A medicine information processing method, device, system and equipment

Abstract

Embodiments of the present disclosure relate to the technical field of medical data processing, and particularly relate to a medication information processing method, device, system and equipment. The main steps of the foregoing method include: in response to an audit request of a first prescription including multiple items of medication information initiated by a physician terminal device, obtaining historical medication data of a patient corresponding to the first prescription; when the number of conflict drug groups determined according to a preset knowledge graph, the first prescription and the historical medication data is greater than 1, determining a medication risk value of each conflict drug group according to the obtained drug importance degree data of each conflict drug group, the action intensity data of conflict drug combination and the actual interval data between conflict drugs; determining a comprehensive medication risk value of the first prescription according to the plurality of medication risk values; and feeding back an audit result corresponding to the comprehensive medication risk value to the physician terminal device to release or intercept the first prescription. The foregoing method can improve the audit efficiency and accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of medical data processing technology, and in particular to a method, apparatus, system and computer equipment for processing medication information. Background Technology

[0002] Reviewing medication intervals in prescriptions is a crucial step in ensuring the safety and effectiveness of clinical medication use. Appropriate medication intervals can prevent reduced efficacy or adverse reactions caused by drug interactions. This is especially important during the treatment of cancer drugs, where common adverse drug reactions may occur. Setting appropriate medication intervals and accurately reviewing them is a prerequisite for ensuring safe medication use by patients.

[0003] The current clinical methods for reviewing medication use have the following limitations: 1) Manual review relies too heavily on the pharmacist's personal experience, making it difficult to systematically assess the safety of complex medication use when multiple drugs are used in combination, resulting in low review efficiency and low accuracy; 2) Existing computer review systems mainly focus on the compliance checks of basic elements such as dosage, route of administration, and frequency of administration, lacking the ability to review the time interval between doses, and the review process still carries a high risk. Summary of the Invention

[0004] Therefore, it is necessary to provide a medication information processing method, device, system, and computer equipment that can adapt to multi-drug combination scenarios, has high review efficiency and accuracy, and can effectively reduce the medication risks for patients, in order to address at least one of the above-mentioned technical problems.

[0005] In a first aspect, embodiments of this disclosure provide a medication information processing method applied to an auditing device. The medication information processing method includes the following steps:

[0006] In response to a review request for a first prescription initiated by a physician's terminal device, which includes multiple medication information, historical medication data of the patient corresponding to the first prescription is obtained;

[0007] Based on the pre-defined knowledge graph, the first prescription, and historical medication data, the conflicting drug group is identified;

[0008] When the number of conflicting drug groups is greater than 1, the drug use risk value of each conflicting drug group is determined based on the obtained drug importance data, the effect intensity data of the combined use of conflicting drugs, and the actual interval data between conflicting drugs.

[0009] The overall medication risk value of the first prescription is determined based on multiple medication risk values.

[0010] The review results corresponding to the comprehensive medication risk value are fed back to the physician's terminal device, and the review results indicate whether the first prescription is approved or blocked.

[0011] The first prescription is a prescription that includes multiple medication information. The medication risk value is used to indicate the risk level of using conflicting drug groups. Conflicting drug groups include the target drug information in the first prescription and conflicting drug information that has a conflicting relationship with the target drug in terms of medication interval. The knowledge graph is used to record the conflicting relationships of medication intervals and safe interval data between various types of drugs.

[0012] In some embodiments, importance data is determined by drug type labels recorded in a knowledge graph to represent the importance of drug treatment, effect intensity data is used to represent the degree of adverse effects caused by the combined use of conflicting drugs, and actual interval data is used to represent the comparison between the actual use interval between conflicting drugs and the preset safe interval. The importance data, effect intensity data, and actual interval data are all represented by fuzzy membership degrees.

[0013] The drug use risk value for each conflicting drug group is determined based on drug importance data, effect intensity data, and actual interval data. The steps include: inputting the drug importance membership value, effect intensity membership value, and actual interval membership value of each conflicting drug group into a preset fuzzy inference model to obtain the drug use risk value for each conflicting drug group.

[0014] The fuzzy inference model includes multiple fuzzy rules, which are used to represent the correspondence between different drug importance membership values, effect intensity membership values, actual interval membership values, and drug use risk values.

[0015] In some embodiments, determining the comprehensive medication risk value of a first prescription based on multiple medication risk values ​​includes the following steps: calculating the comprehensive medication risk value by weighted average based on multiple medication risk values ​​and weighting coefficients corresponding to each medication risk value, wherein the weighting coefficients are proportional to the medication risk values.

[0016] In some embodiments, the medication information processing method further includes the following steps: when the number of conflicting drug groups is equal to 1, calculating the actual interval duration of the conflicting drug groups, determining the review result of the first prescription based on the actual interval duration and the corresponding safe interval data in the knowledge graph, and feeding the review result back to the physician's terminal device, wherein the review result indicates whether the first prescription is blocked or released.

[0017] In some embodiments, the medication information processing method further includes the following steps:

[0018] When it is determined that both the target drug information and the conflicting drug information included in the conflicting drug group are drug information in the first prescription, the importance data of the first drug corresponding to the target drug information and the importance data of the second drug corresponding to the conflicting drug information are obtained.

[0019] Based on the importance data of the first drug and the importance data of the second drug, determine the order markers used to indicate the order of use of the target drug and the conflicting drugs;

[0020] The sequence markers and corresponding review suggestions are fed back to the physicians, and the review suggestions are used to prompt adjustments to the medication order.

[0021] In some embodiments, the knowledge graph is also used to record time interval conflict relationships and safe interval durations between various drugs and various clinical procedures.

[0022] The medication information processing method also includes the following steps:

[0023] In response to a second prescription review request initiated by the physician's terminal device, obtain the clinical operation data of the patient corresponding to the second prescription;

[0024] Based on the second prescription, knowledge graph, and clinical operation data, identify the first medication information in the second prescription that conflicts with the clinical operation data;

[0025] Determine the first interval between the first medication information and the corresponding conflicting clinical operational data;

[0026] Based on the first interval duration and the corresponding safe interval duration in the knowledge graph, the review result of the second prescription is determined, and the review result is fed back to the physician's terminal device. The review result is used to indicate whether to intercept or release the second prescription.

[0027] The second prescription is a medication prescription that differs from the first prescription.

[0028] In some embodiments, the knowledge graph is also used to record conflict relationships between various drugs and various clinical test data.

[0029] The medication information processing method also includes the following steps: responding to a review request for a third prescription initiated by the physician's terminal device, obtaining the clinical test data of the patient corresponding to the third prescription; and, based on the third prescription, knowledge graph, and clinical test data, determining that there is second medication information in the third prescription that conflicts with the clinical test data, feeding back the determined review result used to block the third prescription to the physician's terminal device. Here, the third prescription is a medication prescription different from the first prescription.

[0030] In a second aspect, embodiments of this disclosure provide a medication information processing device, which includes a historical medication acquisition module, a conflict drug group determination module, a risk value determination module, a comprehensive risk determination module, and an audit result output module.

[0031] The historical medication acquisition module is used to respond to the review request of the first prescription initiated by the physician's terminal device, which includes multiple medication information, and to obtain the historical medication data of the patient corresponding to the first prescription.

[0032] The conflict drug group identification module is used to identify conflict drug groups based on a preset knowledge graph, the first prescription, and historical medication data.

[0033] The risk value determination module is used to determine the medication risk value of each conflicting drug group when the number of conflicting drug groups identified based on the preset knowledge graph, the first prescription, and historical medication data is greater than 1, based on the obtained importance data, effect intensity data, and interval data of each conflicting drug group.

[0034] The comprehensive risk determination module is used to determine the comprehensive medication risk value of the first prescription based on multiple medication risk values.

[0035] The review result output module is used to feed back the review result corresponding to the comprehensive medication risk value to the physician terminal device in order to approve or block the first prescription.

[0036] Among them, the medication risk value is directly proportional to the risk level of using conflicting drug groups. Conflicting drug groups include information on the target drug in the first prescription and information on conflicting drugs that have a conflicting relationship with the target drug. The knowledge graph is used to record the conflicting relationships and safety interval data of medication intervals between various types of drugs. Importance data represents the efficacy intensity of the drugs, effect intensity data represents the degree of adverse effects of combined use of conflicting drugs, and interval data represents the rationality of the current use interval of conflicting drugs.

[0037] In a third aspect, embodiments of this disclosure provide a prescription review system, which includes a physician-side device, a review-side device, a medical record database, and a knowledge database.

[0038] The physician-side device is used to issue medication prescriptions and initiate review requests for those prescriptions.

[0039] The review device is used to perform the steps of the medication information processing method provided in any embodiment of the first aspect of this disclosure.

[0040] The medical record database is used to store patients' historical medication data, clinical operation data, and clinical test data.

[0041] The knowledge database is used to store knowledge graphs, which record conflict relationships and safety interval data between various drugs, between drugs and clinical operation data, and between drugs and clinical testing data.

[0042] In a fourth aspect, embodiments of this disclosure provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the medication information processing method provided in any embodiment of the first aspect of this disclosure.

[0043] In a fifth aspect, embodiments of the present disclosure provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the medication information processing method provided in any embodiment of the first aspect of the present disclosure.

[0044] The aforementioned medication information processing method, apparatus, system, and computer equipment, in response to the review request of the first prescription, acquire the historical medication data of the patient corresponding to the first prescription, determine conflicting drug groups based on a preset knowledge graph, the first prescription, and the historical medication data, and when the number of conflicting drug groups is greater than 1, determine the medication risk value of each conflicting drug group based on the acquired drug importance data, effect intensity data, and actual interval data, determine the comprehensive medication risk value of the first prescription based on multiple medication risk values, and feed back the review result corresponding to the comprehensive medication risk value to the physician terminal device to allow or block the first prescription. This paper presents a method for automated review of medication intervals between current prescriptions and historical medication data. It is applicable to situations involving multiple conflicting drug groups in multi-drug combination scenarios. In assessing medication risk, in addition to medication interval data, it also incorporates drug importance data and efficacy data, employing multi-dimensional features to jointly evaluate medication risk. This improves both review efficiency and accuracy. Furthermore, by utilizing a knowledge graph that records conflict relationships and safety interval data between various drugs as the basis for review, it can further enhance review efficiency and ensure the timeliness and safety of patient medication. Attached Figure Description

[0045] Figure 1 This is an application environment diagram of the medication information processing method in some embodiments;

[0046] Figure 2 This is a flowchart illustrating the medication information processing method in some embodiments;

[0047] Figure 3 This is a flowchart illustrating the steps involved in determining conflicting drug groups in some embodiments;

[0048] Figure 4 This is a flowchart illustrating the steps of a medication information processing method in some other embodiments;

[0049] Figure 5 This is a flowchart illustrating the steps of a medication information processing method in some other embodiments;

[0050] Figure 6 This is a structural block diagram of the medication information processing device in some embodiments;

[0051] Figure 7 Here are some block diagrams of the prescription review system in some embodiments;

[0052] Figure 8 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0053] To make the technical solutions and advantages of this disclosure clearer, the embodiments and related technical content of this disclosure will be further described in detail below with reference to the accompanying drawings and text description. It should be understood that the embodiments described below are only used to explain the technical solutions of the embodiments of this disclosure and are not intended to limit more possible implementations of this disclosure.

[0054] It should be noted that relational terms such as "first" and "second" appearing in this document are used only to distinguish things, states, or actions, and do not necessarily indicate or imply relative importance or order. The terms "including," "comprising," or any other variations thereof are used to indicate non-exclusive inclusion, and the included objects may not be limited to those listed in this document. The terms "multiple" or other variations are used to indicate that the number of objects is two or more.

[0055] In a first aspect, embodiments of this disclosure provide a method for processing medication information. This method can be applied to, for example... Figure 1 The application environment shown includes an auditing device 101, a physician device 102, a medical record database 103, and a knowledge database 104.

[0056] The review terminal device 101 can be a local electronic device with data processing and analysis functions, or it can be a server cluster deployed in the hospital information system, connected to the physician terminal device 102 through the hospital intranet to provide prescription review services. In some cases, the review terminal device can also be deployed in the cloud, and the physician terminal device 102 can be accessed through a browser or client.

[0057] The physician terminal device 102 can be a computer device with data input, data processing and display functions, for use by physicians. Physicians can use the physician terminal device 102 to complete operations such as prescription issuance and modification. The physician terminal device 102 includes, but is not limited to, computer devices, smartphones, tablets, etc.

[0058] The medical record database 103 can be deployed on local storage hardware, in cloud storage space, or in a hybrid local and cloud deployment. It is used to store patients' medical information, including patients' historical prescriptions, clinical test data, and clinical operation data.

[0059] The knowledge database 104 can be deployed on local storage hardware, in cloud storage space, or in a hybrid local and cloud deployment. It is used to store knowledge graphs, which record conflict relationships and safety interval data between various drugs, between drugs and clinical operation data, and between drugs and clinical testing data.

[0060] Applying medication information processing methods to Figure 1 Taking the review terminal device 101 as an example, in some embodiments, such as Figure 2 As shown, the medication information processing method includes steps S201 to S205 that can be executed by the review terminal device 101. Each step is described in detail below.

[0061] Step S201: In response to the review request for the first prescription, which includes multiple medication information, initiated by the physician terminal device 102, obtain the historical medication data of the patient corresponding to the first prescription.

[0062] The first prescription is a medication prescription issued by a physician for the patient's condition, which includes multiple medication information. Historical medication data includes the patient's past medication information, which may include a list of historical medications, the time of historical medication use, and the dosage of historical medications.

[0063] Specifically, the physician issues the first prescription through the physician terminal device 102 and initiates a review request. In some examples, the display interface of the physician terminal device 102 may include a prescription editing window and a prescription review request control. After the physician performs the corresponding operation, the physician terminal device 102 initiates a review request for the first prescription. The review request may be an automatic request initiated by the physician terminal device 102 when it confirms that the physician has completed issuing the prescription, or it may be a request initiated by the physician through the operation of relevant controls on the physician terminal device 102.

[0064] In response to the review request for the first prescription, the review device 101 retrieves and obtains the historical medication data of the patient corresponding to the first prescription. Specifically, the review device 101 searches the hospital's medical record database based on the patient's identity information in the first prescription, such as the patient's ID number or name, to retrieve the corresponding historical prescription and obtain the historical medication data from the historical prescription.

[0065] In some specific embodiments, obtaining the historical medication data of the patient corresponding to the first prescription may include: retrieving and obtaining historical medication data within the time period requirement range corresponding to the time period requirement information from the medical record database according to preset time period requirement information. The preset time period requirement information can be the interval length that ensures the combined use of drugs. The preset time period requirement information can be set by those skilled in the art according to actual needs, such as 42 days, 56 days, or other durations. Accordingly, historical medication data within the time period requirement range is retrieved according to the preset time period requirement information. Taking a time period requirement of 42 days as an example, historical medication prescriptions within the last 42 days are retrieved from the medical record database to obtain historical medication data. By distinguishing all historical prescriptions in the medical record database according to the prescription issuance time, and only retrieving and obtaining historical medication data within the time period range where there may be conflicts in medication safety intervals, the waste of computing resources in analyzing a large amount of historical medication data can be avoided.

[0066] Step S202: Determine the conflicting drug group based on the preset knowledge graph, the first prescription, and historical medication data.

[0067] The conflicting drug group includes information on the target drug in the first prescription and information on conflicting drugs that conflict with the target drug. The knowledge graph is used to record the dosing interval conflict relationships and safe interval data between various types of drugs. When the actual dosing interval between two classes of drugs with a dosing interval conflict is less than the preset safe interval, there is a risk of reduced efficacy and adverse reactions. The safe interval data represents the safe interval for the combined use of conflicting drugs. When the actual dosing interval between two conflicting drugs is greater than or equal to the safe interval, there is no risk of medication risk when the combined use of the two drugs is used.

[0068] In some specific examples, the pre-set knowledge graph is based on the drug instructions or drug usage guidelines. Drugs with dosing interval conflicts, i.e., drugs with dosing interval requirements, are categorized and presented according to the safe interval length. Taking the drug "Tegafur" as an example, drugs that have a dosing conflict relationship with "Tegafur" include "Fluorouracil Oral Emulsion", "Fluorouracil Powder Injection", and "Fluorouracil", etc., and the safe interval length is 7 days for all of them. Correspondingly, the content associated with "Tegafur" in the knowledge graph is shown in Table 1.

[0069] Table 1: Safety Interval Requirements Between Certain Drugs

[0070]

[0071] The knowledge graph can also include drug information for other Class A drugs and other Class B drugs that have drug conflict relationships with them.

[0072] A pre-built knowledge graph can categorize multiple drugs with the same safety interval, reducing the amount of computer resources required.

[0073] Specifically, based on the preset knowledge graph, the first prescription, and historical medication data, the conflicting drug group is determined; that is, step S202 can be as follows: Figure 3 As shown, it includes steps S301 to S303.

[0074] Step S301: Based on the knowledge graph, determine that the medication information of the first prescription includes the target drug information with required dosing intervals.

[0075] Step S302: Based on the knowledge graph, identify conflicting drug information that has a conflicting relationship with the target drug information from historical medication data or medication information of the first prescription.

[0076] Step S303: Combine the target drug information and conflicting drug information into a conflicting drug group.

[0077] The target drug information in the conflicting drug group comes from the first prescription, and the conflicting drug information comes from historical medication data or the first prescription.

[0078] Step S203: When the number of conflicting drug groups is greater than 1, determine the drug use risk value of each conflicting drug group based on the obtained drug importance data, the effect strength data of combined use of conflicting drugs, and the actual interval data between conflicting drugs.

[0079] If the number of identified conflicting drug groups is greater than 1, it means that there are multiple conflicting drug groups in the drug information included in the first prescription and historical medication data currently being reviewed. This can include the following situations:

[0080] Scenario 1: There is a medication conflict between the target drug information in the first prescription and multiple conflicting drug information in the historical medication data;

[0081] Scenario 2: Multiple target drug information in the first prescription have medication conflict relationships with multiple conflicting drug information in historical medication data;

[0082] Scenario 3: There are medication conflicts between the multiple target drug information in the first prescription.

[0083] In some specific embodiments, drug importance data may refer to the importance data of the target drug from the first prescription within the conflicting drug group. This importance data can be determined by drug type tags recorded in a knowledge graph, representing the therapeutic importance of the drug. For example, drug type tags may include primary, secondary, and tertiary tags with decreasing importance. Primary tags correspond to key drugs that are irreplaceable for disease treatment, possessing high clinical necessity and therapeutic importance, such as life-saving drugs, drugs with narrow therapeutic windows, targeted therapies, or other core therapeutic drugs. Secondary tags correspond to adjunctive or supportive drugs that enhance the efficacy of core treatment, reduce side effects, or control complications, such as analgesics and antiemetics. Tertiary tags correspond to drugs used to relieve symptoms and improve patient quality of life, but without a direct impact on disease treatment, such as nutritional support drugs or topical pain relievers.

[0084] Drug type labels can be recorded as part of drug information in a knowledge graph. The importance of a drug is determined based on its type label. This importance can be represented numerically or by a notation. For example, a numerical range of 0-1 can represent importance, with values ​​less than or equal to 0.3 indicating low importance, values ​​greater than 0.3 and less than or equal to 0.6 indicating medium importance, and values ​​greater than 0.6 and less than or equal to 1 indicating high importance. Alternatively, letters A through C can be used to represent importance, with C indicating low importance, B indicating medium importance, and A indicating high importance.

[0085] Effect intensity data can be recorded in the knowledge graph as part of drug information to represent the degree of adverse effects caused by the combined use of two types of drugs with a drug conflict relationship. In some specific examples, effect intensity data can be represented by numerical values ​​or other symbols. Effect intensity data can be divided into three categories, representing high, medium and low effects in order. When represented by numerical or letter symbols, the representation method is similar to that of the importance level mentioned above, and will not be elaborated here.

[0086] Actual interval data represents the comparison between the actual usage interval between conflicting drugs and the preset safe interval. The safe interval data in the knowledge graph includes the safe interval duration. The actual usage interval duration needs to be determined based on the target drug and the actual usage time of the conflicting drugs in the conflicting drug group. Specifically, the actual usage time of the target drug is determined by the initiation time of its corresponding first prescription. If the prescription to which the conflicting drug belongs is a historical prescription, it is determined by the last usage time of that historical prescription. If the prescription to which the conflicting drug belongs is the currently reviewed first prescription, it is determined by the initiation time of the current first prescription. In some specific examples, actual interval data can be represented by numerical values ​​or other notations. Actual interval data can include four categories of numerical ranges or notations representing reasonable intervals, long intervals, slightly short intervals, and excessively short intervals. The representation method is similar to that of the importance data mentioned above and will not be elaborated upon here.

[0087] In some specific embodiments, the medication information processing method further includes the steps of: when the number of conflicting drug groups determined based on a preset knowledge graph, a first prescription, and historical medication data is greater than 1, acquiring drug importance data for each conflicting drug group, efficacy data of combined conflicting drugs, and actual interval data between conflicting drugs.

[0088] Specifically, the review device 101 determines the importance label corresponding to the target drug based on the knowledge graph and the target drug information in the conflict drug group, determines the importance data based on the importance label, determines the effect strength data of the conflict drug group based on the knowledge graph, calculates the actual usage interval between the target drug and the conflict drug in the conflict drug group, and determines the actual interval data based on the actual usage interval and the safe interval recorded in the knowledge graph.

[0089] The drug use risk value for each conflicting drug group is determined based on data on the importance of drugs in each conflicting drug group, the intensity of action of combined conflicting drugs, and the actual interval between conflicting drugs.

[0090] Medication risk values ​​can be expressed numerically or using labels. They represent the degree of risk associated with the use of conflicting drug groups. When expressed numerically, the risk value is directly proportional to the level of risk. Different numerical ranges represent different levels of risk. When expressed using labels, three categories of labels can be included, representing high risk, medium risk, and low risk.

[0091] When importance data, efficacy data, actual interval data, and medication risk value are all expressed numerically, the medication risk value can be determined using a preset numerical calculation formula. When importance data, efficacy data, actual interval data, and medication risk value are all expressed using labels, the medication risk value can be determined according to a preset reference table or risk rule. The preset reference table and risk rule are used to record the correspondence between importance data, efficacy data, actual interval data, and medication risk value.

[0092] Step S204: Determine the overall medication risk value of the first prescription based on multiple medication risk values.

[0093] Determining the overall medication risk based on multiple medication risk values ​​can be done using a preset risk calculation formula, a preset overall risk determination rule, or further processing by other models or algorithms.

[0094] The comprehensive risk value of medication can be expressed in numerical, symbolic, or other forms, and can include three categories: high risk, medium risk, and low risk.

[0095] No particular limitations are made here regarding the range of numerical intervals, number of numerical intervals, and label type or number of label types for drug risk values, comprehensive risk values, importance data, effect intensity data, and actual interval data. Those skilled in the art can set these according to actual needs.

[0096] Step S205: Feed back the review result corresponding to the comprehensive medication risk value to the physician terminal device 101. The review result is used to indicate whether to approve or block the first prescription.

[0097] Specifically, the review result is determined based on the comprehensive medication risk value, and the review result is output. In some specific examples, the review result may include a first result indicating approval and a second result indicating rejection. The first result is used to indicate that the first prescription is approved, and the second result is used to indicate that the first prescription is rejected. Taking the comprehensive medication risk value as a numerical range as an example, when the comprehensive medication risk value is greater than or equal to 0.6, it indicates that the first prescription has a medication risk, and the corresponding review result is the second result indicating that the review is rejected. The second result is output to indicate that the first prescription is rejected.

[0098] The review results can be displayed as a pop-up window on the display interface of the physician's terminal device 102, or in the corresponding prescription review result display window on the display interface of the physician's terminal device 102.

[0099] In the aforementioned medication information processing method, in response to the review request of the first prescription, the historical medication data of the patient corresponding to the first prescription is obtained. Conflicting drug groups are determined based on a preset knowledge graph, the first prescription, and the historical medication data. When the number of conflicting drug groups is greater than one, the medication risk value of each conflicting drug group is determined based on the obtained drug importance data, effect intensity data, and actual interval data. The comprehensive medication risk value of the first prescription is determined based on multiple medication risk values, and the review result corresponding to the comprehensive medication risk value is fed back to the physician's terminal device to allow or block the first prescription. This provides a method for automated review of medication intervals between the current prescription and historical medication data, and is applicable to situations with multiple conflicting drug groups in multi-drug combination scenarios. In assessing medication risk, in addition to the medication time interval, drug importance data and effect intensity data are also combined, employing multi-dimensional features to jointly assess medication risk, improving both review efficiency and accuracy. Furthermore, using a knowledge graph that records conflict relationships and safety interval data between various drugs as the review basis further improves review efficiency and ensures the timeliness and safety of patient medication.

[0100] In some embodiments, importance data is determined by drug type labels recorded in a knowledge graph to indicate the importance of drug treatment, effect intensity data indicates the degree of adverse effects caused by the combined use of conflicting drugs, and actual interval data indicates the comparison between the actual use interval between conflicting drugs and the preset safe interval.

[0101] In some specific embodiments, importance data, effect intensity data, and actual interval data can all be represented using fuzzy membership degrees. In some specific examples, the fuzzy set of importance data is defined as: \(I=\{I_{low},I_{medium},I_{high}\}\), where \(I_{low}\) represents low importance, \(I_{medium}\) represents medium importance, and \(I_{high}\) represents high importance. Importance values ​​can be assigned to various drugs based on their therapeutic significance. For example, key drugs that are irreplaceable in the treatment of diseases, such as life-saving drugs, drugs with a narrow therapeutic window, targeted drugs, or other core treatment drugs, are assigned a value close to \(I_{high}\). Adjunctive or supportive drugs that enhance the efficacy of core treatments, reduce side effects, or control complications, such as analgesics and antiemetics, are assigned a value of \(I_{medium}\). Drugs used to relieve symptoms and improve the patient's buffer quality but have no direct impact on the treatment of the disease, such as nutritional support drugs and topical preparations for relieving patient pain, are assigned a value of \(I_{low}\).

[0102] The fuzzy set of drug efficacy data is defined as: \(S=\{S_{weak},S_{medium},S_{strong}\}\), where \(S_{weak}\) represents low efficacy, \(S_{medium}\) represents medium efficacy, and \(S_{strong}\) represents high efficacy. Based on relevant literature and data from pharmacological studies and clinical statistics, the degree of adverse effects of combined use of conflicting drugs can be determined, efficacy values ​​can be assigned to various drugs, and these values ​​can be recorded in a knowledge graph.

[0103] The set of actual interval data is defined as: \(R=\{R_{very-short},R_{short},R_{reasonable},R_{long}\}\), where \({R_{very-short}\) indicates an interval that is too short, \(R_{short}\) indicates an interval that is slightly short, \(R_{reasonable}\) indicates an interval that is reasonable, and \(R_{long}\) indicates an interval that is long. The actual interval data is assigned a value by comparing the calculated actual usage interval between conflicting drugs with the preset safe interval.

[0104] In some embodiments, determining the drug use risk value corresponding to each conflicting drug group based on drug importance data, effect intensity data, and actual interval data includes the following steps: inputting the drug importance membership value, effect intensity membership value, and actual interval membership value of each conflicting drug group into a preset fuzzy inference model to obtain the drug use risk value of each conflicting drug group.

[0105] The fuzzy inference model includes multiple fuzzy rules, which are used to represent the correspondence between different drug importance membership values, effect intensity membership values, actual interval membership values, and drug use risk values.

[0106] In some specific examples, the multiple fuzzy rules included in the fuzzy inference model can be as shown in Table 2.

[0107] Table 2: Examples of Some Fuzzy Rules

[0108]

[0109] By using fuzzy membership degrees to represent the drug importance data, effect intensity data, and actual interval data that determine the drug risk value, and inputting the corresponding fuzzy membership degree values ​​into a preset fuzzy inference model, the mathematical verification model of fuzzy logic can be used to conduct rigorous theoretical verification of prescriptions for multiple drug combinations, thereby improving the accuracy of prescription review results and enhancing medication safety.

[0110] In some embodiments, step S204 may include the following steps: calculating a comprehensive medication risk value by weighted average based on multiple medication risk values ​​and weighting coefficients corresponding to each medication risk value, wherein the weighting coefficients are proportional to the medication risk values.

[0111] Specifically, the higher the level of medication risk represented by the medication risk value, the larger the corresponding weighting coefficient. For example, the weighting coefficient for a high-risk medication risk value can be 0.8, the weighting coefficient for a medium-risk medication risk value can be 0.5, and the weighting coefficient for a low-risk medication risk value can be 0.2.

[0112] In some examples of using fuzzy inference models to determine medication risk values, different fuzzy rules can be assigned different weights \(w_i\). For example, the weight \(w_1\) of rule 1 can be set to a higher value (e.g., 0.8) because situations involving highly important drugs, strong interactions, and extremely unreasonable intervals have a significant impact on patient safety; the weight \(w_2\) of rule 2 is set to a moderate value (e.g., 0.5); and the weight \(w_3\) of rule 3 is set to a lower value (e.g., 0.2). The comprehensive medication risk value can be calculated using a weighted average method: \(D=\frac{\sum_{i=1}^{n}w_i\ti mes\mu_{output-i}}{\sum_{i=1}^{n}w_i}\), where \(\mu_{output-i}\) is the fuzzy set membership degree of the output of rule \(i\). Based on the output fuzzy set membership degree, the corresponding comprehensive medication risk value is determined.

[0113] In some embodiments, step S204 may include the following steps: when there is a medication risk value among the multiple medication risk values ​​that indicates a high level of medication risk, the high-risk medication risk value is taken as the comprehensive medication risk value; when there is no medication risk value among the multiple medication risk values ​​that indicates a high level of medication risk, the average value of the multiple medication risk values ​​is taken as the comprehensive medication risk value.

[0114] In some embodiments, the medication information processing method further includes the following steps:

[0115] When the number of conflicting medicine groups is equal to 1, calculate the actual interval duration of the conflicting medicine groups;

[0116] Based on the actual interval duration and the corresponding safety interval data in the knowledge graph, the review result of the first prescription is determined, and the review result is fed back to the physician terminal device 101. The review result indicates whether the first prescription is intercepted or released.

[0117] Specifically, the number of conflicting drug groups is 1, indicating that there is only one target drug in the first prescription currently being reviewed that conflicts with other drugs in terms of dosing interval. The actual interval between the target drug and the conflicting drug is calculated, and the review result of the first prescription is determined and output based on the actual interval and the safe interval for the conflicting drug group recorded in the knowledge graph.

[0118] When the actual interval duration is greater than or equal to the safe interval duration recorded in the knowledge graph, a first result indicating that the review has been approved is determined and output to indicate that the first prescription has been released. When the actual interval duration is less than the safe interval duration recorded in the knowledge graph, a second result indicating that the review has not been used is determined and output to indicate that the first prescription has been blocked.

[0119] In some specific embodiments, when the review result is a second result indicating that the review has not passed, the reason for the review failure is also output to the physician terminal device 101 to provide prescription modification suggestions.

[0120] In some embodiments, such as Figure 4 As shown, the medication information processing method may further include steps S401 to S403.

[0121] Step S401: When it is determined that both the target drug information and the conflicting drug information included in the conflicting drug group are drug information in the first prescription, obtain the first drug importance data corresponding to the target drug information and the second drug importance data corresponding to the conflicting drug information.

[0122] Specifically, the target drug information and conflicting drug information included in the conflicting drug group are both drug information in the first prescription, indicating that multiple drug information in the currently reviewed first prescription have conflicting dosing intervals. The review terminal device 101 can determine whether the target drug information and conflicting drug information come from the first prescription or from historical medication data by judging the source markers. It then retrieves the target drug information and conflicting drug information from the preset knowledge graph to determine the importance data of the first drug and the importance data of the second drug.

[0123] Step S402: Based on the importance data of the first drug and the importance data of the second drug, determine the order markers used to indicate the order of use of the target drug and the conflicting drugs.

[0124] The sequence markers include a first marker indicating priority of the target drug and a second marker indicating priority of conflicting drugs. Drugs with relatively higher drug importance are prioritized for use. When the drug importance represented by the first drug importance data is higher than the drug importance represented by the second drug importance data, the determined sequence marker is the first marker. When the drug importance represented by the first drug importance data is lower than the drug importance represented by the second drug importance data, the determined sequence marker is the second marker.

[0125] Step S403: Feed back the review suggestions corresponding to the sequence markers to the physician terminal device 101. The review suggestions are used to prompt adjustments to the medication order.

[0126] Specifically, based on the sequence markers and the medication order indicated by the drug information in the current first prescription, an audit recommendation is determined. When the medication order indicated by the drug information in the first prescription differs from the medication order corresponding to the sequence markers, the audit recommendation is used to suggest adjusting the medication order of the target drug and conflicting drugs. The audit recommendation can be output along with the audit result of the first prescription, and the output method is consistent with the audit result.

[0127] By comparing the importance of multiple drugs that conflict in the same prescription, determining the order of rational drug use based on their importance, and outputting the corresponding review suggestions, physicians can be provided with a reference for adjusting the order of drug use, thereby improving the safety of prescription use and the efficiency of prescription modification.

[0128] In some embodiments, the knowledge graph is also used to record time interval conflict relationships and safe interval durations between various drugs and various clinical procedures.

[0129] There are time interval conflicts between various drugs and various clinical procedures, indicating that there are required intervals between drug administration and clinical procedures. If the interval is shorter than the safe interval, the drug efficacy may be reduced or adverse clinical reactions may occur. In some specific examples, the conflict relationships and safe intervals between some drugs and clinical procedures recorded in the knowledge graph can be shown in Table 3.

[0130] Table 3: Safety Interval Requirements for Certain Drugs and Clinical Procedures

[0131]

[0132]

[0133] like Figure 5 As shown, the medication information processing method further includes steps S501 to S504.

[0134] Step S501: In response to the review request for the second prescription initiated by the physician terminal device 102, obtain the clinical operation data of the patient corresponding to the second prescription.

[0135] The second prescription is a medication prescription different from the first prescription. The review request for the second prescription initiated by the physician's device is initiated in the same way as the review request for the first prescription, and will not be repeated here. The review device 101 obtains the clinical operation data of the patient corresponding to the second prescription. The clinical operation data includes surgical scheduling data and historical surgical record data. In some specific examples, the review device 101 obtains the patient's clinical operation data from the hospital's system or database storing clinical operation data based on the patient's identity information in the second prescription. In some cases, this may be obtained from the hospital's surgical system or hospital information management system.

[0136] Step S502: Based on the second prescription, knowledge graph, and clinical operation data, determine the first medication information in the second prescription that conflicts with the clinical operation data.

[0137] Extract medication information from the second prescription, search and match it in the knowledge graph to determine if there is any first medication information that conflicts with clinical operation data.

[0138] Step S503: Determine the first interval between the first medication information and the corresponding conflicting clinical operation data.

[0139] The corresponding conflicting clinical operation data is called conflict operation data. The first interval duration is determined based on the time of the second prescription and the time of the conflict operation data.

[0140] Step S504: Based on the first interval duration and the corresponding safe interval duration in the knowledge graph, determine the review result of the second prescription and feed the review result back to the physician terminal device 101. The review result is used to indicate whether to intercept or release the second prescription.

[0141] The review results can include a first result indicating that the review has passed and a second result indicating that the review has failed. The first interval duration is compared with the corresponding safety interval duration. If the first interval duration is greater than or equal to the corresponding safety interval duration, the first result is determined and output to allow the second prescription to proceed. If the first interval duration is less than the corresponding safety interval duration, the second result is determined and output to block the second prescription.

[0142] By intercepting second prescriptions that conflict with current medications (insufficient interval) in future surgical scheduling or historical surgical records, and prompting physicians to make modifications, a method for reviewing the time interval between medication and clinical operation data is provided, ensuring medication safety.

[0143] In some embodiments, the knowledge graph is also used to record conflict relationships between various drugs and various clinical test data.

[0144] The existence of conflicting relationships between various drugs and clinical test data indicates that when the clinical test data is within a preset abnormal range, there is a risk of using the specific drug with the conflicting relationship, such as reduced efficacy or adverse clinical reactions.

[0145] The medication information processing method may also include the following steps: in response to a review request for a third prescription initiated by the physician terminal device 102, obtaining the clinical test data of the patient corresponding to the third prescription; and when it is determined, based on the third prescription, knowledge graph and clinical test data, that there is second medication information in the third prescription that conflicts with the clinical test data, feeding back the determined review result used to intercept the third prescription to the physician terminal device.

[0146] The third prescription is a medication prescription that differs from the first prescription. The patient's clinical test data can be stored in the hospital's medical record database or information management system, or in the hospital's laboratory system.

[0147] When a second medication information exists in a third prescription that conflicts with clinical test data, a second review result is identified and output to intercept the third prescription, thus improving the security of medication prescriptions.

[0148] In some embodiments, the medication information processing method may further include the following steps:

[0149] In response to the review request for the fourth prescription initiated by the physician terminal device 102, the system obtains the patient's historical medication data, clinical operation data, and clinical test data corresponding to the fourth prescription.

[0150] If, in the fourth prescription determined by the knowledge graph, the actual interval between the third medication information and the corresponding conflicting historical medication information is less than the corresponding safe interval, a second result indicating that the review has failed is output to block the fourth prescription; or,

[0151] If the actual interval between the fourth prescription determined by the knowledge graph and the corresponding conflicting clinical operation data is less than the corresponding safe interval, a second result indicating that the review has failed is output to block the fourth prescription; or,

[0152] When the fifth medication information in the fourth prescription determined by the knowledge graph conflicts with the clinical test data, a second result indicating that the review has not been approved is output to block the fourth prescription.

[0153] In some embodiments, if there are multiple medication conflicts in the first prescription currently being reviewed, the relevant information on the multiple medication conflicts will be output in the review results to prompt for prescription modification.

[0154] In some embodiments, the medication information processing method further includes storing prescription information and review result information that failed the review into a preset interception log database for statistical analysis of the distribution of departments or physicians with violations and the distribution of violation types.

[0155] By storing prescription information and review results that fail the review into a pre-defined interception log database for classification and statistical analysis, it can provide optimization guidance for subsequent updates to the prescription review process and provide data support for hospital department or physician evaluations.

[0156] It should be understood that, although Figure 2-5 The steps in the flowchart are shown sequentially according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Figure 2-5 Unless otherwise expressly stated herein, the steps illustrated and other steps involved in the embodiments are not subject to strict order restrictions and may be performed in other orders. Furthermore, at least some steps in the foregoing embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0157] In a second aspect, embodiments of this disclosure provide a medication information processing device, such as... Figure 6 As shown, the medication information processing device 600 includes: a historical medication acquisition module 610, a conflict drug group determination module 620, a risk value determination module 630, a comprehensive risk determination module 640, and an audit result output module 650.

[0158] The historical medication acquisition module 610 is used to respond to the review request of the first prescription initiated by the physician terminal device, which includes multiple medication information, and to acquire the historical medication data of the patient corresponding to the first prescription.

[0159] The conflict drug group identification module 620 is used to identify conflict drug groups based on a preset knowledge graph, the first prescription, and historical medication data.

[0160] The risk value determination module 630 is used to determine the medication risk value of each conflicting drug group based on the obtained importance data, effect intensity data and interval data of each conflicting drug group when the number of conflicting drug groups determined according to the preset knowledge graph, the first prescription and historical medication data is greater than 1.

[0161] The comprehensive risk determination module 640 is used to determine the comprehensive medication risk value of the first prescription based on multiple medication risk values.

[0162] The review result output module 650 is used to feed back the review result corresponding to the comprehensive medication risk value to the physician terminal device to approve or block the first prescription.

[0163] The first prescription is a prescription that includes multiple medication information. The medication risk value is directly proportional to the risk level of using conflicting drug groups. Conflicting drug groups include the target drug information in the first prescription and conflicting drug information that has a conflicting relationship with the target drug. The knowledge graph is used to record the conflicting relationships and safety interval data between various drugs. The importance data represents the efficacy intensity of the drug, the effect intensity data represents the degree of adverse effects of using conflicting drugs in combination, and the interval data represents the rationality of the current interval of use of conflicting drugs.

[0164] In some embodiments, importance data is determined by drug type labels recorded in a knowledge graph to represent the importance of drug treatment, effect intensity data is used to represent the degree of adverse effects caused by the combined use of conflicting drugs, and actual interval data is used to represent the comparison between the actual use interval between conflicting drugs and the preset safe interval. The importance data, effect intensity data, and actual interval data are all represented by fuzzy membership degrees.

[0165] The risk value determination module 630 includes a fuzzy model running unit, which is used to input the drug importance membership value, effect intensity membership value and actual interval membership value of each conflicting drug group into a preset fuzzy inference model to obtain the drug use risk value of each conflicting drug group.

[0166] The fuzzy inference model includes multiple fuzzy rules, which are used to represent the correspondence between different drug importance membership values, effect intensity membership values, actual interval membership values, and drug use risk values.

[0167] In some embodiments, the comprehensive risk determination module 640 includes a weighted calculation unit for calculating a comprehensive medication risk value by weighting an average of multiple medication risk values ​​and weighting coefficients corresponding to each medication risk value. The weighting coefficients are proportional to the medication risk values.

[0168] In some embodiments, the medication information processing device 600 further includes an actual interval calculation module for calculating the actual interval duration of conflicting drug groups when the number of conflicting drug groups is equal to 1.

[0169] The review result output module 650 is also used to determine the review result of the first prescription based on the actual interval duration and the corresponding safety interval data in the knowledge graph, and to feed the review result back to the physician's terminal device. The review result indicates whether the first prescription is blocked or released.

[0170] In some embodiments, the medication information processing device 600 further includes a medication order determination module, which is used to obtain first drug importance data corresponding to the target drug information and second drug importance data corresponding to the conflicting drug information when it is determined that the target drug information and the conflicting drug information included in the conflicting drug group are both drug information in the first prescription, and to determine an order mark for representing the order of use of the target drug and the conflicting drug based on the first drug importance data and the second drug importance data.

[0171] The review result output module 650 is also used to feed back the review suggestions corresponding to the sequence markers to the physician's terminal device. The review suggestions are used to prompt adjustments to the medication order.

[0172] In some embodiments, the knowledge graph is also used to record conflict relationships and safe intervals between various drugs and various clinical procedures.

[0173] The medication information processing device 600 also includes a clinical data acquisition module, a conflict determination module, and a duration determination module.

[0174] The clinical data acquisition module is used to respond to the review request of the second prescription initiated by the physician's terminal device and acquire the clinical operation data of the patient corresponding to the second prescription, wherein the second prescription is a medication prescription different from the first prescription.

[0175] The conflict determination module is used to identify the first medication information in the second prescription that conflicts with the clinical operation data, based on the second prescription, knowledge graph, and clinical operation data.

[0176] The duration determination module is used to determine the first interval duration between the first medication information and the corresponding conflicting clinical operation data.

[0177] The review result output module 650 is also used to determine the review result of the second prescription based on the first interval duration and the corresponding safe interval duration in the knowledge graph, and to feed the review result back to the physician terminal device. The review result indicates whether the second prescription is blocked or released.

[0178] In some implementation sets, knowledge graphs are also used to record conflicting relationships between various drugs and clinical test data.

[0179] The medication information processing device 600 also includes a clinical laboratory data acquisition module, which is used to respond to the review request of a third prescription initiated by the physician's terminal device and acquire the clinical laboratory data of the patient corresponding to the third prescription.

[0180] The third prescription is a medication prescription that differs from the first prescription.

[0181] The audit result output module 650 is also used to feed back the audit result used to block the third prescription to the physician's device when it is determined that there is second medication information in the third prescription that conflicts with the clinical test data, based on the third prescription, knowledge graph and clinical test data.

[0182] For further specific limitations regarding the medication information processing device 600, please refer to the limitations of the medication information processing method described above. The medication information processing device can also be used to execute further steps of the medication information processing method in the embodiments of this disclosure, which will not be repeated here. Each module in the above-described medication information processing device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0183] In a third aspect, embodiments of this disclosure provide a prescription review system, such as Figure 7 As shown, the prescription review system 700 includes a physician terminal device 710, a review terminal device 720, a medical record database 730, and a knowledge database 740.

[0184] The physician-side device 710 is used to issue medication prescriptions and initiate review requests for those prescriptions.

[0185] The review device 720 is used to perform the steps of the medication information processing method provided in any embodiment of the first aspect of this disclosure.

[0186] The medical record database 730 is used to store patients' historical medication data, clinical operation data, and clinical test data.

[0187] Knowledge database 740 is used to store knowledge graphs, which record conflict relationships and safety interval data between various drugs, between drugs and clinical operation data, and between drugs and clinical testing data.

[0188] In a fourth aspect, embodiments of this disclosure provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the medication information processing method provided in any embodiment of the first aspect of this disclosure.

[0189] In some embodiments, the computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores prescription review results. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements the medication information processing method in any embodiment of this document.

[0190] Those skilled in the art will understand that Figure 8 The structures shown are merely block diagrams of some structures related to the embodiments of this disclosure and do not constitute a limitation on the computer devices to which the embodiments of this disclosure are applied. Specific computer devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0191] In a fifth aspect, embodiments of the present disclosure provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the medication information processing method provided in any embodiment of the first aspect of the present disclosure.

[0192] The computer-readable storage medium may be Figure 8 The non-volatile storage medium in the computer device shown.

[0193] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The aforementioned computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments of this disclosure can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0194] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this disclosure.

[0195] The above embodiments merely illustrate several implementation methods of this disclosure, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of protection of this disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the appended claims.

Claims

1. A method for processing medication information, characterized in that, Applied to an auditing device, the method includes: In response to a review request for a first prescription initiated by a physician's terminal device, which includes multiple medication information, historical medication data of the patient corresponding to the first prescription is obtained; Based on the preset knowledge graph, the first prescription, and the historical medication data, conflicting drug groups are identified. When the number of conflicting drug groups is greater than 1, the medication risk value of each conflicting drug group is determined based on the obtained drug importance data, the effect intensity data of combined conflicting drugs, and the actual interval data between conflicting drugs. The medication risk value is used to represent the degree of risk of using conflicting drug groups. Based on multiple medication risk values, determine the comprehensive medication risk value of the first prescription; The review result corresponding to the comprehensive medication risk value is fed back to the physician's terminal device, and the review result indicates whether to approve or block the first prescription; The conflicting drug group includes information on the target drug in the first prescription and information on conflicting drugs that have a conflicting relationship with the target drug in terms of dosing interval. The knowledge graph is used to record the conflicting relationships of dosing intervals and safe interval data between various types of drugs. The importance data is determined by the drug type labels recorded in the knowledge graph and is used to represent the importance of drug treatment. The effect intensity data is used to represent the degree of adverse effects caused by the combined use of conflicting drugs. The actual interval data is used to represent the comparison result between the actual use interval between conflicting drugs and the preset safe interval. The importance data, the effect intensity data, and the actual interval data are all represented by fuzzy membership degree. The determination of the medication risk value for each conflicting drug group based on the obtained drug importance data, drug combination efficacy data, and actual interval data between conflicting drugs includes: The importance membership value, efficacy membership value, and actual interval membership value of each conflicting drug group are input into a preset fuzzy inference model to obtain the drug use risk value of each conflicting drug group. The fuzzy inference model includes multiple fuzzy rules, which are used to represent the correspondence between different drug importance membership values, effect intensity membership values, actual interval membership values, and drug use risk values. The step of determining the comprehensive medication risk value of the first prescription based on multiple medication risk values ​​includes: The comprehensive medication risk value is calculated by weighted average based on the multiple medication risk values ​​and the weighting coefficients corresponding to each medication risk value, wherein the weighting coefficients are proportional to the medication risk values.

2. The method according to claim 1, characterized in that, The method further includes: When the number of conflicting drug groups is equal to 1, calculate the actual interval duration of the conflicting drug groups; Based on the actual interval duration and the corresponding safety interval data in the knowledge graph, the review result of the first prescription is determined, and the review result is fed back to the physician terminal device. The review result indicates whether the first prescription is blocked or released.

3. The method according to claim 1, characterized in that, The method further includes: When it is determined that both the target drug information and the conflicting drug information included in the conflicting drug group are drug information in the first prescription, the first drug importance data corresponding to the target drug information and the second drug importance data corresponding to the conflicting drug information are obtained; Based on the importance data of the first drug and the importance data of the second drug, determine the order markers used to indicate the order of use of the target drug and the conflicting drugs; The review suggestions corresponding to the sequence markers are fed back to the physician's terminal device, and the review suggestions are used to prompt adjustments to the medication order.

4. The method according to claim 1, characterized in that, The knowledge graph is also used to record time interval conflict relationships and safe interval durations between various drugs and various clinical procedures; The method further includes: in response to a review request for a second prescription initiated by the physician terminal device, obtaining clinical operation data of the patient corresponding to the second prescription, wherein the second prescription is a medication prescription different from the first prescription; Based on the second prescription, the knowledge graph, and the clinical operation data, determine the first medication information in the second prescription that conflicts with the clinical operation data; Determine the first interval between the first medication information and the corresponding conflicting clinical operation data; Based on the first interval duration and the corresponding safe interval duration in the knowledge graph, the review result of the second prescription is determined, and the review result is fed back to the physician's terminal device. The review result is used to indicate whether to intercept or release the second prescription.

5. The method according to claim 1, characterized in that, The knowledge graph is also used to record conflicting relationships between various drugs and various clinical test data; The method further includes: in response to a review request for a third prescription initiated by the physician terminal device, obtaining clinical test data of the patient corresponding to the third prescription, wherein the third prescription is a medication prescription different from the first prescription; When it is determined, based on the third prescription, the knowledge graph, and the clinical test data, that there is second medication information in the third prescription that conflicts with the clinical test data, the determined review result for intercepting the third prescription is fed back to the physician's terminal device.

6. A medication information processing device, characterized in that, The device includes: The historical medication acquisition module is used to respond to the review request of the first prescription, which includes multiple medication information, initiated by the physician's terminal device, and to acquire the historical medication data of the patient corresponding to the first prescription; The conflicting drug group determination module is used to determine conflicting drug groups based on a preset knowledge graph, the first prescription, and the historical medication data. The risk value determination module is used to determine the medication risk value of each conflicting drug group based on the obtained importance data, efficacy data and actual interval data of each conflicting drug group when the number of conflicting drug groups is greater than 1, wherein the medication risk value is directly proportional to the risk level of using the conflicting drug group; The comprehensive risk determination module is used to determine the comprehensive medication risk value of the first prescription based on multiple medication risk values; The review result output module is used to feed back the review result corresponding to the comprehensive medication risk value to the physician terminal device, and the review result indicates whether to approve or block the first prescription; The conflicting drug group includes information on the target drug in the first prescription and information on conflicting drugs that have a conflicting relationship with the target drug. The knowledge graph is used to record the conflicting relationships of medication intervals and safety interval data among various types of drugs. The importance data is determined by the drug type labels recorded in the knowledge graph and is used to represent the importance of drug treatment. The effect intensity data is used to represent the degree of adverse effects caused by the combined use of conflicting drugs. The actual interval data is used to represent the comparison result between the actual use interval between conflicting drugs and the preset safe interval. The importance data, the effect intensity data, and the actual interval data are all represented by fuzzy membership degree. The determination of the medication risk value for each conflicting drug group based on the obtained drug importance data, drug combination efficacy data, and actual interval data between conflicting drugs includes: The importance membership value, efficacy membership value, and actual interval membership value of each conflicting drug group are input into a preset fuzzy inference model to obtain the drug use risk value of each conflicting drug group. The fuzzy inference model includes multiple fuzzy rules, which are used to represent the correspondence between different drug importance membership values, effect intensity membership values, actual interval membership values, and drug use risk values. The step of determining the comprehensive medication risk value of the first prescription based on multiple medication risk values ​​includes: The comprehensive medication risk value is calculated by weighted average based on the multiple medication risk values ​​and the weighting coefficients corresponding to each medication risk value, wherein the weighting coefficients are proportional to the medication risk values.

7. A prescription review system, characterized in that, The system includes physician-side devices, review-side devices, a medical record database, and a knowledge database; The physician-side device is used to issue medication prescriptions and initiate review requests for the medication prescriptions. The auditing terminal device is used to perform the steps of the method according to any one of claims 1 to 5; The medical record database is used to store patients' historical medication data, clinical operation data, and clinical test data; The knowledge database is used to store the knowledge graph, which records the conflict relationships and safety interval data between various drugs, between drugs and clinical operation data, and between drugs and clinical test data.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

Images