WO2020119402A1 - 无关用药的识别方法、装置、终端及计算机可读存储介质 - Google Patents

无关用药的识别方法、装置、终端及计算机可读存储介质 Download PDF

Info

Publication number
WO2020119402A1
WO2020119402A1 PCT/CN2019/119212 CN2019119212W WO2020119402A1 WO 2020119402 A1 WO2020119402 A1 WO 2020119402A1 CN 2019119212 W CN2019119212 W CN 2019119212W WO 2020119402 A1 WO2020119402 A1 WO 2020119402A1
Authority
WO
WIPO (PCT)
Prior art keywords
medication
medicine
range
drug
details
Prior art date
Application number
PCT/CN2019/119212
Other languages
English (en)
French (fr)
Inventor
陈明东
黄越
胥畅
符珺
管音
陆江楠
Original Assignee
平安医疗健康管理股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安医疗健康管理股份有限公司 filed Critical 平安医疗健康管理股份有限公司
Publication of WO2020119402A1 publication Critical patent/WO2020119402A1/zh

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Definitions

  • the present application relates to the technical field of medical insurance, and in particular, to a method, device, device, and computer-readable storage medium for recognizing unrelated medication.
  • the main purpose of the present application is to provide an identification method, device, equipment and computer-readable storage medium for irrelevant medication, aiming to solve the problem that the insured person cannot recognize the behavior of irrelevant medication.
  • the present application provides a method for identifying irrelevant medication.
  • the method includes the following steps:
  • the target attribute value and the preset attribute value included in the range of traditional Chinese medicine and the preset attribute value included in the range of western medicine to determine whether there is a drug that does not belong to the drug range of the disease type;
  • the present application further provides a terminal, the terminal includes a processor, a memory, and computer readable instructions stored on the memory and executable by the processor, wherein the computer can When the read instruction is executed by the processor, the steps of the method for identifying irrelevant medication as described above are realized.
  • the present application also provides a readable storage medium that stores computer readable instructions, wherein when the computer readable instructions are executed by a processor, the implementation is as described above The steps of the method of identifying irrelevant medication.
  • FIG. 1 is a schematic diagram of a hardware structure of a terminal involved in a solution of an embodiment of this application;
  • FIG. 2 is a schematic flowchart of a third embodiment of a method for recognizing irrelevant medication in this application;
  • FIG. 3 is a schematic flowchart of a fourth embodiment of a method for identifying irrelevant medications of the application
  • FIG. 4 is a schematic flowchart of a fifth embodiment of a method for identifying irrelevant medications of the application
  • FIG. 5 is a schematic flowchart of a sixth embodiment of a method for identifying irrelevant medications of the present application.
  • the method for identifying irrelevant medications involved in the embodiments of the present application is mainly applied to a terminal, and the terminal may be a device with display and processing functions such as a PC, a portable computer, and a mobile terminal.
  • FIG. 1 is a schematic structural diagram of a terminal involved in a solution according to an embodiment of this application.
  • the terminal may include a processor 1001 (for example, a CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
  • the communication bus 1002 is used to realize the connection and communication between these components;
  • the user interface 1003 may include a display (Display), an input unit such as a keyboard (Keyboard);
  • the network interface 1004 may optionally include a standard wired interface, a wireless interface (Such as WI-FI interface);
  • the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk storage, the storage 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • FIG. 1 does not constitute a limitation on the device, and may include more or less components than those illustrated, or combine some components, or arrange different components.
  • the memory 1005 in FIG. 1 as a computer-readable storage medium may include an operating system, a network communication module, and computer-readable instructions.
  • the network communication module is mainly used to connect to a server and perform data communication with the server; and the processor 1001 can call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • the target attribute value and the preset attribute value included in the medication range it is determined whether there is a drug that does not belong to the medication range of the disease type.
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • the step of determining whether there is a medicine that does not belong to the medication range of the disease type according to the target attribute value and the preset attribute value included in the medication range includes:
  • the target attribute value and the preset attribute value included in the range of traditional Chinese medicine and the preset attribute value included in the range of western medicine it is determined whether there is a drug that does not belong to the drug range of the disease type.
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • the medicine to which the object set belongs it is determined whether there is an object set that does not belong to the medication range of the disease type in the plurality of object sets.
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • the medicine purchase time of the object set that does not belong to the medicine range of the disease is acquired according to the second preset rule.
  • processor 1001 can also call computer-readable instructions stored in the memory 1005 and perform the following operations:
  • the embodiments of the present application provide a method for identifying irrelevant medication.
  • the method for identifying irrelevant medication includes the following steps:
  • Step S10 Obtain the medication details of the insured person, and confirm the disease type of the insured person;
  • the medication details of the insured persons in the embodiments of the present application can be executed by the terminal, and the terminal can perform data communication with the server, and the server is in communication connection with multiple medical institution management systems and multiple pharmacies.
  • the insured's medication details include the medical details of the insured's treatment at the hospital, as well as the medical purchases resulting from the insured's purchase of drugs at the pharmacy.
  • the terminal may also be directly connected to the management system of the medical institution or pharmacy. In this case, the terminal is used by the medical institution or pharmacy for self-time supervision of the medical institution or pharmacy.
  • the medication details of the insured person when the medication details are the diagnosis and treatment details, the disease details of the insured person are recorded in the diagnosis and treatment details. At this time, the disease types of the insured person are directly obtained from the diagnosis and treatment details.
  • the medication details are drug purchase details, you can retrieve the insured's medical records from the hospital system based on the insured's information, and confirm the insured's illness from the insured's medical records.
  • Step S20 obtaining the medication range corresponding to the disease type from a preset database
  • the preset database stores the allowable medication ranges for various diseases.
  • the preset database can be stored in the terminal, server or medical institution. According to the confirmed disease type of the insured person, the medication range corresponding to the insured person's disease type is obtained from the preset database.
  • step S30 it is determined whether there is a medicine that does not belong to the medicine range of the disease type in the medication details.
  • the drug described in the medication details is compared with the drugs included in the medication range to determine whether there are drugs in the medication details that do not fall within the medication range.
  • the medicine range corresponding to each disease type stored in the preset database is stored in a standardized field, and the same medicine has the same standardized field regardless of the form in which it exists. For example, the same medicine in the form of granules, pills, or capsules has the same standardized field.
  • the standardization process can be through the diagnosis and treatment details data obtained from the terminal (such as the core system of the human society), using the existing NLP processing process, through the cleaning model processing, to achieve the matching of field standardization.
  • the main working mechanism is to use the RNN model to analyze longer and more complex text content, such as diagnosis and treatment data, medicine data, disease data, etc., for the non-standard fields, while expressing both the word itself and the semantic distance.
  • a two-way RNN model is used to encode the vectors into a sentence vector matrix. Each row of this matrix can be understood as a word vector —— They are sensitive to the context of the sentence.
  • the last step is called the attention mechanism. This can compress the sentence matrix into a sentence vector for prediction. By issuing diagnosis information, medicine information, and disease type information to doctors, they are matched into corresponding standardized fields.
  • a standardized detail list corresponding to the medicine details is formed, and the medicine range corresponding to the acquired disease type includes standardized fields corresponding to the medicines.
  • the standardized detailed list and the standardized medication range are input to the irrelevant medication identification model through the observation interface and the reference interface, respectively, and the irrelevant medication identification model calculates the medicine (observed value) and the standardized medication range (reference value) in the standardized detailed list through operation Compare one by one and output the result.
  • the mechanism of the irrelevant medication identification model can be based on the existing deviation detection model. The deviation specifically refers to anomalous instances in the classified samples, special cases that do not meet the rules, or values where the observation results are inconsistent with the model predictions and change over time.
  • the basic goal of deviation detection is to find meaningful differences between observations and reference values.
  • the main deviation techniques involved are clustering, sequence anomalies, nearest neighbor method, and multidimensional data analysis.
  • the algorithm for identifying anomalies in this model is mainly an anomaly detection algorithm based on distance.
  • the main core algorithm is the index-based algorithm, that is, given a data set, the index-based algorithm uses a multi-dimensional index structure R-tree, k-d tree, etc., to find the neighbor of each object within the radius d.
  • M is the maximum number of objects in the d field of the outlier data. If the object O When M+l neighbors are found, object O is not an anomaly.
  • the worst-case complexity of this algorithm is O(k*n2), k is the number of dimensions, and n is the number of objects in the data set. When k increases, the index-based algorithm has good scalability.
  • Step S40 if there is a drug in the medication details that does not belong to the medication range of the disease type, it is marked that the insured person has an act of irrelevant medication.
  • the insured After comparing the drugs listed in the drug details of the insured person with the drugs contained in the drug range by the above method, determine whether there are drugs in the drug details of the insured person that do not belong to the drug range of the diseased species of the insured person, If there is a drug in the medication details that does not belong to the scope of the insured's disease, then the insured is marked as having an unrelated medication. If there is no medication in the medication detail that does not belong to the insured's disease In the case of drugs, it means that the insured person does not have irrelevant medication, and the whole process ends.
  • the drug range corresponding to the diseased type is obtained from the preset database to determine whether the drug details do not belong to the For the drugs of the diseased species, if there is a drug in the medication list that does not belong to the drug category of the diseased species, then the insured person will be marked to have an unrelated drug behavior.
  • This technical solution determines whether the insured person has any illegal operation of irrelevant medication by judging whether the insured person's medication details do not belong to the disease category, which is conducive to supervising the doctor's drug prescribing behavior and avoiding the doctor's prescription for the patient Drugs that are irrelevant to the condition can also monitor the pharmacy's behavior of not selling drugs according to prescriptions, which helps to avoid the waste and illegal use of outpatient co-ordination funds and protect public interests.
  • step S30 includes steps:
  • Step S31 extract the target attribute value of each medicine in the medication details
  • Step S32 According to the target attribute value and the preset attribute value included in the medication range, determine whether there is a drug that does not belong to the medication range of the disease type.
  • each drug can be assigned a unique attribute value.
  • the attribute value can be the name of the main ingredient of the drug, the chemical formula of the main ingredient of the drug, or a numeric number, etc.
  • the attribute value of the drug is composed of the disease code and the numeric number. If the attribute value of the drug is XZB-000001, the drug is used to treat heart disease Drug No. 000001. Each drug has its own unique attribute value.
  • Step S40 is executed to mark the insured person as an irrelevant drug behavior.
  • the target attribute value matches the preset attribute value it means that the drugs in the medication details all belong to the range of medication of the diseased species. At this time, the insured person has unrelated medication behavior, and the insured person's insured behavior is normal.
  • FIG. 2 is a schematic flowchart of a third embodiment of a method for identifying irrelevant medications of the present application. Based on the above embodiment, step S20 includes:
  • Step S21 Acquire the Chinese medicine use range and the Western medicine use range corresponding to the disease type from the preset database.
  • Step S32 includes:
  • step S321 according to the target attribute value and the preset attribute value included in the Chinese medicine range and the preset attribute value included in the western medicine range, it is determined whether there is a drug that does not belong to the disease category.
  • the medication range of each disease type in the preset database is classified according to traditional Chinese medicine and western medicine. Obtain the Chinese medicine usage range and the Western medicine usage range corresponding to the diseased species from the preset database.
  • the attribute values of drugs include disease code and number code, and can also include traditional Chinese medicine code and western medicine code. For example, XZB-01-000001, 01 means Chinese medicine, 02 means Western medicine.
  • step S40 is executed to mark the insured person for the existence of irrelevant medicine behavior.
  • target attribute values match the preset attribute values included in the range of traditional Chinese medicines and/or the preset attribute values included in the range of western medicines, it means that all the drugs in the drug details belong to the drug range of the disease type, see The insured’s participation is normal.
  • FIG. 3 is a schematic flowchart of a fourth embodiment of a method for identifying irrelevant medications of the present application. Based on the above embodiment, step S10 includes:
  • Step S11 Obtain the details of drug purchase of the insured person who has the qualification of outpatient chronic disease within a preset time period, and determine the disease type of the insured person;
  • Insured persons who are eligible for outpatient chronic diseases require long-term outpatient medication to maintain treatment and have higher medical costs.
  • insured persons with chronic diseases need to take drugs for a long time
  • chronic patients in outpatient clinics purchase drugs from designated units by providing prescription details.
  • it is necessary to supervise the drug purchase behavior of outpatient chronic patients. Obtain the drug purchase details of the insured persons who are qualified for outpatient chronic diseases within a preset period of time, and confirm the disease type of their insured persons through the medical history of the outpatient chronic patients.
  • step S12 the same medicine described in the drug purchase details is put into the same object set to obtain multiple object sets;
  • the preset time period can be one month, two months or one year, which is not limited here.
  • the same drugs recorded in multiple drug purchase details are grouped into the same object set to obtain multiple object sets.
  • Step S30 includes:
  • Step S33 According to the medicine to which the object set belongs, determine whether there is an object set that does not belong to the medication range of the disease type in the plurality of object sets.
  • the object set After obtaining a plurality of object sets, according to the medicines in the object set, it is determined whether there is an object set that does not belong to the medication range of the diseased species in the plurality of object sets.
  • the object set has the attribute values of the corresponding drugs.
  • By comparing the attribute value of the object set with the preset attribute value included in the medication range of the diseased species it is determined whether there is an object set in the drug purchase detail that does not belong to the drug range of the affected species, that is, whether the drug purchase detail There are drugs that do not fall within the scope of the diseased species.
  • the attribute value of the object set matches the preset attribute value of the medication range, it indicates whether there is no object set that does not belong to the medication range of the diseased species in the drug purchase details.
  • the attribute value of the object set and the medication range are predicted If the attribute value does not match, it means that there is an object set in the drug purchase list that does not belong to the scope of the diseased drug, and it means that the insured person has irrelevant drug behavior. Perform step S40 to mark the insured person as irrelevant drug. If the attribute value of the object set matches the preset attribute value of the medication range, it means that the object set in the drug purchase details all belong to the medication range of the diseased type, which means that the insured person's participation behavior is normal.
  • FIG. 4 is a schematic flowchart of a fifth embodiment of a method for recognizing irrelevant medication of this application. Based on the above embodiment, after step S40, it further includes:
  • Step S50 Obtain the drug purchase time of the object set that does not belong to the drug category of the disease type, and determine the issuance time according to the first preset rule according to the drug purchase time;
  • the drug purchase time of the object set that does not belong to the medication range of the diseased species is obtained, and the issuance time is determined according to the first preset rule according to the drug purchase time.
  • the issuance time refers to the issuance time of the details of the diagnosis and treatment on which the medicine of the subject set belongs. Since the object set may contain multiple drugs, the drug purchase time corresponding to the drug purchase details of each drug is different. Preferably, the earliest date of drug purchase and the latest date of drug purchase in the object set are selected, and the preset effective time of diagnosis details is calculated on the earliest date of drug purchase to obtain the earliest issue date of the diagnosis details.
  • the date from the latest to the date of drug purchase is the time interval for the issuance of the details of diagnosis and treatment.
  • the first preset rule stipulates that the effective time of the preset diagnosis and treatment details is 2 months, and the earliest date of the earliest issuance is calculated 2 months before the earliest date of drug purchase.
  • Step S60 Obtain the diagnosis and treatment details of the insured person within the prescribed time period from each medical institution, and determine whether there is a medicine corresponding to the object set that does not belong to the disease type medication range in the diagnosis and treatment details;
  • the medical details of the insured within the issuance time are obtained from each medical institution, and it is judged whether the medical details are in the medicine corresponding to the object set that is not within the scope of the diseased medication.
  • the medical institution has issued the diagnosis and treatment details for the insured person within the issuing time, it means that the insured person has been to the medical institution for consultation within the issuing time, and then obtain the medical institution for the insured person.
  • determine whether there is a drug corresponding to the target set that is not within the scope of the diseased medication in the diagnosis and treatment details to specifically determine which medical institution has prescribed the illegal drug for the insured, so that it is easy to determine the responsibility.
  • Step S70 if there is a drug in the diagnosis and treatment details that is related to the object set, an irrelevant medication report is generated.
  • the irrelevant medication report includes information of the insured person, information of medical institutions, illegal drugs and other information.
  • FIG. 5 is a schematic flowchart of a sixth embodiment of a method for identifying irrelevant medications of the present application. Based on the above embodiment, step S50 includes:
  • Step S51 Obtain the number of medicines in the object set that does not belong to the medicine range of the disease type
  • Step S52 judging whether the quantity of the medicine is greater than a preset threshold
  • Step S53 if the quantity of the medicine is greater than a preset threshold, then obtain the medicine purchasing time of the object set that does not belong to the medicine range of the disease according to the second preset rule;
  • Step S54 Determine the issuance time according to the first drug purchase time according to the drug purchase time.
  • the preset threshold is preferably 1.
  • the second preset rule is to select the earliest date of drug purchase and the latest date of drug purchase in the object set, and to calculate the effective time of the preset diagnosis details on the earliest date of drug purchase to obtain the earliest diagnosis details
  • the earliest date of issuance to the latest date of drug purchase is the interval of the time of issuance of the details of diagnosis and treatment.
  • the second preset rule stipulates that the earliest drug purchase date and the latest drug purchase date in the object set are selected as the drug purchase time between the earliest drug purchase date and the latest drug purchase date. The time is the earliest date on which the effective time of the pre-set diagnosis details is calculated from the middle day forward to obtain the diagnosis details.
  • the earliest issuance date to the latest purchase date is the interval of the issuance time of the diagnosis details.
  • the first preset rule stipulates that the effective time of the preset diagnosis and treatment details is 2 months, and the earliest date of the earliest issuance is calculated 2 months before the earliest date of drug purchase.
  • step S70 it includes:
  • Step S80 Send a warning reminder message to the medical institution and the management institution, where the warning reminder message includes the abnormal medication report.
  • a warning message is issued to the relevant medical institution or physician, and the warning message includes the penalty level and the irrelevant medication report.
  • the warning information is sent to the relevant medical institution by mail, announcement or letter.
  • Identification devices for irrelevant medication include:
  • the information acquisition module is used to obtain the medication details of the insured person, and to determine the disease type suffered by the insured person, and to obtain the medication range corresponding to the disease type from a preset database;
  • the judgment module is used for judging whether the medicine in the medicine list contains medicines that are not in the medicine range of the disease type;
  • the marking module is configured to mark the insured person for violations of irrelevant medication if there are drugs in the medication details that do not belong to the medication range of the disease type.
  • the identification device for irrelevant medication also includes:
  • An extraction module used to extract the target attribute value of each medicine in the medication details
  • the judgment module is further configured to judge whether there is a medicine that does not belong to the medicine range of the disease type according to the target attribute value and the preset attribute value included in the medicine range.
  • the information acquisition module is also used to acquire the range of traditional Chinese medicine and the range of western medicine corresponding to the disease type from a preset database;
  • the judging module is also used to judge whether there is a medicine range that does not belong to the disease type according to the target attribute value and the preset attribute value included in the Chinese medicine range and the preset attribute value included in the western medicine range medicine.
  • the information acquisition module is also used to acquire the details of drug purchases of insured persons who are eligible for outpatient chronic diseases within a preset time period, and determine the types of diseases of the insured persons;
  • the classification module is used to classify the same drug described in the drug purchase details into the same object set to obtain multiple object sets;
  • the judging module is also used to judge whether there is an object set that does not belong to the medicine range of the disease type according to the medicine to which the object set belongs.
  • the identification device for irrelevant medication also includes:
  • the calculation module is used to obtain the time of drug purchase of the object set that does not belong to the range of medicines for the disease type, and determine the time of issuance according to the first preset rule according to the time of drug purchase;
  • the information acquisition module is also used to obtain the medical details of the insured person within the prescribed time from various medical institutions;
  • the judging module is also used to judge whether there is a medicine corresponding to the object set that does not belong to the medicine range of the disease in the diagnosis and treatment details;
  • the labeling module is also used to generate an irrelevant medication report if there is a drug corresponding to the object set that does not belong to the medication range of the disease type in the diagnosis and treatment details.
  • classification module is also used to obtain the number of medicines in the object set that does not belong to the medicine range of the disease type
  • the judgment module is also used to judge whether the quantity of the medicine is greater than a preset threshold
  • the calculation module is also used to obtain the drug purchase time of the object set that does not belong to the medicine range of the disease according to the second preset rule if the number of the drugs is greater than a preset threshold.
  • the identification device for irrelevant medication also includes:
  • the reminding unit is used to send warning reminding information to the medical institution and the management institution, and the warning reminding information includes the irrelevant medication report.
  • each module in the identification device for irrelevant medication corresponds to the steps in the embodiment of the method for identifying irrelevant medication, and its function and implementation process will not be repeated here one by one.
  • an embodiment of the present application further provides a readable storage medium, and the computer-readable storage medium may be a non-volatile readable storage medium.
  • Computer readable instructions are stored on the readable storage medium, where when the computer readable instructions are executed by the processor, the steps of the method for recognizing irrelevant medication of any of the above embodiments are implemented.
  • the methods in the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware, but in many cases the former is better Implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or part that contributes to the existing technology, and the computer software product is stored in a storage medium (such as ROM/RAM as described above) , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to perform the method described in each embodiment of the present application.

Abstract

本申请提供一种无关用药的识别方法、装置、终端及计算机可读存储介质。无关用药的识别方法包括获取参保人的用药明细，并确认参保人所患的病种，从预设数据库中获取与所患病种对应的用药范围，判断用药明细中是否存在不属于所患病种的用药范围的药物，若存在，则标记参保人存在无关用药的行为。

Description

无关用药的识别方法、装置、终端及计算机可读存储介质
本申请要求于2018年12月13日提交中国专利局、申请号为201811531032.9、发明名称为“无关用药的识别方法、装置、终端及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及医疗保险技术领域，尤其涉及一种无关用药的识别方法、装置、设备及计算机可读存储介质。
背景技术
在医疗领域中，存在许多欺诈行为，例如患者只患有糖尿病，诊疗明细中却开出了与治疗糖尿病无关的药物，如此不仅容易造成部分药品的紧缺，多开出的药物流入市场还会引起市场乱象，且也会导致社保门诊统筹基金的浪费。而现有技术中，虽然能够根据参保人的信息查询到相关的诊疗明细了解参保人的用药情况，但是并不能确定参保人的诊疗明细或者购药明细中是否存在与参保人病情无关的药物，无法对违规使用无关用药的行为进行监督。
发明内容
本申请的主要目的在于提供一种无关用药的识别方法、装置、设备及计算机可读存储介质，旨在解决不能识别出参保人存在无关用药的行为的问题。
为实现上述目的，本申请提供一种无关用药的识别方法，所述识别方法包括以下步骤：
获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种；
从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
提取所述用药明细中的各药物的目标属性值；
根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物；
若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
此外，为实现上述目的，本申请还提供一种终端，所述终端包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如上述所述的无关用药的识别方法的步骤。
此外，为实现上述目的，本申请还提供一种可读存储介质，所述可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如上述所述的无关用药的识别方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其他特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
图1为本申请实施例方案中涉及的终端的硬件结构示意图；
图2为本申请无关用药的识别方法第三实施例的流程示意图；
图3为本申请无关用药的识别方法第四实施例的流程示意图；
图4为本申请无关用药的识别方法第五实施例的流程示意图；
图5为本申请无关用药的识别方法第六实施例的流程示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例涉及的无关用药的识别方法主要应用于终端，该终端可以是PC、便携计算机、移动终端等具有显示和处理功能的设备。
参照图1，图1为本申请实施例方案中涉及的终端结构示意图。本申请实施例中，终端可以包括处理器1001（例如CPU），通信总线1002，用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信；用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard）；网络接口1004可选的可以包括标准的有线接口、无线接口（如WI-FI接口）；存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器，存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的硬件结构并不构成对设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
继续参照图1，图1中作为一种计算机可读存储介质的存储器1005可以包括操作系统、网络通信模块以及计算机可读指令。
在图1中，网络通信模块主要用于连接服务器，与服务器进行数据通信；而处理器1001可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
获取参保人的用药明细，并确认所述参保人所患的病种；
从预设数据库中获取与所述病种对应的用药范围；
判断所述用药明细中是否存在不属于所述病种的用药范围的药物；
若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
提取所述用药明细中的各药物的目标属性值；
根据所述目标属性值与所述用药范围所包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
所述根据所述目标属性值与所述用药范围所包含的预设属性值判断是否存在不属于所述病种的用药范围的药物的步骤包括：
根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
所述判断所述用药明细中的药物是否存在不属于所述病种的用药范围的药物的步骤包括：
根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细，判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
获取不属于所述病种的用药范围的对象集内的药物的数量；
判断所述药物的数量是否大于预设阈值；
若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
进一步地，处理器1001还可以调用存储器1005中存储的计算机可读指令，并执行以下操作：
发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
基于上述终端的硬件结构，提出本申请无关用药的识别方法的各个实施例。
本申请实施例提供了一种无关用药的识别方法。
本申请实施例中，无关用药的识别方法包括步骤：
步骤S10，获取参保人的用药明细，并确认所述参保人所患的病种；
本申请实施例中的参保人用药明细可以通过终端执行，终端能够与服务器进行数据通信，服务器与多个医疗机构管理系统和多个药店之间通信连接。参保人的用药明细包括参保人在医院就诊产生的诊疗明细，也包括参保人在药店购药所产生的购药明细。参保人在药店自行购药或者在医疗机构取药结算时，参保人的诊疗明细和购药明细通过服务器上传至终端。在其他实施例中，终端还可以与医疗机构或者药店的的管理系统进行直接连接，此时终端为医疗机构或者药店所使用，用于医疗机构或者药店的自我时监督。
获取参保人的用药明细时，当用药明细是诊疗明细时，诊疗明细中记载了参保人所患的病种，此时直接从诊疗明细中获取参保人所患的病种。当用药明细是购药明细时，则可以根据参保人的信息从医院系统中调取参保人的就诊记录，从参保人的就诊记录中确认参保人所患的病种。
步骤S20，从预设数据库中获取与所述病种对应的用药范围；
预设数据库中保存有各种病种所允许的用药范围。预设数据库可以保存在终端、服务器或者医疗机构等。根据所确认的参保人所患的病种，从预设数据库获取与参保人的病种对应的用药范围。
步骤S30，判断所述用药明细中是否存在不属于所述病种的用药范围的药物。
根据获得的与参保人的病种对应的用药范围，将用药明细中记载的药物与用药范围内包含的药物进行对比，判断用药明细中是否存在不属于用药范围的药物。预设数据库内保存的各个病种对应的用药范围以标准化字段保存，同一药物不管以何种形式存在均具有相同的标准化字段。如以颗粒状、药丸状、胶囊状存在的同一药物具有同一标准化字段。当诊疗明细和购药明细中记载的药物尚未标准化时，则需要识别诊疗明细和购药明细中记载的药物，对并其进行标准化字段设置，以便于对比。
利用预设分析机制分析用药明细中记载的药物，并将其标准化。标准化过程可以是通过针对终端（如人社核心系统）获取的诊疗明细数据，利用现有的NLP处理流程，通过清洗模型的处理，实现对字段标准化的匹配。主要工作机制是，对不规范的字段，在既表示词本身又可以考虑语义距离的要求下，利用RNN模型分析更长更复杂的文本内容，如诊疗数据、药品数据、疾病数据等。将文本用一个向量的序列表示之后，使用双向RNN模型将向量编码为一个句子向量矩阵。这个矩阵的每一行可以理解为词向量 —— 它们对句子的上下文敏感。最后一步被称为注意力机制。这可以将句子矩阵压缩成一个句子向量，用于预测。通过对医生出具诊断信息、药品信息、病种信息匹配到相应的标准化字段中。
通过预设分析机制将用药明细的药物匹配到相应的标准化字段后，形成与该用药明细对应的标准化明细列表，获取的病种对应的用药范围内包括有各药物对应的标准化字段。将标准化明细列表和已标准化的用药范围分别通过观察接口和参照接口输入至无关用药识别模型，无关用药识别模型通过运算将标准化明细列表中药物（观察值）与已标准化的用药范围（参照值）进行逐一对比，并输出结果。无关用药识别模型的机制可以是基于现有的偏差检测模型，偏差具体指分类样本中的反常实例、不满足规则的特例，或者观测结果与模型预测值不一致并随时间的变化的值等等。偏差检测的基本目标是寻找观测结果与参照值之间有意义的差别，涉及的主要的偏差技术有聚类、序列异常、最近邻居法、多维数据分析等。本模型识别异常的算法主要是基于距离的异常点检测算法。其中主要的核心算法是基于索引的算法，即给定一个数据集合，基于索引的算法采用多维索引结构 R-树，k-d树等，来查找每个对象在半径 d范围内的邻居。假设 M为异常点数据的d领域内的最大对象数目。如果对象O的 M+l个邻居被发现，则对象O就不是异常点。这个算法在最坏情况下的复杂度为O(k*n2)，k为维数，n为数据集合中对象的数目。当k增加时，基于索引的算法具有良好的扩展性。
步骤S40，若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
通过上述方法将参保人的用药明细记载的药物与用药范围包含的药物进行逐一对比之后，判断参保人的用药明细中是否存在不属于参保人的所患病种的用药范围的药物，若用药明细中存在不属于参保人所患病种的用药范围的药物，则标记参保人存在无关用药的行为，若用药明细中不存在不属于参保人所述病种的用药范围的药物时，则说明参保人不存在无关用药的行为，整个流程结束。
上述技术方案中，通过获取参保人的用药明细，并确认参保人所患的病种，从预设数据库中获取与所患病种对应的用药范围，判断用药明细中是否存在不属于所患病种的用药范围的药物，若用药明细中存在不属于所患病种的用药范围的药物，则标记参保人存在无关用药的行为。本技术方案通过判断参保人的用药明细中是否存在不属于其病种对应的用药范围来判断参保人的是否存在无关用药的违规操作，有利于监管医生开药行为，避免医生为患者开具无关病情的药物，同时还能够对药店的不按照处方售药的行为进行监督，有利于避免门诊统筹基金的浪费和非法使用，保护公共利益。
基于上述实施例，步骤S30包括步骤：
步骤S31，提取所述用药明细中的各药物的目标属性值；
步骤S32，根据所述目标属性值与所述用药范围所包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
为了便于简化药物对比流程，加快药物对比速度，可以将各个药物分配一专属属性值。属性值可以药物主要成分名称、药物主要成分化学式，或者数字编号等，优选地，药物属性值由病种代号和数字编号组成，如药物属性值为XZB-000001，则药物用于为治疗心脏病的第000001号药物。每一种药物对应有其专属的属性值。提取用药明细中各药物的目标属性值，将用药明细中各药物的目标属性值与用药范围所包含的预设属性值进行逐一对比，当用药明细中的目标属性值与预设属性值不匹配时，则说明用药明细中存在不属于所患病种的用药范围的药物，此时说明参保人存在无关用药的行为，执行步骤S40将参保人标记为存在无关用药的行为。当目标属性值与预设属性值匹配时，则说明用药明细中的药物均属于所患病种的用药范围，此时参保人存在无关用药的行为，参保人的参保行为正常。
参照图2，图2为本申请无关用药的识别方法第三实施例的流程示意图。基于上述实施例，步骤S20包括：
步骤S21，从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围。
步骤S32包括：
步骤S321，根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
预设数据库中的各个病种的用药范围按照中药和西药进行分类。从预设数据库中获取所患病种对应的中药用药范围和西药用药范围。药物的属性值包括病种代号和数字编号外，还可以包括中药代号和西药代号。例如XZB-01-000001，01表示为中药，02表示为西药。将目标属性值分别与中药用药范围包含的预设属性值和西药用药范围包含的预设属性值进行对比，优选的，先将目标属性值与中药用药范围包含的预设属性值进行逐一对比，若部分目标属性值与中药用药范围包含的预设属性值不匹配，则不匹配的目标属性值与西药用药范围包含的预设属性值进行对比，当目标属性值均不与中药用药范围包含的预设属性值和西药用药范围包含的预设属性值匹配时，则说明所述用药明细中存在不属于所述病种的用药范围的药物，则执行步骤S40，标记参保人存在无关用药的行为。若目标属性值均与中药用药范围包含的预设属性值和/或西药用药范围包含的预设属性值匹配时，则说明所述用药明细中的药物全部属于所述病种的用药范围，参保人的参保行为正常。
参照图3，图3为本申请无关用药的识别方法第四实施例的流程示意图。基于上述实施例，步骤S10包括：
步骤S11，获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
具有门诊慢性疾病资格的参保人需要长期门诊用药以维持治疗且医疗费用较高。为了减缓门诊慢性病人的经济压力，对于门诊慢性疾病的参保人的医保报销制定有特定的报销政策。由于门诊慢性疾病的参保人需要长期服用药物，因此门诊慢性病人通过是通过提供处方明细向定点单位购买药物。为了对门诊慢性病人的用药情况进行监督，有必要对门诊慢性病人的购药行为进行监督。获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并通过门诊慢性病人的病史确认其参保人所患的病种。
步骤S12，将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
预设时间段可以为一个月、两个月或者一年，在此不限定。在预设时间段内，参保人在定点单位产生的购药明细可能存在若干张，为了加快识别，将多张购药明细中记载的同一药物归入同一对象集，得到多个对象集。
步骤S30包括：
步骤S33，根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
得到多个对象集之后，根据对象集所述的药物，判断多个对象集中是否存在不属于所患病种的用药范围的对象集。对象集拥有与其对应的药物的属性值。通过对比对象集的属性值与所患病种的用药范围包含的预设属性值，判断所述购药明细中是否存在不属于所患病种的用药范围的对象集，即购药明细中是否存在不属于所患病种的用药范围的药物。当对象集的属性值与用药范围的预设属性值匹配时，则说明购药明细中是否不存在不属于所患病种的用药范围的对象集，当对象集的属性值与用药范围的预设属性值不匹配时，则说明购药明细中存在不属于所患病种的用药范围的对象集，则说明参保人存在无关用药的行为，执行步骤S40将参保人标记为存在无关用药的行为，若当对象集的属性值与用药范围的预设属性值均匹配时，说明购药明细中的对象集全部属于所患病种的用药范围，则说明参保人参保行为正常。
参照图4，图4为本申请无关用药的识别方法第五实施例的流程示意图。基于上述实施例，步骤S40之后还包括：
步骤S50，获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
当对象集的属性值与用药范围的预设属性值不匹配时，获取不属于所患病种用药范围的对象集的购药时间，并根据购药时间按照第一预设规则确定开具时间。开具时间是指对象集所属药物所依据的诊疗明细的开具时间。由于对象集可能包含有多个药物，因此每个药物对应的购药明细的购药时间不同。优选地，选取对象集内最早的购药之日和最晚的购药之日，并在最早购药之日上往前推算预设诊疗明细有效时间得到诊疗明细的最早开具之日，最早开具之日至最晚购药之日为诊疗明细的开具时间的区间。优选地，第一预设规则规定预设诊疗明细有效时间为2个月，则最早购药之日往前推算2个月得到最早开具之日。
步骤S60，从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细，判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
根据得到的开具时间，从各个医疗机构中获取参保人的在开具时间内的诊疗明细，并判断诊疗明细中是否处在与不属于所患病种用药范围的对象集对应的药物。在此过程中，若医疗机构在开具时间内为参保人开具了诊疗明细，即说明参保人在开具时间内曾经去该医疗机构就诊，则获取该医疗机构为参保人开具的诊疗明细，并判断诊疗明细中是否存在与不属于所患病种用药范围的对象集对应的药物，以具体确定是哪个医疗机构为参保人开具了违规的药物，便于定责。
步骤S70，若诊疗明细中存在与所述对象集所述的药物，则生成无关用药报告。
若诊疗明细中部存在与不属于所患病种用药范围的对象集对应的药物时，则说明出具该诊疗明细的医疗机构存在违规行为，生成无关用药报告。无关用药报告中包括参保人的信息、医疗机构信息、违规药物等信息。
参照图5，图5为本申请无关用药的识别方法第六实施例的流程示意图。基于上述实施例，步骤S50包括：
步骤S51，获取不属于所述病种的用药范围的对象集内的药物的数量；
步骤S52，判断所述药物的数量是否大于预设阈值；
步骤S53，若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间；
步骤S54，根据所述购药时间按照第一预设规则确定开具时间。
判断出不属于所患病种的用药方位的对象集内的药物的数量，当药物的数量大于预设阈值时，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间，并根据确定的购药时间按照第一预设规则确定开具时间。其中预设阈值优选为1。优选地，第二预设规则是选取对象集内最早的购药之日和最晚的购药之日，并在最早购药之日上往前推算预设诊疗明细有效时间得到诊疗明细的最早开具之日，最早开具之日至最晚购药之日为诊疗明细的开具时间的区间。或者第二预设规则规定选取对象集内最早的购药之日和最晚的购药之日后取最早的购药之日和最晚的购药之日的中间之日作为购药时间，开具时间则为中间之日往前推算预设诊疗明细有效时间得到诊疗明细的最早开具之日，最早开具之日至最晚购药之日为诊疗明细的开具时间的区间。优选地，第一预设规则规定预设诊疗明细有效时间为2个月，则最早购药之日往前推算2个月得到最早开具之日。
基于上述实施例，步骤S70之后包括：
步骤S80，发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述异常用药报告。
当生成无关用药报告后，向相关医疗机构或医师发出警示消息，警示消息中包括有惩罚等级和无关用药报告。如此，医保工作人员通过警报提醒发现无关用药行为的对象之后，将警示信息以为邮件、公告或者书信等方式发送至相关医疗机构。
此外，本申请实施例还提供一种无关用药的识别装置。无关用药的识别装置包括：
信息获取模块，用于获取参保人的用药明细，并确定参保人所患的病种，并用于从预设数据库中获取与所述病种对应的用药范围；
判断模块，用于判断所述用药明细中的药物是否存在不属于所述病种的用药范围的药物；
标记模块，用于若所述用药明细中的药物存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的违规行为。
进一步地，无关用药的识别装置还包括：
提取模块，用于提取所述用药明细中的各药物的目标属性值；
判断模块，还用于根据所述目标属性值与所述用药范围所包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
进一步地， 信息获取模块，还用于从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
判断模块，还用于根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物。
进一步地，信息获取模块，还用于获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
分类模块，用于将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
判断模块，还用于根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
进一步地，无关用药的识别装置还包括：
计算模块，用于获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
信息获取模块，还用于从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细；
判断模块，还用于判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
标记模块，还用于若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
进一步地，分类模块，还用于获取不属于所述病种的用药范围的对象集内的药物的数量；
判断模块，还用于判断所述药物的数量是否大于预设阈值；
计算模块，还用于若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
进一步地，无关用药的识别装置还包括：
提醒单元，用于发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
其中，上述无关用药的识别装置中各个模块的功能实现与上述无关用药的识别方法实施例中各步骤相对应，其功能和实现过程在此处不再一一赘述。
此外，本申请实施例还提供一种可读存储介质，所述计算机可读存储介质可以为非易失性可读存储介质。可读存储介质上存储有计算机可读指令，其中计算机可读指令被处理器执行时，实现上述任一实施例的无关用药的识别方法的步骤。
其中，计算机可读指令被执行时所实现的方法可参照本申请多网页方案测试方法的各个实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种无关用药的识别方法，其中，所述识别方法包括以下步骤：
    获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种；
    从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
    提取所述用药明细中的各药物的目标属性值；
    根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物；
    若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
  2. 如权利要求1所述的无关用药的识别方法，其中，所述获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种的步骤包括：
    获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
    将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
    所述判断所述用药明细中的药物是否存在不属于所述病种的用药范围的药物的步骤包括：
    根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
  3. 如权利要求2所述的无关用药的识别方法，其中，所述若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为的步骤之后，所述识别方法还包括：
    获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
    从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细，判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
    若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
  4. 如权利要求3所述的无关用药的识别方法，其中，所述获取不属于所述病种的用药范围的对象集的购药时间的步骤包括：
    获取不属于所述病种的用药范围的对象集内的药物的数量；
    判断所述药物的数量是否大于预设阈值；
    若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
  5. 如权利要求3所述的无关用药的识别方法，其中，所述若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告的步骤之后，所述识别方法还包括：
    发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
  6. 一种无关用药的识别装置，其中，所述识别装置包括：
    信息获取模块，所述信息获取模块用于获取参保人的用药明细，并确定参保人所患的病种，并用于从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
    判断模块，所述判断模块用于提取所述用药明细中的各药物的目标属性值；根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物；
    标记模块，所述标记模块用于若所述用药明细中的药物存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的违规行为。
  7. 如权利要求6所述的无关用药的识别装置，其中，所述信息获取模块还用于获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；所述无关用药的识别装置，还包括：
    分类模块，用于将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
    所述判断模块还用于根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
  8. 如权利要求7所述的无关用药的识别装置，其中，所述无关用药的识别装置，还包括：
    计算模块，用于获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
    所述信息获取模块，还用于从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细；
    所述判断模块，还用于判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
    所述标记模块，还用于若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
  9. 如权利要求8所述的无关用药的识别装置，其中，所述分类模块，还用于获取不属于所述病种的用药范围的对象集内的药物的数量；
    所述判断模块，还用于判断所述药物的数量是否大于预设阈值；
    所述计算模块，还用于若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
  10. 如权利要求8所述的无关用药的识别装置，其中，所述无关用药的识别装置，还包括：
    提醒单元，用于发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
  11. 一种终端，其中，包括处理器、存储器、以及存储在所述存储器上并可被所述处理器执行的计算机可读指令，其中所述计算机可读指令被所述处理器执行时，实现如下步骤：
    获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种；
    从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
    提取所述用药明细中的各药物的目标属性值；
    根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物；
    若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
  12. 如权利要求13所述的终端，其中，所述获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种的步骤包括：
    获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
    将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
    所述判断所述用药明细中的药物是否存在不属于所述病种的用药范围的药物的步骤包括：
    根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
  13. 如权利要求12所述的终端，其中，所述若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为的步骤之后，还包括：
    获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
    从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细，判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
    若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
  14. 如权利要求13所述的终端，其中，所述获取不属于所述病种的用药范围的对象集的购药时间的步骤包括：
    获取不属于所述病种的用药范围的对象集内的药物的数量；
    判断所述药物的数量是否大于预设阈值；
    若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
  15. 如权利要求13所述的终端，其中，所述若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告的步骤之后，还包括：
    发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
  16. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有计算机可读指令，其中所述计算机可读指令被处理器执行时，实现如下步骤：
    获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种；
    从预设数据库中获取与所述病种对应的中药用药范围和西药用药范围；
    提取所述用药明细中的各药物的目标属性值；
    根据所述目标属性值分别与所述中药用药范围包含的预设属性值和与所述西药用药范围包含的预设属性值判断是否存在不属于所述病种的用药范围的药物；
    若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为。
  17. 如权利要求16所述的计算机可读存储介质，其中，所述获取与多个医疗机构管理系统和多个药店之间通信连接的服务器上传的参保人的用药明细，并确认所述参保人所患的病种的步骤包括：
    获取具有门诊慢性疾病资格的参保人在预设时间段内的购药明细，并确定参保人的病种；
    将所述购药明细中记载的同一药物归入同一对象集，得到多个对象集；
    所述判断所述用药明细中的药物是否存在不属于所述病种的用药范围的药物的步骤包括：
    根据所述对象集所属的药物，判断所述多个对象集中是否存在不属于所述病种的用药范围的对象集。
  18. 如权利要求17所述的计算机可读存储介质，其中，所述若所述用药明细中存在不属于所述病种的用药范围的药物，则标记所述参保人存在无关用药的行为的步骤之后，还包括：
    获取不属于所述病种用药范围的对象集的购药时间，并根据所述购药时间按照第一预设规则确定开具时间；
    从各个医疗机构中获取所述参保人在所述开具时间内的诊疗明细，判断诊疗明细中是否存在与所述不属于所述病种用药范围的对象集对应的药物；
    若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告。
  19. 如权利要求18所述的计算机可读存储介质，其中，所述获取不属于所述病种的用药范围的对象集的购药时间的步骤包括：
    获取不属于所述病种的用药范围的对象集内的药物的数量；
    判断所述药物的数量是否大于预设阈值；
    若所述药物的数量是否大于预设阈值，则按照第二预设规则获取不属于所述病种用药范围的对象集的购药时间。
  20. 如权利要求18所述的计算机可读存储介质，其中，所述若诊疗明细中存在与所述不属于所述病种用药范围的对象集对应的药物，则生成无关用药报告的步骤之后，还包括：
    发送警示提醒信息至医疗机构和管理机构，所述警示提醒信息包括所述无关用药报告。
PCT/CN2019/119212 2018-12-13 2019-11-18 无关用药的识别方法、装置、终端及计算机可读存储介质 WO2020119402A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811531032.9A CN109671476A (zh) 2018-12-13 2018-12-13 无关用药的识别方法、装置、终端及计算机可读存储介质
CN201811531032.9 2018-12-13

Publications (1)

Publication Number Publication Date
WO2020119402A1 true WO2020119402A1 (zh) 2020-06-18

Family

ID=66144865

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/119212 WO2020119402A1 (zh) 2018-12-13 2019-11-18 无关用药的识别方法、装置、终端及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN109671476A (zh)
WO (1) WO2020119402A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109671476A (zh) * 2018-12-13 2019-04-23 平安医疗健康管理股份有限公司 无关用药的识别方法、装置、终端及计算机可读存储介质
CN110782261B (zh) * 2019-10-22 2022-08-16 泰康保险集团股份有限公司 药品信息处理方法、装置、设备及存储介质
CN111445343A (zh) * 2020-03-23 2020-07-24 平安医疗健康管理股份有限公司 风险医疗数据的识别方法、装置、计算机设备和存储介质
CN111402070A (zh) * 2020-03-23 2020-07-10 平安医疗健康管理股份有限公司 医疗信息识别方法、装置、计算机设备及存储介质
CN111951924A (zh) * 2020-08-14 2020-11-17 江苏云脑数据科技有限公司 一种异常用药行为检测方法及系统
CN114866351B (zh) * 2022-07-06 2022-10-14 湖南创星科技股份有限公司 一种基于区块链的区域医疗处方监管方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514576A (zh) * 2013-09-06 2014-01-15 深圳民太安信息技术有限公司 一种社保就诊违规套现的筛查方法
US20160132644A1 (en) * 2013-05-20 2016-05-12 Hitachi, Ltd. Health Care Information Process System
CN106530166A (zh) * 2016-08-31 2017-03-22 中国人民解放军总医院第附属医院 医院医保费用防拒付辅助管理信息系统及防拒付方法
CN107133437A (zh) * 2017-03-03 2017-09-05 平安医疗健康管理股份有限公司 监控药品使用的方法及装置
CN107451400A (zh) * 2017-07-11 2017-12-08 武汉金豆医疗数据科技有限公司 一种医疗行为监控方法和系统
CN109671476A (zh) * 2018-12-13 2019-04-23 平安医疗健康管理股份有限公司 无关用药的识别方法、装置、终端及计算机可读存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104182824B (zh) * 2014-08-08 2018-02-06 平安养老保险股份有限公司 一种识别医保报销违规行为的规则校验系统及校验方法
CN104537764B (zh) * 2014-12-31 2017-06-27 浙江大学 一种医保卡异常使用的检测方法和检测系统
CN104933324A (zh) * 2015-07-10 2015-09-23 庞健 处方用药识别方法及系统
CN106408141A (zh) * 2015-07-28 2017-02-15 平安科技（深圳）有限公司 异常费用自动提取系统及方法
CN105868977A (zh) * 2016-04-01 2016-08-17 深圳市至高通信技术发展有限公司 药品售卖监管的方法、系统及装置
CN107180156A (zh) * 2017-05-11 2017-09-19 杭州逸曜信息技术有限公司 用药信息处理方法
CN107451401A (zh) * 2017-07-11 2017-12-08 武汉金豆医疗数据科技有限公司 一种医保智能审核方法和系统
CN108538352B (zh) * 2018-03-19 2021-03-19 杭州逸曜信息技术有限公司 用药信息处理方法
CN108447536B (zh) * 2018-03-19 2022-01-25 杭州逸曜信息技术有限公司 基于疾病特征和疾病程度信息的用药信息处理方法
CN108766518A (zh) * 2018-06-08 2018-11-06 广州天恒信息科技有限公司 一种基于知识库规则的病生理状态与药物之间分析方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160132644A1 (en) * 2013-05-20 2016-05-12 Hitachi, Ltd. Health Care Information Process System
CN103514576A (zh) * 2013-09-06 2014-01-15 深圳民太安信息技术有限公司 一种社保就诊违规套现的筛查方法
CN106530166A (zh) * 2016-08-31 2017-03-22 中国人民解放军总医院第附属医院 医院医保费用防拒付辅助管理信息系统及防拒付方法
CN107133437A (zh) * 2017-03-03 2017-09-05 平安医疗健康管理股份有限公司 监控药品使用的方法及装置
CN107451400A (zh) * 2017-07-11 2017-12-08 武汉金豆医疗数据科技有限公司 一种医疗行为监控方法和系统
CN109671476A (zh) * 2018-12-13 2019-04-23 平安医疗健康管理股份有限公司 无关用药的识别方法、装置、终端及计算机可读存储介质

Also Published As

Publication number Publication date
CN109671476A (zh) 2019-04-23

Similar Documents

Publication Publication Date Title
WO2020119402A1 (zh) 无关用药的识别方法、装置、终端及计算机可读存储介质
WO2020119131A1 (zh) 用药方案异常的识别方法、装置、终端及可读存储介质
CN111145844B (zh) 综合医疗监管平台
WO2020078053A1 (zh) 医疗数据异常检测方法、装置、设备及存储介质
WO2020213843A1 (ko) 사용자 맞춤형 의료정보 제공 시스템 및 이의 구동방법
WO2020119403A1 (zh) 住院数据异常检测方法、装置、设备及可读存储介质
WO2020078058A1 (zh) 医疗数据异常识别方法、装置、终端及存储介质
WO2020119401A1 (zh) 医师违规执业的监控方法、监控服务端及存储介质
WO2020226456A1 (ko) 처방 정보를 통한 의료 정보 제공 방법 및 장치
WO2020119383A1 (zh) 医保监管方法、设备、装置及计算机可读存储介质
WO2018205373A1 (zh) 人伤理赔定损费用测算方法、装置、服务器和介质
WO2020119385A1 (zh) 基于数据分析的处方生成监测方法、装置、设备和介质
WO2020108111A1 (zh) 医保欺诈行为的识别方法、装置、设备及可读存储介质
WO2020119384A1 (zh) 基于大数据分析的医保异常检测方法、装置、设备和介质
WO2020087981A1 (zh) 风控审核模型生成方法、装置、设备及可读存储介质
WO2018004111A1 (ko) 사용자 단말, 서비스 제공장치, 스마트 체온계를 이용한 체온정보 수집 및 서비스 제공시스템, 이를 이용한 서비스 제공방법
Khaleghi et al. New ways to manage pandemics: using technologies in the era of COVID-19: a narrative review
WO2022035018A1 (ko) 클리닉 매니저 서비스 플랫폼 및 이를 제공하는 시스템
WO2020119118A1 (zh) 异常数据的处理方法、装置、设备及计算机可读存储介质
Lupton The quantified pandemic: digitised surveillance, containment and care in response to the COVID-19 crisis
WO2018088585A1 (ko) 복약 관리 방법 및 그 장치
WO2019124723A1 (ko) 의약품 관리 시스템 및 방법
KR20080042256A (ko) 약물부작용감시 시스템
Win et al. Electronic health record system risk assessment: a case study from the MINET
WO2020119120A1 (zh) 异常购药的识别方法、装置、终端及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19896739

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 15/10/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19896739

Country of ref document: EP

Kind code of ref document: A1