Medication recommendation method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a medication recommendation method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of computers. According to the method, the diagnosis information of the patient is acquired from the hospital information system, the corresponding medical insurance disease group can be accurately matched, the medical insurance payment standard can be determined, close combination of a medication decision and a medical insurance policy is ensured, and medical insurance payment deviation caused by information asymmetry is avoided. Secondly, the cost interval is determined based on the medical insurance payment standard, the medicine cost of the patient and the preset medicine proportion upper limit, a clear cost reference range is provided for a doctor, the medical cost can be reasonably controlled, and unnecessary medical resource waste is reduced. Moreover, the target drug combination is determined by combining the diagnosis information, the cost interval and the hospital medication scheme database, the normalization and effectiveness of medication are considered, the rationality of the cost is also considered, and the optimal drug combination can be recommended for the patient. And finally, the target drug combination is pushed to a doctor end, so that intelligent decision support is provided for doctors, the standardization and consistency of doctor advices are improved, drug use deviation and medical dispute risks caused by manual selection are reduced, and the overall quality and efficiency of medical services are improved.

Description

Cross-reference to related applications

[0001] This application claims priority to Chinese Patent Application No. 2025115702715, filed on October 30, 2025, entitled “Method, Apparatus, Electronic Device, Storage Medium and Program Product for Medication Recommendation”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of computer technology, and more specifically, to a method, apparatus, electronic device, storage medium, and program product for recommending medication. Background Technology

[0003] In the field of hospital information management, hospital information systems have comprehensively covered core business processes such as prescription writing and drug management, becoming an indispensable basic support for medical activities. However, existing hospital information systems have significant limitations in their technical architecture and functionality in clinical decision support, especially in rational drug use and collaborative control of medical costs, making it difficult to meet the dual needs of modern precision medicine and refined management.

[0004] Currently, when prescribing medications, doctors primarily rely on their personal expertise and clinical experience, along with real-time drug catalogs from hospital pharmacies. While existing systems generally integrate basic auxiliary functions such as drug inventory lookup and prescription contraindication alerts, these functions only address information presentation and risk warnings, failing to penetrate the core aspects of treatment decision-making. For example, in terms of real-time accounting and proactive control of medical costs, current technology is severely out of sync with medical insurance payment policies. Doctors' reliance on personal experience in prescribing leads to the isolation between medication selection and medical insurance payment policies, potentially resulting in fragmented information, low decision-making efficiency, and high bias rates in the prescription process. Summary of the Invention

[0005] The purpose of this application is to provide a medication recommendation method, device, electronic device, storage medium, and program product to improve the problems in the prior art where the medication selection and medical insurance payment policy are isolated when doctors prescribe medication, resulting in fragmented information, low decision-making efficiency, and high deviation rate in the prescription writing process.

[0006] In a first aspect, embodiments of this application provide a method for recommending medication, the method comprising: Obtain patient diagnostic information from the hospital information system; Based on the diagnostic information, the corresponding medical insurance disease group is matched from the disease group database, and the medical insurance payment standard for the medical insurance disease group is determined. Based on the aforementioned medical insurance payment standards, the patient's existing drug costs, and the preset upper limit for drug ratio, the cost range is determined; Based on the diagnostic information, the cost range, and the hospital's medication regimen database, a target drug combination is determined; The target drug combination is then pushed to the doctor's end.

[0007] In the aforementioned implementation process, by obtaining patients' diagnostic information from the hospital information system, the corresponding medical insurance disease groups can be accurately matched and the medical insurance payment standards can be determined, ensuring a close integration of medication decisions and medical insurance policies and avoiding medical insurance payment deviations caused by information asymmetry. Secondly, by determining the cost range based on medical insurance payment standards, the patient's incurred drug costs, and the preset upper limit of drug ratio, a clear cost reference range is provided to doctors, helping to rationally control medical costs and reduce unnecessary waste of medical resources. Furthermore, by combining diagnostic information, cost ranges, and the hospital's medication regimen database to determine the target drug combination, not only is the standardization and effectiveness of medication taken into account, but also the rationality of costs, enabling the recommendation of the optimal drug combination for patients. Finally, the target drug combination is pushed to the doctor's end, providing intelligent decision support, improving the standardization and consistency of medical orders, reducing the risk of medication deviations and medical disputes caused by manual selection, and improving the overall quality and efficiency of medical services.

[0008] Optionally, the hospital medication regimen database is constructed based on clinical medication guidelines and historical hospital medication records.

[0009] In the aforementioned process, clinical medication guidelines provide authoritative guidance, ensuring the scientific rigor and compliance of medication use; hospital historical medication records reflect the hospital's actual medication habits and physicians' clinical experience, making the recommendations more aligned with the hospital's specific circumstances. This combined approach not only improves the accuracy and adaptability of medication regimens but also effectively reduces medication risks caused by individual differences and experience biases, further enhancing the quality and safety of medical services.

[0010] Optionally, the hospital medication regimen database can be constructed in the following manner: Obtain the standard medication regimens in the clinical medication guidelines documents corresponding to different diagnostic information and the hospital's historical medication regimens in the hospital's historical medication records; For the same diagnostic information, assess the reliability of the hospital's historical medication regimens for that diagnostic information based on the standard medication regimens corresponding to that diagnostic information; Based on the reliability level, the hospital's historical medication regimen for this diagnostic information is adjusted to obtain the adjusted hospital medication regimen; The hospital medication regimen database is constructed based on the adjusted hospital medication regimen.

[0011] In the aforementioned implementation process, by combining standard medication regimens from clinical medication guidelines with historical medication regimens from hospital records, and by assessing and adjusting the reliability of these historical regimens, a hospital medication regimen database is constructed with higher accuracy and practicality. This process not only ensures that medication regimens comply with authoritative clinical guidelines but also incorporates the hospital's actual medication practices and physicians' clinical experience, making recommended medication regimens more closely aligned with the hospital's specific practices. This approach effectively improves the scientific rigor and standardization of medication decisions, reduces medication risks caused by experience biases, and simultaneously addresses the personalized needs of healthcare services, thereby enhancing the overall quality and efficiency of healthcare services.

[0012] Optionally, the step of assessing the reliability of the hospital's historical medication regimens based on the standard medication regimens corresponding to the diagnostic information includes: Obtain the standard medications in the standard medication regimen corresponding to the diagnostic information, and obtain the hospital medications in the hospital's historical medication regimen corresponding to the diagnostic information; The reliability of the hospital's historical medication regimens is assessed based on the differences between the hospital's medications and the standard medications.

[0013] In the aforementioned process, the reliability of a hospital's historical medication regimen is assessed by comparing the differences between the standard medications corresponding to the diagnostic information and those used in the hospital's past medication practices. This allows for the accurate identification of deviations between the hospital's actual medication use and authoritative standards. This assessment method helps to promptly identify and correct non-standard medication habits, ensuring the scientific validity and compliance of the hospital's medication regimen. Furthermore, adjustments to the hospital's historical medication regimen based on these assessment results can further optimize hospital medication practices, improve the quality and safety of medical services, reduce medical risks and disputes caused by inappropriate medication, and provide patients with more reliable medical services.

[0014] Optionally, assessing the reliability of the hospital's historical medication regimen based on the differences between the hospital's medications and the standard medications includes: Obtain the frequency of use and clinical efficacy scores of the hospital's medications; The reliability of the hospital's historical medication regimens is assessed based on the differences between the hospital's medications and the standard medications, the frequency of medication use, and the clinical efficacy scores.

[0015] In the aforementioned process, this evaluation method not only focuses on whether the selected drugs meet the standards, but also considers the frequency of drug use and clinical efficacy in actual use, making the evaluation results more comprehensive and objective. Secondly, this comprehensive evaluation method can more accurately reflect the actual application effects of the hospital's historical medication regimens, thus providing a stronger basis for optimizing hospital medication regimens. Finally, hospital medication regimens evaluated and adjusted in this way not only comply with clinical guidelines but also incorporate actual usage, effectively improving the scientific rigor and reliability of medication decisions.

[0016] Optionally, assessing the reliability of the hospital's historical medication regimen based on the differences between the hospital's medications and the standard medications, the frequency of medication use, and the clinical efficacy score includes: The reliability of the hospital's historical medication regimen is obtained by weighting and summing the differences between the hospital's medication and the standard medication, the frequency of medication use, and the clinical efficacy score, wherein the differences are used to characterize the degree of consistency between the hospital's medication and the standard medication.

[0017] In the aforementioned implementation process, this quantitative assessment method comprehensively considers multiple key factors, ensuring the comprehensiveness and objectivity of the assessment results. Specifically, the difference index reflects the degree of consistency between hospital medication and standard medication, the frequency of medication reflects the prevalence of the drug in actual application, and the clinical efficacy score directly reflects the actual therapeutic effect of the drug. By using a weighted summation method, the importance of these factors can be balanced, thereby more accurately assessing the reliability of the hospital's historical medication regimens.

[0018] Optionally, adjusting the hospital's historical medication regimen based on the reliability of the diagnostic information to obtain an adjusted hospital medication regimen includes: From the hospital's historical medication regimens based on the diagnostic information, those with a reliability level greater than a set threshold are selected, and the selected hospital historical medication regimens are used as the adjusted hospital medication regimens.

[0019] In the aforementioned implementation process, by screening historical hospital medication regimens with a reliability exceeding a set threshold, the adjusted hospital medication regimens were ensured to possess high scientific rigor and standardization. This method effectively eliminates non-standard medication regimens that deviate significantly from standard regimens, have poor clinical efficacy, or are used infrequently, thereby improving the overall rationality and consistency of hospital medication use. Simultaneously, the screened medication regimens are more in line with clinical norms and actual needs, helping to reduce medical risks, improve the quality of medical services, and provide patients with safer and more effective treatment options.

[0020] Optionally, determining the target drug combination based on the diagnostic information, the cost range, and the hospital medication regimen database includes: Based on the diagnostic information, at least one matching medication regimen is searched from the hospital's medication regimen database; Based on the drug information of the at least one medication regimen, determine the corresponding set of optional drugs for each medication regimen from the hospital drug database; The drugs in the optional drug set are arranged and combined according to the drugs required by the diagnostic information to obtain multiple drug combinations; Based on the cost of each drug combination, a target drug combination whose cost falls within the cost range is determined from the plurality of drug combinations.

[0021] In the above implementation process, matching medication regimens are retrieved from the hospital's medication regimen database based on diagnostic information, ensuring the targeted and compliant nature of medication. Secondly, the set of available drugs for each medication regimen is determined from the hospital's drug database, providing doctors with a wide range of drug choices. Then, multiple drug combinations are obtained through permutations and combinations, and target drug combinations within the specified cost range are selected based on drug costs. This ensures both medication efficacy and optimized drug costs, avoiding unnecessary waste of medical resources.

[0022] Optionally, determining the cost range based on the medical insurance payment standard, the patient's existing drug costs, and the preset upper limit for drug ratio includes: Multiply the medical insurance payment standard by the preset drug ratio limit to obtain the total medical insurance drug budget cost; The remaining medical insurance drug cost is obtained by subtracting the patient's drug expenses from the total medical insurance drug budget cost. Based on the remaining medical insurance drug costs, determine the cost range for the current diagnosis.

[0023] In the aforementioned process, by accurately calculating the total budgeted cost and remaining cost of medical insurance drugs, and based on this, determining the cost range for the current diagnosis, doctors are provided with a clear cost reference range. This not only ensures the rational use of medical insurance funds and avoids medical insurance payment deviations, but also helps doctors to reasonably control drug costs and avoid over-treatment while ensuring treatment effectiveness.

[0024] Secondly, embodiments of this application provide a medication recommendation device, the device comprising: The information acquisition module is used to obtain patients' diagnostic information from the hospital information system; The payment standard determination module is used to match the corresponding medical insurance disease group from the disease group database based on the diagnostic information, and determine the medical insurance payment standard for the medical insurance disease group; The cost range determination module is used to determine the cost range based on the medical insurance payment standard, the patient's incurred drug costs, and the preset upper limit of drug ratio; The drug combination screening module is used to determine the target drug combination based on the diagnostic information, the cost range, and the hospital medication regimen database. The drug delivery module is used to push the target drug combination to the doctor's end.

[0025] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the method provided in the first aspect above are performed.

[0026] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0027] Fifthly, embodiments of this application provide a computer program product, including computer program instructions, which, when read and executed by a processor, perform the steps of the method provided in the first aspect above.

[0028] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart illustrating a medication recommendation method provided in this application embodiment; Figure 2 A structural block diagram of a medication recommendation device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device for performing a medication recommendation method, provided as an embodiment of this application. Detailed Implementation

[0031] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0032] It should be noted that the terms "system" and "network" in the embodiments of this invention can be used interchangeably. "Multiple" refers to two or more; therefore, in the embodiments of this invention, "multiple" can also be understood as "at least two". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / ", unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0033] It should also be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant device.

[0034] This application provides a medication recommendation method. This method obtains the patient's diagnostic information from the hospital information system, accurately matches the corresponding medical insurance disease group, and determines the medical insurance payment standard, ensuring a close integration of medication decisions and medical insurance policies, and avoiding medical insurance payment deviations caused by information asymmetry. Secondly, it determines the cost range based on the medical insurance payment standard, the patient's incurred drug costs, and a preset upper limit for drug ratio, providing doctors with a clear cost reference range, which helps to reasonably control medical costs and reduce unnecessary waste of medical resources. Furthermore, it combines diagnostic information, cost ranges, and the hospital's medication regimen database to determine the target drug combination, considering not only the standardization and effectiveness of medication but also the rationality of costs, and can recommend the optimal drug combination for the patient. Finally, the target drug combination is pushed to the doctor, providing intelligent decision support, improving the standardization and consistency of medical orders, reducing the risk of medication deviations and medical disputes caused by manual selection, and improving the overall quality and efficiency of medical services.

[0035] The medication recommendation method of this application can be applied to an intelligent medical order system. This intelligent medical order system is connected to the hospital's information system. The intelligent medical order system can obtain target drug combinations through the medication recommendation method of this solution and push the target drug combinations to the hospital information system so that they can be pushed to the doctor's end, allowing the doctor to refer to the pushed target drug combinations to prescribe drug lists for users.

[0036] Please refer to Figure 1 , Figure 1 A flowchart of a medication recommendation method provided in this application embodiment includes the following steps: Step S110: Obtain the patient's diagnostic information from the hospital information system.

[0037] The intelligent medical order system can obtain patient diagnostic information from the hospital information system through a data interface. For example, after diagnosing a patient, a doctor can fill in relevant diagnostic information in the hospital information system. This information may include patient information, diagnosed disease, and examination details. After receiving this information, the hospital information system can assign a diagnostic code to it. This code is related to the diagnosed disease and can be understood as a classification code for the diagnosed disease, such as an ICD-10 code. The diagnostic information may also include the diagnostic code. The doctor can then click the submit button in the hospital information system to send this diagnostic information to the intelligent medical order system, which can then obtain the patient's diagnostic information.

[0038] Step S120: Based on the diagnostic information, match the corresponding medical insurance disease group from the disease group database and determine the medical insurance payment standard for the medical insurance disease group.

[0039] In this context, a medical insurance disease group refers to a disease group classified under the medical insurance payment rules. Under the DRG (Diagnosis Related Groups) or DIP (Disease-Based Payment) payment methods, the medical insurance department classifies cases with similar clinical processes and resource consumption into the same disease group based on factors such as the patient's main diagnosis, complications, and treatment methods. Each disease group corresponds to a fixed payment standard. For example, a diagnosis of "acute appendicitis" + "appendectomy" will be assigned to a specific DRG group.

[0040] These disease groups will form a disease group database, such as the DRG / DIP disease group database. The intelligent medical order system can use diagnostic information as input and find the most suitable medical insurance disease group in the disease group database through the corresponding matching algorithm. For example, it can match the DRG group "ET39 Chronic obstructive pulmonary disease with serious complications or comorbidities".

[0041] After determining the corresponding medical insurance disease group for the patient, the medical insurance reimbursement standard for that group can be determined. The medical insurance reimbursement standard is a prepayment amount set by the medical insurance department for each disease group. The total cost of providing medical services to patients with that disease should be kept as close to this standard as possible; exceeding it may result in a loss for the hospital, while any surplus becomes revenue. Therefore, the medical insurance reimbursement standard for that disease group can be found in the medical insurance expense database, which stores the medical insurance reimbursement standards for various medical insurance disease groups.

[0042] In some implementations, the medical insurance payment standard can be calculated based on the payment policies (such as benchmark weight, premium rate, and adjustment coefficient) published by the local medical insurance bureau. For example, if the intelligent medical order system can obtain the benchmark weight (e.g., 1.2), the local premium rate (e.g., 7000 yuan), and the hospital's adjustment coefficient (e.g., 1.05) for the ET39 disease group from the medical insurance policy database, then the medical insurance payment standard = benchmark weight * premium rate * adjustment coefficient = 1.2 * 7000 * 1.05 = 8820 yuan. This means that the total amount ultimately paid by the medical insurance center to the hospital for this case is approximately 8820 yuan.

[0043] Step S130: Determine the cost range based on medical insurance payment standards, the patient's incurred drug costs, and the preset upper limit of drug ratio.

[0044] The preset drug ratio cap refers to the maximum proportion of drug costs in the total cost of a patient's hospitalization. Hospitals set a drug ratio cap for different disease groups to control drug costs and prevent irrational drug use.

[0045] In this plan, taking into account hospital costs, a reasonable range of drug costs to be prescribed in this case can be calculated based on medical insurance payment standards, the cost of drugs already sent to the patient, and the preset drug ratio limit. This range is a dynamic value that ensures that the total drug cost throughout the entire treatment process will not exceed the limit.

[0046] In some implementations, corresponding calculation rules can be used to calculate the cost range based on this information. For example, the medical insurance payment standard can be multiplied by the preset drug ratio limit to obtain the total medical insurance drug budget. Then, the drug costs already incurred by the patient can be subtracted from the total medical insurance drug budget to obtain the remaining medical insurance drug cost. Based on the remaining medical insurance drug cost, the cost range for the current diagnosis can be determined.

[0047] For example, assuming the hospital sets a preset drug ratio limit of 30% for patient group ET39, and the medical insurance payment standard is calculated as 8820 yuan according to the above method, by querying the hospital information system, it is found that the patient's drug expenses have been 1000 yuan. The total medical insurance drug budget is 8820 * 30% = 2646 yuan, and the remaining medical insurance drug expenses are 2646 - 1000 = 1646 yuan. The cost range can fluctuate around the remaining medical insurance drug expenses, for example, the cost range is 1600-1700 yuan.

[0048] Alternatively, the cost range can be within a certain range of the remaining medical insurance drug costs, such as the cost range being the remaining medical insurance drug costs. 10%, according to this method, the cost range can be determined as [14.81.4 yuan, 1810.6 yuan]. This is based on a percentage fluctuation (the upper and lower limits of the fluctuation can be different, for example, the upper limit is 10% and the lower limit is 8%). Of course, it can also fluctuate according to a preset absolute amount value, such as the cost range being [remaining medical insurance drug cost - R, remaining medical insurance drug cost + R].

[0049] In other implementations, different interval calculation strategies can be dynamically adopted based on the amount of remaining medical insurance drug costs. For example, if the remaining medical insurance drug costs are greater than X1 yuan (e.g., 2000 yuan), the cost interval can be set wider, such as [remaining medical insurance drug costs * 0.8, remaining medical insurance drug costs * 1.2]; if the remaining medical insurance drug costs are greater than X2 yuan (e.g., 500 yuan) but less than or equal to X1 yuan, the cost interval can be set appropriately, such as [remaining medical insurance drug costs * 0.9, remaining medical insurance drug costs * 1.1]; if the remaining medical insurance drug costs are less than or equal to X2 yuan, the cost interval is narrowed, such as [remaining medical insurance drug costs * 0.95, remaining medical insurance drug costs].

[0050] In some other implementations, machine learning models can be used to predict the patient's cost range. Specifically, historical data can be used to train the machine learning model to predict the cost range for the current prescription. During training, the training data considers not only the three parameters—medical insurance payment standards, the patient's incurred drug costs, and the preset drug ratio limit—but also relevant patient information such as age, complications, length of hospital stay, and the attending physician's medication habits. During model training, data can be extracted from historical electronic medical records. For example, for each completed case, features such as "diagnosis - incurred costs at a certain point in time - whether the final total drug cost exceeds the limit" can be extracted and input into the model for training. This allows the model to learn a cost range that, given the current situation, meets clinical needs without exceeding the limit. The trained model can then be used to predict the cost range for new patients.

[0051] By accurately calculating the total budgeted cost and remaining cost of drugs covered by medical insurance, and based on this, determining the cost range for the current diagnosis, doctors are provided with a clear cost reference range. This not only ensures the rational use of medical insurance funds and avoids medical insurance payment deviations, but also helps doctors reasonably control drug costs and avoid over-treatment while ensuring treatment effectiveness.

[0052] Step S140: Determine the target drug combination based on diagnostic information, cost range, and hospital medication protocol database.

[0053] After obtaining the cost range, the cost range of the medications prescribed for this diagnosis can be known. Then, based on the diagnosis information, some candidate drug combinations related to the diagnosis information can be matched from the hospital's medication plan database. These candidate drug combinations are combinations of conventional treatment drugs for the diagnosis information, and these drugs can be permutations and combinations of different manufacturers and specifications.

[0054] Then the drug costs of these candidate drug combinations can be calculated, and drug combinations whose drug costs fall within the cost range are selected as the target drug combinations.

[0055] Alternatively, based on the diagnostic information, some drugs required for the diagnosis can be matched from the hospital's medication regimen database, and then a combination of drugs whose costs are within the aforementioned cost range can be selected from these drugs as the target drug combination.

[0056] Step S150: Push the target drug combination to the doctor's end.

[0057] If there are multiple target drug combinations selected above, all of them can be sent to the doctor, or the target drug combination with the lowest total cost or the lowest drug cost can be selected and sent to the doctor.

[0058] For example, if the intelligent medical order system selects 10 possible candidate drug combinations to treat the patient, and after calculation, the drug costs of 3 of the candidate drug combinations are within the cost range, then these 3 candidate drug combinations can be output to the doctor as the target drug combination, or the drug combination with the lowest total cost can be selected and output to the doctor.

[0059] In some implementations, when the intelligent medical order system outputs the target drug combination to the doctor, it can also simultaneously output information such as the name, specifications, usage and dosage, estimated total cost and cost price of each drug in the target drug combination. This allows the doctor to issue a treatment order based on this information when prescribing medical orders.

[0060] In the aforementioned implementation process, by obtaining patients' diagnostic information from the hospital information system, the corresponding medical insurance disease groups can be accurately matched and the medical insurance payment standards can be determined, ensuring a close integration of medication decisions and medical insurance policies and avoiding medical insurance payment deviations caused by information asymmetry. Secondly, by determining the cost range based on medical insurance payment standards, the patient's incurred drug costs, and the preset upper limit of drug ratio, a clear cost reference range is provided to doctors, helping to rationally control medical costs and reduce unnecessary waste of medical resources. Furthermore, by combining diagnostic information, cost ranges, and the hospital's medication regimen database to determine the target drug combination, not only is the standardization and effectiveness of medication taken into account, but also the rationality of costs, enabling the recommendation of the optimal drug combination for patients. Finally, the target drug combination is pushed to the doctor's end, providing intelligent decision support, improving the standardization and consistency of medical orders, reducing the risk of medication deviations and medical disputes caused by manual selection, and improving the overall quality and efficiency of medical services.

[0061] Based on the above embodiments, in the above implementation of determining the target drug combination, at least one matching medication regimen can be found from the hospital medication regimen database according to the diagnostic information. Then, based on the drug information of the at least one medication regimen, the corresponding set of optional drugs for each medication regimen is determined from the hospital drug database. The drugs in the set of optional drugs are arranged and combined according to the drugs required by the diagnostic information to obtain multiple drug combinations. Then, based on the drug cost of each drug combination, the target drug combination whose drug cost is within the cost range is determined from the multiple drug combinations.

[0062] Among them, at least one medication regimen refers to a treatment strategy for the diagnostic information matched from the hospital medication regimen database. It defines the required drug category, drug name, treatment goal or core drug and other information, and usually does not specify the specific manufacturer, specification or dosage form.

[0063] The hospital's medication regimen database includes a correspondence between diagnostic information and medication regimens. Diagnostic information can be a diagnostic code. When searching for a medication regimen, this code can be used for matching and querying. For example, if a patient's current diagnostic information includes: Grade 2 essential hypertension with type 2 diabetes, it corresponds to a diagnostic code. Searching the hospital's medication regimen database using this code will yield two medication regimens: Regimen 1: ACE inhibitors (due to their kidney-protective effect in diabetic patients); Regimen 2: Oral hypoglycemic agent – ​​metformin.

[0064] Then, based on the drug information for each medication regimen, the corresponding set of available drugs can be determined from the hospital's drug database. For example, for regimen 1, the drug information is ACE inhibitors for blood pressure, and for regimen 2, the drug information is metformin. The hospital's drug database is then queried (considering inventory, drug status, etc.) to generate the set of available drugs for each medication regimen.

[0065] For example, the drug selection set 1 for medication regimen 1 (ACEI antihypertensive drugs) includes: Drug A: Enalapril tablets - 10mg, Drug B: Perindopril tablets - 4mg, Drug C: Benazepril tablets - 10mg. The drug selection set 2 for medication regimen 2 (metformin) includes: Drug D: Metformin immediate-release tablets - 0.5g, Drug E: Metformin extended-release tablets - 0.5g.

[0066] When arranging and combining drugs, the Cartesian product operation can be performed on the above optional drug set 1 and optional drug set 2 to generate all possible drug combinations. Each drug combination may include one drug from optional drug set 1 and one drug from optional drug set 2. According to the above example, a total of 6 drug combinations can be generated.

[0067] For each drug combination, the drug cost can be calculated based on the hospital price of each drug in the combination. Then, the calculated drug cost is compared with a pre-determined cost range to select target drug combinations whose drug costs fall within the cost range.

[0068] Of course, when selecting the target drug combination, cost can also be considered simultaneously. For example, first screen out drug combinations whose drug costs are within the cost range. If there are multiple combinations, then select the drug combination with the lowest cost as the target drug combination.

[0069] In the above implementation process, matching medication regimens are retrieved from the hospital's medication regimen database based on diagnostic information, ensuring the targeted and compliant nature of medication. Secondly, the set of available drugs for each medication regimen is determined from the hospital's drug database, providing doctors with a wide range of drug choices. Then, multiple drug combinations are obtained through permutations and combinations, and target drug combinations within the specified cost range are selected based on drug costs. This ensures both medication efficacy and optimized drug costs, avoiding unnecessary waste of medical resources.

[0070] Based on the above embodiments, the aforementioned hospital medication regimen database is constructed based on clinical medication guidelines and hospital historical medication records.

[0071] Clinical drug use guidelines refer to normative documents such as the "Clinical Diagnosis and Treatment Guidelines", "Clinical Pathways", and "Guiding Principles for Drug Use" issued by authoritative institutions such as the National Health Commission and the Chinese Medical Association. These documents provide standardized disease diagnosis and treatment plans based on evidence-based medicine and serve as the benchmark for compliance of medical practices.

[0072] Hospital historical medication records refer to historical electronic prescription data extracted from the hospital information system that can be anonymized. These records may include information such as diagnosis, medication, dosage, and doctor, and accurately reflect the collective medication habits of the hospital's doctors, drug inventory, and localized treatment experience.

[0073] A hospital medication regimen database can be a structured database where each record represents an optimal medication regimen for a specific diagnosis. These regimens are personalized clinical pathways that integrate authoritative guidelines with hospital practical experience.

[0074] Therefore, the hospital medication protocol database is a database that integrates clinical medication guidelines and hospital historical medication records. The medication protocols in this database not only ensure the standardization of medication use, but also preserve the hospital's medication habits.

[0075] In the aforementioned process, clinical medication guidelines provide authoritative guidance, ensuring the scientific rigor and compliance of medication use; hospital historical medication records reflect the hospital's actual medication habits and physicians' clinical experience, making the recommendations more aligned with the hospital's specific circumstances. This combined approach not only improves the accuracy and adaptability of medication regimens but also effectively reduces medication risks caused by individual differences and experience biases, further enhancing the quality and safety of medical services.

[0076] Based on the above embodiments, in constructing a hospital medication regimen database, the standard medication regimens and hospital historical medication records in the clinical medication guidelines corresponding to different diagnostic information can be obtained first. Then, for the same diagnostic information, the reliability of the hospital historical medication regimens for that diagnostic information is evaluated based on the standard medication regimens corresponding to that diagnostic information, and the hospital historical medication regimens for that diagnostic information are adjusted according to the reliability to obtain the adjusted hospital medication regimens. Then, the hospital medication regimen database is constructed based on the adjusted hospital medication regimens.

[0077] In the above scheme, after obtaining the clinical medication guidelines and hospital historical medication records, the clinical medication guidelines and hospital historical medication records can be standardized to obtain standard medication plans and hospital historical medication plans, which will facilitate subsequent retrieval and matching.

[0078] Standard medication regimens can be understood as recommended drug treatment plans for a specific diagnosis, extracted from clinical medication guidelines. For example, for clinical medication guidelines, we can first parse the guidelines in PDF, Word, or other formats, and then use natural language processing technology to perform word segmentation and entity recognition to extract the relationship between the diagnosis code and the recommended drug / treatment plan, thus forming a structured standard medication regimen, such as {Diagnosis code: E11.9 Type 2 diabetes, Medication plan: Metformin}.

[0079] Historical medication regimens in hospitals can be obtained through aggregated analysis of historical medication records, representing medication regimens actually used for a specific diagnosis. For example, historical medication records can be grouped according to the diagnosis codes in the diagnostic information, and then historical prescription data can be aggregated to form structured historical medication regimens, such as {Diagnosis Code: E11.9 Type 2 Diabetes, Medication Regimen: {Drug: Metformin Regular Tablets}, {Drug: Metformin Extended-Release Tablets}}.

[0080] After standardizing clinical medication guidelines and hospital historical medication records, standard medication regimens and hospital historical medication regimens corresponding to different diagnostic information can be obtained. For each type of diagnostic information, the reliability of the hospital historical medication regimen can be assessed using its standard medication regimen.

[0081] Reliability level characterizes the conformity and rationality of a hospital's historical medication regimens relative to clinical medication guidelines. It is a quantitative indicator reflecting the strength of a hospital's historical medication regimens in terms of standardization, safety, and evidence-based support. The higher the reliability level, the more worthy the hospital's historical medication regimens are of being retained and adopted when constructing a hospital medication regimen database.

[0082] In some implementations, a reliability assessment model can be established to calculate a reliability score for each hospital’s historical medication regimen. This model can consider compliance dimensions, such as the degree of matching between the standard medication regimen and the hospital’s historical medication regimen. If they are completely consistent, a high score is given; if they belong to the same type of drug (such as different dosage forms), a medium score is given; and if they are completely different or are drugs not recommended by guidelines, a low score or zero score is given.

[0083] For example, for the diagnostic code E11.9 in the diagnostic information, the corresponding standard medication regimen is {Diagnosis code: E11.9 Type 2 diabetes, medication regimen: metformin immediate-release tablets}. The corresponding hospital historical medication regimens include regimen A: {Diagnosis code: E11.9 Type 2 diabetes, medication regimen: {Drug: metformin immediate-release tablets}}, regimen B: {Diagnosis code: E11.9 Type 2 diabetes, medication regimen: {Drug: metformin extended-release tablets}}, and regimen C: {Diagnosis code: E11.9 Type 2 diabetes, medication regimen: {Drug: glimepiride tablets}}.

[0084] In this study, Regimen A, whose dosage regimen is consistent with the standard dosage regimen, receives a reliability score of 10. Regimen B, which uses the same drug in a different dosage form as the standard dosage regimen, receives a reliability score of 7. Regimen C, which is completely different from the standard dosage regimen, receives a reliability score of 0. Thus, the reliability level can be assessed using the reliability score; in other words, reliability can be characterized by the reliability score.

[0085] The same approach can be used to determine the reliability of a hospital's historical medication regimen for other diagnostic information.

[0086] Once the reliability level is obtained, the hospital's historical medication regimens can be adjusted accordingly. Adjustment can be understood as processing the hospital's historical medication regimens. Adjustment methods include, but are not limited to: direct adoption, modifying their priority (such as downgrading them from first choice to alternative), restricting their use conditions, or direct deletion.

[0087] For example, when adjusting the hospital's historical medication regimens for diagnosis code E11.9, based on the reliability scores (i.e., reliability level) of regimens A, B, and C, regimen A is found to have the highest reliability, so regimen A can be retained. Registrar B and regimen C can be directly deleted. In other words, after the adjustment, only regimen A is retained, and regimen A can be stored in the hospital's medication regimen database.

[0088] In some implementations, Option B has a reliability score of 7, which is above average, so it can be used as an alternative recommended medication option. However, additional usage instructions can be added to the hospital medication database, such as "suitable for patients with significant gastrointestinal reactions to ordinary tablets". When recommending medication options in the future, Option A can be the first choice. If the first choice is not suitable for the patient, Option B can be recommended as an alternative.

[0089] Finally, the hospital's historical medication regimens, after evaluation and adjustment, can be structurally stored in the hospital medication regimen database.

[0090] In the aforementioned implementation process, by combining standard medication regimens from clinical medication guidelines with historical medication regimens from hospital records, and by assessing and adjusting the reliability of these historical regimens, a hospital medication regimen database is constructed with higher accuracy and practicality. This process not only ensures that medication regimens comply with authoritative clinical guidelines but also incorporates the hospital's actual medication practices and physicians' clinical experience, making recommended medication regimens more closely aligned with the hospital's specific practices. This approach effectively improves the scientific rigor and standardization of medication decisions, reduces medication risks caused by experience biases, and simultaneously addresses the personalized needs of healthcare services, thereby enhancing the overall quality and efficiency of healthcare services.

[0091] Based on the above embodiments, in the above method of assessing the reliability of hospital historical medication regimens, it is also possible to obtain the standard medications in the standard medication regimen corresponding to the diagnostic information, as well as the hospital medications in the hospital historical medication regimens corresponding to the diagnostic information, and then assess the reliability of the hospital historical medication regimens based on the differences between the hospital medications and the standard medications.

[0092] First, obtain the standard medication and hospital medication for a specific diagnosis. For example, for the diagnosis code E11.9, the standard medication in its standard medication regimen is metformin immediate-release tablets, and the hospital medications in its historical hospital medication regimen are metformin immediate-release tablets, metformin extended-release tablets, and glimepiride tablets.

[0093] Then, the differences between hospital-used drugs and standard-use drugs can be compared. The differences can refer to the degree of consistency between hospital-used drugs and standard-use drugs in terms of pharmacological properties. These differences can be hierarchical, ranging from completely consistent to completely different, and their degree directly determines the reliability of the hospital's historical medication regimens.

[0094] When assessing differences, the standard medication can be compared with the medications used in each hospital's historical medication regimen. The reliability score can be determined based on the difference comparison table, and this score can serve as a direct measure of reliability.

[0095] For example, the comparison table can be shown below:

[0096] Understandably, the above difference comparison table is only an illustrative example. In practical applications, the difference levels and scores in the difference comparison table can be flexibly adjusted according to the actual situation and needs. This difference comparison table can be pre-built and configured in the intelligent medical order system, so that the corresponding reliability score can be obtained directly based on the difference comparison table when conducting reliability assessments.

[0097] According to the above difference comparison table, the differences between hospital-prescribed drugs and standard-prescribed drugs can be obtained, and the corresponding reliability scores can be obtained. In this way, the reliability of each hospital medication regimen can be obtained.

[0098] In the aforementioned process, the reliability of a hospital's historical medication regimen is assessed by comparing the differences between the standard medications corresponding to the diagnostic information and those used in the hospital's past medication practices. This allows for the accurate identification of deviations between the hospital's actual medication use and authoritative standards. This assessment method helps to promptly identify and correct non-standard medication habits, ensuring the scientific validity and compliance of the hospital's medication regimen. Furthermore, adjustments to the hospital's historical medication regimen based on these assessment results can further optimize hospital medication practices, improve the quality and safety of medical services, reduce medical risks and disputes caused by inappropriate medication, and provide patients with more reliable medical services.

[0099] Based on the above embodiments, in order to conduct a more accurate reliability assessment, the hospital's medication habits can also be considered. For example, the frequency of use and clinical efficacy scores of hospital medications can be obtained first, and then the reliability of the hospital's historical medication regimens can be assessed based on the differences between hospital medications and standard medications, the frequency of use, and the clinical efficacy scores.

[0100] Medication frequency can refer to the number of times a hospital's historical medication regimen for a specific diagnosis is prescribed in the hospital information system within a specified time period, or it can refer to the number of times the hospital's medication regimen is prescribed in the hospital's historical medication records. It can quantify the breadth of use of the hospital's historical medication regimen in clinical practice and the acceptance of the physician community. High frequency usually means a mature medication process and widespread recognition.

[0101] Clinical efficacy scoring refers to the comprehensive evaluation of a medication regimen based on a post-medical record assessment system (such as the improvement of patient follow-up indicators, the doctor's subjective evaluation of the efficacy, adverse reaction reports, etc.) (which can be on a ten-point scale). It directly reflects the effectiveness and safety of the medication regimen in actual application.

[0102] A reliability score can then be calculated based on the difference, frequency of medication, and clinical efficacy score. The difference can be obtained by using the difference comparison table mentioned above to determine the corresponding difference level. In some implementations, the difference level, frequency of medication, and clinical efficacy score can be input into a pre-trained neural network model, which will then predict a reliability score.

[0103] In some implementations, the differences, frequency of medication, and clinical efficacy scores can be weighted and summed to obtain the reliability of the hospital's historical medication regimens. In this implementation, the differences can be used to characterize the degree of consistency between hospital-prescribed medications and standard medications.

[0104] When applying weighted summation, a scoring formula can be designed, such as Reliability Score = Difference Score * W1 + Medication Frequency * W2 + Clinical Efficacy Score * W3. Here, W1, W2, and W3 are the corresponding weights, which can be set according to needs and adjusted as the system runs.

[0105] The difference score can be obtained through differences. For example, if the hospital-used medication is not a standard medication, the difference score is 0; conversely, if the hospital-used medication is a standard medication (i.e., the two are completely identical), the difference score is 10. Alternatively, the degree of consistency between the hospital-used medication and the standard medication can be compared according to the difference comparison table mentioned above to obtain the difference level, and the corresponding difference score can be obtained based on the difference level.

[0106] Regarding the frequency of medication, it can also be quantified into a corresponding score. For example, the highest frequency among all historical medication regimens in all hospitals under this diagnosis can be recorded as 10 points, and the scores of other frequencies can be calculated according to their ratio with the highest frequency. For example, the medication frequency score = (the medication frequency of this regimen / the highest frequency) * 10.

[0107] Regarding clinical efficacy scoring, if it is quantified as a score, the average of a 10-point scale can be used.

[0108] For example, for the three hospital history medication regimens of the above diagnostic code E11.9, regimens A, B, and C, the highest frequency is 700 times for regimen A. Their reliability scores are calculated as shown in the table below:

[0109] This approach combines variability, frequency of medication use, and clinical efficacy scores to assess the reliability of a hospital's historical medication regimens, avoiding the limitations of a single-dimensional evaluation. In practice, in addition to considering these three aspects, more information can be incorporated to comprehensively assess the reliability of a hospital's historical medication regimens. For example, information such as drug cost-effectiveness and authority can also be included. This information can be weighted and summed in the same way to obtain the final reliability score.

[0110] This quantitative assessment method comprehensively considers multiple key factors, ensuring the comprehensiveness and objectivity of the assessment results. Specifically, the difference index reflects the consistency between hospital medication and standard medication, the frequency of medication reflects the prevalence of the drug in actual use, and the clinical efficacy score directly reflects the actual therapeutic effect of the drug. By using a weighted summation method, the importance of these factors can be balanced, thereby more accurately assessing the reliability of the hospital's historical medication regimens.

[0111] In the aforementioned process, this evaluation method not only focuses on whether the selected drugs meet the standards, but also considers the frequency of drug use and clinical efficacy in actual use, making the evaluation results more comprehensive and objective. Secondly, this comprehensive evaluation method can more accurately reflect the actual application effects of the hospital's historical medication regimens, thus providing a stronger basis for optimizing hospital medication regimens. Finally, hospital medication regimens evaluated and adjusted in this way not only comply with clinical guidelines but also incorporate actual usage, effectively improving the scientific rigor and reliability of medication decisions.

[0112] Based on the above embodiments, in the above method of adjusting hospital historical medication plans according to reliability, in order to ensure that more data is available for building a hospital medication plan database, hospital historical medication plans with a reliability greater than a set threshold can be selected from similar hospital medication plans of the diagnostic information. The selected hospital historical medication plans can then be used as the adjusted hospital medication plans.

[0113] The threshold can be a predefined minimum standard for reliability scores, which can be set according to needs. If the threshold is set to 5, based on the example above, the reliability score of scheme A is 9.7, the reliability score of scheme B is 7.69, and the reliability score of scheme C is 3.61. Schemes A and B have reliability scores greater than the set threshold, so schemes A and B can be filtered out, and scheme C can be deleted. Schemes A and B can then be used to build a hospital medication protocol database.

[0114] In the aforementioned implementation process, by screening historical hospital medication regimens with a reliability exceeding a set threshold, the adjusted hospital medication regimens were ensured to possess high scientific rigor and standardization. This method effectively eliminates non-standard medication regimens that deviate significantly from standard regimens, have poor clinical efficacy, or are used infrequently, thereby improving the overall rationality and consistency of hospital medication use. Simultaneously, the screened medication regimens are more in line with clinical norms and actual needs, helping to reduce medical risks, improve the quality of medical services, and provide patients with safer and more effective treatment options.

[0115] As the intelligent medical order system operates, after the recommended target drug combination is administered to the patient, it can automatically track key indicators of the patient's subsequent treatment effect, such as improvement in condition upon discharge and changes in follow-up test results. These key indicators can be used as reference data for subsequent adjustments to the weighting of the aforementioned medications. These key indicators can also be correlated with the medication regimens used and cost data, thereby optimizing the data in the hospital's medication regimen database and recommending more reasonable drug combinations for doctors.

[0116] In some implementations, the data in the hospital medication regimen database can be re-evaluated periodically, such as quarterly, and medication regimens with high reliability scores and low costs can have their recommendation weight automatically increased.

[0117] Please refer to Figure 2 , Figure 2 This is a structural block diagram of a medication recommendation device 200 provided in an embodiment of this application. The device 200 may be a module, program segment, or code on an electronic device. It should be understood that the device 200 corresponds to the above method embodiment and is capable of performing the various steps involved in the method embodiment. The specific functions of the device 200 can be found in the description above, and detailed descriptions are omitted here to avoid repetition.

[0118] Optionally, the device 200 includes: Information acquisition module 210 is used to acquire patient diagnostic information from the hospital information system; The payment standard determination module 220 is used to match the corresponding medical insurance disease group from the disease group database based on the diagnostic information, and determine the medical insurance payment standard for the medical insurance disease group; The cost range determination module 230 is used to determine the cost range based on the medical insurance payment standard, the patient's incurred drug costs, and the preset drug ratio limit; The drug combination screening module 240 is used to determine the target drug combination based on the diagnostic information, the cost range, and the hospital medication plan database. The drug delivery module 250 is used to push the target drug combination to the doctor's end.

[0119] Optionally, the hospital medication regimen database is constructed based on clinical medication guidelines and historical hospital medication records.

[0120] Optionally, the device 200 further includes: The database construction module is used to obtain standard medication regimens from clinical medication guidelines and historical medication regimens from hospital records for different diagnostic information; for the same diagnostic information, the reliability of the historical medication regimens for that diagnostic information is evaluated based on the standard medication regimens corresponding to that diagnostic information; the historical medication regimens for that diagnostic information are adjusted based on the reliability to obtain the adjusted hospital medication regimens; and the hospital medication regimen database is constructed based on the adjusted hospital medication regimens.

[0121] Optionally, the database construction module is used to obtain the standard medications in the standard medication regimen corresponding to the diagnostic information, and to obtain the hospital medications in the hospital's historical medication regimen corresponding to the diagnostic information; and to assess the reliability of the hospital's historical medication regimen based on the differences between the hospital medications and the standard medications.

[0122] Optionally, the database construction module is used to obtain the frequency of use and clinical efficacy scores of the hospital's medications; and to assess the reliability of the hospital's historical medication regimens based on the differences between the hospital's medications and the standard medications, the frequency of use, and the clinical efficacy scores.

[0123] Optionally, the database construction module is used to perform a weighted summation of the differences between the hospital-prescribed drugs and the standard drugs, the frequency of drug use, and the clinical efficacy score to obtain the reliability of the hospital's historical drug use plan, wherein the differences are used to characterize the degree of consistency between the hospital-prescribed drugs and the standard drugs.

[0124] Optionally, the database construction module is used to filter out hospital historical medication plans with a reliability greater than a set threshold from the hospital historical medication plans of the diagnostic information, and the filtered hospital historical medication plans are used as the adjusted hospital medication plans.

[0125] Optionally, the drug combination screening module 240 is used to search for at least one matching medication regimen from the hospital medication regimen database based on the diagnostic information; determine the corresponding set of optional drugs for each medication regimen from the hospital drug database based on the drug information of the at least one medication regimen; arrange and combine the drugs in the set of optional drugs according to the drugs required by the diagnostic information to obtain multiple drug combinations; and determine the target drug combination whose drug cost is within the cost range from the multiple drug combinations based on the drug cost of each drug combination.

[0126] Optionally, the cost range determination module 230 is used to multiply the medical insurance payment standard by a preset drug ratio limit to obtain the total medical insurance drug budget; subtract the drug costs already incurred by the patient from the total medical insurance drug budget to obtain the remaining medical insurance drug cost; and determine the cost range for the current diagnosis based on the remaining medical insurance drug cost.

[0127] It should be noted that those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0128] Please refer to Figure 3 , Figure 3This application provides a schematic diagram of an electronic device for performing a medication recommendation method. The electronic device may include: at least one processor 310, such as a CPU; at least one communication interface 320; at least one memory 330; and at least one communication bus 340. The communication bus 340 is used to establish communication between these components. In this embodiment, the communication interface 320 is used for signaling or data communication with other node devices. The memory 330 may be high-speed RAM or non-volatile memory, such as at least one disk storage device. Optionally, the memory 330 may also be at least one storage device located remotely from the processor. The memory 330 stores computer-readable instructions, which, when executed by the processor 310, cause the electronic device to perform the aforementioned method process.

[0129] Understandable. Figure 3 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 3 The components shown can be implemented using hardware, software, or a combination thereof.

[0130] This application provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it performs the method process executed by the electronic device in the above method embodiments.

[0131] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments, such as including: Obtain patient diagnostic information from the hospital information system; Based on the diagnostic information, the corresponding medical insurance disease group is matched from the disease group database, and the medical insurance payment standard for the medical insurance disease group is determined. Based on the aforementioned medical insurance payment standards, the patient's existing drug costs, and the preset upper limit for drug ratio, the cost range is determined; Based on the diagnostic information, the cost range, and the hospital's medication regimen database, a target drug combination is determined; The target drug combination is then pushed to the doctor's end.

[0132] In summary, this application provides a medication recommendation method, device, electronic device, storage medium, and program product. By obtaining the patient's diagnostic information from the hospital information system, it can accurately match the corresponding medical insurance disease group and determine the medical insurance payment standard, ensuring a close integration of medication decisions and medical insurance policies, and avoiding medical insurance payment deviations caused by information asymmetry. Secondly, by determining the cost range based on the medical insurance payment standard, the patient's incurred drug costs, and the preset drug ratio upper limit, it provides doctors with a clear cost reference range, helping to reasonably control medical costs and reduce unnecessary waste of medical resources. Furthermore, by combining diagnostic information, cost ranges, and the hospital's medication plan database to determine the target drug combination, it not only considers the standardization and effectiveness of medication but also the rationality of costs, and can recommend the optimal drug combination for the patient. Finally, pushing the target drug combination to the doctor provides intelligent decision support, improves the standardization and consistency of medical orders, reduces the risk of medication deviations and medical disputes caused by manual selection, and improves the overall quality and efficiency of medical services.

[0133] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0134] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0136] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0137] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for recommending medication, characterized in that, The method includes: Obtain patient diagnostic information from the hospital information system; Based on the diagnostic information, the corresponding medical insurance disease group is matched from the disease group database, and the medical insurance payment standard for the medical insurance disease group is determined. Based on the aforementioned medical insurance payment standards, the patient's existing drug costs, and the preset upper limit for drug ratio, the cost range is determined; Based on the diagnostic information, the cost range, and the hospital's medication regimen database, a target drug combination is determined; The target drug combination is then pushed to the doctor's end.

2. The method according to claim 1, characterized in that, The step of determining the target drug combination based on the diagnostic information, the cost range, and the hospital medication regimen database includes: Based on the diagnostic information, at least one matching medication regimen is searched from the hospital's medication regimen database; Based on the drug information of the at least one medication regimen, determine the corresponding set of optional drugs for each medication regimen from the hospital drug database; The drugs in the optional drug set are arranged and combined according to the drugs required by the diagnostic information to obtain multiple drug combinations; Based on the cost of each drug combination, a target drug combination whose cost falls within the cost range is determined from the plurality of drug combinations.

3. The method according to claim 1, characterized in that, The process of determining the cost range based on the aforementioned medical insurance payment standards, the patient's existing drug costs, and the preset upper limit for drug ratio includes: Multiply the medical insurance payment standard by the preset drug ratio limit to obtain the total medical insurance drug budget cost; The remaining medical insurance drug cost is obtained by subtracting the patient's drug expenses from the total medical insurance drug budget cost. Based on the remaining medical insurance drug costs, determine the cost range for the current diagnosis.

4. The method according to claim 1, characterized in that, The hospital medication protocol database is built based on clinical medication guidelines and historical hospital medication records.

5. The method according to claim 4, characterized in that, The hospital medication regimen database was constructed using the following methods: Obtain the standard medication regimens in the clinical medication guidelines documents corresponding to different diagnostic information and the hospital's historical medication regimens in the hospital's historical medication records; For the same diagnostic information, assess the reliability of the hospital's historical medication regimens for that diagnostic information based on the standard medication regimens corresponding to that diagnostic information; Based on the reliability level, the hospital's historical medication regimen for this diagnostic information is adjusted to obtain the adjusted hospital medication regimen; The hospital medication regimen database is constructed based on the adjusted hospital medication regimen.

6. The method according to claim 5, characterized in that, The assessment of the reliability of the hospital's historical medication regimens based on the standard medication regimens corresponding to the diagnostic information includes: Obtain the standard medications in the standard medication regimen corresponding to the diagnostic information, and obtain the hospital medications in the hospital's historical medication regimen corresponding to the diagnostic information; The reliability of the hospital's historical medication regimens is assessed based on the differences between the hospital's medications and the standard medications.

7. The method according to claim 6, characterized in that, The assessment of the reliability of the hospital's historical medication regimen based on the differences between the hospital's medications and the standard medications includes: Obtain the frequency of use and clinical efficacy scores of the hospital's medications; The reliability of the hospital's historical medication regimens is assessed based on the differences between the hospital's medications and the standard medications, the frequency of medication use, and the clinical efficacy scores.

8. The method according to claim 7, characterized in that, The assessment of the reliability of the hospital's historical medication regimen based on the differences between the hospital's medications and the standard medications, the frequency of medication use, and the clinical efficacy score includes: The reliability of the hospital's historical medication regimen is obtained by weighting and summing the differences between the hospital's medication and the standard medication, the frequency of medication use, and the clinical efficacy score, wherein the differences are used to characterize the degree of consistency between the hospital's medication and the standard medication.

9. The method according to claim 5, characterized in that, The step of adjusting the hospital's historical medication regimen based on the reliability of the diagnostic information to obtain the adjusted hospital medication regimen includes: From the hospital's historical medication regimens based on the diagnostic information, those with a reliability level greater than a set threshold are selected, and the selected hospital historical medication regimens are used as the adjusted hospital medication regimens.

10. A medication recommendation device, characterized in that, The device includes: The information acquisition module is used to obtain patients' diagnostic information from the hospital information system; The payment standard determination module is used to match the corresponding medical insurance disease group from the disease group database based on the diagnostic information, and determine the medical insurance payment standard for the medical insurance disease group; The cost range determination module is used to determine the cost range based on the medical insurance payment standard, the patient's incurred drug costs, and the preset upper limit of drug ratio; The drug combination screening module is used to determine the target drug combination based on the diagnostic information, the cost range, and the hospital medication regimen database. The drug delivery module is used to push the target drug combination to the doctor's end.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the method as described in any one of claims 1-9.

13. A computer program product, characterized in that, It includes computer program instructions, which, when read and executed by a processor, perform the method as described in any one of claims 1-9.

Images