CN110415779A - Insulation validation checking method, apparatus, equipment and storage medium - Google Patents
Insulation validation checking method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN110415779A CN110415779A CN201910757551.5A CN201910757551A CN110415779A CN 110415779 A CN110415779 A CN 110415779A CN 201910757551 A CN201910757551 A CN 201910757551A CN 110415779 A CN110415779 A CN 110415779A
- Authority
- CN
- China
- Prior art keywords
- data
- insulation
- body temperature
- temperature data
- characteristic parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000009413 insulation Methods 0.000 title claims abstract description 109
- 238000010200 validation analysis Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000036760 body temperature Effects 0.000 claims abstract description 131
- 238000012795 verification Methods 0.000 claims abstract description 65
- 206010002091 Anaesthesia Diseases 0.000 claims abstract description 43
- 230000037005 anaesthesia Effects 0.000 claims abstract description 43
- 238000001356 surgical procedure Methods 0.000 claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 230000002980 postoperative effect Effects 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000013075 data extraction Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000011084 recovery Methods 0.000 abstract description 8
- 238000011002 quantification Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 10
- 238000003745 diagnosis Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 4
- 238000007477 logistic regression Methods 0.000 description 4
- 241000144958 Piaractus mesopotamicus Species 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000004321 preservation Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000000586 desensitisation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 208000011580 syndromic disease Diseases 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 208000034657 Convalescence Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004992 fission Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000020509 sex determination Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Epidemiology (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention discloses a kind of Insulation validation checking method, apparatus, equipment and storage medium, this method comprises: the initial temperature data of acquisition target object, carries out pretreatment to initial temperature data and obtain effective temperature data;Data fitting is carried out to effective temperature data, and the screening of body temperature characteristic parameter is carried out based on curve after fitting and obtains current body temperature characteristic parameter;Current body temperature characteristic parameter is input to validation verification model, and it is whether effective according to the anesthesia surgery Insulation that model output result judgement currently takes target object, by the temperature data for then passing through acquisition user, temperature data is fitted and body temperature characteristic parameter screens, then the body temperature characteristic parameter filtered out is input to validation verification model, determine whether the Insulation currently taken to patient is effective by validation verification model, the Accurate Prediction to Insulation can be realized with the means of Relative quantification, whether effective reference can be provided by quick-recovery fastly for patient with operation.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of Insulation validation checking method, apparatus, set
Standby and storage medium.
Background technique
Existing research shows that having a great impact using convalescence of the Insulation to anesthesia surgery patient, pass through patient
Crowd is grouped control experiment, observes that patient monitors after being anesthetized during capable of shortening anesthesia surgery using effective Insulation
The recovery time of therapeutic room (Postanesthesia care unit, PACU).
Current result of study and investigation report can not mostly provide the result index of Relative quantification to predict to anesthesia
Whether the Insulation that patient with operation is taken is effective, if can really shorten the recovery time of patient.Therefore, how accurately
Whether prediction judgement is effectively carried out to the Insulation that anesthesia surgery patient currently takes, just becomes a skill urgently to be resolved
Art problem.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of Insulation validation checking method, apparatus, equipment and storages
Medium, it is intended to solve whether the prior art can not effectively carry out Accurate Prediction to the Insulation that anesthesia surgery patient currently takes
The technical issues of.
To achieve the above object, the present invention provides a kind of Insulation validation checking method, the method includes with
Lower step:
The initial temperature data for acquiring target object, pre-processes the initial temperature data, to obtain effective body
Warm data;
Data fitting is carried out to effective temperature data, and body temperature is carried out based on the current matched curve after data fitting
Characteristic parameter screening, to obtain current body temperature characteristic parameter;
The current body temperature characteristic parameter is input to validation verification model trained in advance, and is exported and is tied according to model
Whether the anesthesia surgery Insulation that fruit judgement currently takes the target object is effective.
Preferably, the initial temperature data of the acquisition target object, pre-processes the initial temperature data, with
Before the step of obtaining effective temperature data, the method also includes:
It obtains and several is judged as the corresponding diagnostic data of effective anesthesia surgery Insulation in advance;
Temperature data extraction is carried out to the diagnostic data, to obtain different objects during anesthesia surgery Insulation
Corresponding history temperature data;
The history temperature data is pre-processed, and data fitting is carried out to pretreated history temperature data,
To obtain effective matched curve;
Obtain the body temperature characteristic parameter of default dimension respectively based on effective matched curve, and to each body temperature characteristic parameter
Tag definition is carried out respectively, the body temperature characteristic parameter after obtaining tag definition;
The training set that verifying collection and preset quantity are established according to the body temperature characteristic parameter after tag definition, according to the instruction
Practice collection to be respectively trained default regression model, to obtain the regression model to be verified of the preset quantity;
Verification result is verified and is obtained to the regression model to be verified respectively according to verifying collection, based on described
Verification result filters out validation verification model from the regression model to be verified.
Preferably, described that the history temperature data is pre-processed, and to pretreated history temperature data into
Row data fitting, the step of to obtain effective matched curve, comprising:
Data cleansing is carried out to the history temperature data, to obtain target temperature data;
It detects in the target temperature data with the presence or absence of the invalid temperature data for being not belonging to preset temperature threshold range;
If it exists, then data dump is carried out to the ineffective temperature data, and to the target temperature data after data dump
Interpolation processing is carried out, to obtain pretreated history temperature data;
Data fitting is carried out to the pretreated history temperature data, obtains effective matched curve.
Preferably, described that data fitting is carried out to the pretreated history temperature data, obtain effective matched curve
The step of, comprising:
Piecewise fitting is carried out respectively by preset period of time to the pretreated history temperature data, it is corresponding quasi- to obtain
Close curved section, the preset period of time includes in preoperative, art, postoperative, postanesthesia intensive care unit and body temperature return it is normal;
Quadratic fit is carried out to the matched curve section, obtains effective matched curve.
Preferably, the body temperature characteristic parameter for obtaining default dimension respectively based on effective matched curve, and to each
The step of body temperature characteristic parameter carries out tag definition respectively, body temperature characteristic parameter after obtaining tag definition, comprising:
Obtain the body temperature characteristic parameter of default dimension respectively based on effective matched curve;
The significance level coefficient of each body temperature characteristic parameter is calculated using random forests algorithm, and right by sequence from big to small
The significance level coefficient is ranked up;
Target signature parameter is filtered out from the body temperature characteristic parameter according to ranking results, and according to default validity mark
Label carry out tag definition to the target signature parameter respectively, the body temperature characteristic parameter after obtaining tag definition.
Preferably, described that the regression model to be verified is verified respectively according to verifying collection and obtains verifying knot
Fruit, the step of validation verification model is filtered out from the regression model to be verified based on the verification result, comprising:
According to the verifying collection verification result, the verifying are verified and obtained to the regression model to be verified respectively
It as a result include the accuracy rate and recall rate of anesthesia surgery Insulation availability deciding in;
Validation verification mould is filtered out from the regression model to be verified according to the accuracy rate and the recall rate
Type.
Preferably, described to have been filtered out from the regression model to be verified according to the accuracy rate and the recall rate
The step of effect property verifying model, comprising:
According to the accuracy rate and the recall rate, scored by preset formula each regression model to be verified,
Obtain appraisal result;
Validation verification model is filtered out from the regression model to be verified according to the appraisal result;
Wherein, the preset formula are as follows:
Fscore=(2*precision*recall)/(precision+recall)
In formula, FscoreFor appraisal result, precision is accuracy rate, and recall is recall rate.
In addition, to achieve the above object, the present invention also proposes a kind of Insulation validation checking device, described device packet
It includes:
Data processing module carries out the initial temperature data pre- for acquiring the initial temperature data of target object
Processing, to obtain effective temperature data;
Parameter acquisition module, for carrying out data fitting to effective temperature data, and based on working as after data fitting
Preceding matched curve carries out the screening of body temperature characteristic parameter, to obtain current body temperature characteristic parameter;
Measure authentication module, for the current body temperature characteristic parameter to be input to validation verification mould trained in advance
Type, and it is whether effective according to the anesthesia surgery Insulation that model output result judgement currently takes the target object.
In addition, to achieve the above object, the present invention also proposes a kind of Insulation validation checking equipment, the equipment packet
It includes: the Insulation validity inspection that memory, processor and being stored in can be run on the memory and on the processor
Ranging sequence, the Insulation validation checking program are arranged for carrying out Insulation validation checking method as described above
The step of.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, heat preservation is stored on the storage medium
Measure validation checking program, the Insulation validation checking program realize guarantor as described above when being executed by processor
The step of warm measure validation checking method.
The present invention pre-processes initial temperature data by the initial temperature data of acquisition target object, to obtain
Effective temperature data;Data fitting is carried out to effective temperature data, and body is carried out based on the current matched curve after data fitting
Wyntet's sign choice of parameters, to obtain current body temperature characteristic parameter;Current body temperature characteristic parameter is input to the effective of training in advance
Property verifying model, and according to model export result judgement currently whether have to the anesthesia surgery Insulation that target object is taken
Effect is fitted temperature data and body temperature characteristic parameter screens, then will by then passing through the temperature data of acquisition user
The body temperature characteristic parameter filtered out is input to validation verification model trained in advance, is determined by validation verification model current
Whether the Insulation taken patient is effective, so as to be realized with the means of Relative quantification to the accurate pre- of Insulation
It surveys, whether can provide effective reference by quick-recovery fastly for patient with operation.
Detailed description of the invention
Fig. 1 is the structure of the Insulation validation checking equipment for the hardware running environment that the embodiment of the present invention is related to
Schematic diagram;
Fig. 2 is the flow diagram of Insulation validation checking method first embodiment of the present invention;
Fig. 3 is the flow diagram of Insulation validation checking method second embodiment of the present invention;
Fig. 4 is the flow diagram of Insulation validation checking method 3rd embodiment of the present invention;
Fig. 5 is the structural block diagram of Insulation validation checking device first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is that the Insulation validation checking for the hardware running environment that the embodiment of the present invention is related to is set
Standby structural schematic diagram.
As shown in Figure 1, the Insulation validation checking equipment may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory
1005, temperature sensor (not shown).Wherein, communication bus 1002 is for realizing the connection communication between these components,
Temperature sensor is for acquiring temperature data.User interface 1003 may include display screen (Display), input unit such as key
Disk (Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 can
Choosing may include standard wireline interface and wireless interface (such as Wireless Fidelity (WIreless-FIdelity, WI-FI) interface).
Memory 1005 can be random access memory (Random Access Memory, RAM) memory of high speed, be also possible to
Stable nonvolatile memory (Non-Volatile Memory, NVM), such as magnetic disk storage.Memory 1005 is optional
It can also be the storage device independently of aforementioned processor 1001.
Insulation validation checking is set it will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted
Standby restriction may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
As shown in Figure 1, as may include operating system, data storage mould in a kind of memory 1005 of storage medium
Block, network communication module, Subscriber Interface Module SIM and Insulation validation checking program.
In Insulation validation checking equipment shown in Fig. 1, network interface 1004 is mainly used for and network server
Carry out data communication;User interface 1003 is mainly used for carrying out data interaction with user;Insulation validation checking of the present invention
Processor 1001, memory 1005 in equipment can be set in Insulation validation checking equipment, the Insulation
Validation checking equipment calls the Insulation validation checking program stored in memory 1005 by processor 1001, and holds
Row Insulation validation checking method provided in an embodiment of the present invention.
The embodiment of the invention provides a kind of Insulation validation checking methods, are present invention heat preservation referring to Fig. 2, Fig. 2
The flow diagram of measure validation checking method first embodiment.
In the present embodiment, the Insulation validation checking method the following steps are included:
Step S10: acquiring the initial temperature data of target object, pre-processes to the initial temperature data, to obtain
Take effective temperature data;
It should be noted that the executing subject of the present embodiment method can be with data processing, network communication and journey
The calculating service equipment (hereinafter referred to as " detection device ") of sort run function, such as smart phone, tablet computer, PC
Deng.Anesthesia surgery was carried out in the target object, that is, preset period of time and took it (following letter of anesthesia surgery Insulation
Claim " Insulation ") patient with operation.
It should be understood that the initial temperature data, i.e., body temperature acquires equipment from starting to collect during acquisition terminates
The temperature data of collected above-mentioned patient with operation.In view of anesthesia surgery patient need to generally undergo in preoperative, art, it is postoperative,
PACU and body temperature return five stages such as normal, and whether the anesthesia surgery measure currently taken patient with operation for prediction is effective, this
The acquisition period of initial temperature data described in embodiment is preferably preoperative, arrives postoperative this period in art.
It will be appreciated that initially collected temperature data is (i.e. described first under normal conditions due to the problem of acquiring equipment
Beginning temperature data), there may be the case where data distortion (such as acquisition delay, acquisition interruption, temperature data mutation etc.), because
This present embodiment will be pre-processed (including denoising/cleaning, interpolation etc.) to collected initial temperature data, effective to obtain
Temperature data.
Step S20: data fitting is carried out to effective temperature data, and based on the current matched curve after data fitting
The screening of body temperature characteristic parameter is carried out, to obtain current body temperature characteristic parameter;
It should be noted that data fitting is also known as curve matching, it is commonly called as drawing curve, is a kind of available data to be penetrated
Mathematical method substitutes into the representation of a numerical expression.Body temperature physical sign parameters described in the present embodiment can be and can characterize or shadow
Ring organisms wyntet's sign data, body temperature special parameter described in the present embodiment include but is not limited to different periods (it is such as preoperative,
In art, it is postoperative) matched curve area, the matched curve area of unit time, the mean body temperature value of each period, highest body
Warm, minimum body temperature, the parameters such as body temperature standard deviation.
It will be appreciated that body temperature acquires equipment during carrying out body temperature acquisition, the temperature data that actual acquisition arrives can
Can be several independent data points, and or intermittent temperature curve, if being directly based upon these data points or intermittent temperature
Curve carries out the efficiency analysis of Insulation, and it is not accurate enough on the one hand to will lead to analysis result, on the other hand also results in point
Consumption is longer when analysis, once Insulation is judged as in vain, then temporarily changes Insulation and will just be unfavorable for the quick extensive of patient
It is multiple.
In view of drawbacks described above, it is quasi- first can to carry out data to the effective temperature data got for detection device in the present embodiment
It closes the current matched curve after being then based on data fitting to obtain current matched curve and carries out body temperature characteristic parameter screening again,
Obtain current body temperature characteristic parameter.
Step S30: the current body temperature characteristic parameter is input to validation verification model trained in advance, and according to mould
Whether the anesthesia surgery Insulation that type output result judgement currently takes the target object is effective.
It should be noted that validation verification model described in the present embodiment, can be the logic that training is completed in advance and returns
Return model.Logistic regression (Logistic Regression, LR) is also known as logistic regression analysis, is in classification and prediction algorithm
One kind, there are two usage scenario is general: first is used to predict, second finds the influence factor of dependent variable.Logistic regression can
The probability that future outcomes are occurred by the performance of historical data is predicted.For example, anesthesia surgery is protected in the present embodiment
Whether warm measure is effectively set as dependent variable, by the body temperature characteristic parameter of patient with operation, such as the body temperature, flat of patient's different periods
Equal body temperature value, highest body temperature, minimum body temperature, body temperature standard deviation etc. are set as independent variable, predict Insulation according to characteristic parameter
Whether effectively, output result is that " 0 " then Insulation is invalid, is that " 1 " then Insulation is effective.
In the concrete realization, the current body temperature characteristic parameter that detection device can will acquire is input to the effective of training in advance
Property verifying model, then according to model export result judgement currently whether have to the anesthesia surgery Insulation that target object is taken
Effect continues to execute current Insulation if effectively;If invalid, medical staff is reminded to take phase by default prompting mode
The other Insulations answered, to guarantee the normal fast quick-recovery of patient with operation.
The present embodiment pre-processes initial temperature data, by the initial temperature data of acquisition target object to obtain
Take effective temperature data;Data fitting is carried out to effective temperature data, and is carried out based on the current matched curve after data fitting
Body temperature characteristic parameter screening, to obtain current body temperature characteristic parameter;Current body temperature characteristic parameter is input to having for training in advance
Effect property verifying model, and export whether result judgement currently has the anesthesia surgery Insulation that target object is taken according to model
Effect is fitted temperature data and body temperature characteristic parameter screens, then will by then passing through the temperature data of acquisition user
The body temperature characteristic parameter filtered out is input to validation verification model trained in advance, is determined by validation verification model current
Whether the Insulation taken patient is effective, so as to be realized with the means of Relative quantification to the accurate pre- of Insulation
It surveys, whether can provide effective reference by quick-recovery fastly for patient with operation.
With reference to Fig. 3, Fig. 3 is the flow diagram of Insulation validation checking method second embodiment of the present invention.
Based on above-mentioned first embodiment, in the present embodiment, before the step S10, the method also includes:
Step S01: acquisition is several to be judged as the corresponding diagnostic data of effective anesthesia surgery Insulation in advance;
It should be understood that determine to realize whether Insulation effectively carries out accurately prediction, current embodiment require that
It is (i.e. above-mentioned that a model for the Insulation progress validation verification currently used to anesthesia surgery patient is trained in advance
Validation verification model).
In the concrete realization, detection device can from hospital information system (Hospital Information System,
HIS several) are obtained in corresponding database, and the corresponding diagnosis and treatment data of effective anesthesia surgery Insulation are regarded as by doctor,
Then corresponding temperature data is extracted to from these diagnosis and treatment data.The diagnosis and treatment data can be patient with operation and register from operation
To the medical diagnosis on disease data being discharged from hospitals upon recovery in this period.
Step S02: carrying out temperature data extraction to the diagnostic data, is arranged with obtaining different objects in anesthesia surgery heat preservation
Corresponding history temperature data during applying;
In the concrete realization, detection device is reading different anesthesia surgery patients (the i.e. described different objects) from HIS
Diagnostic data after, can to the diagnostic data carry out temperature data extraction, anaesthetized with obtaining different anesthesia surgery patients
Corresponding history temperature data during operation Insulation.
Further, it is contemplated that the individual privacy of patient with operation, detection device described in the present embodiment is from the HIS
When reading the diagnosis and treatment data of patient, will also desensitization process be carried out to these diagnosis and treatment data, then again based on the diagnosis and treatment number after desensitization
According to progress temperature data extraction, such as by the name of patient, identification card number, cell-phone number etc. intermediate several are replaced with " * " number, are prevented
Led to the leakage of private information of patient in data transmission procedure by packet capturing.
Step S03: pre-processing the history temperature data, and counts to pretreated history temperature data
According to fitting, to obtain effective matched curve;
It should be noted that the pretreatment include temperature data is carried out denoise/clean, the operation such as interpolation.Data are clear
It washes, also referred to as denoises, i.e., lengthy and jumbled, chaotic, invalid " dirty data " is cleaned up, allow model that can input the data of high quality
Source.
In the concrete realization, detection device first can carry out data cleansing to the history temperature data, to obtain objective body
Warm data;Then it detects in the target temperature data with the presence or absence of the invalid body temperature number for being not belonging to preset temperature threshold range
According to;If it exists, then data dump is carried out to the ineffective temperature data, and the target temperature data after data dump is carried out slotting
Value processing, to obtain pretreated history temperature data;Finally the pretreated history temperature data is counted again
According to fitting, effective matched curve is obtained.Wherein, the preset temperature threshold range can be the human body set based on practical experience
Body temperature fluctuation range, such as (34 DEG C~39 DEG C).
Data cleansing described in the present embodiment removes and sometime puts duplicate temperature data in temperature data, and or
Be temperature data mutate temperature data (such as the body temperature of 6:01 partial objectives for object be 36 DEG C, 6:02 partial objectives for object
Body temperature then becomes 34.4 DEG C).The interpolation processing, i.e. Missing Data Filling, to caused by acquisition interruption and number in the present embodiment
It is filled according to the body temperature missing values generated after removing, segmentum intercalaris when specific filling mode may is that 1, be corresponded to using missing values
The preceding adjacent node of point and the average value of rear adjacent node are filled;2, according to the maximum temperature in collected temperature data
The average value of angle value and minimum temperature value is filled.Certainly, specific value filling mode the present embodiment really is not made specifically
Limitation.
Further, after pre-processing to history temperature data, detection device can be to pretreated history body
Warm data carry out piecewise fitting by preset period of time respectively, to obtain corresponding matched curve section, the preset period of time include it is preoperative,
In art, postoperative, postanesthesia intensive care unit and body temperature return it is normal;Then quadratic fit is carried out to the matched curve section again, obtained
Take effective matched curve.
For example, detection device according in preoperative, art, postoperative, PACU and body temperature return the corresponding pretreatment of normal five stages
Matched curve section 1, matched curve section 2, matched curve section 3, fitting are obtained after history temperature data piecewise fitting afterwards respectively
Then curved section 4 and matched curve section 5 are carrying out quadratic fit to above-mentioned 5 curved sections, acquisition one is complete and continuous
Curved section, i.e., described effective matched curve.
Step S04: the body temperature characteristic parameter of default dimension is obtained respectively based on effective matched curve, and to each body temperature
Characteristic parameter carries out tag definition respectively, the body temperature characteristic parameter after obtaining tag definition;
It should be understood that the body temperature special parameter as described in above-mentioned first embodiment includes the matched curve area of different periods
(the matched curve such as using body temperature as ordinate, using the time to seek preoperative, the postoperative art medium stage in the coordinate system of abscissa
Area), the matched curve area (such as matched curve area in art the latter hour) of unit time, each period be averaged
Body temperature value, highest body temperature, minimum body temperature, body temperature standard deviation etc..Correspondingly, the default dimension can be area under the curve dimension,
Body temperature draw value, body temperature upper lower limit value etc..
It should be noted that the tag definition carries out validity label to each body temperature characteristic parameter, such as will
The body temperature characteristic parameter that there is contribution to effective Insulation is labeled as " 1 ", on the contrary it is then labeled as " 0 ".
In the concrete realization, detection device can obtain respectively the body temperature feature of default dimension based on effective matched curve
Then parameter carries out tag definition to each body temperature characteristic parameter respectively, the body temperature characteristic parameter after obtaining tag definition.
Further, it is contemplated that there are many possible type of characteristic parameter that patient with operation Temperature changing is influenced under actual conditions,
But in fact their importance specific gravity shared when determining whether Insulation is effective are not quite similar, and some characteristic parameters are high,
Some is then lower.It therefore will also be to body temperature in order to improve efficiency the present embodiment Insulation validation checking method of model training
Characteristic parameter is screened, to obtain body temperature characteristic parameter of high importance.
Specifically, detection device can obtain respectively the body temperature characteristic parameter of default dimension based on effective matched curve;
The significance level coefficient of each body temperature characteristic parameter is calculated using random forests algorithm, and by sequence from big to small to described important
Degree coefficient is ranked up;Target signature parameter is filtered out from the body temperature characteristic parameter according to ranking results, and according to pre-
If validity label carries out tag definition to the target signature parameter respectively, the body temperature characteristic parameter after obtaining tag definition.
It should be understood that random forest refers to setting a kind of classifier for being trained sample and predicting using more,
It is integrated in the present embodiment, the building process of random forest generally comprises: 1, being concentrated use in from the training of body temperature characteristic parameter self-service
Put back to sampling selects m sample to method (Bootstraping method) at random, carries out n_tree sampling altogether, generates n_tree
Training set;2, for n_tree training set, n_tree decision-tree model is respectively trained;3, for single decision-tree model,
Assuming that the number of training sample feature is n, then being selected when dividing every time according to information gain/information gain ratio/gini index
Best feature is divided, and each tree all go down so always by division, until all training examples of the node belong to together
It is a kind of.Beta pruning is not needed in the fission process of decision tree;More decision trees of generation are formed into random forest.Classification is asked
Topic, chooses final classification result in a vote by more Tree Classifiers;For regression problem, then the mean value for setting predicted value by more determines
Final prediction result.
Significance level classification is carried out to body temperature characteristic parameter using random forests algorithm in the present embodiment, and according to classification
As a result the target signature parameter of significance level (the i.e. described significance level coefficient) sequence forward 90% is filtered out.
Step S05: the training set of verifying collection and preset quantity, root are established according to the body temperature characteristic parameter after tag definition
Default regression model is trained respectively according to the training set, to obtain the regression model to be verified of the preset quantity;
It should be understood that can be adopted to guarantee that the validity finally determined returns verifying model accuracy with higher
Default regression model is trained respectively with multiple training sets are established, to obtain multiple regression models to be verified;Then to institute
The regression model to be verified having collects the body temperature spy that different patient with operation are inputted to carry out result verification using the same verifying
Parameter is levied, then judges that different patient with operation are previous according to these body temperature characteristic parameters respectively by these disaggregated models to be verified
Effectively (being actually effective) whether the Insulation taken, finally wait for according to the output result of model to count each
Verify the predictablity rate of regression model.For example, model of a syndrome A to be tested has input the body temperature characteristic parameter of 20 patients, final mould
Type output result is that the Insulation of 19 patients is effective, and 1 invalid, then accuracy rate is (19/20) × 100%=95%.
In addition, it is necessary to illustrate, set element type included in different training sets or dimension are consistent, only
It is patient populations' difference, such as includes body temperature characteristic parameter of 20 patients with dimension, second instruction in first training set
Practicing concentration includes body temperature characteristic parameter of 40 patients with dimension.
Step S06: being verified and obtained verification result to the regression model to be verified respectively according to verifying collection,
Validation verification model is filtered out from the regression model to be verified based on the verification result.
In the concrete realization, detection device is in the regression model to be verified for training preset quantity according to different training sets
Afterwards, it can be collected by the verifying and be verified and obtained verification result to regression model to be verified respectively, be then based on described
Verification result filters out validation verification model from the regression model to be verified, such as by the height of accuracy rate, chooses
The highest regression model to be verified of accuracy rate is as the validation verification model.
The present embodiment is judged as the corresponding diagnostic data of effective anesthesia surgery Insulation by the way that acquisition is several in advance;
Temperature data extraction is carried out to diagnostic data, to obtain different objects corresponding history body during anesthesia surgery Insulation
Warm data;Then history temperature data is pre-processed, and data fitting is carried out to pretreated history temperature data, with
Obtain effective matched curve;Obtain the body temperature characteristic parameter of default dimension respectively based on effective matched curve again, and to each body temperature
Characteristic parameter carries out tag definition respectively, the body temperature characteristic parameter after obtaining tag definition;Then according to the body after tag definition
Wyntet's sign parameter establishes the training set of verifying collection and preset quantity, is instructed respectively to default regression model according to training set
Practice, to obtain the regression model to be verified of preset quantity;Finally regression model to be verified is tested respectively further according to verifying collection
Verification result is demonstrate,proved and obtained, validation verification model is filtered out from regression model to be verified based on verification result, can be guaranteed
The validation verification model accuracy with higher finally got and reliability.
With reference to Fig. 4, Fig. 4 is the flow diagram of Insulation validation checking method 3rd embodiment of the present invention.
Based on the various embodiments described above, in the present embodiment, the step S06 can include:
Step S061: respectively verifying the regression model to be verified according to verifying collection and obtains verifying knot
Fruit includes the accuracy rate and recall rate of anesthesia surgery Insulation availability deciding in the verification result;
It should be understood that being recall rate in the most basic index in two, the fields such as data retrieval, classification, identification, translation
(Recall Rate) and accuracy rate (Precision Rate), recall rate is also recall ratio, and accuracy rate is also precision ratio.Consider
Into realistic model training, thousands of a training sets usually will not be disposably established to carry out model training, if having in screening
Carried out when effect property verifying model only according to accuracy rate, can not guarantee to greatest extent the model filtered out be it is optimal,
Therefore the present embodiment preferably carries out model discrimination by accuracy rate and recall rate.
In the concrete realization, detection device can collect according to the verifying and verify respectively to the regression model to be verified
And verification result is obtained, then determine that each regression model to be verified is effective to anesthesia surgery Insulation according to verification result
The accuracy rate and recall rate of sex determination.
Step S062: it is filtered out from the regression model to be verified effectively according to the accuracy rate and the recall rate
Property verifying model.
In view of under actual conditions, recall rate and accuracy rate be it is shifting, be difficult to take into account, the present embodiment is considered as
One can integrate the mathematical formulae of two kinds of indexs to measure the superiority and inferiority of regression model to be verified.Specifically, detection device according to
The accuracy rate and the recall rate score to each regression model to be verified by preset formula, obtain appraisal result;
Then validation verification model is filtered out from the regression model to be verified according to the appraisal result;Wherein, described default
Formula are as follows:
Fscore=(2*precision*recall)/(precision+recall)
In formula, FscoreFor appraisal result, precision is accuracy rate, and recall is recall rate.
It should be noted that F in above-mentioned formulascoreNeither arithmetic mean of instantaneous value, nor geometrical mean, it is possible to understand that
It is geometrical mean square divided by arithmetic mean of instantaneous value.
In the concrete realization, each regression model to be verified is corresponding to be commented detection device being calculated according to above-mentioned preset formula
After point result, the appraisal result can be also ranked up by sequence from high to low, and first will be sorted according to ranking results
Appraisal result as target appraisal result;It is tested using the corresponding regression model to be verified of the target appraisal result as validity
Model of a syndrome.For example, the corresponding appraisal result of detection device calculated regression model a, b, c to be verified be 98.8%,
99.1%, 97.9%, learn that the appraisal result of sequence first is 99.1% after sequence sequence from high to low, so as to
Determine that optimal regression model to be verified is regression model b to be verified, it at this time can be using regression model b to be verified as described in
Validation verification model.
The present embodiment is described by being verified and being obtained verification result to regression model to be verified respectively according to verifying collection
It include the accuracy rate and recall rate of anesthesia surgery Insulation availability deciding in verification result;Then according in verification result
Including anesthesia surgery Insulation availability deciding accuracy rate and recall rate filtered out from regression model to be verified
Effect property verifying model, compared to the mode that validity model is selected is carried out according only to accuracy rate, the present embodiment can guarantee to sieve
The validation verification model selected is more in line with reality, further improves the accuracy of Insulation validation verification.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is effective to be stored with Insulation on the storage medium
Property detection program, the Insulation validation checking program realizes that Insulation as described above has when being executed by processor
The step of effect property detection method.
It is the structural block diagram of Insulation validation checking device first embodiment of the present invention referring to Fig. 5, Fig. 5.
As shown in figure 5, the Insulation validation checking device that the embodiment of the present invention proposes includes:
Data processing module 501 carries out the initial temperature data for acquiring the initial temperature data of target object
Pretreatment, to obtain effective temperature data;
Parameter acquisition module 502, for carrying out data fitting to the effective temperature data, and based on data fitting after
Current matched curve carries out the screening of body temperature characteristic parameter, to obtain current body temperature characteristic parameter;
Measure authentication module 503, for the current body temperature characteristic parameter to be input to validation verification trained in advance
Model, and it is whether effective according to the anesthesia surgery Insulation that model output result judgement currently takes the target object.
The present embodiment pre-processes initial temperature data, by the initial temperature data of acquisition target object to obtain
Take effective temperature data;Data fitting is carried out to effective temperature data, and is carried out based on the current matched curve after data fitting
Body temperature characteristic parameter screening, to obtain current body temperature characteristic parameter;Current body temperature characteristic parameter is input to having for training in advance
Effect property verifying model, and export whether result judgement currently has the anesthesia surgery Insulation that target object is taken according to model
Effect is fitted temperature data and body temperature characteristic parameter screens, then will by then passing through the temperature data of acquisition user
The body temperature characteristic parameter filtered out is input to validation verification model trained in advance, is determined by validation verification model current
Whether the Insulation taken patient is effective, so as to be realized with the means of Relative quantification to the accurate pre- of Insulation
It surveys, whether can provide effective reference by quick-recovery fastly for patient with operation.
Based on the above-mentioned Insulation validation checking device first embodiment of the present invention, propose that Insulation of the present invention is effective
The second embodiment of property detection device.
In the present embodiment, the Insulation validation checking device further includes model training module, the model instruction
Practice module, several is judged as the corresponding diagnostic data of effective anesthesia surgery Insulation in advance for obtaining;It examines described
Disconnected data carry out temperature data extraction, to obtain different objects corresponding history body temperature number during anesthesia surgery Insulation
According to;The history temperature data is pre-processed, and data fitting is carried out to pretreated history temperature data, to obtain
Effective matched curve;Obtain the body temperature characteristic parameter of default dimension respectively based on effective matched curve, and special to each body temperature
Sign parameter carries out tag definition respectively, the body temperature characteristic parameter after obtaining tag definition;According to the body temperature feature after tag definition
Parameter establishes the training set of verifying collection and preset quantity, is trained respectively to default regression model according to the training set,
To obtain the regression model to be verified of the preset quantity;The regression model to be verified is carried out respectively according to verifying collection
Verification result is verified and obtained, validation verification mould is filtered out from the regression model to be verified based on the verification result
Type.
Further, the model training module is also used to carry out data cleansing to the history temperature data, to obtain
Target temperature data;It detects in the target temperature data with the presence or absence of the invalid body temperature number for being not belonging to preset temperature threshold range
According to;If it exists, then data dump is carried out to the ineffective temperature data, and the target temperature data after data dump is carried out slotting
Value processing, to obtain pretreated history temperature data;Data fitting is carried out to the pretreated history temperature data,
Obtain effective matched curve.
Further, the model training module, be also used to the pretreated history temperature data by it is default when
Section carries out piecewise fitting respectively, and to obtain corresponding matched curve section, the preset period of time includes in preoperative, art, postoperative, anesthesia
Therapeutic room is monitored afterwards and body temperature returns often;Quadratic fit is carried out to the matched curve section, obtains effective matched curve.
Further, the model training module is also used to obtain default dimension respectively based on effective matched curve
Body temperature characteristic parameter;The significance level coefficient of each body temperature characteristic parameter is calculated using random forests algorithm, and by from big to small
Sequence the significance level coefficient is ranked up;Target spy is filtered out from the body temperature characteristic parameter according to ranking results
Parameter is levied, and tag definition is carried out to the target signature parameter according to default validity label respectively, after obtaining tag definition
Body temperature characteristic parameter.
Further, the model training module is also used to be collected according to the verifying respectively to the recurrence mould to be verified
Verification result is verified and obtained to type, includes the accuracy rate of anesthesia surgery Insulation availability deciding in the verification result
And recall rate;Validation verification is filtered out from the regression model to be verified according to the accuracy rate and the recall rate
Model.
Further, the model training module is also used to according to the accuracy rate and the recall rate, by default
Formula scores to each regression model to be verified, obtains appraisal result;According to the appraisal result from the recurrence to be verified
Validation verification model is filtered out in model;Wherein, the preset formula are as follows: Fscore=(2*precision*recall)/
(precision+recall)
In formula, FscoreFor appraisal result, precision is accuracy rate, and recall is recall rate.
The other embodiments or specific implementation of Insulation validation checking device of the present invention can refer to above-mentioned each side
Method embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as read-only memory/random access memory, magnetic disk, CD), including some instructions are used so that a terminal device (can
To be mobile phone, computer, server, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Insulation validation checking method, which is characterized in that the described method includes:
The initial temperature data for acquiring target object, pre-processes the initial temperature data, to obtain effective body temperature number
According to;
Data fitting is carried out to effective temperature data, and body temperature feature is carried out based on the current matched curve after data fitting
Choice of parameters, to obtain current body temperature characteristic parameter;
The current body temperature characteristic parameter is input to validation verification model trained in advance, and result is exported according to model and is sentenced
Whether the disconnected anesthesia surgery Insulation currently taken to the target object is effective.
2. the method as described in claim 1, which is characterized in that the initial temperature data of the acquisition target object, to described
Initial temperature data is pre-processed, the step of to obtain effective temperature data before, the method also includes:
It obtains and several is judged as the corresponding diagnostic data of effective anesthesia surgery Insulation in advance;
Temperature data extraction is carried out to the diagnostic data, it is corresponding during anesthesia surgery Insulation to obtain different objects
History temperature data;
The history temperature data is pre-processed, and data fitting is carried out to pretreated history temperature data, to obtain
Take effective matched curve;
It obtains the body temperature characteristic parameter of default dimension respectively based on effective matched curve, and each body temperature characteristic parameter is distinguished
Tag definition is carried out, the body temperature characteristic parameter after obtaining tag definition;
The training set that verifying collection and preset quantity are established according to the body temperature characteristic parameter after tag definition, according to the training set
Default regression model is trained respectively, to obtain the regression model to be verified of the preset quantity;
Verification result is verified and obtained to the regression model to be verified respectively according to verifying collection, is based on the verifying
As a result validation verification model is filtered out from the regression model to be verified.
3. method according to claim 2, which is characterized in that described to be pre-processed to the history temperature data and right
Pretreated history temperature data carries out data fitting, the step of to obtain effective matched curve, comprising:
Data cleansing is carried out to the history temperature data, to obtain target temperature data;
It detects in the target temperature data with the presence or absence of the invalid temperature data for being not belonging to preset temperature threshold range;
If it exists, then data dump is carried out to the ineffective temperature data, and the target temperature data after data dump is carried out
Interpolation processing, to obtain pretreated history temperature data;
Data fitting is carried out to the pretreated history temperature data, obtains effective matched curve.
4. method as claimed in claim 3, which is characterized in that described to be counted to the pretreated history temperature data
According to fitting, the step of obtaining effective matched curve, comprising:
Piecewise fitting is carried out respectively by preset period of time to the pretreated history temperature data, it is bent to obtain corresponding fitting
Line segment, the preset period of time includes in preoperative, art, postoperative, postanesthesia intensive care unit and body temperature return it is normal;
Quadratic fit is carried out to the matched curve section, obtains effective matched curve.
5. method according to claim 2, which is characterized in that described to obtain default dimension respectively based on effective matched curve
The body temperature characteristic parameter of degree, and tag definition is carried out respectively to each body temperature characteristic parameter, the body temperature feature after obtaining tag definition
The step of parameter, comprising:
Obtain the body temperature characteristic parameter of default dimension respectively based on effective matched curve;
The significance level coefficient of each body temperature characteristic parameter is calculated using random forests algorithm, and by sequence from big to small to described
Significance level coefficient is ranked up;
Target signature parameter is filtered out from the body temperature characteristic parameter according to ranking results, and according to default validity label pair
The target signature parameter carries out tag definition respectively, the body temperature characteristic parameter after obtaining tag definition.
6. such as the described in any item methods of claim 2 to 5, which is characterized in that described to be collected according to the verifying respectively to described
Verification result is verified and obtained to regression model to be verified, is sieved from the regression model to be verified based on the verification result
The step of selecting validation verification model, comprising:
According to the verifying collection verification result, the verification result are verified and obtained to the regression model to be verified respectively
In include anesthesia surgery Insulation availability deciding accuracy rate and recall rate;
Validation verification model is filtered out from the regression model to be verified according to the accuracy rate and the recall rate.
7. method as claimed in claim 6, which is characterized in that it is described according to the accuracy rate and the recall rate from described
The step of validation verification model is filtered out in regression model to be verified, comprising:
It according to the accuracy rate and the recall rate, is scored by preset formula each regression model to be verified, is obtained
Appraisal result;
Validation verification model is filtered out from the regression model to be verified according to the appraisal result;
Wherein, the preset formula are as follows:
Fscore=(2*precision*recall)/(precision+recall)
In formula, FscoreFor appraisal result, precision is accuracy rate, and recall is recall rate.
8. a kind of Insulation validation checking device, which is characterized in that described device includes:
Data processing module pre-processes the initial temperature data for acquiring the initial temperature data of target object,
To obtain effective temperature data;
Parameter acquisition module, for carrying out data fitting to effective temperature data, and based on current quasi- after data fitting
It closes curve and carries out the screening of body temperature characteristic parameter, to obtain current body temperature characteristic parameter;
Measure authentication module, for the current body temperature characteristic parameter to be input to validation verification model trained in advance, and
It is whether effective that the anesthesia surgery Insulation that result judgement currently takes the target object is exported according to model.
9. a kind of Insulation validation checking equipment, which is characterized in that the equipment includes: memory, processor and storage
On the memory and the Insulation validation checking program that can run on the processor, the Insulation are effective
Property detection program the step of being arranged for carrying out the Insulation validation checking method as described in any one of claims 1 to 7.
10. a kind of storage medium, which is characterized in that be stored with Insulation validation checking program, institute on the storage medium
It states when Insulation validation checking program is executed by processor and realizes Insulation as described in any one of claim 1 to 7
The step of validation checking method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910757551.5A CN110415779B (en) | 2019-08-15 | 2019-08-15 | Thermal insulation measure effectiveness detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910757551.5A CN110415779B (en) | 2019-08-15 | 2019-08-15 | Thermal insulation measure effectiveness detection method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110415779A true CN110415779A (en) | 2019-11-05 |
CN110415779B CN110415779B (en) | 2024-07-02 |
Family
ID=68367753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910757551.5A Active CN110415779B (en) | 2019-08-15 | 2019-08-15 | Thermal insulation measure effectiveness detection method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110415779B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111026744A (en) * | 2019-12-11 | 2020-04-17 | 新奥数能科技有限公司 | Data management method and device based on energy station system model framework |
CN111248871A (en) * | 2020-01-19 | 2020-06-09 | 黄宇光 | Perioperative hypothermia prediction method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107209801A (en) * | 2015-01-16 | 2017-09-26 | 艾欧私人定制康复公司 | The heat cure scheme of individuation |
CN109255367A (en) * | 2018-08-03 | 2019-01-22 | 平安科技(深圳)有限公司 | A kind of skin disease curative effect judgment method, device, computer equipment and storage medium |
CN109685102A (en) * | 2018-11-13 | 2019-04-26 | 平安科技(深圳)有限公司 | Breast lesion image classification method, device, computer equipment and storage medium |
-
2019
- 2019-08-15 CN CN201910757551.5A patent/CN110415779B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107209801A (en) * | 2015-01-16 | 2017-09-26 | 艾欧私人定制康复公司 | The heat cure scheme of individuation |
CN109255367A (en) * | 2018-08-03 | 2019-01-22 | 平安科技(深圳)有限公司 | A kind of skin disease curative effect judgment method, device, computer equipment and storage medium |
CN109685102A (en) * | 2018-11-13 | 2019-04-26 | 平安科技(深圳)有限公司 | Breast lesion image classification method, device, computer equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111026744A (en) * | 2019-12-11 | 2020-04-17 | 新奥数能科技有限公司 | Data management method and device based on energy station system model framework |
CN111248871A (en) * | 2020-01-19 | 2020-06-09 | 黄宇光 | Perioperative hypothermia prediction method |
Also Published As
Publication number | Publication date |
---|---|
CN110415779B (en) | 2024-07-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11410770B2 (en) | Medical scan diagnosing system | |
WO2020181805A1 (en) | Diabetes prediction method and apparatus, storage medium, and computer device | |
CN107785057B (en) | Medical data processing method, device, storage medium and computer equipment | |
JP2016519807A (en) | Self-evolving prediction model | |
WO2021179630A1 (en) | Complications risk prediction system, method, apparatus, and device, and medium | |
CN106778685A (en) | Electrocardiogram image-recognizing method, device and service terminal | |
CN110197728A (en) | Prediction technique, device and the computer equipment of diabetes | |
CN111695593A (en) | XGboost-based data classification method and device, computer equipment and storage medium | |
CN109615012A (en) | Medical data exception recognition methods, equipment and storage medium based on machine learning | |
CN110729054B (en) | Abnormal diagnosis behavior detection method and device, computer equipment and storage medium | |
CN110362639A (en) | A kind of method for prewarning risk, device, electronic equipment calculating analysis based on demographic associations | |
CN110415779A (en) | Insulation validation checking method, apparatus, equipment and storage medium | |
CN113707263B (en) | Drug effectiveness evaluation method and device based on group division and computer equipment | |
CN107430590A (en) | Data compare | |
CN113434680A (en) | User intention analysis method and device based on seat data and electronic equipment | |
Romeu | On operations research and statistics techniques: Keys to quantitative data mining | |
CN109784637A (en) | Method and apparatus applied to the analysis of processing platform data | |
US20240321465A1 (en) | Machine Learning Platform for Predictive Malady Treatment | |
CN113971567A (en) | Method and system for providing satisfaction information and trained functions | |
CN118427574A (en) | Analysis feedback method and system for adverse reactions of cosmetics | |
CN115116594A (en) | Method and device for detecting effectiveness of medical device | |
CN117995409A (en) | Patient medication risk evaluation method, system, terminal and medium | |
CN114528910A (en) | User classification method, device and storage medium | |
CN117316288A (en) | Determination method and device of T2DM prediction model based on intestinal microorganisms | |
CN113902318A (en) | Quality management system and quality management method |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220527 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant |