A method, device and equipment for reasonable cost control in medical process

Abstract

The embodiment of the present invention discloses a method, device and equipment for reasonable cost control in the medical process, the method comprising: statistics on the use of drugs for various diseases based on big data technology, obtaining the use frequency of various drugs under each disease, adding drugs with a use frequency exceeding the medication frequency threshold to the necessary drug catalog for each disease; predicting the inclusion of drugs according to the diagnosis information and surgical operation information of the current medical record to obtain the predicted disease; obtaining the doctor's medication instructions, judging whether each target drug in the medication instructions is included in the necessary drug catalog corresponding to the predicted disease, if not, obtaining the medication frequency of the target drug to generate the first prompt information. By adopting the method of the present invention, the doctor's medication situation can be restricted to avoid excessive medical treatment of patients and reduce hospital costs.

Description

Technical Field

[0001] The present invention relates to the field of medical data technology, and in particular to a method, device and equipment for reasonably controlling costs during medical treatment. Background Art

[0002] Medical cost control is a long-term policy of the country. At present, the country has fully implemented a multi-faceted and complex medical insurance payment method based on payment by disease type. Charging by disease type means that from the time the patient is admitted to the hospital, he receives standardized diagnosis and treatment according to the disease treatment management process, and is discharged after reaching the clinical efficacy standard. All the costs of diagnosis, treatment, surgery, etc. incurred during the whole process are charged in a one-time package. Before the adoption of package-based charging, the price difference income of drugs and high-quality medical consumables was one of the main sources of income for hospitals. With the comprehensive cancellation of drug markups in recent years, drug sales and medical consumables sales have changed from the original source of income to cost business, but it is still difficult to control the excessive use of drugs in treatment due to the possible interest relationship between doctors and various pharmaceutical companies. Due to the differences in individual characteristics of patients and the manifestations of each disease in individuals, factors such as the severity of the disease, the presence or absence of comorbidities and complications will lead to different treatment methods and means. Therefore, it is impossible to standardize the doctor's examination, treatment and medication. Therefore, it is particularly important for hospitals to provide a reasonable cost control plan in the medical process. Summary of the invention

[0003] The embodiments of the present invention aim to provide a method, device and equipment for reasonable cost control in the medical process, which can restrict doctors' medication, avoid over-medicalization of patients, and reduce hospital costs.

[0004] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0005] According to one aspect of the present invention, a method for reasonably controlling costs during medical treatment is provided, the method comprising:

[0006] Based on big data technology, statistics are collected on the use of drugs for each disease, and the use frequency of various drugs for each disease is obtained. Drugs with a use frequency exceeding the medication frequency threshold are added to the list of essential drugs for each disease.

[0007] According to the diagnosis information and surgical operation information of the current medical records, the predicted disease type is obtained;

[0008] Obtain the doctor's medication order, determine whether each target drug in the medication order is included in the necessary drug catalog corresponding to the predicted disease, and if not, obtain the medication frequency of the target drug to generate the first prompt information.

[0009] Optionally, the method further comprises:

[0010] Based on big data technology, the drug ratio of each disease type is counted to obtain the standard drug ratio of each disease type; determine whether the ratio of the total cost of each target drug in the medication order to the total cost of each medical service item exceeds the standard drug ratio corresponding to the predicted disease type. If so, generate a second prompt information.

[0011] Optionally, the predicted disease types obtained by predicting the group according to the diagnosis information and surgical operation information of the current medical record include:

[0012] The diagnosis information and / or surgical operation information of the current medical record is reviewed, and the diagnosis information and / or surgical operation information are modified according to the review result to perform prediction and grouping to obtain the predicted disease type.

[0013] Optionally, the review of the diagnosis information of the current medical record includes:

[0014] Obtain a medical data set corresponding to the current medical record, obtain a diagnosis matching rule set corresponding to each diagnosis in the diagnosis information based on a pre-established diagnosis matching rule library, match the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis, and obtain a second audit result of whether the diagnosis information is high-level;

[0015] Wherein, the establishment of the diagnosis matching rule base includes:

[0016] Based on big data technology, the keyword combinations associated with the disease names of various diseases are counted respectively; and the keyword matching rules of various diseases are generated according to the keyword combinations;

[0017] Based on big data technology, the basic medical record information, drug information, surgery information, test index information and inspection index information of each disease are analyzed for correlation with each disease; the combination of basic information characteristics, drug characteristics, surgery characteristics, test index characteristics and inspection index characteristics associated with each disease is obtained, and the feature matching rules of each disease are generated according to the combination;

[0018] The keyword matching rules and feature matching rules of each disease are combined to form a diagnosis matching rule set for each disease.

[0019] Optionally, the review of the diagnosis information of the current medical record also includes:

[0020] The inferred diagnosis set corresponding to each surgical operation in the surgical operation information is analyzed according to the disease score library and the surgical operation information; the inferred diagnosis set corresponding to each surgical operation in the surgical operation information is matched with the diagnostic information to obtain a third audit result of whether the diagnostic information is missing.

[0021] Optionally, the review of the surgical operation information of the current medical record includes:

[0022] Obtain the expense details information corresponding to the current medical record, and based on the pre-established mapping relationship between surgical operations and medical service item sets, match each medical service item contained in the expense details information with the surgical operation information to obtain a first audit result of whether the surgical operation information is omitted or under-edited;

[0023] The established mapping relationship between surgical operations and medical service item sets includes:

[0024] Based on big data technology, the correlation between each surgical operation and each medical service item is counted respectively, and each medical service item exceeding the surgical correlation threshold is screened out to form a set of related medical service items for each surgical operation;

[0025] According to the similarity between the names of the medical service items in the associated medical service item sets of the various surgical operations and the names of the surgical operations, the medical service items exceeding the similarity threshold are screened out to form a mapping medical service item set for the various surgical operations;

[0026] Establish a mapping relationship between each surgical operation and each mapped medical service item set.

[0027] Optionally, the method further comprises:

[0028] Based on big data technology, the use of medical consumables for each disease is counted and the reasonable price range of each type of medical consumables for each disease is obtained;

[0029] It is determined whether the cost of each medical consumable in the medication instruction is within the reasonable price range of the medical consumable under the predicted disease type. If not, a third prompt information is generated.

[0030] According to another aspect of the present invention, a device for reasonably controlling costs during medical treatment is provided, the device comprising:

[0031] The drug catalog building module collects statistics on drug usage for each disease based on big data technology, obtains the usage frequency of various drugs for each disease, and adds drugs whose usage frequency exceeds the medication frequency threshold to the essential drug catalog for each disease;

[0032] Disease prediction module, which predicts the disease based on the diagnosis information and surgical operation information of the current medical record;

[0033] The first prompt module obtains the doctor's medication order and determines whether each target drug in the medication order is included in the necessary drug catalog corresponding to the predicted disease. If not, the medication frequency of the target drug is obtained to generate the first prompt information.

[0034] According to another aspect of the present invention, there is provided a computer device, comprising a memory, a processor and a computer program stored and running on the memory, wherein when the processor executes the program, the processor implements any of the above-mentioned method steps for reasonable cost control during the medical process.

[0035] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes any one of the above-mentioned method steps for reasonable cost control during a medical procedure.

[0036] According to another aspect of the present invention, there is provided a computer program, which includes a computer-readable code, and when the computer-readable code is executed on a computing device, causes the computing device to execute any one of the above-mentioned method steps for reasonable cost control during medical treatment.

[0037] The beneficial effects of the embodiments of the present invention are as follows: Different from the prior art, in the embodiments of the present invention, based on big data technology, statistics are collected on the use of drugs for various diseases, the use frequency of various drugs under each disease is obtained, and drugs with a use frequency exceeding the medication frequency threshold are added to the necessary drug catalog for each disease; prediction is performed based on the diagnosis information and surgical operation information of the current medical record to obtain the predicted disease; the doctor's medication instructions are obtained, and it is determined whether each target drug in the medication instructions is included in the necessary drug catalog corresponding to the predicted disease. If not, the medication frequency of the target drug is obtained to generate the first prompt information. Using the method of the present invention, when a doctor prescribes a drug that does not belong to the necessary drug catalog corresponding to the current disease during the medical process, a reminder can be issued to restrict the doctor's medication situation, avoid excessive medical treatment of patients, and reduce hospital costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0039] Figure 1 It is a flow chart of an optional medical record front page review method provided by an embodiment of the present invention;

[0040] FIG. 2( a ) is a schematic diagram of a first page of an optional medical record homepage provided in an embodiment of the present invention;

[0041] FIG2( b ) is a schematic diagram of a second page of an optional medical record homepage provided in an embodiment of the present invention;

[0042] Figure 3 is a flow chart of an optional method for reviewing surgical operation information provided by an embodiment of the present invention;

[0043] Figure 4 This is a flow chart of an optional method for establishing a mapping relationship between surgical operations and medical service item sets provided by an embodiment of the present invention;

[0044] Figure 5 is a flow chart of an optional method for performing high-level review of diagnostic information provided by an embodiment of the present invention;

[0045] Figure 6 is a flow chart of an optional method for establishing keyword matching rules provided by an embodiment of the present invention;

[0046] Figure 7 It is a flow chart of another optional medical record front page review method provided by an embodiment of the present invention;

[0047] Figure 8 It is a flow chart of an optional method for performing omission review on diagnostic information provided by an embodiment of the present invention;

[0048] Fig. 9 It is a structural schematic diagram of an optional reasonable fee control device provided in an embodiment of the present invention;

[0049] Fig.10 This is a flow chart of an optional method for reasonably controlling costs during medical treatment provided by an embodiment of the present invention;

[0050] Fig.11 This is another optional flow chart of a method for reasonably controlling costs during medical treatment provided by an embodiment of the present invention;

[0051] Fig.12 It is a schematic diagram of the structure of an optional electronic device provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0053] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0054] In each embodiment of the present invention, a method for establishing a mapping relationship between surgical operations and medical service items based on big data technology, a method for establishing a diagnosis matching rule base based on big data technology, a method for statistically analyzing the use of drugs for various diseases based on big data technology, and a method for statistically analyzing the use of medical consumables for various diseases based on big data technology are provided. It should be noted that before executing the above method, it also includes: building a data collection platform based on big data technology, collecting basic medical record information, diagnosis information, surgical operation information, cost details, drug information, test index information, inspection index information, discharge summary information, group information, etc. of each patient, and cleaning the above information according to a preset data dictionary to obtain a medical data set of each medical record, storing each medical data set in units of medical records, and constructing a historical medical database.

[0055] like Figure 1 FIG. 1 is a flow chart of an optional method for reviewing a medical record front page provided by an embodiment of the present invention, the method comprising:

[0056] Step S101, obtaining the target medical record homepage to be reviewed, identifying the target medical record homepage, and obtaining the basic medical record information, diagnosis information and surgical operation information of the target medical record homepage.

[0057] As shown in Figure 2(a) and Figure 2(b), the target medical record homepage is a brief medical record file that records basic medical record information, diagnosis information, surgical operation information, and cost information in accordance with preset specifications; the preset specifications are unified data recording formats set by the medical record management department of the state or medical structure. Basic medical record information includes the patient's medical record number, name, gender, age, admission date, admission department, discharge date, discharge department, etc.; diagnosis information includes the main diagnosis and other diagnoses; surgical operation information includes various surgeries and operations performed by the patient during hospitalization.

[0058] Step S102, obtain the cost detail information corresponding to the target medical record homepage, and based on the pre-established mapping relationship between surgical operations and medical service item sets, match each medical service item contained in the cost detail information with the surgical operation information to obtain a first audit result of whether the surgical operation information is omitted or underestimated.

[0059] Due to the high workload, medical workers may omit one or more surgical procedures on the first page of the medical record. The loss caused by omitting a surgical procedure may be huge for the hospital. For example, the total hospitalization cost of a patient is 219,491.64 yuan, the original main diagnosis is 163,900 cerebral infarction, the original surgical procedure is 38,9301 intravenous catheterization, the original included disease type is I: FBS circulatory system disease: non-conservative, and the original disease type score is 938.81 (calculated according to the unit price of 162.38 points, the medical insurance DIP payment is 152,443.97 yuan, and the hospital loses 67,047.67 yuan). After analysis, it was found that the surgical operation was omitted: 99.9201 Traditional Chinese Medicine Acupuncture. After filling in the operation, the new disease type was added: I63.9.99.9201 Cerebral infarction: Traditional Chinese Medicine Acupuncture. The new disease type score: 1429.02 (Medical Insurance DIP payment: 232044.26 yuan, hospital surplus 12552.62 yuan).

[0060] In order to reduce hospital losses, the existing technology mainly uses manual review, but manual review requires not only high professionalism of the reviewer, but also high concentration of attention of the reviewer, which makes the review difficult. The embodiment of the present invention proposes a method to determine whether there are any missing surgical operations in the target medical record homepage through the medical service items in the expense details information to review the surgical operation information. For the specific implementation method, please refer to the following combined Figure 3 Description.

[0061] In actual applications, there may be a situation where the surgical operation information itself is empty, or the surgical operation information is empty due to omission. Optionally, before step S102, it also includes: judging whether the surgical operation information is empty; if not, executing step S102; if so, obtaining the department information corresponding to the target medical record homepage, if the department information is internal medicine, skipping step S102, executing step S103; if the department information is surgery, continuing to execute step S102. This is because there are relatively few cases where internal medicine patients undergo surgical operations. If the surgical operation information is empty, it can be assumed that the surgical operation information itself is empty. Of course, in the case where the surgical operation information is empty, it is also possible to directly execute step S102 without distinguishing between internal medicine and surgery to ensure that no surgical operations are omitted.

[0062] Step S103, obtain the medical data set corresponding to the target medical record homepage, obtain the diagnosis matching rule set corresponding to each diagnosis in the diagnosis information based on the pre-established diagnosis matching rule library, match the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis, and obtain the second audit result of whether the diagnosis information has a high level of content.

[0063] This step can determine whether the diagnosis is high-level by matching the diagnosis information, medical data set and diagnosis matching rule set. For example, if the diagnosis name on the target medical record homepage is "hyperuricemia", and the medical data set of the medical record shows: patient (male), uric acid level is 380μmol / L, then the diagnosis is judged to be high-level. Because according to medical standards, hyperuricemia (HUA) refers to the fasting blood uric acid level of males and females on two different days higher than 420μmol / L under normal purine diet, which is called hyperuricemia.

[0064] In an optional solution, the method of the embodiment of the present invention further includes: integrating and outputting the first audit result and the second audit result.

[0065] In an optional solution, the method of the embodiment of the present invention further includes: performing a first data verification on the basic medical record information on the target medical record homepage, wherein the first data verification is used to determine whether the basic medical record information is filled in in a standardized and complete manner.

[0066] In an optional scheme, the method of an embodiment of the present invention also includes: performing a second data verification on each data information in the target medical record homepage, and the second data verification judges whether the data information is logically consistent based on preset logical judgment rules, such as: whether the age is consistent with the diagnosis, whether the total cost is equal to the cost details, whether the discharge time is greater than the admission time, etc.

[0067] In an optional solution, the method of the embodiment of the present invention further includes: determining whether there are any medical records that have not been submitted based on the admission information and the discharge information, and if so, sending a reminder message to the doctor who has not submitted the medical record.

[0068] For the specific implementation of step S103, please refer to the following combined Figure 5 Description.

[0069] The following is a detailed description of step S102. Figure 3 FIG. 1 is a flowchart of an optional method for reviewing surgical operation information provided by an embodiment of the present invention, the method comprising:

[0070] Step S1021, obtaining the expense details information corresponding to the target medical record homepage.

[0071] As shown in Figure 2(b), the target medical record homepage only records the total cost and various cost information, such as diagnosis fee, treatment fee, drug fee, etc., but does not record the specific cost information of each medical service item. Specifically, the cost details corresponding to the target medical record homepage can be obtained from the HIS (Hospital Information System) system through the medical record number of the target medical record homepage. The cost details include the costs of various medical service items incurred by the patient during hospitalization. The medical service items can be divided into bed fees, diagnosis fees, nursing fees, surgery fees, treatment fees, examination fees, laboratory fees, drug fees (Western medicine fees, Chinese patent medicine fees, Chinese herbal medicine fees), medical consumables fees, etc. according to the cost category.

[0072] Step S1022: based on the pre-established mapping relationship between surgical operations and medical service item sets, the medical service item sets that are not corresponding to the surgical operation information are screened out from the expense details information.

[0073] At present, surgical operations and medical service items belong to different systems and frameworks. In terms of surgical operations, the state has issued the "National Clinical Version 3.0 Surgical Operation Coding (ICD-9-CM3)", which includes more than 13,000 surgical operations. The names, codes, fee categories and charging standards of medical service items are generally formulated by local government departments. For example, Shenzhen has issued the "Basic Medical Service Items and Prices of Shenzhen Non-profit Medical Institutions (2020 Edition)", which includes more than 9,000 medical service items.

[0074] In order to determine whether there are any missing surgical procedures in the target medical record homepage through the medical service items in the expense details information, a mapping relationship between surgical procedures and medical service item sets must be established. For example, a surgical procedure named "laparoscopic appendectomy" can correspond to "laparoscopic addition" + "appendectomy (referring to simple)"; or "laparoscopic addition" + "appendectomy (referring to simple)" + "appendectomy (suppurative addition)"; or "laparoscopic addition" + "appendectomy (referring to simple)" + "appendectomy (gangrenous addition)". Ultimately, we hope to establish a mapping relationship: the surgical operation "laparoscopic appendectomy" corresponds to the medical service item set {"laparoscopic addition", appendectomy (referring to simple), appendectomy (suppurative addition), appendectomy (gangrenous addition)}.

[0075] like Figure 4 The figure shows a flow chart of an optional method for establishing a mapping relationship between surgical operations and medical service item sets provided by an embodiment of the present invention, the method comprising:

[0076] Step S401: Based on big data technology, the correlation between each surgical operation and each medical service item is counted, and each medical service item exceeding the surgical correlation threshold is screened out to form a set of associated medical service items for each surgical operation.

[0077] Specifically, based on big data technology, medical records containing various surgical operations are screened out according to the names of various surgical operations; the cost details corresponding to each medical record are obtained, and the correlation between each medical service item in the cost details and each surgical operation is calculated; the medical service items whose correlation exceeds the surgical correlation threshold are screened out to form a set of associated service items for the surgical operation. For example, one surgical operation is selected from the "National Clinical Version 3.0 Surgical Operation Coding (ICD-9-CM3)", all medical records including the surgical operation are screened out in the historical medical database, the cost details corresponding to each medical record are obtained, and the occurrence rate of each medical service item in the cost details is counted (the occurrence rate is the correlation between the surgical operation and the medical service item). If the occurrence rate of a medical service item exceeds the preset surgical correlation threshold, such as 95%, the medical service item is screened out.

[0078] Medical service items can be divided into bed fees, examination fees, nursing fees, surgery fees, treatment fees, inspection fees, laboratory fees, medicine fees (Western medicine fees, Chinese patent medicine fees, Chinese herbal medicine fees), medical consumables fees, etc. according to the cost category. In an optional solution, the calculation of the correlation between each medical service item and each surgical operation in the cost details information also includes: screening the cost details information of each medical record according to the cost category to find each medical service item belonging to the surgical operation type; calculating the correlation between each medical service item belonging to the surgical operation type in the cost details information and each surgical operation. According to experience, the cost category of the medical service item of the surgical operation type may include treatment fees, surgery fees and inspection fees.

[0079] The inventors of the present application discovered in their research that there is a situation where a surgical operation corresponds to both medical service item A and medical service item B. For example, the surgical operation coded as 16.2100x001 "fundus examination" can correspond to four medical service items in the "Basic Medical Service Items and Prices of Non-profit Medical Institutions in Shenzhen (2020 Edition)": "Fundus examination under slit lamp", "Fundus examination under slit lamp (front mirror)", "Fundus examination under slit lamp (three-sided mirror)", and "Fundus examination under slit lamp (retinal mirror)". In this way, under the same big data, the correlation between the surgical operation and the above four medical service items will be dispersed, and screening according to a unified surgical correlation threshold may result in a situation where no medical service items are screened out. Therefore, multiple surgical correlation thresholds can be preset. When no medical service items are screened out using the first surgical correlation threshold, a second surgical correlation threshold that is lower than the first surgical correlation threshold is selected for re-screening, and so on, until a medical service item is screened out.

[0080] Step S402, based on the similarity between the names of the medical service items in the associated medical service item sets of the various surgical operations and the names of the surgical operations, the medical service items exceeding the similarity threshold are screened out to form a mapping medical service item set for the various surgical operations.

[0081] Specifically, a keyword set for each surgical operation is obtained based on the name of each surgical operation; the name of each medical service item in the associated medical service item set is matched with each keyword in the keyword set to obtain the similarity between the name of each medical service item in the associated medical service item set and the surgical operation name; and the medical service items that exceed the similarity threshold are screened out to form a mapping medical service item set for each surgical operation.

[0082] In an optional solution, multiple similarity thresholds are preset. Assuming that according to the experience of experts, 70% of surgical operations and medical service items have a one-to-one correspondence, and the name similarity can reach 90%, the first similarity threshold is set to 90%, and 20% of surgical operations and medical service items have a one-to-two correspondence, and the name similarity can reach 50%, so the second similarity threshold is set to 50%. Similarly, the third similarity threshold can be set to 30%.

[0083] Taking the surgical operation named "laparoscopic appendectomy" as an example, it is assumed that the selected related medical service items include "laparoscopic addition" and "appendectomy (referring to simple)". First, the keywords of the surgical operation name are extracted as "laparoscopy" + "appendectomy", and "laparoscopic addition" is matched with "laparoscopy" + "appendectomy", and the similarity is 50%; similarly, "appendectomy (referring to simple)" is matched with "laparoscopy" + "appendectomy", and the similarity is also 50%. At this time, these two medical service items can be screened out according to the second similarity threshold to form a mapping medical service item set. Of course, if there is enough data in step S401, the screened related medical service item set may also include "appendectomy (suppurative addition)" and "appendectomy (gangrenous addition)". At this time, the complete mapping medical service item set of the surgical operation can be obtained {"laparoscopic addition", appendectomy (simple), appendectomy (suppurative addition), appendectomy (gangrenous addition)}.

[0084] Step S403: establishing a mapping relationship between each surgical operation and each mapped medical service item set.

[0085] The following is a detailed description based on Figure 4 The mapping relationship between the established surgical operation and the medical service item set is how to filter out the medical service item set that does not correspond to the surgical operation information from the expense details information.

[0086] In some embodiments, the expense details information is first screened by expense category to screen out various medical service items of the surgical operation type. Further, all medical service items corresponding to various surgical operations in the surgical operation information are obtained and recorded as medical service item set A, and each medical service item belonging to the surgical operation type in the expense details information is recorded as medical service item set B. The result of subtracting medical service item set A from medical service item set B is the medical service item set in medical service item set B that does not correspond to the surgical operation information.

[0087] Step S1023, determining whether the set of medical service items not corresponding to the surgical operation information is empty, if so, proceeding to step S1025, if not, proceeding to step S1024.

[0088] Step S1024, based on the pre-established mapping relationship between surgical operations and medical service item sets, reverse matching is performed on the medical service items that do not correspond to the surgical operation information, missing or under-coded surgical operations are identified, and a first audit result is generated based on the missing or under-coded surgical operations.

[0089] Specifically, all unmatched medical service items are first treated as a whole, and reverse matching is performed based on the mapping relationship between surgical operations and medical service item sets. If a surgical operation is matched, the surgical operation is confirmed to be a missing surgical operation. For example, the missing operation: 99.9201 Traditional Chinese Medicine Acupuncture.

[0090] If the match is unsuccessful, the medical service items will be split and reverse matched until the match is successful. When using medical service items for reverse matching, multiple surgical operations may be matched. At this time, it means that the doctor may have underestimated the surgical operation. At this time, it is necessary to combine the various surgical operations included in the target medical record homepage to find similar surgical operations. For example, the unmatched medical service item is "laparoscopic addition". Based on the pre-established mapping relationship, reverse matching is performed. There may be hundreds of surgical operation items that match "laparoscopic addition". If the filled-in surgical operation includes "appendectomy (referring to simple)", then look for surgical operations similar to "appendectomy (referring to simple)" in the matched surgical operation items, and finally obtain the correct surgical operation information of "laparoscopic appendectomy".

[0091] Step S1025, generating a first audit result indicating that there is no omission or under-editing of surgical operation information.

[0092] like Figure 5 FIG. 1 is a flow chart of an optional method for performing high-level review of diagnostic information provided by an embodiment of the present invention, the method comprising:

[0093] Step S1031, obtaining the medical data set corresponding to the target medical record homepage.

[0094] Step S1032: based on a pre-established diagnosis matching rule library, obtain a diagnosis matching rule set corresponding to each diagnosis in the diagnosis information.

[0095] Among them, the diagnosis matching rule library contains a mapping of at least one disease to a diagnosis matching rule set, the disease is a disease in the International Classification of Diseases (such as the "National Clinical Edition 2.0 Disease Diagnosis Code (ICD-10)"), and the diagnosis matching rule set includes keyword matching rules and / or feature matching rules. For example, the diagnosis matching rule set corresponding to "hyperuricemia" is {("sex = male" and "fasting blood uric acid" > 420μmol / L (not twice on the same day)) or ("sex = female" and "fasting blood uric acid" > 360μmol / L (not twice on the same day))}. In an optional scheme, the establishment of the keyword matching rules includes: based on big data technology, respectively counting the keyword combinations associated with the disease name of each disease; generating keyword matching rules for each disease based on the keyword combinations.

[0096] like Figure 6 FIG. 1 is a flow chart of an optional method for establishing keyword matching rules provided by an embodiment of the present invention, wherein the method includes:

[0097] Step S601, obtaining a disease name, and performing word segmentation on the disease name to obtain a keyword set of the disease.

[0098] In some embodiments, segmenting the disease name to obtain a keyword set for the disease further includes: segmenting the disease name, and obtaining a keyword set for the disease based on approximate words of each segmented word.

[0099] Step S602, combining the keywords in the keyword set of the disease according to the segmentation theme to obtain a plurality of keyword combinations.

[0100] Step S603: Based on big data technology, the correlation between the disease and each keyword combination is counted.

[0101] Specifically, the constructed historical medical database is screened according to the disease name, and the medical record hit rate of each keyword combination in the screened historical medical database is counted. The medical record hit rate is the correlation between the disease and each keyword combination.

[0102] Step S604, determining whether the number of keyword combinations whose relevance is greater than the keyword relevance threshold is 0, if so, proceeding to step S608, if not, proceeding to step S605.

[0103] Step S605, determine whether the number of keyword combinations whose relevance is greater than the keyword relevance threshold is greater than 1, if so, proceed to step S606, if not, proceed to step S607.

[0104] Step S606, analyzing each keyword combination whose relevance is greater than the keyword relevance threshold to obtain the most relevant keyword combination, and generating a keyword matching rule for the disease according to the most relevant keyword combination.

[0105] Specifically, the analysis of each keyword combination whose correlation is greater than the keyword correlation threshold includes: screening out the keyword combination containing the most segmented topics, and counting the number of times each keyword combination appears in each medical record in the screened historical medical database according to the medical records, and screening out the keyword combination with the highest average number of appearances.

[0106] Step S607: Generate a keyword matching rule for the disease according to the keyword combination whose relevance is greater than the keyword relevance threshold.

[0107] Step S608, reducing the keyword relevance threshold according to a preset rule, and returning to step S604.

[0108] The following is an example of the keyword matching rule generation process for the disease name "acute tonsillitis". The first step is to perform word segmentation and expansion based on the disease name to generate the keyword set {"tonsil", "inflammation or redness or swelling"}; the second step is to combine according to the word segmentation theme to obtain seven keyword combinations: {"tonsil"}, {"inflammation"}, {"redness"}, {"swelling"}, {"tonsil" and "inflammation"}, {"tonsil" and "redness"}, {"tonsil" and "swelling"}. The third step is to calculate the correlation between the seven keyword combinations and the disease based on big data technology. Assuming that the relevance of {"tonsil"} is 100%, the relevance of {"inflammation"} is 70%, the relevance of {"redness and swelling"} is 80%, the relevance of {"swelling"} is 95%, the relevance of {"tonsil" and "inflammation"} is 70%, the relevance of {"tonsil" and "swelling"} is 95%, the relevance of {"tonsil" and "swelling"} is 80%, and the keyword relevance threshold is 90%, then the two keyword combinations {"tonsil"} and {"tonsil" and "swelling"} are screened out. Finally, according to step S607, the keyword combination containing the most segmentation topics is screened out, and at this time {"tonsil" and "swelling"} is screened out as the most relevant keyword combination.

[0109] In an optional solution, the establishment of the feature matching rules includes: based on big data technology, analyzing the correlation between the basic information of the medical records, drug information, surgery information, test index information and inspection index information of each disease and each disease; obtaining a combination of basic information features, drug features, surgery features, test index features and inspection index features associated with each disease, and generating feature matching rules for each disease based on the combination. The combination includes any combination of "or" and "and" of any multiple features among the basic information features, drug features, surgery features, test index features and inspection index features.

[0110] Specifically, in the first step, based on big data technology, the correlation between the basic medical record information, drug information, surgical information, test index information and inspection index information of each disease and each disease is calculated respectively, and the first feature correlation threshold is used for screening to obtain the basic information characteristics, drug characteristics, surgical characteristics, test index characteristics and inspection index characteristics associated with each disease; in the second step, the above five characteristics are combined according to the preset rules, the correlation between each combined feature and each disease is calculated, and the second feature correlation threshold is used for screening to obtain the most relevant combination, and the feature matching rules for each disease are generated according to the combination. The preset rules include giving priority to combining features with a high correlation with the disease, giving priority to combining complementary features, etc.

[0111] By adopting the above method, the mapping relationship between each disease and the keyword matching rules and the feature matching rules can be established. Further, the keyword matching rules and feature matching rules of each disease are merged to form a diagnosis matching rule set for each disease, thereby establishing a diagnosis matching rule library for each disease. Specifically, the diagnosis matching rule set is: {keyword matching rules, feature matching rules}. It should be noted that the keyword association threshold in step S608 has a lower limit value. When the keyword association threshold value is reduced to the lower limit value, if no associated keyword combination is screened out, the process ends. That is, the keyword matching feature of the disease is empty. Similarly, when establishing the feature matching rules of the disease, there may be a situation where no matching feature combination appears, resulting in the feature matching rules of the disease being empty. Therefore, the diagnosis matching rule set corresponding to each disease may be any one of {keyword matching rules}, {feature matching rules}, {keyword matching rules, feature matching rules}.

[0112] Step S1033, matching the disease name of each diagnosis with the keywords in the corresponding diagnosis matching rule set to obtain a first matching result, and matching the medical data set with the feature matching rules in the diagnosis matching rule library corresponding to each diagnosis to obtain a second matching result.

[0113] Step S1034: if both the first matching result and the second matching result are successfully matched, proceed to step S1036; otherwise, proceed to step S1035.

[0114] Take "hyperuricemia" as an example for further explanation. Assuming that the diagnosis in the target medical record information is "hyperuricemia", the feature matching rule corresponding to "hyperuricemia" is ("gender = male" and "fasting blood uric acid" > 420μmol / L (not twice on the same day)) or ("gender = female" and "fasting blood uric acid" > 360μmol / L (not twice on the same day)). In the medical data set corresponding to the homepage of the target medical record, the index values ​​of gender information and fasting blood uric acid are obtained respectively. Assuming that the obtained gender is "male", the "fasting blood uric acid" value on March 1 is 400μmol / L, and the "fasting blood uric acid" value on March 2 is 370μmol / L, then the system prompts that the match is unsuccessful and enters step S504; assuming that the obtained gender is "female", the "fasting blood uric acid" value on March 1 is 400μmol / L, and the "fasting blood uric acid" value on March 2 is 370μmol / L, then the system prompts that the match is successful.

[0115] Step S1035, obtaining the diagnosis of failed matching and the matching result information of the diagnosis to generate a second audit result of the diagnosis information existence high level.

[0116] The matching result information includes the diagnostic matching rule that failed to match, the features and feature values ​​that failed to match in the diagnostic matching rule. Continuing with the above case, the following information is obtained in the medical data set corresponding to the target medical record homepage: the gender is "male", the "fasting blood uric acid" value on March 1 is 400μmol / L, and the "fasting blood uric acid" value on March 2 is 370μmol / L. After matching in step S503, it is confirmed that the diagnostic matching rule that failed to match is {"sex = male" and "fasting blood uric acid">420μmol / L (not twice on the same day)}, and the feature one that failed to match is "fasting blood uric acid" on March 1, with a feature value of 400μmol / L; the feature two that failed to match is "fasting blood uric acid" on March 2, with a feature value of 370μmol / L. Based on the above information, a second audit result is generated. For example: The second audit result is: the medical record does not meet the diagnosis of "hyperuricemia". The specific situation is as follows: the patient's "fasting blood uric acid" characteristic value on March 1 was 400μmol / L, and the "fasting blood uric acid" characteristic value on March 2 was 370μmol / L; it did not meet the diagnostic matching rule set of "fasting blood uric acid" {"gender = male" and "fasting blood uric acid">420μmol / L (not twice on the same day)}.

[0117] Step S1036, generating a second audit result indicating that the diagnostic information does not contain any high-level information.

[0118] like Figure 7 FIG. 1 is a flowchart of another optional medical record front page review method provided by an embodiment of the present invention, the method comprising the steps of:

[0119] Step S701, obtaining the target medical record homepage to be reviewed, identifying the target medical record homepage, and obtaining the basic medical record information, diagnosis information and surgical operation information of the target medical record homepage.

[0120] Step S702, obtain the cost detail information corresponding to the target medical record homepage, and based on the pre-established mapping relationship between surgical operations and medical service item sets, match each medical service item included in the cost detail information with the surgical operation information to obtain a first audit result of whether the surgical operation information is omitted or underestimated.

[0121] Step S703, obtain the medical data set corresponding to the target medical record homepage, obtain the diagnosis matching rule set corresponding to each diagnosis in the diagnosis information based on the pre-established diagnosis matching rule library, match the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis, and obtain the second audit result of whether the diagnosis information has a high level of content.

[0122] Step S704, analyzing the inferred diagnosis set corresponding to each surgical operation in the surgical operation information based on the disease score library and the surgical operation information, matching the inferred diagnosis set corresponding to each surgical operation in the surgical operation information with the diagnostic information, and obtaining a third audit result of whether the diagnostic information is missing.

[0123] Steps S701 to S703 and Figure 1 Steps S101 to S103 in the embodiment are the same and will not be described again.

[0124] In an optional embodiment, before step S704, the method further includes: modifying the surgical operation information based on the first review result.

[0125] like Figure 8 As shown, an optional method flow chart of performing omission review on diagnostic information provided by an embodiment of the present invention includes:

[0126] Step S801, obtaining a surgical operation from the surgical operation information, and screening out a first disease type set corresponding to the surgical operation name of the surgical operation in a disease type score library.

[0127] The disease score database is a disease score database based on DIP payment published by the state or an authoritative organization. Each disease corresponds to a disease combination code, a disease combination name and a disease score. Among them, the disease combination name is composed of diagnosis name + surgical operation name 1 + surgical operation name 2... + surgical operation name n. Therefore, by searching in the disease score database by the surgical operation name, all diseases containing the surgical operation name can be found.

[0128] Step S802, predicting the inclusion in the group based on the diagnosis information and surgical operation information on the target medical record homepage, obtaining the disease score of the predicted disease, screening out a second disease set with a disease score greater than the predicted disease from the first disease set, and obtaining each diagnosis contained in the second disease set as the inferred diagnosis set corresponding to the surgical operation.

[0129] The disease grouping based on DIP payment mainly determines the main diagnosis and all surgical operation information. Therefore, the diagnosis information and surgical operation information on the target medical record homepage can be used to predict the grouping and obtain the predicted disease score. The purpose of the present invention is to reduce hospital losses. Therefore, diagnoses with disease scores lower than the predicted disease scores are not considered.

[0130] Step S803: using the above method, obtain a presumed diagnosis set corresponding to each operation in the surgical operation information.

[0131] Step S804, matching the inferred diagnosis set corresponding to each surgical operation in the surgical operation information with the diagnosis information, if the inferred diagnosis set contains one of the diagnoses in the diagnosis information, the match is successful, otherwise, the match fails.

[0132] Step S805, determining whether the inferred diagnosis set corresponding to all surgical operations in the surgical operation information successfully matches the diagnosis information, if so, proceeding to step S807, if not, proceeding to step S806.

[0133] Step S806, obtaining surgical operations that fail to match the diagnostic information, and generating a third audit result indicating omissions in diagnostic information based on a presumed diagnosis set corresponding to the surgical operations.

[0134] There may be multiple surgical operations that fail to match, so the inferred diagnosis set corresponding to each surgical operation is obtained separately to generate a third audit result indicating that there are omissions in the diagnostic information.

[0135] Step S807, generating a third audit result indicating that there is no omission in the diagnostic information.

[0136] In some embodiments, step S804 or step S806 also includes: judging the number of diagnoses in the inferred diagnosis set corresponding to each surgical operation, and if the number of diagnoses in the inferred diagnosis set is greater than a screening threshold, further screening the inferred diagnosis set based on historical inclusion information related to the target medical record homepage, wherein the historical inclusion information is historical inclusion disease information of each medical record queried in the historical medical database based on the patient information or medical structure information corresponding to the target medical record homepage.

[0137] Further screening of each inferred diagnosis set based on the historical enrollment information related to the target medical record homepage specifically includes: obtaining each diagnosis information in the historical enrollment information, judging whether each diagnosis in the inferred diagnosis set is included in the diagnosis information in the historical enrollment information, and if not, deleting the diagnosis. Whether it is a patient or a medical structure, its historical enrollment information is generally concentrated in certain diseases, and each disease corresponds to a diagnosis. Therefore, the inferred diagnosis set can be further screened according to the diagnosis information in the historical enrollment information, and in step S806, a third audit result of missing diagnosis information is generated according to the screened inferred diagnosis set. For example: the diagnosis corresponding to the surgical operation "appendectomy" is omitted, and the possible corresponding diagnoses include: "ileocecal abscess" and "acute suppurative appendicitis".

[0138] The audit method for the medical record homepage provided by the embodiment of the present invention first obtains the basic medical record information, diagnosis information, surgical operation information and cost information of the target medical record homepage; then obtains the cost detail information corresponding to the target medical record homepage, and matches each medical service item contained in the cost detail information with the surgical operation information based on the pre-established mapping relationship between the surgical operation and the medical service item set, and obtains the first audit result of whether the surgical operation information is omitted or under-edited; in addition, the medical data set corresponding to the target medical record homepage is obtained, and the diagnosis matching rule set corresponding to each diagnosis in the diagnosis information is obtained based on the pre-established diagnosis matching rule library, and the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis are matched to obtain the second audit result of whether the diagnosis information is over-edited. By adopting the method of the present invention, whether the surgical operation information and the diagnosis information in the medical record homepage are omitted, under-edited or over-edited, etc., can be audited, so that the medical staff of the medical institution can modify the medical record homepage according to the audit results to reduce the loss of the hospital.

[0139] According to an embodiment of the present invention, a method for reasonably controlling costs during medical treatment is provided, such as Fig.10 As shown, it is a flow chart of an optional method for reasonable cost control in a medical process provided by an embodiment of the present invention, and the method comprises the steps of:

[0140] Step S1001, based on big data technology, statistics are collected on the use of drugs for each disease type to obtain the use frequency of various drugs for each disease type, and drugs with a use frequency exceeding the drug use frequency threshold are added to the necessary drug catalog for each disease type.

[0141] First, collect the medical data sets of various medical records that have completed DIP or DRG enrollment in multiple medical institutions to establish a historical medical database. The medical institutions are preferably local benchmark medical institutions. Since the medication situation of each medical institution is inconsistent, when establishing a historical medical database, it is necessary to standardize the data of each drug in the charging items of each medical institution based on the official drug catalog standards published by various places, and establish a unified drug index. Another optional method is to only count the frequency of use of medical insurance drugs.

[0142] Specifically, statistics are collected on various diseases included in the historical medical database, one of the diseases is obtained to screen the historical medical database, and detailed cost information of each medical record is obtained from the screened historical medical database. Various drugs and the frequency of use of various drugs included in the detailed cost information of each medical record are counted. If the frequency of use of a certain drug exceeds the threshold of the frequency of use, the drug is added to the list of necessary drugs for the disease. For example, assuming that the threshold of the frequency of use is 90%, if a certain drug is used in 95% of the medical records, the drug is added to the list of necessary drugs for the disease.

[0143] Step S1002, predicting the type of disease based on the diagnosis information and surgical operation information of the current medical record.

[0144] In some optional embodiments, predicting enrollment based on the diagnosis information and surgical operation information of the current medical record to obtain the predicted disease type also includes: reviewing the diagnosis information and / or surgical operation information of the current medical record, and pre-modifying the diagnosis information and / or surgical operation information based on the review results to obtain the predicted disease type.

[0145] In some optional embodiments, reviewing the surgical operation information of the current medical record includes:

[0146] Obtain the expense details corresponding to the current medical record, and based on the pre-established mapping relationship between surgical operations and medical service item sets, match each medical service item contained in the expense details with the surgical operation information to obtain a first audit result of whether the surgical operation information is omitted or under-edited;

[0147] The established mapping relationship between surgical operations and medical service item sets includes:

[0148] Based on big data technology, the correlation between each surgical operation and each medical service item is counted respectively, and each medical service item exceeding the surgical correlation threshold is screened out to form a set of related medical service items for each surgical operation;

[0149] According to the similarity between the names of the medical service items in the associated medical service item set of each surgical operation and the name of the surgical operation, the medical service items exceeding the similarity threshold are screened out to form a mapping medical service item set for each surgical operation;

[0150] Establish a mapping relationship between each surgical operation and each mapped medical service item set.

[0151] In some optional embodiments, reviewing the diagnosis information of the current medical record includes:

[0152] Obtain a medical data set corresponding to the current medical record, obtain a diagnosis matching rule set corresponding to each diagnosis in the diagnosis information based on a pre-established diagnosis matching rule library, match the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis, and obtain a second audit result of whether the diagnosis information is high-level;

[0153] The establishment of the diagnosis matching rule base includes:

[0154] Based on big data technology, the keyword combinations associated with the disease names of various diseases are counted respectively; and the keyword matching rules of various diseases are generated according to the keyword combinations;

[0155] Based on big data technology, the basic medical record information, drug information, surgery information, test index information and inspection index information of each disease are analyzed for correlation with each disease; the combination of basic information characteristics, drug characteristics, surgery characteristics, test index characteristics and inspection index characteristics associated with each disease is obtained, and the feature matching rules of each disease are generated according to the combination;

[0156] The keyword matching rules and feature matching rules of each disease are combined to form a diagnosis matching rule set for each disease.

[0157] In some optional embodiments, reviewing the diagnostic information of the current medical record also includes: analyzing the inferred diagnosis set corresponding to each surgical operation in the surgical operation information based on the disease score library and the surgical operation information; matching the inferred diagnosis set corresponding to each surgical operation in the surgical operation information with the diagnostic information to obtain a third review result of whether the diagnostic information is missing.

[0158] For technical details not fully described in this embodiment, reference may be made to the method for reviewing diagnosis information and / or surgical operation information in the method for reviewing the medical record front page provided in the method embodiment of the present invention.

[0159] Step S1003, obtaining the doctor's medication instructions, determining whether each target drug in the medication instructions is included in the necessary drug catalog corresponding to the predicted disease, and if not, obtaining the medication frequency of the target drug to generate the first prompt information.

[0160] The embodiment of the present invention collects statistics on the medication big data of each benchmark medical institution to obtain the DDDs (Defined Daily Dose) of a certain drug for each disease, and uses DDDs to remind doctors to use the drug. The smaller the DDDs, the less frequently the drug is used. When a single doctor uses the drug, the doctor is reminded whether he should use it.

[0161] In an optional scheme, the method also includes: based on big data technology, statistics are collected on the drug proportion of each disease type to obtain the standard drug proportion of each disease type; whether the ratio of the total cost of each target drug in the medication order to the total cost of each medical service item exceeds the standard drug proportion corresponding to the predicted disease type, and if so, a third prompt information is generated.

[0162] like Fig.11 As shown, it is a flowchart of another optional method for reasonable cost control in a medical process provided by an embodiment of the present invention, and the method comprises the steps of:

[0163] Step S1101, based on big data technology, statistics are collected on the use of drugs for each disease type to obtain the use frequency of various drugs for each disease type, and drugs with a use frequency exceeding the drug use frequency threshold are added to the necessary drug catalog for each disease type.

[0164] Step S1102, based on big data technology, statistics are collected on the usage of medical consumables for each disease type, and a reasonable price range for each type of medical consumables for each disease type is obtained.

[0165] Similarly, since the use of medical consumables in various medical institutions is inconsistent, when establishing a historical medical database, it is necessary to standardize the data of each medical consumable in the charging items of each medical institution based on the official medical consumables use standards announced by various places, and establish a unified medical consumables index.

[0166] Medical consumables include chargeable medical consumables and non-chargeable medical consumables. The embodiment of the present invention only counts chargeable medical consumables. In actual applications, statistics can also be only counted for high-value medical consumables, such as orthopedic implant consumables, vascular interventional devices, and high-value neurosurgery consumables. These high-value medical consumables generally appear in certain types of diseases. Therefore, before counting the use of medical consumables, the types of diseases that need to be counted can be screened out first.

[0167] Specifically, a disease type is obtained from the screened diseases, and the historical medical database is screened based on the disease type. The cost details of each medical record are obtained in the screened historical medical database, and the use of various medical consumables in the cost details of each medical record is counted, so as to obtain the reasonable price range of various medical consumables. For example: According to statistics, under the category of inguinal hernia: surgical operation-level II, the reasonable price range of domestic inguinal hernia patch is 2,500 yuan to 2,600 yuan.

[0168] Step S1103, obtaining a predicted disease type based on the diagnosis information and surgical operation information of the current medical record.

[0169] Step S1104, obtaining the doctor's medication instructions, determining whether each target drug in the medication instructions is included in the necessary drug catalog corresponding to the predicted disease, and if not, obtaining the medication frequency of the target drug to generate the first prompt information.

[0170] Step S1105, determining whether the cost of each medical consumable in the medication instruction is within the reasonable price range of the medical consumable under the predicted disease type, and if not, generating a third prompt message.

[0171] For example, if a doctor prescribes an imported inguinal hernia patch in a medication order, which costs 6,000 yuan, the system will generate a prompt message to remind the doctor to prescribe medical consumables within a reasonable price range.

[0172] Step S1101, step S1103 and step S1104 are respectively Fig.10 In the embodiment, step S1001, step S1002 and step S1003 are the same and will not be described in detail herein.

[0173] According to an embodiment of the present invention, a device for reasonably controlling costs during medical treatment is provided, such as Fig. 9 , which is a schematic diagram of the structure of an optional reasonable cost control device provided in an embodiment of the present invention, wherein the reasonable cost control device 900 includes:

[0174] The drug catalog establishment module 902 is used to collect statistics on drug usage for each disease based on big data technology, obtain the usage frequency of various drugs for each disease, and add drugs whose usage frequency exceeds the medication frequency threshold to the essential drug catalog for each disease;

[0175] The disease prediction module 904 is used to obtain the predicted disease based on the diagnosis information and surgical operation information of the current medical record;

[0176] The first prompt module 906 is used to obtain the doctor's medication instructions, determine whether each target drug in the medication instructions is included in the necessary drug catalog corresponding to the predicted disease, and if not, obtain the medication frequency of the target drug to generate the first prompt information.

[0177] The above-mentioned device can execute the method for reasonable cost control during the medical process described in the embodiment of the method of the present invention, and has the corresponding functional modules and beneficial effects of the method. For technical details not described in detail in this embodiment, please refer to the method for reasonable cost control during the medical process provided in the embodiment of the method of the present invention.

[0178] According to an embodiment of the present invention, there is provided an electronic device, such as Fig.12As shown, it is a schematic diagram of the structure of an optional electronic device provided in an embodiment of the present invention, and the electronic device may include a processor 1201, a communication interface 1202, a memory 1203 and a communication bus 1204, wherein the processor 1201, the communication interface 1202, and the memory 1203 communicate with each other through the communication bus 1204. The processor 1201 can call the logical instructions in the memory 1203 to execute the method described in any of the above embodiments, such as the method for reviewing the medical record homepage, which includes: obtaining the target medical record homepage to be reviewed, identifying the target medical record homepage, and obtaining the basic medical record information, diagnosis information and surgical operation information of the target medical record homepage; obtaining the cost detail information corresponding to the target medical record homepage, and matching each medical service item included in the cost detail information with the surgical operation information based on a pre-established mapping relationship between the surgical operation and the medical service item set, to obtain a first review result of whether the surgical operation information is omitted or under-coded; obtaining the medical data set corresponding to the target medical record homepage, matching the diagnosis information with the medical data set based on a pre-established diagnosis matching rule library, and obtaining a second review result of whether the diagnosis information is over-coded.

[0179] In addition, the logic instructions in the above-mentioned memory 1203 can be implemented in the form of software functional units and can be stored in several computer-readable storage media when they are sold or used as independent products. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the method of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.

[0180] According to an embodiment of the present invention, a computer-readable storage medium is provided, and its type is as described in the electronic device embodiment. The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in any of the above embodiments of the present invention, such as the steps of the method for reviewing the medical record front page.

[0181] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may also be combined, the steps may be implemented in any order, and there are many other changes in different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for reasonable cost control in the medical process, characterized in that: The method comprises: Based on big data technology, statistics are collected on the use of drugs for each disease, and the use frequency of various drugs for each disease is obtained. Drugs with a use frequency exceeding the medication frequency threshold are added to the list of essential drugs for each disease. Review the diagnosis information and / or surgical operation information of the current medical record, and modify the diagnosis information and / or surgical operation information according to the review result to perform prediction and obtain the predicted disease type; Obtaining the doctor's medication order, determining whether each target drug in the medication order is included in the necessary drug catalog corresponding to the predicted disease, and if not, obtaining the medication frequency of the target drug to generate the first prompt information; The review of the diagnostic information of the current medical record includes: Acquire a surgical operation from the surgical operation information, and select a first disease type set corresponding to the surgical operation name of the surgical operation in the disease type score library; Based on the diagnosis information and surgical operation information of the current medical record, the predicted disease is enrolled in the group, and the disease score of the predicted disease is obtained. A second disease set with a disease score greater than the predicted disease is selected from the first disease set, and each diagnosis included in the second disease set is obtained as the inferred diagnosis set corresponding to the surgical operation; Using the above method, a presumed diagnosis set corresponding to each surgical operation in the surgical operation information is obtained; The inferred diagnosis set corresponding to each surgical operation in the surgical operation information is matched with the diagnostic information. If the inferred diagnosis set contains one of the diagnoses in the diagnostic information, a third audit result indicating that there is no omission in the diagnostic information is generated. Otherwise, the surgical operation that fails to match the diagnostic information is obtained, and a third audit result indicating that there is omission in the diagnostic information is generated based on the inferred diagnosis set corresponding to the surgical operation.

2. The method according to claim 1, characterized in that The method further comprises: Based on big data technology, the drug ratio of each disease type is counted to obtain the standard drug ratio of each disease type; determine whether the ratio of the total cost of each target drug in the medication order to the total cost of each medical service item exceeds the standard drug ratio corresponding to the predicted disease type. If so, generate a second prompt information.

3. The method according to claim 1, characterized in that The review of the diagnostic information of the current medical record includes: Obtain a medical data set corresponding to the current medical record, obtain a diagnosis matching rule set corresponding to each diagnosis in the diagnosis information based on a pre-established diagnosis matching rule library, match the diagnosis information, the medical data set and the diagnosis matching rule set corresponding to each diagnosis, and obtain a second audit result of whether the diagnosis information is high-level; Wherein, the establishment of the diagnosis matching rule base includes: Based on big data technology, the keyword combinations associated with the disease names of various diseases are counted respectively; and the keyword matching rules of various diseases are generated according to the keyword combinations; Based on big data technology, the basic medical record information, drug information, surgery information, test index information and inspection index information of each disease are analyzed for correlation with each disease; the combination of basic information characteristics, drug characteristics, surgery characteristics, test index characteristics and inspection index characteristics associated with each disease is obtained, and the feature matching rules of each disease are generated according to the combination; The keyword matching rules and feature matching rules of each disease are combined to form a diagnosis matching rule set for each disease.

4. The method according to claim 1, characterized in that The review of the surgical operation information of the current medical record includes: Obtain the expense details corresponding to the current medical record, and based on the pre-established mapping relationship between surgical operations and medical service item sets, match each medical service item contained in the expense details with the surgical operation information to obtain a first audit result of whether the surgical operation information is omitted or under-edited; The established mapping relationship between surgical operations and medical service item sets includes: Based on big data technology, the correlation between each surgical operation and each medical service item is counted respectively, and each medical service item exceeding the surgical correlation threshold is screened out to form a set of related medical service items for each surgical operation; According to the similarity between the names of the medical service items in the associated medical service item set of each surgical operation and the name of the surgical operation, the medical service items exceeding the similarity threshold are screened out to form a mapping medical service item set for each surgical operation; Establish a mapping relationship between each surgical operation and each mapped medical service item set.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Based on big data technology, the use of medical consumables for each disease is counted and the reasonable price range of each type of medical consumables for each disease is obtained; It is determined whether the cost of each medical consumable in the medication instruction is within the reasonable price range of the medical consumable under the predicted disease type. If not, a third prompt information is generated.

6. A device for reasonably controlling costs during medical treatment, characterized in that: The device comprises: The drug catalog building module collects statistics on drug usage for each disease based on big data technology, obtains the usage frequency of various drugs for each disease, and adds drugs whose usage frequency exceeds the medication frequency threshold to the essential drug catalog for each disease; The disease type prediction module reviews the diagnosis information and / or surgical operation information of the current medical record, and modifies the diagnosis information and / or surgical operation information according to the review result to predict the type of disease, and obtains the predicted disease type. The review of the diagnosis information of the current medical record includes: obtaining a surgical operation from the surgical operation information, screening out a first disease type set corresponding to the surgical operation name of the surgical operation in a disease type score library, predicting the type of disease based on the diagnosis information and surgical operation information of the current medical record, obtaining the disease type score of the predicted disease, and screening out a second disease type set with a disease type score greater than the predicted disease type in the first disease type set. Disease type set, obtaining each diagnosis included in the second disease type set as the inferred diagnosis set corresponding to the surgical operation, using the above method to obtain the inferred diagnosis set corresponding to each surgical operation in the surgical operation information, matching the inferred diagnosis set corresponding to each surgical operation in the surgical operation information with the diagnostic information, if the inferred diagnosis set contains one of the diagnoses in the diagnostic information, generating a third audit result that the diagnostic information does not have omissions, otherwise, obtaining the surgical operation that fails to match the diagnostic information, and generating a third audit result that the diagnostic information has omissions according to the inferred diagnosis set corresponding to the surgical operation; The first prompt module obtains the doctor's medication order and determines whether each target drug in the medication order is included in the necessary drug catalog corresponding to the predicted disease. If not, the medication frequency of the target drug is obtained to generate the first prompt information.

7. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored and running on the memory, wherein when the processor executes the program, the method steps for reasonably controlling costs during the medical process as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the method steps for reasonable cost control during a medical procedure as described in any one of claims 1-5.

Images