WO2023273455A1 - Procédé et appareil pour construire un graphique de connaissances médicales, dispositif et support lisible par ordinateur - Google Patents

Procédé et appareil pour construire un graphique de connaissances médicales, dispositif et support lisible par ordinateur Download PDF

Info

Publication number
WO2023273455A1
WO2023273455A1 PCT/CN2022/083925 CN2022083925W WO2023273455A1 WO 2023273455 A1 WO2023273455 A1 WO 2023273455A1 CN 2022083925 W CN2022083925 W CN 2022083925W WO 2023273455 A1 WO2023273455 A1 WO 2023273455A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
human body
body structure
case
medical knowledge
Prior art date
Application number
PCT/CN2022/083925
Other languages
English (en)
Chinese (zh)
Inventor
朱一帆
曹艳萍
Original Assignee
医智泉(杭州)医疗科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 医智泉(杭州)医疗科技有限公司 filed Critical 医智泉(杭州)医疗科技有限公司
Publication of WO2023273455A1 publication Critical patent/WO2023273455A1/fr

Links

Images

Classifications

    • 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the embodiments of the present application relate to the field of medical technology, and in particular to a method, device, electronic device, and computer-readable medium for constructing a medical knowledge map.
  • the Knowledge Graph is essentially a language network. Its nodes represent entities, and connections represent various semantic relationships between entities, which can connect scattered knowledge to each other. Thus forming a A huge, networked knowledge system built with the "semantic network" as the skeleton. As more and more semantic WWW data is opened on the Internet, various Internet search engine companies at home and abroad have begun to build knowledge graphs based on this to improve service quality, such as Google Knowledge Graph (Google Knowledge Graph), Baidu "Zhixin” and so on. The construction of knowledge graphs in the medical field is a major research hotspot at present. Electronic medical records (Electronic Medical Records, EMRs) refer to the digital information generated by medical personnel using electronic medical systems during medical activities.
  • EMRs Electronic Medical Records
  • Chinese electronic medical records are a valuable Chinese medical resource, containing a large amount of valuable medical knowledge and patient health information, but at the same time, Chinese electronic medical records are also a kind of unstructured information, which creates obstacles for medical research on it.
  • the medical knowledge map stores, manages, transmits and reproduces the medical knowledge in the medical records in a structured way, which can help to establish clinical auxiliary decision-making systems, personalized health models and intelligent medical questions and answers, etc., and is important for promoting the development of smart medical care. significance.
  • the purpose of the embodiments of the present application is to propose a method, device, electronic device, and computer-readable medium for constructing a medical knowledge map, so as to solve the technical problem of how to effectively construct a medical knowledge map existing in the prior art.
  • a method for constructing a medical knowledge graph includes: removing sensitive information from original case data obtained from a case database or the Internet to obtain case source data from which sensitive information has been removed;
  • the corresponding results of the human body structure data and the human body structure inspection technical data, the corresponding results of the human body function data and the human body function inspection technical data, and the clinical performance data are organized to construct a medical knowledge map.
  • the operation of removing sensitive information from the original case data acquired from the case database or the Internet includes: performing the operation of removing sensitive information from the original case data obtained from the case database or the Internet through a sensitive information elimination model, To obtain the case source data whose sensitive information has been removed.
  • screening out the human body structure data, human body function data and clinical performance data of the case from the case source data from which the sensitive information has been eliminated includes: the case source data Compared with the human body structure data in the human body structure knowledge sub-base included in the basic medical knowledge base, if they are the same, it is determined that the human body structure data screened from the case source data is the human body structure data in the human body structure knowledge sub-base Human body structure data; compare the case source data with the human body function data in the human body function knowledge sub-base included in the basic medical knowledge base, and if they are the same, determine the human body function data screened from the case source data It is the human body function data in the human body function knowledge sub-base; compare the case source data with the clinical performance data in the clinical performance sub-database included in the basic medical knowledge base, and if they are the same, determine the The clinical manifestation data screened from the case source data is the clinical manifestation data in the clinical manifestation sub-database.
  • screening out the technical data of human body structure examination and technical data of human body function examination of the case from the case source data from which the sensitive information has been eliminated including: The source data is compared with the human body structure inspection technology data in the human body structure inspection technology sub-library included in the clinical medical knowledge base, and if they are the same, it is determined that the human body structure inspection technology data screened from the case source data is the described The human body structure examination technical data in the human body structure examination technology sub-library; compare the said case source data with the human body function examination technical data in the human body function examination technology sub-library included in the clinical medical knowledge base, if they are the same, then It is determined that the technical data of the human body function test screened from the case source data is the technical data of the human body function test in the sub-library of the human function test technology.
  • the method further includes: receiving the patient's clinical performance data; deriving the human body structure data and human body structure inspection technical data related to the patient's clinical performance data according to the medical knowledge map , human body function data, and human body function test technical data; determine the patient's clinical Check item.
  • the method further includes: if it is determined according to the examination results of the patient's clinical examination items that the patient's anatomy is abnormal, then according to the patient's abnormal anatomy data and the causal logic chain, determine Anatomical treatment technical data for said patient.
  • the method further includes: if it is determined according to the examination results of the patient's clinical examination items that the patient's body function is abnormal, then according to the patient's abnormal body function data and the causal logic chain, determine Technical data of human body function therapy for said patient.
  • an apparatus for constructing a medical knowledge graph includes: an elimination module, configured to eliminate sensitive information from original case data obtained from a case database or the Internet, so as to obtain case source data whose sensitive information has been eliminated; a first screening module, configured to The basic medical knowledge base is used to filter out the human body structure data, human body function data and clinical performance data of the case from the case source data whose sensitive information has been eliminated; the second screening module is used to select the Screening out the technical data of human body structure examination and technical data of human body function examination of the case from the case source data whose sensitive information has been eliminated; the knowledge map building module is used to correspond the human body structure data to the technical data of human body structure examination, The human body function data corresponds to the human body function inspection technical data, and according to the pre-configured causal logic chain, the corresponding result of the human body structure data and the human body structure inspection technical data, the human body function data and the The corresponding results of the technical data of the human body function examination and the
  • an electronic device including: one or more processors; a storage device configured to store one or more programs; when the one or more programs are executed by the one or a plurality of processors, so that the one or more processors implement the method for constructing a medical knowledge graph as described in the first aspect of the embodiment of the present application.
  • a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the medical knowledge map as described in the first aspect of the embodiment of the present application is realized The construction method.
  • the sensitive information elimination operation is performed on the original case data obtained from the case database or the Internet, so as to obtain the case source data whose sensitive information has been eliminated; according to the pre-configured basic medical knowledge library, from the source data of the cases whose sensitive information has been eliminated, to screen out the human structure data, human body function data and clinical performance data of the cases; according to the pre-configured clinical medical knowledge base, to filter Obtain the technical data of the human body structure examination and the technical data of the human body function test of the case: correspond the said human body structure data with the said human body structure test technical data, and the said human body function data with the said human body function test technical data, and follow
  • the pre-configured causal logic chain organizes the corresponding results of the human body structure data and the human body structure examination technical data, the corresponding results of the human body function data and the human body function test technical data, and the clinical performance data , can effectively construct a medical knowledge map.
  • Fig. 1 is a flow chart of the steps of the construction method of the medical knowledge graph in Embodiment 1 of the present application;
  • FIG. 2 is a schematic structural diagram of a construction device for a medical knowledge graph according to Embodiment 2 of the present application;
  • FIG. 3 is a schematic structural diagram of the electronic device in Embodiment 3 of the present application.
  • FIG. 4 is a hardware structure of the electronic device in Embodiment 4 of the present application.
  • FIG. 1 shows a flow chart of the steps of the method for constructing the medical knowledge map according to Embodiment 1 of the present application.
  • the construction method of the medical knowledge map provided in this embodiment includes the following steps:
  • step S101 the sensitive information removal operation is performed on the original case data obtained from the case database or the Internet, so as to obtain the case source data from which the sensitive information has been removed.
  • sensitive information may be identified on the original case data, and the sensitive information may be eliminated, or data other than the sensitive information may be directly extracted from the original case data as case source data.
  • the sensitive information mainly includes the patient's name, home address, ID number, phone number, etc.
  • the original case data can be understood as the original data used to describe the patient's medical records, and the case source data can be understood as the original case data from which sensitive information has been eliminated.
  • the sensitive information when removing sensitive information from the original case data acquired from the case database or the Internet, the sensitive information is eliminated from the original case data obtained from the case database or the Internet through the sensitive information elimination model Operation to obtain the case source data whose sensitive information has been removed. Therefore, through the sensitive information elimination model, the sensitive information elimination operation on the original case data obtained from the case database or the Internet can effectively eliminate the sensitive information in the original case data obtained from the case database or the Internet.
  • the sensitive information elimination model can be any appropriate neural network model that can realize feature extraction or target object detection, including but not limited to convolutional neural network, reinforcement learning neural network, and adversarial neural network. Generate networks, etc.
  • the setting of the specific structure in the neural network can be appropriately set by those skilled in the art according to actual needs, such as the number of convolutional layers, the size of the convolutional kernel, and the number of channels.
  • the sensitive information elimination model can be trained based on the sensitive information elimination marks in the original case data samples through the backpropagation algorithm or the stochastic gradient descent algorithm.
  • step S102 according to the pre-configured basic medical knowledge base, the anatomical data, human body function data and clinical performance data of the case are screened out from the case source data from which sensitive information has been removed.
  • the pre-configured basic medical knowledge base can be understood as a pre-configured database for storing basic medical knowledge.
  • the basic medical knowledge includes a series of basic medical knowledge from gross structure to fine structure, such as anatomy, pathology, histology, cytology, and molecular biology, as well as physiology, biochemistry, A series of basic medical knowledge about functions such as drug physiology, cell physiology, and molecular biology.
  • the human body structure data can be understood as the data used to describe the human body structure of the case
  • the human body function data can be understood as the data used to describe the human body function of the case
  • the clinical performance data can be understood as the data used to describe the clinical features of the case. performance data.
  • the case The source data is compared with the human body structure data in the human body structure knowledge sub-base included in the basic medical knowledge base, and if they are the same, it is determined that the human body structure data screened from the case source data is the human body structure knowledge sub-base the human body structure data in; compare the case source data with the human body function data in the human body function knowledge sub-base included in the basic medical knowledge base, and if they are the same, determine the human body selected from the case source data
  • the function data is the human body function data in the human body function knowledge sub-database; the case source data is compared with the clinical performance data in the clinical performance sub-database included in the basic medical knowledge base, and if they are the same, then determine from The clinical manifestation data screened from the case source data is the clinical manifestation data in the clinical manifestation sub-database.
  • the human body structure knowledge sub-database can be understood as a sub-database for storing the human body structure knowledge
  • the human body function knowledge sub-database can be understood as a sub-database for storing human body function knowledge
  • the clinical manifestation sub-database can be Understand as a sub-database for storing knowledge of clinical manifestations.
  • step S103 according to the pre-configured clinical medical knowledge base, the technical data of human structure examination and technical data of human body function examination of the case are screened out from the case source data from which sensitive information has been removed.
  • the pre-configured clinical medical knowledge base can be understood as a pre-configured database for storing clinical medical knowledge.
  • qualitative and quantitative measurements of the structure and function of the body are required, and the techniques and indicators of these measurements belong to clinical medical knowledge. Measurement techniques and indicators include gross measurement to subtle measurement such as blood pressure, heart rate, electrocardiogram, renal function, echocardiography, screening of gene mutation sites, etc.
  • the human body structure examination technical data can be understood as the data of the human body structure examination technique used to describe the case, and the human body function examination technique data can be understood as the data of the human body function examination technique described for the case.
  • the obtained The case source data is compared with the human body structure inspection technology data in the human body structure inspection technology sub-library included in the clinical medical knowledge base, and if they are the same, then it is determined that the human body structure inspection technology data screened out from the case source data is The human body structure inspection technology data in the human body structure inspection technology sub-library; compare the case source data with the human body function inspection technology data in the human body function inspection technology sub-library included in the clinical medical knowledge base, if they are the same , then it is determined that the technical data of human body function test screened from the case source data is the technical data of human body function test in the sub-library of human function test technology.
  • the human body structure inspection technology sub-database can be understood as a sub-database for storing technical knowledge of human body structure inspection
  • the human body function inspection technology sub-database can be understood as a sub-database for storing human body function inspection technology knowledge.
  • the human body structure data is corresponding to the human body structure inspection technical data
  • the human body function data is corresponding to the human body function inspection technical data
  • the pre-configured causal logic chain the human body structure
  • the corresponding results of the data and the technical data of the human body structure examination, the corresponding results of the human body function data and the technical data of the human body function test, and the clinical performance data are organized to construct a medical knowledge map.
  • the human body structure data may be associated with the human body structure inspection technical data through a human body structure keyword.
  • the human body function data may be associated with the human body function inspection technical data through a human body function keyword.
  • the pre-configured causal logic chain can be understood as a pre-configured logic chain used to represent causal logic.
  • the specific form of the above-mentioned medical knowledge map can be, but not limited to, a clinical case database.
  • the clinical case database finds the human body structure data and human body structure inspection technical data in the case through the steps described in this patent based on the desensitized clinical cases. , human body function data, technical data of human body function examination, and clinical performance data, and establish a database containing the contents in the above table according to the causal logic of "human structure ⁇ (executive) human body function ⁇ (reflection) physical state".
  • the representation form of medical knowledge graph may include but not limited to clinical case database.
  • the human body structure etiology or human body function etiology of the medical knowledge graph can be the confirmed etiology of the clinical case database
  • the physical state of the medical knowledge graph can be the clinical manifestation of the clinical case database
  • the causal logic of the medical knowledge graph "human body composition ⁇ human body function ⁇ Physical state" can be the path of etiology-clinical manifestation of the clinical case database.
  • coronary atherosclerosis ⁇ extensive stenosis of coronary arteries ⁇ myocardial ischemia ⁇ (1) acute right ventricular myocardial infarction ⁇ chest tightness, arrhythmia, (2) mitral and tricuspid regurgitation ⁇
  • Heart failure ⁇ increased left and right atrial pressure ⁇ pulmonary congestion (lung moist rales), systemic circulation congestion (pleural effusion, jugular vein slightly filled)
  • the method further includes: receiving the patient's clinical performance data; deriving the human body structure data, human body data related to the patient's clinical performance data according to the medical knowledge map Structural inspection technical data, human body function data, and human body function inspection technical data; according to the human body structure data related to the patient's clinical performance data, human body structure inspection technical data, human body function data, and human body function inspection technical data, determine the The clinical examination items of the patients mentioned above.
  • the clinical examination items of the patient can be accurately determined through the human body structure data, human body structure examination technical data, human body function data, and human body function examination technical data related to the patient's clinical performance data.
  • the application of the above-mentioned knowledge map is based on the causal logic of "human body structure ⁇ human body function ⁇ body state", and deduces from symptoms and signs what are the related human body structures, what are the human body functions, and the corresponding human body What are the structural inspection techniques and human body function examination techniques, so that the necessary clinical examination items can be determined.
  • the method further includes: if it is determined according to the examination results of the patient's clinical examination items that the patient's anatomy is abnormal, then according to the abnormal anatomy data of the patient and the causal Logical chain, determine the patient's anatomical treatment technical data. Thereby, according to the patient's abnormal body structure data and the causal logic chain, the patient's body structure treatment technical data can be accurately determined.
  • the method further includes: if it is determined according to the examination results of the patient's clinical examination items that the patient's human body function is abnormal, then according to the abnormal human body function data of the patient and the causal Logical chain, to determine the technical data of the patient's human body function treatment. Thereby, according to the patient's abnormal human body function data and the causal logic chain, the patient's body function treatment technical data can be accurately determined.
  • the composition of the medical knowledge map includes: (1) etiology, (2) clinical manifestation-etiology path: pathophysiological logic chain, (3) treatment strategy.
  • COPD chronic obstructive pulmonary disease
  • COPD chronic obstructive pulmonary disease
  • the disease burden ranks first in the scope of the disease.
  • the incidence rate of the population over 40 years old in my country is as high as 13.6%.
  • the disease has a high disability rate, a heavy medical burden, and a great impact on the lives of patients, resulting in a huge economic and social burden.
  • COPD clinical case database (clinical case database), which will provide information for the pathogenesis of COPD, laboratory Diagnostic and drug development research lays an important data foundation.
  • sorting out, summarizing and managing COPD clinical data in the form of a COPD clinical case database sharing platform is conducive to the integration and standardized management of COPD clinical case data information, improving the efficiency of data resource management and use, and benefiting clinical teaching and clinical practice.
  • the COPD clinical case database can be established by the construction method of the medical knowledge graph provided in this embodiment.
  • the representation form of the medical knowledge map may include but not limited to the COPD clinical case database.
  • the human body structural lesion or human functional lesion of the medical knowledge map can be the pathological change or pathophysiology of the COPD clinical case database
  • the body state of the medical knowledge map can be the clinical manifestation of the COPD clinical case database
  • the causal logic of the medical knowledge map "human body composition ⁇ Human body function ⁇ physical condition” can be the causal logic chain "pathological changes ⁇ pathophysiology ⁇ clinical manifestations" of the COPD clinical case database.
  • the causal logic chain of "pathological changes ⁇ pathophysiology ⁇ clinical manifestations" is the objective law of disease occurrence and development, and it is also the theoretical basis for doctors to judge the disease, diagnose and treat it.
  • the same etiology may have different disease (pathophysiological) development status and clinical manifestations; different etiology (pathological changes) may have the same disease (pathophysiological) status and clinical manifestations which performed.
  • This example is based on a large number of clinical cases, using the method of clinical thinking to analyze the cases, find out the logical correlation of "pathological changes ⁇ pathophysiology ⁇ clinical manifestations" of each case, and summarize the different pathophysiology and clinical manifestations of the same pathological changes , as well as the same pathophysiological and clinical manifestations of different pathological changes, and in-depth exploration of its causes, constitute a clinical case library.
  • the sensitive information elimination operation is performed on the original case data obtained from the case database or the Internet, so as to obtain the case source data whose sensitive information has been eliminated; according to the pre-configured basic medical knowledge library, from the source data of the cases whose sensitive information has been eliminated, to screen out the human structure data, human body function data and clinical performance data of the cases; according to the pre-configured clinical medical knowledge base, to filter Obtain the technical data of the human body structure examination and the technical data of the human body function examination of the case: correspond the said human body structure data with the said human body structure examination technical data, and the said human body function data with the said human body function examination technical data, and follow
  • the pre-configured causal logic chain organizes the corresponding results of the human body structure data and the human body structure examination technical data, the corresponding results of the human body function data and the human body function test technical data, and the clinical performance data , can effectively construct a medical knowledge map.
  • the method for constructing a medical knowledge graph provided in this embodiment can be executed by any appropriate device with data processing capabilities, including but not limited to: cameras, terminals, mobile terminals, PCs, servers, vehicle-mounted devices, entertainment devices, advertising devices, Personal digital assistants (PDAs), tablets, laptops, handheld game consoles, smart glasses, smart watches, wearable devices, virtual display devices or display enhancement devices, etc.
  • PDAs Personal digital assistants
  • FIG. 2 it shows a schematic structural diagram of an apparatus for constructing a medical knowledge graph according to Embodiment 2 of the present application.
  • the device for constructing the medical knowledge map includes: an elimination module 201, which is used to perform an operation of eliminating sensitive information on the original case data acquired from the case database or the Internet, so as to obtain case source data whose sensitive information has been eliminated;
  • the screening module 202 is used to screen out the anatomical data, human body function data and clinical performance data of the case from the case source data whose sensitive information has been eliminated according to the pre-configured basic medical knowledge base;
  • the second screening module 203 is used to According to the pre-configured clinical medical knowledge base, the human body structure inspection technical data and human body function inspection technical data of the case are screened out from the case source data that has eliminated sensitive information;
  • the knowledge map construction module 204 is used to
  • the structural data corresponds to the technical data of the human body structure inspection
  • the human body function data corresponds to the technical data of the human body function inspection, and according to the pre-configured causal logic chain, the human body structure data and the human body structure inspection technical data
  • the elimination module 201 is specifically configured to: use the sensitive information elimination model to perform sensitive information elimination operations on the original case data obtained from the case database or the Internet, so as to obtain the case source data whose sensitive information has been eliminated .
  • the first screening module 202 is specifically configured to: compare the case source data with the human body structure data in the human body structure knowledge sub-base included in the basic medical knowledge base, and if they are the same, determine The human body structure data screened from the case source data is the human body structure data in the human body structure knowledge sub-base; combine the case source data with the human body function in the human body function knowledge sub-base included in the basic medical knowledge base The data are compared, and if they are the same, it is determined that the human body function data screened out from the case source data is the human body function data in the human body function knowledge sub-base; the case source data and the basic medical knowledge base include Compare the clinical manifestation data in the clinical manifestation sub-database, if they are the same, then determine the clinical manifestation data screened from the case source data as the clinical manifestation data in the clinical manifestation sub-database.
  • the second screening module 203 is specifically configured to: compare the case source data with the human body structure inspection technology data in the human body structure inspection technology sub-library included in the clinical medical knowledge base, if they are the same , it is determined that the human body structure examination technical data screened from the case source data is the human body structure examination technical data in the human body structure examination technology sub-library; the case source data and the human body included in the clinical medical knowledge base Compare the human body function test technical data in the function test technology sub-library, if they are the same, then determine that the human body function test technology data screened from the case source data is the human body function test technology in the human body function test technology sub-library data.
  • the device further includes: a first determination module, configured to receive the patient's clinical performance data after constructing the medical knowledge graph; deduce the human body structure related to the patient's clinical performance data according to the medical knowledge graph data, technical data of human anatomy examination, data of human body function, and technical data of examination of human body function; , to determine the clinical examination items of the patient.
  • a first determination module configured to receive the patient's clinical performance data after constructing the medical knowledge graph; deduce the human body structure related to the patient's clinical performance data according to the medical knowledge graph data, technical data of human anatomy examination, data of human body function, and technical data of examination of human body function; , to determine the clinical examination items of the patient.
  • the device further includes: a second determining module, configured to, if it is determined that the patient's anatomy is abnormal according to the examination results of the patient's clinical examination items, then according to the abnormal anatomy data of the patient and the The causal logic chain determines the technical data of the patient's anatomical structure treatment.
  • a second determining module configured to, if it is determined that the patient's anatomy is abnormal according to the examination results of the patient's clinical examination items, then according to the abnormal anatomy data of the patient and the The causal logic chain determines the technical data of the patient's anatomical structure treatment.
  • the device further includes: a third determining module, configured to determine that the patient's human body function is abnormal according to the examination results of the patient's clinical examination items, then according to the patient's abnormal human body function data and The causal logic chain determines the technical data of the patient's body function treatment.
  • a third determining module configured to determine that the patient's human body function is abnormal according to the examination results of the patient's clinical examination items, then according to the patient's abnormal human body function data and The causal logic chain determines the technical data of the patient's body function treatment.
  • the device for constructing a medical knowledge graph in this embodiment is used to implement the corresponding methods for constructing a medical knowledge graph in the foregoing method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.
  • FIG. 3 is a schematic structural diagram of an electronic device in Embodiment 3 of the present application; the electronic device may include:
  • processors 301 one or more processors 301;
  • the computer-readable medium 302 may be configured to store one or more programs,
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the method for constructing a medical knowledge map as described in the first embodiment above.
  • Fig. 4 is the hardware structure of the electronic device in Embodiment 4 of the present application; as shown in Fig. 4, the hardware structure of the electronic device may include: a processor 401, a communication interface 402, a computer readable medium 403 and a communication bus 404;
  • processor 401 the communication interface 402, and the computer-readable medium 403 complete mutual communication through the communication bus 404;
  • the communication interface 402 may be an interface of a communication module, such as an interface of a GSM module;
  • the processor 401 can specifically be configured to: perform sensitive information elimination operations on the original case data acquired from the case database or the Internet, so as to obtain case source data from which sensitive information has been eliminated; According to the pre-configured clinical medical knowledge base, screen out the cases from the source data of cases whose sensitive information has been eliminated Human body structure inspection technical data and human body function inspection technical data: the human body structure data is corresponding to the human body structure inspection technical data, the human body function data is corresponding to the human body function inspection technical data, and according to the pre-configured cause and effect Logical chain, organize the corresponding results of the human body structure data and the human body structure examination technical data, the corresponding results of the human body function data and the human body function test technical data, and the clinical performance data, so as to construct a medical Knowledge graph.
  • Processor 401 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC) ), off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the computer-readable medium 403 may be, but not limited to, a random access storage medium (Random Access Memory, RAM), a read-only storage medium (Read Only Memory, ROM), a programmable read-only storage medium (Programmable Read-Only Memory, PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc.
  • RAM Random Access Memory
  • ROM Read Only Memory
  • PROM Programmable Read-Only Memory
  • EPROM Erasable Programmable Read-Only Memory
  • EEPROM Electric Erasable Programmable Read-Only Memory
  • the processes described above with reference to the flowcharts can be implemented as computer software programs.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program code configured to execute the method shown in the flowchart.
  • the computer program can be downloaded and installed from a network via the communication part, and/or installed from a removable medium.
  • CPU central processing unit
  • the above-mentioned functions defined in the method of the present application are performed.
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • a computer readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer diskettes, hard disks, random access storage media (RAM), read only storage media (ROM), erasable Programmable read-only storage medium (EPROM or flash memory), optical fiber, portable compact disk read-only storage medium (CD-ROM), optical storage medium, magnetic storage medium, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit a program configured to be used by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code configured to carry out the operations of the present application may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, including conventional A procedural programming language—such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network: including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider). connect).
  • LAN local area network
  • WAN wide area network
  • connect such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions configured to implement specified executable instructions.
  • sequence relationships There are specific sequence relationships in the above specific embodiments, but these sequence relationships are only exemplary, and in actual implementation, these steps may be fewer, more, or the order of execution may be adjusted. That is, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments described in the present application may be implemented by means of software or hardware.
  • the described modules can also be set in a processor, for example, it can be described as: a processor includes an elimination module, a first screening module, a second screening module and a knowledge map building module.
  • a processor includes an elimination module, a first screening module, a second screening module and a knowledge map building module.
  • the names of these modules do not constitute a limitation of the module itself under certain circumstances.
  • the elimination module can also be described as "elimination of sensitive information on the original case data obtained from the case database or the Internet, to A module for obtaining case source data from which sensitive information has been removed".
  • the present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method for constructing a medical knowledge map as described in the first embodiment above is implemented.
  • the present application also provides a computer-readable medium.
  • the computer-readable medium may be included in the device described in the above embodiments, or it may exist independently without being assembled into the device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the device, the device: performs an operation of eliminating sensitive information on the original case data obtained from the case database or the Internet to obtain Case source data whose sensitive information has been removed; according to the pre-configured basic medical knowledge base, the anatomical structure data, human body function data and clinical performance data of the case are screened out from the case source data whose sensitive information has been removed; according to the pre-configured clinical Medical knowledge base, screening out the technical data of human body structure examination and technical data of human body function examination of the case from the source data of the cases whose sensitive information has been eliminated: corresponding the human body structure data with the technical data of human body structure examination, the The human body function data corresponds to the human body function inspection technical data, and according to the pre
  • first, second, the first or “the second” used in various embodiments of the present disclosure may modify various components regardless of order and/or importance , but these expressions do not limit the corresponding components.
  • the above expressions are configured only for the purpose of distinguishing an element from other elements.
  • the first user equipment and the second user equipment represent different user equipments, although both are user equipments.
  • a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure.
  • an element eg, a first element
  • another element eg, a second element
  • an element eg, a second element
  • an element eg, a second element
  • the one element is directly connected to the other element or that the one element is connected via another element (eg, a second element).
  • third element is indirectly connected to the other element.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioethics (AREA)
  • General Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pathology (AREA)
  • Computational Linguistics (AREA)
  • Epidemiology (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne un procédé et un appareil pour construire un graphique de connaissances médicales, un dispositif et un support lisible par ordinateur. Le procédé consiste à : éliminer des informations sensibles de données d'enregistrement médical d'origine obtenues à partir d'une base de données d'enregistrements médicaux ou d'Internet pour obtenir des données de source d'enregistrement médical à partir desquelles les informations sensibles sont éliminées (S101) ; sélectionner, selon une base de connaissances médicales de base, des données de structure de corps humain, des données de fonction de corps humain et des données de manifestation clinique d'enregistrements médicaux à partir des données de source d'enregistrement médical à partir desquelles les informations sensibles sont éliminées (S102) ; sélectionner, selon une base de connaissances médicales cliniques, des données techniques d'examen de structure de corps humain et des données techniques d'examen de fonction de corps humain des enregistrements médicaux à partir des données de source d'enregistrement médical à partir desquelles les informations sensibles sont éliminées (S103) ; et faire correspondre les données de structure de corps humain avec les données techniques d'examen de structure de corps humain, et les données de fonction de corps humain avec les données techniques d'examen de la fonction de corps humain, et organiser les résultats de correspondance de structures de corps humain, les résultats de correspondance de fonctions de corps humain et les données de manifestation clinique selon une chaîne logique causale pour construire un graphique de connaissances médicales (S104).
PCT/CN2022/083925 2021-06-29 2022-03-30 Procédé et appareil pour construire un graphique de connaissances médicales, dispositif et support lisible par ordinateur WO2023273455A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202110726345.5 2021-06-29
CN202110726345 2021-06-29
CN202110767253.1A CN113505236B (zh) 2021-06-29 2021-07-07 医疗知识图谱的构建方法、装置、设备及计算机可读介质
CN202110767253.1 2021-07-07

Publications (1)

Publication Number Publication Date
WO2023273455A1 true WO2023273455A1 (fr) 2023-01-05

Family

ID=78011877

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/083925 WO2023273455A1 (fr) 2021-06-29 2022-03-30 Procédé et appareil pour construire un graphique de connaissances médicales, dispositif et support lisible par ordinateur

Country Status (2)

Country Link
CN (1) CN113505236B (fr)
WO (1) WO2023273455A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113505236B (zh) * 2021-06-29 2023-08-04 朱一帆 医疗知识图谱的构建方法、装置、设备及计算机可读介质
CN113871003B (zh) * 2021-12-01 2022-04-08 浙江大学 一种基于含因果性医学知识图谱的疾病辅助鉴别诊断系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180165415A1 (en) * 2016-12-09 2018-06-14 International Business Machines Corporation Method and system for automatic knowledge-based feature extraction from electronic medical records
CN108492887A (zh) * 2018-04-13 2018-09-04 合肥工业大学 医疗知识图谱构建方法及装置
CN109635121A (zh) * 2018-11-07 2019-04-16 平安科技（深圳）有限公司 医疗知识图谱创建方法及相关装置
CN110083708A (zh) * 2019-04-26 2019-08-02 常州市贝叶斯智能科技有限公司 一种基于知识图谱的医疗实体关联分析方法
CN110362690A (zh) * 2019-07-04 2019-10-22 北京爱医生智慧医疗科技有限公司 一种医学知识图谱构建方法及装置
CN113505236A (zh) * 2021-06-29 2021-10-15 医智泉(杭州)医疗科技有限公司 医疗知识图谱的构建方法、装置、设备及计算机可读介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11069432B2 (en) * 2016-10-17 2021-07-20 International Business Machines Corporation Automatic disease detection from unstructured textual reports
US11195600B2 (en) * 2016-10-17 2021-12-07 International Business Machines Corporation Automatic discrepancy detection in medical data
CN106874643B (zh) * 2016-12-27 2020-02-28 中国科学院自动化研究所 基于词向量自动构建知识库实现辅助诊疗的方法和系统
CN106844723B (zh) * 2017-02-10 2019-09-10 厦门大学 基于问答系统的医学知识库构建方法
CN109346169A (zh) * 2018-10-17 2019-02-15 长沙瀚云信息科技有限公司 一种人工智能辅助诊疗系统及其构建方法、设备和存储介质
CN111048167B (zh) * 2019-10-31 2023-08-18 中电药明数据科技(成都)有限公司 一种层级式病例结构化方法及系统
CN112863630A (zh) * 2021-01-20 2021-05-28 中国科学院自动化研究所 基于数据和知识的个性化精准医疗问答系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180165415A1 (en) * 2016-12-09 2018-06-14 International Business Machines Corporation Method and system for automatic knowledge-based feature extraction from electronic medical records
CN108492887A (zh) * 2018-04-13 2018-09-04 合肥工业大学 医疗知识图谱构建方法及装置
CN109635121A (zh) * 2018-11-07 2019-04-16 平安科技（深圳）有限公司 医疗知识图谱创建方法及相关装置
CN110083708A (zh) * 2019-04-26 2019-08-02 常州市贝叶斯智能科技有限公司 一种基于知识图谱的医疗实体关联分析方法
CN110362690A (zh) * 2019-07-04 2019-10-22 北京爱医生智慧医疗科技有限公司 一种医学知识图谱构建方法及装置
CN113505236A (zh) * 2021-06-29 2021-10-15 医智泉(杭州)医疗科技有限公司 医疗知识图谱的构建方法、装置、设备及计算机可读介质

Also Published As

Publication number Publication date
CN113505236A (zh) 2021-10-15
CN113505236B (zh) 2023-08-04

Similar Documents

Publication Publication Date Title
Acosta et al. Multimodal biomedical AI
Estiri et al. Evolving phenotypes of non-hospitalized patients that indicate long COVID
JP6916107B2 (ja) 患者データに基づく健康診断および治療のためのベイジアン因果関係ネットワークモデル
Cooke et al. Using existing data to address important clinical questions in critical care
WO2023273455A1 (fr) Procédé et appareil pour construire un graphique de connaissances médicales, dispositif et support lisible par ordinateur
Lee et al. A framework for data quality assessment in clinical research datasets
Cole et al. Profiling risk factors for chronic uveitis in juvenile idiopathic arthritis: a new model for EHR-based research
Robinson et al. Defining phenotypes from clinical data to drive genomic research
Tariq et al. Deep learning techniques for optimizing medical big data
Antoniades et al. The year in cardiovascular medicine 2020: digital health and innovation
Pang et al. Construction and management of ARDS/sepsis registry with REDCap
WO2017106819A1 (fr) Procédés et systèmes de représentation, de stockage et d'accès à des quantités dérivées d'imagerie médicale calculables
Kumar Healthcare analytics made simple: techniques in healthcare computing using machine learning and Python
Wang et al. Application prospect of the SOFA score and related modification research progress in sepsis
do Valle et al. Network-medicine framework for studying disease trajectories in US veterans
JPWO2019220833A1 (ja) 診断支援システム、診断支援装置および診断支援方法
Cazacu et al. The Accuracy of Pre-Endoscopic Scores for Mortality Prediction in Patients with Upper GI Bleeding and No Endoscopy Performed
Kamel et al. How Artificial Intelligence Can Enhance the Diagnosis of Cardiac Amyloidosis: A Review of Recent Advances and Challenges
Di Costanzo et al. An artificial intelligence analysis of electrocardiograms for the clinical diagnosis of cardiovascular diseases: a narrative review
CN107610783A (zh) 一种脑肿瘤信息平台
Castro Portillo et al. Modified sequential organ failure assessment score vs. early warning scores in prehospital care to predict major adverse cardiac events in acute cardiovascular disease
Hossain et al. Inter Disease Relations Based on Human Biomarkers by Network Analysis
CN112652400A (zh) 基于专病视图相似分析病情参考方法、系统、设备和介质
CN111128330A (zh) 电子病例报告表自动录入方法、装置以及相关设备
CN117453752B (zh) 基于检索配置表数据模型的医院临床数据检索方法及装置

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: 22831286

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE