CN110019491B - Visualization method, visualization device, computer device, and storage medium - Google Patents
Visualization method, visualization device, computer device, and storage medium Download PDFInfo
- Publication number
- CN110019491B CN110019491B CN201710624251.0A CN201710624251A CN110019491B CN 110019491 B CN110019491 B CN 110019491B CN 201710624251 A CN201710624251 A CN 201710624251A CN 110019491 B CN110019491 B CN 110019491B
- Authority
- CN
- China
- Prior art keywords
- variable
- preset
- structured
- information
- variables
- 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
- 238000012800 visualization Methods 0.000 title claims abstract description 52
- 238000007794 visualization technique Methods 0.000 title abstract description 4
- 238000007619 statistical method Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 9
- 238000013079 data visualisation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 18
- 201000010099 disease Diseases 0.000 description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 18
- 238000007418 data mining Methods 0.000 description 13
- 238000001914 filtration Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 230000000007 visual effect Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000009412 basement excavation Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 208000024172 Cardiovascular disease Diseases 0.000 description 3
- 208000026106 cerebrovascular disease Diseases 0.000 description 3
- 230000002526 effect on cardiovascular system Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007721 medicinal effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a visualization method and a visualization device of structured medical data, a computer device and a computer readable storage medium, wherein the visualization method comprises the following steps: basic information of each preset structured variable contained in each medical record is obtained; forming an information distribution view corresponding to each preset structured variable and/or forming variable relation views among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable; and outputting and displaying the information distribution view and/or the variable relation view. By the technical scheme, the visualization of the structured medical data can be effectively realized, so that a user can more conveniently excavate the structured medical data.
Description
Technical Field
The present invention relates to the technical field of medical data visualization, and in particular, to a method for visualizing structured medical data, a device for visualizing structured medical data, a computer device, and a computer-readable storage medium.
Background
At present, data mining is a process of processing, classifying, clustering and the like on a large amount of data, and selecting useful information by means of statistical analysis and logic analysis, including feature extraction on the data. With the application of the digitizing technology in the medical field, the medical data volume is larger and larger, which contains a lot of valuable information resources, and the medical data mining has wide application fields including: medical activity assisted diagnosis, medical quality management, medical information processing, medical research and development, biomedicine, medical images, and the like.
However, medical data has pattern polymorphism (such as multiple co-morbidities), incompleteness, timeliness, redundancy, privacy, and the like, which can pose challenges to data mining, and unstructured data is particularly difficult to analyze. Therefore, the data mining is performed on the structured medical data, and the structured medical data is a better break for the medical data mining.
Therefore, how to make the user more convenient to mine the structured medical data and realize the visualization of the structured medical data becomes a technical problem to be solved.
Disclosure of Invention
Based on the problems, the invention provides a new technical scheme which can effectively realize the visualization of the structured medical data, thereby ensuring that a user can more conveniently excavate the structured medical data.
In view of this, a first aspect of the present invention proposes a method of visualizing structured medical data, comprising: basic information of each preset structured variable contained in each medical record is obtained; forming an information distribution view corresponding to each preset structured variable and/or forming variable relation views among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable; and outputting and displaying the information distribution view and/or the variable relation view.
According to the technical scheme, the basic information of each preset structured variable contained in each medical case is subjected to statistical analysis, so that not only can the information distribution view of each preset structured variable be drawn, but also variable relation views showing the relevance among different preset structured variables can be drawn, and the output display of the information distribution view and/or the variable relation views can be carried out, and the visualization processing of the structured medical data is realized, so that a user can intuitively know the basic information condition of the structured medical data, the user can conveniently excavate the structured medical data, the manpower resources are saved, and the data excavation efficiency can be improved.
In the above technical solution, preferably, before the step of obtaining the basic information of each preset structured variable included in each medical record, the method further includes: detecting whether a classification instruction for each medical case input by a user is received; if yes, classifying all medical cases according to preset classification standards contained in the classification instructions, and respectively executing the steps of acquiring basic information of each preset structural variable contained in each medical case and forming an information distribution view and/or a variable relation view aiming at each medical case group obtained by classification; if not, directly executing the step of acquiring the basic information of each preset structured variable contained in each medical record.
In the technical scheme, in order to more conveniently realize the visualization of the structured medical data, and the obtained information distribution view of the preset structured variables and/or the obtained variable relation view among the preset structured variables can more intuitively display the basic information data condition, all medical cases needing to be visualized can be classified in advance according to the actual demands of users, and the data mining of the structured medical data with more pertinence is realized.
In any of the foregoing solutions, preferably, the basic information of each preset structured variable includes one or more combinations of: variable attribute information, variable type information and variable value information; and forming an information distribution view corresponding to each preset structured variable according to the statistical analysis result of the basic information of each preset structured variable, wherein the method specifically comprises the following steps: when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and an information distribution view corresponding to the first target variable value information is represented by a first preset graph; when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
In this embodiment, the basic information of each preset structured variable included in each medical record includes, but is not limited to, one or more of the following combinations: variable attribute information such as character attribute, numerical attribute, time attribute, and the like; variable type information such as discrete type variable, continuous type variable; variable value information such as value interval, value category, etc.
Further, when the basic information of each preset structured variable is analyzed to determine the type of the variable, the corresponding visual graph can be adopted to further perform visual processing on the basic information, specifically, the variable type of each preset structured variable can be determined according to the variable attribute information and/or the variable type information of each preset structured variable, further, automatic processing is performed on the variable value-taking information based on the variable type of each preset structured variable, so that bad data points can be reasonably displayed, and then the graph is drawn to realize visualization. By the scheme, bad data of the preset structured variables can be filtered, and the information distribution view is built only according to reasonable and meaningful data, so that the accuracy of building the information distribution view is ensured.
The preset interval for filtering the value of the continuous variable and the preset value for filtering the value of the discrete variable can be specifically set according to actual needs. Further, when the preset structured variable is a variable that can be naturally ordered, such as time, the structured variable can be ordered first, and then the filtering and the corresponding visualization processing of the values can be performed.
In any of the foregoing technical solutions, preferably, the step of forming a variable relationship view between different preset structured variables according to a statistical analysis result of basic information of each preset structured variable specifically includes: acquiring at least one preset statistical theme; determining a target structured variable associated with each preset statistical theme in the preset structured variables; and forming a variable relation view between the target structured variables associated with each preset statistical theme according to the statistical analysis result of the basic information of the target structured variables, and representing the variable relation view between the target structured variables associated with each preset statistical theme by adopting a third preset graph.
In the technical scheme, variable relation views among different preset structured variables can be constructed by presetting a common statistical theme form, namely, summarizing preset structured variables related to the same preset statistical theme, generating variable relation views among all target structured variables related to the same preset statistical theme based on statistical analysis of basic information of the screened target structured variables, and further, displaying statistical relations among different structured variables more intuitively by adopting a parallel coordinate graph, a star graph, a matrix scatter graph, a polyhedron graph and the like.
Wherein the preset statistical theme includes but is not limited to: medical fee topics, treatment effect topics, disease topics, and time topics.
In any of the foregoing solutions, preferably, the method for visualizing structured medical data further includes: when an adjusting instruction input by a user is received, one or more of a preset classification standard, a preset interval, a preset value, a preset statistical theme, a first preset graph, a second preset graph and a third preset graph are correspondingly adjusted according to adjusting parameters contained in the adjusting instruction.
In the technical scheme, in order to enable the visualization result of the structured medical data to meet the requirements of users more so as to facilitate the subsequent data mining and the like, corresponding parameters can be adjusted according to the requirements of the users in the visualization process and after corresponding views are output, so that an friendly man-machine interaction function in the visualization process of the structured medical data is realized, and the user experience is improved; specifically, the user may at least classify the preset classification criteria for classifying the medical records, filter the preset intervals and preset values of the preset structured variables, and set preset statistical topics, and may also change the visual view form of the structured medical data.
A second aspect of the present invention proposes a visualization device of structured medical data, comprising: the acquisition module is used for acquiring basic information of each preset structured variable contained in each medical case; the processing module is used for forming an information distribution view corresponding to each preset structured variable and/or forming a variable relation view among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable acquired by the acquisition module; and the output module is used for outputting and displaying the information distribution view and/or the variable relation view.
According to the technical scheme, the basic information of each preset structured variable contained in each medical case is subjected to statistical analysis, so that not only can the information distribution view of each preset structured variable be drawn, but also variable relation views showing the relevance among different preset structured variables can be drawn, and the output display of the information distribution view and/or the variable relation views can be carried out, and the visualization processing of the structured medical data is realized, so that a user can intuitively know the basic information condition of the structured medical data, the user can conveniently excavate the structured medical data, the manpower resources are saved, and the data excavation efficiency can be improved.
In the above technical solution, preferably, the visualization device for structured medical data further includes: the detection module is used for detecting whether a classification instruction for each medical case input by a user is received before the acquisition module acquires the basic information of each preset structured variable contained in each medical case; the classification module classifies all medical cases according to preset classification standards contained in the classification instructions when the detection module detects that the classification instructions are received, so that the step of acquiring basic information of each preset structured variable contained in each medical case and forming an information distribution view and/or a variable relation view is respectively executed for each medical case group obtained by classification; and the acquisition module directly executes the step of acquiring the basic information of each preset structured variable contained in each medical case when the detection module detects that the classification instruction is not received.
In the technical scheme, in order to more conveniently realize the visualization of the structured medical data, and the obtained information distribution view of the preset structured variables and/or the obtained variable relation view among the preset structured variables can more intuitively display the basic information data condition, all medical cases needing to be visualized can be classified in advance according to the actual demands of users, and the data mining of the structured medical data with more pertinence is realized.
In any of the foregoing solutions, preferably, the basic information of each preset structured variable includes one or more combinations of: variable attribute information, variable type information and variable value information; the processing module is specifically configured to: when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and an information distribution view corresponding to the first target variable value information is represented by a first preset graph; when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
In this embodiment, the basic information of each preset structured variable included in each medical record includes, but is not limited to, one or more of the following combinations: variable attribute information such as character attribute, numerical attribute, time attribute, and the like; variable type information such as discrete type variable, continuous type variable; variable value information such as value interval, value category, etc.
Further, when the basic information of each preset structured variable is analyzed to determine the type of the variable, the corresponding visual graph can be adopted to further perform visual processing on the basic information, specifically, the variable type of each preset structured variable can be determined according to the variable attribute information and/or the variable type information of each preset structured variable, further, automatic processing is performed on the variable value-taking information based on the variable type of each preset structured variable, so that bad data points can be reasonably displayed, and then the graph is drawn to realize visualization. By the scheme, bad data of the preset structured variables can be filtered, and the information distribution view is built only according to reasonable and meaningful data, so that the accuracy of building the information distribution view is ensured.
The preset interval for filtering the value of the continuous variable and the preset value for filtering the value of the discrete variable can be specifically set according to actual needs. Further, when the preset structured variable is a variable that can be naturally ordered, such as time, the structured variable can be ordered first, and then the filtering and the corresponding visualization processing of the values can be performed.
In any of the foregoing solutions, preferably, the processing module specifically includes: the acquisition sub-module is used for acquiring at least one preset statistical theme; the determining submodule is used for determining a target structured variable which is associated with each preset statistical theme in the preset structured variables; and the processing sub-module is used for forming a variable relation view between the target structured variables associated with each preset statistical theme according to the statistical analysis result of the basic information of the target structured variables, and adopting a third preset graph to represent the variable relation view between the target structured variables associated with each preset statistical theme.
In the technical scheme, variable relation views among different preset structured variables can be constructed by presetting a common statistical theme form, namely, summarizing preset structured variables related to the same preset statistical theme, generating variable relation views among all target structured variables related to the same preset statistical theme based on statistical analysis of basic information of the screened target structured variables, and further, displaying statistical relations among different structured variables more intuitively by adopting a parallel coordinate graph, a star graph, a matrix scatter graph, a polyhedron graph and the like.
Wherein the preset statistical theme includes but is not limited to: medical fee topics, treatment effect topics, disease topics, and time topics.
In any of the foregoing aspects, preferably, the visualization device for structured medical data further includes: and the adjusting module is used for correspondingly adjusting one or more of a preset classification standard, a preset interval, a preset value, a preset statistical theme, a first preset graph, a second preset graph and a third preset graph according to the adjusting parameters contained in the adjusting instructions when the adjusting instructions input by the user are received.
In the technical scheme, in order to enable the visualization result of the structured medical data to meet the requirements of users more so as to facilitate the subsequent data mining and the like, corresponding parameters can be adjusted according to the requirements of the users in the visualization process and after corresponding views are output, so that an friendly man-machine interaction function in the visualization process of the structured medical data is realized, and the user experience is improved; specifically, the user may at least classify the preset classification criteria for classifying the medical records, filter the preset intervals and preset values of the preset structured variables, and set preset statistical topics, and may also change the visual view form of the structured medical data.
A third aspect of the invention proposes a computer device comprising a processor for implementing the steps of the method of visualizing structured medical data according to any of the above-mentioned technical solutions when executing a computer program stored in a memory.
A fourth aspect of the invention proposes a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of a method of visualizing structured medical data according to any of the above-mentioned aspects.
By the technical scheme, the visualization of the structured medical data can be effectively realized, so that a user can more conveniently excavate the structured medical data.
Drawings
FIG. 1 shows a flow diagram of a method of visualizing structured medical data in accordance with an embodiment of the invention;
FIG. 2 illustrates a flow diagram of a method of building a variable relationship view in accordance with an embodiment of the present invention;
FIG. 3 shows an information distribution view of an embodiment of the present invention;
FIG. 4 illustrates a variable relationship view of an embodiment of the present invention;
FIG. 5 shows a schematic block diagram of a visualization device of structured medical data of an embodiment of the invention;
FIG. 6 shows a schematic block diagram of the processing module shown in FIG. 5;
FIG. 7 shows a schematic block diagram of a computer device of an embodiment of the invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow diagram of a method of visualizing structured medical data in accordance with an embodiment of the invention.
As shown in fig. 1, the method for visualizing structured medical data according to an embodiment of the present invention specifically includes the following steps:
It is understood that the preset structured variables included in each medical record may include at least: age, sex, disease, department, treatment cost, treatment time, etc.
And 104, forming an information distribution view corresponding to each preset structured variable and/or forming variable relation views among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable.
And step 106, outputting and displaying the information distribution view and/or the variable relation view.
In this embodiment, by performing statistical analysis on the basic information of each preset structured variable included in each medical record, not only can the information distribution view of each preset structured variable be drawn, but also variable relation views showing the relevance between different preset structured variables can be drawn, and output display of the information distribution view and/or the variable relation views can be performed, so that the visualization processing of the structured medical data is realized, and a user can more intuitively know the basic information condition of the structured medical data, thereby enabling the user to more conveniently excavate the structured medical data, saving manpower resources, and improving the efficiency of data excavation.
Further, in the foregoing embodiment, before step 102, the method for visualizing structured medical data according to the embodiment of the present invention may further include the following flow steps:
Detecting whether a classification instruction for each medical case input by a user is received; if yes, classifying all medical cases according to preset classification standards contained in the classification instructions, and respectively executing the steps of acquiring basic information of each preset structural variable contained in each medical case and forming an information distribution view and/or a variable relation view aiming at each medical case group obtained by classification; if not, directly executing the step of acquiring the basic information of each preset structured variable contained in each medical record.
In this embodiment, further, in order to more conveniently realize visualization of the structured medical data, and enable the obtained information distribution view of the preset structured variables and/or the obtained variable relation view between the preset structured variables to more intuitively display the basic information data condition of the basic information data, all medical cases needing to be visualized can be classified in advance according to the actual needs of the user, so as to realize data mining of the structured medical data with more pertinence.
Specifically, it may be classified according to disease categories such as cardiovascular and cerebrovascular diseases, skin diseases, gynecological diseases, and the like.
Further, in the above embodiment, the basic information of each preset structured variable includes one or a combination of more of: variable attribute information, variable type information, and variable value information.
It is understood that the basic information of each preset structured variable contained in each medical record includes, but is not limited to, one or a combination of more of the following: variable attribute information such as character attribute, numerical attribute, time attribute, and the like; variable type information such as discrete type variable, continuous type variable; variable value information such as value interval, value category, etc.
Further, in the foregoing embodiment, the step 104 of forming the information distribution view corresponding to each preset structured variable according to the statistical analysis result of the basic information of each preset structured variable may be specifically performed as follows:
when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and an information distribution view corresponding to the first target variable value information is represented by a first preset graph.
It can be understood that when the preset structured variable is a continuous variable, a meaningful section can be intercepted according to the distribution characteristics of the continuous value interval, that is, an abnormal value or an unimportant section is filtered, so that the value interval is located in the preset section, and specifically, the information distribution view of the continuous variable can be displayed through a histogram, a box diagram and the like.
Further, when the information distribution view of the continuous variable is displayed, the average value, the intermediate value, the median, the maximum value and the variance of the continuous variable can be counted and displayed.
When the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
It can be understood that when the preset structured variable is a discrete variable, the value category with the frequency higher than the preset value can be selected according to the frequency distribution characteristics of the value category of the preset structured variable, and the information distribution view of the discrete variable can be displayed through a pie chart, a bar chart and the like.
Further, when the information distribution view of the discrete variable is displayed, the average value, the intermediate value, the median, the maximum value and the variance of the frequency number of the value class can be counted and displayed.
In this embodiment, after the basic information of each preset structured variable is analyzed to determine the type of the variable to which the basic information belongs, a corresponding visualization graph can be adopted to further perform visualization processing, specifically, the variable type of each preset structured variable can be determined according to the variable attribute information and/or the variable type information of the preset structured variable, and then the variable value information is automatically processed based on the variable attribute information and/or the variable type information, so that data can be reasonably displayed, bad data points can be filtered out, and then the graph is drawn to realize visualization; by the embodiment, bad data of the preset structured variables can be filtered, and the information distribution view is built only according to reasonable and meaningful data, so that the accuracy of building the information distribution view is ensured.
It is further understood that the preset interval for filtering the value of the continuous variable and the preset value for filtering the value of the discrete variable may be specifically set according to actual needs.
It is further understood that when the preset structured variable is a variable that can be naturally ordered, such as time, the structured variable can be ordered first, and then the filtering of the values and the corresponding visualization process can be performed.
Further, in the foregoing embodiment, the solution for forming the variable relationship view between different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable in step 104 may be specifically implemented according to the flow shown in fig. 2, which includes:
step S20, at least one preset statistical theme is obtained.
It will be appreciated that the number of components,
step S22, determining a target structured variable associated with each preset statistical theme in the preset structured variables.
And step S24, forming a variable relation view among the target structured variables associated with each preset statistical theme according to the statistical analysis result of the basic information of the target structured variables, and representing the variable relation view among the target structured variables associated with each preset statistical theme by adopting a third preset graph.
In this embodiment, a variable relationship view between different preset structured variables may be constructed by presetting a common statistical theme, that is, summarizing preset structured variables related to the same preset statistical theme, generating a variable relationship view between each target structured variable associated with the same preset statistical theme based on statistical analysis of basic information of the screened target structured variables, and further, a parallel coordinate graph, a star graph, a matrix scatter graph, a polyhedral graph, etc. may be used to more intuitively display statistical relationships between different structured variables.
Wherein the preset statistical theme includes but is not limited to: medical fee topics, treatment effect topics, disease topics, and time topics.
Further, in the above embodiment, the method for visualizing structured medical data further includes: when an adjusting instruction input by a user is received, one or more of a preset classification standard, a preset interval, a preset value, a preset statistical theme, a first preset graph, a second preset graph and a third preset graph are correspondingly adjusted according to adjusting parameters contained in the adjusting instruction.
In the embodiment, in order to enable the visualization result of the structured medical data to meet the requirements of users more so as to facilitate subsequent data mining and the like, corresponding parameters can be adjusted according to the requirements of the users in the visualization process and after corresponding views are output, so that an friendly man-machine interaction function in the visualization process of the structured medical data is realized, and user experience is improved; specifically, the user may at least classify the preset classification criteria for classifying the medical records, filter the preset intervals and preset values of the preset structured variables, and set preset statistical topics, and may also change the visual view form of the structured medical data.
For example, the user may adjust the abscissa range of the histogram by means of a mouse or dialog box; the user can define the medical theme and the field relation diagram required by the medical theme, and can also customize the standard and condition of the level of dividing the field and adjust the standard and condition, thereby realizing man-machine interaction.
The following describes a visualization scheme of structured medical data according to the present invention, taking cardiovascular and cerebrovascular diseases as an example. Specifically, the preset structured variables included in each medical case of cardiovascular and cerebrovascular diseases include: age, sex, disease, department, treatment cost, treatment time, etc.
Further, according to the basic information of each preset structured variable, the sex, the disease name and the department name can be determined as character attributes and discrete variables, the age and the treatment cost are numerical attributes and continuous variables, and the treatment time is a time attribute and can be regarded as discrete variables.
For example, for discrete variable diseases and departments, each disease name and each department name are value categories, and because the number of diseases and the number of departments are more, several disease names with higher frequency of the value categories can be selected for drawing information distribution views of discrete variables, and cake diagrams or bar diagrams, such as cardiology, neurology and neurosurgery, with higher frequency of departments, can be drawn, wherein the information distribution diagrams are shown in fig. 3; the continuous variable treatment cost can be drawn by using a histogram to draw an information distribution diagram, and the treatment cost can be specifically refined as follows: hospitalization costs, surgical costs, medication costs, care costs, and total treatment costs, etc.
Further, if the above-mentioned variables are the variables of the predetermined type, the variables of the predetermined type are the variables that can be naturally ordered, such as time and age, the information distribution map can be ordered first and then constructed, so that the constructed information distribution map is more ordered, and the user can check conveniently.
Further, for variable relation views among different preset structured variables, for example, for a disease subject, a distribution map of a disease of different ages and sexes can be drawn; the medical expense is taken as a theme, and a treatment expense distribution diagram, a relation diagram between total expense, operation expense and the like of different diseases and different departments can be drawn; the treatment time is taken as a theme, and the morbidity maps of different diseases in different seasons can be drawn; further, in the relationship diagrams, correlation coefficients between different variables can be calculated, and statistics such as conditional probabilities can be calculated.
As shown in fig. 4, the constructed variable relation view is a tetrahedron diagram, and four vertices in the variable relation view correspond to one variable respectively, that is, four variables of season, disease, treatment cost and treatment time in total. The vertex size of each variable in the variable relationship view is different, the vertex size reflects the fraction of the variable, the thickness of the line segment between the two variables is also different, and the thicker the line segment is, the greater the correlation between the two variables is.
Fig. 5 shows a schematic block diagram of a visualization device of structured medical data according to an embodiment of the invention.
As shown in fig. 5, a visualization device 50 of structured medical data according to an embodiment of the present invention includes: an acquisition module 502, a processing module 504, and an output module 506.
The acquiring module 502 is configured to acquire basic information of each preset structured variable included in each medical record; the processing module 504 is configured to form an information distribution view corresponding to each preset structured variable and/or form a variable relationship view between different preset structured variables according to a statistical analysis result of the basic information of each preset structured variable acquired by the acquiring module 502; the output module 506 is configured to output and present the information distribution view and/or the variable relationship view.
In this embodiment, by performing statistical analysis on the basic information of each preset structured variable included in each medical record, not only can the information distribution view of each preset structured variable be drawn, but also variable relation views showing the relevance between different preset structured variables can be drawn, and output display of the information distribution view and/or the variable relation views can be performed, so that the visualization processing of the structured medical data is realized, and a user can more intuitively know the basic information condition of the structured medical data, thereby enabling the user to more conveniently excavate the structured medical data, saving manpower resources, and improving the efficiency of data excavation.
Further, as shown in fig. 5, in the above embodiment, the visualization device 50 of structured medical data further includes: a detection module 508 and a classification module 510.
The detection module 508 is configured to detect whether a classification instruction for each medical case input by a user is received before the acquisition module 502 acquires basic information of each preset structured variable included in each medical case; the classification module 510 classifies all medical cases according to a preset classification standard contained in the classification instruction when the detection module 508 detects that the classification instruction is received, so as to respectively execute the steps of acquiring basic information of each preset structured variable contained in each medical case and forming an information distribution view and/or a variable relation view aiming at each medical case group obtained by classification; and the obtaining module 502 directly performs the step of obtaining the basic information of each preset structured variable included in each medical record when the detecting module 508 detects that the classification instruction is not received.
In this embodiment, further, in order to more conveniently realize visualization of the structured medical data, and enable the obtained information distribution view of the preset structured variables and/or the obtained variable relation view between the preset structured variables to more intuitively display the basic information data condition of the basic information data, all medical cases needing to be visualized can be classified in advance according to the actual needs of the user, so as to realize data mining of the structured medical data with more pertinence.
Further, in the above embodiment, the basic information of each preset structured variable includes one or a combination of more of: variable attribute information, variable type information and variable value information; the processing module 504 is specifically configured to: when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and an information distribution view corresponding to the first target variable value information is represented by a first preset graph; when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
In this embodiment, the basic information of each preset structured variable contained in each medical record includes, but is not limited to, a combination of one or more of the following: variable attribute information such as character attribute, numerical attribute, time attribute, and the like; variable type information such as discrete type variable, continuous type variable; variable value information such as value interval, value category, etc.
Further, when the basic information of each preset structured variable is analyzed to determine the type of the variable, the corresponding visual graph can be adopted to further perform visual processing on the basic information, specifically, the variable type of each preset structured variable can be determined according to the variable attribute information and/or the variable type information of each preset structured variable, further, automatic processing is performed on the variable value-taking information based on the variable type of each preset structured variable, so that bad data points can be reasonably displayed, and then the graph is drawn to realize visualization. By the scheme, bad data of the preset structured variables can be filtered, and the information distribution view is built only according to reasonable and meaningful data, so that the accuracy of building the information distribution view is ensured.
The preset interval for filtering the value of the continuous variable and the preset value for filtering the value of the discrete variable can be specifically set according to actual needs. Further, when the preset structured variable is a variable that can be naturally ordered, such as time, the structured variable can be ordered first, and then the filtering and the corresponding visualization processing of the values can be performed.
Further, in the above embodiment, the processing module 504 specifically includes: the acquisition submodule 5042, the determination submodule 5044 and the processing submodule 5046 are shown in fig. 6.
Wherein, the obtaining submodule 5042 is configured to obtain at least one preset statistical topic; the determining submodule 5044 is used for determining a target structured variable associated with each preset statistical theme in preset structured variables; the processing sub-module 5046 is configured to form a variable relationship view between the target structured variables associated with each preset statistical topic according to the result of the statistical analysis on the basic information of the target structured variables, and use a third preset graphic to represent the variable relationship view between the target structured variables associated with each preset statistical topic.
In this embodiment, a variable relationship view between different preset structured variables may be constructed by presetting a common statistical theme, that is, summarizing preset structured variables related to the same preset statistical theme, generating a variable relationship view between each target structured variable associated with the same preset statistical theme based on statistical analysis of basic information of the screened target structured variables, and further, a parallel coordinate graph, a star graph, a matrix scatter graph, a polyhedral graph, etc. may be used to more intuitively display statistical relationships between different structured variables.
Wherein the preset statistical theme includes but is not limited to: medical fee topics, treatment effect topics, disease topics, and time topics.
Further, as shown in fig. 5, in the above embodiment, the visualization device 50 of structured medical data further includes: the adjusting module 512 is configured to correspondingly adjust one or more of a preset classification standard, a preset interval, a preset value, a preset statistical theme, a first preset graphic, a second preset graphic and a third preset graphic according to an adjustment parameter included in the adjustment instruction when the adjustment instruction input by the user is received.
In the embodiment, in order to enable the visualization result of the structured medical data to meet the requirements of users more so as to facilitate subsequent data mining and the like, corresponding parameters can be adjusted according to the requirements of the users in the visualization process and after corresponding views are output, so that an friendly man-machine interaction function in the visualization process of the structured medical data is realized, and user experience is improved; specifically, the user may at least classify the preset classification criteria for classifying the medical records, filter the preset intervals and preset values of the preset structured variables, and set preset statistical topics, and may also change the visual view form of the structured medical data.
As an embodiment of the present invention, a server is provided, which includes the visualization device 50 of structured medical data according to any of the above embodiments, and therefore, the server has all the beneficial technical effects of the visualization device 50 of structured medical data, which are not described herein.
FIG. 7 shows a schematic block diagram of a computer device of an embodiment of the invention.
As shown in fig. 7, a computer device 70 according to an embodiment of the present invention comprises a memory 702, a processor 704 and a computer program stored on the memory 702 and executable on the processor 704, wherein the memory 702 and the processor 704 may be connected by a bus, and the processor 704 is configured to implement the steps of the method for visualizing structured medical data as described in the above embodiment when executing the computer program stored in the memory 702.
Steps in the methods of embodiments of the present disclosure may be sequentially adjusted, combined, and pruned as desired.
The visualization apparatus and the units in the computer device of the structured medical data of the embodiments of the present disclosure may combine, divide, and prune according to actual needs.
According to an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the feature extraction method of structured medical data as described in the above embodiments.
Further, it will be appreciated by those of ordinary skill in the art that all or part of the steps of the various methods of the above embodiments may be implemented by hardware associated with a program stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used to carry or store data that is readable by a computer.
Further, the computer device may be a PC (Personal Computer ) terminal.
The technical scheme of the invention is explained in detail above with reference to the attached drawings, and the visualization of the structured medical data can be effectively realized through the technical scheme of the invention, so that a user can more conveniently excavate the structured medical data.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method of visualizing structured medical data, comprising:
basic information of each preset structured variable contained in each medical record is obtained;
forming an information distribution view corresponding to each preset structured variable and/or forming a variable relation view among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable;
outputting and displaying the information distribution view and/or the variable relation view;
The step of forming a variable relation view between different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable specifically includes:
acquiring at least one preset statistical theme;
determining a target structured variable associated with each preset statistical topic in the preset structured variables;
and forming a variable relation view among the target structured variables associated with each preset statistical theme according to the statistical analysis result of the basic information of the target structured variables, and representing the variable relation view among the target structured variables associated with each preset statistical theme by adopting a third preset graph.
2. The method of visualizing structured medical data as in claim 1, further comprising, prior to said step of obtaining basic information for each preset structured variable contained in each medical record:
detecting whether a classification instruction for each medical case input by a user is received;
if yes, classifying all medical cases according to preset classification standards contained in the classification instructions, and respectively executing the steps of acquiring basic information of each preset structured variable contained in each medical case and forming the information distribution view and/or the variable relation view aiming at each medical case group obtained by classification;
If not, directly executing the step of acquiring the basic information of each preset structured variable contained in each medical record.
3. The method of visualizing structured medical data as in claim 2, wherein said basic information for each preset structured variable comprises one or a combination of more of: variable attribute information, variable type information and variable value information; and
the step of forming the information distribution view corresponding to each preset structured variable according to the statistical analysis result of the basic information of each preset structured variable specifically includes:
when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and a first preset graph is adopted to represent an information distribution view corresponding to the first target variable value information;
when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
4. The method of visualizing structured medical data of claim 3, further comprising:
when an adjustment instruction input by a user is received, one or more of the preset classification standard, the preset interval, the preset value, the preset statistical theme, the first preset graph, the second preset graph and the third preset graph are correspondingly adjusted according to adjustment parameters contained in the adjustment instruction.
5. A structured medical data visualization device, comprising:
the acquisition module is used for acquiring basic information of each preset structured variable contained in each medical case;
the processing module is used for forming an information distribution view corresponding to each preset structured variable and/or forming a variable relation view among different preset structured variables according to the statistical analysis result of the basic information of each preset structured variable acquired by the acquisition module;
the output module is used for outputting and displaying the information distribution view and/or the variable relation view;
the processing module specifically comprises:
the acquisition sub-module is used for acquiring at least one preset statistical theme;
The determining submodule is used for determining a target structured variable which is associated with each preset statistical theme in the preset structured variables;
and the processing sub-module is used for forming a variable relation view among the target structured variables associated with each preset statistical theme according to the statistical analysis result of the basic information of the target structured variables, and representing the variable relation view among the target structured variables associated with each preset statistical theme by adopting a third preset graph.
6. The structured medical data visualization device of claim 5, further comprising:
the detection module is used for detecting whether a classification instruction for each medical case input by a user is received before the acquisition module acquires the basic information of each preset structured variable contained in each medical case;
the classification module classifies all medical records according to preset classification standards contained in the classification instructions when the detection module detects that the classification instructions are received, so that the step of acquiring basic information of each preset structured variable contained in each medical record and forming the information distribution view and/or the variable relation view is respectively executed for each medical record group obtained by classification; and
And the acquisition module directly executes the step of acquiring the basic information of each preset structured variable contained in each medical record when the detection module detects that the classification instruction is not received.
7. The visualization device of claim 6, wherein the basic information of each preset structured variable comprises one or a combination of more of: variable attribute information, variable type information and variable value information; and
the processing module is specifically configured to:
when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be continuous variables, first target variable value information in a preset interval in the variable value information of each preset structured variable is acquired, and a first preset graph is adopted to represent an information distribution view corresponding to the first target variable value information;
when the variable attribute information and/or the variable type information of each preset structured variable are/is determined to be discrete variables, second target variable value information with the frequency higher than a preset value in the variable value information of each preset structured variable is acquired, and a second preset graph is adopted to represent an information distribution view corresponding to the second target variable value information.
8. The visualization device of claim 7, further comprising:
and the adjusting module is used for correspondingly adjusting one or more of the preset classification standard, the preset interval, the preset value, the preset statistical theme, the first preset graph, the second preset graph and the third preset graph according to the adjusting parameters contained in the adjusting instructions when the adjusting instructions input by the user are received.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710624251.0A CN110019491B (en) | 2017-07-27 | 2017-07-27 | Visualization method, visualization device, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710624251.0A CN110019491B (en) | 2017-07-27 | 2017-07-27 | Visualization method, visualization device, computer device, and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110019491A CN110019491A (en) | 2019-07-16 |
CN110019491B true CN110019491B (en) | 2023-07-04 |
Family
ID=67185987
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710624251.0A Active CN110019491B (en) | 2017-07-27 | 2017-07-27 | Visualization method, visualization device, computer device, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110019491B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110675925B (en) * | 2019-08-31 | 2021-01-15 | 南京医渡云医学技术有限公司 | Data output method and device based on dynamic distribution diagram |
CN111190902A (en) * | 2019-12-25 | 2020-05-22 | 南京医睿科技有限公司 | Medical data structuring method, device, equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599088A (en) * | 2008-11-18 | 2009-12-09 | 北京美智医疗科技有限公司 | The mining multi-dimensional data system and method for medical information system |
CN102819656A (en) * | 2011-06-10 | 2012-12-12 | 中国科学院深圳先进技术研究院 | System and method for generating electronic medical record |
CN103778346A (en) * | 2014-02-18 | 2014-05-07 | 中国科学院上海技术物理研究所 | Medical information processing method and device |
CN103793611A (en) * | 2014-02-18 | 2014-05-14 | 中国科学院上海技术物理研究所 | Medical information visualization method and device |
CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
CN105808712A (en) * | 2016-03-07 | 2016-07-27 | 陈宽 | Intelligent system and method for converting text type medical reports into structured data |
CN106649431A (en) * | 2016-08-31 | 2017-05-10 | 天津南大通用数据技术股份有限公司 | Method of displaying charts in data visualization |
CN106919671A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of traditional Chinese medical science text medical record is excavated and aid decision intelligence system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9875339B2 (en) * | 2011-01-27 | 2018-01-23 | Simbionix Ltd. | System and method for generating a patient-specific digital image-based model of an anatomical structure |
US20140038152A1 (en) * | 2012-07-31 | 2014-02-06 | Sandro Micieli | Medical visualization method and system |
-
2017
- 2017-07-27 CN CN201710624251.0A patent/CN110019491B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599088A (en) * | 2008-11-18 | 2009-12-09 | 北京美智医疗科技有限公司 | The mining multi-dimensional data system and method for medical information system |
CN102819656A (en) * | 2011-06-10 | 2012-12-12 | 中国科学院深圳先进技术研究院 | System and method for generating electronic medical record |
CN103778346A (en) * | 2014-02-18 | 2014-05-07 | 中国科学院上海技术物理研究所 | Medical information processing method and device |
CN103793611A (en) * | 2014-02-18 | 2014-05-14 | 中国科学院上海技术物理研究所 | Medical information visualization method and device |
CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
CN105808712A (en) * | 2016-03-07 | 2016-07-27 | 陈宽 | Intelligent system and method for converting text type medical reports into structured data |
CN106649431A (en) * | 2016-08-31 | 2017-05-10 | 天津南大通用数据技术股份有限公司 | Method of displaying charts in data visualization |
CN106919671A (en) * | 2017-02-20 | 2017-07-04 | 广东省中医院 | A kind of traditional Chinese medical science text medical record is excavated and aid decision intelligence system |
Non-Patent Citations (1)
Title |
---|
吴颖慧.数据可视化背景下雷达图在医院管理中的应用.《广西医学》.2016,全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN110019491A (en) | 2019-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110245213B (en) | Questionnaire generation method, device, equipment and storage medium | |
US20160055190A1 (en) | Event detection and characterization in big data streams | |
CN111324659B (en) | Visual recommendation method and system for time-series medical data | |
CN110019491B (en) | Visualization method, visualization device, computer device, and storage medium | |
AU2017427586A1 (en) | Interactive model performance monitoring | |
CN111324511A (en) | Alarm rule generation method and device, electronic equipment and storage medium | |
DE102016204397A1 (en) | CLASSIFICATION OF A TIME SERIES SIGNAL AS VENTRICULAR EXTRASYSTOLE | |
CN111312351A (en) | Regional medical record data analysis method and system | |
CN110990445A (en) | Data processing method, device, equipment and medium | |
CN110751092B (en) | Agricultural monitoring method and device based on Internet of things, storage medium and electronic equipment | |
CN113326472A (en) | Pattern extraction and evolution visual analysis method based on time sequence multivariable data | |
CN109389972B (en) | Quality testing method and device for semantic cloud function, storage medium and equipment | |
CN112115182A (en) | Time sequence data processing method, device, equipment and storage medium | |
KR102197152B1 (en) | System for providing investment information | |
CN111523764A (en) | Business architecture detection method, device, tool, electronic equipment and medium | |
CN111027599B (en) | Clustering visualization method and device based on random sampling | |
CN113986954A (en) | User event acquisition method and device, intelligent terminal and readable storage medium | |
CN110941608B (en) | Method, device and equipment for generating buried point analysis and funnel analysis report | |
CN112991083A (en) | Fishery data visualization method and system, electronic device and storage medium | |
CN114691837B (en) | Insurance business data processing method and processing system based on big data | |
US20230004557A1 (en) | Systems and Methods for Network Explainability | |
Wang et al. | Interactive selection of multivariate features in large spatiotemporal data | |
CN116229521B (en) | Method, device and equipment for detecting heart information based on multi-scale features | |
CN117973883A (en) | Enterprise information management method, device, equipment and medium | |
US20230015637A1 (en) | Method and System for Analyzing Data in a Database |
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 | ||
PP01 | Preservation of patent right |
Effective date of registration: 20240202 Granted publication date: 20230704 |
|
PP01 | Preservation of patent right |