Big data-based DRG / DIP dissimilatory illegal behavior supervision method

Abstract

The invention relates to the technical field of medical violation supervision, and particularly discloses a DRG / DIP dissimilatory violation behavior supervision method based on big data, and the method comprises the steps: S1, firstly, forming a local rule base in combination with a payment mode type DRG / DIP actually implemented by a project site, confirming rule base logic and a framework, and carrying out the verification of the rule base logic and framework; a rule base logic and a framework are established through two payment modes according to disease diagnosis related groups and disease category scores, and then the connotation of a medical insurance settlement list filled and reported by a medical institution is supervised, so that the charging details of a patient during the period of seeing a doctor are obtained; then, by analyzing and comparing the charging data of the patient in the doctor seeing period with preset charging data in a local rule base, judgment can be carried out according to whether the charging of the patient in the doctor seeing period is abnormal or not, and whether a medical institution has an illegal behavior of abnormal charging or not is further judged; therefore, illegal behaviors of the medical institution in charging can be supervised.

Description

Technical Field

[0001] The present invention relates to the technical field of medical violation supervision, and in particular to a DRG / DIP alienation violation supervision method based on big data. Background Art

[0002] Alienated and illegal behaviors of medical institutions refer to the behaviors of medical institutions that violate relevant laws, regulations, rules and medical ethics in the course of operation in order to obtain improper benefits or damage the rights and interests of patients. Therefore, in order to ensure the fairness and credibility of the medical industry, it is very necessary to strengthen the supervision of alienated and illegal behaviors of medical institutions.

[0003] DRG Diagnosis Related Group is a medical insurance payment method that divides patients into similar case groups based on their condition, treatment method, disease course and other factors to determine the average cost of each group of cases and pay the hospital based on this cost level. DIP payment by disease type score is an objective classification of medical record data based on the common characteristics of disease diagnosis and treatment methods, objectively reflecting the severity of the disease, the complexity of treatment, the level of resource consumption and clinical behavior norms, and formulating corresponding payment standards according to different diseases. The traditional method of regulating alienated violations is to combine the DRG / DIP payment method, establish a strict data control mechanism, a daily management assessment mechanism, a supervision and inspection mechanism, improve the level of intelligent supervision, and strengthen the internal management of medical institutions to achieve the supervision of alienated violations.

[0004] However, due to the obvious logical differences between payment by DRG / DIP and traditional payment by project, the violations of medical institutions under the new model will change significantly due to insufficient supervision in existing technologies. There are inevitable loopholes in medical charges and alienated charging behaviors. Therefore, the reliability of supervision on alienated violations of medical charges is poor, resulting in medical institutions violating regulations in their charging behaviors and being unable to be effectively supervised. Summary of the invention

[0005] The purpose of the present invention is to provide a DRG / DIP alienation violation supervision method based on big data to solve the following technical problems:

[0006] How to supervise medical institutions’ violations in charging practices.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A DRG / DIP alienation violation supervision method based on big data, the method comprising:

[0009] S1: First, based on the payment method type DRG / DIP actually implemented in the project area, confirm the logic and framework of the rule base to form a local rule base;

[0010] S2: Monitor the contents of the medical insurance settlement list filled in by medical institutions, and verify the authenticity and accuracy of the reported medical information by combining the DRG / DIP grouping results with the fee details;

[0011] S3: By combining the confirmed and verified patient medical information and the patient's charge data during the medical treatment, and analyzing it with the preset charge data in the local rule base, the illegal behavior can be supervised;

[0012] S4: Correct the medical insurance settlement list data based on the illegal data confirmed by the medical institution and calculate the correct amount of medical insurance funds to be allocated;

[0013] Through the above technical scheme, this embodiment provides a method for supervising DRG / DIP alienated violations based on big data. First, combined with the payment method type DRG / DIP actually implemented in the project site, the rule base logic and framework are confirmed to form a local rule base, where DRG and DIP are two payment methods based on disease diagnosis-related grouping and disease type score. Then, the content of the medical insurance settlement list filled in by the medical institution is supervised, and the authenticity and accuracy of the reported medical information are verified in combination with the DRG / DIP grouping results and the charging details. Then, the confirmed verified reported patient medical information and the charging data during the patient's medical treatment can be combined and analyzed with the preset charging data in the local rule base to achieve supervision of violations, and correct the medical insurance settlement list data based on the illegal data confirmed by the medical institution, and calculate the correct amount of medical insurance funds to be allocated.

[0014] Furthermore, the process of analyzing the violation in S3 includes:

[0015] S31: Calculate the patient's medical status qualification index during the medical treatment period by combining the confirmed verified and reported patient medical information;

[0016] S32: By comparing the patient's diagnosis and treatment status qualification index during the medical treatment period with the preset diagnosis and treatment status qualification index, and judging whether the diagnosis and treatment operation of the medical institution during the patient's medical treatment period is in violation of regulations according to the comparison result, if yes, correct the medical insurance settlement list data according to the violation data, otherwise, proceed to step S33;

[0017] S33: Calculate the abnormal coefficient of the patient's charges during the medical treatment period by combining the patient's charge data during the medical treatment period with the charge data of the same disease group in the local rule base and the patient's diagnosis and treatment status qualification index during the medical treatment period;

[0018] S34: By comparing the abnormal charging coefficient of the patient during the medical treatment with the preset abnormal charging coefficient, and judging whether the expenses spent by the patient during the medical treatment are abnormal according to the comparison result, if yes, correct the medical insurance settlement list data according to the illegal data, if no, proceed to step S35;

[0019] S35: By combining the abnormal charging coefficients of different patients with the same disease group during their medical treatment, we can further analyze whether there are any charging violations in medical institutions, and use this data to improve the hospital management system.

[0020] Furthermore, the diagnosis and treatment information in S31 includes the number of diagnosis and treatment items, the actual number of consumables, the number of medicines used, and the number of core medicines used during the patient's medical treatment, and the charging data in S33 includes the number of repeated charges, the total amount of charges exceeding the standard, the total amount of charges exceeding the limit, and the actual number of diagnosis and treatment.

[0021] Furthermore, the process of calculating the patient's treatment status qualification index during medical treatment in S31 includes:

[0022] By formula Calculate the treatment status qualification index of the i-th patient during the medical treatment period ;

[0023] Where i is any patient in the same disease group, a is any day during the patient's medical treatment, and b is the total number of days during the patient's medical treatment. is the amount of medicine used by the i-th patient on the a-th day during medical treatment, The preset dosage of the drug. is the amount of core drugs used by the i-th patient on the a-th day during medical treatment, The preset core drug usage amount is and is the first weight coefficient, which is set according to empirical fitting. is the total number of medical treatment items for the i-th patient during his medical treatment, is the number of pre-set diagnosis and treatment items. is the error influence coefficient, which is set according to empirical fitting. is the actual number of consumables during the treatment of the i-th patient, is the preset number of consumables. for The standard value can be selected and set according to the allowable error in the empirical data. To define a function, if , then let , otherwise, let , and is the second weight coefficient, which is set based on empirical fitting.

[0024] Furthermore, the comparison process in S32 includes:

[0025] By calculating the eligibility index of the diagnosis and treatment status of the i-th patient during the medical treatment Compared with the preset diagnosis and treatment status qualification index threshold Make a comparison;

[0026] like , judge that the patient's diagnosis and treatment status during the medical treatment is qualified, and the medical institution's diagnosis and treatment operations are abnormal during the medical treatment, which means that the medical institution has not violated the regulations, and further analyze it in combination with the patient's charging data during the medical treatment;

[0027] like , it is judged that the patient’s diagnosis and treatment status during the medical treatment is unqualified, and there are abnormalities in the diagnosis and treatment operations of the medical institution during the medical treatment, which means that the medical institution has violated the regulations, and a warning is issued.

[0028] Furthermore, the process of calculating the abnormal coefficient of charges for the patient during medical treatment in S33 includes:

[0029] By formula Calculate the abnormal coefficient of charges for the i-th patient during medical treatment ;

[0030] in, is the number of repeated charges for the i-th patient on the a-th day during medical treatment, The amount of repeated charges on day a during the medical treatment period. for The standard value of is the total amount of excess charges for the i-th patient during medical treatment, is the preset total amount of excess charges. is the total amount of excess charges for the i-th patient during the medical treatment period, is the preset total amount of over-limit charges, is the total refund amount for the i-th patient, is the correction coefficient, set according to empirical fitting, is the actual number of consultations and treatments for patient i during the medical treatment period, The preset number of diagnosis and treatment.

[0031] Furthermore, the comparison process in S34 includes:

[0032] By calculating the abnormal coefficient of the charge of the i-th patient during the medical treatment Threshold value of abnormal coefficient of charges Make a comparison;

[0033] like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is high, which means that the patient's expenses during the medical treatment are abnormal, which means that the medical institution has violated the regulations in charging fees;

[0034] like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is low, which means that there is no abnormality in the expenses spent by the patient during the medical treatment, which means that there is no violation of the fee collection by the medical institution.

[0035] Furthermore, the analysis process in S35 includes:

[0036] By formula Calculate the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group ;

[0037] Among them, n is the total number of patients in the same disease group, is the number of days of treatment for the i-th patient, is the proportionality coefficient, which is set according to empirical fitting. For all The average value of For all The maximum value in For all The minimum value in ;

[0038] By dividing the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group The preset coefficient of dispersion threshold Make a comparison;

[0039] like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is large, that is, the medical expenses of different patients vary greatly and fluctuate greatly, which means that there are some abnormal values ​​or special circumstances, indicating that the medical institutions have abnormal and illegal behaviors;

[0040] like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is small, and the medical expenses of most patients are concentrated near the average value with small fluctuations, indicating that the homogeneity of medical expense data is high, indicating that there is no abnormal violation of regulations in medical institutions.

[0041] Beneficial effects of the present invention:

[0042] (1) The present invention establishes the logic and framework of the rule base by two payment methods: grouping by disease diagnosis and paying by disease type score. Then, the content of the medical insurance settlement list filled in by the medical institution is supervised to obtain the detailed charges of the patient during the medical treatment. Then, by analyzing and comparing the charge data of the patient during the medical treatment with the preset charge data in the local rule base, it is possible to judge whether there are any abnormal charges according to the patient's expenses during the medical treatment, and further judge whether the medical institution has any illegal behavior of charging abnormally, thereby realizing the supervision of the medical institution's illegal behavior in charging.

[0043] (2) The present invention analyzes the patient's diagnosis and treatment status during the medical treatment period by combining the patient's diagnosis and treatment information, and can preliminarily determine whether the medical institution's diagnosis and treatment operations during the patient's medical treatment period are in violation of regulations. Then, by combining the charging data of the same disease group in the local rule library and the patient's actual charging data during the medical treatment period, it is determined whether there are any abnormalities in the expenses spent by the patient during the medical treatment period. By conducting an overall analysis based on the charging situation of multiple patients in the same disease group, it is possible to further analyze whether the medical institution has any charging violations, thereby achieving supervision of the alienated violations of medical institution diagnosis and treatment charges.

[0044] (3) The present invention calculates the treatment status qualification index of the i-th patient during the medical treatment period. Compared with the preset diagnosis and treatment status qualification index threshold By comparing, we can determine whether the patient's diagnosis and treatment status during the medical treatment is qualified, thereby reflecting whether the medical institution has multiple or abusive use of drugs. Based on this data information, we can further determine whether there are any abnormalities in the medical institution's diagnosis and treatment operations during the medical treatment, thereby making a preliminary judgment on whether the medical institution has any violations, so as to achieve supervision of alienated violations.

[0045] (4) The present invention calculates the abnormal charge coefficient of the i-th patient during the medical treatment period. Threshold value of abnormal coefficient of charges By comparing, through this comparison method, it is possible to judge the abnormal degree of charges for the ith patient during the medical treatment, and further analyze whether there are any abnormalities in the expenses spent by the patient during the medical treatment based on the judgment results. By combining the patient's medical charges and medical status data, the accuracy of the analysis and judgment results can be improved, so as to accurately judge whether the medical institution has violated the regulations on fee collection, and then realize the supervision of the medical institution's violations in charging behavior.

[0046] (5) The present invention calculates the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group by The preset coefficient of dispersion threshold A comparison is made to judge the volatility of the abnormal charging coefficients of all patients in the same disease group. The volatility reflects the difference in charges between different patients. If the volatility of the abnormal charging coefficients of all patients in the same disease group increases, it means that the medical expenses of different patients vary greatly and the fluctuation is large, which means that there are certain abnormal values ​​or special circumstances, indicating that the medical institution has abnormal and illegal behavior, thereby further improving the accuracy of judging whether the medical institution has violated the regulations in its charging behavior, thereby improving the accuracy of supervision of illegal behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] Figure 1 It is a flow chart of a method for supervising DRG / DIP alienation violations based on big data in the present invention;

[0049] Figure 2 It is a flow chart of the process of analyzing illegal behaviors in the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 As shown, in one embodiment, the present application provides a DRG / DIP alienation violation supervision method based on big data, the method comprising:

[0052] S1: First, based on the payment method type DRG / DIP actually implemented in the project area, confirm the logic and framework of the rule base to form a local rule base;

[0053] S2: Monitor the contents of the medical insurance settlement list filled in by medical institutions, and verify the authenticity and accuracy of the reported medical information by combining the DRG / DIP grouping results with the fee details;

[0054] S3: By combining the confirmed and verified patient medical information and the patient's charge data during the medical treatment, and analyzing it with the preset charge data in the local rule base, the illegal behavior can be supervised;

[0055] S4: Correct the medical insurance settlement list data based on the illegal data confirmed by the medical institution and calculate the correct amount of medical insurance funds to be allocated;

[0056] Through such a setting, this embodiment first establishes the rule base logic and framework through two payment methods: grouping by disease diagnosis-related groups and paying by disease type scores. Then, the content of the medical insurance settlement list filled out by the medical institution is supervised to obtain the patient's charge details during the medical treatment. Then, by analyzing and comparing the patient's charge data during the medical treatment with the preset charge data in the local rule base, it is possible to judge whether there are any abnormal charges based on the patient's expenses during the medical treatment, and further judge whether the medical institution has any violations of abnormal charges, thereby realizing the supervision of medical institutions' violations in charging.

[0057] See also Figure 2 As shown, the process of analyzing the violation in S3 includes:

[0058] S31: Calculate the patient's medical status qualification index during the medical treatment period by combining the confirmed verified and reported patient medical information;

[0059] S32: By comparing the patient's diagnosis and treatment status qualification index during the medical treatment period with the preset diagnosis and treatment status qualification index, and judging whether the diagnosis and treatment operation of the medical institution during the patient's medical treatment period is in violation of regulations according to the comparison result, if yes, correct the medical insurance settlement list data according to the violation data, otherwise, proceed to step S33;

[0060] S33: Calculate the abnormal coefficient of the patient's charges during the medical treatment period by combining the patient's charge data during the medical treatment period with the charge data of the same disease group in the local rule base and the patient's diagnosis and treatment status qualification index during the medical treatment period;

[0061] S34: By comparing the abnormal charging coefficient of the patient during the medical treatment with the preset abnormal charging coefficient, and judging whether the expenses spent by the patient during the medical treatment are abnormal according to the comparison result, if yes, correct the medical insurance settlement list data according to the illegal data, if no, proceed to step S35;

[0062] S35: By combining the abnormal charging coefficients of different patients with the same disease group during medical treatment, further analyze whether there are any irregularities in charging in medical institutions, and use this data to improve the hospital management system;

[0063] Through the above technical scheme, this embodiment provides a process for analyzing illegal behaviors. First, by combining the confirmed and verified patient medical information, the patient's medical status qualification index during the medical treatment period is calculated, and then the patient's medical status qualification index during the medical treatment period is compared with the preset medical status qualification index, and whether the medical institution's medical treatment operation of the patient during the medical treatment period is judged according to the comparison result. The patient's charging data during the medical treatment period is combined with the charging data of the same disease group in the local rule library, and the patient's medical status qualification index during the medical treatment period. The abnormal charging coefficient of the patient during the medical treatment period is calculated, and then the abnormal charging coefficient of the patient during the medical treatment period is compared with the preset abnormal charging coefficient, and whether the patient's expenses during the medical treatment period are abnormal according to the comparison result. Finally, by combining the abnormal charging coefficients of the same disease group but different patients during the medical treatment period, it is further analyzed whether the medical institution has charging violations, and the hospital management system is improved in combination with the data;

[0064] Through such a setting, by combining the patient's diagnosis and treatment information and analyzing the patient's diagnosis and treatment status during the medical treatment, it is possible to preliminarily determine whether the medical institution's diagnosis and treatment operations during the patient's medical treatment are in violation of regulations. Afterwards, by combining the charging data of the same disease group in the local rule library and the patient's actual charging data during the medical treatment, it is possible to determine whether there are abnormalities in the expenses spent by the patient during the medical treatment. By conducting a comprehensive analysis based on the charging situation of multiple patients in the same disease group, it is possible to further analyze whether the medical institution has any charging violations, thereby achieving supervision of the alienated violations of medical institutions' diagnosis and treatment charges.

[0065] The diagnosis and treatment information in S31 includes the number of diagnosis and treatment items, the actual number of consumables, the number of drugs used, and the number of core drugs used during the patient's medical treatment. The charging data in S33 includes the number of repeated charges, the total amount of over-standard charges, the total amount of over-limit charges, and the actual number of diagnosis and treatment;

[0066] Through the above technical scheme, this embodiment provides diagnosis and treatment information including the number of diagnosis and treatment items, the actual number of consumables, the number of medicines used and the number of core medicines used during the patient's medical treatment. This data is the common characteristics of disease diagnosis and treatment methods, which can objectively reflect the severity of the disease, the complexity of treatment, the level of resource consumption and clinical behavior norms. In fact, it is a data reference for DIP payment by disease score. The charging data includes the number of repeated charges, the total amount of charges exceeding the standard, the total amount of charges exceeding the limit and the actual number of diagnosis and treatment. It is obtained according to the DRG disease diagnosis-related grouping, and the patients are divided into similar case groups according to the patient's condition, treatment method, course of disease and other factors. The cost of each group of cases is determined. By obtaining this data, accurate data can be provided for subsequent judgments on whether the medical institution has violated the regulations to ensure the accuracy and reliability of the judgment results.

[0067] The process of calculating the patient's treatment status qualification index during the medical treatment period in S31 includes:

[0068] By formula Calculate the treatment status qualification index of the i-th patient during the medical treatment period ;

[0069] Where i is any patient in the same disease group, a is any day during the patient's medical treatment, and b is the total number of days during the patient's medical treatment. is the amount of medicine used by the i-th patient on the a-th day during medical treatment, The preset dosage of the drug. is the amount of core drugs used by the i-th patient on the a-th day during medical treatment, The preset core drug usage amount is and is the first weight coefficient, which is set according to empirical fitting. is the total number of medical treatment items for the i-th patient during his medical treatment, is the number of pre-set diagnosis and treatment items. is the error influence coefficient, which is set according to empirical fitting. is the actual number of consumables during the treatment of the i-th patient, is the preset number of consumables. for The standard value of To define a function, if , then let , otherwise, let , and is the second weight coefficient, which is set according to empirical fitting;

[0070] Through the above technical solution, this embodiment provides the diagnosis and treatment status qualification index of the i-th patient during the medical treatment period. , can be obtained by formula It is obvious that when the i-th patient's drug usage and core drug usage on the a-th day during medical treatment are less, and the total number of medical treatment items and the actual number of consumables are less, then the i-th patient's medical treatment status qualification index during medical treatment is The higher the index, the higher the patient's qualified index is. The higher the index, the higher the qualified index of the patient's qualified index is. The lower the cost, the more likely it is that the patient has recovered after using more drugs and treatment methods. In this case, the medical institution may use more drugs or abuse drugs to make more profits.

[0071] Through this calculation method, the treatment status qualification index of the i-th patient during the medical treatment can be obtained The data can reflect the number of drugs and treatment methods used by patients during medical treatment, and further reflect whether the medical institution has multiple drug use or abuse of drugs, thereby providing reliable data support for subsequent analysis of whether the medical institution has any violations, and ensuring the accuracy and reliability of the analysis results.

[0072] The comparison process in S32 includes:

[0073] By calculating the eligibility index of the diagnosis and treatment status of the i-th patient during the medical treatment Compared with the preset diagnosis and treatment status qualification index threshold Make a comparison;

[0074] like , judge that the patient's diagnosis and treatment status during the medical treatment is qualified, and the medical institution's diagnosis and treatment operations are abnormal during the medical treatment, which means that the medical institution has not violated the regulations, and further analyze it in combination with the patient's charging data during the medical treatment;

[0075] like , judge that the patient's diagnosis and treatment status during the medical treatment is unqualified, and the medical institution's diagnosis and treatment operations during the medical treatment are abnormal, which means that the medical institution has violated regulations, and issue a warning;

[0076] Through the above technical solution, this embodiment calculates the qualified index of the diagnosis and treatment status of the i-th patient during the medical treatment period. Compared with the preset diagnosis and treatment status qualification index threshold By comparing, we can determine whether the patient's diagnosis and treatment status during the medical treatment is qualified, thereby reflecting whether the medical institution has multiple or abusive use of drugs. Based on this data information, we can further determine whether there are any abnormalities in the medical institution's diagnosis and treatment operations during the medical treatment, thereby making a preliminary judgment on whether the medical institution has any violations, so as to achieve supervision of alienated violations.

[0077] The process of calculating the abnormal coefficient of charges for the patient during medical treatment in S33 includes:

[0078] By formula Calculate the abnormal coefficient of charges for the i-th patient during medical treatment ;

[0079] in, is the number of repeated charges for the i-th patient on the a-th day during medical treatment, The amount of repeated charges on day a during the medical treatment period. for The standard value of is the total amount of excess charges for the i-th patient during medical treatment, is the preset total amount of excess charges. is the total amount of excess charges for the i-th patient during the medical treatment period, is the preset total amount of over-limit charges, is the total refund amount for the i-th patient, is the correction coefficient, set according to empirical fitting, is the actual number of consultations and treatments for patient i during the medical treatment period, The number of consultations and treatments is preset;

[0080] Through the above technical solution, this embodiment provides the abnormal coefficient of the charge of the i-th patient during the medical treatment period: , can be obtained by formula Obviously, when the total number of charges, repeated charges, and total amount of over-standard charges and over-limit charges of the i-th patient during the medical treatment are higher, and the actual number of diagnosis and treatment is less, then the abnormal charge coefficient of the i-th patient during the medical treatment is The higher the coefficient, the greater the difference between the charges and actual charges of the i-th patient during the medical treatment, and the medical institution may have charged randomly. On the contrary, when the total number of repeated charges and the amount of repeated charges of the i-th patient during the medical treatment are higher, the total amount of over-standard charges and the total amount of over-limit charges are lower, and the actual number of diagnosis and treatment is more, then the abnormal charge coefficient of the i-th patient during the medical treatment is higher. The lower the value, the more it indicates that the charges for the i-th patient during the medical treatment are similar to the actual costs, and the medical institution may not charge randomly. This data reflects the amount of medicine used and the number of medical treatments performed by the patient during the medical treatment. By correcting the total amount of over-standard charges and over-limit charges based on this data, the accuracy of the calculation results can be ensured, thereby providing accurate data for subsequent judgment on whether there are any abnormal charges in the medical institution.

[0081] The comparison process in S34 includes:

[0082] By calculating the abnormal coefficient of the charge of the i-th patient during the medical treatment Threshold value of abnormal coefficient of charges Make a comparison;

[0083] like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is high, which means that the patient's expenses during the medical treatment are abnormal, which means that the medical institution has violated the regulations in charging fees;

[0084] like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is low, which means that there is no abnormality in the expenses spent by the patient during the medical treatment, which means that there is no violation of the fee collection by the medical institution;

[0085] Through the above technical solution, this embodiment calculates the abnormal charge coefficient of the i-th patient during the medical treatment period. Threshold value of abnormal coefficient of charges By comparing, through this comparison method, it is possible to judge the abnormal degree of charges for the ith patient during the medical treatment, and further analyze whether there are any abnormalities in the expenses spent by the patient during the medical treatment based on the judgment results. By combining the patient's medical charges and medical status data, the accuracy of the analysis and judgment results can be improved, so as to accurately judge whether the medical institution has violated the regulations on fee collection, and then realize the supervision of the medical institution's violations in charging behavior.

[0086] The analysis process in S35 includes:

[0087] By formula Calculate the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group ;

[0088] Among them, n is the total number of patients in the same disease group, is the number of days of treatment for the i-th patient, is the proportionality coefficient, which is set according to empirical fitting. For all The average value of For all The maximum value in For all The minimum value in ;

[0089] By dividing the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group The preset coefficient of dispersion threshold Make a comparison;

[0090] like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is large, that is, the medical expenses of different patients vary greatly and fluctuate greatly, which means that there are some abnormal values ​​or special circumstances, indicating that the medical institutions have abnormal and illegal behaviors;

[0091] like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is small, and the medical expenses of most patients are concentrated near the average value with small fluctuations, indicating that the homogeneity of medical expense data is high, indicating that there is no abnormal violation of regulations by medical institutions;

[0092] Through the above technical solution, this implementation provides the discrete coefficient of the abnormal charging coefficient of all patients in the same disease group. , can be obtained through The data can be calculated to reflect the cost difference of the same disease group in the same treatment period. Then, the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group is calculated. The preset coefficient of dispersion threshold A comparison is made to judge the volatility of the abnormal charging coefficients of all patients in the same disease group. The volatility reflects the difference in charges between different patients. If the volatility of the abnormal charging coefficients of all patients in the same disease group increases, it means that the medical expenses of different patients vary greatly and the fluctuation is large, which means that there are certain abnormal values ​​or special circumstances, indicating that the medical institution has abnormal and illegal behavior, thereby further improving the accuracy of judging whether the medical institution has violated the regulations in its charging behavior, thereby improving the accuracy of supervision of illegal behavior.

[0093] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for supervising DRG / DIP alienation violations based on big data, characterized in that: The method comprises: S1: First, based on the payment method type DRG / DIP actually implemented in the project area, confirm the logic and framework of the rule base to form a local rule base; S2: Monitor the contents of the medical insurance settlement list filled in by medical institutions, and verify the authenticity and accuracy of the reported medical information by combining the DRG / DIP grouping results with the fee details; S3: By combining the confirmed and verified patient medical information and the patient's charge data during the medical treatment, and analyzing it with the preset charge data in the local rule base, the illegal behavior can be supervised; S4: Correct the medical insurance settlement list data based on the illegal data confirmed by the medical institution and calculate the correct amount of medical insurance funds to be allocated.

2. According to the big data-based DRG / DIP alienation violation supervision method of claim 1, it is characterized by: The process of analyzing the violation in S3 includes: S31: Calculate the patient's medical status qualification index during the medical treatment period by combining the confirmed verified and reported patient medical information; S32: By comparing the patient's diagnosis and treatment status qualification index during the medical treatment period with the preset diagnosis and treatment status qualification index, and judging whether the diagnosis and treatment operation of the medical institution during the patient's medical treatment period is in violation of regulations according to the comparison result, if yes, correct the medical insurance settlement list data according to the violation data, otherwise, proceed to step S33; S33: Calculate the abnormal coefficient of the patient's charges during the medical treatment period by combining the patient's charge data during the medical treatment period with the charge data of the same disease group in the local rule base and the patient's diagnosis and treatment status qualification index during the medical treatment period; S34: By comparing the abnormal charging coefficient of the patient during the medical treatment with the preset abnormal charging coefficient, and judging whether the expenses spent by the patient during the medical treatment are abnormal according to the comparison result, if yes, correct the medical insurance settlement list data according to the illegal data, if no, proceed to step S35; S35: By combining the abnormal charging coefficients of different patients with the same disease group during their medical treatment, we can further analyze whether there are any charging violations in medical institutions, and use this data to improve the hospital management system.

3. According to the big data-based DRG / DIP alienation violation supervision method of claim 2, it is characterized by: The diagnosis and treatment information in S31 includes the number of diagnosis and treatment items, the actual number of consumables, the number of medicines used and the number of core medicines used during the patient's medical treatment. The charging data in S33 includes the number of repeated charges, the total amount of charges exceeding the standard, the total amount of charges exceeding the limit and the actual number of diagnosis and treatment.

4. According to the big data-based DRG / DIP alienation violation supervision method of claim 3, it is characterized in that: The process of calculating the patient's treatment status qualification index during the medical treatment period in S31 includes: By formula Calculate the treatment status qualification index of the i-th patient during the medical treatment period ; Where i is any patient in the same disease group, a is any day during the patient's medical treatment, and b is the total number of days during the patient's medical treatment. is the amount of medicine used by the i-th patient on the a-th day during medical treatment, The preset dosage of the drug. is the amount of core drugs used by the i-th patient on the a-th day during medical treatment, The preset core drug usage amount is and is the first weight coefficient, which is set according to empirical fitting. is the total number of medical treatment items for the i-th patient during his medical treatment, is the number of pre-set diagnosis and treatment items. is the error influence coefficient, which is set according to empirical fitting. is the actual number of consumables during the treatment of the i-th patient, is the preset consumable quantity, for The standard value of To define a function, if , then let , otherwise, let , and is the second weight coefficient, which is set based on empirical fitting.

5. According to the big data-based DRG / DIP alienation violation supervision method of claim 4, it is characterized in that: The comparison process in S32 includes: By calculating the eligibility index of the diagnosis and treatment status of the i-th patient during the medical treatment Compared with the preset diagnosis and treatment status qualification index threshold Make a comparison; like , judge that the patient's diagnosis and treatment status during the medical treatment is qualified, and the medical institution's diagnosis and treatment operations are abnormal during the medical treatment, which means that the medical institution has not violated the regulations, and further analyze it in combination with the patient's charging data during the medical treatment; like , it is judged that the patient’s diagnosis and treatment status during the medical treatment is unqualified, and there are abnormalities in the diagnosis and treatment operations of the medical institution during the medical treatment, which means that the medical institution has violated the regulations, and a warning is issued.

6. According to the big data-based DRG / DIP alienation violation supervision method of claim 5, it is characterized in that: The process of calculating the abnormal coefficient of charges for the patient during medical treatment in S33 includes: By formula Calculate the abnormal coefficient of charges for the i-th patient during medical treatment ; in, is the number of repeated charges for the i-th patient on the a-th day during medical treatment, The amount of repeated charges on day a during the medical treatment period. for The standard value of is the total amount of excess charges for the i-th patient during medical treatment, is the preset total amount of excess charges. is the total amount of excess charges for the i-th patient during the medical treatment period, is the preset total amount of over-limit charges, is the total refund amount for the i-th patient, is the correction coefficient, set according to empirical fitting, is the actual number of consultations and treatments for patient i during the medical treatment period, The preset number of diagnosis and treatment.

7. According to the big data-based DRG / DIP alienation violation supervision method of claim 6, it is characterized by: The comparison process in S34 includes: By calculating the abnormal coefficient of the charge of the i-th patient during the medical treatment Threshold value of abnormal coefficient of charges Make a comparison; like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is high, which means that the patient's expenses during the medical treatment are abnormal, which means that the medical institution has violated the regulations in charging fees; like , it is judged that the abnormal degree of charges for the i-th patient during the medical treatment is low, which means that there is no abnormality in the expenses spent by the patient during the medical treatment, which means that there is no violation of the fee collection by the medical institution.

8. According to the big data-based DRG / DIP alienation violation supervision method of claim 7, it is characterized by: The analysis process in S35 includes: By formula Calculate the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group ; Among them, n is the total number of patients in the same disease group, is the number of days of treatment for the i-th patient, is the proportionality coefficient, which is set according to empirical fitting. For all The average value of For all The maximum value in For all The minimum value in ; By dividing the dispersion coefficient of the abnormal charge coefficient of all patients in the same disease group The preset coefficient of dispersion threshold Make a comparison; like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is large, that is, the medical expenses of different patients vary greatly and fluctuate greatly, which means that there are some abnormal values ​​or special circumstances, indicating that the medical institutions have abnormal and illegal behaviors; like ,It is judged that the volatility of the abnormal coefficient of charges for all patients in the same disease group is small, and the medical expenses of most patients are concentrated near the average value with small fluctuations, indicating that the homogeneity of medical expense data is high, indicating that there is no abnormal violation of regulations in medical institutions.

Images