CN111383773A - Medical entity information processing method and device, storage medium and electronic equipment - Google Patents
Medical entity information processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111383773A CN111383773A CN201811624476.7A CN201811624476A CN111383773A CN 111383773 A CN111383773 A CN 111383773A CN 201811624476 A CN201811624476 A CN 201811624476A CN 111383773 A CN111383773 A CN 111383773A
- Authority
- CN
- China
- Prior art keywords
- entity
- medical
- information
- list
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
-
- 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
Abstract
The disclosure belongs to the field of knowledge graphs, and relates to a method and a device for processing medical entity information and electronic equipment. The method comprises the following steps: acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list; determining a plurality of pieces of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, determining one piece of associated entity information from the first medical entity list or the second medical entity list, and acquiring a higher-order entity relationship pair according to the plurality of pieces of conditional entity information and the associated entity information; wherein the plurality of conditional entity information is different from the associated entity information; and determining the incidence relation between different medical entity information according to the high-order entity relation pair. The method and the device can enable the information expression in the medical knowledge graph to be more perfect and accurate, and improve the accuracy of reasoning and calculation.
Description
Technical Field
The present disclosure relates to the field of knowledge graph technology, and in particular, to a method and an apparatus for processing medical entity information, a computer-readable storage medium, and an electronic device.
Background
The knowledge map is also called a scientific knowledge map, is called knowledge domain visualization or knowledge domain mapping map in the book information field, is a series of different graphs for displaying the relationship between the knowledge development process and the structure, describes knowledge resources and carriers thereof by using visualization technology, and excavates, analyzes, constructs, draws and displays knowledge and the mutual connection between the knowledge resources and the carriers.
With the development of electronic information technology, in the medical field, a medical knowledge map is formed by summarizing and sorting medical knowledge, wherein the medical knowledge map comprises the complicated and intricate relations among symptoms, diseases and diagnosis and treatment means, and a good auxiliary diagnosis means can be provided for medical staff through the medical knowledge map. However, when a medical knowledge graph is constructed, only the relationship between every two medical entities is designed, and when reasoning is performed according to the medical knowledge graph, a condition-independent assumption needs to be introduced to convert a multivariate condition into a univariate condition for calculation, but not all conditions are mutually independent, so the condition-independent assumption does not meet the actual situation, and calculation errors can be caused in many scenes.
Therefore, there is a need in the art for a new method and apparatus for processing medical entity information.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The present disclosure is directed to a method for constructing a medical knowledge graph, a data processing apparatus, a computer-readable storage medium, and an electronic device, so as to overcome, at least to some extent, the problems of computational errors and the like caused by the need of independent assumption conditions when reasoning is performed according to the medical knowledge graph due to the limitations and disadvantages of the related art.
According to an aspect of the present disclosure, there is provided a method for processing medical entity information, including:
acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list;
determining a plurality of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, and determining one associated entity information from the first medical entity list or the second medical entity list, and obtaining higher-order entity relationship pairs according to the plurality of conditional entities and the associated entity; wherein the plurality of conditional entity information is different from the associated entity information;
and determining the incidence relation between different medical entity information according to the high-order entity relation pair.
In an exemplary embodiment of the present disclosure, target medical information is acquired according to a preset condition, the target medical information including a first medical entity list, a second medical entity list, and a third medical entity list, including:
acquiring medical information corresponding to the visit ID from an electronic medical record database according to the visit ID;
performing a preprocessing operation on the medical information to obtain the target medical information, wherein the target medical data includes the first medical entity list, the second medical entity list, and the third medical entity list.
In an exemplary embodiment of the present disclosure, determining an incidence relation between different medical entity information according to the higher-order entity relation pair includes:
calculating conditional probability among the different medical entity information according to the high-order entity relation pair;
and determining the incidence relation between the different medical entity information according to the conditional probability.
In an exemplary embodiment of the present disclosure, calculating a conditional probability between the different medical entity information according to the pair of higher order entity relationships includes:
acquiring a first number of entity relationship pairs in an electronic medical record database, wherein the entity relationship pairs are the same as the high-order entity relationship pairs;
acquiring a second number of entity relationship pairs in the electronic medical record database, wherein the entity relationship pairs have conditional entity information which is the same as the conditional entity information in the higher-order entity relationship pairs;
comparing the first number to the second number to obtain the conditional probability.
In an exemplary embodiment of the present disclosure, the method further comprises:
mapping the diagnosis entity information in the first medical entity list with the non-diagnosis entity information in the second medical entity list and the patient information entity information in the third medical entity list respectively to obtain a first one-order entity relationship pair;
mapping non-diagnostic entity information in the second medical entity list with patient information entity information in the third medical entity list to obtain a second-order entity relationship pair;
mapping target non-diagnostic entity information in the second medical entity list with other non-diagnostic entity information to obtain a third-order entity relationship pair;
and determining a first-order entity relationship pair according to the first-order entity relationship pair, the second-order entity relationship pair and the third-order entity relationship pair.
In an exemplary embodiment of the present disclosure, the first medical entity list is a diagnostic entity list, the second medical entity list is a non-diagnostic entity list, and the third medical entity list is a patient information entity list.
In an exemplary embodiment of the present disclosure, the method further comprises:
and respectively carrying out Cartesian product on the diagnosis entity list and the non-diagnosis entity list, the diagnosis entity list and the patient information entity list, the non-diagnosis entity list and the patient information entity list, and forming an entity relationship pair according to target non-diagnosis entity information and other non-diagnosis entity information in the non-diagnosis entity list so as to obtain a first-order entity relationship pair.
According to an aspect of the present disclosure, there is provided a processing apparatus of medical entity information, including:
the target medical data acquisition module is used for acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list;
a higher-order entity relationship pair obtaining module, configured to determine multiple pieces of conditional entity information from the first medical entity list, the second medical entity list, and/or the third medical entity list, determine one piece of associated entity information from the first medical entity list or the second medical entity list, and obtain a higher-order entity relationship pair according to the multiple pieces of conditional entity information and the associated entity; wherein the plurality of conditional entity information is different from the associated entity information;
and the entity incidence relation determining module is used for determining incidence relations among different medical entity information according to the high-order entity relation pairs.
According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of processing medical entity information as described in any one of the above.
According to an aspect of the present disclosure, there is provided an electronic device including:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the processing method of the medical entity information according to any one of the above items via executing the executable instructions.
The method comprises the steps of determining a plurality of pieces of conditional entity information from a first medical entity list, a second entity medical list and/or a third medical entity list, determining one piece of associated entity information from the first medical entity list or the second entity medical list, then obtaining a higher-order entity relation pair according to the plurality of pieces of conditional entity information and the associated entity information, and finally determining an association relation between different pieces of medical entity information according to the higher-order entity relation pair. According to the method, on one hand, the incidence relation between different medical entity information is determined according to the high-order entity relation, the condition independent assumption can be avoided, the multivariate conditional probability can be obtained, and the calculation accuracy is improved; on the other hand, the medical knowledge graph is constructed according to the incidence relation among the first-order entity relation pair, the high-order entity relation pair and the medical entity information, so that the information expression in the medical knowledge graph is more perfect and accurate.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
Fig. 1 schematically shows a flow diagram of a method of processing medical entity information;
FIG. 2 is a diagram schematically illustrating an exemplary application scenario of a method for processing medical entity information;
FIG. 3 schematically illustrates a flow chart for determining a high-order entity-relationship pair;
FIG. 4 schematically illustrates a flow chart for obtaining first order entity-relationship pairs;
FIG. 5 schematically illustrates a flow diagram for constructing a medical knowledge-map;
fig. 6 schematically shows a schematic structural diagram of a medical entity information processing apparatus;
fig. 7 schematically shows an example block diagram of an electronic device for implementing the above-described processing method of medical entity information;
fig. 8 schematically illustrates a computer-readable storage medium for implementing the above-described processing method of medical entity information.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
In the related art in the field, knowledge generally comes from two aspects for medical related workers, namely, learning of literature knowledge such as textbooks, clinical guidelines, monographs and treatises, and experience knowledge accumulated in clinical diagnosis and treatment work. The literature knowledge and the experience knowledge are not cleavable or replaceable, but rather complement each other. With the medical industry further understanding on the value of real world clinical data and the correction of the diagnosis and treatment method based on the real world data, a knowledge source similar to human beings is needed, and a computer algorithm system needs to construct a medical knowledge map according to literature knowledge and the real world data.
However, in the related art, the method for constructing the medical knowledge map according to the literature knowledge and the real world data has corresponding inevitable defects, and particularly, the medical knowledge map only designs the relationship between every two medical entities, when the inference is made according to the medical knowledge graph, the assumption condition is independent, the description is carried out through the unary conditional probability, however, the entity relationships in medicine are not necessarily univariate conditional probabilities that can be described in many cases, e.g., a patient with pneumonia, the symptom is milk cough, if a medical knowledge map is constructed according to [ pneumonia, milk cough ], a problem exists, since symptoms of milk cough are generally only seen by infants, adults are less likely to be present, therefore, the simple univariate conditional probability description of P (coughing | pneumonia) cannot embody the key constraint of "infants". In the face of this problem, based on a naive bayes algorithm, a multivariate condition is converted into a univariate condition for calculation, for example, it is assumed that "pneumonia" is independent from a "baby" condition, and P (coughing | pneumonia, baby) ═ P (coughing | pneumonia) × P (baby | coughing milk)/P (pneumonia, baby), but the assumption that the condition is independent does not satisfy the actual situation, which may cause calculation errors in many scenarios, so the information expression in the current medical knowledge graph is not perfect, and multivariate condition probability cannot be expressed.
For the problems in the related art, in the present exemplary embodiment, a method for processing medical entity information is first provided, and the method for processing medical entity information may be executed on a server, or may also be executed on a server cluster or a cloud server, and of course, a person skilled in the art may also execute the method disclosed in the present disclosure on another platform as needed, which is not particularly limited in the present exemplary embodiment. Referring to fig. 1, the method for processing medical entity information may include the following steps:
s110, acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list;
step S120, determining a plurality of pieces of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, determining one piece of associated entity information from the first medical entity list or the second medical entity list, and acquiring a higher-order entity relationship pair according to the plurality of conditional entities and the associated entity; wherein the plurality of conditional entity information is different from the associated entity information;
and S130, determining the incidence relation between different medical entity information according to the high-order entity relation pair.
On one hand, the multivariate conditional probability can be expressed by determining a plurality of pieces of conditional entity information and one piece of associated entity information from different medical entity lists and forming a high-order entity relationship pair according to the plurality of pieces of conditional entity information and the associated entity information, and then the problem of calculation errors caused by the independence of assumed conditions can be avoided when determining the association relationship between different pieces of medical entity information according to the high-order entity relationship pair; on the other hand, the determination of the high-order entity relationship pair can enable the information in the medical knowledge map to be more complete and the information expression to be more comprehensive.
Next, the respective steps of the processing method of medical entity information of the present disclosure will be explained according to the structure shown in fig. 2:
in step S110, target medical information is acquired according to preset conditions, where the target medical information includes a first medical entity list, a second medical entity list, and a third medical entity list.
In an exemplary embodiment of the disclosure, the medical information refers to data information in medical records generated during a patient's hospitalization, and may specifically include clinical medical data stored in an electronic medical record database. In the process of hospitalizing the patient, all the generated medical data may be stored in an electronic medical record database, which may be a data warehouse disposed in the terminal device 201 and used for storing medical data, or a storage server used for storing medical data, and the server 202 may obtain the target medical data from the data warehouse of the terminal device 201 and may also obtain the target medical data from the storage server. Since the number of patients to be treated is large, and a plurality of examinations are required for each patient according to the difference of symptoms, and accordingly, many examination data are generated, the number of medical data in the electronic medical record database is huge, and in order to improve the efficiency of acquiring target medical data, the target medical data can be acquired according to preset conditions. The preset condition may be a patient visit ID for identifying each visit of the patient, and the server 202 may perform screening in the electronic medical record database according to the visit ID to obtain the target medical data corresponding to the visit ID. Further, the medical examination ID may be a patient ID or new identification information generated from the patient ID, and the patient ID may specifically be ID information generated from the date of birth and the date of medical examination of the patient, may also be ID information generated from the date of birth, the department number of medical examination, and the date of medical examination of the patient, or may of course be ID information generated from other information, which is not particularly limited in the present disclosure.
In an exemplary embodiment of the present disclosure, different types of medical entity lists may be included in the target medical information, and in an embodiment of the present disclosure, the first medical entity list, the second medical entity list, and the third medical entity list are included in the target medical information, and specifically, the medical entity lists may be classified according to different types: as a specific embodiment, the first medical entity list in the embodiment of the present disclosure is a diagnosis entity list, the second medical entity list is a non-diagnosis entity list, and the third medical entity list is a patient information entity list. The entity information in the diagnosis entity list may specifically be a diagnosis name and a corresponding ICD code, and the diagnosis entity list may be generated according to node information by extracting the main diagnosis information corresponding to the visit ID, searching relevant nodes of the main diagnosis information in the ICD-10 disease naming standard, and then performing a search. For example, if the main diagnosis information of a patient is "antral malignancy", ICD is coded as C16.301, the diagnosis-related entity information of this visit includes C16.3-antral malignancy, C16-gastric malignancy. The entity information in the list of non-diagnostic entities may be entity information related to signs of symptoms, examination, etc., and may be, for example, a visit department entity, a medicine combination entity, a surgery name entity, etc., and the list of non-diagnostic entities may be obtained by extracting medicine combinations and medicine entities in a medicine order prescribed by a doctor from an order table, extracting a surgery name entity from a surgery table, extracting a visit department entity of a patient from a first page of a medical case or a visit table, and extracting other related entity information from other data tables, and forming a list of non-diagnostic entities according to the obtained entities. The entity information in the patient information entity list can be specifically patient ID, patient gender, patient age, patient height, patient weight and the like, and the patient information entity list can be formed by extracting patient information from a clinic table or a medical record homepage.
In an exemplary embodiment of the present disclosure, in order to ensure high availability of the target medical data, the target medical data may be subjected to a preprocessing operation after being acquired, for example, the target medical data may be cleaned, and abnormal values, repeated values, missing values, and the like may be removed; performing data integration on the target medical data, and integrating the target medical data according to the type corresponding to the target medical data; of course, other preprocessing operations may be performed, and the present disclosure is not described in detail herein.
In step S120, determining a plurality of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, and determining one associated entity information from the first medical entity list or the second medical entity list, and obtaining higher-order entity relationship pairs according to the plurality of conditional entities and the associated entity; wherein the plurality of conditional entity information is different from the associated entity information.
In an exemplary embodiment of the present disclosure, after the first medical entity list, the second medical entity list, and the third medical entity list are obtained, an entity relationship pair may be formed according to interrelations between entities in the respective lists, and the entity relationship pair may include a first order entity relationship pair and a higher order entity relationship pair.
In the exemplary embodiment of the present disclosure, generally, the occurrence of a certain symptom or a certain disease is not caused by only one condition factor, but may occur due to the combined action of a plurality of condition factors, so that it is not comprehensive to embody the relationship between the information of the medical entities through only a first-order entity relationship pair, and thus it is necessary to jointly determine a higher-order entity relationship pair according to a plurality of condition factors and corresponding symptoms or diseases to embody the relationship between different medical entities. The higher-order entity relationship pair may be a second-order entity relationship pair, a third-order entity relationship pair, or a higher-order entity relationship pair, fig. 3 shows a schematic flow chart of determining the higher-order entity relationship pair, and as shown in fig. 3, in step S301, a plurality of conditional entity information is determined from the first medical entity list, the second medical entity list, and/or the third medical entity list; the occurrence of a disease may be influenced by different ages and sexes, different diseases and ages, different ages, sexes and diseases, and the like, and similarly, the occurrence of a disease may be determined by a plurality of condition factors, and the condition factors may belong to the same entity type or different entity types, and a plurality of condition entity information may be determined from the first medical entity list, the second medical entity list and/or the third medical entity list in order to correctly express the relationship of the medical entity information; in step S302, determining an associated entity information from the first medical entity list or the second medical entity list; since condition factors affect the generation of results, and in the medical field, patient information such as patient age, patient sex, patient weight, etc. is generally the cause of the generation of results, one associated entity information may be determined from the list of diagnostic entities or the list of non-diagnostic entities; in step S303, obtaining a higher-order entity relationship pair according to the plurality of conditional entity information and associated entity information; after the condition entity information and the associated entity information are determined, a higher-order entity relationship pair can be formed according to the condition entity information and the associated entity information, and the specific expression form of the higher-order entity relationship pair can be < (condition 1+ condition 2+ … …) -associated entity >.
Table 1 shows a specific composition of target medical information, and as shown in table 1, the diagnosis names in the diagnosis entity list are pneumonia; symptoms contained in the non-diagnostic entity list are cough and milk secretion, dyspnea, pediatrics department, chest X-ray examination, blood routine examination and etiology examination; the patient information entity list comprises the age of the patient of 3 months, the sex of the patient of a male, the weight of the patient of 5Kg and the height of the patient of 50 cm.
TABLE 1
From the target medical information shown in table 1, according to the relationship among the diagnostic entity, the non-diagnostic entity, and the patient information entity, the diagnosis name and the patient age can be used as the conditional entity information, the symptom can be used as the associated entity information, and a second-order entity relationship pair < (pneumonia +3 months) -cough > can be formed according to the conditional entity information and the associated entity information; or taking the age, symptoms and examination of the patient as condition entities, taking the diagnosis name as an associated entity, and forming a three-order entity relationship pair < (3 months + cough + chest X-ray) -pneumonia > according to the condition entity and the associated entity; of course, a higher-order entity relationship pair may be formed according to other relationships between entities, so as to obtain a higher-order entity relationship. The higher-order entity relationship pairs in the present disclosure include, but are not limited to, the second-order entity relationship pair and the third-order entity relationship pair described above, and may also be other higher-order entity relationship pairs, which are not specifically limited in the present disclosure.
Further, for some specific entity relationships, higher-order entity relationship pairs can be directly formed according to the entity relationships, for example, some symptoms may only occur under certain gender, certain age group and certain diseases, so in order to describe the relationship, the higher-order entity relationship pairs can be formed according to the symptoms, gender, age group and diseases, for example, when a certain disease D occurring between 20 and 40 years old of female has a specific symptom S, a third-order entity relationship pair can be directly constructed, which is specifically expressed as < (D + female +20-40 years old) -S >.
In step S130, an association relationship between different medical entity information is determined according to the higher-order entity relationship pair.
In an exemplary embodiment of the present disclosure, after the higher-order entity relationship pair is acquired, an incidence relationship between different medical entity information may be determined according to the higher-order entity relationship pair. The association relationship can be reflected by conditional probability among different medical entity information, the conditional probability can be obtained by calculation according to a high-order entity relationship pair, and a calculation formula of the conditional probability is shown as a formula (1):
p (associated entity | condition 1, condition 2, … …, condition K) ═ Ni/N (1)
Wherein K is the number of conditional entity information in the high-order entity relationship pair, NiThe number of entity relationship pairs in the electronic medical record database, which are the same as the high-order entity relationship pairs, and the number of entity relationship pairs in the electronic medical record database, which have the same conditional entity information as the conditional entity information in the high-order entity relationship pairs.
Taking the example of calculating the conditional probability of a certain symptom R under K conditions, the calculation formula is: p (symptom-R | condition 1, condition 2, … …, condition K) ═ K in the K-th order relationship pair, where K is the amount of conditional entity information in the higher order entity relationship pair, and the number of records for which the symptom is R/the number of records for all symptoms in the K-th order relationship pair, where K is the number of conditional entity information in the higher order entity relationship pair, satisfying K conditions. It is worth mentioning that formula (1) can also be used to calculate the conditional probability of the first-order entity-relationship pair, i.e. the unary conditional probability calculated when K is 1.
In an exemplary embodiment of the present disclosure, a first-order entity relationship between different pieces of medical entity information may also be obtained according to the first medical entity list, the second medical entity list, and the third medical entity list, fig. 4 shows a flowchart for obtaining a first-order entity relationship pair, and as shown in fig. 4, in step S401, diagnostic entity information in the first medical entity list is mapped with non-diagnostic entity information in the second medical entity list and patient information entity information in the third medical entity list, respectively, to obtain a first-order entity relationship pair; in step S402, mapping the non-diagnostic entity information in the second medical entity list with the patient information entity information in the third medical entity list to obtain a second-order entity relationship pair; in step S403, mapping the target non-diagnostic entity information in the second medical entity list with other non-diagnostic entity information to obtain a third-order entity relationship pair; in step S404, a first-order entity-relationship pair is determined according to the first-order entity-relationship pair, the second-order entity-relationship pair, and the third-order entity-relationship pair. Wherein the first entity list may be a list of diagnostic entities, the second entity list may be a list of non-diagnostic entities, and the third entity list may be a list of patient information entities.
Further, when mapping the diagnostic entity information with the non-diagnostic entity information, mapping the diagnostic entity information with the patient information entity information, and mapping the non-diagnostic entity information with the patient information entity information, cartesian products may be made for the diagnostic entity list and the non-diagnostic entity list, cartesian products may be made for the diagnostic entity list and the patient information entity list, and cartesian products may be made for the non-diagnostic entity list and the patient information entity list, so as to obtain a first-order entity relationship pair between entity information in each entity list. After the diagnostic entity list and the non-diagnostic entity list are subjected to Cartesian product, the relationship between the diagnostic name and non-diagnostic entity information such as medication, examination, inspection, operation, and doctor's office can be obtained, such as medical entity relationship pairs such as < gastric malignant tumor-tegafur >, and < gastric malignant tumor-gastroscopy >; after the diagnosis entity list and the patient information entity list are subjected to Cartesian product, the relationship between the diagnosis name and entity information such as the age of the patient, the sex of the patient and the like can be obtained, for example, a medical entity relationship pair such as < gastric malignant tumor-61 years >, and < gastric malignant tumor-male > and the like; after cartesian product is performed on the non-diagnostic entity list and the patient information entity list, the relationship between the non-diagnostic entity information such as medication, examination, operation, and clinic and the entity information such as patient age and patient sex, for example, the medical entity relationship pair such as < tegioo-male > can be obtained. Meanwhile, the target non-diagnostic entity information in the second entity list may be mapped with other non-diagnostic entity information to form a medical entity relationship pair, and specifically, any one of non-diagnostic entities such as medication, examination, inspection, surgery, and doctor's office may be mapped with other non-diagnostic entity information, for example, mapping symptom "abdominal pain" with examination "gastroscopy" to form a < abdominal pain-gastroscopy > medical entity relationship pair.
In an exemplary embodiment of the present disclosure, after the first order entity relationship pair and the higher order entity relationship pair are acquired according to the relationship between the medical entity information, the medical knowledge graph may be formed according to the first order entity relationship pair and the higher order entity relationship pair. In embodiments of the present disclosure, a medical knowledge graph may be constructed in the form of a bayesian network for recording relationships between different medical concepts. Fig. 5 shows a flow chart for constructing a medical knowledge graph, as shown in fig. 5, in step S501, K-element conditional probabilities between respective pieces of medical entity information are calculated, where K is 1,2,3, … …; specifically, the conditional probability between the pieces of medical entity information can be obtained by calculation according to formula (1); in step S502, determining whether there is a directed edge between nodes in the bayesian network according to the conditional probability; when the conditional probability of certain two pieces of medical entity information is 0, the situation that no edge exists between nodes in the Bayesian network formed by the two pieces of medical entity information is shown; when the conditional probability of certain two pieces of medical entity information is not 0, indicating that an edge exists between nodes in the Bayesian network formed by the two pieces of medical entity information, and the direction of the edge points to the associated entity information from the conditional entity information; in step S503, a conditional probability table is set corresponding to each medical entity information; the conditional probability table is used to indicate the degree of influence of the change of the conditional entity information on the associated entity information.
In an exemplary embodiment of the present disclosure, since the medical knowledge graph includes a pair of high-order entity relationships, not only a pair of first-order entity relationships, when reasoning is performed according to the medical knowledge graph in the present disclosure, the high-order entity relationships can be converted into multiple conditional probabilities without making a condition-independent assumption between the conditions, for example, for a pair of second-order entity relationships < (pneumonia +3 months) -cough >, a corresponding binary conditional probability is P (cough with pneumonia |3 months), and when calculating the binary conditional probability, the condition-independent assumption between pneumonia and 3 months is not needed; similarly, for the third-order entity relationship pair < (3 months + milk cough + chest X-ray) -pneumonia >, the corresponding ternary conditional probability is P (pneumonia |3 months, milk cough, chest X-ray), and when the ternary conditional probability is calculated, it is not necessary to assume that the conditions of 3 months, milk cough and chest X-ray are independent.
The medical entity information processing method can obtain the high-order entity relationship pair, so that when reasoning is carried out according to the medical knowledge graph, the high-order entity relationship can be converted into the multi-element conditional probability, the multi-element conditions do not need to be assumed to be mutually independent, and the calculation error caused by the fact that the condition independent assumption does not meet the actual condition is avoided.
The present disclosure also provides a processing apparatus of medical entity information. Fig. 6 shows a schematic structural diagram of a processing apparatus of medical entity information, which may include a target medical data acquisition module 610, a higher-order entity relationship pair acquisition module 620, and an entity association relationship determination module 630, as shown in fig. 6. Wherein:
the target medical data acquisition module 610 is configured to acquire target medical information according to preset conditions, where the target medical information includes a first medical entity list, a second medical entity list, and a third medical entity list;
a higher-order entity relationship pair obtaining module 620, configured to determine multiple pieces of conditional entity information from the first medical entity list, the second medical entity list, and/or the third medical entity list, determine one piece of associated entity information from the first medical entity list or the second medical entity list, and obtain a higher-order entity relationship pair according to the multiple pieces of conditional entity information and the associated entity information; wherein the plurality of conditional entity information is different from the associated entity information;
and an entity association relationship determining module 630, configured to determine an association relationship between different pieces of medical entity information according to the higher-order entity relationship pair.
The specific details of each module in the processing apparatus for the medical entity care have been described in detail in the processing method of the corresponding medical entity information, and therefore are not described herein again.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 700 according to this embodiment of the disclosure is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 7, electronic device 700 is embodied in the form of a general purpose computing device. The components of the electronic device 700 may include, but are not limited to: the at least one processing unit 710, the at least one memory unit 720, and a bus 730 that couples various system components including the memory unit 720 and the processing unit 710.
Wherein the storage unit stores program code that is executable by the processing unit 710 to cause the processing unit 710 to perform steps according to various exemplary embodiments of the present disclosure as described in the above section "exemplary methods" of this specification. For example, the processing unit 710 may perform step S110 as shown in fig. 1: acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list; step S120: determining a plurality of pieces of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, determining one piece of associated entity information from the first medical entity list or the second medical entity list, and acquiring a higher-order entity relationship pair according to the plurality of pieces of conditional entity information and the associated entity information; wherein the plurality of conditional entity information is different from the associated entity information; step S130: and determining the incidence relation between different medical entity information according to the high-order entity relation pair.
The storage unit 720 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)7201 and/or a cache memory unit 7202, and may further include a read only memory unit (ROM) 7203.
The storage unit 720 may also include a program/utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 700 may also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 700, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 700 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 550. Also, the electronic device 700 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 760. As shown, the network adapter 760 communicates with the other modules of the electronic device 700 via the bus 730. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.
Referring to fig. 8, a program product 800 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a 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.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. A method for processing medical entity information, comprising:
acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list;
determining a plurality of pieces of conditional entity information from the first medical entity list, the second medical entity list and/or the third medical entity list, determining one piece of associated entity information from the first medical entity list or the second medical entity list, and acquiring a higher-order entity relationship pair according to the plurality of pieces of conditional entity information and the associated entity information; wherein the plurality of conditional entity information is different from the associated entity information;
and determining the incidence relation between different medical entity information according to the high-order entity relation pair.
2. The method for processing medical entity information according to claim 1, wherein target medical information is acquired according to preset conditions, the target medical information includes a first medical entity list, a second medical entity list and a third medical entity list, and the method includes:
acquiring medical information corresponding to the visit ID from an electronic medical record database according to the visit ID;
performing a preprocessing operation on the medical information to obtain the target medical information, wherein the target medical data includes the first medical entity list, the second medical entity list, and the third medical entity list.
3. The method for processing medical entity information according to claim 1, wherein determining the association relationship between different medical entity information according to the higher-order entity relationship pair comprises:
calculating conditional probability among the different medical entity information according to the high-order entity relation pair;
and determining the incidence relation between the different medical entity information according to the conditional probability.
4. The method for processing medical entity information according to claim 3, wherein calculating the conditional probability between the different medical entity information according to the higher-order entity relationship pair comprises:
acquiring a first number of entity relationship pairs in an electronic medical record database, wherein the entity relationship pairs are the same as the high-order entity relationship pairs;
acquiring a second number of entity relationship pairs in the electronic medical record database, wherein the entity relationship pairs have conditional entity information which is the same as the conditional entity information in the higher-order entity relationship pairs;
comparing the first number to the second number to obtain the conditional probability.
5. The method for processing medical entity information according to claim 1, further comprising:
mapping the diagnosis entity information in the first medical entity list with the non-diagnosis entity information in the second medical entity list and the patient information entity information in the third medical entity list respectively to obtain a first one-order entity relationship pair;
mapping non-diagnostic entity information in the second medical entity list with patient information entity information in the third medical entity list to obtain a second-order entity relationship pair;
mapping target non-diagnostic entity information in the second medical entity list with other non-diagnostic entity information to obtain a third-order entity relationship pair;
and determining a first-order entity relationship pair according to the first-order entity relationship pair, the second-order entity relationship pair and the third-order entity relationship pair.
6. The method for processing medical entity information according to any one of claims 1-5, wherein the first medical entity list is a diagnostic entity list, the second medical entity list is a non-diagnostic entity list, and the third medical entity list is a patient information entity list.
7. The method for processing medical entity information according to claim 6, further comprising:
and respectively carrying out Cartesian product on the diagnosis entity list and the non-diagnosis entity list, the diagnosis entity list and the patient information entity list, the non-diagnosis entity list and the patient information entity list, and forming an entity relationship pair according to target non-diagnosis entity information and other non-diagnosis entity information in the non-diagnosis entity list so as to obtain a first-order entity relationship pair.
8. An apparatus for processing information of a medical entity, comprising:
the target medical data acquisition module is used for acquiring target medical information according to preset conditions, wherein the target medical information comprises a first medical entity list, a second medical entity list and a third medical entity list;
a higher-order entity relationship pair obtaining module, configured to determine multiple pieces of conditional entity information from the first medical entity list, the second medical entity list, and/or the third medical entity list, determine one piece of associated entity information from the first medical entity list or the second medical entity list, and obtain a higher-order entity relationship pair according to the multiple pieces of conditional entity information and the associated entity; wherein the plurality of conditional entity information is different from the associated entity information;
and the entity incidence relation determining module is used for determining incidence relations among different medical entity information according to the high-order entity relation pairs.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of processing medical entity information of any one of claims 1 to 7.
10. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of processing medical entity information of any one of claims 1-7 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624476.7A CN111383773B (en) | 2018-12-28 | 2018-12-28 | Medical entity information processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624476.7A CN111383773B (en) | 2018-12-28 | 2018-12-28 | Medical entity information processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111383773A true CN111383773A (en) | 2020-07-07 |
| CN111383773B CN111383773B (en) | 2023-04-28 |
Family
ID=71218001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811624476.7A Active CN111383773B (en) | 2018-12-28 | 2018-12-28 | Medical entity information processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111383773B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199957A (en) * | 2020-11-03 | 2021-01-08 | 中国人民解放军战略支援部队信息工程大学 | Character entity alignment method and system based on attribute and relation information joint embedding |
| CN112732940A (en) * | 2021-01-15 | 2021-04-30 | 医渡云（北京）技术有限公司 | Model-based medical knowledge graph reasoning method, device, equipment and medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140272914A1 (en) * | 2013-03-15 | 2014-09-18 | William Marsh Rice University | Sparse Factor Analysis for Learning Analytics and Content Analytics |
| CN105528349A (en) * | 2014-09-29 | 2016-04-27 | 华为技术有限公司 | Method and apparatus for analyzing question based on knowledge base |
| US9471606B1 (en) * | 2012-06-25 | 2016-10-18 | Google Inc. | Obtaining information to provide to users |
| US20170161311A1 (en) * | 2015-12-03 | 2017-06-08 | International Business Machines Corporation | Using knowledge graphs to identify potential inconsistencies in works of authorship |
| CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
| CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
| JP2017174407A (en) * | 2016-03-24 | 2017-09-28 | 富士通株式会社 | System and method for supporting diagnosis of patient |
| CN107609163A (en) * | 2017-09-15 | 2018-01-19 | 南京深数信息科技有限公司 | Generation method, storage medium and the server of medical knowledge collection of illustrative plates |
| CN107644062A (en) * | 2017-08-29 | 2018-01-30 | 广州思涵信息科技有限公司 | The knowledge content Weight Analysis System and method of a kind of knowledge based collection of illustrative plates |
| CN108268580A (en) * | 2017-07-14 | 2018-07-10 | 广东神马搜索科技有限公司 | The answering method and device of knowledge based collection of illustrative plates |
| CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
| US20180315182A1 (en) * | 2017-04-28 | 2018-11-01 | Siemens Healthcare Gmbh | Rapid assessment and outcome analysis for medical patients |
| CN108920453A (en) * | 2018-06-08 | 2018-11-30 | 医渡云（北京）技术有限公司 | Data processing method, device, electronic equipment and computer-readable medium |
-
2018
- 2018-12-28 CN CN201811624476.7A patent/CN111383773B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9471606B1 (en) * | 2012-06-25 | 2016-10-18 | Google Inc. | Obtaining information to provide to users |
| US20140272914A1 (en) * | 2013-03-15 | 2014-09-18 | William Marsh Rice University | Sparse Factor Analysis for Learning Analytics and Content Analytics |
| CN105528349A (en) * | 2014-09-29 | 2016-04-27 | 华为技术有限公司 | Method and apparatus for analyzing question based on knowledge base |
| US20170161311A1 (en) * | 2015-12-03 | 2017-06-08 | International Business Machines Corporation | Using knowledge graphs to identify potential inconsistencies in works of authorship |
| JP2017174407A (en) * | 2016-03-24 | 2017-09-28 | 富士通株式会社 | System and method for supporting diagnosis of patient |
| CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
| US20180315182A1 (en) * | 2017-04-28 | 2018-11-01 | Siemens Healthcare Gmbh | Rapid assessment and outcome analysis for medical patients |
| CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
| CN108268580A (en) * | 2017-07-14 | 2018-07-10 | 广东神马搜索科技有限公司 | The answering method and device of knowledge based collection of illustrative plates |
| CN107644062A (en) * | 2017-08-29 | 2018-01-30 | 广州思涵信息科技有限公司 | The knowledge content Weight Analysis System and method of a kind of knowledge based collection of illustrative plates |
| CN107609163A (en) * | 2017-09-15 | 2018-01-19 | 南京深数信息科技有限公司 | Generation method, storage medium and the server of medical knowledge collection of illustrative plates |
| CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
| CN108920453A (en) * | 2018-06-08 | 2018-11-30 | 医渡云（北京）技术有限公司 | Data processing method, device, electronic equipment and computer-readable medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199957A (en) * | 2020-11-03 | 2021-01-08 | 中国人民解放军战略支援部队信息工程大学 | Character entity alignment method and system based on attribute and relation information joint embedding |
| CN112199957B (en) * | 2020-11-03 | 2023-12-08 | 中国人民解放军战略支援部队信息工程大学 | Character entity alignment method and system based on attribute and relationship information joint embedding |
| CN112732940A (en) * | 2021-01-15 | 2021-04-30 | 医渡云（北京）技术有限公司 | Model-based medical knowledge graph reasoning method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111383773B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bradshaw et al. | Nuclear medicine and artificial intelligence: best practices for algorithm development | |
| Stone et al. | A systematic review of the prediction of hospital length of stay: Towards a unified framework | |
| CN107799160B (en) | Medication aid decision-making method and device, storage medium and electronic equipment | |
| CN109670054B (en) | Knowledge graph construction method and device, storage medium and electronic equipment | |
| JP5952835B2 (en) | Imaging protocol updates and / or recommenders | |
| Tas et al. | Serial measurements in COVID-19-induced acute respiratory disease to unravel heterogeneity of the disease course: design of the Maastricht Intensive Care COVID cohort (MaastrICCht) | |
| Li et al. | Automated assessment of COVID-19 pulmonary disease severity on chest radiographs using convolutional Siamese neural networks | |
| CN111382275A (en) | Construction method, device and medium of medical knowledge graph and electronic equipment | |
| CN111564223B (en) | Infectious disease survival probability prediction method, and prediction model training method and device | |
| CN111145909B (en) | Diagnosis and treatment data processing method and device, storage medium and electronic equipment | |
| CN107895013B (en) | Data quality rule control method and device, storage medium and electronic equipment | |
| US20150106125A1 (en) | Automated Mapping of Service Codes in Healthcare Systems | |
| CN112541066B (en) | Text-structured-based medical and technical report detection method and related equipment | |
| Persson et al. | A machine learning sepsis prediction algorithm for intended intensive care unit use (NAVOY Sepsis): proof-of-concept study | |
| CN115497616A (en) | Method, system, equipment and storage medium for aid decision making of infectious diseases | |
| Khader et al. | Artificial intelligence for clinical interpretation of bedside chest radiographs | |
| CN111383773A (en) | Medical entity information processing method and device, storage medium and electronic equipment | |
| Baum et al. | Image quality assessment for closed-loop computer-assisted lung ultrasound | |
| Donnat et al. | A Bayesian hierarchical network for combining heterogeneous data sources in medical diagnoses | |
| CN112133389A (en) | Clinical assistant decision-making high-risk automatic early warning method, system, equipment and medium | |
| Dinh et al. | New technologies to improve healthcare in low-and middle-income countries: global grand challenges satellite event, Oxford University clinical research unit, Ho Chi Minh City, 17th-18th September 2019 | |
| Edye et al. | Applying Bayesian networks to help physicians diagnose respiratory diseases in the context of COVID-19 pandemic | |
| Cossio et al. | Would the Use of Artificial Intelligence in COVID-19 Patient Management Add Value to the Healthcare System? | |
| US11537818B2 (en) | Apparatus, computer program product, and method for predictive data labelling using a dual-prediction model system | |
| Stone et al. | A systematic review of the prediction of hospital length of stay: Towards a unified framework. PLOS Digit Health 1 (4): e0000017 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |