CN114067966A - Medical consumable tracing method and system, corresponding equipment and storage medium - Google Patents
Medical consumable tracing method and system, corresponding equipment and storage medium Download PDFInfo
- Publication number
- CN114067966A CN114067966A CN202111161122.5A CN202111161122A CN114067966A CN 114067966 A CN114067966 A CN 114067966A CN 202111161122 A CN202111161122 A CN 202111161122A CN 114067966 A CN114067966 A CN 114067966A
- Authority
- CN
- China
- Prior art keywords
- udi
- similarity
- coding
- algorithm
- code
- 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 36
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 110
- 239000013598 vector Substances 0.000 claims abstract description 54
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application discloses a medical consumable tracing method, a system, corresponding equipment and a storage medium, wherein the method comprises the following steps: determining a corresponding characteristic value based on hospital consumable self-coding; calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity algorithm; calculating at least a second UDI coding similarity value based on at least a second similarity algorithm; determining weights for the first similarity algorithm and the at least second similarity algorithm; and determining a matching score of the hospital consumable self-code and the UDI code based on the first and at least second UDI code similarity values and the corresponding algorithm weight, and taking the UDI code with the highest matching score as the UDI code matched with the hospital consumable self-code. The invention can reduce the matching difficulty and error rate of different coding systems of medical consumables and improve the management efficiency of the medical consumables.
Description
Technical Field
The application relates to the field of electric digital data processing, in particular to a medical consumable tracing method. The application also relates to a medical consumable tracing system and a corresponding computer device and computer readable storage medium.
Background
Under the background of advanced medical improvement and intensive management vigorously promoted by hospitals, the state requires medical institutions to establish medical consumable management information systems, and covers all links such as selection, purchase, acceptance, warehousing, storage, inventory, application, ex-warehouse, clinical use, quality safety event reporting, adverse reaction monitoring, key monitoring and the like, so that the traceability of the whole life cycle of each medical consumable is realized.
Currently, the main standard coding systems for consumables in the medical industry include: UDI code and national medical insurance settlement code.
The UDI (Unique Identification of the medical instrument) code is an identity assigned to the medical instrument throughout its life cycle. The national food and drug administration requires that the medical consumables applied for market admission are endowed with UDI codes on the minimum sale unit. The adoption of a uniform and standard UDI is beneficial to improving the transparency and the operation efficiency of a supply chain; the operation cost is reduced; the information sharing and exchange are realized; the system is beneficial to monitoring adverse events and recalling problematic products, improves the medical service quality and ensures the safety of patients. The UDI code is a code existing immediately after the medical supplies leave the factory, and records various attributes of the medical supplies and circulation thereof outside the hospital. By parsing the UDI code, the hospital can obtain necessary information required for internal management.
Regarding the code of the national medical insurance settlement consumables, the national medical insurance office issues a notice of the national medical insurance office about issuing medical insurance standardization work guidance opinions on 6 months and 27 days in 2019, and 4 information service coding rules and methods of medical insurance consumables and the like are published. According to the public, the medical consumable codes comprise primary classification (subject, category), secondary classification (use, item), tertiary classification (position, function, category), medical insurance common name, consumable material, specification (characteristic, parameter) and production enterprise information. The medical insurance consumable information business coding rule is as follows, part 1: the consumable identification code is represented by a 1-digit capital English letter 'C'; section 2: the classification codes are divided according to medical consumable subject, purpose, position and function; section 3: the universal name code is used for creating a nationwide uniform medical insurance consumable universal name code; section 4: the product feature code is a code given according to the characteristics of consumable materials, specifications and the like; section 5: the manufacturing enterprise code is a unique code given to the consumable manufacturing enterprise according to the medical instrument registration certificate or the record certificate. The medical insurance consumable code is a necessary identification for the settlement of the consumable medical insurance and is also a necessary carrier for smoothly completing the fund transfer on the consumable supply chain.
However, the hospital's own management code (hereinafter, referred to as hospital self-code or hospital consumable self-code) is used for many years in the business management, and replacement is liable to cause confusion of historical data, clinical use and management. Without the industry mainstream UDI, however, the necessary management attributes of medical supplies cannot be automatically and accurately identified and recorded, such as: date of manufacture, expiration date, etc.; accurate information of the original consumable factory cannot be identified, manual checking is needed, and errors are easy to occur; and the circulation process of consumables outside the hospital cannot be traced based on UDI. At present, UDI codes, medical insurance settlement codes and hospital self-codes are frequently used in daily business in a multi-code combination mode, the matching is disordered, the matching rate of the hospital self-codes, the medical insurance settlement codes and the UDI codes is low, and the manual matching efficiency is low. Therefore, a medical consumable full-process tracing system based on matching of different coding systems needs to be established.
Disclosure of Invention
The invention provides a medical consumable tracing method, a medical consumable tracing system, corresponding equipment and a storage medium, which can reduce the matching difficulty and error rate of different coding systems of medical consumables and improve the management efficiency of the medical consumables.
In a first aspect of the invention, there is provided a medical consumable tracing method, the method comprising:
determining corresponding characteristic values based on hospital consumable self-coding, wherein the characteristic values are one or more characteristic value libraries, and the characteristic value libraries comprise consumable names, manufacturing enterprises, specifications, models and registration card numbers;
calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity algorithm;
calculating at least a second UDI coding similarity value between the self-coding feature value vector of the hospital consumables and the corresponding feature value vector of each entry of the UDI coding knowledge base based on at least a second similarity algorithm;
determining weights for the first similarity algorithm and the at least second similarity algorithm;
determining a matching score of the hospital consumable self-encoding and the UDI encoding based on the first UDI encoding similarity value, at least a second UDI encoding similarity value and corresponding algorithm weight;
and taking the UDI code with the highest matching score as the UDI code matched with the hospital consumable self-code.
In a second aspect of the present invention, there is provided a medical consumable traceability system, the system comprising:
the characteristic value determining module is used for determining corresponding characteristic values based on hospital consumable self-coding, wherein the characteristic values are one or more characteristic value libraries, and the characteristic value libraries comprise consumable names, manufacturing enterprises, specifications, models and registration certificate numbers;
the first similarity value calculation module is used for calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity calculation method;
the second similarity value calculation module is used for calculating at least a second UDI coding similarity value between the self-coding feature value vector of the hospital consumables and the corresponding feature value vector of each entry of the UDI coding knowledge base based on at least a second similarity algorithm;
a weight determination module for determining weights of the first similarity algorithm and the at least second similarity algorithm;
the matching score determining module is used for determining a matching score of the hospital consumable self-coding and the UDI coding based on the first UDI coding similarity value, at least a second UDI coding similarity value and corresponding algorithm weight;
and the matching code determining module is used for taking the UDI code with the highest matching score as the UDI code matched with the self-code of the hospital consumable.
In a third aspect of the invention, a computer device is provided, comprising a processor, a memory and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method according to the first aspect of the invention or implements the functions of the system according to the second aspect of the invention.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to the first aspect of the present invention or performs the functions of the system according to the second aspect of the present invention.
According to the invention, by determining the characteristic value of the hospital consumable self-encoding, calculating the similarity value between the hospital consumable self-encoding characteristic value vector and the corresponding characteristic value vector of each entry of the UDI encoding knowledge base by using different similarity algorithms, determining the weight of each similarity algorithm, determining the matching score of the hospital consumable self-encoding and the UDI encoding based on each similarity value and the corresponding algorithm weight, and finally determining the UDI encoding with the highest matching score as the UDI encoding matched with the hospital consumable self-encoding, an industry mainstream encoding system is introduced on the basis of reserving the hospital self-encoding, thereby realizing the automatic high matching rate and solving the confused situation of Ten thousand 'codes'. By introducing an industry UDI code and a medical insurance settlement code, a full-process tracing system for medical consumable management is constructed, namely, the whole process of 'production-supply-admission-in-hospital circulation-clinical consumption-medical insurance settlement' is covered. The method greatly reduces the matching difficulty and error rate of different coding systems, so that hospitals can improve the management efficiency of medical consumables by using the newly introduced standard codes on the basis of keeping the original code use habit.
Other features and advantages of the present invention will become more apparent from the detailed description of the embodiments of the present invention when taken in conjunction with the accompanying drawings.
Drawings
FIG. 1 is a flow chart of one embodiment of a method according to the present invention;
FIG. 2 is a block diagram of one embodiment of a system according to the present invention.
For the sake of clarity, the figures are schematic and simplified drawings, which only show details which are necessary for understanding the invention and other details are omitted.
Detailed Description
Embodiments and examples of the present invention will be described in detail below with reference to the accompanying drawings.
The scope of applicability of the present invention will become apparent from the detailed description given hereinafter. It should be understood, however, that the detailed description and the specific examples, while indicating preferred embodiments of the invention, are given by way of illustration only.
Fig. 1 shows a flowchart of a preferred embodiment of a medical consumable tracing method according to the present invention.
In step S102, an input of a hospital consumable self-code to be traced is received.
In step S104, the characteristic value corresponding to the input hospital consumable self-code is determined according to the internal management specifications of the hospital and the like. The feature value is one or more of a library of feature values. The characteristic value library comprises consumable item names, production enterprises, specifications, models, registration certificate numbers and the like.
In step S106, a first UDI coding similarity value between the self-coding characteristic value vector of the hospital consumable and the corresponding characteristic value vector of each entry of the UDI coding knowledge base issued by the national food and drug administration is calculated based on a first similarity algorithm.
The first similarity algorithm is one of the similarity algorithms known in the art, such as a cosine similarity algorithm, a word2vec similarity algorithm, a TF-IDF algorithm, a BM25 algorithm, a simhash algorithm, and the like. The first similarity calculation method will be described as a cosine similarity calculation method.
Assuming that the characteristic values determined from the input hospital consumable self-code are: consumable item name A, manufacturing enterprise B, specification C, model D and registration number E.
First, the determined feature values are combined. In the above hypothetical case, the combination of eigenvalues is ABCDE.
The feature values are then vectorized to applyVectors from the cosine similarity algorithm. For hospital consumable self-encoded feature values, the corresponding vector is, for example, ABCDE ═ x,y]. For each entry of the UDI encoding repository, the vector of eigenvalues corresponding to the determined eigenvalues is, for example, anBnCnDnEn＝[xn,yn]And n represents an entry.
Then, all entries in the UDI coding knowledge base are traversed, and self-coding feature vectors [ x ] of hospital consumables are calculated respectively,y]And UDI coding knowledge base entry characteristic value vector [ xn,yn]The cosine similarity between them is taken as the first UDI encoding similarity value, and is denoted as score1n, where n denotes an entry of the UDI encoding knowledge base.
In step S108, a first score vector score1 is formed based on the calculated respective first UDI encoding similarity values, e.g., denoted score1 ═ score11, score12, …, score1 n.
At step S110, at least a second UDI encoding similarity value between the hospital consumable self-encoding eigenvalue vector and the corresponding eigenvalue vector of each entry of the UDI encoding knowledge base is calculated based on a second similarity algorithm.
The second similarity algorithm is also one of similarity algorithms known in the art, such as a cosine similarity algorithm, a word2vec similarity algorithm, a TF-IDF algorithm, a BM25 algorithm, a simhash algorithm, etc., but the second similarity algorithm should be different from the first similarity algorithm. The second similarity algorithm is described as a word2vec similarity algorithm.
First, the feature values are vectorized into vectors suitable for word2vec similarity algorithms. For hospital consumable self-encoded feature values, the corresponding vector is, for example, ABCDE ═ x]. For each entry of the UDI encoding repository, the vector of eigenvalues corresponding to the determined eigenvalues is, for example, anBnCnDnEn＝[xn]And n represents an entry.
Then, self-encoding the hospital consumables with the feature vector [ x ]]And vector of characteristic values [ x ] of each UDI-encoded repository entryn]As an input to the input layer of word2vec, the output of the output layer of word2vecSelf-coding feature vector x as hospital consumable]And UDI coding knowledge base entry characteristic value vector [ xn]A second UDI encoding similarity value in between, for example, as score2n, where n represents an entry of the UDI encoding repository.
At step S112, a second score vector score2 is formed based on the respective second UDI encoding similarity values, e.g., denoted score2 ═ score21, score22, …, score2 n.
In this embodiment, only two different similarity algorithms are used. In other embodiments, however, more than three similarity algorithms may be used. For each of the third and further similarity algorithms, the processing involved is similar to steps S106 and S108 or S110 and S112 described above.
In step S114, weights of the first similarity algorithm and the second similarity algorithm are determined.
In an embodiment, the weights for each similarity algorithm are derived using a differential evolution algorithm (DE).
The original weight given to each similarity algorithm is weighted by 1, i.e. [ w ]1,w2,w3,…,wn]＝[1,1,1,…,1]，w1Representing the weight, w, of the similarity algorithm 12Representing the weight, w, of the similarity algorithm 2nRepresenting the weight of the similarity algorithm n.
The scoring vectors obtained based on each algorithm, such as the first scoring vector score1 and the second scoring vector score2, and the medical consumable training items (the matching results after artificial calibration) are used as the input of a differential evolution algorithm (DE), and the optimized weight value of each similarity algorithm is obtained as [ o _ w [ ]1,o_w2,o_w3,…,o_wn]。
In other embodiments, the weights of the multiple similarity algorithms used may also be determined using a Pairwise Comparison (Pairwise Comparison) method, an Analytic Hierarchy Process (AHP), or any other suitable algorithm.
In step S116, a matching score of the hospital consumable self-code and the UDI code is determined based on the first UDI code similarity value, the second UDI code similarity value and the corresponding algorithm weight.
In an embodiment, the match score of the hospital consumable self-code and the UDI code is determined as:
Hi＝∑j=1,2,…nO_Wj*scoreji
wherein H is the matching score of hospital consumable self-coding and UDI coding, i represents the item of UDI coding knowledge base, HiRepresents the matching score of the hospital consumable self-code and the ith UDI code, j represents the similarity algorithm, scorejiRepresents the similarity value corresponding to the ith UDI code of the jth similarity algorithm, O _ WjThe weight of the jth similarity algorithm is represented, and n represents the number of algorithms.
In step S118, the matching score is the highest, i.e., HiThe code of the largest valued UDI code repository entry serves as the UDI code that matches the hospital consumable self-code.
In other embodiments, a match between the hospital consumable self-code and the medical insurance settlement code may also be included. The matching between the hospital consumable self-coding and the medical insurance settlement coding is similar to the matching between the hospital consumable self-coding and the UDI coding described above, see steps S106-S118, except that the UDI coding knowledge base is replaced by a medical insurance settlement coding knowledge base issued by the national medical insurance agency and the UDI coding is replaced by the medical insurance settlement coding, which is not described herein again.
The method is based on a knowledge base, combines natural language processing, machine learning, neural network and deep learning, uses different algorithms to automatically match and calculate entries in a hospital self-encoding and UDI encoding knowledge base and a medical insurance settlement encoding knowledge base so as to obtain a final matching relation, realizes automatic high matching rate, enables 'universal codes to be normalized', further establishes a supply chain tracing system based on hospital self-encoding, medical insurance settlement encoding and UDI encoding, covers all links of production, distribution, hospital selection purchase, acceptance, warehousing, storage, inventory, claiming, ex-warehouse, clinical use and the like, and realizes the full life cycle traceability of each medical consumable.
Fig. 2 shows a block diagram of a preferred embodiment of a medical consumable traceability system according to the present invention, the system comprising:
the characteristic value determining module 202 is used for determining corresponding characteristic values based on hospital consumable self-coding, wherein the characteristic values are one or more characteristic value libraries, and the characteristic value libraries comprise consumable names, manufacturing enterprises, specifications, models and registration certificate numbers;
the first similarity value calculation module 204 is used for calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity algorithm;
a second similarity value calculation module 206, configured to calculate at least a second UDI encoding similarity value between the hospital consumable self-encoding eigenvalue vector and a corresponding eigenvalue vector of each entry of the UDI encoding knowledge base based on at least a second similarity algorithm;
a weight determination module 208 for determining weights of the first similarity algorithm and the at least second similarity algorithm;
a matching score determination module 210 for determining a matching score of the hospital consumable self-code and the UDI code based on the first UDI code similarity value, the at least second UDI code similarity value and the corresponding algorithm weight;
and a matching code determination module 212 for determining the UDI code with the highest matching score as the UDI code matched with the hospital consumable self-code.
In another embodiment, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method embodiment or other corresponding method embodiments shown and described in connection with fig. 1 or implements the functions of the system embodiment or other corresponding system embodiments shown and described in connection with fig. 2, and is not described herein again.
In another embodiment, the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the processor, when executing the computer program, implements the steps of the method embodiment or other corresponding method embodiments shown and described in connection with fig. 1 or implements the functions of the system embodiment or other corresponding system embodiments shown and described in connection with fig. 2, and therefore, the details are not repeated herein.
The various embodiments described herein, or certain features, structures, or characteristics thereof, may be combined as suitable in one or more embodiments of the invention. Additionally, in some cases, the order of steps depicted in the flowcharts and/or in the pipelined process may be modified, as appropriate, and need not be performed exactly in the order depicted. In addition, various aspects of the invention may be implemented using software, hardware, firmware, or a combination thereof, and/or other computer implemented modules or devices that perform the described functions. Software implementations of the present invention may include executable code stored in a computer readable medium and executed by one or more processors. The computer-readable medium may include a computer hard drive, ROM, RAM, flash memory, portable computer storage media such as CD-ROM, DVD-ROM, flash drives, and/or other devices with a Universal Serial Bus (USB) interface, and/or any other suitable tangible or non-transitory computer-readable medium or computer memory on which executable code may be stored and executed by a processor. The present invention may be used in conjunction with any suitable operating system.
As used herein, the singular forms "a", "an" and "the" include plural references (i.e., have the meaning "at least one"), unless the context clearly dictates otherwise. It will be further understood that the terms "has," "includes" and/or "including," when used in this specification, specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and/or groups thereof. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The foregoing describes some preferred embodiments of the present invention, but it should be emphasized that the invention is not limited to these embodiments, but can be implemented in other ways within the scope of the inventive subject matter. Various modifications and alterations of this invention will become apparent to those skilled in the art without departing from the spirit and scope of this invention.
Claims (10)
1. A medical consumable traceability method, characterized in that the method comprises:
determining corresponding characteristic values based on hospital consumable self-coding, wherein the characteristic values are one or more characteristic value libraries, and the characteristic value libraries comprise consumable names, manufacturing enterprises, specifications, models and registration card numbers;
calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity algorithm;
calculating at least a second UDI coding similarity value between the self-coding feature value vector of the hospital consumables and the corresponding feature value vector of each entry of the UDI coding knowledge base based on at least a second similarity algorithm;
determining weights for the first similarity algorithm and the at least second similarity algorithm;
determining a matching score of the hospital consumable self-encoding and the UDI encoding based on the first UDI encoding similarity value, at least a second UDI encoding similarity value and corresponding algorithm weight;
and taking the UDI code with the highest matching score as the UDI code matched with the hospital consumable self-code.
2. The method of claim 1, further comprising:
calculating a first medical insurance settlement encoding similarity value between the self-encoding characteristic value vector of the hospital consumables and the corresponding characteristic value vector of each item of the medical insurance settlement encoding knowledge base based on a first similarity algorithm;
calculating at least a second medical insurance settlement encoding similarity value between the hospital consumable self-encoding characteristic value vector and the corresponding characteristic value vector of each item of the medical insurance settlement encoding knowledge base based on at least a second similarity algorithm;
determining a matching score of the hospital consumable self-coding and the medical insurance settlement coding based on the first medical insurance settlement coding similarity value, at least a second medical insurance settlement coding similarity value and corresponding algorithm weight;
and taking the medical insurance settlement code with the highest matching score as the medical insurance settlement code matched with the hospital consumable self-code.
3. The method of claim 1, wherein calculating a first UDI encoded similarity value between a hospital consumable self-encoded eigenvalue vector and a corresponding eigenvalue vector of an individual entry of a UDI encoded knowledge base based on a first similarity algorithm comprises:
vectorizing the characteristic value determined based on the hospital consumable self-encoding into a hospital consumable self-encoding characteristic value vector suitable for a first similarity algorithm;
vectorizing, for each entry of the UDI encoded knowledge base, a feature value corresponding to the determined feature value into a UDI encoded knowledge base entry feature value vector suitable for a first similarity algorithm;
and calculating similarity values between the self-coding characteristic value vectors of the hospital consumables and the characteristic value vectors of the entries of the UDI coding knowledge bases respectively based on a first similarity algorithm.
4. The method of claim 1, wherein the first similarity algorithm is one of a cosine similarity algorithm, a word2vec similarity algorithm, a TF-IDF algorithm, a BM25 algorithm, and a simhash algorithm, and wherein the at least second similarity algorithm comprises one or more of the cosine similarity algorithm, the word2vec similarity algorithm, the TF-IDF algorithm, the BM25 algorithm, and the simhash algorithm that are different from the first similarity algorithm.
5. The method of claim 1, wherein determining the weights for the first similarity algorithm and the at least second similarity algorithm comprises: the weights of the first similarity algorithm and the at least second similarity algorithm are derived using a differential evolution algorithm.
6. The method of claim 1, wherein determining a match score for the hospital consumable self-code and the UDI code comprises determining a match score for the hospital consumable self-code and the UDI code as:
Hi＝∑j＝1,2,…no_wj*scoreji
wherein H is the matching score of hospital consumable self-coding and UDI coding, i represents the item of UDI coding knowledge base, HiRepresents the matching score of the hospital consumable self-code and the ith UDI code, j represents the similarity algorithm, scorejiRepresents the similarity value corresponding to the ith UDI code of the jth similarity algorithm, o _ wjThe weight of the jth similarity algorithm is represented, and n represents the number of algorithms.
7. The method of claim 4, wherein the first similarity algorithm is a cosine similarity algorithm and the at least second similarity algorithm comprises only the second similarity algorithm, the second similarity algorithm being a word2vec similarity algorithm.
8. A medical consumable traceability system, the system comprising:
the characteristic value determining module is used for determining corresponding characteristic values based on hospital consumable self-coding, wherein the characteristic values are one or more characteristic value libraries, and the characteristic value libraries comprise consumable names, manufacturing enterprises, specifications, models and registration certificate numbers;
the first similarity value calculation module is used for calculating a first UDI coding similarity value between a self-coding feature value vector of a hospital consumable and a corresponding feature value vector of each entry of the UDI coding knowledge base based on a first similarity calculation method;
the second similarity value calculation module is used for calculating at least a second UDI coding similarity value between the self-coding feature value vector of the hospital consumables and the corresponding feature value vector of each entry of the UDI coding knowledge base based on at least a second similarity algorithm;
a weight determination module for determining weights of the first similarity algorithm and the at least second similarity algorithm;
the matching score determining module is used for determining a matching score of the hospital consumable self-coding and the UDI coding based on the first UDI coding similarity value, at least a second UDI coding similarity value and corresponding algorithm weight;
and the matching code determining module is used for taking the UDI code with the highest matching score as the UDI code matched with the self-code of the hospital consumable.
9. A computer device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, wherein the steps of the method according to any of claims 1-7 are implemented when the computer program is executed by the processor.
10. 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 method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111161122.5A CN114067966A (en) | 2021-09-30 | 2021-09-30 | Medical consumable tracing method and system, corresponding equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111161122.5A CN114067966A (en) | 2021-09-30 | 2021-09-30 | Medical consumable tracing method and system, corresponding equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114067966A true CN114067966A (en) | 2022-02-18 |
Family
ID=80234023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111161122.5A Pending CN114067966A (en) | 2021-09-30 | 2021-09-30 | Medical consumable tracing method and system, corresponding equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114067966A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140244283A1 (en) * | 2013-02-25 | 2014-08-28 | Complete Consent, Llc | Pathology, radiology and other medical or surgical specialties quality assurance |
| CN109545341A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Medical consumable management method and relevant device based on data analysis |
| CN113436730A (en) * | 2021-07-14 | 2021-09-24 | 山大地纬软件股份有限公司 | Hospital disease diagnosis classification automatic coding method and system |
-
2021
- 2021-09-30 CN CN202111161122.5A patent/CN114067966A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140244283A1 (en) * | 2013-02-25 | 2014-08-28 | Complete Consent, Llc | Pathology, radiology and other medical or surgical specialties quality assurance |
| CN109545341A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Medical consumable management method and relevant device based on data analysis |
| CN113436730A (en) * | 2021-07-14 | 2021-09-24 | 山大地纬软件股份有限公司 | Hospital disease diagnosis classification automatic coding method and system |
Non-Patent Citations (2)
| Title |
|---|
| 中国医疗器械有限公司: "UDI服务公益平台详细操作指南来啦", 《SINOPHARM-CMDC.COM.CN/NEWSINOFO/1255012.HTML》, 16 March 2021 (2021-03-16), pages 1 - 4 * |
| 李杨 等: "医疗机构快速导入UDI管理的"UDI公共服务平台"模型初探", 《中国医疗设备》, 28 February 2021 (2021-02-28), pages 4 - 7 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11501874B2 (en) | System and method for machine based medical diagnostic code identification, accumulation, analysis and automatic claim process adjudication | |
| US20170286608A1 (en) | System and method for evidence based differential analysis and incentives based healthcare policy | |
| WO2019169756A1 (en) | Product recommendation method and apparatus, and storage medium | |
| CN107680661B (en) | System and method for estimating medical resource demand | |
| US10950329B2 (en) | Hybrid human and computer-assisted coding workflow | |
| US20070226040A1 (en) | Product market determination | |
| US20160378942A1 (en) | System and method to estimate reduction of lifetime healthcare costs based on body mass index | |
| US11923075B2 (en) | System and method associated with determining physician attribution related to in-patient care using prediction-based analysis | |
| US20070276704A1 (en) | System and Method for Providing Insurance Data | |
| US11829891B2 (en) | Integrated hospital logistics management system using AI technology, and integrated hospital logistics management method using same | |
| Prasad et al. | Integration of SWOT analysis with hybrid modified TOPSIS for the lean strategy evaluation | |
| Lu et al. | Design-based theory for cluster rerandomization | |
| Zemlyak et al. | Tools for Correlation and Regression Analyses in Estimating a Functional Relationship of Digitalization Factors | |
| Wang | Analysis and Application of Quality Indicators in Hospital Administrative Management Based on a Fuzzy Hierarchical Model | |
| Ferrara et al. | A robust optimization model for a decision-making problem: An application for stock market | |
| CN112786124B (en) | Problem troubleshooting method and device, storage medium and equipment | |
| Machado et al. | Analysis of the influence of standard time variability on the reliability of the simulation of assembly operations in manufacturing systems | |
| US20180260903A1 (en) | Computerized machine learning based recommendations | |
| CN114067966A (en) | Medical consumable tracing method and system, corresponding equipment and storage medium | |
| Chakrabarti et al. | An interoperable similarity-based cohort identification method using the omop common data model version 5.0 | |
| Huang et al. | Assessing the validity of race and ethnicity coding in administrative Medicare data for reporting outcomes among Medicare advantage beneficiaries from 2015 to 2017 | |
| Teichmann et al. | Data preparation for clinical data mining to identify patients at risk of readmission | |
| Ellingsworth et al. | Text mining improves business intelligence and predictive modeling in insurance | |
| US11120894B2 (en) | Medical concierge | |
| US10983959B2 (en) | Merchant table and associated processes |
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: 20220218 |