CN110752027B - Electronic medical record data pushing method, device, computer equipment and storage medium - Google Patents
Electronic medical record data pushing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110752027B CN110752027B CN201911000771.XA CN201911000771A CN110752027B CN 110752027 B CN110752027 B CN 110752027B CN 201911000771 A CN201911000771 A CN 201911000771A CN 110752027 B CN110752027 B CN 110752027B
- Authority
- CN
- China
- Prior art keywords
- electronic medical
- medical record
- record set
- similar
- sorting
- 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.)
- Active
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application relates to a method, a device, computer equipment and a storage medium for pushing electronic medical record data, wherein the method comprises the following steps: the method comprises the steps of obtaining an electronic medical record set, screening the current electronic medical record set to obtain a similar electronic medical record set, obtaining corresponding medical institution characteristic fields based on electronic medical record identification marks in the similar electronic medical record set, constructing a relation model of a disease-treating doctor-treating institution, matching the relation model with the similar electronic medical record set, and carrying out sorting pushing on a matching result by adopting a sorting rule of most similar sorting, difficult and complicated sorting or most authoritative sorting. In the whole process, the matching result of the electronic medical records is accurately obtained by learning the data in the electronic medical record set, and the three different directions of similarity, disease rarity or diagnosis authority are adopted for sorting and pushing, so that accurate diagnosis data support can be provided by different emphasis points.
Description
Technical Field
The present disclosure relates to the field of electronic medical records, and in particular, to a method, an apparatus, a computer device, and a storage medium for pushing electronic medical record data.
Background
With the development of medical technology and internet technology, electronic medical records are popularized and applied in more and more hospitals at present. In particular, electronic medical records, also known as computerized medical records systems or computer-based patient records, are digitized patient medical records that are stored, managed, transferred, and reproduced by electronic devices (computers, health cards, etc.), in place of handwritten paper medical records.
The popularization and application of the electronic medical record bring convenience to people, and research of a plurality of new technologies is derived based on the electronic medical record at present, for example, research such as large data analysis and processing based on the electronic medical record, and associated pushing of medical record data is realized.
The traditional large data processing method based on the electronic medical records adopts a method of analyzing or machine learning internal data of a system and adding some disease public materials for diagnosis, and the related pushing method based on the large data can push some data of related electronic medical records to a user, but the data analysis and machine learning processes are directly transplanted from large data analysis in other fields and do not optimize the characteristics of the electronic medical record data, so that the pushed data accuracy is different, and the pushed electronic medical record data cannot provide reliable data support for doctor diagnosis.
Disclosure of Invention
Based on the foregoing, it is necessary to provide an accurate electronic medical record data pushing method, device, computer equipment and storage medium for the technical problems.
An electronic medical record data pushing method, the method comprising:
acquiring an electronic medical record set of a hospital;
screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set;
identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring a medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution;
and matching the relation model with the similar electronic medical record set, and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting.
In one embodiment, the acquiring the electronic medical record set of the hospital includes:
acquiring an initial electronic medical record set of a trimethyl hospital;
and carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, working units, telephones and addresses.
In one embodiment, the screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain the similar electronic medical record set includes:
and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the characteristic fields to obtain a similar electronic medical record set, wherein the characteristic fields comprise an age field, a symptom field and a disease name field.
In one embodiment, the screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the feature field, and obtaining the similar electronic medical record set includes:
processing the electronic medical record set by adopting a natural language processing method according to the characteristic field, and obtaining the characteristic vector of the electronic medical record in the electronic medical record set according to a preset medical symptom knowledge graph;
carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record;
matching the characteristic vector of the electronic medical record in the electronic medical record set with the characteristic vector of the current electronic medical record to obtain a similar electronic medical record set.
In one embodiment, the processing the electronic medical record set by using a natural language processing method according to the feature field, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the preset medical symptom knowledge graph includes:
Performing text word segmentation processing on the electronic medical record set according to the characteristic field to obtain a word segmentation result;
and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and a preset medical symptom knowledge graph.
In one embodiment, the matching the feature vector of the electronic medical record in the electronic medical record set with the feature vector of the current electronic medical record to obtain the similar electronic medical record set includes:
calculating Euclidean distance between the characteristic vector of the electronic medical record in the electronic medical record set and the characteristic vector of the current electronic medical record;
and obtaining a similar electronic medical record set according to the Euclidean distance.
In one embodiment, the identifying the identity of the electronic medical record in the similar electronic medical record set, obtaining the medical institution feature field corresponding to the identity, and constructing the disease-treating doctor-treating institution relationship model includes:
identifying the electronic medical record filing ID in the similar electronic medical record set, and extracting a disease name field of the electronic medical record in the similar electronic medical record set;
Searching the doctor working age, the department and the hospital name corresponding to the filing ID;
and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the searched doctor working age, the name of the department and the name of the hospital.
An electronic medical record data pushing device, the device comprising:
the medical record acquisition module is used for acquiring an electronic medical record set of a hospital;
the similarity screening module is used for screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set;
the identification module is used for identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification and constructing a relationship model of a disease-treating doctor-treating institution;
and the matching and sorting module is used for matching the relation model with the similar electronic medical record set and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method as described above.
According to the method, the device, the computer equipment and the storage medium for pushing the electronic medical record data, the similar electronic medical record set is obtained by screening the current electronic medical record set, the corresponding medical institution characteristic fields are obtained based on the electronic medical record identity marks in the similar electronic medical record set, the relationship model of the disease-treating doctor-treating institution is constructed, the relationship model is matched with the similar electronic medical record set, and the matching result is subjected to sorting pushing by adopting the sorting rule of the most similar sorting, the difficult and complicated sorting or the most authoritative sorting. In the whole process, the matching result of the electronic medical records is accurately obtained by learning the data in the electronic medical record set, and the accurate diagnosis data support can be provided by adopting the sorting pushing in three different directions of similarity (most similar sorting), disease rarity (problematic and miscellaneous diseases sorting) or diagnosis authority (most authoritative sorting).
Drawings
FIG. 1 is an application environment diagram of an electronic medical record data pushing method in one embodiment;
FIG. 2 is a flowchart of a method for pushing electronic medical record data according to an embodiment;
FIG. 3 is a flowchart of a method for pushing electronic medical record data according to another embodiment;
FIG. 4 is a flowchart of a method for pushing electronic medical record data according to an embodiment of the present invention;
FIG. 5 is a block diagram of an electronic medical record data pushing device according to one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The electronic medical record data pushing method provided by the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 may be a server of an electronic medical record management system, the terminal 102 inputs the current electronic medical record data into the server 104, the server 104 obtains an electronic medical record set of a hospital, and screens electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set; identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution; matching the relation model with a similar electronic medical record set, sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated disease sorting or the most authoritative sorting, and the terminal 102 receives sorted related data pushed by the server 104 and displays the data to a user (doctor) so as to provide data support in diagnosis. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, there is provided a method for pushing electronic medical record data, which is illustrated by applying the method to the server 104 in fig. 1, and includes the following steps:
s100: and acquiring an electronic medical record set of the hospital.
The electronic medical record set of the hospital can be specifically an electronic medical record set of all hospitals in a certain area, for example, an electronic medical record set of all hospitals in a certain city, or even a store sub medical record set of all hospitals in a certain province, which requires the data intercommunication and sharing of the electronic medical record of the hospitals in the area, and preferably requires the electronic medical record systems of all hospitals to be built based on the same architecture and have an intercommunication function. The electronic medical record data of the hospital can also be an electronic medical record set of a certain hospital history record, such as an electronic medical record set of a certain city center hospital, an electronic medical record set of a certain province people hospital, and the like. Because the electronic medical record relates to more privacy and explicit information, the acquired electronic medical record set needs to be subjected to personal information desensitization or hiding treatment so as to protect the privacy of each patient, and only the data related to the symptoms carried in the electronic medical record is used as the basis for subsequent learning treatment.
S200: and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set.
The current electronic medical record refers to the currently generated electronic medical record, and the server needs to find the electronic medical record similar to the current electronic medical record from the electronic medical record set obtained in the step S100. Taking Zhang San of a diabetic patient as an example, a doctor diagnoses Zhang San of the patient, inputs all examination and diagnosis data of Zhang San into an electronic medical record system, generates Zhang San electronic medical record, and the current electronic medical record is Zhang San electronic medical record. Further, the doctor can input the examination and diagnosis data of Zhang San into the electronic medical record system in the own office computer (terminal), and the electronic medical record system server screens the electronic medical record similar to Zhang San electronic medical record from the electronic medical record set to obtain Zhang San-diabetes-similar electronic medical record set.
S300: and identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution.
The identity identification mark of the electronic medical record is used for distinguishing the identity of the electronic medical record, and further the storage position of the electronic medical record can be identified. Generally, in an electronic medical record system, the electronic medical record is classified and documented according to a disease name field, a diagnosis disease name, a medicament, a treatment means and the like, for example, the electronic medical record can be classified and documented in a tree-shaped manner, and the identification mark of the specific electronic medical record can be a documented ID. The medical institution characteristic field may specifically include information of a name of an attending doctor, a working age of the doctor, a department of science, a hospital of the doctor, and the like. After the processing, the server can obtain the disease name field carried in the electronic medical record, inquire about information about the treating doctor and information about the treating mechanism obtained by the filing ID, and construct a relation model of the disease-treating doctor-treating mechanism based on the information. For example, a profile ID of the four-in-li electronic medical record in the similar electronic medical record set is identified as 5678, the medical feature field corresponding to the profile ID5678 is mainly used by a doctor, a medical treatment organization is a people hospital in X province, the four-in-li electronic medical record carries a disease name of diabetes, the relationship of the disease-treatment doctor-treatment organization constructed based on the data is a people hospital in diabetes-five-X province, it is understood that the relationship of the disease-treatment doctor-treatment organization can be obtained by repeating the above processes based on each electronic medical record in the similar electronic medical record set, and the relationship model can be finally obtained by optimizing the corresponding relationship model based on the corresponding relationships.
S400: matching the relation model with the similar electronic medical record set, and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting.
The relationship model of the disease-treating doctor-treating mechanism carries three-dimensional associated data of the disease name, the treating doctor and the treating mechanism, the matching process is specifically matching the three dimensions of the disease name, the treating doctor and the treating mechanism based on the relationship model and a similar electronic inner set, sorting pushing is carried out by adopting a preset sorting rule mode aiming at the matching result, and the matching result and the preset sorting rule are needed to be based on the three-dimensional data during sorting. Specifically, the preset ordering rule comprises the most similar ordering, the difficult and complicated symptom ordering or the most authoritative ordering, wherein the most similar ordering takes the disease name as a main dimension, and specifically takes the similarity of symptoms and disease descriptions as a core matching index for ordering; the difficult and complicated disease sorting is performed by taking the disease name as a main dimension and finding related rare possible diseases as indexes based on the disease name and the corresponding medical record description, so as to prompt doctors that certain symptoms are not serious, but the symptoms are possibly the characteristics of the rare diseases, and the doctor is required to pay attention to and exclude the symptoms; the most authoritative ranking is to take a treating doctor and a treating mechanism as main dimensions, and associate the ranking of the hospital level and the main treating doctor level from high to low in a similar medical record set, so as to refer to the diagnosis scheme given by the authoritative specialist of the disease for the current doctor.
According to the electronic medical record data pushing method, for the current electronic medical record, a similar electronic medical record set is obtained by screening from the electronic medical record set, corresponding medical institution characteristic fields are obtained based on the electronic medical record identity marks in the similar electronic medical record set, a relation model of a disease-treating doctor-treating institution is constructed, matching is carried out based on the relation model and the similar electronic medical record set, and sorting pushing is carried out on the matching result by adopting a sorting rule of most similar sorting, difficult and complicated sorting or most authoritative sorting. In the whole process, the matching result of the electronic medical records is accurately obtained by learning the data in the electronic medical record set, and the accurate diagnosis data support can be provided by adopting the sorting pushing in three different directions of similarity (most similar sorting), disease rarity (problematic and miscellaneous diseases sorting) or diagnosis authority (most authoritative sorting).
As shown in fig. 3, in one embodiment, step S100 includes:
s120: and obtaining an initial electronic medical record set of the trimethyl hospital.
S140: and (3) carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, work units, telephones and addresses.
The three hospitals are medical institution levels classified according to the regulations of the current hospital hierarchical management method in China, and the three hospitals are the highest level in the classification level of three levels, six levels, and the like of the hospitals in China and China. The main items of reporting and checking in the three-hospital include medical service and management, medical quality and safety, and technical level and efficiency. Generally, three-dimensional hospital doctors encounter more medical records and make diagnosis results relatively more authoritative and accurate, so that in order to ensure the accuracy and the comprehensiveness of the original data, an initial electronic medical record set of the three-dimensional hospital is selected and acquired. In addition, because the electronic medical record carries more remarkable personal information, in order to protect the privacy of users (patients), the personal field information needs to be hidden or desensitized, and the personal field information mainly comprises names, professions, working units, telephones, addresses and the like. For example, a certain electronic medical record is originally recorded with the following information, name: wang San one, occupation: subway driver, work unit: the rail traffic group is subjected to hiding treatment, namely the names, professions and working units are all hidden directly; the desensitization treatment can be specifically carried out by replacing specific characters with common symbols, for example, the name is obtained after the desensitization treatment: king XX, occupation: XX driver, work unit: XX group. In the embodiment, on one hand, the electronic medical record of the three hospitals is selected as the original data set, so that the original data is more authoritative, comprehensive and accurate; on the other hand, the obvious personal information carried in the electronic medical record is subjected to hiding or desensitizing treatment, so that the personal privacy of a patient is protected.
In one embodiment, the step of screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain the similar electronic medical record set includes: and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the characteristic fields to obtain a similar electronic medical record set, wherein the characteristic fields comprise an age field, a symptom field and a disease name field.
The characteristic field comprises an age field, a symptom field and a disease name field, wherein the age field specifically refers to age, the symptom field is used for describing the disease symptoms and clinical manifestations of a patient, and the disease name field specifically refers to the disease name recorded in the diagnosis result. Taking Zhang Sanas an example, the characteristic fields comprise an age field, namely 45 years old, a symptom field, emaciation, high food intake, ultrahigh sugar content in urine and the like, and a disease name field, namely diabetes. And screening the electronic medical records similar to the previous electronic medical records from the electronic medical record sets according to the characteristic fields, and collecting the similar electronic medical records. Specifically, the three index levels of the age field, the symptom field and the disease name field can be selected, for example, electronic medical records with similar ages, similar symptoms and the same or similar or related disease names are selected as the subset in the similar electronic medical record set.
In one embodiment, screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the feature field, and obtaining the similar electronic medical record set includes:
processing the electronic medical record set by adopting a natural language processing method according to the characteristic fields, and obtaining characteristic vectors of electronic medical records in the electronic medical record set according to a preset medical symptom knowledge graph; carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record; matching the feature vector of the electronic medical record in the electronic medical record set with the feature vector of the current electronic medical record to obtain a similar electronic medical record set.
Natural language processing is an important direction in the fields of computer science and artificial intelligence. It is studying various theories and methods that enable effective communication between a person and a computer in natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Thus, the research in this field will involve natural language, i.e. language that people use daily, so it has a close relation with the research in linguistics, but has important differences. The preset medical symptom knowledge graph is a pre-constructed indication graph, and the knowledge graph can directly adopt the existing medical symptom knowledge graph. Specifically, the natural language processing method includes text word segmentation and other processing, obtains feature vectors based on data processed by the natural language processing method and a preset medical symptom knowledge graph, wherein the processing of the electronic medical records in the electronic medical record set is performed on the other layer, semantic analysis is performed on the electronic medical records first, symptom fields are extracted based on semantic word segmentation results, feature vectors of the current electronic medical records are obtained according to the extracted symptom fields and feature fields including age fields, symptom fields and disease name fields corresponding to the current electronic medical records, and two feature vectors are matched to construct a similar electronic medical record set. In addition, the extracted symptom fields can be specifically extracted obvious symptom fields, and when a plurality of obvious symptom fields exist, the symptom fields are sequenced according to a medical symptom training model to obtain the feature vector of the feature field of the current electronic medical record.
Further, the Euclidean distance between the characteristic vector of the electronic medical record in the electronic medical record set and the characteristic vector of the current electronic medical record can be calculated; and obtaining a similar electronic medical record set according to the Euclidean distance. Specifically, different medical record sets can be constructed according to the Euclidean distance, and a set with similar distances is selected as a similar medical record set.
In one embodiment, processing the electronic medical record set by adopting a natural language processing method according to the feature field, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the preset medical symptom knowledge graph includes:
text word segmentation processing is carried out on the electronic medical record set according to the characteristic field, and a word segmentation result is obtained; and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and the preset medical symptom knowledge graph.
And performing text word segmentation processing on the electronic medical record according to the feature field, performing part-of-speech recognition and part-of-speech tagging on the word segmentation result, and obtaining a feature vector according to the word segmentation result, the part-of-speech recognition result and the medical symptom knowledge graph. Taking wang electronic medical records in an electronic medical record set as an example, performing word segmentation processing on wang electronic medical records according to characteristic fields to obtain wang age field word segmentation, namely 50 years old, symptom field word segmentation, chest distress and dizziness, disease name field word segmentation, namely coronary heart disease, performing part-of-speech recognition on word segmentation results to obtain part-of-speech names, verbs, graduated words and the like, obtaining wang characteristic vectors according to the word segmentation results and part-of-speech recognition results of the wang, and repeating the processes for electronic medical records of other people in the electronic medical record set by means of preset medical symptom knowledge graphs to obtain the characteristic vectors of the electronic medical records in the electronic medical record set.
In one embodiment, identifying the identity of the electronic medical record in the set of similar electronic medical records, obtaining the medical facility feature field corresponding to the identity, and constructing the disease-treating doctor-treating facility relationship model includes:
identifying the electronic medical record filing ID in the similar electronic medical record set, and extracting a disease name field of the electronic medical record in the similar electronic medical record set; searching the doctor working age, the department and the hospital name corresponding to the filing ID; and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the working age of the doctor, the department and the hospital name.
Specifically, the relationship model of the disease-treating doctor-treating mechanism carries the related data of three dimensions of the disease name, the treating doctor and the treating mechanism, the relationship model can be constructed based on the electronic medical record filing ID, further data of the working age of the doctor, the department of the doctor, the name of the hospital and the like can be obtained through the filing ID, and the relationship model comprising the three dimensions of the disease name, the treating doctor and the treating mechanism can be constructed by combining the disease name fields obtained before.
In order to further explain the technical scheme of the electronic medical record data pushing method in detail, a specific application example is adopted in the following, and the detailed description is carried out with reference to fig. 4. In one application example, the method for pushing the electronic medical record data comprises the following steps:
step S1, an electronic medical record set A of the electronic medical record of the three-dimensional hospital is obtained, wherein the obvious personal information fields such as the name, occupation, work unit, telephone, address and the like of the electronic medical record are hidden or desensitized.
Step S2, screening medical records similar to the medical records, and searching similar electronic medical record sets obtained by matching according to the information including but not limited to an age field, a symptom field and a disease name field. Step S2 specifically includes the following substeps S21 to S24.
Step S21, age fields, symptom fields and disease name fields in the electronic medical record set A of the trimethyl hospital are processed by adopting a natural language processing method, for example, a text is segmented, part-of-speech tagging is carried out on segmentation results, and feature vectors are established according to the segmentation, part-of-speech and medical symptom knowledge graph.
Step S22, carrying out semantic analysis on the current electronic medical record, extracting representative obvious symptom fields, and if a plurality of symptoms exist, sorting according to a medical symptom training model to establish age, symptom and disease name feature vectors of the current electronic medical record.
Step S23, calculating the Euclidean distance between the feature vector obtained by the step S21 of the three-hospital electronic medical record set A and the feature vector obtained by the step S22 of the current electronic medical record age, symptom and disease name.
Step S24, constructing different medical record sets according to the Euclidean distance, and taking the set with similar distances as a similar medical record set.
Step S3, identifying the documented ID of the similar electronic medical record, checking the working age of the doctor with the ID, the department, the hospital name and the construction model, namely, definitely determining the doctor and hospital information for treating the diseases related to the medical record, and establishing a relation model of the disease, the treating doctor and the treating mechanism.
And S4, matching the relation model constructed in the step S3 with each electronic medical record in the similar electronic medical record set in the step S2 to form a recommended sorting result of the medical records.
Step S5, during sorting, three sorting results are produced: most similar sorting, difficult and complicated diseases sorting and most authoritative sorting are used for a doctor of the current electronic medical record to check, so that high-quality medical experience is obtained, and misdiagnosis accidents caused by lack of doctor experience in small hospitals are reduced. The 3 sorting modes finally generate the following three sorting tables: recommending an ordered list based on symptoms of similarity and disease similarity; a rare-related special cases ordered list based on rarity; the diseases based on authority degree are ordered according to the professional authority degree of hospitals and doctors.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or steps.
In addition, as shown in fig. 5, the application further provides an electronic medical record data pushing device, where the device includes:
a medical record acquisition module 100, configured to acquire an electronic medical record set of a hospital;
the similarity screening module 200 is configured to screen electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set;
the identification module 300 is configured to identify an identity of an electronic medical record in a similar electronic medical record set, obtain a medical institution feature field corresponding to the identity, and construct a relationship model of a disease-treating doctor-treating institution;
The matching and sorting module 400 is configured to match the relationship model with the similar electronic medical record set, and sort and push the matching result according to a preset sorting rule, where the preset sorting rule includes a most similar sorting, a problematic sorting or a most authoritative sorting.
According to the electronic medical record data pushing device, for the current electronic medical record, the similar electronic medical record set is obtained by screening from the electronic medical record set, the corresponding medical institution characteristic field is obtained based on the electronic medical record identity identification in the similar electronic medical record set, the relationship model of the disease-treating doctor-treating institution is constructed, then the relationship model is matched with the similar electronic medical record set, and the matching result is subjected to sorting pushing by adopting the sorting rule of the most similar sorting, the difficult and complicated sorting or the most authoritative sorting. In the whole process, the matching result of the electronic medical records is accurately obtained by learning the data in the electronic medical record set, and the accurate diagnosis data support can be provided by adopting the sorting pushing in three different directions of similarity (most similar sorting), disease rarity (problematic and miscellaneous diseases sorting) or diagnosis authority (most authoritative sorting).
In one embodiment, the medical record acquisition module 100 is further configured to acquire an initial set of electronic medical records for a trimethyl hospital; and (3) carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, work units, telephones and addresses.
In one embodiment, the similarity filtering module 200 is further configured to filter electronic medical records similar to the current electronic medical record from the electronic medical record set according to the feature fields, so as to obtain a similar electronic medical record set, where the feature fields include an age field, a symptom field, and a disease name field.
In one embodiment, the similarity screening module 200 is further configured to process the electronic medical record set by adopting a natural language processing method according to the feature field, and obtain a feature vector of the electronic medical record in the electronic medical record set according to a preset medical symptom knowledge graph; carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record; matching the feature vector of the electronic medical record in the electronic medical record set with the feature vector of the current electronic medical record to obtain a similar electronic medical record set.
In one embodiment, the similarity screening module 200 is further configured to perform text word segmentation on the electronic medical record set according to the feature field to obtain a word segmentation result; and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and the preset medical symptom knowledge graph.
In one embodiment, the similarity screening module 200 is further configured to calculate a euclidean distance between a feature vector of the electronic medical record in the electronic medical record set and a feature vector of the current electronic medical record; and obtaining a similar electronic medical record set according to the Euclidean distance.
In one embodiment, the identifying module 300 is further configured to identify an electronic medical record profile ID in the similar electronic medical record set, and extract a disease name field of the electronic medical record in the similar electronic medical record set; searching the doctor working age, the department and the hospital name corresponding to the filing ID; and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the working age of the doctor, the department and the hospital name.
For specific limitation of the electronic medical record data pushing device, the above limitation of the electronic medical record data pushing method may be referred to, and will not be described herein. All or part of the modules in the electronic medical record data pushing device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing data such as hospital electronic medical records in the history record. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is configured to implement a method for pushing electronic medical record data.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring an electronic medical record set of a hospital;
screening the electronic medical records similar to the current electronic medical records from the electronic medical record set to obtain a similar electronic medical record set;
identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution;
matching the relation model with the similar electronic medical record set, and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring an initial electronic medical record set of a trimethyl hospital; and (3) carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, work units, telephones and addresses.
In one embodiment, the processor when executing the computer program further performs the steps of:
and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the characteristic fields to obtain a similar electronic medical record set, wherein the characteristic fields comprise an age field, a symptom field and a disease name field.
In one embodiment, the processor when executing the computer program further performs the steps of:
processing the electronic medical record set by adopting a natural language processing method according to the characteristic fields, and obtaining characteristic vectors of electronic medical records in the electronic medical record set according to a preset medical symptom knowledge graph; carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record; matching the feature vector of the electronic medical record in the electronic medical record set with the feature vector of the current electronic medical record to obtain a similar electronic medical record set.
In one embodiment, the processor when executing the computer program further performs the steps of:
text word segmentation processing is carried out on the electronic medical record set according to the characteristic field, and a word segmentation result is obtained; and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and the preset medical symptom knowledge graph.
In one embodiment, the processor when executing the computer program further performs the steps of:
calculating the Euclidean distance between the characteristic vector of the electronic medical record in the electronic medical record set and the characteristic vector of the current electronic medical record; and obtaining a similar electronic medical record set according to the Euclidean distance.
In one embodiment, the processor when executing the computer program further performs the steps of:
identifying the electronic medical record filing ID in the similar electronic medical record set, and extracting a disease name field of the electronic medical record in the similar electronic medical record set; searching the doctor working age, the department and the hospital name corresponding to the filing ID; and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the working age of the doctor, the department and the hospital name.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an electronic medical record set of a hospital;
screening the electronic medical records similar to the current electronic medical records from the electronic medical record set to obtain a similar electronic medical record set;
identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution;
Matching the relation model with the similar electronic medical record set, and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring an initial electronic medical record set of a trimethyl hospital; and (3) carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, work units, telephones and addresses.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the characteristic fields to obtain a similar electronic medical record set, wherein the characteristic fields comprise an age field, a symptom field and a disease name field.
In one embodiment, the computer program when executed by the processor further performs the steps of:
processing the electronic medical record set by adopting a natural language processing method according to the characteristic fields, and obtaining characteristic vectors of electronic medical records in the electronic medical record set according to a preset medical symptom knowledge graph; carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record; matching the feature vector of the electronic medical record in the electronic medical record set with the feature vector of the current electronic medical record to obtain a similar electronic medical record set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
text word segmentation processing is carried out on the electronic medical record set according to the characteristic field, and a word segmentation result is obtained; and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and the preset medical symptom knowledge graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating the Euclidean distance between the characteristic vector of the electronic medical record in the electronic medical record set and the characteristic vector of the current electronic medical record; and obtaining a similar electronic medical record set according to the Euclidean distance.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying the electronic medical record filing ID in the similar electronic medical record set, and extracting a disease name field of the electronic medical record in the similar electronic medical record set; searching the doctor working age, the department and the hospital name corresponding to the filing ID; and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the working age of the doctor, the department and the hospital name.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. An electronic medical record data pushing method, the method comprising:
acquiring an electronic medical record set of a hospital;
screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set;
identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring a medical institution characteristic field corresponding to the identity identification, and constructing a relationship model of disease-treating doctor-treating institution;
Matching the relation model with the similar electronic medical record set, and sorting and pushing matching results according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting; the matching process is to match the disease name, the treating doctor and the treating mechanism in three dimensions.
2. The method of claim 1, wherein the acquiring the set of electronic medical records for the hospital comprises:
acquiring an initial electronic medical record set of a trimethyl hospital;
and carrying out personal field information hiding or desensitizing treatment on the initial electronic medical record set to obtain the electronic medical record set, wherein the personal field information comprises names, professions, working units, telephones and addresses.
3. The method of claim 1, wherein the screening the electronic medical records from the set of electronic medical records for a similar electronic medical record to the current electronic medical record comprises:
and screening the electronic medical records similar to the current electronic medical record from the electronic medical record set according to the characteristic fields to obtain a similar electronic medical record set, wherein the characteristic fields comprise an age field, a symptom field and a disease name field.
4. The method of claim 3, wherein the screening the electronic medical records from the set of electronic medical records for similarity to the current electronic medical record based on the feature field, the obtaining a set of similar electronic medical records comprises:
processing the electronic medical record set by adopting a natural language processing method according to the characteristic field, and obtaining the characteristic vector of the electronic medical record in the electronic medical record set according to a preset medical symptom knowledge graph;
carrying out semantic analysis on the current electronic medical record, and extracting symptom fields to obtain feature vectors of corresponding feature fields of the current electronic medical record;
matching the characteristic vector of the electronic medical record in the electronic medical record set with the characteristic vector of the current electronic medical record to obtain a similar electronic medical record set.
5. The method of claim 4, wherein the processing the electronic medical record set according to the feature field by using a natural language processing method, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the preset medical symptom knowledge graph comprises:
performing text word segmentation processing on the electronic medical record set according to the characteristic field to obtain a word segmentation result;
and performing part-of-speech recognition on the word segmentation result, and obtaining the feature vector of the electronic medical record in the electronic medical record set according to the word segmentation result, the part-of-speech recognition result and a preset medical symptom knowledge graph.
6. The method of claim 4, wherein the matching the feature vector of the electronic medical record in the set of electronic medical records with the feature vector of the current electronic medical record to obtain a set of similar electronic medical records comprises:
calculating Euclidean distance between the characteristic vector of the electronic medical record in the electronic medical record set and the characteristic vector of the current electronic medical record;
and obtaining a similar electronic medical record set according to the Euclidean distance.
7. The method of claim 1, wherein the identifying the identity of the electronic medical record in the set of similar electronic medical records, obtaining a medical facility feature field corresponding to the identity, and constructing a disease-treating doctor-treating facility relationship model comprises:
identifying the electronic medical record filing ID in the similar electronic medical record set, and extracting a disease name field of the electronic medical record in the similar electronic medical record set;
searching the doctor working age, the department and the hospital name corresponding to the filing ID;
and constructing a relation model of the disease-treating doctor-treating institution according to the disease name field, the searched doctor working age, the name of the department and the name of the hospital.
8. An electronic medical record data pushing device, characterized in that the device comprises: the medical record acquisition module is used for acquiring an electronic medical record set of a hospital;
the similarity screening module is used for screening the electronic medical records similar to the current electronic medical record from the electronic medical record set to obtain a similar electronic medical record set;
the identification module is used for identifying the identity identification of the electronic medical record in the similar electronic medical record set, acquiring the medical institution characteristic field corresponding to the identity identification and constructing a relationship model of a disease-treating doctor-treating institution;
the matching and sorting module is used for matching the relation model with the similar electronic medical record set and sorting and pushing the matching result according to a preset sorting rule, wherein the preset sorting rule comprises the most similar sorting, the difficult and complicated symptom sorting or the most authoritative sorting; the matching process is to match the disease name, the treating doctor and the treating mechanism in three dimensions.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911000771.XA CN110752027B (en) | 2019-10-21 | 2019-10-21 | Electronic medical record data pushing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911000771.XA CN110752027B (en) | 2019-10-21 | 2019-10-21 | Electronic medical record data pushing method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110752027A CN110752027A (en) | 2020-02-04 |
| CN110752027B true CN110752027B (en) | 2023-05-23 |
Family
ID=69279138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911000771.XA Active CN110752027B (en) | 2019-10-21 | 2019-10-21 | Electronic medical record data pushing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110752027B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111430037B (en) * | 2020-03-30 | 2024-04-09 | 讯飞医疗科技股份有限公司 | Similar medical record searching method and system |
| CN111540425B (en) * | 2020-04-26 | 2021-01-15 | 和宇健康科技股份有限公司 | Intelligent medical information pushing method based on artificial intelligence and electronic medical record cloud platform |
| CN111613339B (en) * | 2020-05-15 | 2021-07-09 | 山东大学 | Similar medical record searching method and system based on deep learning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184103A (en) * | 2015-10-15 | 2015-12-23 | 清华大学深圳研究生院 | Virtual medical expert based on medical record database |
| CN108154928A (en) * | 2017-12-27 | 2018-06-12 | 北京嘉和美康信息技术有限公司 | A kind of methods for the diagnosis of diseases and device |
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109346185A (en) * | 2018-09-19 | 2019-02-15 | 北京科技大学 | A kind of aided diagnosis of traditional Chinese medicine system |
| CN109473169A (en) * | 2018-10-18 | 2019-03-15 | 安吉康尔（深圳）科技有限公司 | A kind of methods for the diagnosis of diseases, device and terminal device |
| CN109801690A (en) * | 2017-11-17 | 2019-05-24 | 深圳市前海安测信息技术有限公司 | Area medical electronic health record is shared to integrate inquiry system and method |
| CN109801688A (en) * | 2017-11-17 | 2019-05-24 | 深圳市前海安测信息技术有限公司 | The safe synergism action system and method for area medical electronic health record |
-
2019
- 2019-10-21 CN CN201911000771.XA patent/CN110752027B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184103A (en) * | 2015-10-15 | 2015-12-23 | 清华大学深圳研究生院 | Virtual medical expert based on medical record database |
| CN109801690A (en) * | 2017-11-17 | 2019-05-24 | 深圳市前海安测信息技术有限公司 | Area medical electronic health record is shared to integrate inquiry system and method |
| CN109801688A (en) * | 2017-11-17 | 2019-05-24 | 深圳市前海安测信息技术有限公司 | The safe synergism action system and method for area medical electronic health record |
| CN108154928A (en) * | 2017-12-27 | 2018-06-12 | 北京嘉和美康信息技术有限公司 | A kind of methods for the diagnosis of diseases and device |
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109346185A (en) * | 2018-09-19 | 2019-02-15 | 北京科技大学 | A kind of aided diagnosis of traditional Chinese medicine system |
| CN109473169A (en) * | 2018-10-18 | 2019-03-15 | 安吉康尔（深圳）科技有限公司 | A kind of methods for the diagnosis of diseases, device and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110752027A (en) | 2020-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112365987B (en) | Diagnostic data abnormality detection method, diagnostic data abnormality detection device, computer device, and storage medium | |
| Mason et al. | An investigation of biometric authentication in the healthcare environment | |
| CN111180024B (en) | Data processing method and device based on word frequency and inverse document frequency and computer equipment | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| CN109036545B (en) | Medical information processing method, apparatus, computer device and storage medium | |
| CN113724848A (en) | Medical resource recommendation method, device, server and medium based on artificial intelligence | |
| CN112132624A (en) | Medical claims data prediction system | |
| US10936962B1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| JP7280705B2 (en) | Machine learning device, program and machine learning method | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN111415760B (en) | Doctor recommendation method, doctor recommendation system, computer equipment and storage medium | |
| CN113658712A (en) | Doctor-patient matching method, device, equipment and storage medium | |
| Chang et al. | Morbidity trajectories as predictors of utilization: multi-year disease patterns in Taiwan's national health insurance program | |
| Hom et al. | Facilitating clinical research through automation: Combining optical character recognition with natural language processing | |
| CN113722507B (en) | Hospitalization cost prediction method and device based on knowledge graph and computer equipment | |
| US12087442B2 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| CN109522331B (en) | Individual-centered regionalized multi-dimensional health data processing method and medium | |
| US20230377697A1 (en) | System and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history | |
| CN116070260A (en) | Anonymizing method and device for privacy information, electronic equipment and storage medium | |
| CN113590845B (en) | Knowledge graph-based document retrieval method and device, electronic equipment and medium | |
| US20230154596A1 (en) | Predictive Recommendation Systems Using Compliance Profile Data Objects | |
| US20150339602A1 (en) | System and method for modeling health care costs | |
| CN115631823A (en) | Similar case recommendation method and system | |
| CN115700826A (en) | Receipt processing method, receipt display method, receipt processing device, receipt display device, computer equipment and storage medium |
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 |