Medical data processing method, device, equipment and storage medium

Abstract

The present disclosure provides a medical data processing method, device and equipment and a storage medium, relates to the technical field of computers, in particular to the technical field of knowledge graph, big data and AI medical treatment. The specific implementation scheme is as follows: the medical data processing method comprises the following steps: determining the type of the medical data to be processed according to the feature information in the medical data to be processed; and screening the medical result in the medical data to be processed according to the screening mode corresponding to the type of the medical data to be processed. The embodiment of the present disclosure can flexibly select the screening mode according to the type of the medical data, the application scenarios are more extensive, and it is beneficial to screen the medical result more in line with the scene requirements from the medical data.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to the fields of knowledge graphs, big data, and artificial intelligence (AI) in the medical field. Background Technology

[0002] Medical records, also known as medical case files, typically include records kept by medical staff documenting the onset, development, and outcome of a patient's illness, as well as the medical activities performed, including examinations, diagnoses, and treatments. In information systems, multiple roles may need to use medical records, such as medical staff who write them and coders who fill out medical insurance system forms. Due to these different roles, their understanding of the medical record content may differ, potentially leading to frequent communication between them and impacting work efficiency. Summary of the Invention

[0003] This disclosure provides a medical data processing method, apparatus, device, and storage medium.

[0004] According to one aspect of this disclosure, a medical data processing method is provided, comprising:

[0005] The type of medical data to be processed is determined based on the feature information in the medical data to be processed;

[0006] Based on the filtering method corresponding to the type of medical data to be processed, the medical results in the medical data to be processed are filtered.

[0007] According to another aspect of this disclosure, a medical data processing apparatus is provided, comprising:

[0008] The first determining module is used to determine the type of the medical data to be processed based on the feature information in the medical data to be processed;

[0009] The filtering module is used to filter the medical results in the medical data to be processed according to the filtering method corresponding to the type of medical data to be processed.

[0010] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0011] At least one processor; and

[0012] The memory is communicatively connected to the at least one processor; wherein,

[0013] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods of any embodiment of the present disclosure.

[0014] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform a method according to any embodiment of this disclosure.

[0015] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements a method according to any embodiment of this disclosure.

[0016] The embodiments disclosed herein can flexibly select the filtering method according to the type of medical data, making it applicable to a wider range of scenarios and facilitating the selection of medical results from medical data that better meet the needs of the scenario.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0018] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0019] Figure 1 This is a schematic flowchart of a medical data processing method according to an embodiment of the present disclosure;

[0020] Figure 2 This is a schematic flowchart of a medical data processing method according to another embodiment of the present disclosure;

[0021] Figure 3 This is a schematic flowchart of a medical data processing method according to another embodiment of the present disclosure;

[0022] Figure 4 This is a schematic flowchart of a medical data processing method according to another embodiment of the present disclosure;

[0023] Figure 5 This is a schematic diagram of the structure of a medical data processing apparatus according to an embodiment of the present disclosure;

[0024] Figure 6 This is a schematic diagram of the structure of a medical data processing apparatus according to another embodiment of the present disclosure;

[0025] Figure 7 This is a schematic diagram of the structure of a medical data processing apparatus according to another embodiment of the present disclosure;

[0026] Figure 8 This is a schematic diagram of the structure of a medical data processing apparatus according to another embodiment of the present disclosure;

[0027] Figure 9This is a schematic diagram illustrating an application example of a medical data processing method according to an embodiment of the present disclosure;

[0028] Figure 10 This is a schematic diagram of a ranking decision tree model;

[0029] Figure 11 This is a diagram illustrating the correspondence between diagnosis and consumption;

[0030] Figure 12 This is a schematic diagram showing the display effect of the test results;

[0031] Figure 13 This is a block diagram of an electronic device used to implement the medical data processing method of the embodiments of this disclosure. Detailed Implementation

[0032] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0033] Figure 1 This is a schematic flowchart of a medical data processing method according to an embodiment of the present disclosure. The method may include:

[0034] S101. Determine the type of medical data to be processed based on the feature information in the medical data to be processed;

[0035] S102. Filter the medical results in the medical data to be processed according to the filtering method corresponding to the type of medical data to be processed.

[0036] In this embodiment of the disclosure, medical data may include medical records, etc. Medical records may include records of medical activities such as examination, diagnosis, and treatment of one or more diseases of the patient. Medical outcomes in the medical data may include diagnostic results from the medical records.

[0037] In one possible implementation, the medical data processing method may include a medical record processing method, which may include: determining the type of the medical record to be processed based on the feature information in the medical record to be processed; and filtering the diagnostic results in the medical record to be processed according to the filtering method corresponding to the type of the medical record to be processed.

[0038] In this embodiment of the disclosure, a patient's pending medical record may include records of medical activities such as examination, diagnosis, and treatment for one or more diseases of that patient. The sources of the pending medical records can be various, such as medical record front page statistics systems, hospital quality monitoring systems (HQMS), electronic medical record systems, and disease related group (DRG) platforms.

[0039] In this embodiment of the disclosure, the type of medical data can be determined based on the type range specified in the set requirements. These set requirements may include specific medical guidelines, rules, or regulations of certain institutions, or they may include requirements set based on medical experience. For example, if the characteristic information in a medical record conforms to a certain medical standard, then the medical record is a special case; if it does not conform to the standard, then the medical record is a common case.

[0040] In this embodiment, clinicians may write (or fill out) medical records according to diagnostic requirements, such as arranging diagnostic results according to etiological diagnosis, pathological morphology diagnosis, pathophysiological diagnosis, complications, and concomitant diseases. Diagnostic results can also be simply referred to as diagnoses. Based on the characteristic information in the medical records to be processed, such as diagnostic features, disease names, and medical items, the medical records can be classified. Different screening methods can be used for diagnostic results in different types of medical records. This embodiment allows for flexible selection of screening methods based on the type of medical data, making it applicable to a wider range of scenarios and facilitating the selection of medical results that better meet the needs of the specific scenario. For example, flexibly selecting screening methods based on the type of medical record makes it applicable to a wider range of scenarios and facilitates the selection of diagnostic results that better meet the needs of the specific scenario.

[0041] Figure 2 This is a flowchart illustrating a medical data processing method according to another embodiment of the present disclosure. The method of this embodiment includes one or more features of the above-described medical data processing method embodiments. In one possible implementation, the method further includes:

[0042] S201. Based on the screened medical results, determine at least one coded information corresponding to the medical data to be processed.

[0043] In one possible implementation, S201 may include: determining at least one coded information corresponding to the medical record to be processed based on the screened diagnostic results.

[0044] In this embodiment, one or more medical results can be filtered from the medical data to be processed. If one medical result is filtered, it can be matched with one code; if multiple medical results are filtered, multiple codes can be matched. For example, one or more diagnostic results can be filtered from the medical records to be processed. If one diagnostic result is filtered, it can be matched with one code; if multiple diagnostic results are filtered, multiple codes can be matched. In some application scenarios, it is necessary to match code information to the medical records based on the diagnostic results. In different scenarios, the code information can also express different meanings. For example, in the scenario of medical insurance payment, the code information can include the medical insurance code matched with the diagnostic result. Among them, those that consume the most medical resources, pose the greatest threat to the patient's health, and affect the longest hospitalization time can be used as the selection criteria for the diagnostic result. Then, an appropriate medical insurance code can be matched based on the main diagnostic results in the medical record.

[0045] In this embodiment of the disclosure, based on medical results filtered from medical data, coding information matching the medical data can be determined, thus making it applicable to various scenarios where medical data is identified by coding. This method is convenient to use and has a wide range of applications. For example, based on diagnostic results filtered from medical records, coding information matching the medical records can be determined, making it applicable to various scenarios where medical records are identified by coding. This method is convenient to use and has a wide range of applications.

[0046] In one possible implementation, the method further includes:

[0047] S202. Send the encoding recommendation result to the client. The encoding recommendation result includes at least one encoding information corresponding to the medical data to be processed.

[0048] In one possible implementation, S202 includes: sending a coding recommendation result to the client, the coding recommendation result including at least one coding information corresponding to the medical record to be processed.

[0049] For example, the client can include applications (apps), browsers, etc., that can run on terminal devices. If a diagnosis result is filtered from the medical records on the server and its coding information is matched, a coding recommendation result including that coding information can be sent to the client. After receiving the coding recommendation result, the client can display it on the user interface through methods such as pop-ups, prompts, drop-down menus, etc., for operators to use. For example, one or more medical insurance codes recommended for the medical record can be provided to the coder, who can refer to the medical insurance codes provided by the server for subsequent operations.

[0050] In this embodiment of the disclosure, based on the diagnostic results filtered from medical data, coding information matching the medical data can be determined, thus making it applicable to various scenarios where medical data is identified by coding. This method is convenient to use and has a wide range of applications. For example, based on the diagnostic results filtered from medical records, coding information matching the medical records can be determined, making it applicable to various scenarios where medical records are identified by coding. This method is convenient to use and has a wide range of applications.

[0051] Figure 3 This is a flowchart illustrating a medical data processing method according to another embodiment of the present disclosure. The method of this embodiment includes one or more features of the above-described medical data processing method embodiments. In one possible implementation, the method further includes:

[0052] S301. Determine the filtering method corresponding to the type of medical data to be processed.

[0053] In one possible implementation, the filtering methods corresponding to the types of medical data to be processed include decision tree methods and / or medical consumption methods. For example, if the type of medical record to be processed meets the set requirements, the filtering method corresponding to the type of medical record to be processed is the decision tree method; if the type of medical record to be processed does not meet the set requirements, the filtering method corresponding to the type of medical record to be processed is the medical consumption method. The set requirements can vary depending on different application scenarios and can also vary according to changes in various regulations and standards. For example, the set requirements may include the main diagnosis selection principles required in the "Medical Insurance Settlement List Filling Specifications". Based on the characteristic information in the medical record, if the medical record meets the special medical record criteria in the set requirements, the main diagnosis result can be filtered using the decision tree method; if the medical record does not meet the special medical record criteria in the set requirements, the main diagnosis result can be filtered using the medical consumption method. The main diagnosis result can also be referred to as the primary diagnosis. Flexible selection of filtering methods based on the type of medical data is beneficial for filtering out diagnostic results that better meet the needs of the scenario from the medical data. For example, flexible selection of filtering methods based on the type of medical record is beneficial for filtering out diagnostic results that better meet the needs of the scenario from the medical records.

[0054] In one possible implementation, the filtering method corresponding to the type of medical data to be processed is a decision tree method, and S102 may include:

[0055] S302. Input the feature information in the medical data to be processed into the decision tree model, and select the main medical result from the medical results corresponding to the feature information through the decision tree model; wherein, the decision tree model is generated according to the medical result selection method in the set requirements.

[0056] For example, the diagnostic results in the medical records to be processed are filtered according to the filtering method corresponding to the type of the medical records to be processed. This includes: inputting the feature information of the medical records to be processed into a decision tree model, and selecting the main diagnostic result from each diagnostic result corresponding to the feature information through the decision tree model; wherein, the decision tree model is generated according to the diagnostic result selection method in the set requirements.

[0057] In this embodiment, a decision tree model is generated based on the diagnostic result selection method specified in the settings. After inputting the feature information of the medical record to be processed into the decision tree model, the model can make judgments based on the feature information. For example, it determines whether the medical record belongs to injury, burn, poisoning, postpartum condition, tumor, etc. If it is an injury, the primary diagnostic result (which can be referred to as the primary diagnosis) is selected according to the requirements of injury; if it is poisoning, the primary diagnostic result is selected according to the requirements of poisoning. The following uses injury and poisoning as examples for illustration; the principles of other solutions are similar and will not be exhaustive.

[0058] For example, the requirements might include: for multiple injuries, the diagnosis of the most severe injury and / or the primary disease requiring treatment should be selected as the primary diagnosis. For poisoning, the diagnosis of poisoning should be selected as the primary diagnosis. The decision tree model can assess the features of the medical record, such as diagnostic features. If it determines that the medical record includes multiple injuries, it can select the injury posing the greatest health hazard, such as a head injury, as the primary diagnosis. If it determines that the primary purpose of the medical record is to treat poisoning, it can select poisoning as the primary diagnosis.

[0059] In this embodiment, a decision tree model is used to filter out primary diagnostic results from medical records that better meet the set requirements, facilitating subsequent operations using these results. For example, a medical insurance number can be matched using the primary diagnostic results, and this number can be sent to the client via a coding recommendation, thus assisting the coder in quickly filling in the appropriate medical insurance number for the medical record. Furthermore, the decision tree model can filter out one or more primary diagnostic results from the diagnostic results in the medical records to be processed. If multiple primary diagnostic results are selected, they can be sorted according to set requirements or other methods, such as the medical consumption method described below.

[0060] In one possible implementation, the filtering method corresponding to the type of medical data to be processed is the medical consumption method, and S102 includes:

[0061] S303. Calculate the cost of each medical outcome in the medical data to be processed based on the consumption factor model of the medical data to be processed.

[0062] S304. Select the medical outcome with the highest cost as the primary medical outcome corresponding to the medical data to be processed.

[0063] For example, the diagnostic results in the medical records to be processed are filtered according to the filtering method corresponding to the type of medical record to be processed, including: calculating the consumption cost of each diagnostic result in the medical record to be processed according to the consumption factor model of the medical record to be processed; and selecting the diagnostic result with the largest consumption cost as the main diagnostic result corresponding to the medical record to be processed.

[0064] In this embodiment of the disclosure, the medical data to be processed may include one or more medical outcomes. Each medical outcome may require the cost of one or more medical procedures. For example, the medical record to be processed may include one or more diagnostic results. Each diagnostic result may require the cost of one or more medical procedures. Medical procedures may include, but are not limited to, medication, examination, treatment, consumables, hand anesthesia, and laboratory tests. Medical procedures that require payment can be used as consumption factors. Different diagnostic results may have different consumption factor models. For example, the consumption factor model for diagnostic result 1 includes medication, examination, and treatment; the consumption factor model for diagnostic result 2 includes treatment, consumables, and hand anesthesia; and the consumption factor model for diagnostic result 3 includes medication, examination, and laboratory tests. The cost of each diagnostic result in the medical record to be processed can be calculated separately. Then, the cost of these options is compared to determine which option has the highest cost, and the diagnostic result with the highest cost corresponds to the primary diagnostic result of that medical record. In addition, multiple diagnostic results in the medical record can be sorted from highest to lowest cost, with the option at the top having the highest cost.

[0065] In this embodiment, by calculating the cost of medical outcomes in medical data, the medical outcome with the highest cost can be quickly and accurately selected, facilitating its use as the primary medical outcome for subsequent operations. For example, by calculating the cost of diagnoses in medical records, the diagnosis with the highest cost can be quickly and accurately selected, facilitating its use as the primary diagnosis for subsequent operations. As another example, the medical insurance number can be matched using the diagnosis with the highest cost, and this number can be sent to the client based on coding recommendations, thereby assisting coders in quickly filling in the appropriate medical insurance number for the medical record.

[0066] In one possible implementation, the consumption factor model is based on a medical knowledge graph and includes the sum of costs for each consumption factor in a medical outcome. For example, the consumption factor model includes the sum of costs for each consumption factor in a diagnostic outcome.

[0067] In the disclosed embodiments, clinical medical knowledge can be processed to generate a medical knowledge graph. The medical knowledge graph can include medical knowledge from various departments such as outpatient, emergency, inpatient, nursing, and medical technology. By associating medical costs in the medical records to be processed with relationships within the knowledge graph, a connection can be established with the diagnostic results in the medical records. Consumption factors for the diagnostic results identified in the medical records are used to obtain a consumption factor model for that diagnostic result. For example, if the consumption factor model for diagnostic result 1 includes medication, examination, and treatment, the consumption factor model can calculate the sum of medication costs, examination costs, and treatment costs. If the consumption factor model for diagnostic result 2 includes treatment, consumables, and anesthesia, the consumption factor model can calculate the sum of treatment costs, consumable costs, and anesthesia costs. If the consumption factor model for diagnostic result 3 includes medication, examination, and laboratory tests, the consumption factor model can calculate the sum of medication costs, examination costs, and laboratory test costs.

[0068] In the disclosed embodiments, by constructing a consumption factor model for medical outcomes using a medical knowledge graph, the sum of costs for each consumption factor in a medical outcome can be accurately calculated, thereby obtaining the consumption cost of each medical outcome. This allows for the rapid and accurate identification of the primary medical outcome with the highest consumption cost in the medical data, and ultimately, the medical outcome consuming the most medical resources. For example, by constructing a consumption factor model for diagnostic outcomes using a medical knowledge graph, the sum of costs for each consumption factor in a diagnostic outcome can be accurately calculated, thereby obtaining the consumption cost of each diagnostic outcome. This allows for the rapid and accurate identification of the primary diagnostic outcome with the highest consumption cost in the medical record, and ultimately, the diagnostic outcome consuming the most medical resources.

[0069] Figure 4 This is a flowchart illustrating a medical data processing method according to another embodiment of the present disclosure. The method of this embodiment includes one or more features of the above-described medical data processing method embodiments. In one possible implementation, the method further includes:

[0070] S401. Based on the feature information in the medical data to be processed and the evidence-based medicine cognitive computing method, search the medical knowledge graph to obtain the standard medical result. For example, based on the feature information in the medical record to be processed and the evidence-based medicine cognitive computing method, search the medical knowledge graph to obtain the standard diagnostic result.

[0071] S402. Compare the cost of the medical items consumed in the standard medical outcome with the cost of the medical items consumed in the actual medical outcome included in the medical data to be processed, in order to determine whether the medical items in the actual medical outcome are reasonable. For example, compare the cost of the medical items consumed in the standard diagnostic result with the cost of the medical items consumed in the actual diagnostic result included in the medical record to be processed, in order to determine whether the medical items in the actual diagnostic result are reasonable.

[0072] In this embodiment, evidence-based medicine, meaning medicine that follows evidence, is a medical diagnostic and treatment approach that emphasizes optimizing decision-making through well-designed and executed research (evidence). Evidence-based medicine principles are combined with artificial intelligence algorithms to form an evidence-based medical cognitive computing method. Using the feature information in the medical data to be processed, the actual medical outcome can be obtained from that data. The evidence-based medical cognitive computing method then searches for standard medical outcomes in a medical knowledge graph. For example, using the feature information in a medical record to be processed, the actual diagnostic result can be obtained from that record. The evidence-based medical cognitive computing method then searches for a standard diagnostic result in a medical knowledge graph.

[0073] For example, if the actual diagnosis result 1 includes medication, examination, and treatment, while the standard diagnosis result 1 includes examination and treatment, then the actual diagnosis result 1 is different from the standard diagnosis result 1. The actual diagnosis result 1 includes the additional medical procedure of medication compared to the standard diagnosis result 1. Therefore, the medication is an unreasonable medical procedure, and consequently, it incurs excessive costs for this medical procedure, which constitutes unreasonable medical expenditure.

[0074] For example, the actual diagnosis result 2 includes medical items such as treatment, consumables, and hand anesthesia, while the standard diagnosis result 2 also includes medical items such as treatment, consumables, and hand anesthesia. The two are identical, and there is no unreasonable medical consumption.

[0075] In this embodiment, by employing evidence-based medicine cognitive computing methods and medical knowledge graphs, more reasonable medical outcomes can be obtained from medical data. These reasonable medical outcomes can be used as standard medical outcomes, thereby enabling a rationality evaluation of the actual medical items included in the medical data. For example, by using evidence-based medicine cognitive computing methods and medical knowledge graphs, more reasonable diagnostic results can be obtained from medical records. These reasonable diagnostic results can be used as standard diagnostic results, thereby enabling a rationality evaluation of the actual medical items included in the diagnostic results of the medical records, providing support for scenarios such as medical insurance payments.

[0076] In one possible implementation, the method further includes:

[0077] S403. Send the medical consumption result of the medical data to be processed to the client, wherein the medical consumption result includes at least one of the following:

[0078] The recommended ranking of each medical outcome in the medical data to be processed;

[0079] Reasons for recommending major medical outcomes;

[0080] Recommendations for major medical outcomes;

[0081] The percentage of consumption for each medical outcome;

[0082] Unreasonable medical expenses.

[0083] In one possible implementation, S403 may include: sending the medical consumption result of the pending medical record to the client, the medical consumption result including at least one of the following:

[0084] Recommended ranking of diagnostic results in the pending medical records;

[0085] Reasons for recommending the primary diagnostic result;

[0086] Recommended results for the primary diagnostic findings;

[0087] The percentage of consumption for each diagnostic result;

[0088] Unreasonable medical expenses.

[0089] In this embodiment of the disclosure, if the medical record to be processed includes multiple diagnostic results, they can be sorted in descending order of cost. For example, the recommended sorting results for diagnostic results may include diagnostic result 2, diagnostic result 3, and diagnostic result 1. The server can send the medical cost results and the code recommendation results to the same client, or it can send the medical cost results or the code recommendation results to different clients separately.

[0090] In this embodiment of the disclosure, the recommended reasons and recommended results for the primary diagnosis can be displayed on the client side. For example, based on the medical insurance settlement filling specifications, the recommended primary diagnosis is diagnosis result 3. Other recommended reasons are also possible, which will not be exhaustively listed here.

[0091] In this embodiment of the disclosure, the consumption percentage of each diagnostic result in the medical record to be processed can be calculated based on the consumption cost of each diagnostic result. For example, in the medical record to be processed, the consumption cost of diagnostic result 2 is 100 yuan, the consumption cost of diagnostic result 3 is 50 yuan, and the consumption cost of diagnostic result 1 is 10 yuan. Then, the consumption percentage of diagnostic result 2 is 62.5%, the consumption percentage of diagnostic result 3 is 31.25%, and the consumption percentage of diagnostic result 1 is 6.25%.

[0092] In this embodiment of the disclosure, unreasonable medical expenses may include the costs of unreasonable medical items in each diagnostic result of the pending medical record. For example, the medication in diagnostic result 1 is unreasonable, and the cost is X yuan. The laboratory test in diagnostic result 3 is unreasonable, and the cost is XX yuan. Unreasonable medical expenses may also include the sum of the costs of unreasonable medical items in all diagnostic results of the pending medical record. For example, the medication in the medical record is unreasonable, and the cost is X yuan; the laboratory test is unreasonable, and the cost is XX yuan.

[0093] In this embodiment of the disclosure, sending medical consumption results to the client can display various medical consumption results on the client, which is helpful to remind or assist operators in making subsequent decisions or operations.

[0094] Figure 5 This is a schematic diagram of a medical data processing apparatus according to an embodiment of the present disclosure. The apparatus may include:

[0095] The first determining module 501 is used to determine the type of the medical data to be processed based on the feature information in the medical data to be processed;

[0096] The filtering module 502 is used to filter the medical results in the medical data to be processed according to the filtering method corresponding to the type of medical data to be processed.

[0097] In one possible implementation, the first determining module 501 is used to determine the type of the medical record to be processed based on the feature information in the medical record to be processed; the filtering module 502 is used to filter the diagnostic results in the medical record to be processed according to the filtering method corresponding to the type of the medical record to be processed.

[0098] Figure 6 This is a schematic diagram of a medical data processing apparatus according to another embodiment of the present disclosure, which includes one or more features of the above-described medical data processing apparatus embodiment. In one possible implementation, the apparatus further includes:

[0099] The second determining module 601 is used to determine at least one coded information corresponding to the medical data to be processed based on the filtered medical results.

[0100] In one possible implementation, the second determining module 601 is used to determine at least one coded information corresponding to the medical record to be processed based on the screened diagnostic results.

[0101] In one possible implementation, the device further includes:

[0102] The first sending module 602 is used to send an encoding recommendation result to the client, the encoding recommendation result including at least one encoding information corresponding to the medical data to be processed.

[0103] In one possible implementation, the first sending module 602 is used to send a coding recommendation result to the client, the coding recommendation result including at least one coding information corresponding to the medical record to be processed.

[0104] Figure 7This is a schematic diagram of a medical data processing apparatus according to another embodiment of the present disclosure, which includes one or more features of the above-described medical data processing apparatus embodiment. In one possible implementation, the apparatus further includes:

[0105] The third determining module 701 is used to determine the filtering method corresponding to the type of medical data to be processed. The filtering method corresponding to the type of medical data to be processed includes decision tree method and / or medical consumption method.

[0106] In one possible implementation, the third determining module 701 is used to determine the filtering method corresponding to the type of medical record to be processed, which includes the decision tree method and / or the medical consumption method.

[0107] In one possible implementation, the filtering method corresponding to the type of medical data to be processed is a decision tree method; the filtering module 502 includes:

[0108] The decision tree filtering submodule 703 is used to input the feature information in the medical data to be processed into the decision tree model, and select the main medical result from the medical results corresponding to the feature information through the decision tree model; wherein, the decision tree model is generated according to the medical result selection method in the set requirements.

[0109] In one possible implementation, the decision tree filtering submodule 703 is used to input the feature information of the medical record to be processed into the decision tree model, and select the main diagnostic result from the diagnostic results corresponding to the feature information through the decision tree model; wherein, the decision tree model is generated according to the diagnostic result selection method in the set requirements.

[0110] In one possible implementation, the filtering method corresponding to the type of medical data to be processed is medical consumption method; the filtering module 502 includes:

[0111] The consumption calculation submodule 704 is used to calculate the consumption cost of each medical result in the medical data to be processed based on the consumption factor model of the medical data to be processed.

[0112] The consumption filtering submodule 705 is used to select the medical result with the highest consumption cost as the primary medical result corresponding to the medical data to be processed.

[0113] In one possible implementation, the consumption calculation submodule 704 is used to calculate the consumption cost of each diagnostic result in the medical record to be processed according to the consumption factor model of the medical record to be processed; the consumption screening submodule 705 is used to select the diagnostic result with the largest consumption cost as the main diagnostic result corresponding to the medical record to be processed.

[0114] In one possible implementation, the consumption factor model is based on a medical knowledge graph and includes the sum of costs for each consumption factor in a medical outcome.

[0115] In one possible implementation, the consumption factor model includes the sum of the costs of each consumption factor in the diagnostic results.

[0116] Figure 8 This is a schematic diagram of a medical data processing apparatus according to another embodiment of the present disclosure, which includes one or more features of the above-described medical data processing apparatus embodiment. In one possible implementation, the apparatus further includes:

[0117] The search module 801 is used to search for standard medical results in the medical knowledge graph based on the feature information in the medical data to be processed and the evidence-based medical cognitive computing method.

[0118] The comparison module 802 is used to compare the cost of the medical items consumed in the standard medical outcome with the cost of the medical items consumed in the actual medical outcome included in the medical data to be processed, in order to determine whether the medical items in the actual medical outcome are reasonable.

[0119] In one possible implementation, the search module 801 is used to search for a standard diagnostic result in a medical knowledge graph based on the feature information in the medical record to be processed and the evidence-based medical cognitive computing method; the comparison module 802 is used to compare the cost of the medical items consumed by the standard diagnostic result with the cost of the medical items consumed by the actual diagnostic result included in the medical record to be processed, so as to determine whether the medical items of the actual diagnostic result are reasonable.

[0120] In one possible implementation, the device further includes:

[0121] The second sending module 803 is used to send the medical consumption result of the medical data to be processed to the client, wherein the medical consumption result includes at least one of the following:

[0122] The recommended ranking of each medical outcome in the medical data to be processed;

[0123] Reasons for recommending major medical outcomes;

[0124] Recommendations for major medical outcomes;

[0125] The percentage of consumption for each medical outcome;

[0126] Unreasonable medical expenses.

[0127] In one possible implementation, the second sending module 803 is configured to send the medical consumption result of the medical record to be processed to the client, the medical consumption result including at least one of the following:

[0128] Recommended ranking of diagnostic results in the pending medical records;

[0129] Reasons for recommending the primary diagnostic result;

[0130] Recommended results for the primary diagnostic findings;

[0131] The percentage of consumption for each diagnostic result;

[0132] Unreasonable medical expenses.

[0133] The specific functions and examples of each module and submodule of the medical data processing device in this disclosure can be found in the relevant descriptions of the corresponding steps in the above medical data processing method embodiments, and will not be repeated here.

[0134] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0135] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0136] In one application scenario, with the increasing use of Diagnosis Related Groups (DRG) and Big Data Diagnosis Intervention (DIP) in public hospital medical insurance payments, the data quality of the medical insurance fund settlement list has a growing impact on DRG / DIP grouping. When filling in clinical diagnoses on the medical insurance fund settlement list, clinicians typically write them according to diagnostic requirements, prioritizing them by etiology, pathological morphology, pathophysiology, complications, and comorbidities. In the context of medical insurance payments, the general principle for selecting the primary diagnosis is that it consumes the most medical resources, poses the greatest threat to the patient's health, and affects the longest hospital stay. Differences in the order of clinical diagnoses and the order of discharge diagnoses can affect the accuracy of primary diagnosis selection, thus impacting DRG / DIP grouping results and leading to payment outcomes that do not accurately reflect the hospital's treatment work.

[0137] Currently, information systems assisting in the selection of the primary diagnosis offer different functions for physicians writing medical records and coders. For example, when a resident physician makes a diagnosis, the definition of the diagnosis and the principles for selecting the primary diagnosis are noted. The coder's coding interface can display relevant coding principles for the diagnosis and possible merged codes for reference. However, this approach is not very helpful for clinicians in selecting the primary diagnosis, and coders often still need to communicate frequently with clinicians.

[0138] Furthermore, the principles for selecting the primary diagnosis will also change due to the DRG / DIP payment rules. Clinicians choosing based on habitual clinical thinking can lead to biases in the selection of the primary diagnosis. If the selection of the primary diagnosis relies heavily on the clinician's subjectivity, we can only remind them of the principles for selecting the primary diagnosis, rather than providing an objective, quantifiable ranking of diagnoses.

[0139] The medical data processing method provided in this disclosure can include a medical record processing method, specifically a primary diagnosis selection method based on knowledge graph-based calculation of consumption factors. A primary diagnosis selection system can be formed based on this method. This primary diagnosis selection method includes: a ranking decision tree model based on specific medical records using a medical knowledge graph, evaluation of the rationality of medical consumption, construction of a medical consumption factor model, and primary diagnosis recommendation ranking, etc. For example, the primary diagnosis selection method of this disclosure can be embedded in hospital medical record systems to help clinicians, coders, etc., fill out medical insurance fund settlement lists.

[0140] Based on medical knowledge graphs, a medical consumption factor model can be provided. This model can associate all the medical consumption of a patient in a medical record with diagnoses through knowledge graph relationships, calculate the diagnosis that consumes the most medical resources, and provide a ranking decision tree based on special medical records (such as obstetrics, oncology, burns, injuries, poisoning, etc.) to assist clinicians in selecting the primary diagnosis.

[0141] See Figure 9Taking a specific type of medical record, such as an inpatient medical record, as an example: First, medical records with a hospital stay of more than 60 days or a total cost of less than 4 yuan are excluded from the grouper. All others are included in the grouper, i.e., records awaiting processing. This filtering rule is only an example and not a demonstration; other rules can also be used as the filtering rules for whether to include a patient in the grouper. The grouping can be DRG (Diagnosis Related Groups). For cases included in the grouper, it is determined whether they meet the set requirements, such as whether they meet the rules of the "Medical Insurance Settlement List Filling Specifications". If so, sorting and / or filtering are performed using a ranking decision tree model based on specific medical records. Specifically, sorting and / or filtering can be performed on special medical records such as injuries, burns, obstetrics, tumors, and poisoning to obtain the primary diagnosis. Otherwise, a reasonable evaluation of medical consumption based on a medical knowledge graph is performed. This requires building a medical consumption factor model and using the medical consumption factor model to filter the primary diagnosis. Finally, a recommended ranking can be performed on the primary diagnoses.

[0142] The following sections will provide detailed information about each part.

[0143] 1. Decision tree model for ranking based on special medical records

[0144] For special medical records, a ranking decision tree model can be established according to the primary diagnosis selection principles required by established requirements, such as the "Medical Insurance Settlement List Filling Specifications." Examples of specific requirements include, but are not limited to: 1) For multiple injuries, select the diagnosis of the most severe injury and / or the primary disease requiring treatment as the primary diagnosis. 2) For multiple burns, select the diagnosis of the most severely burned area as the primary diagnosis. In cases of equal burn severity, select the diagnosis of the area with the largest burn area as the primary diagnosis. 3) For patients with poisoning, select the diagnosis of poisoning as the primary diagnosis. 4) For obstetric cases, the primary diagnosis refers to the major obstetric complications or comorbidities. In cases of delivery without any complications or comorbidities, select O80 or O84 as the primary diagnosis. 5) Special medical records such as tumors.

[0145] See Figure 10 For a specific medical record, the characteristic information of the medical record can be input into the ranking decision tree model, and the ranking decision tree model can make a judgment according to certain rules.

[0146] For example, the ranking decision tree model first determines whether the feature information of the medical record satisfies the priority rule attribute. If the priority rule attribute is satisfied, it then determines whether the feature information of the medical record is injury, burn, poisoning, postpartum, or tumor.

[0147] If the medical record's key information is injury, burn, or poisoning, the ranking decision tree model can select the appropriate diagnosis for each. For multiple injuries, the primary diagnosis is the injury posing the greatest health hazard or the injury requiring primary treatment. For multiple burns, the diagnosis of the most severe burn is the primary diagnosis; among burns of equal severity, the diagnosis of the largest affected area is the primary diagnosis. If the primary purpose is to treat poisoning, poisoning is selected as the primary diagnosis, with other clinical manifestations as the secondary diagnosis. Additionally, drug addiction can also be selected.

[0148] If the medical record's key information indicates a pregnant woman, the ranking decision tree model can further determine whether she was admitted due to complications or comorbidities. If so, the primary diagnosis is selected based on the major obstetric comorbidity or comorbidity. Otherwise, the diagnosis is based on factors such as pregnancy and delivery details, including gestational age, number of fetuses (G), parity (P), fetal position, and fetal and delivery information.

[0149] If the medical record's key characteristic is tumor, the ranking decision tree model can determine if there is a previous diagnosis of this tumor. If there is, it can further determine if there are secondary diagnoses such as metastasis. If secondary diagnoses are present, it can further determine if this diagnosis was confirmed by pathology. If so, the secondary tumor is selected as the primary diagnosis, and the primary tumor as another diagnosis. Otherwise, it can further determine whether radiotherapy or chemotherapy was administered. If radiotherapy or chemotherapy was administered, the malignant tumor radiotherapy or chemotherapy is selected as the primary diagnosis. If radiotherapy or chemotherapy was not administered, it can find the disease (consumption factor) indicated by the doctor's treatment plan and select that disease as the primary diagnosis. If no secondary diagnoses such as metastasis are present, it can further determine if this diagnosis was confirmed by pathology. If so, regardless of whether surgery was performed, tumor can be selected as the primary diagnosis.

[0150] If the ranking decision tree model determines that the feature information of the medical record does not meet the priority rule attributes, it can further determine whether surgery and / or procedures should be performed. If surgery and / or procedures are performed, it can further determine whether there are postoperative complications. Regardless of whether there are, the main surgical procedures can be read, and the discipline to which the surgical procedures belong can be determined. Then, the disease consistent with the surgical treatment can be selected as the primary diagnosis.

[0151] If no surgery and / or procedures are performed, and the treatment is purely medical, it's possible to determine whether the diagnosis at discharge was clear. If unclear, select the reason for admission as the symptom or disease diagnosis (e.g., diagnosis includes a high-priority suspected diagnosis indicated by laboratory tests and treatment plans; disease includes the symptom, sign, or abnormal test results). If clear, the following steps can be taken: extract the diagnosis based on past medical history, chief complaint, and reason for admission (e.g., admitted for reason A with diagnosis B); determine if a new diagnosis has emerged based on the discharge diagnosis minus the admission diagnosis; etiological diagnosis takes precedence over clinical manifestation diagnosis. After extracting the diagnosis based on past medical history, chief complaint, and reason for admission, it's possible to determine if the associated disease type overlaps with the current hospitalization diagnosis. When determining if a new diagnosis has emerged based on the discharge diagnosis minus the admission diagnosis, if yes, in-hospital comorbidities and complications can be identified; otherwise, the original disease can be detected.

[0152] 2. Rationality Evaluation of Medical Consumption Based on Medical Knowledge Graph

[0153] Clinical medical knowledge is processed to generate a medical knowledge graph. Using this knowledge graph and evidence-based cognitive computing technology, reasonable diagnostic results can be searched based on diagnostic features. Combined with the patient's actual consumption, the rationality of medical procedures such as medication, examinations, treatments, consumables, hand anesthesia, and laboratory tests can be automatically determined.

[0154] 3. Construction of a medical consumption factor model

[0155] Except for the special medical records mentioned in point 1, other types of medical records are modeled using a consumption factor model based on a knowledge graph, as shown in the following formula:

[0156] Yi = X1i + X2i + X3i + ... + Xni

[0157] In this formula, the meaning of the variables can include:

[0158] Yi: The total cost of all expenses associated with this diagnosis;

[0159] X1i-Xni: Costs of reasonable medical procedures, including medications, examinations, treatments, consumables, hand anesthesia, and laboratory tests, associated with the diagnosis.

[0160] See Figure 11 Diagnosis A includes medical items A, consumables C, and medical service F; diagnosis B includes medical items B and consumables C; diagnosis C includes medical service D. According to the medical consumption factor model, the cost of diagnosis A is the sum of the costs of drug A, consumables C, and medical service F. The cost of diagnosis B is the sum of the costs of drug B and consumables C. The cost of diagnosis C is the cost of medical service D.

[0161] 4. Ranking of Primary Diagnoses

[0162] For cases meeting the criteria for special medical records, the primary diagnosis is recommended using the primary diagnosis ranking decision tree; for cases not meeting the criteria for special medical records, the diagnosis corresponding to MAX(Yi), i.e., the diagnosis with the highest cost, is recommended as the primary diagnosis. See also Figure 12 On the client side, detection conclusions can be generated based on consumption results and sorting results. For example, a quick delivery of detection conclusions may include:

[0163] Recommended diagnostic order: cerebral infarction, grade 3 hypertension (high risk), gallstones;

[0164] Reason for recommendation: Standardized completion of medical insurance fund settlement statements;

[0165] Recommendation result: Based on the standard procedures for filling out the medical insurance fund settlement statement, cerebral infarction is the primary diagnosis;

[0166] The percentages of each diagnosis were as follows: cerebral infarction 76.69%; grade 3 hypertension (high risk) 10.9%; gallstones 5.03%; general consumption 0%; and unreasonable consumption 7.32%, etc.

[0167] Unreasonable medical expenses: There are two items in total, involving a total medical cost of xx.x yuan.

[0168] Applications and other products developed using this solution can be installed and run independently, or they can be integrated with other systems (such as medical record statistics systems, HQMS systems, electronic medical record systems, DRGs platforms, etc.) to help clinicians, coders, and other personnel fill out medical insurance fund settlement lists. Furthermore, it ensures the continuity of clinical thinking, resulting in better application effectiveness.

[0169] The medical record processing method of this disclosure has one or more of the following effects.

[0170] 1. More complete diagnoses can be found in the medical records.

[0171] It provides automatic extraction of medical record information based on natural language understanding technology, automatically finding the complete set of diagnoses. Based on this, it offers medical record snapshots to clarify the source of diagnostic information.

[0172] 2. The primary diagnosis in the medical record is selected more accurately.

[0173] Based on a complete and accurate diagnosis, the correctness of the primary diagnostic selection is judged according to the consumption relationship.

[0174] 3. Medical records included in the DRG group are of higher quality.

[0175] Avoid inclusion bias caused by incorrect selection of the primary diagnosis.

[0176] Figure 13A schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0177] like Figure 13 As shown, device 1300 includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1302 or a computer program loaded from storage unit 1308 into random access memory (RAM) 1303. The RAM 1303 may also store various programs and data required for the operation of device 1300. The computing unit 1301, ROM 1302, and RAM 1303 are interconnected via bus 1304. Input / output (I / O) interface 1305 is also connected to bus 1304.

[0178] Multiple components in device 1300 are connected to I / O interface 1305, including: input unit 1306, such as keyboard, mouse, etc.; output unit 1307, such as various types of monitors, speakers, etc.; storage unit 1308, such as disk, optical disk, etc.; and communication unit 1309, such as network card, modem, wireless transceiver, etc. Communication unit 1309 allows device 1300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0179] The computing unit 1301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1301 performs the various methods and processes described above, such as medical data processing methods. For example, in some embodiments, the medical data processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1300 via ROM 1302 and / or communication unit 1309. When the computer program is loaded into RAM 1303 and executed by the computing unit 1301, one or more steps of the medical data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 1301 may be configured to perform medical data processing methods by any other suitable means (e.g., by means of firmware).

[0180] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0181] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0182] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0183] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0184] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0185] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0186] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0187] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A medical data processing method, comprising: determining a type of the medical data to be processed according to feature information in the medical data to be processed, wherein the type of the medical data to be processed is determined based on a type range in a set requirement, and the set requirement comprises at least one of a medical specification, a medical rule, a medical regulation and a medical experience; determining a screening manner corresponding to the type of the medical data to be processed, wherein the screening manner corresponding to the type of the medical data to be processed comprises a decision tree manner and / or a medical consumption manner; in a case where the type of the medical data to be processed meets the set requirement, the screening manner corresponding to the type of the medical data to be processed is the decision tree manner, and the decision tree manner is used to select a main medical result from each medical result corresponding to the feature information of the medical data to be processed; in a case where the type of the medical data to be processed does not meet the set requirement, the screening manner corresponding to the type of the medical data to be processed is the medical consumption manner, and the medical consumption manner is used to determine the main medical result according to a consumption cost of each medical result in the medical data to be processed; screening medical results in the medical data to be processed according to the screening manner corresponding to the type of the medical data to be processed.

2. The method of claim 1, further comprising: determining at least one coding information corresponding to the medical data to be processed according to the screened medical results.

3. The method of claim 2, further comprising: sending a coding recommendation result to a client, wherein the coding recommendation result comprises the at least one coding information corresponding to the medical data to be processed.

4. The method of any one of claims 1 to 3, wherein, the screening manner corresponding to the type of the medical data to be processed is the decision tree manner; screening the medical results in the medical data to be processed according to the screening manner corresponding to the type of the medical data to be processed, comprising: inputting the feature information in the medical data to be processed into a decision tree model, and selecting a main medical result from each medical result corresponding to the feature information through the decision tree model, wherein the decision tree model is generated according to a medical result selection manner in a set requirement.

5. The method of claim 4, wherein, the screening manner corresponding to the type of the medical data to be processed is the medical consumption manner; screening the medical results in the medical data to be processed according to the screening manner corresponding to the type of the medical data to be processed, comprising: calculating a consumption cost of each medical result in the medical data to be processed according to a consumption factor model of the medical data to be processed; selecting a medical result with the largest consumption cost as a main medical result corresponding to the medical data to be processed.

6. The method of claim 5, wherein, the consumption factor model is established based on a medical knowledge graph, and the consumption factor model comprises a sum of costs of each consumption factor in the medical result.

7. The method of any one of claims 1 to 6, further comprising: searching for a standard medical result in a medical knowledge graph according to the feature information in the medical data to be processed and an evidence-based medical cognition calculation method. Compare the cost of the medical items consumed by the standard medical result with the cost of the medical items consumed by the actual medical result included in the medical data to be processed to determine whether the medical items of the actual medical result are reasonable.

8. The method of any one of claims 1-7, further comprising: sending, to a client, a medical consumption result of the medical data to be processed, the medical consumption result including at least one of: a ranking recommendation result of each medical result in the medical data to be processed; a recommendation reason of a main medical result; a recommendation result of the main medical result; a consumption proportion of each medical result; unreasonable medical consumption.

9. A medical data processing apparatus, comprising: a first determination module configured to determine a type of the medical data to be processed according to feature information in the medical data to be processed, wherein the type of the medical data to be processed is determined based on a type range in a set requirement, and the set requirement includes at least one of a medical specification, a medical rule, a medical regulation, and a medical experience; a third determination module configured to determine a screening manner corresponding to the type of the medical data to be processed, wherein the screening manner corresponding to the type of the medical data to be processed includes a decision tree manner and / or a medical consumption manner; in a case where the type of the medical data to be processed meets the set requirement, the screening manner corresponding to the type of the medical data to be processed is the decision tree manner, and the decision tree manner is used to select a main medical result from each medical result corresponding to the feature information in the medical data to be processed; in a case where the type of the medical data to be processed does not meet the set requirement, the screening manner corresponding to the type of the medical data to be processed is the medical consumption manner, and the medical consumption manner is used to determine the main medical result according to a consumption cost of each medical result in the medical data to be processed; a screening module configured to screen medical results in the medical data to be processed according to the screening manner corresponding to the type of the medical data to be processed.

10. The apparatus of claim 9, further comprising: a second determination module configured to determine at least one coding information corresponding to the medical data to be processed according to the screened medical results.

11. The apparatus of claim 10, further comprising: a first sending module configured to send a coding recommendation result to a client, wherein the coding recommendation result includes the at least one coding information corresponding to the medical data to be processed.

12. The apparatus of any one of claims 9-11, wherein, The screening manner corresponding to the type of the medical data to be processed is the decision tree manner; and the screening module includes: a decision tree screening submodule configured to input the feature information in the medical data to be processed into a decision tree model, and select a main medical result from each medical result corresponding to the feature information through the decision tree model, wherein the decision tree model is generated according to a medical result selection manner in a set requirement.

13. The apparatus of claim 12, wherein, The screening manner corresponding to the type of the medical data to be processed is the medical consumption manner; and the screening module includes: The consumption calculation sub-module is configured to calculate a consumption cost of each medical result in the to-be-processed medical data according to a consumption factor model of the to-be-processed medical data. The consumption screening sub-module is configured to select a medical result with a maximum consumption cost as a main medical result corresponding to the to-be-processed medical data.

14. The apparatus of claim 13, wherein, The consumption factor model is established based on a medical knowledge graph, and the consumption factor model includes a sum of costs of each consumption factor in the medical result.

15. The apparatus according to any one of claims 9-14, further comprising: The search module is configured to search for a standard medical result in a medical knowledge graph according to feature information in the to-be-processed medical data and a evidence-based medical cognition calculation method. The comparison module is configured to compare a cost of a medical item consumed by the standard medical result with a cost of a medical item consumed by an actual medical result included in the to-be-processed medical data, to determine whether a medical item of the actual medical result is reasonable.

16. The apparatus according to any one of claims 9-15, further comprising: The second sending module is configured to send a medical consumption result of the to-be-processed medical data to a client, and the medical consumption result includes at least one of the following: a sorting recommendation result of each medical result in the to-be-processed medical data; a recommendation reason of the main medical result; a recommendation result of the main medical result; a consumption proportion of each medical result; unreasonable medical consumption.

17. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8. The computer instructions are used to make the computer execute the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, 19. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-8. ​

Images