CN111402070A - Medical information identification method and device, computer equipment and storage medium - Google Patents
Medical information identification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111402070A CN111402070A CN202010207018.4A CN202010207018A CN111402070A CN 111402070 A CN111402070 A CN 111402070A CN 202010207018 A CN202010207018 A CN 202010207018A CN 111402070 A CN111402070 A CN 111402070A
- Authority
- CN
- China
- Prior art keywords
- medical
- medicine
- information
- similarity
- drug
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000003814 drug Substances 0.000 claims abstract description 321
- 229940079593 drug Drugs 0.000 claims abstract description 146
- 201000010099 disease Diseases 0.000 claims abstract description 62
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 62
- 230000002159 abnormal effect Effects 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 107
- 238000001914 filtration Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 8
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 10
- 238000003745 diagnosis Methods 0.000 description 5
- 206010000117 Abnormal behaviour Diseases 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000002552 dosage form Substances 0.000 description 2
- 208000019622 heart disease Diseases 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 201000006549 dyspepsia Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 208000024798 heartburn Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Chemical & Material Sciences (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a medical information identification method, a medical information identification device, computer equipment and a storage medium, and belongs to the field of medical information processing. According to the medical information identification method, the medical information identification device, the computer equipment and the storage medium, a medical list comprising medicine information of a patient is generated according to medical settlement data, and the medical list is analyzed according to the type of a target disease to generate a medicine similarity degree form; abnormal medicines corresponding to the target disease type are screened out from the medical list by utilizing the medicine similarity form, so that the purpose of accurately identifying the abnormal medicines in the medical documents is achieved, and the identification accuracy is high.
Description
Technical Field
The present invention relates to the field of medical information processing, and in particular, to a medical information identification method, apparatus, computer device, and storage medium.
Background
With the rapid increase of the scale of national basic medical insurance funds and medical expenses, few of them cheat the abnormal behavior of medical insurance funds. The abnormal behavior means that: fraudulent fraud corresponding to normal behavior. For example: abnormal behaviors of examination and medicine use, standard hospitalization behaviors reduction, operation counterfeiting behaviors and the like. Most of the existing medical insurance fee control systems integrate medical knowledge and clinical medical experience on the basis of massive medical data, and check the standard degree of each diagnosis and treatment process and the rationality of a prescription so as to judge the compliance of expense.
The inventor of the invention discovers in research that the existing medical insurance fee control system can judge whether the medicines in the prescription issued by the doctor are abnormal (for example, the doctor opens a plurality of medicines with the same function and different types in a bill, the dosage exceeds the standard, the medicine effect similarity of the medicines with the types aiming at a certain disease is high, the bill can be judged as an abnormal bill), the automatic identification cannot be realized, a person with medical knowledge is required, the manual examination and verification are carried out, the efficiency is low, and the accuracy is poor.
Disclosure of Invention
Aiming at the problem that the existing medical insurance charge control system cannot accurately identify whether the medicines issued in the medical documents are abnormal or not, a medical information identification method and a medical information identification device which aim at accurately identifying the abnormal medicines are provided.
The invention provides a medical information identification method, which comprises the following steps:
acquiring medical settlement data of patient objects in a medical database;
generating a medical list according to the medical settlement data, wherein the medical list comprises personal information, disease types and medicine information of each patient object;
analyzing the medical list according to the type of the target disease to generate a medicine similarity form;
and matching the medicine information in the medical list with the medicine similarity form according to the target disease type to acquire abnormal medicine information of the patient object.
Preferably, the generating a medical list according to the medical settlement data includes:
and according to a preset form template, extracting the disease type and the drug information of each patient object in the medical settlement data for single treatment to generate the medical list.
Preferably, the analyzing the medical list according to the target disease type to generate a drug similarity table includes:
extracting personal information and drug information of patient subjects in the medical checklist associated with the target disease type;
constructing a first scoring matrix according to the personal information and the drug information of the patient object;
processing the first scoring matrix by adopting a preset collaborative filtering algorithm to generate a first medicine similarity matrix;
weighting the first scoring matrix according to the medicine information to generate a second scoring matrix;
processing the second scoring matrix by adopting the collaborative filtering algorithm to generate a second medicine similarity matrix;
carrying out weighted average on the first medicine similarity matrix and the second medicine similarity matrix to generate a third medicine similarity matrix;
and matching each similarity medicine element in the third medicine similarity matrix with a preset range, extracting the matched similarity medicine elements, and generating the medicine similarity table.
Preferably, the processing the first scoring matrix by using a preset collaborative filtering algorithm to generate a first drug similarity matrix includes:
calculating a first similarity value between the medicines in the first scoring matrix by adopting the collaborative filtering algorithm;
and generating the first medicine similarity matrix based on the first similarity value and the first scoring matrix.
Preferably, the weighting the first scoring matrix according to the drug information to obtain a second scoring matrix includes:
the medicine information comprises dosage data, and dosage coefficients corresponding to the dosage information are respectively calculated;
multiplying the dose coefficient of each drug by the corresponding drug element in the first scoring matrix to generate the second scoring matrix.
Preferably, the processing the second scoring matrix by using the collaborative filtering algorithm to generate a second drug similarity matrix includes:
calculating a second similarity value between the medicines in the second scoring matrix by adopting the collaborative filtering algorithm;
and generating the first medicine similarity matrix based on the second similarity value and the second scoring matrix.
Preferably, the matching, according to the target disease type, the drug information in the medical list with the drug similarity table to obtain abnormal drug information of the patient object includes:
acquiring medicine information of the patient object matched with the target disease type in the medical list item by item, and matching the medicine similarity form associated with the target disease type with the medicine information;
if the drug information is not matched with the drug similarity list, carrying out abnormal identification on the patient object;
and if the medicine information is matched with the medicine similarity list, the medicine information of the patient object is normal.
The present invention also provides a medical information recognition apparatus, including:
an acquisition unit for acquiring medical settlement data of a patient object in a medical database;
the generation unit is used for generating a medical list according to the medical settlement data, wherein the medical list comprises personal information, disease types and medicine information of each patient object;
the analysis unit is used for analyzing the medical list according to the type of the target disease to generate a medicine similarity form;
and the identification unit is used for matching the medicine information in the medical list with the medicine similarity form according to the target disease type to acquire abnormal medicine information of the patient object.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when executing the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the medical information identification method, the medical information identification device, the computer equipment and the storage medium, the medical list including the medicine information of the patient is generated according to the medical settlement data, and the medical list is analyzed according to the type of the target disease to generate the medicine similarity degree form; abnormal medicines corresponding to the target disease type are screened out from the medical list by utilizing the medicine similarity form, so that the purpose of accurately identifying the abnormal medicines in the medical documents is achieved, and the identification accuracy is high.
Drawings
FIG. 1 is a flow chart of one embodiment of a medical information identification method according to the present invention;
FIG. 2 is a flowchart illustrating an embodiment of the present invention for generating a drug similarity table by analyzing a medical manifest according to a target disease type;
FIG. 3 is a block diagram of an embodiment of a medical information identification device according to the present invention;
fig. 4 is a hardware architecture diagram of one embodiment of the computer apparatus of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The medical information identification method, the medical information identification device, the computer equipment and the storage medium provided by the invention can be suitable for the fields of medical business, insurance business and the like, a medical list comprising medicine information of a patient is generated according to medical settlement data, and the medical list is analyzed according to the type of a target disease to generate a medicine similarity degree form; abnormal medicines corresponding to the target disease type are screened out from the medical list by utilizing the medicine similarity form, so that the purpose of accurately identifying the abnormal medicines in the medical documents is achieved, and the identification accuracy is high.
Example one
Referring to fig. 1, a medical information identification method of the present embodiment includes the following steps:
s1, acquiring medical settlement data of a patient object in a medical database;
in the present embodiment, the medical database is a database that stores medical settlement data of all patients (medical insurance patients, non-medical insurance patients). The medical settlement data includes personal information, hospital information, medical information, and the like of the patient. The diagnosis and treatment information can comprise medicine information, diagnosis and treatment information and the like.
S2, generating a medical list according to the medical settlement data, wherein the medical list comprises personal information, disease types and medicine information of each patient object;
the drug information may include the name of the social security three-directory, the uniform code (the name and the uniform code of the drug related to the basic medical insurance drug directory), the dosage, the medication time, the corresponding expense details, and other data.
In the embodiment, the field and the code format are unified by cleaning the medical settlement data in the medical database, so that the medical settlement data is converted into the data convenient to identify.
Further, step S2 is to generate a medical invoice according to the medical settlement data, including:
and according to a preset form template, extracting the disease type and the drug information of each patient object in the medical settlement data for single treatment to generate the medical list.
In this embodiment, because the medical settlement data in the medical database has the situations of non-uniform codes and non-uniform fields, in order to facilitate the effective analysis and abnormal drug identification of the drug information of each patient object by using the association analysis algorithm, the information of each patient object in the medical settlement data is extracted according to the preset form template to generate the medical list with uniform information format, thereby achieving the purpose of unifying the information of each patient.
S3, analyzing the medical list according to the type of the target disease to generate a medicine similarity form;
in this embodiment, similarity analysis is performed on the medicines prescribed for the single treatment of all patients in the medical list according to the target disease type (e.g., diabetes, heart disease, burn, etc.) through step S3, so as to obtain all the medicines for treating the target disease type and the similarity between the medicines, so as to identify the patient medical settlement data including a plurality of medicines with the same function and different functions in the single treatment by using the medicine similarity list.
Further, referring to fig. 2, step S3 is to analyze the medical list according to the type of the target disease to generate a drug similarity table, including:
s31, extracting personal information and medicine information of the patient object associated with the target disease type in the medical list;
in this step, the personal information and the drug information of the patient subject associated with the type are extracted in the medical checklist according to the target disease type, and a data set including the patient subject name and the drug information is generated.
S32, constructing a first scoring matrix according to the personal information and the medicine information of the patient object;
in this step, a first scoring matrix R of patient-medicine is constructed according to the personal identification (such as name, account number) of each patient object and the medicine name or medicine uniform code in the corresponding medicine informationm×nWherein m represents the number of drugs and n represents the number of patients.
S33, processing the first scoring matrix by adopting a preset collaborative filtering algorithm to generate a first medicine similarity matrix;
in this step, the similarity between the medicines is statistically calculated by a collaborative filtering algorithm (collaborative filtering).
Specifically, step S33 may include:
calculating a first similarity value between the medicines in the first scoring matrix by adopting the collaborative filtering algorithm; and generating the first medicine similarity matrix based on the first similarity value and the first scoring matrix.
S34, weighting the first scoring matrix according to the medicine information to generate a second scoring matrix;
considering that the dosage of the drug for each patient is different, the present embodiment may analyze the dosage of each drug separately, and analyze the drug information from the dimension of the dosage.
Specifically, step S34 may include:
the medicine information comprises dosage data, and dosage coefficients corresponding to the dosage information are respectively calculated; multiplying the dose coefficient of each drug by the corresponding drug element in the first scoring matrix to generate the second scoring matrix.
In this step, a drug dose form is provided, which includes dose coefficients corresponding to different dose intervals for each drug. And inquiring a medicine dosage form according to dosage data in the medicine information of each patient object to obtain dosage coefficients corresponding to the dosage data, and multiplying the corresponding dosage coefficients by corresponding medicine elements in the first scoring matrix to obtain a second scoring matrix.
Where sim (u, v) represents the similarity value between drug u and drug v, Ruv represents the co-score set of drug u and drug v, and Ru,iIndicates the i-th user's score, R, for the drug uv,iIndicating the i-th user's score for the drug v,to representThe user's average rating of the rated drugs u,representing the average rating of the user for the rated drug v;
wherein, Pu,v,iRepresents the value of the score of the ith user predicted medicine u for the medicine v;
wherein Correct (u, v, i) indicates whether the ith user predicts success for the drug u with respect to the drug v; is a constant;
wherein, T1(u, v) denotes a first drug similarity matrix, u ═ k1,k2,…,km,v=k1,k2,…,km;
Wherein, Tu,vRepresenting the confidence similarity of drug u to drug v.
S35, processing the second scoring matrix by adopting the collaborative filtering algorithm to generate a second medicine similarity matrix;
specifically, step S35 may include:
calculating a second similarity value between the medicines in the second scoring matrix by adopting the collaborative filtering algorithm; and generating the first medicine similarity matrix based on the second similarity value and the second scoring matrix. In this step, the same collaborative filtering algorithm as that in step S33 is used to obtain the similarity of the second medicine, and therefore, the details are not repeated here.
S36, carrying out weighted average on the first medicine similarity matrix and the second medicine similarity matrix to generate a third medicine similarity matrix;
in the step, the purpose of calculating the similarity of the medicines by combining the factors of the medicine types and the medicine doses is achieved. The first drug similarity matrix corresponds to a first weighted value (e.g., 0.4), the second drug similarity matrix corresponds to a second weighted value (e.g., 0.6), the first drug similarity matrix is multiplied by the first weighted value, the second drug similarity matrix is multiplied by the second weighted value, and the first and second weighted values are added to obtain a third drug similarity matrix.
And S37, matching each similarity medicine element in the third medicine similarity matrix with a preset range, extracting the matched similarity medicine elements, and generating the medicine similarity table.
In practical application, the preset range may be a similarity threshold or a similarity range. And when the preset range is the similarity range, matching each similarity medicine element in the third medicine similarity matrix with the similarity range, screening the medicine elements with high similarity, filtering the medicine elements with low similarity, and sequencing the screened medicine elements from high similarity to low similarity to obtain a medicine similarity table.
And S4, matching the medicine information in the medical list with the medicine similarity form according to the target disease type to acquire abnormal medicine information of the patient object.
In step S4, the medicine information of each patient in the medical list is filtered according to the medicine similarity table, the medical settlement information of the patient matching with the medicine similarity table is obtained, and the patient object of the medicine with multiple identical functions and abnormal dosage (dosage exceeding standard dosage) in the medical document is obtained.
Further, step S4 is to match the drug information in the medical list with the drug similarity table according to the target disease type, and obtain the abnormal drug information of the patient, including:
acquiring medicine information of the patient object matched with the target disease type in the medical list item by item, and matching the medicine similarity form associated with the target disease type with the medicine information;
if the drug information is not matched with the drug similarity list, carrying out abnormal identification on the patient object;
and if the medicine information is matched with the medicine similarity list, the medicine information of the patient object is normal.
The medical information of the patient object matched with the target disease type is screened out from the medical list through the step S4, the acquired medical information is matched with the corresponding medicine similarity table, and at least two medicines with the same function and abnormal dose are identified in the medicine information, so that the purpose of identifying the medicine abnormality in the medical receipt is achieved.
In the embodiment, the medical information identification method generates a medical list including medicine information of a patient according to medical settlement data, and analyzes the medical list according to a target disease type to generate a medicine similarity degree form; abnormal medicines corresponding to the target disease type are screened out from the medical list by utilizing the medicine similarity form, so that the purpose of accurately identifying the abnormal medicines in the medical documents is achieved, and the identification accuracy is high. The method is based on integration of a plurality of algorithms, identifies the similarity between medicines and judges whether the medication on the receipt is reasonable or not, and the method is based on data driving without depending on any medical knowledge or medical background, acquires a medicine similarity table with high similarity between the medicines by analyzing medical settlement data in a medical database, so as to judge whether a plurality of medicines with high similarity simultaneously appear in one receipt and the dosage is large, and further identifies an abnormal receipt.
Example two
Referring to fig. 3, a medical information identification apparatus 1 of the present embodiment includes: an acquisition unit 11, a generation unit 12, an analysis unit 13, and a recognition unit 14; wherein the content of the first and second substances,
an acquisition unit 11 for acquiring medical settlement data of a patient object in a medical database;
in the present embodiment, the medical database is a database that stores medical settlement data of all patients (medical insurance patients, non-medical insurance patients). The medical settlement data includes personal information, hospital information, medical information, and the like of the patient. The diagnosis and treatment information can comprise medicine information, diagnosis and treatment information and the like.
A generating unit 12, configured to generate a medical list according to the medical settlement data, where the medical list includes personal information, disease types, and drug information of each patient object;
the drug information may include the name of the social security three-directory, the uniform code (the name and the uniform code of the drug related to the basic medical insurance drug directory), the dosage, the medication time, the corresponding expense details, and other data.
In the embodiment, the field and the code format are unified by cleaning the medical settlement data in the medical database, so that the medical settlement data is converted into the data convenient to identify.
Further, the generating unit 12 extracts the disease type and drug information of each patient subject for single treatment in the medical settlement data according to a preset form template, and generates the medical list.
In this embodiment, because the medical settlement data in the medical database has the situations of non-uniform codes and non-uniform fields, in order to facilitate the effective analysis and abnormal drug identification of the drug information of each patient object by using the association analysis algorithm, the information of each patient object in the medical settlement data is extracted according to the preset form template to generate the medical list with uniform information format, thereby achieving the purpose of unifying the information of each patient.
The analysis unit 13 is used for analyzing the medical list according to the type of the target disease to generate a medicine similarity table;
in the embodiment, the analysis unit 13 performs similarity analysis on the medicines prescribed by all patients in the medical list for a single treatment according to the target disease type (such as diabetes, heart disease, burn, and other disease types), so as to obtain all the medicines for treating the target disease type and the similarity between the medicines, so as to identify the patient medical settlement data including a plurality of medicines with the same function and different functions in a single treatment by using the medicine similarity list.
Further, referring to fig. 2, the step of analyzing the medical list by the analysis unit 13 according to the type of the target disease to generate a drug similarity table may include the following steps:
s31, extracting personal information and medicine information of the patient object associated with the target disease type in the medical list;
in this step, the personal information and the drug information of the patient subject associated with the type are extracted in the medical checklist according to the target disease type, and a data set including the patient subject name and the drug information is generated.
S32, constructing a first scoring matrix according to the personal information and the medicine information of the patient object;
in this step, a first scoring matrix R of patient-medicine is constructed according to the personal identification (such as name, account number) of each patient object and the medicine name or medicine uniform code in the corresponding medicine informationm×nWherein m represents the number of drugs and n represents the number of patients.
S33, processing the first scoring matrix by adopting a preset collaborative filtering algorithm to generate a first medicine similarity matrix;
in this step, the similarity between the medicines is statistically calculated by a collaborative filtering algorithm (collaborative filtering).
Specifically, step S33 may include:
calculating a first similarity value between the medicines in the first scoring matrix by adopting the collaborative filtering algorithm; and generating the first medicine similarity matrix based on the first similarity value and the first scoring matrix.
S34, weighting the first scoring matrix according to the medicine information to generate a second scoring matrix;
considering that the dosage of the drug for each patient is different, the present embodiment may analyze the dosage of each drug separately, and analyze the drug information from the dimension of the dosage.
Specifically, step S34 may include:
the medicine information comprises dosage data, and dosage coefficients corresponding to the dosage information are respectively calculated; multiplying the dose coefficient of each drug by the corresponding drug element in the first scoring matrix to generate the second scoring matrix.
In this step, a drug dose form is provided, which includes dose coefficients corresponding to different dose intervals for each drug. And inquiring a medicine dosage form according to dosage data in the medicine information of each patient object to obtain dosage coefficients corresponding to the dosage data, and multiplying the corresponding dosage coefficients by corresponding medicine elements in the first scoring matrix to obtain a second scoring matrix.
S35, processing the second scoring matrix by adopting the collaborative filtering algorithm to generate a second medicine similarity matrix;
specifically, step S35 may include: calculating a second similarity value between the medicines in the second scoring matrix by adopting the collaborative filtering algorithm; and generating the first medicine similarity matrix based on the second similarity value and the second scoring matrix. In this step, the same collaborative filtering algorithm as that in step S33 is used to obtain the similarity of the second medicine, and therefore, the details are not repeated here.
S36, carrying out weighted average on the first medicine similarity matrix and the second medicine similarity matrix to generate a third medicine similarity matrix;
in the step, the purpose of calculating the similarity of the medicines by combining the factors of the medicine types and the medicine doses is achieved. The first drug similarity matrix corresponds to a first weighted value (e.g., 0.4), the second drug similarity matrix corresponds to a second weighted value (e.g., 0.6), the first drug similarity matrix is multiplied by the first weighted value, the second drug similarity matrix is multiplied by the second weighted value, and the first and second weighted values are added to obtain a third drug similarity matrix.
And S37, matching each similarity medicine element in the third medicine similarity matrix with a preset range, extracting the matched similarity medicine elements, and generating the medicine similarity table.
In practical application, the preset range may be a similarity threshold or a similarity range. And when the preset range is the similarity range, matching each similarity medicine element in the third medicine similarity matrix with the similarity range, screening the medicine elements with high similarity, filtering the medicine elements with low similarity, and sequencing the screened medicine elements from high similarity to low similarity to obtain a medicine similarity table.
And the identification unit 14 is used for matching the medicine information in the medical list with the medicine similarity table according to the target disease type to acquire abnormal medicine information of the patient object.
The identification unit 14 screens the medicine information of each patient in the medical list according to the medicine similarity list to obtain the medical settlement information of the patient matched with the medicine similarity list, and further obtain the patient object of the medicine with multiple identical functions and abnormal dosage (dosage exceeding standard dosage) in the medical bill.
Further, the identification unit 14 is adopted to acquire the drug information of the patient subject matched with the target disease type in the medical list one by one, and the drug similarity table associated with the target disease type is matched with the drug information;
if the drug information is not matched with the drug similarity list, carrying out abnormal identification on the patient object; and if the medicine information is matched with the medicine similarity list, the medicine information of the patient object is normal.
The medical information of the patient object matched with the target disease type is screened out from the medical list through the identification unit 14, the acquired medical information is matched with the corresponding medicine similarity table, and at least two medicines with the same function and abnormal dose are identified in the medicine information, so that the purpose of identifying the medicine abnormality in the medical bill is achieved.
In the present embodiment, the medical information identification apparatus 1 generates a medical list including the drug information of the patient according to the medical settlement data, and analyzes the medical list according to the type of the target disease to generate a drug similarity table; abnormal medicines corresponding to the target disease type are screened out from the medical list by utilizing the medicine similarity form, so that the purpose of accurately identifying the abnormal medicines in the medical documents is achieved, and the identification accuracy is high. The method is based on integration of a plurality of algorithms, identifies the similarity between medicines and judges whether the medication on the receipt is reasonable or not, and the method is based on data driving without depending on any medical knowledge or medical background, acquires a medicine similarity table with high similarity between the medicines by analyzing medical settlement data in a medical database, so as to judge whether a plurality of medicines with high similarity simultaneously appear in one receipt and the dosage is large, and further identifies an abnormal receipt.
EXAMPLE III
In order to achieve the above object, the present invention further provides a computer device 2, where the computer device 2 includes a plurality of computer devices 2, components of the medical information identification apparatus 1 according to the second embodiment may be dispersed in different computer devices 2, and the computer device 2 may be a smartphone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster formed by a plurality of servers) that executes a program, and the like. The computer device 2 of the present embodiment includes at least, but is not limited to: a memory 21, a processor 23, a network interface 22, and the medical information identification apparatus 1 (refer to fig. 4) that can be communicatively connected to each other through a system bus. It is noted that fig. 4 only shows the computer device 2 with components, but it is to be understood that not all of the shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the memory 21 includes at least one type of computer-readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both an internal storage unit of the computer device 2 and an external storage device thereof. In this embodiment, the memory 21 is generally used for storing an operating system installed in the computer device 2 and various types of application software, such as a program code of the medical information identification method according to the first embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 23 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data Processing chip in some embodiments. The processor 23 is typically used for controlling the overall operation of the computer device 2, such as performing control and processing related to data interaction or communication with the computer device 2. In this embodiment, the processor 23 is configured to operate the program code stored in the memory 21 or process data, such as operating the medical information identification apparatus 1.
The network interface 22 may comprise a wireless network interface or a wired network interface, and the network interface 22 is typically used to establish a communication connection between the computer device 2 and other computer devices 2. For example, the network interface 22 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global system of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 4 only shows the computer device 2 with components 21-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the medical information identification apparatus 1 stored in the memory 21 may be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 23) to complete the present invention.
Example four
To achieve the above objects, the present invention also provides a computer-readable storage medium including a plurality of storage media such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by the processor 23, implements corresponding functions. The computer-readable storage medium of the present embodiment is used for storing the medical information identification apparatus 1, and when being executed by the processor 23, the computer-readable storage medium implements the medical information identification method of the first embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A medical information identification method is characterized by comprising the following steps:
acquiring medical settlement data of patient objects in a medical database;
generating a medical list according to the medical settlement data, wherein the medical list comprises personal information, disease types and medicine information of each patient object;
analyzing the medical list according to the type of the target disease to generate a medicine similarity form;
and matching the medicine information in the medical list with the medicine similarity form according to the target disease type to acquire abnormal medicine information of the patient object.
2. The medical information identification method according to claim 1, wherein the generating a medical manifest from the medical settlement data includes:
and according to a preset form template, extracting the disease type and the drug information of each patient object in the medical settlement data for single treatment to generate the medical list.
3. The medical information identification method of claim 1, wherein the analyzing the medical list according to the target disease type to generate a drug similarity table comprises:
extracting personal information and drug information of patient subjects in the medical checklist associated with the target disease type;
constructing a first scoring matrix according to the personal information and the drug information of the patient object;
processing the first scoring matrix by adopting a preset collaborative filtering algorithm to generate a first medicine similarity matrix;
weighting the first scoring matrix according to the medicine information to generate a second scoring matrix;
processing the second scoring matrix by adopting the collaborative filtering algorithm to generate a second medicine similarity matrix;
carrying out weighted average on the first medicine similarity matrix and the second medicine similarity matrix to generate a third medicine similarity matrix;
and matching each similarity medicine element in the third medicine similarity matrix with a preset range, extracting the matched similarity medicine elements, and generating the medicine similarity table.
4. The medical information identification method according to claim 3, wherein the processing the first scoring matrix by using a preset collaborative filtering algorithm to generate a first drug similarity matrix comprises:
calculating a first similarity value between the medicines in the first scoring matrix by adopting the collaborative filtering algorithm;
and generating the first medicine similarity matrix based on the first similarity value and the first scoring matrix.
5. The medical information identification method according to claim 3, wherein the weighting the first scoring matrix according to the drug information to generate a second scoring matrix includes:
the medicine information comprises dosage data, and dosage coefficients corresponding to the dosage information are respectively calculated;
multiplying the dose coefficient of each drug by the corresponding drug element in the first scoring matrix to generate the second scoring matrix.
6. The medical information identification method according to claim 3, wherein the processing the second scoring matrix by using the collaborative filtering algorithm to generate a second drug similarity matrix comprises:
calculating a second similarity value between the medicines in the second scoring matrix by adopting the collaborative filtering algorithm;
and generating the first medicine similarity matrix based on the second similarity value and the second scoring matrix.
7. The medical information identification method according to claim 3, wherein the matching of the drug information in the medical list with the drug similarity table according to the target disease type to obtain abnormal drug information of the patient object comprises:
acquiring medicine information of the patient object matched with the target disease type in the medical list item by item, and matching the medicine similarity form associated with the target disease type with the medicine information;
if the drug information is not matched with the drug similarity list, carrying out abnormal identification on the patient object;
and if the medicine information is matched with the medicine similarity list, the medicine information of the patient object is normal.
8. A medical information identification apparatus characterized by comprising:
an acquisition unit for acquiring medical settlement data of a patient object in a medical database;
the generation unit is used for generating a medical list according to the medical settlement data, wherein the medical list comprises personal information, disease types and medicine information of each patient object;
the analysis unit is used for analyzing the medical list according to the type of the target disease to generate a medicine similarity form;
and the identification unit is used for matching the medicine information in the medical list with the medicine similarity form according to the target disease type to acquire abnormal medicine information of the patient object.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010207018.4A CN111402070A (en) | 2020-03-23 | 2020-03-23 | Medical information identification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010207018.4A CN111402070A (en) | 2020-03-23 | 2020-03-23 | Medical information identification method and device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111402070A true CN111402070A (en) | 2020-07-10 |
Family
ID=71413396
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010207018.4A Pending CN111402070A (en) | 2020-03-23 | 2020-03-23 | Medical information identification method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111402070A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
CN112380402A (en) * | 2020-11-16 | 2021-02-19 | 零氪科技(天津)有限公司 | Medical document processing method, device and system |
CN112966787A (en) * | 2021-04-16 | 2021-06-15 | 平安科技(深圳)有限公司 | Similar patient identification method and device, computer equipment and storage medium |
CN113642669A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Fraud prevention detection method, device and equipment based on feature analysis and storage medium |
CN117316404A (en) * | 2023-09-11 | 2023-12-29 | 北京合源汇丰医药科技有限公司 | Medical information anomaly detection method and system based on AI algorithm |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150085981A1 (en) * | 2013-09-24 | 2015-03-26 | Siemens Aktiengesellschaft | Method of image registration in a multi-source/single detector radiographic imaging system, and image acquisition apparatus |
CN108062556A (en) * | 2017-11-10 | 2018-05-22 | 广东药科大学 | A kind of drug-disease relationship recognition methods, system and device |
CN108630322A (en) * | 2018-04-27 | 2018-10-09 | 厦门大学 | Drug interaction modeling and methods of risk assessment, terminal device and storage medium |
CN109545388A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of medicine risk control method, server and storage medium |
CN109636641A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis |
CN109671476A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of unrelated medication |
CN109830302A (en) * | 2019-01-28 | 2019-05-31 | 北京交通大学 | Medication mode excavation method, apparatus and electronic equipment |
CN110245217A (en) * | 2019-06-17 | 2019-09-17 | 京东方科技集团股份有限公司 | A kind of drug recommended method, device and electronic equipment |
CN110390021A (en) * | 2019-06-13 | 2019-10-29 | 平安科技(深圳)有限公司 | Drug knowledge mapping construction method, device, computer equipment and storage medium |
CN110880361A (en) * | 2019-10-16 | 2020-03-13 | 平安科技(深圳)有限公司 | Personalized accurate medication recommendation method and device |
-
2020
- 2020-03-23 CN CN202010207018.4A patent/CN111402070A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150085981A1 (en) * | 2013-09-24 | 2015-03-26 | Siemens Aktiengesellschaft | Method of image registration in a multi-source/single detector radiographic imaging system, and image acquisition apparatus |
CN108062556A (en) * | 2017-11-10 | 2018-05-22 | 广东药科大学 | A kind of drug-disease relationship recognition methods, system and device |
CN108630322A (en) * | 2018-04-27 | 2018-10-09 | 厦门大学 | Drug interaction modeling and methods of risk assessment, terminal device and storage medium |
CN109545388A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of medicine risk control method, server and storage medium |
CN109636641A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis |
CN109671476A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of unrelated medication |
CN109830302A (en) * | 2019-01-28 | 2019-05-31 | 北京交通大学 | Medication mode excavation method, apparatus and electronic equipment |
CN110390021A (en) * | 2019-06-13 | 2019-10-29 | 平安科技(深圳)有限公司 | Drug knowledge mapping construction method, device, computer equipment and storage medium |
CN110245217A (en) * | 2019-06-17 | 2019-09-17 | 京东方科技集团股份有限公司 | A kind of drug recommended method, device and electronic equipment |
CN110880361A (en) * | 2019-10-16 | 2020-03-13 | 平安科技(深圳)有限公司 | Personalized accurate medication recommendation method and device |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
CN112380402A (en) * | 2020-11-16 | 2021-02-19 | 零氪科技(天津)有限公司 | Medical document processing method, device and system |
CN112380402B (en) * | 2020-11-16 | 2023-03-14 | 零氪科技(天津)有限公司 | Medical document processing method, device and system |
CN112966787A (en) * | 2021-04-16 | 2021-06-15 | 平安科技(深圳)有限公司 | Similar patient identification method and device, computer equipment and storage medium |
CN112966787B (en) * | 2021-04-16 | 2023-11-14 | 平安科技(深圳)有限公司 | Method, device, computer equipment and storage medium for identifying similar patients |
CN113642669A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Fraud prevention detection method, device and equipment based on feature analysis and storage medium |
CN113642669B (en) * | 2021-08-30 | 2024-04-05 | 平安医疗健康管理股份有限公司 | Feature analysis-based fraud prevention detection method, device, equipment and storage medium |
CN117316404A (en) * | 2023-09-11 | 2023-12-29 | 北京合源汇丰医药科技有限公司 | Medical information anomaly detection method and system based on AI algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111402070A (en) | Medical information identification method and device, computer equipment and storage medium | |
CN111899878B (en) | Old person health detection system, method, computer device and readable storage medium | |
US10943302B2 (en) | Systems, methods, and computer program products for risk and insurance determination | |
CN111430036B (en) | Medical information identification method and device for abnormal operation behaviors | |
CN110880361A (en) | Personalized accurate medication recommendation method and device | |
CN106687960A (en) | System and method for detecting activation of a medical delivery device | |
CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
WO2019006920A1 (en) | Chronic disease patient health examination system and method based on doctor inquiry | |
CN111210917A (en) | Medication guiding method and system based on offline code scanning | |
CN109598302B (en) | Method, device and equipment for predicting treatment cost and computer readable storage medium | |
CN112132624A (en) | Medical claims data prediction system | |
CN109359802B (en) | Inverse selection risk determination method, system, computer device and storage medium | |
CN109671476A (en) | Recognition methods, device, terminal and the computer readable storage medium of unrelated medication | |
CN111383732B (en) | Medicine auditing method, device, computer system and readable storage medium based on mutual exclusion identification | |
CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
CN110232636B (en) | Nuclear protection method and device | |
CN110718276A (en) | Clinical path management information system | |
CN111429289B (en) | Single disease identification method and device, computer equipment and storage medium | |
CN111428198A (en) | Method, device, equipment and storage medium for determining abnormal medical list | |
CN116434931A (en) | Medical behavior abnormality identification method, device, storage medium and equipment | |
CN115841674A (en) | Automatic recording method and device for CRF, electronic equipment and storage medium | |
CN111259089B (en) | Medical insurance data processing method and device, computer equipment and storage medium | |
CN109615546A (en) | Extremely medical recognition methods, device, terminal and computer readable storage medium | |
CN111274231B (en) | Abnormal medical insurance data checking method and device, computer equipment and storage medium | |
CN110689441B (en) | Case auditing method, device, equipment and storage medium based on commonality extraction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200710 |