CN109785961A - A kind of equipment differentiating asthma - Google Patents
A kind of equipment differentiating asthma Download PDFInfo
- Publication number
- CN109785961A CN109785961A CN201811644307.XA CN201811644307A CN109785961A CN 109785961 A CN109785961 A CN 109785961A CN 201811644307 A CN201811644307 A CN 201811644307A CN 109785961 A CN109785961 A CN 109785961A
- Authority
- CN
- China
- Prior art keywords
- patient
- asthma
- classification
- disaggregated model
- model
- 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
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The embodiment of the present application provides a kind of equipment for differentiating asthma, it is related to technical field of data processing, differentiate that the equipment of asthma obtains the diagnosis information of patient by input module, then extracts the characteristic value of multiple default features of patient from diagnosis information using preprocessing module.The characteristic value of default feature is inputted into categorization module again later, categorization module determines that the classification of patient, the classification of patient include with asthma and not suffering from asthma according to the characteristic value of multiple default features.Whether suffered from for asthma in compared to the prior art only in accordance with symptom or course of disease diagnosis patient, accuracy is higher.Secondly, disaggregated model can automatically determine whether patient suffers from asthma according to multiple features of patient, it is smaller by doctor's subjective impact, while improving the efficiency for differentiating asthma.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of equipment for differentiating asthma.
Background technique
Asthma in children (infantile asthma) is the common Pulmonary Diseases of children, is a kind of performance repeated relapsing cough
It coughs, stridulates and have difficulty in breathing, and with the invertibity of airway hyperreactivity, obstructive airways diseases.Asthma is a kind of serious
The common chronic respiratory disease of children's torso health is endangered, disease incidence is high, often shows as the chronic course of disease of recurrent exerbation, sternly
The study, life and activity for affecting infant again, influence the growth and development of children.Many children with bronchial asthma disease due to treat not in time or
Malpractice finally develop for Adults Asthma and protracted course of disease, impaired lung function, part infant even completely lose physical exertion
Ability.Severe asthma attacks can be fatal if not obtaining timely and effective treatment.
For doctor in Diagnosing children asthma, often by inquiry medical history, this diagnostic method lacks clinic due to existing
Index, different doctors will appear different diagnostic results, have it is very big restricted, can not be promoted.And for each
The diagnostic method that kind tool detects the lung function of children, it may appear that the ill-matched problem of children, and the result detected
Accuracy be also not very high.In addition, there are also the Diagnosis of Children with Asthma index system announced according to some tissues, using marking plan
The method slightly diagnosed, this mode accuracy is not high, and very cumbersome, is also not suitable for promoting.
Summary of the invention
The embodiment of the present application provides a kind of equipment for differentiating asthma, roars to be realized based on the diagnostic message obtained comprehensively
Asthma diagnosis, improves the accuracy of Diagnosing Asthma.
The embodiment of the present application provides a kind of equipment for differentiating asthma, comprising:
Input module, for inputting the diagnosis information of patient；
Preprocessing module, the characteristic value of multiple default features for extracting the patient from the diagnosis information；
Categorization module, for determining the classification of the patient, the patient according to the characteristic value of the multiple default feature
Classification include with asthma and not suffering from asthma；
Output module, for exporting the classification of the patient.
Optionally, the multiple default feature includes following characteristics any combination:
Gender, the age, weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether have it is athermic
Wheeze, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergies, whether have
Whether history of rhinitis has dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, whether raises pet.
It optionally, include disaggregated model in the categorization module, the disaggregated model is the default feature with multiple patients
Characteristic value and the corresponding classification of the multiple patient be training sample training obtain.
Optionally, the disaggregated model is Logic Regression Models, includes logistic regression function in the Logic Regression Models；
The categorization module is specifically used for:
According to the logistic regression function of the characteristic value of multiple default features of the patient and the Logic Regression Models, really
The asthma probability of the fixed patient；
According to the classification of patient described in the asthma determine the probability of the patient.
Optionally, the multiple default feature are as follows:
Weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether have it is athermic wheeze, whether
Limitation of activity, whether shortness of breath, whether raise pet.
Optionally, the disaggregated model is Random Forest model, and the Random Forest model includes multiple decision trees；
The categorization module is specifically used for:
The characteristic value of multiple default features of the patient is inputted into each decision tree in the Random Forest model, is obtained
Obtain the classification results of each decision data output in the random forest；
The classification of the patient is determined according to the classification results that decision tree each in the random forest exports.
Optionally, the disaggregated model is Adaboost disaggregated model, and the Adaboost disaggregated model includes multiple weak
Classifier；
The categorization module is specifically used for:
The characteristic value of multiple default features of the patient is inputted into weak point of each of described Adaboost disaggregated model
Class device obtains the classification results of each Weak Classifier output in the Adaboost disaggregated model；
The classification results and the Adaboost exported according to Weak Classifier each in the Adaboost disaggregated model
The weight of each Weak Classifier determines the classification of the patient in disaggregated model.
Optionally, the disaggregated model is neural network model；
The categorization module is specifically used for:
It is handled using characteristic value of the neural network model to multiple default features of the patient, described in determination
The corresponding confidence level of patient；
The table of comparisons is inquired according to the corresponding confidence level of the patient, determines the asthma probability of the patient, the table of comparisons
In save confidence level each score section and asthma probability corresponding relationship；
According to the classification of patient described in the asthma determine the probability of the patient.
Optionally, the input module is also used to, and inputs disaggregated model more new command；
The categorization module is also used to, and updates the disaggregated model according to the disaggregated model more new command.
It optionally, further include memory module；
The memory module, for storing the feature of the diagnosis information of the patient, multiple default features of the patient
Value and the classification of the patient.
In the embodiment of the present application, differentiates that the equipment of asthma obtains the diagnosis information of patient by input module, then use
Preprocessing module extracts the characteristic value of multiple default features of patient from diagnosis information.Later again by the characteristic value of default feature
Categorization module is inputted, categorization module determines that the classification of patient, the classification of patient include suffering from according to the characteristic value of multiple default features
There is asthma and does not suffer from asthma.Whether suffered from for asthma in compared to the prior art only in accordance with symptom or course of disease diagnosis patient,
Accuracy is higher.Secondly, disaggregated model can automatically determine whether patient suffers from asthma according to multiple features of patient, by doctor
Subjective impact is smaller, while improving the efficiency for differentiating asthma.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of structural schematic diagram of equipment for differentiating asthma provided by the embodiments of the present application；
Fig. 2 is a kind of structural schematic diagram of equipment for differentiating asthma provided by the embodiments of the present application；
Fig. 3 is a kind of structural schematic diagram of equipment for differentiating asthma provided by the embodiments of the present application.
Specific embodiment
In order to which the purpose of the present invention, technical solution and beneficial effect is more clearly understood, below in conjunction with attached drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
The equipment of differentiation asthma in the embodiment of the present application can provide auxiliary to diagnosis asthma, while can also make
For a kind of home medical equipment, ordinary user is allowed to diagnose whether oneself suffers from asthma in life.
Fig. 1 illustratively shows a kind of structure of equipment for differentiating asthma provided by the embodiments of the present application, the equipment packet
It includes:
Input module 101, for inputting the diagnosis information of patient.
Diagnosis information can be the Medical record record of patient, that is, doctor inquires the information of input system after patient,
It can be history, and can be and input after doctor's on-the-spot inquiry, and the embodiment of the present application is without limitation.
Preprocessing module 102, the characteristic value of multiple default features for extracting patient from diagnosis information.
Multiple default features can be any combination of following characteristics:
Gender, the age, weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether have it is athermic
Wheeze, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergies, whether have
Whether history of rhinitis has dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, whether raises pet.
Illustratively, set multiple default features wheeze as weight, for the first time the age, frequency of wheezing, whether have wheezing sound, be
It is no have it is athermic wheeze, whether limitation of activity, whether shortness of breath, whether raise pet.Get the diagnosis information of patient Xiao Wang
Afterwards, the characteristic value of multiple default features of Xiao Wang is extracted are as follows:
Weight: 30kg；It wheezes for the first time the age: 7 years old；It wheezes frequency: 4 times；Whether there is wheezing sound: being；Whether have and does not generate heat
Wheeze: be；Whether limitation of activity: it is no；Whether shortness of breath: it is no；Whether raise pet: being.
Categorization module 103, for determining that the classification of patient, the classification of patient include according to the characteristic value of multiple default features
Asthma is not suffered from asthma and.
Before categorization module 103 determines the classification of patient, to the features of multiple default features to being further processed, with
Realize data unified standard.For example, male is 1, and female 2 for gender item.For whether have wheezing sound/inducement/history of rhinitis/
Dermatitis history/eczema history/asthma family history/rhinitis family history several, promising 1, it is not set as 0.For weight, age, height is first
It is secondary to wheeze the age, frequency of wheezing.The average value η and standard deviation sigma that respective items can be concentrated according to training sample, by [η -3 σ, η+3
σ] value linear normalization between [0,1].Item less than η -3 σ is counted as 0, and the item greater than η -3 σ is counted as 1.If diagnosis information has
The item lacked can be denoted as 0.The characteristic value normalization of default feature can be handled by the above method, realize data
Unification, and reduce data calculation amount.
Output module 104, for exporting the classification of patient.
In the embodiment of the present application, differentiates that the equipment of asthma obtains the diagnosis information of patient by input module, then use
Preprocessing module extracts the characteristic value of multiple default features of patient from diagnosis information.Later again by the characteristic value of default feature
Categorization module is inputted, categorization module determines that the classification of patient, the classification of patient include suffering from according to the characteristic value of multiple default features
There is asthma and does not suffer from asthma.Whether suffered from for asthma in compared to the prior art only in accordance with symptom or course of disease diagnosis patient,
Accuracy is higher.Secondly, disaggregated model can automatically determine whether patient suffers from asthma according to multiple features of patient, by doctor
Subjective impact is smaller, while improving the efficiency for differentiating asthma.
Optionally, as shown in Fig. 2, categorization module 103 includes disaggregated model 1031, disaggregated model 1031 is with multiple patients
Default feature characteristic value and the corresponding classification of multiple patients be training sample training obtain.
In a kind of possible embodiment, disaggregated model 1031 is Logic Regression Models, includes in Logic Regression Models
Logistic regression function.
The logistic regression function of Logic Regression Models can be chosen according to the actual situation.
Illustratively, shown in the logistic regression function of Logic Regression Models such as formula (1):
Wherein, y (x) is the asthma probability of patient, and x is the characteristic value of multiple default features of patient.
At this point, categorization module 103 is specifically used for:
According to the logistic regression function of the characteristic value of multiple default features of patient and Logic Regression Models, determine patient's
Asthma probability, then according to the classification of the asthma determine the probability patient of patient.Specifically, when the asthma probability of patient is greater than 0.5,
The classification of patient is with asthma, and when the asthma probability of patient is less than 0.5, the classification of patient is not suffer from asthma.
It optionally, can be to be set as by multiple default features when determining the classification of patient using Logic Regression Models
9 features below: weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether have it is athermic wheeze,
Whether limitation of activity, whether shortness of breath, whether raise pet.
For the performance of verifying logic regression model, the diagnosis information of multiple patients is obtained as training set and test set,
Extract the characteristic value of above-mentioned 9 default features of each patient in training set and test set.Then it is returned using training Set Pair Logic
Return model to be trained, after training terminates, trained Logic Regression Models are tested using test set.Calculating logic
The test set AUC=0.825 of regression model therefore deduces that the classification performance of the Logic Regression Models is preferable.
It optionally, can be to be set as by multiple default features when determining the classification of patient using Logic Regression Models
19 features below: whether gender at the age, weight, at the age of wheezing for the first time, frequency of wheezing, have wheezing sound, inducement, have not
Fever wheeze, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergies,
Whether there is history of rhinitis, whether has dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, whether raises pet.
For the performance of verifying logic regression model, the diagnosis information of multiple patients is obtained as training set and test set,
Extract the characteristic value of above-mentioned 19 default features of each patient in training set and test set.Then it is returned using training Set Pair Logic
Return model to be trained, after training terminates, trained Logic Regression Models are tested using test set.Calculating logic
The test set AUC=0.822 of regression model therefore deduces that the classification performance of the Logic Regression Models is preferable.
In a kind of possible embodiment, disaggregated model 1031 is Random Forest model, and Random Forest model includes more
A decision tree.
Random Forest model is the model that decision tree combines with bagging method (Bagging), and specific implementation is in model
When training, several latent structure decision trees are randomly choosed with putting back to.In this process, the selection of sample is random, special
The selection of sign is also random, it means that some samples may repeatedly appear in the training set of one tree in total training set
In, it is also possible to from the training set for not appearing in any one tree.Its key step is as follows: applying boostrap resampling technique
N sample set is randomly selected from m training sample, and thus constructs n decision tree.To in every decision tree growth course,
Each node randomly selects the subset that F feature is divided as present node from all features, leads to when constructing decision tree
Judgment criteria frequently with least mean-square error as division, best divisional mode is selected with this.Most by n decision tree composition
Whole Random Forest model.
Specifically, when constructing the Random Forest model for differentiating asthma, the diagnosis information conduct of multiple patients is obtained
The training set and test set of Random Forest model are constructed, Random Forest model is then constructed using training set.Construct random forest
After model, Random Forest model is assessed using test set, evaluation index is the test set for calculating Random Forest model
AUC。
After training Random Forest model, categorization module 103 determines the classification of patient using Random Forest model, specifically
Are as follows:
By each decision tree in the characteristic value input Random Forest model of multiple default features of patient, obtain random gloomy
The classification results of each decision data output, then determine according to the classification results of decision tree each in random forest output in woods
The classification of patient.
Specifically, by Random Forest model, more than the classification that the classification results of half decision tree output are determined as patient.
Illustratively, setting in Random Forest model includes 100 decision trees, for some patient, in this 100 decision trees, and 70
Decision tree determines that the classification of the patient is not suffer from asthma, and 70 decision trees determine that the classification of the patient is then should with asthma
The classification of patient is determined as with asthma.
It optionally, can be to be set as by multiple default features when determining the classification of patient using Random Forest model
19 features below: whether gender at the age, weight, at the age of wheezing for the first time, frequency of wheezing, have wheezing sound, inducement, have not
Fever wheeze, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergies,
Whether there is history of rhinitis, whether has dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, whether raises pet.
In order to verify the performance of Random Forest model, the diagnosis information of multiple patients is obtained as training set and test set,
Extract the characteristic value of above-mentioned 19 default features of each patient in training set and test set.Then using training set to random gloomy
Woods model is trained, and after training terminates, is tested using test set trained Random Forest model.It calculates random
The test set AUC=0.85 of forest model therefore deduces that the classification performance of the Random Forest model is preferable.
In a kind of possible embodiment, disaggregated model 1031 is Adaboost disaggregated model, Adaboost classification mould
Type includes multiple Weak Classifiers.
In training Adaboost disaggregated model, each training sample is concentrated to assign one power for training sample
Weight, these weights constitute weight vectors D, and dimension is equal to the number of samples that training sample is concentrated.When beginning, these weights are all phases
Deng, a Weak Classifier is trained on training sample set first and calculates the error rate of the classifier, then in same instruction
Practice and trains Weak Classifier on sample set again, but in second of training, it will according to the error rate of classifier, to training sample
Each weight of this collection is adjusted, and the weight for correct training sample of classifying reduces, and classifies wrong training sample weight then
Rise, but it is 1 that the summation of these weights, which remains unchanged,.Final classifier can be based on the classification mistake of the Weak Classifier of these training
Accidentally rate distributes different weights, and the low classifier of error rate obtains higher weight, thus carrying out prediction Shi Qiguan to data
Key effect.
After training Adaboost disaggregated model, categorization module 103 determines patient's using Adaboost disaggregated model
Classification, specifically:
The characteristic value of multiple default features of patient is inputted into each Weak Classifier in the Adaboost disaggregated model,
Obtain the classification results of each Weak Classifier output in Adaboost disaggregated model.Then according to every in Adaboost disaggregated model
The weight of each Weak Classifier determines the patient in the classification results and Adaboost disaggregated model of a Weak Classifier output
Classification.
It optionally, can be to set by multiple default features when determining the classification of patient using Adaboost disaggregated model
Be set to following 19 features: gender, the age, weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether
Have it is athermic wheeze, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergy
Whether whether history have history of rhinitis, whether have dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, raise and dote on
Object.
In order to verify the performance of Adaboost disaggregated model, the diagnosis information of multiple patients is obtained as training set and test
Collection extracts the characteristic value of above-mentioned 19 default features of each patient in training set and test set.Then training set pair is used
Adaboost disaggregated model is trained, training terminate after, using test set to trained Adaboost disaggregated model into
Row test.The test set AUC=0.836 for calculating Adaboost disaggregated model, therefore deduces that the Adaboost disaggregated model
Classification performance it is preferable.
In a kind of possible embodiment, disaggregated model 1031 is neural network model, and neural network model is with more
The corresponding confidence level of diagnosis information and diagnosis information of a patient is that training sample training obtains.Training neural network model it
Afterwards, it is also necessary to the corresponding confidence level of each diagnosis information is ranked up, the corresponding asthma of each score section for counting confidence level is general
Rate generates the table of comparisons of each the score section and asthma probability of confidence level.
After training neural network model, categorization module 103 determines the classification of patient using neural network model, specifically
Are as follows: it is handled using characteristic value of the neural network model to multiple default features of patient, determines the corresponding confidence level of patient,
Then the table of comparisons is inquired according to the corresponding confidence level of patient, determines the asthma probability of patient, saves confidence level in the table of comparisons
The corresponding relationship of each score section and asthma probability.According to the classification of the asthma determine the probability patient of patient.
Diagnosing Asthma is realized based on the diagnostic message that obtains comprehensively in the embodiment of the present application, compared to the prior art in only
Whether suffered from for asthma according to symptom or course of disease diagnosis patient, accuracy is higher.Secondly, disaggregated model fully take into account it is each
Influence of the nonlinear characteristic to Diagnosing Asthma, thus compared to traditional classification model for, fitting effect is more preferable, and robustness is more preferably.
Furthermore it can automatically determine whether patient suffers from asthma according to multiple features of patient, it is smaller by doctor's subjective impact, it mentions simultaneously
The high efficiency for differentiating asthma.
Optionally, input module 101 is also used to input disaggregated model more new command, and categorization module 103 is also used to, according to point
Class model more new command updates disaggregated model.
In specific implementation, when receiving disaggregated model more new command, it can replace or modify in categorization module 103
Disaggregated model.
Optionally, as shown in figure 3, differentiating that the equipment of asthma further includes memory module 105, memory module 105 is for storing
Diagnosis information, the characteristic value of multiple default features of patient and the classification of patient of patient.
In the embodiment of the present application, differentiates that the equipment of asthma obtains the diagnosis information of patient by input module, then use
Preprocessing module extracts the characteristic value of multiple default features of patient from diagnosis information.Later again by the characteristic value of default feature
Categorization module is inputted, categorization module determines that the classification of patient, the classification of patient include suffering from according to the characteristic value of multiple default features
There is asthma and does not suffer from asthma.Whether suffered from for asthma in compared to the prior art only in accordance with symptom or course of disease diagnosis patient,
Accuracy is higher.Secondly, disaggregated model can automatically determine whether patient suffers from asthma according to multiple features of patient, by doctor
Subjective impact is smaller, while improving the efficiency for differentiating asthma.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of equipment for differentiating asthma characterized by comprising
Input module, for inputting the diagnosis information of patient；
Preprocessing module, the characteristic value of multiple default features for extracting the patient from the diagnosis information；
Categorization module, for determining the classification of the patient, the class of the patient according to the characteristic value of the multiple default feature
With asthma and asthma Bao Kuo not be suffered from；
Output module, for exporting the classification of the patient.
2. equipment as described in claim 1, which is characterized in that the multiple default feature includes following characteristics any combination:
Whether gender at the age, weight, at the age of wheezing for the first time, frequency of wheezing, has wheezing sound, inducement, whether has athermic asthma
Breath, whether night suppress it is awake, whether limitation of activity, whether shortness of breath, whether break out, whether have gas source allergies, whether have nose
Whether scorching history has dermatitis/eczema history, asthma family history, rhinitis family history, dermatitis family history, whether raises pet.
3. equipment as described in claim 1, which is characterized in that include disaggregated model, the classification mould in the categorization module
Type is obtained using the characteristic value of the default feature of multiple patients and the corresponding classification of the multiple patient as training sample training.
4. equipment as claimed in claim 3, which is characterized in that the disaggregated model is Logic Regression Models, and the logic is returned
Returning includes logistic regression function in model；
The categorization module is specifically used for:
According to the logistic regression function of the characteristic value of multiple default features of the patient and the Logic Regression Models, institute is determined
State the asthma probability of patient；
According to the classification of patient described in the asthma determine the probability of the patient.
5. equipment as claimed in claim 4, which is characterized in that the multiple default feature are as follows:
Weight, the age of wheezing for the first time, frequency of wheezing, whether have wheezing sound, inducement, whether have it is athermic wheeze, whether activity
It is limited, whether shortness of breath, whether raise pet.
6. equipment as claimed in claim 3, which is characterized in that the disaggregated model is Random Forest model, described random gloomy
Woods model includes multiple decision trees；
The categorization module is specifically used for:
The characteristic value of multiple default features of the patient is inputted into each decision tree in the Random Forest model, obtains institute
State the classification results of each decision data output in random forest；
The classification of the patient is determined according to the classification results that decision tree each in the random forest exports.
7. equipment as claimed in claim 3, which is characterized in that the disaggregated model is Adaboost disaggregated model, described
Adaboost disaggregated model includes multiple Weak Classifiers；
The categorization module is specifically used for:
The characteristic value of multiple default features of the patient is inputted into each Weak Classifier in the Adaboost disaggregated model,
Obtain the classification results of each Weak Classifier output in the Adaboost disaggregated model；
According to the classification results of Weak Classifier each in Adaboost disaggregated model output and Adaboost classification
The weight of each Weak Classifier determines the classification of the patient in model.
8. equipment as claimed in claim 3, which is characterized in that the disaggregated model is neural network model；
The categorization module is specifically used for:
It is handled using characteristic value of the neural network model to multiple default features of the patient, determines the patient
Corresponding confidence level；
The table of comparisons is inquired according to the corresponding confidence level of the patient, the asthma probability of the patient is determined, is protected in the table of comparisons
The corresponding relationship of each the score section and asthma probability of confidence level is deposited；
According to the classification of patient described in the asthma determine the probability of the patient.
9. equipment as claimed in claim 3, which is characterized in that the input module is also used to, and input disaggregated model update refers to
It enables；
The categorization module is also used to, and updates the disaggregated model according to the disaggregated model more new command.
10. equipment as described in claim 1, which is characterized in that further include memory module；
The memory module, for store the characteristic value of the diagnosis information of the patient, multiple default features of the patient with
And the classification of the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811644307.XA CN109785961A (en) | 2018-12-29 | 2018-12-29 | A kind of equipment differentiating asthma |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811644307.XA CN109785961A (en) | 2018-12-29 | 2018-12-29 | A kind of equipment differentiating asthma |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109785961A true CN109785961A (en) | 2019-05-21 |
Family
ID=66499590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811644307.XA Pending CN109785961A (en) | 2018-12-29 | 2018-12-29 | A kind of equipment differentiating asthma |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785961A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081370A (en) * | 2019-10-25 | 2020-04-28 | 中国科学院自动化研究所 | User classification method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9495515B1 (en) * | 2009-12-09 | 2016-11-15 | Veracyte, Inc. | Algorithms for disease diagnostics |
| CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
| CN108399951A (en) * | 2018-03-12 | 2018-08-14 | 东南大学 | Ventilator Associated Pneumonia decision assistant method, apparatus, equipment and medium |
| CN108877924A (en) * | 2018-03-30 | 2018-11-23 | 杭州依图医疗技术有限公司 | A kind of asthma method of determining probability and device |
| CN109065171A (en) * | 2018-11-05 | 2018-12-21 | 苏州贝斯派生物科技有限公司 | The construction method and system of Kawasaki disease risk evaluation model based on integrated study |
-
2018
- 2018-12-29 CN CN201811644307.XA patent/CN109785961A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9495515B1 (en) * | 2009-12-09 | 2016-11-15 | Veracyte, Inc. | Algorithms for disease diagnostics |
| CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
| CN108399951A (en) * | 2018-03-12 | 2018-08-14 | 东南大学 | Ventilator Associated Pneumonia decision assistant method, apparatus, equipment and medium |
| CN108877924A (en) * | 2018-03-30 | 2018-11-23 | 杭州依图医疗技术有限公司 | A kind of asthma method of determining probability and device |
| CN109065171A (en) * | 2018-11-05 | 2018-12-21 | 苏州贝斯派生物科技有限公司 | The construction method and system of Kawasaki disease risk evaluation model based on integrated study |
Non-Patent Citations (2)
| Title |
|---|
| 尚凌月: "疾病辅助诊断方法的研究与应用", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 王俊文 等: "小儿咳喘中医复诊医案疗效判断模型的建立", 《循证医学方法在中西医结合皮肤病临床研究中的应用论文集》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081370A (en) * | 2019-10-25 | 2020-04-28 | 中国科学院自动化研究所 | User classification method and device |
| CN111081370B (en) * | 2019-10-25 | 2023-11-03 | 中国科学院自动化研究所 | User classification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9687208B2 (en) | Method and system for recognizing physiological sound | |
| CN108597601B (en) | Support vector machine-based chronic obstructive pulmonary disease diagnosis auxiliary system and method | |
| Behlouli et al. | Identifying relative cut-off scores with neural networks for interpretation of the Minnesota Living with Heart Failure questionnaire | |
| Pavlopoulos et al. | A decision tree–based method for the differential diagnosis of Aortic Stenosis from Mitral Regurgitation using heart sounds | |
| CN104127193B (en) | Assessment system and its appraisal procedure that a kind of depression degree quantifies | |
| CN109036553A (en) | A kind of disease forecasting method based on automatic extraction Medical Technologist's knowledge | |
| CN109817328A (en) | A kind of method and device differentiating asthma | |
| Yan et al. | Selecting critical clinical features for heart diseases diagnosis with a real-coded genetic algorithm | |
| Anupam et al. | Preliminary diagnosis of COVID-19 based on cough sounds using machine learning algorithms | |
| Sankaranarayanan et al. | A predictive approach for diabetes mellitus disease through data mining technologies | |
| Podgorelec et al. | Improving mining of medical data by outliers prediction | |
| CN108877924A (en) | A kind of asthma method of determining probability and device | |
| Kristiansen et al. | Data mining for patient friendly apnea detection | |
| KR20110098286A (en) | Self health diagnosis system of oriental medicine using fuzzy inference method | |
| Nguyen et al. | Heart disease classification using novel heterogeneous ensemble | |
| Abeyratne et al. | Cough Sound Analysis-A new tool for diagnosing Pneumonia | |
| Chen et al. | Personalized sleep staging system using evolutionary algorithm and symbolic fusion | |
| Davies et al. | A transition probability based classification model for enhanced N1 sleep stage identification during automatic sleep stage scoring | |
| CN109785961A (en) | A kind of equipment differentiating asthma | |
| Wu et al. | ECG identification based on neural networks | |
| CN113569985B (en) | Intelligent recognition system for bites of iron head snakes or bamboo leaf snakes | |
| Di Nuovo et al. | Benefits of fuzzy logic in the assessment of intellectual disability | |
| Spino et al. | The prediction of heart disease using naive Bayes classifier | |
| Xu et al. | Hybrid label noise correction algorithm for medical auxiliary diagnosis | |
| Patil et al. | Detection of Cardiac Abnormalities and Heart Disease Using Machine Learning Techniques |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |