CN112071425A - Data processing method and device, computer equipment and storage medium - Google Patents
Data processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112071425A CN112071425A CN202010921656.2A CN202010921656A CN112071425A CN 112071425 A CN112071425 A CN 112071425A CN 202010921656 A CN202010921656 A CN 202010921656A CN 112071425 A CN112071425 A CN 112071425A
- Authority
- CN
- China
- Prior art keywords
- visit
- data
- patient
- historical
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H50/20—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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Bioethics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Animal Behavior & Ethology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a data processing method, a data processing device, computer equipment and a storage medium, and relates to the field of intelligent medical treatment. The invention can construct a knowledge graph based on historical patient diagnosis data, and acquire a first treatment sequence of each historical patient in the knowledge graph; acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data; by matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph, the diagnosis data of the historical patients matched with the second visit sequence is obtained, and the reliability and accuracy of the diagnosis data are improved; and classifying the second visit sequence by adopting a classification model to acquire diagnosis probability data so as to provide medical reference for the target patient/doctor, and combining the diagnosis data and the diagnosis probability data obtained by matching to provide more reliable and accurate parameter data for the target patient/doctor.
Description
Technical Field
The invention relates to the field of intelligent medical treatment, in particular to a data processing method, a data processing device, computer equipment and a storage medium.
Background
With the development of information technology and the arrival of the intelligent era, the information technology is applied to the aspects of national governance, economic operation, medical treatment and health and the like, a large amount of data is generated, the data growth range of the medical industry is particularly prominent, the medical big data has great value, and particularly, in the aspects of clinical auxiliary diagnosis and treatment and health management, the clinical data, the clinical guideline and the omics data are combined through big data, a knowledge graph and a visualization system, the comprehensive coverage of the core medical concept and the aggregation of all-round knowledge data in the medical ecosphere are combined to construct a comprehensive medical brain, so that the comprehensive medical brain provides help for clinicians, scientific research workers and management workers, and becomes the development direction of future medical treatment. In recent years, researchers have been focusing on some machine learning-based disease prediction methods and deep learning-based disease prediction methods in the field.
The existing disease prediction method can construct a patient image through electronic case information of a patient, such as data of diagnosis, medical advice, demographics and the like, so as to provide a doctor with disease risk prediction of the patient, but the manual construction features are usually limited to professional experience of the doctor, and the patient cannot predict the disease risk by himself.
Disclosure of Invention
Aiming at the problems that the existing disease prediction method is mainly limited to the professional experience of doctors and the patients cannot predict the disease risk by themselves, the data processing method, the device, the computer equipment and the storage medium are provided, which aim to provide a prediction result with high reliability and accuracy for the patients and the doctors by combining the diagnosis data of historical patients.
In order to achieve the above object, the present invention provides a data processing method, comprising the steps of:
constructing a knowledge graph based on historical patient diagnostic data;
obtaining a first visit sequence for each historical patient in the knowledge-graph;
acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data;
matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnostic data of the historical patients matched with the second visit sequence;
classifying the second visit sequence using a classification model to obtain diagnosis probability data.
Preferably, the constructing a knowledge-map based on historical patient diagnostic data comprises:
performing entity identification and relationship extraction on the historical patient diagnosis data to construct a data set of entities and relationships;
carrying out format standardization processing on the data in the data set;
and importing the data set into a database, and constructing the knowledge graph according to the data attributes in the data set.
Preferably, the acquiring the first visit sequence of each historical patient in the knowledge-graph comprises:
obtaining a first visit vector for the historical patient;
stitching a plurality of first visit vectors of the same historical patient according to a visit time sequence to generate the first visit sequence.
Preferably, the acquiring a first visit vector of the historical patient includes:
and generating a first treatment vector of the historical patient according to the single treatment information of the historical patient corresponding to each node in the knowledge graph.
Preferably, the stitching a plurality of first visit vectors of the same historical patient according to the visit time sequence to generate a first visit sequence includes:
and splicing the first clinic vectors corresponding to each clinic information of the same historical patient according to the time sequence of the clinic to generate the first clinic sequence.
Preferably, the acquiring the diagnosis data of the target patient and generating the second visit sequence of the target patient according to the diagnosis data includes:
acquiring diagnostic data of a target patient;
inquiring nodes of the knowledge graph by adopting a node2vec algorithm according to the structure of the knowledge graph, and converting the diagnosis data of the target patient into a second diagnosis vector according to the attribute of the data corresponding to each node;
and generating the second visit sequence according to the second visit vector.
Preferably, matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnostic data of the historical patients matched with the second visit sequence comprises:
and calculating a distance value between the first clinic sequence and the second clinic sequence by adopting a sequence distance calculation algorithm according to the first clinic sequence of the historical patient and the second clinic sequence of the target patient, taking the historical patient corresponding to the distance value meeting preset conditions as the target historical patient, and acquiring the diagnosis data of the target patient.
In order to achieve the above object, the present invention also provides a data processing apparatus, comprising:
an acquisition unit for constructing a knowledge graph based on historical patient diagnostic data;
a first processing unit for obtaining a first visit sequence for each historical patient in the knowledge-graph;
the second processing unit is used for acquiring the diagnosis data of the target patient and generating a second visit sequence of the target patient according to the diagnosis data;
a matching unit for matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnostic data of the historical patients matched with the second visit sequence;
and the classification unit is used for classifying the second visit sequence by adopting a classification model so as to obtain diagnosis probability data.
To achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the above method.
According to the data processing method, the data processing device, the computer equipment and the storage medium, the knowledge graph can be constructed based on historical patient diagnosis data, and a first diagnosis sequence of each historical patient in the knowledge graph is obtained; acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data; by matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph, the diagnosis data of the historical patients matched with the second visit sequence, namely the diagnosis data of the historical patients with similar symptoms to the target patient, are obtained, so that the reliability and accuracy of the diagnosis data are improved, a treatment reference is provided for the target patient or a doctor, and the target patient can know the current situation more intuitively; and classifying the second visit sequence by adopting a classification model to acquire diagnosis probability data so as to provide medical reference for the target patient/doctor, and combining the diagnosis data and the diagnosis probability data obtained by matching to provide more reliable and accurate parameter data for the target patient/doctor.
It should be noted that: the main objective of the knowledge graph is to describe various entities and concepts existing in the real world and strong relationships between them, relationships can be used to describe the association between two entities, and the knowledge graph can be constructed and defined artificially to describe weak relationships between various concepts.
Drawings
FIG. 1 is a flow chart of an embodiment of a data processing method according to the present invention;
FIG. 2 is a flow chart of a method of one embodiment of constructing a knowledge graph based on historical patient diagnostic data in accordance with the present invention;
FIG. 3 is a flowchart of a method of one embodiment of the present invention for obtaining a first visit sequence for each of the historic patients in the knowledge-graph;
FIG. 4 is a flowchart of a method of another embodiment of the present invention for obtaining diagnostic data of a target patient and generating a second visit sequence for the target patient based on the diagnostic data;
FIG. 5 is a flowchart of a method of one embodiment of the present invention for matching the second visit sequence to the first visit sequence of all the historical patients in the knowledgemap to obtain diagnostic data for the historical patients that match the second visit sequence;
FIG. 6 is a block diagram of an embodiment of a data processing apparatus according to the present invention;
fig. 7 is a schematic hardware architecture diagram of an embodiment of a computer device according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
According to the data processing method, the data processing device, the computer equipment and the storage medium, the knowledge graph can be constructed based on historical patient diagnosis data, and a first diagnosis sequence of each historical patient in the knowledge graph is obtained; acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data; by matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph, the diagnosis data of the historical patients matched with the second visit sequence, namely the diagnosis data of the historical patients with similar symptoms to the target patient, are obtained, so that the reliability and accuracy of the diagnosis data are improved, a treatment reference is provided for the target patient or a doctor, and the target patient can know the current situation more intuitively; and classifying the second visit sequence by adopting a classification model to acquire diagnosis probability data so as to provide medical reference for the target patient/doctor, and combining the diagnosis data and the diagnosis probability data obtained by matching to provide more reliable and accurate parameter data for the target patient/doctor.
Example one
Referring to fig. 1, a data processing method of the present embodiment includes the following steps:
s1, constructing a knowledge graph based on historical patient diagnosis data;
in this step, the historical diagnosis data of the patient may include information of the name, department, symptom, cause, treatment method, drug name, prevention, etc. of the patient, and a knowledge base including the understanding of the patient and the diagnosis experience of the doctor is generated, and the knowledge base may include a triple structure of nodes, contents and relations, and may be roughly summarized as a component map of nodes and relations, which is very helpful for the analysis and research of the medical data.
Further, the step S1 may include the following steps:
s11, performing entity identification and relationship extraction on the historical patient diagnosis data to construct a data set of entities and relationships;
in this embodiment, the entity relationship extraction is an important task of information extraction, and is to extract a predefined entity relationship from an unstructured text based on entity identification, where an entity refers to something that is distinguishable and exists independently. Such as "Zhang three", "Li four", etc. of the patient. The entity is the most basic element in the knowledge graph, and different relationships exist among different entities. Each entity is a node, each visit of each historical patient can be an individual node, each node has diagnosis attribute information of a plurality of historical patients, including diagnosis information such as names, departments, symptoms, causes, complications, treatment, prevention and the like, and the diagnosis information is stored in the corresponding node of the entity in a long text form; in the knowledge-graph, the relationship is formalized as a function that maps nodes (entities) to attribute values, whereby the nodes of historical patients have a direct association with the attribute information of disease diagnosis, forming a data set of entities and relationships.
S12, carrying out format standardization processing on the data in the data set;
in this embodiment, since the relationship is a function for mapping a node (entity) to an attribute value, format standardization processing of data is required, including coding uniformity of an attribute information word and standardization processing of a separator of the word.
S13, importing the data set into a database, and constructing the knowledge graph according to data attributes in the data set;
in this embodiment, based on the historical patient diagnosis data, a semantic relationship between entities is established, and finally a knowledge graph is formed, and reference information for seeing a doctor can be provided for the patient through the knowledge graph, for example, two symptom words of "dizziness" and "nausea" are input into the patient, and the graph can display disease information related to the symptom.
S2, acquiring a first visit sequence of each historical patient in the knowledge graph;
in this step, in the knowledge graph, each node contains one-time visit attribute information of a historical patient, different nodes represent visit attribute information of different times of the historical patient, each node contains visit attribute information of the historical patient, the visit attribute information can be information of symptoms, causes, complications, treatment methods, prevention and the like, and the visit attribute information of one node forms a first visit vector of the historical patient. The plurality of first visit vectors of the historical patient are spliced to generate a first visit sequence of the historical patient.
By way of example and not limitation, for example, the node corresponding to the first visit attribute information of the historical patient "zhangsan" is a1, the first visit vector corresponding to the historical patient is N1, the node corresponding to the second visit attribute information of the historical patient "zhangsan" is a2, the visit vector corresponding to the historical patient is the first visit vector N2, and so on, and the different first visit vectors of the historical patient "zhangsan" are spliced to generate the first visit sequence of the historical patient "zhangsan". By generating the first visit sequence of the historical patients, the target patient can conveniently acquire the diagnosis information of the related diseases with reference values according to the diagnosis information of the target patient.
Further, the step S2 includes (shown with reference to fig. 3):
s21, acquiring a first visit vector of the historical patient;
in this embodiment, each node contains one-time visit attribute information of a historical patient, different nodes represent visit attribute information of different times of the historical patient, each node contains visit attribute information of the historical patient, the visit attribute information can be information of symptoms, causes, complications, treatment methods, prevention and the like, and the visit attribute information of one node forms a first visit vector of the historical patient.
S22, splicing a plurality of first clinic vectors of the same historical patient according to clinic time sequence to generate a first clinic sequence;
in this embodiment, each time the diagnosis information of the historical patient can be the first visit vector generated by the knowledge map, and it is assumed that the first visit information of the historical patient a is processed according to the knowledge map, and the generated first visit vector is X1Processing the second visit information of the historical patient A according to the knowledge graph to generate a first visit vector X2By analogy, the ith treatment information of the historical patient A is processed according to the knowledge graph, and a first treatment vector is generated to be Xi, wherein i represents the treatment times. Splicing the corresponding first treatment vectors according to each treatment time, thereby obtaining a first treatment sequence [ X ] of the historical patient A1，X2…,Xi,…]。
Further, the step S21 includes:
and generating a first treatment vector of the historical patient according to the single treatment information of the historical patient corresponding to each node in the knowledge graph.
In this embodiment, each node contains single-visit information of a historical patient, different nodes represent visit information of different times of the historical patient, each node contains visit attribute information of the historical patient, and the visit attribute information of one node forms a first visit vector of the historical patient. For example, the node corresponding to the first visit attribute information of the historical patient "zhangsan" is a1, the first visit vector corresponding to the historical patient is N1, and the first visit vector N1 includes the visit attribute information of the historical patient "zhangsan".
Further, the step S22 includes:
and splicing the first clinic vectors corresponding to each clinic information of the same historical patient according to the time sequence of the clinic to generate the first clinic sequence.
In the present embodiment, the number of visits of each historical patient is not necessarily the same, and therefore the length of the first visit sequence generated for the historical patients is not necessarily the same.
S3, acquiring diagnosis data of a target patient, and generating a second treatment sequence of the target patient according to the diagnosis data;
in this step, the target patient's diagnostic data includes electronic medical records as well as medical diagnostic records handwritten by the physician. It should be noted that the diagnostic data of the target patient, which is used to generate the second visit sequence of the target patient, is subjected to desensitization processing, so as to prevent disclosure of personal privacy and protect the personal privacy of the target patient.
Further, acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data, including:
s31, acquiring diagnosis data of a target patient;
in this embodiment, the diagnosis data of the target patient includes an electronic medical record and a handwritten diagnosis medical record of a doctor, and has no mandatory requirement on the form of the diagnosis data, and may be information such as characters, images, and charts, for example, specifically, all doctor diagnosis data such as various index data of blood routine, various index data of urine test, CT examination, and other medical image films may be included, and the diagnosis data of the target patient may be obtained.
S32, inquiring nodes of the knowledge graph by adopting a node2vec algorithm according to the structure of the knowledge graph, and converting the diagnosis data of the target patient into a second diagnosis vector according to the attribute of the data corresponding to each node;
in this embodiment, the node2vec algorithm is a graph embedding method, and relates to the attribute information of the target patient and the structural information of the knowledge graph, and maps the attribute information of the target patient into the second visit vector.
If the target patient has a plurality of treatment records (treatment attribute information), a plurality of second treatment vectors can be generated, and each treatment attribute information corresponds to one second treatment vector.
And S33, generating the second visit sequence according to the second visit vector.
In this embodiment, each diagnosis information of the target patient may be generated into a second diagnosis vector by the knowledge map, assuming that the first diagnosis vector of the target patient B is the first diagnosis vector of the target patient B according to the knowledge mapThe second visit information is processed to generate a second visit vector Y1Processing the second visit information of the target patient B according to the knowledge graph to generate a second visit vector Y2By analogy, the jth visit information of the target patient B is processed according to the knowledge graph, and a second visit vector Y is generatedjWherein j represents the number of visits. Splicing the corresponding second clinic vectors according to each clinic time, thereby obtaining a second clinic sequence [ Y ] of the target patient B1，Y2…,Yj,…]。
S4, matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph to acquire diagnosis data of the historical patients matched with the second visit sequence;
further, the step S4 includes:
s41, calculating a distance value between the first clinic sequence and the second clinic sequence according to the first clinic sequence of the historical patient and the second clinic sequence of the target patient by adopting a sequence distance calculation algorithm;
in this embodiment, due to the problem that it is difficult to calculate the distance between the first visit sequence and the second visit sequence due to the difference between the number of times of visits of the target patient and the number of times of visits of the historical patients, a method such as a dynamic planning algorithm and a clustering algorithm may be adopted to calculate the minimum distance between the second visit vector of the target patient and the first visit vectors of all the historical patients as the distance between the visit vectors of the target patient and the historical patients based on the idea of the dynamic planning algorithm.
And S42, taking the historical patient corresponding to the distance value meeting the preset condition as a target historical patient, and acquiring the diagnosis data of the target patient.
In this embodiment, since the first visit sequence of the historical patient may include a plurality of first visit vectors, and the second visit sequence of the current patient may also include a plurality of second visit vectors, a distance matrix may be obtained, a dynamic planning algorithm may be applied to find the diagnosis information of the TOP-K historical patient that has the most similar symptoms to the historical patient, and the disease of the target patient may be predicted based on the diagnosis information of the K historical patients, and may also serve as a reference for similar patients.
By way of example and not limitation, the diagnosis information of the first 10 historical patients with the most similar symptoms to the historical patients can be selected as the reference of similar patients, so that treatment reference can be provided for target patients or doctors, the reliability and accuracy of diagnosis data are improved, the target patients can know the current conditions more intuitively, medical accidents are reduced, convenient disease self-evaluation can be provided for the masses, and people can find the disease and make a positive diagnosis and treatment as soon as possible.
And S5, classifying the second visit sequence by adopting a classification model to obtain diagnosis probability data.
In this step, the classification model may adopt a Bi-Long-Short Term Memory (Bi-LSTM) model, which is a bidirectional Long-Short Memory network, and compared with a unidirectional LSTM, the Bi-LSTM can better capture context information in sentences, such as word form information of disease symptoms "dizziness", "fever", etc. of the target patient in the second visit sequence, or sentence form information of "intermittent cough of patient", etc., compared with the unidirectional LSTM, the Bi-LSTM can better capture context information in sentences for more accurate disease classification, so as to provide medical reference for the target patient/doctor, and the Bi-LSTM can provide more reliable and accurate parameter measurement data for the target patient/doctor in combination with the matched diagnosis data and the diagnosis probability data, although the Recurrent Neural Network (RNN) can theoretically provide context information, but when the context information is too long, the effect is too poor. The Bi-LSTM model can be put forward to well solve the problem, so that the recurrent neural network can have very good application results in practice. In addition, the classification model may be a model trained in advance, or may be a model continuously trained and updated in the classification process.
The invention is based on a data processing method, and can construct a knowledge graph based on historical patient diagnosis data, and acquire a first treatment sequence of each historical patient in the knowledge graph; acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data; by matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph, the diagnosis data of the historical patients matched with the second visit sequence, namely the diagnosis data of the historical patients with similar symptoms to the target patient, are obtained, so that the reliability and accuracy of the diagnosis data are improved, a treatment reference is provided for the target patient or a doctor, and the target patient can know the current situation more intuitively; and classifying the second visit sequence by adopting a classification model to acquire diagnosis probability data so as to provide medical reference for the target patient/doctor, and combining the diagnosis data and the diagnosis probability data obtained by matching to provide more reliable and accurate parameter data for the target patient/doctor.
Example two
Referring to fig. 6, a data processing apparatus 1 of the present embodiment includes: an obtaining unit 11, a first processing unit 12, a second processing unit 13, a matching unit 14 and a classifying unit 15, wherein:
an acquisition unit 11 for constructing a knowledge graph based on historical patient diagnostic data;
the historical diagnosis data of the patient can comprise information of the name, department, symptom, cause, treatment method, medicine, prevention and the like of the patient, a knowledge base comprising the understanding of human beings on diseases and the diagnosis experience of doctors is generated, and the knowledge base can comprise a node, content and relation triple structure and can be roughly summarized into a composition map of the node and the relation, so that the analysis and the research of medical data are facilitated. An entity refers to something that is distinguishable and exists independently. Such as "Zhang three", "Li four", etc. of the patient. The entity is the most basic element in the knowledge graph, and different relationships exist among different entities. Each entity is a node, each visit of each historical patient can be an individual node, each node has diagnosis attribute information of a plurality of historical patients, including diagnosis information such as names, departments, symptoms, causes, complications, treatment, prevention and the like, and the diagnosis information is stored in the corresponding node of the entity in a long text form; in a knowledge graph, a relationship is formalized as a function that maps nodes (entities) to attribute values.
By establishing semantic relations between entities based on the historical patient diagnosis data, and finally forming a knowledge graph, reference information of a doctor can be provided for a patient through the knowledge graph, for example, the patient inputs two symptom words of dizziness and nausea, and the graph can display disease information related to the symptom.
A first processing unit 12 for obtaining a first visit sequence for each historical patient in the knowledge-graph;
each node contains one-time visit attribute information of a historical patient, different nodes represent visit attribute information of different times of the historical patient, each node contains the visit attribute information of the historical patient, the visit attribute information can be information of symptoms, causes, complications, treatment methods, prevention and the like, and the visit attribute information of one node forms a first visit vector of the historical patient.
Stitching a plurality of first visit vectors of the same historical patient according to a visit time sequence to generate the first visit sequence.
The diagnosis information of the historical patient can be a first treatment vector generated by the knowledge map, and the first treatment vector generated by processing the first treatment information of the historical patient A according to the knowledge map is X1Processing the second visit information of the historical patient A according to the knowledge graph to generate a first visit vector X2By analogy, the ith treatment information of the historical patient A is processed according to the knowledge graph, and a first treatment vector is generated to be Xi, wherein i represents the treatment times. Splicing the corresponding first treatment vectors according to each treatment time, thereby obtaining a first treatment sequence [ X ] of the historical patient A1，X2…,Xi,…]。
The second processing unit 13 is configured to acquire diagnostic data of a target patient, and generate a second visit sequence of the target patient according to the diagnostic data;
the diagnosis data of the target patient comprises an electronic medical record and a diagnosis medical record handwritten by a doctor, has no mandatory requirement on the form of the diagnosis data, can be information such as characters, images, charts and the like, and can specifically comprise various index data of blood routine, index data of urine examination, and diagnosis data of all doctors such as CT examination and other medical image films and can be the diagnosis data of the target patient. It should be noted that the diagnostic data of the target patient, which is used to generate the second visit sequence of the target patient, is subjected to desensitization processing, so as to prevent disclosure of personal privacy and protect the personal privacy of the target patient.
Inquiring nodes of the knowledge graph by adopting a node2vec algorithm according to the structure of the knowledge graph, and converting the diagnosis data of the target patient into a second diagnosis vector according to the attribute of the data corresponding to each node;
generating the second treatment sequence according to the second treatment vector, wherein each time of diagnosis information of the target patient can generate a second treatment vector through a knowledge graph, and if the first treatment information of the target patient B is processed according to the knowledge graph, the generated second treatment vector is Y1Processing the second visit information of the target patient B according to the knowledge graph to generate a second visit vector Y2By analogy, the jth visit information of the target patient B is processed according to the knowledge graph, and a second visit vector Y is generatedjWherein j represents the number of visits. Splicing the corresponding second clinic vectors according to each clinic time, thereby obtaining a second clinic sequence [ Y ] of the target patient B1，Y2…,Yj,…]。
A matching unit 14 for matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnosis data of the historical patients matched with the second visit sequence;
the distance value between the first clinic sequence and the second clinic sequence can be calculated by adopting an algorithm for calculating the sequence distance according to the first clinic sequence of the historical patient and the second clinic sequence of the target patient, the historical patient corresponding to the distance value meeting the preset condition is taken as the target historical patient, the diagnosis data of the target patient is obtained, namely the diagnosis data of the historical patient with similar disease condition with the target patient is obtained, the reliability and the accuracy of the diagnosis data are improved, so that the target patient or a doctor can conveniently provide treatment reference, and the target patient can conveniently and visually know the current condition of the target patient.
A classification unit 15, configured to classify the second visit sequence by using a classification model to obtain diagnosis probability data;
the classification model can adopt a Bi-LSTM (Bi-Long-ShortTermMemory) model, the Bi-LSTM is a bidirectional Long-short memory network, the Bi-LSTM can better capture the context information in the sentence compared with the unidirectional LSTM and the Bi-LSTM can better capture the context information in the sentence compared with the unidirectional LSTM, the classification model is adopted to classify the second diagnosis sequence to obtain diagnosis probability data so as to provide medical reference for a target patient/doctor, and the diagnosis data and the diagnosis probability data obtained by matching can provide more reliable and accurate parameter data for the target patient/doctor, so that the presentation of the analysis result of the data is more visualized. In addition, the classification model may be a model trained in advance, or may be a model continuously trained and updated in the classification process.
The data processing device 1 provided by the invention can construct a knowledge map according to historical patient diagnosis data through the acquisition unit 11, and a first treatment sequence of each historical patient in the knowledge map is acquired through the first processing unit 12; acquiring diagnosis data of a target patient by using a second processing unit 13, and generating a second visit sequence of the target patient according to the diagnosis data; matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge graph through the matching unit 14 to obtain diagnosis data of the historical patients matched with the second visit sequence, namely the diagnosis data of the historical patients with similar symptoms to the target patient, so that the reliability and accuracy of the diagnosis data are improved, a treatment reference is provided for the target patient or a doctor, and the target patient can know the current situation more intuitively; the classification unit 15 is adopted to classify the second visit sequence based on the classification model to obtain diagnosis probability data so as to provide medical reference for the target patient/doctor, and more reliable and accurate parameter data can be provided for the target patient/doctor by combining the diagnosis data obtained by matching and the diagnosis probability data.
EXAMPLE III
In order to achieve the above object, the present invention further provides a computer device 2, where the computer device 2 includes a plurality of computer devices 2, components of the data processing apparatus 1 according to the second embodiment may be distributed in different computer devices 2, and the computer device 2 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster formed by a plurality of servers) that executes a program, or the like. The computer device 2 of the present embodiment includes at least, but is not limited to: a memory 21, a processor 23, a network interface 22 and a data processing apparatus 1 (refer to fig. 7) which are communicatively connected to each other through a system bus. It is noted that fig. 7 only shows the computer device 2 with components, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
In this embodiment, the memory 21 includes at least one type of computer-readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both an internal storage unit of the computer device 2 and an external storage device thereof. In this embodiment, the memory 21 is generally used for storing an operating system installed in the computer device 2 and various types of application software, such as a program code of the data processing method in the first embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 23 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data Processing chip in some embodiments. The processor 23 is typically used for controlling the overall operation of the computer device 2, such as performing control and processing related to data interaction or communication with the computer device 2. In this embodiment, the processor 23 is configured to run the program code stored in the memory 21 or process data, for example, run the data processing apparatus 1.
The network interface 22 may comprise a wireless network interface or a wired network interface, and the network interface 22 is typically used to establish a communication connection between the computer device 2 and other computer devices 2. For example, the network interface 22 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 7 only shows the computer device 2 with components 21-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the data processing apparatus 1 stored in the memory 21 may be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 23) to complete the present invention.
Example four
To achieve the above objects, the present invention also provides a computer-readable storage medium including a plurality of storage media such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by the processor 23, implements corresponding functions. The computer readable storage medium of the embodiment is used for storing a data processing apparatus 1, and when being executed by the processor 23, the data processing method of the first embodiment is realized.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A data processing method, comprising:
constructing a knowledge graph based on historical patient diagnostic data;
obtaining a first visit sequence for each historical patient in the knowledge-graph;
acquiring diagnosis data of a target patient, and generating a second visit sequence of the target patient according to the diagnosis data;
matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnostic data of the historical patients matched with the second visit sequence;
classifying the second visit sequence using a classification model to obtain diagnosis probability data.
2. The data processing method of claim 1, wherein constructing a knowledge-map based on historical patient diagnostic data comprises:
performing entity identification and relationship extraction on the historical patient diagnosis data to construct a data set of entities and relationships;
carrying out format standardization processing on the data in the data set;
and importing the data set into a database, and constructing the knowledge graph according to the data attributes in the data set.
3. The data processing method of claim 1, wherein obtaining a first visit sequence for each historic patient in the knowledge-graph comprises:
obtaining a first visit vector for the historical patient;
stitching a plurality of first visit vectors of the same historical patient according to a visit time sequence to generate the first visit sequence.
4. The data processing method of claim 3, wherein obtaining a first visit vector for the historical patient comprises:
and generating a first treatment vector of the historical patient according to the single treatment information of the historical patient corresponding to each node in the knowledge graph.
5. The data processing method of claim 3, wherein stitching a plurality of first visit vectors of the same historical patient in a visit time order to generate a first visit sequence comprises:
and splicing the first clinic vectors corresponding to each clinic information of the same historical patient according to the time sequence of the clinic to generate the first clinic sequence.
6. The data processing method of claim 1, wherein obtaining diagnostic data for a target patient, generating a second visit sequence for the target patient from the diagnostic data, comprises:
acquiring diagnostic data of a target patient;
inquiring nodes of the knowledge graph by adopting a node2vec algorithm according to the structure of the knowledge graph, and converting the diagnosis data of the target patient into a second diagnosis vector according to the attribute of the data corresponding to each node;
and generating the second visit sequence according to the second visit vector.
7. The data processing method of claim 1, wherein matching the second visit sequence with the first visit sequences of all the historical patients in the knowledgemap to obtain diagnostic data for the historical patients that match the second visit sequence comprises:
calculating a distance value between the first and second visit sequences according to the first visit sequence of the historical patient and the second visit sequence of the target patient by adopting a sequence distance calculation algorithm;
and taking the historical patient corresponding to the distance value meeting the preset condition as a target historical patient, and acquiring the diagnosis data of the target patient.
8. A data processing apparatus, comprising:
an acquisition unit for constructing a knowledge graph based on historical patient diagnostic data;
a first processing unit for obtaining a first visit sequence for each historical patient in the knowledge-graph;
the second processing unit is used for acquiring the diagnosis data of the target patient and generating a second visit sequence of the target patient according to the diagnosis data;
a matching unit for matching the second visit sequence with the first visit sequences of all the historical patients in the knowledge-graph to obtain diagnostic data of the historical patients matched with the second visit sequence;
and the classification unit is used for classifying the second visit sequence by adopting a classification model so as to obtain diagnosis probability data.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921656.2A CN112071425B (en) | 2020-09-04 | 2020-09-04 | Data processing method and device, computer equipment and storage medium |
| PCT/CN2020/134545 WO2021151351A1 (en) | 2020-09-04 | 2020-12-08 | Data processing method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921656.2A CN112071425B (en) | 2020-09-04 | 2020-09-04 | Data processing method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112071425A true CN112071425A (en) | 2020-12-11 |
| CN112071425B CN112071425B (en) | 2022-10-21 |
Family
ID=73666169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010921656.2A Active CN112071425B (en) | 2020-09-04 | 2020-09-04 | Data processing method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112071425B (en) |
| WO (1) | WO2021151351A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327691A (en) * | 2021-06-01 | 2021-08-31 | 平安科技（深圳）有限公司 | Query method and device based on language model, computer equipment and storage medium |
| CN113569293A (en) * | 2021-08-12 | 2021-10-29 | 明品云(北京)数据科技有限公司 | Similar user acquisition method, system, electronic device and medium |
| CN113782221A (en) * | 2021-09-16 | 2021-12-10 | 平安科技（深圳）有限公司 | Disease prediction device, equipment and storage medium based on self-training learning |
| CN113792344A (en) * | 2021-09-17 | 2021-12-14 | 平安国际智慧城市科技股份有限公司 | Data desensitization processing method, device, equipment and storage medium |
| CN114220548A (en) * | 2021-12-13 | 2022-03-22 | 山东畅想大数据服务有限公司 | Big data anonymous protection method and system serving digital medical treatment |
| WO2022206500A1 (en) * | 2021-03-29 | 2022-10-06 | 北京京东拓先科技有限公司 | Information pushing method and apparatus, and computer-readable storage medium |
| CN113792344B (en) * | 2021-09-17 | 2024-06-04 | 平安国际智慧城市科技股份有限公司 | Data desensitization processing method, device, equipment and storage medium |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628726B (en) * | 2021-08-10 | 2023-12-26 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine diagnosis and treatment recommendation system and method based on graph neural network and electronic equipment |
| CN113658655A (en) * | 2021-08-24 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Physical examination recommendation method and device, storage medium and equipment |
| CN113724831A (en) * | 2021-08-31 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medicine allocation method and device, terminal equipment and medium |
| CN114334145B (en) * | 2021-12-06 | 2023-06-30 | 中国医学科学院北京协和医院 | Dynamic identification method for atypical critical patients |
| CN115966292B (en) * | 2023-01-05 | 2023-09-15 | 江苏拜仁控股集团有限公司 | Intelligent hospital-based data automation management system and method |
| CN115762813B (en) * | 2023-01-09 | 2023-04-18 | 之江实验室 | Doctor-patient interaction method and system based on patient individual knowledge graph |
| CN116469532B (en) * | 2023-04-20 | 2023-11-03 | 荣科科技股份有限公司 | Intelligent hospital management method, system, computer equipment and storage medium |
| CN116737945B (en) * | 2023-05-10 | 2024-05-07 | 百洋智能科技集团股份有限公司 | Mapping method for EMR knowledge map of patient |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001069513A2 (en) * | 2000-03-10 | 2001-09-20 | David S Zakim | A system and method for obtaining, processing and evaluating patient information for diagnosing disease and selecting treatment |
| CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
| CN110189831A (en) * | 2019-06-06 | 2019-08-30 | 厦门大学 | A kind of case history knowledge mapping construction method and system based on dynamic diagram sequences |
| CN110335676A (en) * | 2019-07-09 | 2019-10-15 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111430037A (en) * | 2020-03-30 | 2020-07-17 | 安徽科大讯飞医疗信息技术有限公司 | Similar medical record searching method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3296903A1 (en) * | 2016-09-20 | 2018-03-21 | Fujitsu Limited | Method and apparatus for discovering a sequence of events forming an episode in a set of medical records from a patient |
| CN110162638B (en) * | 2019-04-12 | 2023-06-20 | 淮阴工学院 | Expert combination recommendation method based on graph vectors |
| CN110297908B (en) * | 2019-07-01 | 2021-09-21 | 中国医学科学院医学信息研究所 | Diagnosis and treatment scheme prediction method and device |
| CN110459320B (en) * | 2019-08-20 | 2021-01-05 | 山东众阳健康科技集团有限公司 | Knowledge graph-based auxiliary diagnosis and treatment system |
-
2020
- 2020-09-04 CN CN202010921656.2A patent/CN112071425B/en active Active
- 2020-12-08 WO PCT/CN2020/134545 patent/WO2021151351A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001069513A2 (en) * | 2000-03-10 | 2001-09-20 | David S Zakim | A system and method for obtaining, processing and evaluating patient information for diagnosing disease and selecting treatment |
| CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
| CN110189831A (en) * | 2019-06-06 | 2019-08-30 | 厦门大学 | A kind of case history knowledge mapping construction method and system based on dynamic diagram sequences |
| CN110335676A (en) * | 2019-07-09 | 2019-10-15 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111430037A (en) * | 2020-03-30 | 2020-07-17 | 安徽科大讯飞医疗信息技术有限公司 | Similar medical record searching method and system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022206500A1 (en) * | 2021-03-29 | 2022-10-06 | 北京京东拓先科技有限公司 | Information pushing method and apparatus, and computer-readable storage medium |
| CN113327691A (en) * | 2021-06-01 | 2021-08-31 | 平安科技（深圳）有限公司 | Query method and device based on language model, computer equipment and storage medium |
| CN113327691B (en) * | 2021-06-01 | 2022-08-12 | 平安科技（深圳）有限公司 | Query method and device based on language model, computer equipment and storage medium |
| CN113569293A (en) * | 2021-08-12 | 2021-10-29 | 明品云(北京)数据科技有限公司 | Similar user acquisition method, system, electronic device and medium |
| CN113569293B (en) * | 2021-08-12 | 2024-06-07 | 明品云(北京)数据科技有限公司 | Similar user acquisition method, system, electronic equipment and medium |
| CN113782221A (en) * | 2021-09-16 | 2021-12-10 | 平安科技（深圳）有限公司 | Disease prediction device, equipment and storage medium based on self-training learning |
| CN113792344A (en) * | 2021-09-17 | 2021-12-14 | 平安国际智慧城市科技股份有限公司 | Data desensitization processing method, device, equipment and storage medium |
| CN113792344B (en) * | 2021-09-17 | 2024-06-04 | 平安国际智慧城市科技股份有限公司 | Data desensitization processing method, device, equipment and storage medium |
| CN114220548A (en) * | 2021-12-13 | 2022-03-22 | 山东畅想大数据服务有限公司 | Big data anonymous protection method and system serving digital medical treatment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021151351A1 (en) | 2021-08-05 |
| CN112071425B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112071425B (en) | Data processing method and device, computer equipment and storage medium | |
| CN111863267B (en) | Data information acquisition method, data analysis method, device and storage medium | |
| US11881293B2 (en) | Methods for automatic cohort selection in epidemiologic studies and clinical trials | |
| US8214224B2 (en) | Patient data mining for quality adherence | |
| US20170300635A1 (en) | Identification of codable sections in medical documents | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| CN110291555B (en) | Systems and methods for facilitating computational analysis of health conditions | |
| CN112035674B (en) | Diagnosis guiding data acquisition method, device, computer equipment and storage medium | |
| WO2019070200A1 (en) | A healthcare information management system | |
| US20230386670A1 (en) | Method and system for recommending treatment plans, preventive actions, and preparedness actions | |
| US20220044809A1 (en) | Systems and methods for using deep learning to generate acuity scores for critically ill or injured patients | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN111144658B (en) | Medical risk prediction method, device, system, storage medium and electronic equipment | |
| US20170052943A1 (en) | Method, apparatus, and computer program product for generating a preview of an electronic document | |
| CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
| CN114550859A (en) | Single disease quality monitoring method, system, equipment and storage medium | |
| CN114220541A (en) | Disease prediction method, disease prediction device, electronic device, and storage medium | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| US20180349558A1 (en) | Systems and methods for autonomous discharge queue management | |
| CN113160914A (en) | Online inquiry method and device, electronic equipment and storage medium | |
| CN116798584A (en) | Diagnosis guiding method and device and electronic equipment | |
| CN108154919B (en) | Hospital department information processing method and system | |
| CN112908488B (en) | Event recognition method and device, computer equipment and storage medium | |
| CN114664458A (en) | Patient classification device, computer device and storage medium | |
| CN114743660A (en) | Clinical path maintenance method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40043403 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |