CN113160999B - Data structured analysis system and data processing method for medical decision - Google Patents
Data structured analysis system and data processing method for medical decision Download PDFInfo
- Publication number
- CN113160999B CN113160999B CN202110448445.6A CN202110448445A CN113160999B CN 113160999 B CN113160999 B CN 113160999B CN 202110448445 A CN202110448445 A CN 202110448445A CN 113160999 B CN113160999 B CN 113160999B
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- decision
- subsystem
- desensitization
- 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
- G16H50/70—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a data structured analysis system and a data processing method for medical decision. The system comprises a data access subsystem, a data classification subsystem, a data desensitization subsystem, a data selection subsystem and a decision-making subsystem; the data access subsystem acquires medical data uploaded or acquired by a data source terminal in real time; the data classification subsystem receives the medical data sent by the data access subsystem and classifies the medical data; a data desensitization subsystem performs desensitization processing on the classified medical data; the decision subsystem is used for setting a medical decision target. The method comprises the steps of displaying a plurality of goal decision options, displaying at least one medical decision goal, generating a data selection instruction, a first data classification instruction, a second data desensitization instruction, outputting a medical decision result and the like. According to the technical scheme, targeted data can be acquired from massive medical big data according to the medical decision target to execute medical decision.
Description
Technical Field
The invention belongs to the technical field of medical decision, and particularly relates to a data structured analysis system for medical decision, a data processing method and a computer program instruction medium for realizing the method.
Background
With the development and application of cloud computing, internet of things, virtualization technologies and internet technologies, artificial intelligence technologies are gradually introduced into the medical field. Hospitals gradually build population health information integration platforms and clinical data centers with electronic medical records as a core in order to better serve patients, medical care personnel and medical management personnel. Aiming at generating tens of thousands of medical data in the medical process, the massive medical health unstructured data contains information with various values.
Through scientific, normative, synchronous and dynamic analysis on massive medical structure data and unstructured data, the due value of the medical structure data and unstructured data can be better exerted, and evidence support is provided for clinical medical decision management, medical insurance payment decision making and government health policy making.
With the rapid development of information technology and the establishment of various data standardization methods. The problem that massive and unstructured data which troubles the medical industry for a long time cannot be effectively integrated and analyzed is solved, so that a reliable method and a reliable foundation are also provided for establishing a high-quality medical large database, accumulated massive medical structural data, unstructured data and historical data can be sufficiently analyzed, and greater clinical guidance and evidence-based decision making values are exerted.
However, practice proves that effective medical structure data analysis needs to be established on the basis of establishment of a high-quality medical structure data big database and a strict scientific analysis method, otherwise analysis and decision of the medical structure data are difficult to avoid interference of various confounding factors.
Disclosure of Invention
In order to solve the technical problems, the invention provides a data structured analysis system and a data processing method for medical decision.
The system comprises a data access subsystem, a data classification subsystem, a data desensitization subsystem, a data selection subsystem and a decision-making subsystem; the data access subsystem acquires medical data uploaded or acquired by a data source terminal in real time; the data classification subsystem receives the medical data sent by the data access subsystem and classifies the medical data; a data desensitization subsystem performs desensitization processing on the classified medical data; the decision subsystem is used for setting a medical decision target.
The method comprises the steps of displaying a plurality of goal decision options, displaying at least one medical decision goal, generating a data selection instruction, a first data classification instruction, a second data desensitization instruction, outputting a medical decision result and the like.
Specifically, the technical scheme of the invention comprises the following three aspects:
in a first aspect of the invention, there is provided a data structured analysis system for medical decision-making, the system comprising a data access subsystem, a data classification subsystem, a data desensitization subsystem, a data selection subsystem and a decision-making subsystem;
the data access subsystem is communicated with a plurality of data source terminals and is used for acquiring medical data uploaded or acquired by the data source terminals in real time;
the data classification subsystem receives the medical data sent by the data access subsystem and classifies the medical data;
the data desensitization subsystem performs desensitization processing on the classified medical data;
the decision subsystem is used for setting a medical decision target;
the data selection subsystem generates a data selection instruction based on a medical decision target set by the decision subsystem;
generating a first data classification instruction based on the data selection instruction, the data classification subsystem performing classification on the medical data based on the first data classification instruction;
and generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction, wherein the data desensitization subsystem executes desensitization processing on the classified medical data based on the second data desensitization instruction.
The decision subsystem comprises a human-machine interaction interface which provides a plurality of selectable goal decision options;
in response to a user-selected goal decision option, the decision subsystem recommends at least one medical decision goal.
In a second aspect of the invention, a data processing method for medical decision is provided, wherein the data processing method is realized based on a data structured analysis system comprising a human-machine touch interaction interface.
Specifically, the method comprises the following steps:
s810: displaying a plurality of target decision options in a first display area of the human-computer touch interaction interface;
s820: in response to a touch interaction selection input of a user, displaying at least one medical decision target in a second display area of the human-computer touch interaction interface;
s830: generating a data selection instruction based on the at least one medical decision goal;
s840: generating a first data classification instruction based on the data selection instruction;
s850: generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction;
s860: classifying medical data to be processed based on the first data classification instruction;
s870: performing desensitization processing on the classified medical data based on the second data desensitization instruction;
s880: inputting the medical data after desensitization treatment into a medical decision model, and outputting a medical decision result;
wherein the medical decision model is conditioned on the at least one medical decision target.
The above method of the present invention can be automatically executed by program instructions through a terminal device comprising a processor and a memory, especially an image processing terminal device, including a mobile terminal, a desktop terminal, a server cluster, and the like, and therefore, in a third aspect of the present invention, there is also provided a computer-readable storage medium having computer program instructions stored thereon; the program instructions are executed by an image terminal processing device comprising a processor and a memory for implementing all or part of the steps of the method of the second aspect.
Generally speaking, the technical scheme of the invention can acquire targeted data from massive medical big data according to the medical decision target to execute medical decision.
Further advantages of the invention will be apparent in the detailed description section in conjunction with the drawings attached hereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a block diagram of a subsystem of a data structured analysis system for medical decision making, in accordance with one embodiment of the present invention
FIG. 2 is a schematic diagram of data acquisition and data classification models of the data access subsystem of the system of FIG. 1
FIG. 3 is a schematic diagram of a source of unstructured medical data acquired by a mobile terminal in the system of FIG. 1
FIG. 4 is a schematic diagram of a display of a human-machine interface of a decision making subsystem of the system of FIG. 1
FIG. 5 is a main flow chart of a data processing method for medical decision making according to an embodiment of the present invention
FIG. 6 is a data source diagram of a medical data corpus of a data structured analysis system implementing the method of FIG. 5
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
Referring to fig. 1, a block diagram of a subsystem of a data structured analysis system for medical decision making according to an embodiment of the present invention is shown.
In fig. 1, the data structured analysis system for medical decision-making comprises a data access subsystem, a data classification subsystem, a data desensitization subsystem, a data selection subsystem and a decision-making subsystem.
By way of a general and restrictive introduction, in the embodiment of fig. 1, the data access subsystem is a relatively independent working subsystem whose working state is not affected by other working subsystems; in other words, the data access subsystem is an independently working subsystem, and the subsystem is communicated with a plurality of data source terminals, acquires medical data uploaded or acquired by the data source terminals in real time and stores the medical data into a medical data aggregation library;
correspondingly, various selectable working states exist in the data classification subsystem, the data desensitization subsystem and the data selection subsystem, and the specific selection of which working state is determined based on the decision subsystem.
Specifically, the data classification subsystem classifies the medical data after receiving the medical data sent by the data access subsystem.
The data classification subsystem is internally provided with a plurality of data classification models, and each data classification model corresponds to different medical data classification outputs.
Different data classification models can adopt different data classification standards to classify the medical data.
As non-limiting examples, the medical data may be classified according to the medical data source, for example, into mobile terminal data and desktop terminal data; the medical data can be classified according to the age range corresponding to the medical data, such as medical data of infants, medical data of teenagers, medical data of middle-aged people and medical data of old people; the medical data can be classified according to the types of the medicines, such as first medicine type medical data and second medicine type medical data, wherein the first medicine type medical data comprises clinical treatment cost, clinical treatment cycle, clinical treatment effect and the like of the first medicine; the second medicine type medical data comprises the clinical treatment cost, the clinical treatment period, the clinical treatment effect and the like of the second medicine;
a data desensitization subsystem is used to perform data desensitization operations on the medical data.
Data desensitization, also known as data anonymization operations. Generally, in order to protect data privacy, after obtaining big data medical data, data anonymization operations, such as removing patient names therein, etc., are generally required before data mining and data decision making.
In the technical scheme of the invention, the data desensitization operation is to selectively perform more data desensitization according to the subsequent medical decision requirement on the basis of the conventional anonymization operation (removing the name of a patient therein).
In particular, the data desensitization subsystem includes a plurality of selectable desensitization parameters. Desensitization parameters comprise operations of age desensitization, gender desensitization, address desensitization, drug name desensitization, treatment disease desensitization, data source desensitization and the like.
If age desensitization is selected, the method means that the age description field in the classified medical data is removed, so that the desensitized data does not contain any age field, that is, medical decision cannot be performed on the age factor, or the influence of the age factor on a medical decision target is avoided;
if gender desensitization is selected, the gender description field in the medical data after classification is removed, so that the medical decision cannot be executed aiming at gender factors without the gender description field in the medical data after the desensitization, or the influence of the gender factors on a medical decision target is avoided;
if address desensitization is selected, the classified medical data is removed of the address description field, so that the desensitized data does not contain any address field, that is, medical decision cannot be executed aiming at address factors, or the influence of the address factors on a medical decision target is avoided;
if the drug name is selected for desensitization, the medical decision making method means that the drug name description fields in the classified medical data are removed, so that the desensitized data do not contain any drug name fields, that is, medical decision can not be executed according to the drug name factors, or the influence of the drug name factors on a medical decision making target is avoided;
if the treatment disease desensitization is selected, the classified medical data is removed from the treatment disease description field, so that the desensitized data does not contain any treatment disease field, that is, the medical decision cannot be executed for the treatment disease factors, or the influence of the treatment disease factors on the medical decision target is avoided;
if data source desensitization is selected, the data source description field in the classified medical data is removed, so that the desensitized data does not contain any data source field, that is, medical decision cannot be performed on data source factors, or the influence of the data source factors on a medical decision target is avoided.
Of course, it is particularly noted that regardless of which desensitization parameter option is implemented, name/name desensitization is the default mandatory option in various embodiments of the present invention.
As a controlling working subsystem, the working states of the data classification subsystem, the data desensitization subsystem and the data selection subsystem are determined based on the setting of the decision-making subsystem.
In particular, the decision subsystem is used to set a medical decision goal;
the data selection subsystem generates a data selection instruction based on a medical decision target set by the decision subsystem;
generating a first data classification instruction based on the data selection instruction, the data classification subsystem performing classification on the medical data based on the first data classification instruction;
and generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction, wherein the data desensitization subsystem executes desensitization processing on the classified medical data based on the second data desensitization instruction.
As a non-limiting example, the medical decision goal may be to analyze clinical medical data from the mobile terminal regarding the first drug and the second drug for the same medical condition for selecting whether to include the first drug or the second drug in an reimbursement inventory, or a reimbursement ratio of the first drug and the second drug, when formulating a medical insurance reimbursement policy.
Based on the medical decision-making goal, the corresponding data selection instruction is to select the medical data from the mobile terminal related to the first medicine and the second medicine.
Generating a first data classification instruction based on the data selection instruction, the data classification subsystem performing classification on the medical data based on the first data classification instruction
At this time, the first data sorting instruction causes the data sorting subsystem to perform at least two operations:
a first operation: screening out unstructured medical data acquired from a mobile terminal from the medical data aggregation library connected with the data access subsystem;
a second operation: and performing data structuring operation on the unstructured medical data acquired by the mobile terminal according to the correlation attributes of the first medicine and the second medicine, and at least dividing the unstructured medical data into first medicine mobile medical data and second medicine mobile medical data.
Next, based on the data selection instruction and the first data classification instruction, a second data desensitization instruction is generated, and the data desensitization subsystem performs desensitization processing on the classified medical data based on the second data desensitization instruction.
At this point, the second data desensitization instruction causes the data desensitization subsystem to perform at least the following:
the second data desensitization instruction corresponds to a plurality of desensitization parameters.
In the above example (the medical decision goal is to analyze clinical medical data from the mobile terminal regarding the first drug and the second drug for the same medical condition for selecting whether to include the first drug or the second drug in the reimbursement inventory, or the reimbursement ratio of the two, when formulating the medical insurance reimbursement policy), the desensitization parameters herein include at least: age desensitization, gender desensitization, address desensitization, and desensitization parameters which should not be performed are drug name desensitization, treatment disease desensitization, data source desensitization, and the like.
Next, the data desensitization subsystem performs desensitization processing on the classified medical data based on the second data desensitization instruction, including: age desensitization, gender desensitization, address desensitization.
Removing the age description field from the classified medical data, so that the desensitized data does not contain any age field, that is, medical decision cannot be performed according to age factors, or the influence of the age factors on a medical decision target is avoided;
removing the gender description field from the classified medical data, so that the desensitized data does not contain any gender field, that is, medical decision cannot be performed aiming at gender factors, or the influence of gender factors on a medical decision target is avoided;
and removing the address description field from the classified medical data, so that the desensitized data does not contain any address field, that is, medical decision cannot be performed aiming at the address factors, or the influence of the address factors on a medical decision target is avoided.
On the basis of fig. 1, see fig. 2. Fig. 2 is a schematic diagram of the data access subsystem acquiring data and a data classification model of the system of fig. 1.
The data access subsystem is communicated with a plurality of data source terminals, and is used for acquiring medical data uploaded or acquired by the data source terminals in real time and sending the medical data to the data classification subsystem.
In fig. 2, the plurality of data source terminals include a mobile terminal and a desktop terminal; the data access subsystem acquires the structured medical data uploaded by the desktop terminal in real time; and the data access subsystem acquires the unstructured medical data acquired by the mobile terminal in real time.
A plurality of data classification models are arranged in the data classification subsystem, and each data classification model corresponds to different medical data classification outputs;
based on the first data classification instructions, the data classification subsystem matches out at least one first data classification model;
and taking the medical data as the input of the at least one first data classification model matched by the data classification subsystem, and taking the output of the first data classification model as the classification result of the medical data.
In fig. 2, the data classification subsystem is internally provided with a data classification model a, a data classification model B, and a data classification model C.
Continuing with the above example (the medical decision objective is to analyze clinical medical data from the mobile terminal about the first drug and the second drug for the same disease, so as to select whether to include the first drug or the second drug in the reimbursement catalog or the reimbursement proportion of the first drug and the second drug when formulating the medical insurance reimbursement policy), the data classification model a may be a model for distinguishing a mobile data source from a desktop data source, and may output mobile medical data; the data classification model B can be a model for distinguishing different medicine class data, and can output the classified first medicine class medical data and second medicine class medical data.
Fig. 3 is a schematic diagram of a source of unstructured medical data acquired by a mobile terminal in the system of fig. 1.
Under the normal condition, the desktop terminal is configured with professional data acquisition software or an interface, and data can be input and acquired according to a standard mode, so that structured data can be generated easily; the mobile terminal can input or upload data at any time and any place, but the data structure is not specified, the format is random, and generally, unstructured data which cannot be directly used are obtained.
FIG. 3 illustrates a conventional source of such unstructured data, including:
auscultation data of doctors, dictation medical advice and telephone consultation;
temporary field data transmitted by an ambulance (mobile terminal vehicle);
temporary medical or clinical data generated by the portable terminal;
the data may relate to various physiological medical indicators, including electroencephalogram, vision, hearing, blood pressure, blood sugar, gene detection, protein assay, mycin level, status monitoring parameters of the implant, and the like, and also include corresponding positioning system data, and the data transmission network includes a telephone, a mobile phone and a WiFi network.
Referring next to fig. 4, fig. 4 is a schematic diagram of a display of a human-computer interface of a decision making subsystem of the system of fig. 1.
In FIG. 4, the decision subsystem includes a human-machine interface that provides a plurality of selectable goal decision options;
in response to a user-selected goal decision option, the decision subsystem recommends at least one medical decision goal.
More specifically, the human-computer interaction interface is a touch human-computer interaction interface, and comprises at least two display areas, namely a first display area and a second display area.
Displaying a plurality of goal decision options on the first display area;
displaying a medical decision goal in the second display area based on a user selection of the goal decision option.
Continuing with the above example (where the medical decision goal is to analyze clinical medical data from the mobile terminal regarding the first drug and the second drug for the same medical condition for selecting whether to include the first drug or the second drug in the reimbursement inventory, or a reimbursement ratio of the first drug and the second drug in formulating a medical insurance reimbursement policy), the goal decision options may include: data source option, medicine name option, disease condition option corresponding to the medicine, and analysis target option of the medicine;
the medical decision goals may include: clinical cost, clinical effect, age group drug advantage analysis and the like.
Preferably, the plurality of selectable goal decision options are associated with categories of the medical data.
Preferably, the plurality of selectable goal decision options are associated with a category of a plurality of selectable desensitization parameters of the data desensitization subsystem.
On the basis of fig. 1-4, fig. 5 is a main flow chart of a data processing method for medical decision making according to an embodiment of the present invention.
The method shown in fig. 5 is implemented based on a data structured analysis system including a human-computer touch interaction interface, and includes the main steps of S810 to S880, where each step is implemented specifically as follows:
s810: displaying a plurality of target decision options in a first display area of the man-machine touch interaction interface;
s820: in response to a touch interaction selection input of a user, displaying at least one medical decision target in a second display area of the human-computer touch interaction interface;
s830: generating a data selection instruction based on the at least one medical decision goal;
s840: generating a first data classification instruction based on the data selection instruction;
s850: generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction;
s860: classifying medical data to be processed based on the first data classification instruction;
s870: performing desensitization processing on the classified medical data based on the second data desensitization instruction;
s880: inputting the medical data after desensitization treatment into a medical decision model, and outputting a medical decision result;
wherein the medical decision model is conditioned on the at least one medical decision target.
The decision model can be various existing data decision models in the prior art, including a deep learning-based neural network model, a deep belief network model and the like, and the invention does not specifically develop the decision model. Preferably, the present invention may employ a clinical assistance data decision system, and similar prior art teachings may be found in the following documents:
[1]Sohail MN,Ren J,Uba Muhammad M A.Euclidean Group Assessment on Semi-Supervised Clustering for Healthcare Clinical Implications Based on eal-Life Data[J].Int J Environ Res Public Health,2019,16(9):E1581.
[2]Berger ML,Dreyer N,Anderson F,et al.Prospective Observational Studies to Assess Comparative Effectiveness:The ISPOR Good Research Practices Task Force Report[J].Value Health,2012,15(2):217-230.
it is understood that the method described in fig. 5 can be implemented based on the systems described in fig. 1-4, and corresponding steps can implement corresponding functional options of the systems described in fig. 1-4, which are not repeated herein for brevity, and specific examples can refer to the examples described in the embodiments of fig. 1-4.
Further, referring to fig. 6, fig. 6 is a schematic data source diagram of a medical data collection library of a data structured analysis system implementing the method of fig. 5.
The data structured analysis system is also connected with a medical data aggregation library;
the medical data collection library is used for collecting medical data generated by the multi-source data terminal;
the data selection instructions are for selecting a portion of medical data from the medical data corpus. The first data classification instruction is used for setting classification standards of the medical data;
the second data desensitization instruction is for setting a desensitization parameter of the medical data.
Similar to the aforementioned fig. 1-4, in fig. 5 or fig. 6, the medical data aggregation library connected to the data structured analysis system including the human-machine touch interaction interface continuously aggregates massive medical data from multiple data terminals in real time through multiple communication networks, including small and medium hospitals, large hospitals, doctor individuals, patient individuals, home remote medical systems, medical nursing place systems, research institutions, and the like, and sends the aggregated medical data to the medical data aggregation library for storage for subsequent analysis.
After the classification criteria and desensitization parameters are determined based on the selected decision analysis objective, the aforementioned data structured analysis and data processing procedures are executed, which refer to the foregoing embodiments specifically.
According to the technical scheme, after the decision target is set for massive medical data, the corresponding classification model and desensitization means are selected to obtain targeted sample data, so that the attribute of the data input into the decision model is closely related to the decision target, the influence of the irrelevant attribute is eliminated, and the efficiency and accuracy of medical decision are greatly improved.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A data structured analysis system for medical decision making, characterized by: the system comprises a data access subsystem, a data classification subsystem, a data desensitization subsystem, a data selection subsystem and a decision-making subsystem;
the data access subsystem is communicated with a plurality of data source terminals and is used for acquiring medical data uploaded or acquired by the data source terminals in real time;
the data classification subsystem receives the medical data sent by the data access subsystem and classifies the medical data;
the data desensitization subsystem performs desensitization processing on the classified medical data, the data desensitization subsystem including a plurality of selectable desensitization parameters;
the decision subsystem is used for setting a medical decision target and providing a plurality of selectable target decision options;
the plurality of selectable goal decision options are associated with a category of the medical data;
the plurality of selectable goal decision options are associated with categories of a plurality of selectable desensitization parameters of the data desensitization subsystem;
the data selection subsystem generates a data selection instruction based on a medical decision target set by the decision subsystem, and the data selection instruction is used for selecting partial medical data from the medical data aggregation library;
generating a first data classification instruction based on the data selection instruction, wherein the data classification subsystem performs classification on the medical data based on the first data classification instruction, and the first data classification instruction is used for setting classification standards of the medical data;
a plurality of data classification models are arranged in the data classification subsystem, and each data classification model corresponds to different medical data classification outputs;
based on the first data classification instruction, the data classification subsystem matches out at least one first data classification model;
using the medical data as an input to the at least one first data classification model matched out by the data classification subsystem; outputting the first data classification model as a classification result of classifying the medical data;
generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction;
the second data desensitization instruction corresponds to at least one desensitization parameter;
the data desensitization subsystem performs desensitization processing on the classified medical data based on the second data desensitization instruction.
2. A data structured analysis system for medical decision making as claimed in claim 1 wherein:
the plurality of data source terminals comprise a mobile terminal and a desktop terminal;
the data access subsystem acquires the structured medical data uploaded by the desktop terminal in real time;
and the data access subsystem acquires the unstructured medical data acquired by the mobile terminal in real time.
3. A data structured analysis system for medical decision making as claimed in claim 1 wherein:
the decision subsystem comprises a human-computer interaction interface, and the human-computer interaction interface provides a plurality of selectable target decision options;
in response to a user-selected goal decision option, the decision subsystem recommends at least one medical decision goal.
4. A data processing method for medical decision, which is implemented based on the data structured analysis system for medical decision as claimed in any one of claims 1 to 3, the data structured analysis system for medical decision comprises a human-machine touch interactive interface,
characterized in that the method comprises the following steps:
s810: displaying a plurality of target decision options in a first display area of the man-machine touch interaction interface;
s820: in response to a touch interaction selection input of a user, displaying at least one medical decision target in a second display area of the human-computer touch interaction interface;
s830: generating a data selection instruction based on the at least one medical decision goal;
s840: generating a first data classification instruction based on the data selection instruction;
s850: generating a second data desensitization instruction based on the data selection instruction and the first data classification instruction;
s860: classifying medical data to be processed based on the first data classification instruction;
s870: performing desensitization processing on the classified medical data based on the second data desensitization instruction;
s880: inputting the medical data after desensitization treatment into a medical decision model, and outputting a medical decision result;
wherein the medical decision model is conditioned on the at least one medical decision target;
the first data classification instruction is used for setting classification standards of the medical data;
the second data desensitization instruction is for setting a desensitization parameter of the medical data.
5. A data processing method for medical decision-making according to claim 4, characterized in that:
the data structured analysis system is also connected with a medical data aggregation library;
the medical data collection library is used for collecting medical data generated by the multi-source data terminal;
the data selection instructions are for selecting a portion of medical data from the medical data corpus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448445.6A CN113160999B (en) | 2021-04-25 | 2021-04-25 | Data structured analysis system and data processing method for medical decision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448445.6A CN113160999B (en) | 2021-04-25 | 2021-04-25 | Data structured analysis system and data processing method for medical decision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113160999A CN113160999A (en) | 2021-07-23 |
| CN113160999B true CN113160999B (en) | 2022-09-16 |
Family
ID=76870257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110448445.6A Active CN113160999B (en) | 2021-04-25 | 2021-04-25 | Data structured analysis system and data processing method for medical decision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160999B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN114067947A (en) * | 2021-11-18 | 2022-02-18 | 杨成兴 | Cloud data case and transmission system based on data sharing and information intercommunication |
| WO2024042348A1 (en) * | 2022-08-24 | 2024-02-29 | Evyd科技有限公司 | English medical text structurization method, apparatus, medium and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815736A (en) * | 2019-01-24 | 2019-05-28 | 深圳昂楷科技有限公司 | A kind of database desensitization method, device and desensitization equipment |
| CN109885597A (en) * | 2019-01-07 | 2019-06-14 | 平安科技（深圳）有限公司 | Tenant group processing method, device and electric terminal based on machine learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180211007A1 (en) * | 2017-01-25 | 2018-07-26 | International Business Machines Corporation | Assist Selection of Provider/Facility for Surgical Procedures Based on Frequency of Procedure, History of Complications, and Cost |
| CN109583226A (en) * | 2018-10-26 | 2019-04-05 | 平安科技（深圳）有限公司 | Data desensitization process method, apparatus and electronic equipment |
| CN109830303A (en) * | 2019-02-01 | 2019-05-31 | 上海众恒信息产业股份有限公司 | Clinical data mining analysis and aid decision-making method based on internet integration medical platform |
| CN112231747A (en) * | 2020-09-25 | 2021-01-15 | 中国建设银行股份有限公司 | Data desensitization method, data desensitization apparatus, and computer readable medium |
-
2021
- 2021-04-25 CN CN202110448445.6A patent/CN113160999B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109885597A (en) * | 2019-01-07 | 2019-06-14 | 平安科技（深圳）有限公司 | Tenant group processing method, device and electric terminal based on machine learning |
| CN109815736A (en) * | 2019-01-24 | 2019-05-28 | 深圳昂楷科技有限公司 | A kind of database desensitization method, device and desensitization equipment |
Non-Patent Citations (1)
| Title |
|---|
| 数据脱敏全生命周期过程研究;叶水勇;《电力与能源》;20191228(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113160999A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113160999B (en) | Data structured analysis system and data processing method for medical decision | |
| CN111599488A (en) | Intelligent inquiry implementing method, system and storage medium | |
| WO2020037454A1 (en) | Smart auxiliary diagnosis and treatment system and method | |
| US11450434B2 (en) | Implementation of machine-learning based query construction and pattern identification through visualization in user interfaces | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| KR20210056598A (en) | Method and system for providing medical data collection and analyzing service based on machine learning | |
| CN110827994A (en) | Myocardial infarction early warning method, device and equipment and storage medium | |
| CN112562808B (en) | Patient portrait generation method, apparatus, electronic device and storage medium | |
| WO2021148967A1 (en) | A computer-implemented system and method for outputting a prediction of a probability of a hospitalization of patients with chronic obstructive pulmonary disorder | |
| CN112365941A (en) | Method and system for recruitment of subjects | |
| CN111292815A (en) | Community big data health service system based on cloud | |
| US20240138780A1 (en) | Digital kiosk for performing integrative analysis of health and disease condition and method thereof | |
| KR20150007468A (en) | Clinical Decision Support System and Device supporting the same | |
| CN115831298B (en) | Clinical trial patient recruitment method and device based on hospital management information system | |
| KR20230049592A (en) | Self-diagnosis linked health record management method and medical information service providing platform through the same method | |
| US20210335491A1 (en) | Predictive adaptive intelligent diagnostics and treatment | |
| Rao et al. | AI-enabled clinical decision support system | |
| CN113870973A (en) | Information output method, device, computer equipment and medium based on artificial intelligence | |
| Lee | Reference model and architecture of interactive cognitive health advisor based on evolutional cyber-physical systems | |
| US20240156415A1 (en) | Diagnosis support system and diagnosis support apparatus | |
| AU2021101132A4 (en) | Analysis and monitoring of brainwaves for epilepsy treatment using artificial intelligence | |
| Mosavi et al. | Intelligent Decision Support System for Precision Medicine; Time Series Multi-variable Approach for Data Processing. | |
| US20240006067A1 (en) | System by which patients receiving treatment and at risk for iatrogenic cytokine release syndrome are safely monitored | |
| Alterazi | Towards Reaping the Promotions of Big Data in Healthcare Services | |
| US20240029898A1 (en) | Medical information processing device, medical information processing method, 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 |