treatment comparison" obtained after calculation when a settlement list is uploaded to the medical insurance settlement platform, representing the duplication of treatment methods in the settlement list. Treatment comparison = {S2 of the insured person's previous settlement list} ∩ {S2 of this settlement list}. If the intersection is not an empty set, S3 of the settlement list is "the same type of hospitalization treatment as the last time"; if the intersection is an empty set, S3 of the settlement list is "a different type of hospitalization treatment from the last time". For example, after a settlement list is passed through the grouper, it is classified into the DRG group "CB39", and the S2 obtained this time is the "Surgery Group"; after the settlement list generated by the insured person's last hospitalization is passed through the grouper, it is classified into the DRG group "CC19", and the last S2 is the "Surgery Group"; treatment means comparison = {"Surgery Group"}, the intersection is not an empty set, then the S3 of the settlement list is "the same as the last hospitalization treatment type"; (4) S4 refers to the classification of "comorbidities and complications" obtained after a settlement list is uploaded to the medical insurance settlement platform and then passed through the DRG grouper, representing the complexity of the settlement list. According to the DRG grouping scheme, the fourth digit of the DRG group code "1" represents "with serious complications and complications", the fourth digit of the DRG group code "3" represents "with general complications and complications", the fourth digit of the DRG group code "5" represents "without complications and complications", and the fourth digit of the DRG group code "9" represents "no complications and complications". For example, after a settlement list is grouped by the grouper, it is classified into the DRG group code "ID11", the DRG name is "small joint surgery, with serious complications and complications", and the fourth digit of the DRG group code is "1", then S4 of the settlement list is "with serious complications and complications";

[0074] (5) S5 refers to the classification of the "total cost amount" obtained after a certain settlement list is uploaded to the medical insurance settlement platform, which represents the cost consumption of the settlement list. If the total cost amount is less than 1,000 yuan, S5 of the settlement list is "extremely low cost"; if the total cost amount is between 1,000 yuan and 3,000 yuan, S5 of the settlement list is "lower cost"; if the total cost amount is between 3,000 yuan and 6,000 yuan, S5 of the settlement list is "general cost"; if the total cost amount is between 6,000 yuan and 10,000 yuan, S5 of the settlement list is "higher cost"; if the total cost amount is greater than 10,000 yuan, S5 of the settlement list is "extremely high cost". For example, the total cost of a settlement list uploaded to the medical insurance settlement platform is 7,680 yuan, then S5 of the settlement list is "higher cost";

[0075] (6) S6 refers to the classification of the "settlement department" obtained through calculation after a certain settlement list is uploaded to the medical insurance settlement platform, representing the special disease single negotiation situation of the settlement list. If the settlement department is the Department of Traditional Chinese Medicine, then S6 of the settlement list will be "Special disease single negotiation for Traditional Chinese Medicine diseases"; if the settlement department is the Department of Rehabilitation, then S6 of the settlement list will be "Special disease single negotiation for rehabilitation diseases"; if the settlement department is the Department of Critical Care Medicine, then S6 of the settlement list will be "Special disease single negotiation for critical care medicine diseases"; if the settlement department is other departments, then S6 of the settlement list will be "No special disease single negotiation". For example, if the settlement department of a certain settlement list uploaded to the medical insurance settlement platform is the Department of Obstetrics and Gynecology, then S6 of the settlement list will be "No special disease single negotiation";

[0076] (7) S7 refers to the classification of "time interval" obtained after a certain settlement list is uploaded to the medical insurance settlement platform. The time interval = the settlement date uploaded to the medical insurance settlement platform - the settlement date when the insured person's last settlement list was uploaded to the medical insurance settlement platform, which represents the repeated hospitalization of the settlement list. If the time interval is less than 14 days, S7 of the settlement list is "repeated hospitalization in the short term". If the time interval is greater than 14 days, S7 of the settlement list is "non-repeated hospitalization in the short term". For example, the settlement date of a certain settlement list uploaded to the medical insurance settlement platform is January 10, 2024, and the settlement date of the insured person's last settlement list uploaded to the medical insurance settlement list is January 2, 2024. The time interval between the two is 8 days, then S7 of the settlement list is "repeated hospitalization in the short term";

[0077] (8) S8 refers to the classification of the "multiplier" obtained after a certain settlement list is uploaded to the medical insurance settlement platform and then passed through the DRG grouper. The multiplier = the total amount of expenses uploaded to the medical insurance settlement platform / the DRG payment standard assigned by the grouper, which represents the DRG profit and loss situation of the settlement list. The smaller the multiplier, the better the profit situation. If the multiplier is less than 0.4, the S8 of the settlement list is "strong profit"; if the multiplier is between 0.4 and 0.8, the S8 of the settlement list is "weak profit"; if the multiplier is between 0.8 and 1.2, the S8 of the settlement list is "break-even profit"; if the multiplier is between 1.6, the S8 of the settlement list is "weak loss"; if the multiplier is greater than 1.6, the S8 of the settlement list is "strong loss". For example, after a settlement list is grouped by the grouper, the DRG payment standard is 8,000 yuan. The total cost of the settlement list uploaded to the medical insurance settlement list is 6,000 yuan. The multiplier = 6,000 yuan / 8,000 yuan = 0.75, then S8 of the settlement list is "weak profit";

[0078] (9) S9 refers to the classification of "inspection ratio" obtained after a settlement list is uploaded to the medical insurance settlement list. Inspection ratio = inspection fee amount uploaded to the medical insurance settlement platform / total fee uploaded to the medical insurance settlement platform, representing the consumption of inspection items in the settlement list. If the ratio is between 0 and 0.7, S9 of the settlement list is "normal inspection ratio". If the ratio is greater than 0.7, S9 of the settlement list is "abnormal inspection ratio". For example, the inspection fee amount uploaded to the medical insurance settlement list of a settlement list is 3,600 yuan, and the total fee amount is 4,000 yuan. The inspection ratio = 3,600 yuan / 4,000 yuan = 90%, then S9 of the settlement list is "abnormal inspection ratio".

[0079] Step S02: establishing corresponding violation label sub-libraries according to the types in the violation feature library.

[0080] Specifically, according to the definitions of each type in the violation feature library, a violation label sub-library S is established. ij , where: (1) S 1j For each element of S1, S1 = {MDCA, MDCB, MDCC, MDCD, MDCE, MDCF, MDCG, MDCH, MDCI, MDCJ, MDCK, MDCL, MDCM, MDCN, MDCO, MDCP, MDCQ, MDCR, MDCS, MDCT, MDCU, MDCV, MDCW, MDCX, MDCY, MDCZ};

[0081] (2)S 2j For each element of S2, S2 = {surgical group, operation group, internal medicine group};

[0082] (3)S 3j For each element of S3, S3 = {same as the last hospitalization type, different from the last hospitalization type};

[0083] (4)S 4j The elements of S4, S4 = {with severe comorbidities and complications, with general comorbidities and complications, without comorbidities and complications, without comorbidities and complications};

[0084] (5)S 5j For each element of S5, S5 = {extremely low cost, relatively low cost, average cost, relatively high cost, extremely high cost};

[0085] (6)S 6j Each element of S6, S6 = {special disease single discussion for TCM diseases, special disease single discussion for rehabilitation diseases, special disease single discussion for critical care medicine diseases, no special disease single discussion};

[0086] (7)S 7j For each element of S7, S7 = {repeated hospitalization within a short period of time, repeated hospitalization within a non-short period of time};

[0087] (8)S 8j are the elements of S8, S8 = {strong profit, weak profit, break-even profit, weak loss, strong loss}; (9) S 9j For each element of S9, S9 = {the inspection and examination ratio is abnormal, the inspection and examination ratio is normal}.

[0088] Step S03, putting several medical insurance settlement lists uploaded to the medical insurance settlement platform in preset areas and preset time periods into the DRG grouper, and determining the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library.

[0089] Specifically, N medical insurance settlement lists uploaded to the medical insurance settlement platform in a certain area during a certain period of time are put into the DRG grouper. After the above calculation method, the violation label library Q of each settlement list is obtained. n , Q n For each S in the settlement list ij For example, a settlement list is grouped by the grouper and data is calculated to obtain its Q n ={MDCE, internal medicine group, same type of hospitalization as the last time, with general comorbidities and complications, general expenses, no special disease list, no repeated hospitalization in a short period of time, weak loss, normal proportion of tests and examinations}.

[0090] Step S04, set up a regulatory risk category library, define violations for each regulatory risk category in the regulatory risk category library, extract corresponding violation label sub-libraries from the violation label library, and calculate the Cartesian product between the extracted violation label sub-libraries to form a regulatory risk rule library, which includes a number of elements that have undergone Cartesian products.

[0091] Specifically, set up a regulatory risk category library M i , where M1 is “low code and high coding”, M2 is “special disease single discussion exception”, M3 is “decomposed hospitalization”, M4 is “low standard hospitalization”, and M5 is “physical examination hospitalization”.

[0092] To M i Define "violation behavior" and extract the corresponding violation label sub-library S from the violation feature library according to the definition ij , calculate the Cartesian product between each set to form the regulatory risk rule base M ij , where: (1) M1 “low code and high coding” refers to the violation of “changing CC type to obtain a lower multiple”, so the S4 “CC type” set and the S8 “profit type” set are extracted, and the Cartesian product between the two sets is calculated = {(with severe comorbidities and complications, strong profit), (with general comorbidities and complications, strong profit), (without comorbidities and complications, strong profit), (without comorbidities and complications, strong profit), (with severe comorbidities and complications, weak profit), (with general comorbidities and complications, weak profit), (without comorbidities and complications, weak profit), (without comorbidities and complications, weak profit), (without comorbidities and complications, weak profit), (without comorbidities and complications, weak profit) With complications, weak profit), (With serious complications and complications, flat profit), (With general complications and complications, flat profit), (Without complications and complications, flat profit), (Without complications and complications, flat profit), (With serious complications and complications, weak loss), (With general complications and complications, weak loss), (Without complications and complications, weak loss), (Without complications and complications, weak loss), (With serious complications and complications, strong loss), (With general complications and complications, strong loss), (Without complications and complications, strong loss), (Without complications and complications, strong loss)}, where M 1j are the elements of the above Cartesian product;

[0093] (2) M2 “Special disease single discussion exception” refers to the violation of “the settlement list of non-TCM, rehabilitation, and critical care medicine disciplines entering the special disease single discussion”. Therefore, we extract the S1 “MDC type” set and the S6 “Special disease single discussion type” set, and calculate the Cartesian product between the two sets, where M 2j are the elements of the above Cartesian product;

[0094] (3) M3 “decomposed hospitalization” refers to the violation of “repeated hospitalization for the same disease in a short period of time”. Therefore, we extract the set of S7 “interval type with the last hospitalization” and the set of S3 “comparison type with the last treatment” and calculate the Cartesian product between the two sets, where M 3j are the elements of the above Cartesian product;

[0095] (4) M4 “low-standard hospitalization” refers to the violation of “hospitalization for diseases that do not require hospitalization”. Therefore, we extract the set S5 “total hospitalization cost type” and the set S2 “type of hospitalization treatment this time” and calculate the Cartesian product between the two sets, where M 4j are the elements of the above Cartesian product;

[0096] (5) M5 “Physical examination admission” refers to the violation of “hospitalization purpose is mainly for examination and inspection”, so we take the set of S5 “total hospitalization cost type” and the set of S9 “examination and inspection proportion type” and calculate the Cartesian product between the two sets, where M 5j are the elements of the Cartesian product above.

[0097] Step S05, calculating the first occurrence rate of the regulatory risk rule library in the violation tag library of a single settlement list.

[0098] Specifically, calculate M ij In the single settlement list of illegal tag library Q n The incidence rate p nij , where p nij ={0,1}, when When p nij = 0, otherwise 1. For example, the violation tag library Q1 of a settlement list = {MDCE, internal medicine group, same type of hospitalization as last time, with general comorbidities and complications, general expenses, no special disease list, not repeated hospitalization in a short period of time, weak loss, normal proportion of tests and examinations}, the regulatory risk rule library M 11 = {with severe comorbidities and complications, strong profitability}, at this time Q1 and M 11 There is no intersection, M 11 The incidence rate p in Q1 111 =0.

[0099] Step S06: Calculate the first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate.

[0100] Specifically, calculate M ij In all settlement lists, the illegal tag library Q n The total probability of occurrence p ij , where p ij =(∑ n＝1 pnij ) / N.

[0101] Step S07, based on the four-part method and the total incidence rate, the regulatory risk rule base is screened to determine each target element, and each target element is sorted to form a target regulatory risk rule base.

[0102] It should be noted that if p ij The smaller the M ij The larger the amount of illegal information it carries, the larger the amount of illegal information it carries. ij Filter and select p ij Sort by high to low, filter the M ranking in the bottom 25% ij It is a high-risk regulation rule, otherwise it is a medium- and low-risk regulation rule. ij Organized into a regulatory high-risk rule library M it .

[0103] Step S08, calculating the second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list.

[0104] Calculate M it In the single settlement list of illegal tag library Q n The incidence rate p nit , where p nit ={0,1}, when When p nit =0, otherwise 1.

[0105] Step S09: Calculate the second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists according to the second occurrence rate.

[0106] Understandably, calculate M it In all settlement lists, the illegal tag library Q n The total incidence rate p it , where p it =(∑ n＝1 p nit ) / N.

[0107] Step S10, calculate the risk weight coefficient of each major regulatory risk library based on the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule library based on the second total incidence rate and the risk weight coefficient.

[0108] Specifically, calculate each M i The risk weight coefficient C i , where C i =∑ i＝1 p it , C iIt is expressed as the risk weight coefficient of the ith regulatory risk category library, p it Expressed as the second total incidence. i The larger the M i The greater the probability of occurrence, the more you need to use M i Make a high risk determination of violation.

[0109] In the step of calculating the amount of violation information of each target regulatory risk rule base according to the second total incidence rate and the risk weight coefficient, the calculation formula is:

[0110] K it =C i ×(-log2p it );

[0111] Among them, K it The amount of violation information represented as the target regulatory risk rule base.

[0112] Step S11, calculating the total amount of violation information of each medical insurance settlement list according to the amount of violation information and the second incidence rate, and calculating the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list.

[0113] In the step of calculating the total amount of violation information of each medical insurance settlement list according to the violation information amount and the second incidence rate, the calculation formula is:

[0114] R n =∑ n＝1 (K it ×p nit );

[0115] Among them, p nit Expressed as the second incidence rate, R n Represents the total amount of violation information in the medical insurance settlement list.

[0116] According to the total amount of illegal information in each medical insurance settlement list, in the step of calculating the average amount of illegal information in all medical insurance settlement lists, the calculation formula is:

[0117]

[0118] in, It is represented by the average amount of violation information in all medical insurance settlement lists, and N is represented by the total number of medical insurance settlement lists.

[0119] Step S12, calculating the standard deviation of the amount of violation information in all medical insurance settlement lists and the standard deviation of the amount of violation information in each medical insurance settlement list based on the total amount of violation information in each medical insurance settlement list and the average amount of violation information in all medical insurance settlement lists.

[0120]

[0121] Among them, σ represents the standard deviation of the amount of illegal information in all medical insurance settlement lists;

[0122]

[0123] Among them, σ n It is expressed as the standard deviation of the amount of illegal information in the nth medical insurance settlement list.

[0124] Step S13, calculating the violation risk coefficient of each medical insurance settlement list according to the standard deviation of the violation information volume of all medical insurance settlement lists and the standard deviation of the violation information volume of each medical insurance settlement list.

[0125] Calculate the risk factor K of each medical insurance settlement list violation n =σ n / σ, where K n It is expressed as the risk coefficient of violation of the nth medical insurance settlement list.

[0126] It should be noted that according to relevant requirements, local medical insurance departments are required to spot check at least 5% of medical insurance settlement lists every year. Assuming that all of these 5% of medical insurance settlement lists are high-risk for supervision, according to the concept of normal distribution proposed by Moivre in 1733, the larger the amount of data, the more objective it is, and the more it tends to be normally distributed. When the amount of historical medical insurance settlement data is large enough, the total amount of illegal information on each medical insurance settlement list is normally distributed. At the same time, the total amount of illegal information on the high-risk medical insurance settlement list is R n Must be greater than the average Therefore, the confidence interval of the normal distribution is 90%, that is, 90% of the medical insurance settlement list violation information is within between.

[0127] Step S14, determine whether there is a single medical insurance settlement list with a total amount of violation information greater than the average amount of violation information in all medical insurance settlement lists. If so, execute step S15.

[0128] That is, when the total amount of illegal information in a medical insurance settlement list is R n >R, then make a subsequent judgment. n >1.64, if so, it is judged as high regulatory risk.

[0129] In step S15, it is determined whether the corresponding medical insurance settlement list violation risk coefficient is greater than a threshold value. If so, step S16 is executed.

[0130] Among them, the threshold is 1.64, that is, to judge whether K n >1.64, if so, it is judged as high regulatory risk.

[0131] In step S16, it is determined to be a high regulatory risk, and a corresponding high regulatory risk settlement list is output.

[0132] It should be noted that after outputting the corresponding regulatory high-risk settlement list, you can enter the manual appeal and review process, and take measures such as fund deductions for cases that fail the review.

[0133] In summary, an embodiment of the present invention proposes a method for determining a high-risk medical insurance settlement list under DRG payment, by setting a violation feature library of the medical insurance settlement list, and establishing corresponding violation label sub-libraries according to each type in the violation feature library; putting a number of medical insurance settlement lists uploaded to the medical insurance settlement platform in a preset area and a preset time period into a DRG grouper, and determining the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library; setting a regulatory risk category library, defining violation behaviors for each regulatory risk category in the regulatory risk category library, extracting the corresponding violation label sub-library from the violation label library, and calculating the extracted Cartesian products between the violation label sub-libraries form a regulatory risk rule base, which includes a number of elements that have undergone Cartesian products; calculate the first incidence rate of the regulatory risk rule base in the violation label base of a single settlement list; based on the first incidence rate, calculate the first total incidence rate of the regulatory risk rule base in the violation label base of all settlement lists; according to the four-part method and the total incidence rate, screen the regulatory risk rule base, determine each target element, and organize each target element to form a target regulatory risk rule base; calculate the second incidence rate of the target regulatory risk rule base in the violation label base of a single settlement list; based on the second incidence rate, rate, calculate the second total incidence rate of the target regulatory risk rule base in the violation label base of all settlement lists; calculate the risk weight coefficient of each regulatory risk category library according to the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule base according to the second total incidence rate and the risk weight coefficient; calculate the total amount of violation information of each medical insurance settlement list according to the violation information volume and the second incidence rate, and calculate the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list; calculate the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list according to the total amount of violation information of each medical insurance settlement list and the average amount of violation information of all medical insurance settlement lists; calculate the violation risk coefficient of each medical insurance settlement list according to the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list; determine whether there is a single medical insurance settlement list with a total amount of violation information greater than the average amount of violation information of all medical insurance settlement lists; if so, determine whether the corresponding medical insurance settlement list violation risk coefficient is greater than the threshold; if so, determine it as a high regulatory risk, and output the corresponding high regulatory risk settlement list, which effectively solves the problem of time-consuming and labor-intensive manual judgment of violations in medical insurance settlement.

[0134] Embodiment 2

[0135] Embodiment 2 of the present invention provides a system 200 for determining a high-risk medical insurance settlement list under DRG payment. The system 200 for determining a high-risk medical insurance settlement list under DRG payment includes:

[0136] Setting module 201, used to set the violation feature library of the medical insurance settlement list, wherein the violation feature library includes MDC type, current hospitalization treatment method type, comparison type with the last treatment method, CC type, total hospitalization cost type, special disease single negotiation type, interval type with the last hospitalization, profit type and examination and testing proportion type;

[0137] Establishing module 202, used for establishing each violation label sub-library corresponding to each type in the violation feature library;

[0138] The illegal label library determination module 203 is used to put a number of medical insurance settlement lists uploaded to the medical insurance settlement platform in a preset region and a preset time period into a DRG grouper, and determine the illegal label library of each medical insurance settlement list, wherein the illegal label library is a collection of each illegal label sub-library;

[0139] The first calculation module 204 is used to set up a regulatory risk category library, define violations for each regulatory risk category in the regulatory risk category library, extract corresponding violation label sub-libraries from the violation label library, and calculate the Cartesian product between the extracted violation label sub-libraries to form a regulatory risk rule library, wherein the regulatory risk rule library includes a number of elements that have undergone Cartesian products;

[0140] A second calculation module 205 is used to calculate a first occurrence rate of the regulatory risk rule base in the violation tag base of a single settlement list;

[0141] A third calculation module 206 is used to calculate a first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate;

[0142] The screening module 207 is used to screen the regulatory risk rule base according to the four-part method and the total incidence rate, determine each target element, and organize each target element to form a target regulatory risk rule base;

[0143] A fourth calculation module 208, for calculating a second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list;

[0144] A fifth calculation module 209, configured to calculate a second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists according to the second occurrence rate;

[0145] The sixth calculation module 210 is used to calculate the risk weight coefficient of each regulatory risk category library according to the second total incidence rate, and the calculation formula is:

[0146] C i =∑ i＝1 p it ;

[0147] Among them, C i It is expressed as the risk weight coefficient of the ith regulatory risk category library, p it It is expressed as the second total incidence rate, and according to the second total incidence rate and the risk weight coefficient, the violation information volume of each target regulatory risk rule base is calculated, and the calculation formula is:

[0148] K it =C i ×(-log2p it );

[0149] Among them, K it The amount of violation information represented as the target regulatory risk rule base;

[0150] The seventh calculation module 211 is used to calculate the total amount of violation information of each medical insurance settlement list according to the violation information amount and the second incidence rate, and the calculation formula is:

[0151] R n =∑ n＝1 (K it ×p nit );

[0152] Among them, p nit Expressed as the second incidence rate, R n It is expressed as the total amount of medical insurance settlement list violation information, and according to the total amount of each medical insurance settlement list violation information, the average amount of all medical insurance settlement list violation information is calculated. The calculation formula is:

[0153]

[0154] in, It is represented by the average amount of violation information in all medical insurance settlement lists, and N is represented by the total number of medical insurance settlement lists;

[0155] The eighth calculation module 212 is used to calculate the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list according to the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists. Specifically, the calculation formula is:

[0156]

[0157] Among them, σ represents the standard deviation of the amount of illegal information in all medical insurance settlement lists;

[0158]

[0159] Among them, σ n It is expressed as the standard deviation of the amount of illegal information in the nth medical insurance settlement list;

[0160] The ninth calculation module 213 is used to calculate the violation risk coefficient of each medical insurance settlement list according to the standard deviation of the violation information volume of all medical insurance settlement lists and the standard deviation of the violation information volume of each medical insurance settlement list. The calculation formula is:

[0161] K n =σ n / σ;

[0162] Among them, K n It is expressed as the risk coefficient of violation of the nth medical insurance settlement list;

[0163] The first judgment module 214 is used to judge whether there is a single medical insurance settlement list with a total amount of illegal information greater than the average amount of illegal information in all medical insurance settlement lists;

[0164] The second judgment module 215 is used to judge whether the corresponding medical insurance settlement list violation risk coefficient is greater than a threshold value when it is judged that the total amount of violation information of a single medical insurance settlement list is greater than the average amount of violation information of all medical insurance settlement lists;

[0165] The output module 216 is used to determine that the corresponding medical insurance settlement list is at high risk of supervision when the risk coefficient of violation of the medical insurance settlement list is greater than a threshold value, and output the corresponding high-risk supervision settlement list.

[0166] Embodiment 3

[0167] Embodiment 3 of the present invention proposes an electronic device, comprising a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor, wherein when the processor 10 executes the computer program 30, the method for determining a high-risk medical insurance settlement list under DRG payment as described above is implemented.

[0168] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0169] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 20 may be an internal storage unit of an electronic device in some embodiments, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 may also include both an internal storage unit and an external storage device of the electronic device. The memory 20 may be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is to be output.

[0170] An embodiment of the present invention also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for determining a high-risk medical insurance settlement list under DRG payment as described above is implemented.

[0171] Those skilled in the art will appreciate that the logic and / or steps described in other ways herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0172] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0173] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0174] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0175] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for determining a high-risk medical insurance settlement list under DRG payment, characterized in that: The method comprises: Set up a violation feature library for the medical insurance settlement list, where the violation feature library includes MDC type, type of treatment method for this hospitalization, type of comparison with the last treatment method, CC type, type of total hospitalization cost, type of special disease single negotiation, type of interval with the last hospitalization, profit type, and type of proportion of inspection and testing; According to each type in the violation feature library, corresponding violation label sub-libraries are established; Put several medical insurance settlement lists uploaded to the medical insurance settlement platform in preset regions and preset time periods into the DRG grouper, and calculate them using the calculation methods defined for each type in the violation feature library to determine the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library; A regulatory risk category library is set up, and violations are defined for each regulatory risk category in the regulatory risk category library, and corresponding violation label sub-libraries are extracted from the violation label library, and the Cartesian product between the extracted violation label sub-libraries is calculated to form a regulatory risk rule library, wherein the regulatory risk rule library includes a number of elements that have undergone Cartesian product; Calculate the first occurrence rate of the regulatory risk rule base in the violation tag base of a single settlement list; Calculate the first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate; According to the four-part method and the total incidence rate, the regulatory risk rule base is screened to determine each target element, and each target element is sorted to form a target regulatory risk rule base; Calculate the second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list; According to the second occurrence rate, calculate the second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists; Calculate the risk weight coefficient of each regulatory risk category based on the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule base based on the second total incidence rate and the risk weight coefficient; Calculate the total amount of violation information of each medical insurance settlement list according to the amount of violation information and the second incidence rate, and calculate the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list; According to the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists, calculate the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list; Calculate the risk factor of each medical insurance settlement list violation based on the standard deviation of all medical insurance settlement list violation information and the standard deviation of each medical insurance settlement list violation information; Determine whether there is a single medical insurance settlement list with a total amount of illegal information greater than the average amount of illegal information in all medical insurance settlement lists; If so, determine whether the corresponding medical insurance settlement list violation risk coefficient is greater than the threshold; If so, it is determined to be a high regulatory risk and the corresponding high regulatory risk settlement list is output.

2. The method for determining a high-risk medical insurance settlement list under DRG payment according to claim 1 is characterized in that: In the step of calculating the risk weight coefficient of each regulatory risk category based on the second total incidence rate, the calculation formula is: C i =∑ i=1 p it ; Among them, C i It is expressed as the risk weight coefficient of the ith regulatory risk category library, p it Expressed as the second overall incidence.

3. The method for determining a high-risk medical insurance settlement list under DRG payment according to claim 2 is characterized in that: In the step of calculating the amount of violation information of each target regulatory risk rule base according to the second total incidence rate and the risk weight coefficient, the calculation formula is: K it =C i ×(-log2p it ); Among them, K it The amount of violation information represented as the target regulatory risk rule base.

4. The method for determining a high-risk medical insurance settlement list under DRG payment according to claim 3 is characterized in that: In the step of calculating the total amount of violation information of each medical insurance settlement list according to the violation information amount and the second incidence rate, the calculation formula is: R n =∑ n=1 (K it ×p nit ); Among them, p nit Expressed as the second incidence rate, R n Represents the total amount of violation information in the medical insurance settlement list.

5. The method for determining the high-risk medical insurance settlement list under DRG payment according to claim 4 is characterized in that: In the step of calculating the average amount of illegal information in all medical insurance settlement lists based on the total amount of illegal information in each medical insurance settlement list, the calculation formula is: ； in, It is represented by the average amount of violation information in all medical insurance settlement lists, and N is represented by the total number of medical insurance settlement lists.

6. The method for determining the high-risk medical insurance settlement list under DRG payment according to claim 5 is characterized in that: In the step of calculating the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list based on the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists, the calculation formula for the standard deviation of the amount of illegal information in all medical insurance settlement lists is: ； in, It is expressed as the standard deviation of the amount of information on violations in all medical insurance settlement lists; ； in, It is expressed as the standard deviation of the amount of illegal information in the nth medical insurance settlement list.

7. The method for determining a high-risk medical insurance settlement list under DRG payment according to claim 6 is characterized in that: In the step of calculating the risk coefficient of violation of each medical insurance settlement list based on the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list, the calculation formula is: ； Among them, K n It is expressed as the risk coefficient of violation of the nth medical insurance settlement list.

8. A system for determining high-risk medical insurance settlement lists under DRG payment, characterized in that: The system comprises: A setting module is used to set a violation feature library of the medical insurance settlement list, wherein the violation feature library includes MDC type, type of this hospitalization treatment method, type of comparison with the last treatment method, CC type, total hospitalization cost type, special disease single negotiation type, interval type with the last hospitalization, profit type, and inspection and test proportion type; An establishment module, used for establishing each violation label sub-library corresponding to each type in the violation feature library; The violation label library determination module is used to put a number of medical insurance settlement lists uploaded to the medical insurance settlement platform in a preset region and a preset time period into the DRG grouper, and calculate through the calculation method defined for each type in the violation feature library to determine the violation label library of each medical insurance settlement list, wherein the violation label library is a collection of each violation label sub-library; The first calculation module is used to set up a regulatory risk category library, define violations for each regulatory risk category in the regulatory risk category library, extract corresponding violation label sub-libraries from the violation label library, and calculate the Cartesian product between the extracted violation label sub-libraries to form a regulatory risk rule library, wherein the regulatory risk rule library includes a number of elements that have undergone Cartesian products; A second calculation module is used to calculate a first occurrence rate of the regulatory risk rule base in the violation tag base of a single settlement list; A third calculation module is used to calculate a first total occurrence rate of the regulatory risk rule base in the violation tag base of all settlement lists according to the first occurrence rate; The screening module is used to screen the regulatory risk rule base according to the four-part method and the total incidence rate, determine each target element, and organize each target element to form a target regulatory risk rule base; A fourth calculation module, used to calculate a second occurrence rate of the target regulatory risk rule base in the violation tag base of a single settlement list; A fifth calculation module, configured to calculate a second total occurrence rate of the target regulatory risk rule base in the violation tag base of all settlement lists according to the second occurrence rate; a sixth calculation module, configured to calculate the risk weight coefficient of each regulatory risk category library according to the second total incidence rate, and calculate the violation information volume of each target regulatory risk rule library according to the second total incidence rate and the risk weight coefficient; a seventh calculation module, configured to calculate the total amount of violation information of each medical insurance settlement list according to the amount of violation information and the second incidence rate, and calculate the average amount of violation information of all medical insurance settlement lists according to the total amount of violation information of each medical insurance settlement list; An eighth calculation module, for calculating the standard deviation of the amount of illegal information in all medical insurance settlement lists and the standard deviation of the amount of illegal information in each medical insurance settlement list according to the total amount of illegal information in each medical insurance settlement list and the average amount of illegal information in all medical insurance settlement lists; A ninth calculation module, for calculating the risk coefficient of violation of each medical insurance settlement list according to the standard deviation of the amount of violation information of all medical insurance settlement lists and the standard deviation of the amount of violation information of each medical insurance settlement list; The first judgment module is used to judge whether the total amount of illegal information in a single medical insurance settlement list is greater than the average amount of illegal information in all medical insurance settlement lists; The second judgment module is used to judge whether the corresponding medical insurance settlement list violation risk coefficient is greater than a threshold value when it is judged that the total amount of violation information in a single medical insurance settlement list is greater than the average amount of violation information in all medical insurance settlement lists; The output module is used to determine that when the risk coefficient of violation of the corresponding medical insurance settlement list is greater than a threshold, it is considered as a high regulatory risk and output the corresponding high-risk regulatory settlement list.

9. A computer-readable storage medium, characterized in that: include: The readable storage medium stores one or more programs, which, when executed by the processor, implement the method for determining a high-risk medical insurance settlement list under DRG payment as described in any one of claims 1-7.

10. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the method for determining a high-risk medical insurance settlement list under DRG payment as described in any one of claims 1-7.

Images