CN114242258A

CN114242258A - Medical data exploration method and device based on medical knowledge map

Info

Publication number: CN114242258A
Application number: CN202111623593.3A
Authority: CN
Inventors: 秦晓宏; 华宗楠
Original assignee: Shanghai Clinbrain Information Technology Co Ltd
Current assignee: Shanghai Clinbrain Information Technology Co Ltd
Priority date: 2021-12-28
Filing date: 2021-12-28
Publication date: 2022-03-25

Abstract

The embodiment of the invention discloses a medical data exploration method and device based on a medical knowledge graph. The method comprises the following steps: when receiving a retrieval instruction for retrieving medical data stored in a medical database, determining a corresponding retrieval condition based on the retrieval instruction; determining associated retrieval data meeting retrieval conditions from medical data stored in a medical database based on a pre-established medical knowledge map; and displaying the associated retrieval data according to a preset display mode. According to the technical scheme of the embodiment of the invention, a doctor can directly check the association relation among the medical data, and the doctor can conveniently analyze and explore the searched medical data.

Description

Medical data exploration method and device based on medical knowledge map

Technical Field

The embodiment of the invention relates to the technical field of data processing, in particular to a medical data exploration method and device based on a medical knowledge graph.

Background

Doctors use the medical data retrieval database to carry out the exploration of the combing, the analysis and the like of clinical data, which is an important link in the medical scientific research task.

In the prior art, clinical data are acquired by manually searching and reviewing electronic cases in a medical retrieval database, so that doctors can conveniently analyze the data. Because a large amount of data is needed in scientific research, a large amount of human resources are consumed by adopting the method, the time is consumed, and the error rate is high; moreover, because these stacked data cannot reflect the diagnosis and treatment logic of the doctor at that time, the doctor needs to thoroughly read all cases and arrange the logic by himself to connect the research clues in the cases in series, which is not convenient for the doctor to analyze and search the searched medical data.

Disclosure of Invention

The embodiment of the invention provides a medical data exploration method and device based on a medical knowledge graph, which are used for enabling doctors to directly check the association relation among medical data and facilitating the doctors to analyze and explore the searched medical data.

In a first aspect, an embodiment of the present invention provides a medical data exploration method based on a medical knowledge graph, including:

when receiving a retrieval instruction for retrieving medical data stored in a medical database, determining a corresponding retrieval condition based on the retrieval instruction;

determining associated retrieval data meeting the retrieval conditions from medical data stored in the medical database based on a pre-established medical knowledge map;

and displaying the associated retrieval data according to a preset display mode.

In a second aspect, an embodiment of the present invention further provides a medical data exploration apparatus based on a medical knowledge-graph, the apparatus including:

the retrieval condition determining module is used for determining corresponding retrieval conditions based on a retrieval instruction when the retrieval instruction for retrieving the medical data stored in the medical database is received;

the association retrieval determining module is used for determining association retrieval data meeting the retrieval conditions in the medical data stored in the medical database based on a pre-established medical knowledge map;

and the display module is used for displaying the associated retrieval data according to a preset display mode.

According to the medical data exploration method based on the medical knowledge graph, when a retrieval instruction for retrieving medical data stored in a medical database is received, a corresponding retrieval condition is determined based on the retrieval instruction; through the pre-established medical knowledge map, the associated retrieval data meeting the retrieval conditions are determined from the medical data stored in the medical database, and the associated retrieval data are displayed according to the preset display mode, so that a doctor can directly view the association relation among the medical data, and the doctor can conveniently analyze and explore the searched medical data.

In addition, the medical data searching device based on the medical knowledge graph provided by the invention corresponds to the method and has the same beneficial effects.

Drawings

In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.

FIG. 1 is a flow chart of a medical knowledge-graph-based medical data exploration method according to an embodiment of the present invention;

FIG. 2 is a flow chart of another medical data exploration method based on a medical knowledge-graph according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating a search timeline according to an embodiment of the present invention;

FIG. 4 is a diagram of a target associated knowledge element according to an embodiment of the present invention;

FIG. 5 is a table of comparative data provided by an embodiment of the present invention;

FIG. 6 is a block diagram of a medical knowledge-graph based medical data exploration apparatus according to an embodiment of the present invention;

fig. 7 is a structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.

In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments.

Example one

Fig. 1 is a flowchart of a medical data exploration method based on a medical knowledge graph according to an embodiment of the present invention. The method may be performed by a medical knowledge graph-based medical data exploration device, which may be implemented by software and/or hardware, and may be configured in a terminal and/or a server to implement the medical knowledge graph-based medical data exploration method in the embodiment of the present invention.

As shown in fig. 1, the method of the embodiment may specifically include:

s101, when a retrieval instruction for retrieving the medical data stored in the medical database is received, corresponding retrieval conditions are determined based on the retrieval instruction.

In a specific implementation, a medical staff or a medical researcher can access the medical data platform through the user terminal and send a retrieval instruction for retrieving the medical data stored in the medical database to the medical data platform. Illustratively, the medical data stored in the medical database includes outpatient and emergency records, examination reports, electronic medical records, medical information, discharge records, follow-up reports, and the like of each patient.

Specifically, after the retrieval instruction is received, the retrieval instruction includes retrieval condition information, and the retrieval condition to be satisfied by the retrieval result can be determined based on the retrieval instruction. Illustratively, the keyword information in the retrieval instruction may be extracted to constitute the retrieval condition. For example, if the search instruction is "nasopharyngeal carcinoma-related, male", it is determined that the search condition to be satisfied by the search result is all medical data of the male with the laryngeal carcinoma in the medical database. Further, the medical data in the medical database may be retrieved by associating any one or a combination of at least one of a disease, a disease name, a sex, an age, an occupation, a disease history, a marriage and childbirth situation, a smoking situation, a drinking situation, and a symptom as a retrieval condition.

S102, determining associated retrieval data meeting retrieval conditions in the medical data stored in the medical database based on the pre-established medical knowledge graph.

Optionally, before determining associated retrieval data meeting the retrieval condition from the medical data stored in the medical database, the method further includes: acquiring medical data of each object stored in a medical database, preprocessing the medical data and generating an object characteristic data set; and performing knowledge extraction on the object characteristic data set based on an association rule mining algorithm to generate a medical knowledge map.

In particular implementations, the medical knowledge map may be pre-established based on medical data of each subject stored in a clinical medical database. Wherein the medical data comprises at least one of outpatient emergency records, examination reports, medical information, discharge records, and follow-up reports. The medical knowledge graph can be established by preprocessing the medical data to generate an object feature data set, extracting the knowledge of facts and reasoning from the feature data of each object in the object feature data set based on an association rule mining algorithm, representing the feature data in a triple form, and storing the feature data into the knowledge graph.

Optionally, the search condition includes at least one specified disease name; the method for determining the associated retrieval data meeting the retrieval conditions in the medical data stored in the medical database based on the pre-established medical knowledge graph comprises the following steps: determining an associated knowledge element corresponding to the specified disease name based on the association relationship among the knowledge elements displayed in the medical knowledge map; and determining the associated medical data corresponding to the associated knowledge element from the medical data, and determining the associated medical data as associated retrieval data meeting retrieval conditions.

Specifically, the medical knowledge graph comprises knowledge elements corresponding to different medical entity types, and the association relationship between the knowledge elements can be determined through the medical knowledge graph. When the retrieval condition is that retrieval is carried out according to the specified disease name, the specified disease name can be used as a target knowledge element, and each associated knowledge element related to the target knowledge element is determined in the medical knowledge map.

Illustratively, the associated knowledge elements include examination tests corresponding to a specified disease name, disease symptoms, risk factors, causes of illness, associated diseases, treatment plans, follow-up situations, and the like. The associated medical data corresponding to each associated knowledge element can be determined from the medical data, and the associated medical data can be determined as associated retrieval data satisfying the retrieval condition.

And S103, displaying the associated retrieval data according to a preset display mode.

Specifically, the display mode can be voice playing display and/or interface display; the interface display further comprises at least one of a text display form, a picture display form and a table display form. In specific implementation, the retrieval conditions and the corresponding associated retrieval data can be displayed in the same display interface at the same time, so that comparison and check of doctors are facilitated, and medical relations between the retrieval conditions and the associated retrieval data are analyzed.

Furthermore, the associated retrieval data can be displayed in a classified manner, and for example, the associated retrieval data can be displayed according to different entity types of knowledge elements corresponding to the associated retrieval data, so that the type of the associated retrieval data can be clearly known.

Illustratively, the entity types corresponding to the knowledge elements include diseases, symptoms, signs, tests, surgery, drugs, chemotherapy, previous diseases, smoking and drinking, and symptom sites, etc. The relevant retrieval data corresponding to the disease, symptom, physical sign, inspection, operation, medicine, chemotherapy, previous disease, smoking and drinking and symptom part can be respectively determined and displayed in a classified way.

Furthermore, the associated retrieval data corresponding to each retrieval object can be respectively displayed according to the corresponding relation between the associated retrieval data and the retrieval object generating the associated retrieval data, so that doctors can better combine the individual conditions of the retrieval objects and better perform medical analysis.

Exemplarily, when left acute mumps is taken as a search condition, the correlation search data is obtained as "symptom: swelling and pain in the ear and face, local swelling, pain, and tenderness in soft tissues. Medicine preparation: azithromycin, diagnostic of disease: left acute pyogenic parotitis, left acute otitis externa. Physical signs: poor spirit, poor sleep, poor diet "; when the related search data is displayed, a patient with the symptoms, the diagnosed diseases and the physical signs can be used as a search target; and classifying according to each retrieval object, and respectively displaying corresponding associated retrieval data.

Example two

Fig. 2 is a flowchart of another medical data exploration method based on a medical knowledge-graph according to an embodiment of the present invention. The present embodiment is optimized based on the above technical solutions. Optionally, displaying the associated retrieval data according to a preset display manner, including: and carrying out classified display on the associated retrieval data according to a preset medical stage. Optionally, the method further includes: when a specified comparison instruction is received, determining at least two comparison contents needing to be compared based on the specified comparison instruction; the comparison content comprises a specified target object needing to be compared, search conditions and each associated search data corresponding to each search condition; and determining the comparison content in a pre-stored historical database, and displaying the comparison content to the same display interface. Optionally, the method further includes: when a new data request is received, new object information and new data corresponding to the new data request are obtained; and adding the newly added object information and the newly added data to the medical database. The same or corresponding terms as those in the above embodiments are not explained in detail herein.

S201, when a retrieval instruction for retrieving the medical data stored in the medical database is received, corresponding retrieval conditions are determined based on the retrieval instruction.

S202, based on a pre-established medical knowledge map, relevant retrieval data meeting retrieval conditions are determined from medical data stored in a medical database.

Alternatively, when the search condition is two or more specified disease names, it can be understood that it is currently necessary to determine the associated search data that satisfies the two or more specified disease names at the same time. Specifically, each associated knowledge element corresponding to each specified disease name can be determined based on the association relationship between each knowledge element displayed in the medical knowledge map; and determining each associated medical data corresponding to each associated knowledge element in the medical data, determining common medical data in each associated medical data corresponding to each specified disease name, determining the common medical data as associated retrieval data meeting retrieval conditions, and displaying the common medical data.

Illustratively, when the search condition is "nasopharyngeal carcinoma" and "lung cancer", obtain one or more first electronic medical records that "nasopharyngeal carcinoma" is correlated to, and one or more second electronic medical records that "lung cancer" is correlated to; determining first associated medical data of the first electronic medical record and second associated medical data of the second electronic medical record respectively based on the medical knowledge graph; displaying the first associated medical data on a retrieval time axis according to a first preset mode, and displaying the second associated medical data on the retrieval time axis according to a second preset mode; the time axis may represent the temporal relationship between the data. And meanwhile, common medical data which are consistent between the first associated medical data and the second associated medical data are determined, and the common data are marked according to a third preset mode. For example, the first predetermined manner may be a manner of labeling by a square symbol, the second predetermined manner may be a manner of labeling by a circular symbol, and the third predetermined manner may be a manner of highlighting.

And S203, performing classified display on the associated retrieval data according to preset medical stages.

Optionally, the medical phase comprises at least one of an outpatient phase, an inpatient phase, and a follow-up phase. It should be noted that, in general, the daily diagnosis and treatment thinking of a doctor during clinical work is to firstly know the medical history and the state of an illness of a diagnosis object, and then to make the diagnosis object perform medical examination based on the medical history and the state of the illness; making a diagnosis based on the examination results, and determining whether to proceed with further treatment or to continue further examination. In the daily diagnosis and treatment process, doctors need to obtain medical data in different stages according to medical stages, so that the medical data displayed according to the medical stages more accords with the daily diagnosis and treatment thinking of the doctors, the associated retrieval data can be conveniently checked and analyzed by the doctors, the experience of the doctors in the retrieval process is improved, and the medical stages are time points generated by the associated retrieval data.

For example, a medical stage and a retrieval object generated by the associated retrieval data can be determined, and for different retrieval objects, the associated retrieval data corresponding to the medical stage is displayed according to the time sequence of each medical stage, so that a doctor can conveniently view and analyze the associated retrieval data.

Furthermore, texts composed of the associated retrieval data corresponding to each medical stage can be directly displayed on a display interface; and each medical stage can be displayed according to a time axis mode, and the doctor can trigger the associated retrieval data of the medical stage to be viewed for displaying by selecting the medical stage to be viewed.

Optionally, the classified display of the associated retrieval data according to the preset medical stage includes: respectively establishing retrieval time axes for each retrieval object contained in the associated retrieval data; and respectively displaying the associated retrieval data corresponding to each retrieval object in each medical stage to a corresponding retrieval time axis. Specifically, the corresponding retrieval object can be determined according to the associated retrieval data, and a retrieval time axis is respectively established for each retrieval object, so as to display the associated retrieval data of each retrieval object in each medical stage.

Optionally, the displaying, to a corresponding retrieval time axis, associated retrieval data corresponding to each retrieval object at each medical stage respectively includes: determining medical events of various retrieval objects appearing at different medical stages, and displaying the medical events to a retrieval time axis according to the time sequence of the appearance time; determining related medical events of related retrieval data in the medical events of the retrieval objects; marking the associated medical events in the medical events on a retrieval time axis according to a preset marking mode; when the trigger display instruction is received, the associated retrieval data corresponding to the associated medical event indicated in the trigger display instruction is displayed.

FIG. 3 is a diagram illustrating a search timeline according to an embodiment of the present invention; as shown in fig. 3, each medical event that occurs in different medical stages of the visit process of each search object can be respectively determined, the medical stages include outpatient service, emergency treatment and hospitalization, the medical events are events corresponding to each stage, such as "outpatient case", "admission record", "first disease course record", "preoperative discussion record", "ward visit record", "discharge record", and "follow-up record", and the like, each medical event of the search object can be shown on the search time axis, whether each medical event is an event for generating associated search data is determined, if yes, the medical event is determined to be an associated medical event, and the associated medical event can be labeled according to a preset labeling mode.

For example, the preset labeling manner may include at least one of labeling according to a set color, labeling according to a set shape, labeling according to a set symbol, selecting a circular or square frame, and labeling by a highlight identifier. Furthermore, the doctor can click the corresponding position of the key medical event on the display interface through the user terminal or input the key medical event to be checked through the input box, and a triggering display instruction is generated based on the click operation or the input operation of the user terminal. After the trigger display instruction is received, the associated retrieval data corresponding to the associated medical event indicated in the trigger display instruction can be displayed, so that the interface can be kept clean and tidy, information to be searched can be provided for a doctor, and the user experience is improved.

Furthermore, each medical event occurring in different medical stages can be distinguished and labeled on the retrieval time axis for distinguishing display; non-key medical events can be hidden, and only the key medical events are displayed on the retrieval time axis, so that interference is eliminated, and a doctor can visually and clearly find information corresponding to retrieval conditions. The occurrence time of each medical event can be marked on the retrieval time axis, and the personal authorization information of the retrieval object is displayed in the display interface, wherein the personal authorization information can comprise the contents of name, age, discharge diagnosis, discharge time and the like.

S204, when a specified comparison instruction is received, determining at least two comparison contents needing to be compared based on the specified comparison instruction; and determining comparison contents in a pre-stored historical database, and displaying the comparison contents in the same display interface.

Optionally, the comparison content includes a specified target object to be compared, a search condition, and each associated search data corresponding to each search condition. At least one item of content in the target object to be compared, the retrieval condition and the associated retrieval data corresponding to the retrieval condition can be displayed simultaneously in the same display interface. The doctor can visually and clearly check the internal relation among the retrieval conditions, the target object and the associated retrieval data, and the associated retrieval data generated by different retrieval conditions can be clear at a glance, so that the doctor can conveniently perform medical exploration and analysis on the comparison result.

Optionally, displaying the comparison content in the same display interface includes: and distinguishing and labeling at least two pieces of comparison content according to different labeling modes, and displaying the labeled comparison content on the same display interface.

Specifically, the different labeling modes include at least one of different serial number labeling, different shape labeling, different color labeling and different character labeling. When the same display interface displays the associated retrieval data obtained by two or more retrieval conditions, in order to facilitate the differentiation and comparison of doctors, different labeling modes can be adopted to label the comparison contents. As shown in fig. 3, for the first relevant search data obtained under the search condition of "nasopharyngeal carcinoma", a triangular mark may be used; for the second associated retrieval data obtained under the retrieval condition of lung cancer, diamond identification can be adopted; for the third associated search data obtained under the search condition of "liver cancer", a square mark may be used. If the medical events at the respective time points on the time axis include data related to the search condition, the medical events can be marked below with a flag corresponding to the search condition, so that the doctor can know the time node, the corresponding stage, the search condition, and the like where the related data occurs.

As shown in fig. 3, the doctor can freely select "nasopharyngeal carcinoma", "lung cancer" and "liver cancer", select at least one of them as the search condition to be displayed, and assign different shape identifiers to each search related data. In this embodiment, it is shown in fig. 3 that the doctor respectively selects "nasopharyngeal carcinoma", "lung cancer" and "liver cancer", data related to "nasopharyngeal carcinoma", "lung cancer" or "liver cancer" below the time axis are marked according to the correspondingly set identifiers, and when square, diamond and triangle identifiers are displayed below the medical event at the same time, it indicates that the medical event is related to "nasopharyngeal carcinoma", "lung cancer" or "liver cancer".

In specific implementation, in order to facilitate comparison and analysis by doctors, when the comparison content is a target object, the target medical data of each target object can be determined in the medical database; the target medical data may include disease data, symptom data, physical sign data, examination data, surgery data, medicine data, chemotherapy data, past disease data, smoking and drinking data, symptom site data, and the like of the target subject.

Further, in order to facilitate a doctor to find the association relationship among the target medical data, the target association knowledge elements among the target medical data can be determined based on a medical knowledge graph established in advance, the target association data corresponding to the target association knowledge elements in the target medical data of each target object can be respectively determined, and the target association data can be displayed on a display interface. Fig. 4 is a schematic diagram of a target associated knowledge element according to an embodiment of the present invention, and as shown in fig. 4, the target associated knowledge element may include knowledge elements such as symptoms, past diseases, locations, diagnoses, etiologies, heart rates, sexes, ages, and medications. The display of the target association data through the display interface, for example, the data displayed in the dashed line box in fig. 4, can better assist the doctor to check the basis of the internal association relationship in the data exploration trying process, and the exploration completion degree is higher.

The display interface can be provided with function options such as 'export', 'export to subject' and 'share', and when the user terminal selects the 'export', 'export to subject' or 'share' key, an export instruction for saving the related retrieval data can be generated. The export instruction includes an export format and an export address, and the associated retrieved data may be stored at the export address specified in the export instruction.

The scheme supported by the embodiment comprises that before the data exploration performed by the doctor is finally completed, the data exploration performed by the doctor is different and temporally changed between the setting of the initial search condition and the preliminary actual exploration target and the final actual exploration target.

Then, there are application scenarios: the setting of exploring initial retrieval condition does not accord with preliminary actual exploration target very much, or, along with the doctor is receiving preliminary data exploration result's show feedback and suggestion under, the preliminary actual exploration target can constantly be revised to the doctor, and a plurality of attempts correspond and form a plurality of intermediate data exploration result states, except changing the target, the exploration process is incomplete one-way going on in addition, still has the back-off and repeated exploration demand, therefore, further contains in order to satisfy above-mentioned application situation this case:

the timeline displays the associated data related to the search condition of the intermediate attempt, further comparison and analysis are needed for one or more intermediate attempt search conditions, an intermediate data exploration result state formed by each intermediate attempt search condition is generated, and the timeline display interface can further comprise: the intermediate retrieval condition temporary storage key and the intermediate retrieval condition checkbox area. The temporary storage key is used for storing the intermediate retrieval conditions and selecting the intermediate retrieval conditions in the check box area according to a preset naming mode, one or more doctors check the check boxes, and then the comparison data table of the checked intermediate data exploration result states is further displayed in the check box area.

Fig. 5 is a schematic diagram of a comparison data table provided in an embodiment of the present invention, which is used to assist a user in forming a final actual exploration object, and form a comparison data table for comparing a plurality of association relations from at least one preset aspect, corresponding to a plurality of intermediate data exploration result states, to obtain a corresponding comparison analysis result, as shown in fig. 5, a correlation relation 1 between "nasopharyngeal carcinoma" and "lung cancer", a correlation relation 2 between "nasopharyngeal carcinoma" and "liver cancer", and a correlation relation 3 between "liver cancer" and "lung cancer" are compared from a hexagonal aspect, which is "number of cases", "lymphocyte metastasis", "number of lymphocyte metastasis", "absence of invasion of surgical incision", "cisplatin", and "white blood cell count", respectively. Moreover, the display interface is provided with a result using option, and the doctor can be helped to select the corresponding association relation by clicking the option. By displaying a plurality of comparison relations, the states of the intermediate data exploration results can be displayed in a comparison mode, and a doctor is assisted to form the final actual exploration purpose.

And the intermediate data exploration result state or the incidence relation for comparison can be set by a user selection. That is, the user may select one or more of the plurality of intermediate data search result states formed by the plurality of intermediate attempts to search the condition, and compare the one or more of the association relations to form the comparison data table. One or more of the aligned associations may be derived for utilization by a user selection.

Furthermore, the export instruction may further include export content information, and the export content information determines the target export content displayed in the display interface and performs export operation on the target export content. For example, the target export content may be data content such as personal information, diagnosis results, treatment schemes, and follow-up records of the retrieval target.

Illustratively, the display interface can also display keys such as 'download', 'collect', 'view the information of previous visits', 'case association', 'generate a data map' and the like, so that the displayed medical data can be conveniently subjected to functions corresponding to the keys by simply clicking or selecting operation, and convenience and experience of doctors are improved.

Specifically, upon receiving an export instruction, an export format included in the export instruction may be determined. Illustratively, the export format may include at least one of a text format, a tabular format, and a graphical format. And modifying the data format of the currently stored associated retrieval data according to the export format, and storing the associated retrieval data with the modified format into the export address.

Further, after the export operation is finished, whether the export address contains the associated retrieval data in the export format or not can be detected, if yes, the export is determined to be successful, and prompt information of 'export success' can be displayed in a display interface; if not, repeating the export operation again, detecting whether the export address contains the associated retrieval data in the export format again, and if not, generating prompt information of 'export failure' and displaying the prompt information on a display interface.

Further, whether an uploading instruction for uploading medical data is received or not can be determined; if so, acquiring the medical data transmitted in the uploading instruction, determining whether the medical data is the medical data of the stock object already stored in the medical database, and if so, storing the medical data and other data of the stock object to the same storage position.

S205, when a new data request is received, new object information and new data corresponding to the new data request are obtained; and adding the newly added object information and the newly added data to the medical database.

In specific implementation, in order to ensure the integrity and timeliness of the associated retrieval data retrieved by the doctor, when a new data request is received, new object information and new data corresponding to the new data request can be added to the medical database for participating in the data retrieval process.

Further, when a request for deleting data and/or a request for modifying data is received, corresponding target deleting data and/or target modifying data can be determined based on the request for deleting data and/or the request for modifying data, and corresponding deleting and modifying operations can be performed on the target deleting data and/or the target modifying data, so that the accuracy of each data stored in the current medical database is ensured.

The medical data exploration method based on the medical knowledge graph provided by the embodiment of the invention can realize comparison of more than two target objects, so that the target medical data corresponding to each target object can be visually and clearly displayed, and a doctor can conveniently compare and check the target medical data; cases such as export, sharing and downloading can be added on the interface, so that doctors can conveniently record and check the displayed medical data. When data is added, deleted and modified, the operations of adding, deleting and modifying can be carried out on the medical database in time, and the accuracy and integrity of each data stored in the current medical database are ensured.

EXAMPLE III

FIG. 6 is a block diagram of a medical knowledge-graph based medical data exploration apparatus according to an embodiment of the present invention, which is used for executing the medical knowledge-graph based medical data exploration method according to any of the above embodiments. The device and the medical data searching method based on the medical knowledge map of the embodiments belong to the same inventive concept, and details which are not described in detail in the embodiments of the medical data searching device based on the medical knowledge map can refer to the embodiments of the medical data searching method based on the medical knowledge map. The device may specifically comprise:

a search condition determining module 10, configured to, when a search instruction for searching medical data stored in the medical database is received, determine a corresponding search condition based on the search instruction;

a determining association retrieval data module 11, configured to determine, based on a pre-established medical knowledge graph, association retrieval data that meets a retrieval condition from medical data stored in a medical database;

and the display module 12 is configured to display the associated search data according to a preset display mode.

On the basis of any optional technical scheme in the embodiment of the present invention, optionally, the method further includes:

the medical data acquisition module is used for acquiring medical data of each object stored in the medical database before determining associated retrieval data meeting retrieval conditions in the medical data stored in the medical database, preprocessing the medical data and generating an object characteristic data set; wherein the medical data comprises at least one of an examination report, medical information, a discharge record, and a follow-up report; and performing knowledge extraction on the object characteristic data set based on an association rule mining algorithm to generate a medical knowledge map.

On the basis of any optional technical scheme in the embodiment of the invention, optionally, the retrieval condition comprises at least one specified disease name; the association search data determining module 11 includes:

the associated medical data determining unit is used for determining associated knowledge elements corresponding to the specified disease names based on the association relation among the knowledge elements displayed in the medical knowledge map; and determining the associated medical data corresponding to the associated knowledge element from the medical data, and determining the associated medical data as associated retrieval data meeting retrieval conditions.

On the basis of any optional technical solution in the embodiment of the present invention, optionally, the display module 12 includes:

the classified display unit is used for performing classified display on the associated retrieval data according to a preset medical stage; wherein the medical treatment stage comprises at least one of an outpatient stage, an inpatient stage, and a follow-up stage.

On the basis of any optional technical solution in the embodiment of the present invention, optionally, the classification display unit includes:

a search time axis establishing unit for establishing a search time axis for each search object included in the associated search data; and respectively displaying the associated retrieval data corresponding to each retrieval object in each medical stage to a corresponding retrieval time axis.

On the basis of any optional technical solution in the embodiment of the present invention, optionally, the establishing of the search time axis unit includes:

the medical event determining unit is used for determining medical events of the retrieval objects in different medical stages and displaying the medical events on a retrieval time axis according to the time sequence of the occurrence time; determining related medical events of related retrieval data in the medical events of the retrieval objects; marking the related medical events in the medical events on the retrieval time axis according to a preset marking mode; when the trigger display instruction is received, the associated retrieval data corresponding to the associated medical event indicated in the trigger display instruction is displayed.

On the basis of any optional technical solution in the embodiment of the present invention, optionally, the apparatus further includes:

the target medical data determining module is used for determining each target object needing to be compared based on the specified comparison instruction when the specified comparison instruction is received; wherein the number of target objects is at least two; determining target medical data corresponding to each target object in a medical database; and determining target associated data among the target medical data based on the medical knowledge graph, and displaying the target associated data.

the system comprises a determination export instruction module, a storage module and a display module, wherein the determination export instruction module is used for determining whether an export instruction used for storing the associated retrieval data is received or not after the associated retrieval data is displayed according to a preset display mode; wherein the export instruction comprises an export format and an export address; and if so, carrying out format modification on the associated retrieval data according to the export format, and storing the associated retrieval data after format modification into the export address.

the data adding module is used for acquiring newly added object information and newly added data corresponding to the newly added data request when the newly added data request is received; and adding the newly added object information and the newly added data to the medical database.

The medical data exploration device based on the medical knowledge graph provided by the embodiment of the invention can execute the following method: when receiving a retrieval instruction for retrieving medical data stored in a medical database, determining a corresponding retrieval condition based on the retrieval instruction; determining associated retrieval data meeting retrieval conditions from medical data stored in a medical database based on a pre-established medical knowledge map; and displaying the associated retrieval data according to a preset display mode, so that a doctor can directly check the association relation among the medical data, and the doctor can conveniently analyze and explore the searched medical data.

It should be noted that, in the embodiment of the medical data exploration apparatus based on the medical knowledge graph, the included units and modules are only divided according to the functional logic, but not limited to the above division, as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

Example four

Fig. 7 is a structural diagram of an electronic device according to an embodiment of the present invention. FIG. 7 illustrates a block diagram of an exemplary electronic device 20 suitable for use in implementing embodiments of the present invention. The illustrated electronic device 20 is merely an example and should not be used to limit the functionality or scope of embodiments of the present invention.

As shown in fig. 7, the electronic device 20 is embodied in the form of a general purpose computing device. The components of the electronic device 20 may include, but are not limited to: one or more processors or processing units 201, a system memory 202, and a bus 203 that couples the various system components (including the system memory 202 and the processing unit 201).

Bus 203 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 20 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 20 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 202 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)204 and/or cache memory 205. The electronic device 20 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, the storage system 206 may be used to read from and write to non-removable, nonvolatile magnetic media. A magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 203 by one or more data media interfaces. Memory 202 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 208 having a set (at least one) of program modules 207 may be stored, for example, in memory 202, such program modules 207 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 207 generally perform the functions and/or methodologies of embodiments of the present invention as described herein.

The electronic device 20 may also communicate with one or more external devices 209 (e.g., keyboard, pointing device, display 210, etc.), with one or more devices that enable a user to interact with the electronic device 20, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 20 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 211. Also, the electronic device 20 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 212. As shown, the network adapter 212 communicates with other modules of the electronic device 20 over the bus 203. It should be understood that other hardware and/or software modules may be used in conjunction with electronic device 20, 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.

The processing unit 201 executes various functional applications and data processing by running a program stored in the system memory 202.

The electronic equipment provided by the invention can realize the following method: when receiving a retrieval instruction for retrieving medical data stored in a medical database, determining a corresponding retrieval condition based on the retrieval instruction; determining associated retrieval data meeting retrieval conditions from medical data stored in a medical database based on a pre-established medical knowledge map; and displaying the associated retrieval data according to a preset display mode, so that a doctor can directly check the association relation among the medical data, and the doctor can conveniently analyze and explore the searched medical data.

EXAMPLE five

An embodiment of the present invention provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a medical knowledge-graph-based medical data exploration method, the method comprising:

when receiving a retrieval instruction for retrieving medical data stored in a medical database, determining a corresponding retrieval condition based on the retrieval instruction; determining associated retrieval data meeting retrieval conditions from medical data stored in a medical database based on a pre-established medical knowledge map; and displaying the associated retrieval data according to a preset display mode, so that a doctor can directly check the association relation among the medical data, and the doctor can conveniently analyze and explore the searched medical data.

Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the medical knowledge-map-based medical data exploration method provided by any embodiment of the present invention.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer 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 computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, 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. In the context of this document, a computer 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.

A computer readable signal medium may include a propagated data signal with computer 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 computer readable signal medium may also be any computer readable medium that is not a computer 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 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 for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, 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 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. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A medical data exploration method based on a medical knowledge map is characterized by comprising the following steps:

2. The method according to claim 1, before determining associated retrieval data satisfying the retrieval condition among the medical data stored in the medical database, further comprising:

acquiring medical data of each object stored in the medical database, preprocessing the medical data and generating an object characteristic data set; wherein the medical data comprises at least one of outpatient emergency records, examination reports, medical information, discharge records, and follow-up reports;

and extracting knowledge from the object feature data set based on an association rule mining algorithm to generate the medical knowledge map.

3. The method of claim 1, wherein the search criteria include at least one specified disease name; wherein the determining, based on the pre-established medical knowledge graph, associated retrieval data satisfying the retrieval condition from the medical data stored in the medical database comprises:

determining an associated knowledge element corresponding to the specified disease name based on the association relationship among the knowledge elements displayed in the medical knowledge map;

and determining the associated medical data corresponding to the associated knowledge element from the medical data, and determining the associated medical data as the associated retrieval data meeting the retrieval condition.

4. The method according to claim 1, wherein the displaying the associated search data according to a preset display mode comprises:

performing classified display on the associated retrieval data according to a preset medical stage; wherein the medical phase comprises at least one of an outpatient phase, an inpatient phase, and a follow-up phase.

5. The method according to claim 4, wherein the classified display of the associated search data according to the preset medical stages comprises:

respectively establishing retrieval time axes for retrieval objects contained in the associated retrieval data;

and displaying the associated retrieval data corresponding to each retrieval object in each medical stage to the corresponding retrieval time axis respectively.

6. The method according to claim 5, wherein the displaying the associated search data corresponding to each of the search objects at each of the medical stages onto the corresponding search timeline respectively comprises:

determining medical events of the retrieval objects in different medical stages, and displaying the medical events on the retrieval time axis according to the time sequence of the occurrence time;

determining a related medical event of the related retrieval data in each medical event of each retrieval object;

labeling the associated medical events in the medical events on the retrieval time axis according to a preset labeling mode;

when a trigger display instruction is received, displaying the associated retrieval data corresponding to the associated medical event indicated in the trigger display instruction.

7. The method of claim 1, further comprising:

when a specified comparison instruction is received, determining at least two comparison contents needing to be compared based on the specified comparison instruction; the comparison content comprises a specified target object needing to be compared, search conditions and each associated search data corresponding to each search condition;

and determining the comparison content in a pre-stored historical database, and displaying the comparison content to the same display interface.

8. The method of claim 7, wherein the presenting the comparison content into the same presentation interface comprises:

distinguishing and labeling the at least two pieces of comparison content according to different labeling modes, and displaying the labeled comparison content on the same display interface;

the different labeling modes comprise at least one of different serial number labeling, different shape labeling, different color labeling and different character labeling.

9. The method of claim 1, further comprising:

when a newly added data request is received, newly added object information and newly added data corresponding to the newly added data request are obtained;

and adding the newly added object information and the newly added data to the medical database.

10. A medical knowledge-graph-based medical data exploration apparatus, comprising: