CN110047592A - A kind of critical value warning system of medical test and method - Google Patents
A kind of critical value warning system of medical test and method Download PDFInfo
- Publication number
- CN110047592A CN110047592A CN201910331741.0A CN201910331741A CN110047592A CN 110047592 A CN110047592 A CN 110047592A CN 201910331741 A CN201910331741 A CN 201910331741A CN 110047592 A CN110047592 A CN 110047592A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- medical
- classification
- critical value
- 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.)
- Pending
Links
- 238000010339 medical test Methods 0.000 title claims abstract description 28
- 238000000968 medical method and process Methods 0.000 title abstract description 5
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000000465 moulding Methods 0.000 claims 1
- 210000004218 nerve net Anatomy 0.000 claims 1
- 238000010606 normalization Methods 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 abstract description 4
- 238000013499 data model Methods 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 239000003814 drug Substances 0.000 abstract description 2
- 230000006870 function Effects 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 229910002056 binary alloy Inorganic materials 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- 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)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to technical field of medical examination, a kind of critical value warning system of medical test and method are disclosed, the critical value warning system of medical test includes: patient test's data acquisition module, central control module, data categorization module, data judgment module, data analysis module, alarm modules, display module.The present invention passes through the characteristics of data categorization module combination medical data, the feature extraction algorithm of operational development type, more reasonably calculate the term weight function of medical data, to keep feature selecting more accurate, according to the dynamic change characteristic of medical data, the method of incremental learning is introduced into characteristic extraction procedure, solves training text collection dynamic change, improves the accuracy of training classification；Meanwhile the recent diagnosis and treatment data in area are screened using LASSO model by data analysis module, it determines moding amount in conjunction with the theoretical basis of evidence-based medicine EBM, improves the analysis result accuracy of Analysis of Medical Treatment Data model.
Description
Technical field
The invention belongs to technical field of medical examination more particularly to a kind of critical value warning system of medical test and methods.
Background technique
Critical value (CriticalValues) refers to that a certain or certain class examines abnormal results, and works as this inspection abnormal results
When appearance, show that patient may be in the rim condition being in peril of one's life, clinician needs to obtain checking information in time, fast
Speed gives the effective intervening measure of patient or treatment, it is possible to save patient vitals, otherwise be possible to serious consequence occur, lose
Go best rescue machine meeting.However, the accuracy of medical data classification cannot be provided during existing medical test；Meanwhile to doctor
It is big to treat data analytical error.
In conclusion problem of the existing technology is: medical data classification cannot be provided during existing medical test
Accuracy；Meanwhile it is big to Analysis of Medical Treatment Data error.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of critical value warning system of medical test and methods.
The invention is realized in this way a kind of critical value warning system of medical test, the critical value alarm of medical test
System includes:
Patient test's data acquisition module, central control module, data categorization module, data judgment module, data analysis
Module, alarm modules, display module；
Patient test's data acquisition module, connect with central control module, for acquiring conditions of patients by Medical Devices
Detection data；
Central control module, with patient test's data acquisition module, data categorization module, data judgment module, data point
Module, alarm modules, display module connection are analysed, is worked normally for controlling modules by single-chip microcontroller；
Data categorization module is connect with central control module, for being divided by data classification program medical data
Generic operation；
Data judgment module, connect with central control module, for the state of an illness number by data processor judgement acquisition
According to whether normal；
Data analysis module is connect with central control module, for carrying out analysis behaviour to medical data by analyzing program
Make；
Alarm modules are connect with central control module, for being warned by alarm device according to the improper data of judgement
Report；
Display module is connect with central control module, for the conditions of patients detection data by display display acquisition.
Another object of the present invention is to provide a kind of medical tests for executing the critical value warning system of the medical test
Critical value alarming method, the critical value alarming method of medical test include:
Firstly, acquiring conditions of patients detection data using Medical Devices by patient test's data acquisition module；In secondly,
Control module is entreated to carry out sort operation to medical data using data classification program by data categorization module；Judged by data
Module judges whether the state of an illness data of acquisition are normal using data processor；Analysis program pair is utilized by data analysis module
Medical data carries out analysis operation；Then, alarm is carried out according to the improper data of judgement using alarm device by alarm modules；
Finally, utilizing the conditions of patients detection data of display display acquisition by display module.
Further, the data classification method of the critical value alarming method of the medical test is as follows:
(1) classification data pre-processes: noise and processing missing values are reduced or removed for the data before classification, use mind
Variation is normalized to data through network；
(2) nearest neighbour classification of data: giving a specific classification sample, and preceding K nearest therewith are found out from data set
Then neighbours determine the classification of the sample according to the classification of these neighbours；
(3) feature selecting: sorting according to the size of the weight of Feature Words, selects have biggish weight word as the data
Feature Words, reduce text representation vector dimension, to reduce the computational complexity of computer；
(4) document database is established: according to the demand of data directory and dynamic queries, and in the form of single document data
Establish storing data library.
Further, in the step (1), when handling missing values, there is most values using the data attribute or most may be used
The value that can occur substitutes missing values, and when variation is normalized to data, the data attribute value given is contracted in proportion
It puts, drops into all data in one lesser diameter section, specification is carried out to data by WaveCluster.
Further, in the step (2), specific step is as follows for nearest neighbour classification:
Calculating there is not center vector of all simple arithmetic means of training text vector of class text collection as each classification；
Text to be sorted is segmented, indicates the text with feature vector；
According to formulaWherein diBe text to be sorted feature to
Amount, wikIndicate the kth dimension of text i to be sorted, djIt is the center vector of classification j, wjkFor the K dimension of the center vector of classification j, N
For the dimension of feature vector；
In K neighbour, the weight of each classification is calculated, formula is
Compare weight, the maximum classification of weight is exactly the classification of text to be sorted.
Further, the data analysing method of the critical value alarming method of the medical test is as follows:
1) using the medical data training LASSO model of several patients to generate the first ICD code set；
2) using the union of the first ICD code set and default ICD code set as the 2nd ICD code set；
3) using the 2nd ICD code set and the medical data training regression model to generate parameter set；
4) analysis model is generated according to the 2nd ICD code set and the parameter set.
Advantages of the present invention and good effect are as follows: the present invention passes through the characteristics of data categorization module combination medical data, fortune
The follow-on feature extraction algorithm of row, more reasonably calculates the term weight function of medical data, to keep feature selecting more quasi-
Really, according to the dynamic change characteristic of medical data, the method for incremental learning is introduced into characteristic extraction procedure, solves training text
This collection dynamic change improves the accuracy of training classification；Meanwhile it is close to area using LASSO model by data analysis module
Phase diagnosis and treatment data are screened, and are determined moding amount in conjunction with the theoretical basis of evidence-based medicine EBM, are improved Analysis of Medical Treatment Data model
Analysis result accuracy.
Detailed description of the invention
Fig. 1 is the critical value warning system structural block diagram of medical test provided in an embodiment of the present invention.
In figure: 1, patient test's data acquisition module；2, central control module；3, data categorization module；4, data judge
Module；5, data analysis module；6, alarm modules；7, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, the critical value warning system of medical test provided in an embodiment of the present invention includes: that patient test's data are adopted
Collect module 1, central control module 2, data categorization module 3, data judgment module 4, data analysis module 5, alarm modules 6, show
Show module 7.
Patient test's data acquisition module 1 is connect with central control module 2, for acquiring disease by Medical Devices
Feelings detection data；
Central control module 2, with patient test's data acquisition module 1, data categorization module 3, data judgment module 4, number
It connects according to analysis module 5, alarm modules 6, display module 7, is worked normally for controlling modules by single-chip microcontroller；
Data categorization module 3 is connect with central control module 2, for being carried out by data classification program to medical data
Sort operation；
Data judgment module 4 is connect with central control module 2, for the state of an illness by data processor judgement acquisition
Whether data are normal；
Data analysis module 5 is connect with central control module 2, for being analyzed by analyzing program medical data
Operation；
Alarm modules 6 are connect with central control module 2, for being carried out by alarm device according to the improper data of judgement
Alarm；
Display module 7 is connect with central control module 2, for the conditions of patients testing number by display display acquisition
According to.
3 classification method of data categorization module provided by the invention is as follows:
(1) classification data pre-processes: noise and processing missing values are reduced or removed for the data before classification, use mind
Variation is normalized to data through network；
(2) nearest neighbour classification of data: giving a specific classification sample, and preceding K nearest therewith are found out from data set
Then neighbours determine the classification of the sample according to the classification of these neighbours；
(3) feature selecting: sorting according to the size of the weight of Feature Words, selects have biggish weight word as the data
Feature Words, reduce text representation vector dimension, to reduce the computational complexity of computer；
(4) document database is established: according to the demand of data directory and dynamic queries, and in the form of single document data
Establish storing data library.
In step (1) provided by the invention, when handling missing values, there is most values using the data attribute or most may be used
The value that can occur substitutes missing values, and when variation is normalized to data, the data attribute value given is contracted in proportion
It puts, drops into all data in one lesser diameter section, specification is carried out to data by WaveCluster.
In step (2) provided by the invention, specific step is as follows for nearest neighbour classification:
Calculating there is not center vector of all simple arithmetic means of training text vector of class text collection as each classification；
Text to be sorted is segmented, indicates the text with feature vector；
According to formulaWherein diBe text to be sorted feature to
Amount, wikIndicate the kth dimension of text i to be sorted, djIt is the center vector of classification j, wjkFor the K dimension of the center vector of classification j, N
For the dimension of feature vector；
In K neighbour, the weight of each classification is calculated, formula is
Compare weight, the maximum classification of weight is exactly the classification of text to be sorted.
5 analysis method of data analysis module provided by the invention is as follows:
1) using the medical data training LASSO model of several patients to generate the first ICD code set；
2) using the union of the first ICD code set and default ICD code set as the 2nd ICD code set；
3) using the 2nd ICD code set and the medical data training regression model to generate parameter set；
4) analysis model is generated according to the 2nd ICD code set and the parameter set.
It is provided by the invention to include: using the medical data training LASSO model of several patients
The continuous n medical data for participating in the patient of social medical insurance were suffered to the patient for presetting disease for the first time with (n+1)th year
Information according to ICD coding do binary system processing；
Suffered from for the first time according to the medical data of the identity information of patient, binary system treated the patient and the patient
The wide table including several patient assessment's data that the information of the default disease generates；
The wide table is inputted into the LASSO model, the training LASSO model exports each of described medical data
The relevant parameter of ICD coding and the default disease.
First ICD code set of generation provided by the invention includes:
The regression coefficient of the coding of multiple ICD in the medical data is obtained according to the training result of the LASSO model；
The first ICD code set is generated according to the ICD coding that regression coefficient is greater than threshold value.
Generation parameter set provided by the invention includes:
The recurrence system of the coding of the ICD in the 2nd ICD code set is obtained according to the training result of the regression model
Number；
According to the regression coefficient for being greater than preset value, corresponding ICD coding generates the parameter set.
When the invention works, it is examined firstly, acquiring conditions of patients using Medical Devices by patient test's data acquisition module 1
Measured data；Secondly, central control module 2 classifies to medical data using data classification program by data categorization module 3
Operation；Judge whether the state of an illness data of acquisition are normal using data processor by data judgment module 4；It is analyzed by data
Module 5 carries out analysis operation to medical data using analysis program；Then, utilize alarm device according to judgement by alarm modules 6
Improper data carry out alarm；Finally, utilizing the conditions of patients detection data of display display acquisition by display module 7.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (6)
1. a kind of critical value warning system of medical test, which is characterized in that the critical value warning system of medical test includes:
Patient test's data acquisition module, central control module, data categorization module, data judgment module, data analysis module,
Alarm modules, display module；
Patient test's data acquisition module, connect with central control module, for acquiring conditions of patients detection by Medical Devices
Data；
Central control module analyzes mould with patient test's data acquisition module, data categorization module, data judgment module, data
Block, alarm modules, display module connection, work normally for controlling modules by single-chip microcontroller；
Data categorization module is connect with central control module, for carrying out classification behaviour to medical data by data classification program
Make；
Data judgment module, connect with central control module, for being by the state of an illness data of data processor judgement acquisition
It is no normal；
Data analysis module is connect with central control module, for carrying out analysis operation to medical data by analyzing program；
Alarm modules are connect with central control module, for carrying out alarm according to the improper data of judgement by alarm device；
Display module is connect with central control module, for the conditions of patients detection data by display display acquisition.
2. a kind of perform claim requires the critical value alarming method of medical test of the 1 critical value warning system of medical test,
It is characterized in that, the critical value alarming method of medical test includes:
Firstly, acquiring conditions of patients detection data using Medical Devices by patient test's data acquisition module；Secondly, center control
Molding block carries out sort operation to medical data using data classification program by data categorization module；Pass through data judgment module
Judge whether the state of an illness data of acquisition are normal using data processor；By data analysis module using analysis program to medical treatment
Data carry out analysis operation；Then, alarm is carried out according to the improper data of judgement using alarm device by alarm modules；Most
Afterwards, the conditions of patients detection data of display display acquisition is utilized by display module.
3. the critical value alarming method of medical test as claimed in claim 2, which is characterized in that the critical value police of medical test
The data classification method of reporting method is as follows:
(1) classification data pre-processes: noise and processing missing values are reduced or removed for the data before classification, use nerve net
Variation is normalized to data in network；
(2) nearest neighbour classification of data: giving a specific classification sample, preceding K neighbours nearest therewith found out from data set,
Then the classification of the sample is determined according to the classification of these neighbours；
(3) feature selecting: sorting according to the size of the weight of Feature Words, selects have spy of the biggish weight word as the data
Word is levied, the dimension of text representation vector is reduced, to reduce the computational complexity of computer；
(4) document database is established: being established according to the demand of data directory and dynamic queries, and in the form of single document data
Storing data library.
4. the critical value alarming method of medical test as claimed in claim 2, which is characterized in that in the step (1), handling
When missing values, there is most value using the data attribute or value that most probable occurs substitute missing values, and to data into
When row normalization variation, the data attribute value bi-directional scaling that will be given makes all data drop into a lesser diameter
In section, specification is carried out to data by WaveCluster.
5. the critical value alarming method of medical test as claimed in claim 2, which is characterized in that in the step (2), Jin Linfen
Specific step is as follows for class:
Calculating there is not center vector of all simple arithmetic means of training text vector of class text collection as each classification；
Text to be sorted is segmented, indicates the text with feature vector；
According to formulaWherein diIt is the feature vector of text to be sorted, wik
Indicate the kth dimension of text i to be sorted, djIt is the center vector of classification j, wjkFor the K dimension of the center vector of classification j, N is characterized
The dimension of vector；
In K neighbour, the weight of each classification is calculated, formula is
Compare weight, the maximum classification of weight is exactly the classification of text to be sorted.
6. the critical value alarming method of medical test as claimed in claim 2, which is characterized in that the critical value police of medical test
The data analysing method of reporting method is as follows:
1) using the medical data training LASSO model of several patients to generate the first ICD code set；
2) using the union of the first ICD code set and default ICD code set as the 2nd ICD code set；
3) using the 2nd ICD code set and the medical data training regression model to generate parameter set；
4) analysis model is generated according to the 2nd ICD code set and the parameter set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910331741.0A CN110047592A (en) | 2019-04-24 | 2019-04-24 | A kind of critical value warning system of medical test and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910331741.0A CN110047592A (en) | 2019-04-24 | 2019-04-24 | A kind of critical value warning system of medical test and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110047592A true CN110047592A (en) | 2019-07-23 |
Family
ID=67278854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910331741.0A Pending CN110047592A (en) | 2019-04-24 | 2019-04-24 | A kind of critical value warning system of medical test and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110047592A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105224821A (en) * | 2015-11-17 | 2016-01-06 | 中国人民解放军第二军医大学 | The sick and wounded information monitoring early warning system of a kind of military personnel based on GIS and method |
| CN107967948A (en) * | 2017-12-07 | 2018-04-27 | 泰康保险集团股份有限公司 | Medical big data analysis method and apparatus |
| CN108710700A (en) * | 2018-05-24 | 2018-10-26 | 文丹 | A kind of sorting technique of medical treatment & health big data |
| CN109567742A (en) * | 2018-10-17 | 2019-04-05 | 吴平 | A kind of paediatrics state of an illness early warning method |
-
2019
- 2019-04-24 CN CN201910331741.0A patent/CN110047592A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105224821A (en) * | 2015-11-17 | 2016-01-06 | 中国人民解放军第二军医大学 | The sick and wounded information monitoring early warning system of a kind of military personnel based on GIS and method |
| CN107967948A (en) * | 2017-12-07 | 2018-04-27 | 泰康保险集团股份有限公司 | Medical big data analysis method and apparatus |
| CN108710700A (en) * | 2018-05-24 | 2018-10-26 | 文丹 | A kind of sorting technique of medical treatment & health big data |
| CN109567742A (en) * | 2018-10-17 | 2019-04-05 | 吴平 | A kind of paediatrics state of an illness early warning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105550653B (en) | Electrocardio lead intelligent selection method and system | |
| CN106580282A (en) | Human body health monitoring device, system and method | |
| CN108717867A (en) | Disease forecasting method for establishing model and device based on Gradient Iteration tree | |
| CN109480864A (en) | A kind of schizophrenia automatic evaluation system based on nervous functional defects and machine learning | |
| CN112070239B (en) | Analysis method, system, medium, and device based on user data modeling | |
| CN107507197A (en) | A kind of pulmonary parenchyma extracting method based on clustering algorithm and convolutional neural networks | |
| CN113053535A (en) | Medical information prediction system and medical information prediction method | |
| CN108647707A (en) | Probabilistic neural network creation method, method for diagnosing faults and device, storage medium | |
| Wadhera et al. | Brain functional network topology in autism spectrum disorder: a novel weighted hierarchical complexity metric for electroencephalogram | |
| Leontidis et al. | Evaluation of geometric features as biomarkers of diabetic retinopathy for characterizing the retinal vascular changes during the progression of diabetes | |
| CN114707608B (en) | Medical quality control data processing method, device, equipment, medium and program product | |
| CN113796873B (en) | Wearable dynamic electrocardiosignal classification method and system | |
| CN116738352B (en) | Method and device for classifying abnormal rod cells of retinal vascular occlusion disease | |
| CN113824580B (en) | Network index early warning method and system | |
| CN117423458A (en) | Human health state evaluation system and method | |
| CN113539473A (en) | Method and system for diagnosing brucellosis only by using blood routine test data | |
| Tawhid et al. | Brain data mining framework involving entropy topography and deep learning | |
| CN112155520A (en) | Monitoring device and method based on body temperature data, electronic equipment and storage medium | |
| CN117116475A (en) | Method, system, terminal and storage medium for predicting risk of ischemic cerebral apoplexy | |
| CN110047592A (en) | A kind of critical value warning system of medical test and method | |
| Nugraha et al. | Over-sampling strategies with data cleaning for handling imbalanced problems for diabetes prediction | |
| Ajesh et al. | Cad systems for automatic detection and classification of covid19 using image processing and machine learning | |
| Adel et al. | Muscle categorization using PDF estimation and naive Bayes classification | |
| Stark et al. | Deep Learning Investigation of Mass Spectrometry Analysis from Melanoma Samples | |
| CN117577334B (en) | Health monitoring system based on medical instrument equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |
|
| RJ01 | Rejection of invention patent application after publication |