Summary of the invention
The present invention is based on the above problems, proposes a kind of new technical solution, can effectively realize to structuringThe visualization of medical data, so that user more easily excavates structured medical data.
In view of this, the first aspect of the present invention proposes a kind of method for visualizing of structured medical data, comprising: obtainTake the essential information for each preset structure variable for including in each medical medical record；According to the basic of each preset structure variableThe statistic analysis result of information forms the corresponding information arrangement view of each preset structure variable and/or forms different default knotsVariable relation view between structure variable；Export and show information arrangement view and/or variable relation view.
In the technical scheme, by the essential information to each preset structure variable for including in each medical medical record intoIt goes and statisticallys analyze, and then not only can draw its information arrangement view for each preset structure variable can also draw embodimentThe variable relation view of relevance between different preset structure variables, and it is able to carry out information arrangement view and/or changeThe output of magnitude relation view is shown, realizes the visualization processing to structured medical data, is allowed the user to more intuitiveGround understands the essential information situation of structured medical data, so that user more easily carries out structured medical dataIt excavates, not only saves human resources, additionally it is possible to improve the efficiency of data mining.
In the above-mentioned technical solutions, it is preferable that the base for each preset structure variable for including in obtaining each medical medical recordBefore the step of this information, further includes: detect whether to receive the sort instructions for each medical medical record of user's input；IfIt is that all medical medical records are classified according to the default classification standard for including in sort instructions, it is every to be obtained for classificationA medical treatment medical record group executes the essential information for obtaining each preset structure variable for including in wherein each medical medical record respectivelyAnd the step of forming information arrangement view and/or variable relation view；If it is not, directly including in each medical medical record of execution acquisitionThe step of essential information of each preset structure variable.
In the technical scheme, further in order to more easily realize the visualization of structured medical data, and makeVariable relation view between the information arrangement view and/or preset structure variable of the preset structure variable arrived is more intuitiveGround shows its essential information data cases, can own previously according to the actual demand of user to needing to carry out visualization processingMedical medical record is classified, and realizes the data mining of more targeted structured medical data.
In any of the above-described technical solution, it is preferable that the essential information of each preset structure variable include one or more ofCombination: variable's attribute information, types of variables information and variable-value information；And according to each preset structure variableThe statistic analysis result of essential information forms the step of each preset structure variable corresponding information arrangement view, specific to wrapIt includes: when determining that it is continuous variable according to the variable's attribute information and/or types of variables information of each preset structure variable,The first object variable-value information in the variable-value information of each preset structure variable in pre-set interval is obtained, is adoptedThe corresponding information arrangement view of first object variable-value information is indicated with the first preset pattern；When according to each preset structureWhen the variable's attribute information and/or types of variables information of variable determine that it is discrete variable, each preset structure variable is obtainedVariable-value information in frequency be higher than the second target variable value information of preset value, indicate the using the second preset patternThe corresponding information arrangement view of two target variable value information.
In the technical scheme, the essential information for each preset structure variable for including in each medical medical record includes but unlimitedIn following one or a variety of combinations: variable's attribute information, such as character attibute, numerical attribute, time attribute etc.；Types of variablesInformation, such as discrete variable, continuous variable；Variable-value information, such as value interval, value classification etc..
Further, change belonging to it has been determined when carrying out analysis by the essential information to each preset structure variableIt then can be using correspondingly visualized graphs, specifically can be according to each to its further progress visualization processing after amount typeThe variable's attribute information and/or types of variables information of preset structure variable determine its types of variables, and then are become based on this to itIt measures value information and carries out automatic processing, reasonably bad data point can be filtered out by display data, then graphingIt realizes visualization, then when preset structure variable is continuous variable, can be cut according to the characteristic distributions of continuous value intervalSignificant section is taken, that is, filters out exceptional value or unessential section, is located at its value interval in pre-set interval, specificallyThe information arrangement view of continuous variable can be shown by histogram, box traction substation etc., and when preset structure variable is discrete changeWhen amount, frequency taking higher than preset value can be selected according to the frequency disribution feature of the value classification of the preset structure variableIt is worth classification, the information arrangement view of discrete variable can be specifically shown by pie chart, bar chart etc..It, can be with by above schemeThe bad data of preset structure variable is filtered out, only constructs its information arrangement view according to reasonable, significant data, fromAnd it ensure that the accuracy of building information arrangement view.
Wherein, for the value condition to continuous variable it is filtered the pre-set interval of processing and for discrete variableThe preset value that value condition is filtered processing can be specifically arranged according to actual needs.Further, work as preset structureChanging variable is when can be with the variable of natural ordering, such as the time, then can first be ranked up, then carry out again the filtering of value withAnd correspondingly visualization processing.
In any of the above-described technical solution, it is preferable that according to the statistics of the essential information to each preset structure variableThe step of analysis result forms the variable relation view between different preset structure variables, specifically includes: obtaining at least oneDefault statistics theme；It determines in each preset structure variable and presets the statistics associated target structural variable of theme with each；RootIt is formed and each default statistics associated each target of theme according to the statistic analysis result of the essential information to target structural variableVariable relation view between structured variable, and indicate associated each with each default statistics theme using third preset patternVariable relation view between target structural variable.
In the technical scheme, different preset structures can be constructed by way of presetting common statistics themeVariable relation view between variable summarizes preset structure variable related with same default statistics theme, andStatistical analysis based on the essential information to the target structural variable filtered out generates associated with same default statistics themeVariable relation view between each target structural variable can further use parallel coordinates figure, star graph, matrix scatterplotFigure, polyhedron figure etc. more intuitively show the statistical relationship between different structured variables.
Wherein, presetting statistics theme includes but is not limited to: medical expense theme, therapeutic effect theme, disease theme, timeTheme.
In any of the above-described technical solution, it is preferable that the method for visualizing of structured medical data further include: when receivingWhen the regulating command of user's input, default classification standard, preset areas are adjusted according to the adjustment parameter for including in regulating command is correspondingBetween, one or more of preset value, default statistics theme, the first preset pattern, the second preset pattern and third preset pattern.
In the technical scheme, in order to meet the needs of users the visualization result to structured medical data more,It, can be during realizing visually and after the corresponding view of output according to the need of user in order to subsequent data mining etc.It asks and adjusts corresponding parameter, realize human-computer interaction function friendly in the visualization process of structured medical data, promote userExperience；Specifically, user at least can be to default classification standard, each preset structure of filtering for classifying to medical medical recordThe pre-set interval and preset value and the default statistics theme of setting of the value of change variable, and structured medical can also be changedThe visual view of data.
The second aspect of the present invention proposes a kind of visualization device of structured medical data, comprising: obtains module, usesIn the essential information for obtaining each preset structure variable for including in each medical medical record；Processing module, for according to acquisition mouldIt is corresponding that the statistic analysis result of the essential information for each preset structure variable that block obtains forms each preset structure variableInformation arrangement view and/or form variable relation view between different preset structure variables；Output module, for exportingAnd show information arrangement view and/or variable relation view.
In the technical scheme, by the essential information to each preset structure variable for including in each medical medical record intoIt goes and statisticallys analyze, and then not only can draw its information arrangement view for each preset structure variable can also draw embodimentThe variable relation view of relevance between different preset structure variables, and it is able to carry out information arrangement view and/or changeThe output of magnitude relation view is shown, realizes the visualization processing to structured medical data, is allowed the user to more intuitiveGround understands the essential information situation of structured medical data, so that user more easily carries out structured medical dataIt excavates, not only saves human resources, additionally it is possible to improve the efficiency of data mining.
In the above-mentioned technical solutions, it is preferable that the visualization device of structured medical data further include: detection module is usedIn before the essential information that acquisition module obtains each preset structure variable for including in each medical medical record, detect whether to receiveThe sort instructions for each medical medical record inputted to user；Categorization module, when detection module detection receives sort instructions,All medical medical records are classified according to the default classification standard for including in sort instructions, with each doctor obtained for classificationIt treats medical record group and executes the essential information and shape for obtaining each preset structure variable for including in wherein each medical medical record respectivelyThe step of at information arrangement view and/or variable relation view；And it obtains module and does not receive classification in detection module detectionWhen instruction, direct the step of executing the essential information for obtaining each preset structure variable for including in each medical medical record.
In the technical scheme, further in order to more easily realize the visualization of structured medical data, and makeVariable relation view between the information arrangement view and/or preset structure variable of the preset structure variable arrived is more intuitiveGround shows its essential information data cases, can own previously according to the actual demand of user to needing to carry out visualization processingMedical medical record is classified, and realizes the data mining of more targeted structured medical data.
In any of the above-described technical solution, it is preferable that the essential information of each preset structure variable include one or more ofCombination: variable's attribute information, types of variables information and variable-value information；And processing module is specifically used for: when according to everyWhen the variable's attribute information and/or types of variables information of a preset structure variable determine that it is continuous variable, obtain each pre-It is default using first if the first object variable-value information in the variable-value information of structured variable in pre-set intervalThe corresponding information arrangement view of graphical representation first object variable-value information；When the variable according to each preset structure variableWhen attribute information and/or types of variables information determine that it is discrete variable, the variable-value of each preset structure variable is obtainedFrequency in information is higher than the second target variable value information of preset value, indicates the second target variable using the second preset patternThe corresponding information arrangement view of value information.
In the technical scheme, the essential information for each preset structure variable for including in each medical medical record includes but unlimitedIn following one or a variety of combinations: variable's attribute information, such as character attibute, numerical attribute, time attribute etc.；Types of variablesInformation, such as discrete variable, continuous variable；Variable-value information, such as value interval, value classification etc..
Further, change belonging to it has been determined when carrying out analysis by the essential information to each preset structure variableIt then can be using correspondingly visualized graphs, specifically can be according to each to its further progress visualization processing after amount typeThe variable's attribute information and/or types of variables information of preset structure variable determine its types of variables, and then are become based on this to itIt measures value information and carries out automatic processing, reasonably bad data point can be filtered out by display data, then graphingIt realizes visualization, then when preset structure variable is continuous variable, can be cut according to the characteristic distributions of continuous value intervalSignificant section is taken, that is, filters out exceptional value or unessential section, is located at its value interval in pre-set interval, specificallyThe information arrangement view of continuous variable can be shown by histogram, box traction substation etc., and when preset structure variable is discrete changeWhen amount, frequency taking higher than preset value can be selected according to the frequency disribution feature of the value classification of the preset structure variableIt is worth classification, the information arrangement view of discrete variable can be specifically shown by pie chart, bar chart etc..It, can be with by above schemeThe bad data of preset structure variable is filtered out, only constructs its information arrangement view according to reasonable, significant data, fromAnd it ensure that the accuracy of building information arrangement view.
Wherein, for the value condition to continuous variable it is filtered the pre-set interval of processing and for discrete variableThe preset value that value condition is filtered processing can be specifically arranged according to actual needs.Further, work as preset structureChanging variable is when can be with the variable of natural ordering, such as the time, then can first be ranked up, then carry out again the filtering of value withAnd correspondingly visualization processing.
In any of the above-described technical solution, it is preferable that processing module specifically includes: acquisition submodule, for obtaining at leastOne default statistics theme；It determines submodule, is associated with for determining in each preset structure variable with each default statistics themeTarget structural variable；Submodule is handled, for the statistic analysis result according to the essential information to target structural variableThe variable relation view between each default statistics associated each target structural variable of theme is formed, and default using thirdVariable relation view between graphical representation and each default statistics associated each target structural variable of theme.
In the technical scheme, different preset structures can be constructed by way of presetting common statistics themeVariable relation view between variable summarizes preset structure variable related with same default statistics theme, andStatistical analysis based on the essential information to the target structural variable filtered out generates associated with same default statistics themeVariable relation view between each target structural variable can further use parallel coordinates figure, star graph, matrix scatterplotFigure, polyhedron figure etc. more intuitively show the statistical relationship between different structured variables.
Wherein, presetting statistics theme includes but is not limited to: medical expense theme, therapeutic effect theme, disease theme, timeTheme.
In any of the above-described technical solution, it is preferable that the visualization device of structured medical data further include: adjust mouldBlock, for being preset according to corresponding adjust of the adjustment parameter for including in regulating command when receiving the regulating command of user's inputClassification standard, pre-set interval, preset value, default statistics theme, the first preset pattern, the second preset pattern and third preset patternOne or more of.
In the technical scheme, in order to meet the needs of users the visualization result to structured medical data more,It, can be during realizing visually and after the corresponding view of output according to the need of user in order to subsequent data mining etc.It asks and adjusts corresponding parameter, realize human-computer interaction function friendly in the visualization process of structured medical data, promote userExperience；Specifically, user at least can be to default classification standard, each preset structure of filtering for classifying to medical medical recordThe pre-set interval and preset value and the default statistics theme of setting of the value of change variable, and structured medical can also be changedThe visual view of data.
The third aspect of the present invention proposes a kind of computer equipment, and the computer equipment includes processor, the placeReason device realizes the structure as described in any one of above-mentioned technical proposal when being used to execute the computer program stored in memoryThe step of changing the method for visualizing of medical data.
The fourth aspect of the present invention proposes a kind of computer readable storage medium, is stored thereon with computer program, instituteIt states realizing the structured medical data as described in any one of above-mentioned technical proposal when computer program is executed by processorThe step of method for visualizing.
According to the technical solution of the present invention, the visualization to structured medical data can be effectively realized, so thatUser more easily excavates structured medical data.
Specific embodiment
It is with reference to the accompanying drawing and specific real in order to be more clearly understood that the above objects, features and advantages of the present inventionApplying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the applicationFeature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used alsoTo be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described belowSpecific embodiment limitation.
Fig. 1 shows the flow diagram of the method for visualizing of the structured medical data of the embodiment of the present invention.
As shown in Figure 1, the method for visualizing of structured medical data according to an embodiment of the present invention, specifically includes to flow downJourney step:
Step 102, the essential information for each preset structure variable for including in each medical medical record is obtained.
It is understood that it is each medical treatment medical record in include preset structure variable at least may include: the age, gender,Disease, department, medical expense, treatment time etc..
Step 104, it is formed according to the statistic analysis result of the essential information to each preset structure variable each defaultVariable relation view between the corresponding information arrangement view of structured variable and/or the different preset structure variables of formation.
Step 106, export and show information arrangement view and/or variable relation view.
In this embodiment, it is carried out by the essential information to each preset structure variable for including in each medical medical recordStatistical analysis, and then can not only draw its information arrangement view for each preset structure variable and can also draw and embody notThe variable relation view of relevance between same preset structure variable, and it is able to carry out information arrangement view and/or variableThe output of relational view is shown, is realized the visualization processing to structured medical data, is allowed the user to more intuitivelyThe essential information situation for understanding structured medical data, so that user more easily digs structured medical dataPick, not only saves human resources, additionally it is possible to improve the efficiency of data mining.
Further, in the above-described embodiments, before step 102, the structured medical data of the embodiment of the present inventionMethod for visualizing can also include following below scheme step:
It detects whether to receive the sort instructions for each medical medical record that user inputs；If so, according in sort instructionsThe default classification standard for including classifies all medical medical records, each of to obtain medical medical record group difference for classificationIt executes the essential information for obtaining each preset structure variable for including in wherein each medical medical record and forms information arrangement viewAnd/or the step of variable relation view；If it is not, directly executing each preset structure variable for obtaining and including in each medical medical recordThe step of essential information.
In this embodiment, further in order to more easily realize the visualization of structured medical data, and make to obtainPreset structure variable information arrangement view and/or preset structure variable between variable relation view more intuitivelyShow its essential information data cases, can previously according to user actual demand to all doctors for needing to carry out visualization processingIt treats medical record to classify, realizes the data mining of more targeted structured medical data.
Specifically, can classify according to disease category, such as cardiovascular and cerebrovascular disease, skin disease, gynecological disease etc..
Further, in the above-described embodiments, the group that the essential information of each preset structure variable one or more of includesIt closes: variable's attribute information, types of variables information and variable-value information.
It is understood that the essential information for each preset structure variable for including in each medical treatment medical record includes but is not limited toFollowing one or a variety of combinations: variable's attribute information, such as character attibute, numerical attribute, time attribute etc.；Types of variables letterBreath, such as discrete variable, continuous variable；Variable-value information, such as value interval, value classification etc..
Further, in the above-described embodiments, according to the basic of each preset structure variable described in step 104The scheme that the statistic analysis result of information forms the corresponding information arrangement view of each preset structure variable can be executed specificallyAre as follows:
When determining that it is continuous change according to the variable's attribute information and/or types of variables information of each preset structure variableWhen amount, the first object variable-value letter in the variable-value information of each preset structure variable in pre-set interval is obtainedBreath indicates the corresponding information arrangement view of first object variable-value information using the first preset pattern.
It is understood that when preset structure variable is continuous variable, it can be according to point of continuous value intervalCloth feature, intercepts significant section, that is, filters out exceptional value or unessential section, its value interval is made to be located at pre-set intervalIt is interior, the information arrangement view of continuous variable can be specifically shown by histogram, box traction substation etc..
Further, when showing the information arrangement view of continuous variable, it can also count and show its average value, centreValue, median, most value, variance.
When determining that it is discrete change according to the variable's attribute information and/or types of variables information of each preset structure variableWhen amount, the second target variable value that the frequency in the variable-value information of each preset structure variable is higher than preset value is obtainedInformation indicates the corresponding information arrangement view of the second target variable value information using the second preset pattern.
It is understood that when preset structure variable is discrete variable, it can be according to the preset structure variableThe frequency disribution feature of value classification selects the value classification that frequency is higher than preset value, can specifically pass through pie chart, bar chart etc.Show the information arrangement view of discrete variable.
Further, when showing the information arrangement view of discrete variable, it can also count and show its value classificationThe average value of frequency, median, median, most value and variance.
In this embodiment, it has determined belonging to it when carrying out analysis by the essential information to each preset structure variableTypes of variables after then can be using correspondingly visualized graphs, specifically can basis to its further progress visualization processingThe variable's attribute information and/or types of variables information of each preset structure variable determine its types of variables, and then right based on thisIts variable-value information carries out automatic processing and is then drawn with that reasonably can filter out bad data point by display dataImage hotpoint visualization；And through the foregoing embodiment, the bad data of preset structure variable can be filtered out, basisRationally, significant data construct its information arrangement view, to ensure that the accuracy of building information arrangement view.
It will be further understood that pre-set interval and use for being filtered processing to the value condition of continuous variableCan specifically it be arranged according to actual needs in the preset value that the value condition to discrete variable is filtered processing.
It will be further understood that when preset structure variable be can be with the variable of natural ordering when, such as time, thenIt can first be ranked up, then carry out the filtering and correspondingly visualization processing of value again.
Further, in the above-described embodiments, according to the basic of each preset structure variable described in step 104The statistic analysis result of information formed the variable relation view between different preset structure variables scheme can specifically according toProcess as shown in Figure 2 is executed, comprising:
Step S20 obtains at least one default statistics theme.
It is understood that
Step S22 is determined in each preset structure variable and is preset the statistics associated target structural variable of theme with each.
Step S24 is formed and each default system according to the statistic analysis result of the essential information to target structural variableCount the variable relation view between the associated each target structural variable of theme, and using third preset pattern indicate with it is each pre-If counting the variable relation view between the associated each target structural variable of theme.
In this embodiment it is possible to which the different preset structureizations of building become by way of presetting common statistics themeVariable relation view between amount summarizes preset structure variable related with same default statistics theme, and baseIt is generated in the statistical analysis of the essential information to the target structural variable filtered out associated each with same default statistics themeVariable relation view between target structural variable can further use parallel coordinates figure, star graph, matrix scatterplotFigure, polyhedron figure etc. more intuitively show the statistical relationship between different structured variables.
Wherein, presetting statistics theme includes but is not limited to: medical expense theme, therapeutic effect theme, disease theme, timeTheme.
Further, in the above-described embodiments, the method for visualizing of structured medical data further include: when receiving userWhen the regulating command of input, according to the corresponding default classification standard, pre-set interval, pre- of adjusting of the adjustment parameter for including in regulating commandIf one or more of value, default statistics theme, the first preset pattern, the second preset pattern and third preset pattern.
In this embodiment, in order to meet the needs of users the visualization result to structured medical data more, withIt, can be during realizing visually and after the corresponding view of output according to the demand of user convenient for subsequent data mining etc.Corresponding parameter is adjusted, realizes human-computer interaction function friendly in the visualization process of structured medical data, promotes user's bodyIt tests；Specifically, user at least can be to default classification standard, each preset structure of filtering for classifying to medical medical recordThe pre-set interval and preset value of the value of variable and the default statistics theme of setting, and structured medical number can also be changedAccording to visual view.
For example, user can adjust the transverse and longitudinal coordinate range of histogram by way of mouse or dialog box；User canField relational graph required for medical problem and the medical problem is defined with oneself, it can be with the customized level for dividing fieldStandard and condition, and be adjusted, to realize human-computer interaction.
The visualization scheme of structured medical data of the invention is illustrated by taking cardiovascular and cerebrovascular disease as an example below.ToolBody, the preset structure variable for including in each medical medical record of cardiovascular and cerebrovascular disease include: the age, gender, disease, department,Medical expense, treatment time etc..
Further, gender, disease name, department's title can be determined according to the essential information of each preset structure variableIt for character attibute and is discrete variable, age, medical expense are numerical attribute and are continuous variable, and when treatment time isBetween attribute and can be considered discrete variable.
For example, for discrete variable disease and department, each disease name and each department's title are exactly its valueClassification, and since disease number and department's number are more, the higher several disease names of frequency of value classification can be selectedThe drafting for carrying out the information arrangement view of discrete variable, can draw pie chart or bar chart, for example department's frequency is higher includesCardiological, Neurology, neurosurgery, information distributing plan are as shown in Figure 3；And histogram can be used for continuous variable medical expenseFigure carries out the drafting of information distributing plan, and medical expense can also specifically refine are as follows: cost of hospitalization, Operation Fee, drug take, nurse is taken andTotal medical expense etc..
Further, if above-mentioned variable is the variable of predefined type, the variable of the predefined type is can be with natural orderingVariable, such as time, age, then can first sort and construct information distributing plan again, so that the information distributing plan constructed is moreAdded with order, user is facilitated to check.
Further, for the variable relation view between different preset structure variables, for example, for disease main body,All ages and classes can be drawn, different sexes obtain the distribution map of certain disease；It is the theme with medical expense, different diseases can be drawnMedical expense distribution map between disease, different department, the relational graph between total cost and surgery cost etc.；Based on treatment timeTopic, can draw various disease in the incidence graph of Various Seasonal；Further in these relational graphs, different changes can also be calculatedThe statistics such as correlativity coefficient and design conditions probability between amount.
As shown in figure 4, the variable relation view of building is tetrahedral figure, four vertex in the variable relation viewRespectively correspond a variable, i.e., this four variables of a total of season, disease, medical expense and treatment time.In the variable relationThe vertex size of each variable is different in view, and vertex size reflects the score of variable, and line segment is thick between two variablesIt is carefully also different, line segment is thicker, illustrates that the correlation between the two variables is bigger.
Fig. 5 shows the schematic block diagram of the visualization device of the structured medical data of the embodiment of the present invention.
As shown in figure 5, the visualization device 50 of structured medical data according to an embodiment of the present invention, comprising: obtain mouldBlock 502, processing module 504 and output module 506.
Wherein, the essential information that module 502 is used to obtain each preset structure variable in each medical medical record included is obtained；Processing module 504 is used for according to the statistical analysis to the essential information for obtaining each preset structure variable that module 502 obtainsAs a result it forms the corresponding information arrangement view of each preset structure variable and/or is formed between different preset structure variablesVariable relation view；Output module 506 is for exporting and showing information arrangement view and/or variable relation view.
In this embodiment, it is carried out by the essential information to each preset structure variable for including in each medical medical recordStatistical analysis, and then can not only draw its information arrangement view for each preset structure variable and can also draw and embody notThe variable relation view of relevance between same preset structure variable, and it is able to carry out information arrangement view and/or variableThe output of relational view is shown, is realized the visualization processing to structured medical data, is allowed the user to more intuitivelyThe essential information situation for understanding structured medical data, so that user more easily digs structured medical dataPick, not only saves human resources, additionally it is possible to improve the efficiency of data mining.
Further, as shown in figure 5, in the above-described embodiments, the visualization device 50 of structured medical data further include:Detection module 508 and categorization module 510.
Wherein, detection module 508 is used to obtain each preset structureization for including in each medical medical record in acquisition module 502 and becomeBefore the essential information of amount, the sort instructions for each medical medical record for receiving user's input are detected whether；Categorization module 510When the detection of detection module 508 receives sort instructions, according to the default classification standard for including in sort instructions by all medical treatmentMedical record is classified, and executing acquisition respectively each of to obtain medical medical record group for classification wherein wraps in each medical treatment medical recordThe essential information of each preset structure variable contained and the step of form information arrangement view and/or variable relation view；AndModule 502 is obtained when the detection of detection module 508 does not receive sort instructions, directly execution, which obtains in each medical medical record, includesThe step of essential information of each preset structure variable.
In this embodiment, further in order to more easily realize the visualization of structured medical data, and make to obtainPreset structure variable information arrangement view and/or preset structure variable between variable relation view more intuitivelyShow its essential information data cases, can previously according to user actual demand to all doctors for needing to carry out visualization processingIt treats medical record to classify, realizes the data mining of more targeted structured medical data.
Further, in the above-described embodiments, the group that the essential information of each preset structure variable one or more of includesIt closes: variable's attribute information, types of variables information and variable-value information；And processing module 504 is specifically used for: when according to eachWhen the variable's attribute information and/or types of variables information of preset structure variable determine that it is continuous variable, obtain each defaultFirst object variable-value information in the variable-value information of structured variable in pre-set interval, using the first default figureShape indicates the corresponding information arrangement view of first object variable-value information；When the variable category according to each preset structure variableProperty information and/or types of variables information when determining that it is discrete variable, obtain the variable-value letter of each preset structure variableFrequency in breath is higher than the second target variable value information of preset value, indicates that the second target variable takes using the second preset patternThe corresponding information arrangement view of value information.
In this embodiment, the essential information for each preset structure variable for including in each medical medical record includes but is not limited toFollowing one or a variety of combinations: variable's attribute information, such as character attibute, numerical attribute, time attribute etc.；Types of variables letterBreath, such as discrete variable, continuous variable；Variable-value information, such as value interval, value classification etc..
Further, change belonging to it has been determined when carrying out analysis by the essential information to each preset structure variableIt then can be using correspondingly visualized graphs, specifically can be according to each to its further progress visualization processing after amount typeThe variable's attribute information and/or types of variables information of preset structure variable determine its types of variables, and then are become based on this to itIt measures value information and carries out automatic processing, reasonably bad data point can be filtered out by display data, then graphingIt realizes visualization, then when preset structure variable is continuous variable, can be cut according to the characteristic distributions of continuous value intervalSignificant section is taken, that is, filters out exceptional value or unessential section, is located at its value interval in pre-set interval, specificallyThe information arrangement view of continuous variable can be shown by histogram, box traction substation etc., and when preset structure variable is discrete changeWhen amount, frequency taking higher than preset value can be selected according to the frequency disribution feature of the value classification of the preset structure variableIt is worth classification, the information arrangement view of discrete variable can be specifically shown by pie chart, bar chart etc..It, can be with by above schemeThe bad data of preset structure variable is filtered out, only constructs its information arrangement view according to reasonable, significant data, fromAnd it ensure that the accuracy of building information arrangement view.
Wherein, for the value condition to continuous variable it is filtered the pre-set interval of processing and for discrete variableThe preset value that value condition is filtered processing can be specifically arranged according to actual needs.Further, work as preset structureChanging variable is when can be with the variable of natural ordering, such as the time, then can first be ranked up, then carry out again the filtering of value withAnd correspondingly visualization processing.
Further, in the above-described embodiments, processing module 504 specifically includes: acquisition submodule 5042 determines submodule5044 and processing submodule 5046, as shown in Figure 6.
Wherein, acquisition submodule 5042 is for obtaining at least one default statistics theme；Determine that submodule 5044 is used for reallyThe statistics associated target structural variable of theme is preset with each in fixed each preset structure variable；Processing submodule 5046 is used forIt is formed and each default statistics associated each mesh of theme according to the statistic analysis result of the essential information to target structural variableThe variable relation view between structured variable is marked, and indicates associated with each default statistics theme using third preset patternVariable relation view between each target structural variable.
In this embodiment it is possible to which the different preset structureizations of building become by way of presetting common statistics themeVariable relation view between amount summarizes preset structure variable related with same default statistics theme, and baseIt is generated in the statistical analysis of the essential information to the target structural variable filtered out associated each with same default statistics themeVariable relation view between target structural variable can further use parallel coordinates figure, star graph, matrix scatterplotFigure, polyhedron figure etc. more intuitively show the statistical relationship between different structured variables.
Wherein, presetting statistics theme includes but is not limited to: medical expense theme, therapeutic effect theme, disease theme, timeTheme.
Further, as shown in figure 5, in the above-described embodiments, the visualization device 50 of structured medical data further include:Adjustment module 512, for being corresponded to according to the adjustment parameter for including in regulating command when receiving the regulating command of user's inputAdjust default classification standard, pre-set interval, preset value, default statistics theme, the first preset pattern, the second preset pattern and thirdOne or more of preset pattern.
In this embodiment, in order to meet the needs of users the visualization result to structured medical data more, withIt, can be during realizing visually and after the corresponding view of output according to the demand of user convenient for subsequent data mining etc.Corresponding parameter is adjusted, realizes human-computer interaction function friendly in the visualization process of structured medical data, promotes user's bodyIt tests；Specifically, user at least can be to default classification standard, each preset structure of filtering for classifying to medical medical recordThe pre-set interval and preset value of the value of variable and the default statistics theme of setting, and structured medical number can also be changedAccording to visual view.
As an embodiment of the present invention, a kind of server is proposed, including described in any one of embodiment as aboveThe visualization device 50 of structured medical data, therefore, the server have the visualization device 50 of the structured medical dataAll beneficial technical effects, details are not described herein.
Fig. 7 shows the schematic block diagram of the computer equipment of the embodiment of the present invention.
As shown in fig. 7, the computer equipment 70 of embodiment according to an embodiment of the present invention, including memory 702, processor704 and it is stored in the computer program that can be run on the memory 702 and on the processor 704, wherein memory 702It can be connected by bus between processor 704, the processor 704 is for executing the computer stored in memory 702The step of as above method for visualizing of structured medical data as described in the examples is realized when program.
Step in the method for the embodiment of the present disclosure can be sequentially adjusted, merged and deleted according to actual needs.
Unit in the visualization device and computer equipment of the structured medical data of the embodiment of the present disclosure can basisActual needs is combined, divided and deleted.
According to the embodiment of the present disclosure, a kind of computer readable storage medium is proposed, is stored thereon with computer program, instituteState the feature extracting method that the structured medical data as described in above-described embodiment is realized when computer program is executed by processorThe step of.
Further, one of ordinary skill in the art will appreciate that whole in the various methods of above-described embodimentOr part steps are relevant hardware can be instructed to complete by program, which can store computer-readable deposits in oneIn storage media, storage medium includes read-only memory (Read-Only Memory, ROM), random access memory (RandomAccess Memory, RAM), it is programmable read only memory (Programmable Read-only Memory, PROM), erasableOnly except programmable read only memory (Erasable Programmable Read Only Memory, EPROM), disposable programmableReading memory (One-time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-onlyMemory (Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM(Compact Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage,Or it can be used in any other computer-readable medium of carrying or storing data.
Further, above-mentioned computer equipment can hold for PC (Personal Computer, PC).
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, according to the technical solution of the present invention, can be effectiveThe visualization to structured medical data is realized on ground, so that user more easily digs structured medical dataPick.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this fieldFor art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repairChange, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.