WO2021251558A1 - Appareil, système et procédé de classification de données pour une recherche d'essai clinique - Google Patents

Appareil, système et procédé de classification de données pour une recherche d'essai clinique Download PDF

Info

Publication number
WO2021251558A1
WO2021251558A1 PCT/KR2020/013478 KR2020013478W WO2021251558A1 WO 2021251558 A1 WO2021251558 A1 WO 2021251558A1 KR 2020013478 W KR2020013478 W KR 2020013478W WO 2021251558 A1 WO2021251558 A1 WO 2021251558A1
Authority
WO
WIPO (PCT)
Prior art keywords
clinical trial
data
classification
search
processing unit
Prior art date
Application number
PCT/KR2020/013478
Other languages
English (en)
Korean (ko)
Inventor
정지희
송남구
Original Assignee
(주)메디아이플러스
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by (주)메디아이플러스 filed Critical (주)메디아이플러스
Publication of WO2021251558A1 publication Critical patent/WO2021251558A1/fr

Links

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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/289—Object oriented databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3347—Query execution using vector based model
    • 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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records

Definitions

  • the present invention relates to a data classification apparatus, system and method for a clinical trial search, and specifically, a clinical trial data classification apparatus, system and it's about how
  • a clinical trial is a test conducted on humans to confirm the safety, pharmacological effect, and clinical effect of a drug prior to developing a drug.
  • a clinical trial is a process that must be carried out in the development of a drug because it is a procedure to ensure the safety of a drug and to confirm that it is a drug that can be marketed. Therefore, in addition to designing and conducting clinical trials, analyzing and managing past clinical trial data is also an important step.
  • KMS knowledge management system
  • the present invention provides a clinical trial data classification device that converts clinical trial data expressed in different methods into normalized expressions, thereby enabling a user to efficiently search for desired clinical trial data, in order to solve the above problems;
  • An object of the present invention is to provide a system and method.
  • the present invention is a clinical trial data classification device that can reduce time and cost for clinical trials and increase success probability by providing information on clinical trial institutions and researchers suitable for pharmaceutical/bio companies that want to conduct clinical trials for new drug development , to provide a system and method.
  • the present invention provides a clinical trial data classification device and system that can be processed according to an automated process from the collection of clinical trial data to the storage of classification data, thereby overcoming the inefficiency of the administrator having to normalize clinical trial data one by one and to provide a method.
  • the clinical trial data classification apparatus for providing the most appropriate clinical trial information regarding a search term input by a user when searching for clinical trial data according to an embodiment of the present invention receives a clinical trial registration request from a user, and registers clinical trial data a request processing unit for instructing, a clinical trial data processing unit that generates classification data converted to have a standardized search standard from the clinical trial data, and classification data, and stores classification data or classification data in response to a user's clinical trial search request It includes a clinical trial data storage unit that provides a recommended search term related to classification data, and the clinical trial data processing unit extracts a clinical trial unique code and key elements that can describe the clinical trial from the clinical trial data and creates object data and a normalization processing unit for receiving object data from the main element extracting unit and the main element extracting unit, and performing a normalization process for converting the object data into a standard search standard.
  • the inefficiency of the administrator having to normalize the clinical trial data one by one can be overcome.
  • FIG. 1 is a view for explaining a clinical trial data classification system according to an embodiment of the present invention.
  • FIG. 2 is a block diagram illustrating an operation of a clinical trial data classification device for a clinical trial registration request according to an embodiment of the present invention.
  • FIG. 3 is a block diagram for explaining the operation of a clinical trial data classification device for a clinical trial search request according to an embodiment of the present invention.
  • FIG. 4 is a flowchart for explaining the operation of a clinical trial data classification system for a clinical trial registration request according to an embodiment of the present invention.
  • FIG. 5 is a flowchart illustrating an operation of a clinical trial data classification system for a clinical trial search request according to an embodiment of the present invention.
  • each of the components may be implemented as a hardware processor, the above components may be integrated into one hardware processor, or the above components may be combined with each other and implemented as a plurality of hardware processors.
  • FIG. 1 is a view for explaining a clinical trial data classification system according to an embodiment of the present invention.
  • a clinical trial data classification system 50 may include a user terminal 100 and a clinical trial data classification apparatus 200 .
  • the user terminal 100 may be implemented as a smart phone, a tablet PC, or the like.
  • the clinical trial data classification system 50 receives a clinical trial registration request from a user, and a request processing unit 210 for instructing registration of clinical trial data, a unified search from the clinical trial data Clinical trial data that stores the clinical trial data processing unit 220 that generates classification data converted to have a standard specification and classification data, and provides classification data or a recommended search word related to classification data in response to a user's clinical trial search request and a storage unit 230 .
  • a user may include a person who wants to register clinical trial data and a person who wants to search for clinical trial data.
  • Users may include clinical trial institutions, consignee institutions, researchers, and general public who want to use clinical trial results.
  • Clinical trials are tests conducted or researched on humans or animals for the purpose of proving the safety and effectiveness of new drugs, food, medical devices, and new procedures. In order to proceed with a successful clinical trial, cooperation among various institutions, clinical trial institutions, and researchers is required. Users of clinical trial data also need to accurately search the clinical trial data they want to search in order to prevent duplicate trials and utilize clinical trial data in accordance with the purpose of use.
  • Clinical trial data may contain different multilingual expressions for each country or may contain numbers or special characters in addition to letters, so it is necessary to develop a technology to accurately classify them and find the necessary data.
  • the clinical trial data classification system 50 extracts and normalizes major elements when registering clinical trial data, and then generates and stores classification data that is clinical trial data expressed in standardized terms.
  • Clinical trial data may be directly entered by the registrant and registered, or any clinical trial data related to clinical trials stored in an external database may be received and stored.
  • the data storage unit stores the Ministry of Food and Drug Safety clinical trial approval information from the Ministry of Food and Drug Safety, clinical research registration information from the Clinical Research Information Service (CRIS), and Clinical Trials.gov (A Service of the US National Institutes of Health). Global clinical research registration information can be received and stored.
  • CRIS Clinical Research Information Service
  • Clinical Trials.gov A Service of the US National Institutes of Health
  • Clinical trial data may include information about clinical trials.
  • Clinical trial data may include clinical trial title, clinical trial institution name, disease name, drug name, researcher information, subject's gender, age, test method, test tool, biological tissue information, and the like. This is merely an example, and the clinical trial data is not limited thereto.
  • the clinical trial data classification system 50 extracts major elements from the user's clinical trial search request and normalizes the list object data expressed in unified terms. create It is retrieved from the clinical trial data database based on the list object data, and the clinical trial data or recommended search word with the highest similarity may be provided to the user as classification data.
  • the user can more accurately find the clinical trial data to be searched, and efficient search is possible to reduce the time and cost for the clinical trial, and as a result, the clinical trial data It has the effect of increasing the probability of success of the test.
  • the clinical trial data classification apparatus 200 extracts major elements from the clinical trial data, undergoes normalization processing, and creates a list object, and obtains classification data having standard specifications optimized for search. can create
  • the classification data After the classification data is stored in the database, it may be provided to the user when a corresponding user's clinical trial search request is received.
  • the clinical trial data classification apparatus 200 is optimized for classification data search through extraction of major elements from the clinical trial search data, normalization processing, and list object creation. List object data with standard specifications can be created.
  • the clinical trial data classification apparatus 200 may search classification data using the list object data and provide it to the user terminal 100 as clinical trial data related to the user's search request.
  • the classification data may be clinical trial data itself, or may include a search term related to a user's clinical trial search request.
  • the clinical trial data classification apparatus 200 may include a request processing unit 210 , a clinical trial data processing unit 220 , and a clinical trial data storage unit 230 .
  • the request processing unit 210 When the request processing unit 210 receives a clinical trial registration request from the user, it may transmit clinical trial data to the clinical trial data processing unit 220 and request registration of the clinical trial.
  • the clinical trial data processing unit 220 may generate classification data by extracting a major element from the clinical trial data, normalizing it, and then generating a list object.
  • the generated classification data may be stored in the clinical trial data storage 230 .
  • the request processing unit 210 may transmit clinical trial search data to the clinical trial data processing unit 220 and request a clinical trial search.
  • the clinical trial data processing unit 220 may generate list object data by extracting a major element from the clinical trial search data, normalizing it, and then generating a list object.
  • the generated list object data may be used as a search source for searching for classification data in the clinical trial data storage 230 .
  • the clinical trial data storage unit 230 may provide the clinical trial data with high similarity to the list object data as the searched classification data to the user terminal 100 .
  • the classification data may include recommended search terms highly related to the clinical trial data or search terms included in the clinical trial search request.
  • FIG. 2 is a block diagram illustrating an operation of a clinical trial data classification device for a clinical trial registration request according to an embodiment of the present invention.
  • the clinical trial data classification apparatus 200 may include a request processing unit 210 , a clinical trial data processing unit 220 , and a clinical trial data storage unit 230 .
  • the clinical trial data processing unit 220 extracts a clinical trial unique code and a main element that is information that can explain a clinical trial from clinical trial data, and a main element extractor that generates object data 221 and a normalization processing unit 222 that receives object data from the main element extraction unit 221 and performs a normalization process of converting the object data into a search standard standard, extracts main keywords from the normalized data, and selects the main keywords and a list object generator 223 for generating a list object by sorting by clinical trial unique code, and grouping the list object through a clustering algorithm.
  • the request processing unit 210 may instruct the user to convert and store the clinical trial data into classification data.
  • the classification data may be clinical trial data converted to have a standard specification optimized for search.
  • the request processing unit 210 may receive clinical trial data to be registered from an external database or may receive clinical trial data from the internal clinical trial data storage unit 230 .
  • the data request processing unit 210 receives the Ministry of Food and Drug Safety clinical trial approval information from the Ministry of Food and Drug Safety, clinical research registration information from CRIS (Clinical Research Information Service), Clinical Trials.gov (A Service of the US National Institutes) of Health) can receive global clinical research registration information.
  • Received clinical trial data is expressed in Korean or foreign languages, and can be returned in natural language or file format.
  • the clinical trial data includes domestic as well as overseas clinical trial data, and may include information on at least one of a clinical trial title, a clinical trial institution name, a disease name, a drug name, and researcher information.
  • the request processing unit 210 transmits the clinical trial data to the clinical trial data processing unit 220 , and the clinical trial data processing unit 230 may generate classification data through main element extraction, normalization processing, and list object generation.
  • the clinical trial data processing unit 220 may receive clinical trial data from the request processing unit 210 , convert it into classification data, and store it in the clinical trial data storage unit 230 .
  • the clinical trial data processing unit 220 may include a main element extraction unit 221 , a normalization processing unit 222 , and a list object generation unit 223 .
  • the main element extraction unit 221 may generate object data by extracting the clinical trial unique code and main element from the clinical trial data.
  • the clinical trial unique code and key elements can be sequentially extracted from the clinical trial data by reading it in the form of a string.
  • the clinical trial unique code is a unique identification code assigned to each clinical trial, and is information that allows different clinical trials to be distinguished.
  • the main elements are information that can describe the clinical trial, and may include the title of the clinical trial, the name of the clinical trial institution, the name of the disease, the drug name, the researcher information, the subject's gender, age, the test method, the test tool, and the biological tissue information. .
  • the main elements may include all of the usual information included in clinical trials, and are not limited to the examples described.
  • the normalization processing unit 130 may receive the object data from the main element extraction unit 221 and generate normalized data through a normalization process.
  • the normalization process may be a process of converting object data into a standard standard optimized for search.
  • the normalization process may include an operation of converting all data including English characters into lowercase letters or removing adjectives, adverbs, prepositions, and special characters.
  • the normalization processing unit 222 may utilize a separate stopword dictionary, and if necessary, perform a spelling check to convert the misspelled or misspelled term into a standard language.
  • the normalization process is the process of unifying the language by expressing all expressions in a foreign language in Korean and all expressions in a foreign language in a foreign language, a process of processing mainly terms related to clinical trials frequently used in the field of clinical trials, or having the same meaning. Or, it may include a process of treating a term that can be interpreted as having a similar meaning as a single unified term, and the unified term may be a term used by a person skilled in the art of clinical trials.
  • the normalization process may include a process of converting terms that are no longer used in the field of clinical trials into terms used in the current clinical trial field.
  • the list object generator 223 may extract a main keyword from the normalized data that has undergone the normalization process.
  • the extracted main keywords may be listed and created as a list object.
  • the main keyword may be determined according to the frequency number of words included in one normalized data that has undergone a normalization process.
  • the normalized data from which the main elements are extracted are the disease name (lung cancer, lung cancer, lung malignancy, lung metastasis, small cell cancer), researcher (professor A, researcher B, researcher C), and part of the clinical trial title (EP/IP) Clinical trials, expanded stage small cell lung cancer, and D-combination chemotherapy) can be exemplified.
  • the list object generator 223 selects 'lung cancer' with the highest frequency among disease names in normalized data for one clinical trial, 'Professor A' with the highest frequency among researchers, and 'Professor A' with the highest frequency among some of the clinical trial titles. High 'EP/IP clinical trial' can be determined as the main keyword.
  • the main keyword may be determined according to the number of occurrences in the entire normalized data.
  • All normalized data may be data obtained by normalizing object data generated by extracting major elements from clinical trial data for a plurality of clinical trials.
  • the overall normalized data may include normalized data for a plurality of clinical trial data (clinical trial 1, clinical trial 2, ..., clinical trial N) as well as single clinical trial data.
  • the main keyword may be determined according to the frequency of appearance from the object data from which the main element before the normalization process is extracted. Normalizing all clinical trial data collected for the determination of key keywords takes a lot of time and resources, so it may be impossible to provide fast search results.
  • the list object generating unit 223 may collect clinical trial data for a plurality of clinical trials, extract main elements, analyze the frequency of appearance, and use it as a criterion for extracting main keywords.
  • the list object generating unit 223 may refer to the clinical trial data stored in the clinical trial data storage unit 230 or refer to the clinical trial data received from an external database.
  • the list object generating unit 223 may generate a list object by arranging the main keywords by clinical trial unique code.
  • a list object is clustered through a clustering algorithm, and a cluster-specific code may be assigned to each cluster for which classification is completed.
  • the clustering algorithm may be an algorithm for classifying main elements included in the list object. Through a clustering algorithm, the main elements are grouped by individual items, and the classification data can be stored along with distance values and cluster-specific codes around the main keywords. For example, “CL0001: ⁇ 'Lung Cancer': 0.34, 'Gil-Dong Hong': 0.56, ... ⁇ ”, the cluster-specific code may be CL0001, lung cancer, Hong Gil-dong, the main keyword, and 0.34, 0.56, distance values from the cluster center.
  • the list object generator 223 may calculate a distance value from the cluster center based on the main keywords included in the cluster.
  • the distance value may be a value expressing an absolute distance numerically without considering directionality or a vector value calculated considering directionality.
  • the direction may have different values depending on the category of the main keyword (part of the clinical trial title, the name of the institution conducting the clinical trial, the name of the disease, the name of the drug, the researcher, ).
  • the list object generating unit 223 may generate a list object by further including a cluster-specific code and a distance value for each of the main keywords of the list object.
  • the distance value may be calculated by giving weights to specific main keywords.
  • the distance value can be calculated by weighting the drug name, disease name, and clinical trial institution in relation to the clinical trial among the main keywords. Information on weights may be extracted through conditional search when a user searches for a clinical trial.
  • weights can be found through conditional search for elements that should be referenced more than other elements when a user searches for clinical trials. For example, when a user enters a search word, a conditional search can be performed through a search in parentheses with the search word and (clinical trial institution). Through the search, specific weights are given to key keywords for the clinical trial site, so that the cluster center and distance values are calculated closer.
  • the weight may be any numerical value, and is not limited to a specific numerical value and is not interpreted.
  • a cluster name may be created by naming a characteristic of the cluster together with a unique code for the cluster, and the list object may further include the cluster name.
  • the list object generator 223 may store, as classification data, clinical trial data in which cluster classification is completed after the list object is created, in the clinical trial data storage unit 230 .
  • the clinical trial data storage unit 230 may compress or divide classification data and store it.
  • the classification data may be information obtained by converting different search keywords into a unified search standard.
  • the clinical trial data classification apparatus 220 may search for and provide the corresponding classification data to the user through main element extraction, normalization processing, and list object creation.
  • FIG. 3 is a block diagram for explaining the operation of a clinical trial data classification device for a clinical trial search request according to an embodiment of the present invention.
  • the clinical trial data classification apparatus 200 may include a request processing unit 210 , a clinical trial data processing unit 220 , and a clinical trial data storage unit 230 .
  • the request processing unit 210 may receive a clinical trial search request from a user, search for classification data corresponding to the search request, and provide the search request to the user.
  • the request processing unit 210 may extract clinical trial search data, which is information about a clinical trial to be searched, from the clinical trial search request, and transmit it to the clinical trial data processing unit 220 .
  • the clinical trial data processing unit 220 may finally generate list object data according to the operations of the main element extraction unit 221 , the normalization processing unit 222 , and the list object generation unit 223 . Since the operation of the clinical trial data processing unit 220 is the same as that of FIG. 2 described above, a detailed description thereof will be omitted below.
  • the request processing unit 210 may search the clinical trial data storage unit 230 for corresponding classification data based on the list object data and provide it to the user. Specifically, the request processing unit 210 may return a cluster related to the main keyword and a list object value of the cluster as a result value. With respect to the result value, the request processing unit 210 may generate a value of a list object included within a set arbitrary distance value as the result value.
  • the request processing unit 210 may provide a search result based on a distance value according to a user's search request and a distance value of a list object. For example, a value of a list object having the same distance value as a distance value according to a user's search request may be provided as a recommended search result value, or a result value of another user who has performed a similar search may be provided as a recommended search result value. .
  • the request processing unit 210 may provide a result value according to a weight through the user's conditional search. For example, when the user searches for clinical trial data based on the clinical trial institution and disease name, the request processing unit 210 gives weight to the clinical trial institution and disease name, and the clinical trial institution and disease name rather than other major factors. Classification data having a close distance value of may be preferentially provided as a search result.
  • the clinical trial data classification system may provide priority to the most recent clinical trial data by arranging and managing registered clinical trial data in time series.
  • FIG. 4 is a flowchart for explaining the operation of a clinical trial data classification system for a clinical trial registration request according to an embodiment of the present invention.
  • the clinical trial data classification device may receive a clinical trial registration request from the user and instruct clinical trial data registration.
  • the clinical trial data may be received from a database within the clinical trial data classification device or may be received from an external database.
  • the clinical trial data classification device may extract major elements from the clinical trial data.
  • the main elements are information that can describe the clinical trial, and may include the title of the clinical trial, the name of the clinical trial institution, the name of the disease, the drug name, the researcher information, the subject's gender, age, the test method, the test tool, and the biological tissue information. .
  • the main elements may include all of the usual information included in clinical trials, and are not limited to the examples described.
  • the clinical trial data classification apparatus may normalize the clinical trial data through a normalization process.
  • the normalization process may be a process of converting object data into a standard standard optimized for search.
  • the normalization process may include an operation of converting all data including English characters into lowercase letters or removing adjectives, adverbs, prepositions, and special characters.
  • a separate stop-word dictionary can be used, and if necessary, a spelling check can be performed to convert misspelled or misspelled terms into standard words.
  • the normalization process is the process of unifying the language by expressing all expressions in a foreign language in Korean and all expressions in a foreign language in a foreign language, a process of processing mainly terms related to clinical trials frequently used in the field of clinical trials, or having the same meaning. Or, it may include a process of treating a term that can be interpreted as having a similar meaning as a single unified term, and the unified term may be a term used by a person skilled in the art of clinical trials.
  • the normalization process may include a process of converting terms that are no longer used in the field of clinical trials into terms used in the current clinical trial field.
  • the clinical trial data classification apparatus may determine a main keyword according to the frequency of appearance from the normalized data.
  • the main keyword is determined according to the number of occurrences in one normalized data that has undergone the normalization process, is determined according to the number of frequencies that appears in all normalized data, or from the object data from which the main element before normalization is extracted It can be determined according to the frequency of appearance.
  • the clinical trial data classification apparatus may classify the clusters through a clustering algorithm, and may generate a list object including a cluster-specific code and a main keyword. Thereafter, in step S460, the clinical trial data classification apparatus may create and store classification data by creating a list object as a file separated by rows between clusters.
  • FIG. 5 is a flowchart illustrating an operation of a clinical trial data classification system for a clinical trial search request according to an embodiment of the present invention.
  • the clinical trial data classification apparatus may receive a clinical trial search request from the user and request a corresponding classification data search.
  • step S520 the clinical trial data classification apparatus extracts main elements from the search data included in the clinical trial search data, normalizes the clinical trial search data through the normalization process (S530), and determines the main keywords according to the frequency of appearance (Step S540), it is possible to classify groups through a clustering algorithm, and create a list object including a unique code for the cluster and a key keyword (step S550).
  • classification data is searched for based on the generated list object data, and in this case, classification data may be searched for based on a distance value according to a similarity.
  • the retrieved classification data may be provided to the user as clinical trial data or a recommended search word.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Computational Linguistics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Selon un mode de réalisation de la présente invention, un appareil de classification de données d'essai clinique permettant de fournir les informations d'essai clinique les plus appropriées se rapportant à un mot de recherche entré par un utilisateur durant une recherche de données d'essai clinique comprend : une unité de traitement de demande permettant de recevoir une demande d'enregistrement d'essai clinique de l'utilisateur et de diriger l'enregistrement de données d'essai clinique ; une unité de traitement de données d'essai clinique permettant de générer, à partir des données d'essai clinique, des données de classification converties de façon à avoir une norme de recherche unifiée ; et une unité de stockage de données d'essai clinique permettant de stocker les données de classification et de fournir les données de classification ou un mot de recherche recommandé associé aux données de classification en réponse à une demande de recherche d'essai clinique de l'utilisateur, l'unité de traitement de données d'essai clinique comprenant : une unité d'extraction de facteur principal permettant d'extraire un code unique d'essai clinique et un facteur principal, qui représente des informations qui peuvent décrire un essai clinique à partir des données d'essai clinique, et de générer des données d'objet ; et une unité de traitement de normalisation permettant de recevoir les données d'objet provenant de l'unité d'extraction de facteur principal et de convertir les données d'objet en la norme de recherche.
PCT/KR2020/013478 2020-06-08 2020-10-05 Appareil, système et procédé de classification de données pour une recherche d'essai clinique WO2021251558A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020200068779A KR102521963B1 (ko) 2020-06-08 2020-06-08 임상시험 검색을 위한 데이터 분류 장치, 시스템 및 방법
KR10-2020-0068779 2020-06-08

Publications (1)

Publication Number Publication Date
WO2021251558A1 true WO2021251558A1 (fr) 2021-12-16

Family

ID=78845781

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2020/013478 WO2021251558A1 (fr) 2020-06-08 2020-10-05 Appareil, système et procédé de classification de données pour une recherche d'essai clinique

Country Status (2)

Country Link
KR (1) KR102521963B1 (fr)
WO (1) WO2021251558A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20230100462A (ko) * 2021-12-28 2023-07-05 (주)메디아이플러스 다국가 임상데이터 표준화 방법 및 장치
KR102441576B1 (ko) * 2022-06-03 2022-09-08 주식회사 클래스액트 임상 참여 조건의 정형화를 위한 속성 인식 방법
KR102464893B1 (ko) * 2022-06-03 2022-11-09 주식회사 클래스액트 임상 참여 조건의 정형화를 위한 데이터 파이프라인 처리 방법
KR102571399B1 (ko) 2022-09-15 2023-08-29 (주)메디아이플러스 임상시험 콘텐츠 출력 장치 및 방법

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100706765B1 (ko) * 2004-11-30 2007-04-11 경북대학교 산학협력단 의료문서 통합 관리 시스템 및 방법
JP2012509542A (ja) * 2008-11-18 2012-04-19 ダタシ，エルエルシー データ収集プロセスの間の、データおよび関係するメタデータの資格付与
KR101226056B1 (ko) * 2011-07-18 2013-01-24 서울대학교병원 사용자 지향적 전자 임상시험 데이터 관리시스템
JP2016192085A (ja) * 2015-03-31 2016-11-10 富士通株式会社 臨床試験用データフォーマット作成支援プログラム、臨床試験用データフォーマット作成支援方法および情報処理装置
JP2020035036A (ja) * 2018-08-28 2020-03-05 株式会社日立製作所 試験計画策定支援装置、試験計画策定支援方法及びプログラム

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120096352A (ko) * 2011-02-22 2012-08-30 (주)서울씨알오 임상 시험 용어 코딩 장치
KR20170085813A (ko) * 2016-01-15 2017-07-25 사회복지법인 삼성생명공익재단 임상 연구 데이터 제공 방법 및 시스템
KR102073686B1 (ko) 2017-12-29 2020-02-05 건국대학교 산학협력단 유사성 판단 방법 및 그 장치

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100706765B1 (ko) * 2004-11-30 2007-04-11 경북대학교 산학협력단 의료문서 통합 관리 시스템 및 방법
JP2012509542A (ja) * 2008-11-18 2012-04-19 ダタシ，エルエルシー データ収集プロセスの間の、データおよび関係するメタデータの資格付与
KR101226056B1 (ko) * 2011-07-18 2013-01-24 서울대학교병원 사용자 지향적 전자 임상시험 데이터 관리시스템
JP2016192085A (ja) * 2015-03-31 2016-11-10 富士通株式会社 臨床試験用データフォーマット作成支援プログラム、臨床試験用データフォーマット作成支援方法および情報処理装置
JP2020035036A (ja) * 2018-08-28 2020-03-05 株式会社日立製作所 試験計画策定支援装置、試験計画策定支援方法及びプログラム

Also Published As

Publication number Publication date
KR20210152126A (ko) 2021-12-15
KR102521963B1 (ko) 2023-04-14

Similar Documents

Publication Publication Date Title
WO2021251558A1 (fr) Appareil, système et procédé de classification de données pour une recherche d'essai clinique
WO2020213843A1 (fr) Système de fourniture d'informations médicales personnalisées par l'utilisateur et son procédé de fonctionnement
Jimeno et al. Assessment of disease named entity recognition on a corpus of annotated sentences
US20200075135A1 (en) Trial planning support apparatus, trial planning support method, and storage medium
Dogan et al. An inference method for disease name normalization
WO2016190496A1 (fr) Procédé de gestion de base de métadonnées médicales et appareil associé
Golshan et al. A study of recent contributions on information extraction
Johnson et al. Evaluation of lexical methods for detecting relationships between concepts from multiple ontologies
Wang et al. Evidenceminer: Textual evidence discovery for life sciences
WO2022092409A1 (fr) Procédé de prédiction de mot-clé principal d'essais cliniques et serveur pour son exécution
WO2012046904A1 (fr) Procédé et dispositif pour fournir des informations de recherche à partir de ressources multiples
Brixtel et al. Any language early detection of epidemic diseases from web news streams
WO2020242086A1 (fr) Serveur, procédé et programme informatique pour supposer l'avantage comparatif de multi-connaissances
Huang et al. Pandasearch: A fine-grained academic search engine for research documents
WO2019112223A1 (fr) Procédé de récupération de document électronique et serveur associé
Nuzzo et al. Text Mining approaches for automated literature knowledge extraction and representation
Graubitz et al. The DIAsDEM framework for converting domain-specific texts into XML documents with data mining techniques
Ahmad et al. Pattern analysis of citation-anchors in citing documents for accurate identification of in-text citations
CN111986818A (zh) 一种基于tmprss2的新冠covid-19治疗药物筛选系统
WO2023128020A1 (fr) Procédé et dispositif de normalisation de données cliniques multinationales
Accuosto et al. Improving the accessibility of biomedical texts by semantic enrichment and definition expansion
Hussain et al. Ai driven knowledge extraction from clinical practice guidelines: Turning research into practice
Wennerberg Aligning medical domain ontologies for clinical query extraction
Segev et al. Internet as a knowledge base for medical diagnostic assistance
Hachey Towards generic relation extraction

Legal Events

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

Ref document number: 20939541

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20939541

Country of ref document: EP

Kind code of ref document: A1

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07/07/2023)