CN113040711A - Cerebral stroke attack risk prediction system, equipment and storage medium - Google Patents
Cerebral stroke attack risk prediction system, equipment and storage medium Download PDFInfo
- Publication number
- CN113040711A CN113040711A CN202110233465.1A CN202110233465A CN113040711A CN 113040711 A CN113040711 A CN 113040711A CN 202110233465 A CN202110233465 A CN 202110233465A CN 113040711 A CN113040711 A CN 113040711A
- Authority
- CN
- China
- Prior art keywords
- data
- classifier
- weak
- weak classifier
- stroke
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a stroke onset risk prediction system, which comprises: a data acquisition unit: the system is used for acquiring health data information of a target crowd and performing desensitization treatment; a pretreatment unit: the method is used for standardizing basic data information of a target population and marking the risk category of the cerebral apoplexy; a characteristic screening unit: the method is used for screening cerebral apoplexy characteristic data based on an IV value analysis method to obtain characteristic data with higher prediction value on the model to form a data set; a model establishing unit: the method is used for training data and establishing a fusion model by using an Adaboost reinforcement learning method based on logistic regression; a model prediction unit: and the method is used for predicting the sample data to be tested through the fusion model to obtain the stroke risk category. According to the method, the stroke risk category is accurately analyzed based on the target crowd health data information, and the morbidity risk prediction efficiency can be improved.
Description
Technical Field
The invention belongs to the technical field of health management, and particularly relates to a stroke morbidity risk prediction system, equipment and a storage medium.
Background
Stroke (also called stroke) is an acute cerebrovascular disease, seriously threatening the life and health of human beings. The stroke is often characterized by high morbidity, high mortality and high disability rate, and particularly causes serious death or the consequence of leaving different degrees of disabilities to the elderly population, thus extremely bothering patients and families.
The medical community currently considers the prevention of stroke as the best preventive measure. However, in the prior art, risk prediction is performed only on one side of clinical symptoms, so that the targets of accurate identification and early prevention and treatment cannot be achieved. The stroke onset risk prediction model can be used for identifying high-risk individuals in the crowd and providing preventive intervention measures for preventing and treating stroke for the high-risk individuals, and plays a role in early identifying and intervening stroke. Therefore, the research and design of the stroke onset risk prediction model which is accurate in assessment, convenient and easy to use has important clinical value, and has important significance for preventing and treating stroke.
Disclosure of Invention
In view of this, the invention provides a stroke onset risk prediction system, equipment and a storage medium, which are used for providing a stroke onset risk prediction scheme with convenience, easiness in use and high accuracy for high-risk individuals.
In a first aspect of the present invention, a stroke onset risk prediction system is disclosed, the system comprising:
a data acquisition unit: the system is used for acquiring health data information of a target crowd and performing desensitization treatment;
a pretreatment unit: the method is used for standardizing basic data information of a target population and marking the risk category of the cerebral apoplexy;
a characteristic screening unit: the method is used for screening cerebral apoplexy characteristic data based on an IV value analysis method to obtain characteristic data with higher prediction value on the model to form a data set;
a model establishing unit: the method is used for training data and establishing a fusion model by using an Adaboost reinforcement learning method based on logistic regression;
a model prediction unit: and the method is used for predicting the sample data to be tested through the fusion model to obtain the stroke risk category.
Preferably, in the data acquisition unit, the target population health data information includes name, sex, age, weight, occupation, residence, blood pressure, heart rate, blood oxygen, atrial fibrillation, smoking history, alcoholism history, diabetes history, cardiovascular disease history, family stroke history, obesity, carotid artery stenosis accompanying symptoms, limb weakness accompanying symptoms, speech disorder accompanying symptoms and duration of corresponding accompanying symptoms.
Preferably, the normalization process includes: performing type conversion, data filling and data deleting operations on irregular and non-uniform data; the data conversion includes binary data conversion and continuous data conversion.
Preferably, the model establishing unit specifically includes:
weak classification subunit: constructing a weak classifier by using a plurality of LR classifiers, initializing a sample weight value, and training an ith weak classifier based on LR in a one-VS-rest form; taking the maximum probability value of the cerebral apoplexy as the output of each weak classifier, wherein the number of LR classifiers in each weak classifier is equal to the number of cerebral apoplexy risk categories;
calculating the output weight value alpha of the ith weak classifieri：αi＝max(ln((1-fi)/fi)+ln2,0)，fiThe sum of the weighted values of the training samples misclassified by the weak classifier;
strongly categorised subunits: updating the strong classifier based on the plurality of weak classifiers, and calculating the error rate of classification of the strong classifier;
a circulation subunit: judging whether a circulation ending condition is reached, if so, ending circulation, otherwise, recalculating a sample weight value according to the classification error rate of the ith weak classifier, and adding a new sample weight value into the sample for training; and the cycle ending condition is to judge whether the classification error rate of the strong classifier is 0 or not, if so, the cycle is ended, otherwise, whether the number of the weak classifiers is more than or equal to the set maximum number of the weak classifiers is judged, and if so, the cycle is ended.
Preferably, the expression of the update strong classifier is as follows:
wherein HfqIn order to have a strong classifier before updating,
for the updated strong classifier, η1∈[0,1]To the learning rate, αjIs the output weight value of the jth weak classifier,
for the input of the weak classifier, l is the return value of the argmax function, i.e. the stroke risk class grade prediction value.
Preferably, the expression for calculating the error rate of the strong classifier classification is as follows:
where sign is a sign function, TkIs the feature of the kth training sample, if the kth sample is a positive sample, SkTo correspond to TkThe stroke risk level of (1), m is the number of training set samples.
Preferably, the recalculating the sample weight value according to the classification error rate of the ith weak classifier, and adding the new sample weight value to the sample specifically includes:
calculating a new sample weight value of the (i + 1) th weak classifier according to the classification error rate of the (i) th weak classifier: e.g. of the typei+1k＝eik·exp(αi·[Hi fq(Tk)≠Sk]),k∈[1,2,…,m]，αiIs the output weight value of the ith weak classifier, eikIs the kth sample weight value of the ith weak classifier, ei+1kThe kth sample weight value of the (i + 1) th weak classifier; and processing the weight values newly generated by the samples and carrying out normalization processing.
In a second aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor which are invoked by the processor to implement the system according to the first aspect of the invention.
In a third aspect of the invention, a computer-readable storage medium is disclosed, which stores computer instructions for causing a computer to implement the system of the first aspect of the invention.
Compared with the prior art, the invention has the following beneficial effects:
1) the method provided by the invention has the advantages that the technologies such as data analysis and processing are applied, the characteristics of the stroke data samples are screened by combining an IV value analysis method, the characteristics with lower prediction value on the stroke risk are removed, the characteristic dimension is reduced, then a stroke onset risk prediction model is constructed by an Adaboost algorithm fused with logistic regression, and the classification category to which the stroke sample onset risk to be recognized belongs is calculated.
2) According to the invention, a plurality of LR classifiers are used for constructing the weak classifier, a one-VS-rest form is adopted for training the weak classifier, and the strong classifier is formed based on the plurality of weak classifiers, so that the prediction accuracy of the stroke morbidity risk can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a block diagram of a stroke risk prediction system according to the present invention;
FIG. 2 is a schematic diagram of a model building unit according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, the present invention provides a system for predicting stroke onset risk, the system comprising: the system comprises a data acquisition unit 10, a preprocessing unit 20, a feature screening unit 30, a model establishing unit 40 and a model predicting unit 50;
the data acquisition unit 10 is used for acquiring health data information of a target crowd and performing desensitization treatment;
the target population health data information includes name, gender, age, weight, occupation, residence, blood pressure, heart rate, blood oxygen, atrial fibrillation, smoking history, alcoholism history, diabetes history, cardiovascular disease history, family stroke history, obesity, carotid artery stenosis with symptoms, limb weakness with symptoms, speech disorder with symptoms, and duration of corresponding with symptoms. And coding desensitization protection is performed on sensitive privacy information.
The preprocessing unit 20 is configured to perform standardized processing on basic data information of a target population and label a stroke risk category;
the normalization process includes: performing type conversion, data filling and data deleting operations on irregular and non-uniform data; the data conversion includes binary data conversion and continuous data conversion. Binary data conversion such as sex field "male" or "female", residence field "south" or "north", blood pressure ≧ 140/90mmHg field "yes" or "no", and fields "yes" or "no" such as smoking history, alcohol history, atrial fibrillation, carotid stenosis, accompanying limb weakness, accompanying speech impairment, diabetes history, cardiovascular disease history, family stroke history, etc., which can represent "0" or "1", respectively; continuous data conversion, such as blood oxygen (95-99%, 90-94%, 85-89%, 70-84%) converted into "0", "1", "2", "3"), heart rate (sub/min) [ 55-90, 91-100, 101-110, 111-130, 131-180 ] converted into "0", "1", "2", "3", "4", etc. And data filling is to perform mean filling on the related null value fields of all the health items so as to improve the accuracy of model training. The stroke risk type is labeled as a single category, namely the category label only corresponds to one of the risk category sets (low risk, medium risk, high risk).
The feature screening unit 30 is configured to screen stroke feature data based on an IV value analysis method to obtain feature data with a high prediction value for a model, and form a data set;
the IV value analysis method measures the influence degree of a certain characteristic on a target, the basic idea is to compare and calculate the correlation degree of the characteristic according to the ratio of a black and white sample hit by the characteristic and the ratio of a total black and white sample, and the IV value analysis method is carried out on stroke labeling sample data to obtain the filtered sample characteristic data, so that the interference of noise information is reduced, the convergence speed in model training is accelerated, and the time overhead is reduced. For example, for health data information of a certain target population, 14 characteristics having a large influence on stroke are finally selected by an IV value analysis method to serve as input variables of a follow-up model, wherein the input variables comprise age, weight, smoking history, alcoholism history, blood pressure, heart rate, blood oxygen, atrial fibrillation, carotid stenosis, limb weakness, symptom duration, diabetes history, cardiovascular disease history and family stroke history.
The model establishing unit 40 is configured to train data and establish a fusion model by using an Adaboost reinforcement learning method based on logistic regression;
based on an LR and Adaboost fusion model, the method comprises the steps that 1 strong classifier and a plurality of weak classifiers are formed, wherein the weak classifiers are formed by the LR classifiers, one-VS-rest form is adopted for classification, and the maximum probability value of the cerebral apoplexy is used as the output of each weak classifier; the number of LR classifiers in each weak classifier is equal to the number of stroke risk classes. Referring to fig. 2, the model building unit 40 specifically includes:
weak classification subunit 41: constructing weak classifiers by using a plurality of LR classifiers, and training an ith weak classifier based on LR in a one-VS-rest form; calculating the output weight value of the ith weak classifier according to the classification error rate; taking the maximum probability value of the cerebral apoplexy as the output of each weak classifier, wherein the number of LR classifiers in each weak classifier is equal to the number of cerebral apoplexy risk categories;
specifically, let the training set be represented by R { (T)1,S1),…(Tk,Sk) Where T iskFor the feature of the kth training sample, Tk∈{tk1,tk2,…,tkp}，tkl(l ═ 1,2, …, p) is the l-th element of the kth sample feature, SkE {1,2,3} is corresponding to TkThe stroke risk levels are { low-risk, medium-risk and high-risk }, m is the number of samples in the training set and accounts for 80% of the total sample data; in addition, the maximum weak classifier number g is set to 60, and the learning rate eta is set10.8 and η20.01, 110 as a regularization parameter, and 100 as a maximum LR iteration number n;
initializing the current weak classifier index i to 1, and initializing the sample weight value to eik＝1/m，k∈[1,2,…,m]Initialize the strong classifier Hfq0; weak classifier CiConsisting of 3 LR classifiers, i.e. c1,c2,c3Weak classifier CiIs output of
a is the number of LR classifiers in each weak classification, where
w is a regression coefficient of the linear transformation,
is the input of the classifier; taking m training sample data as input, adjusting a regression coefficient by using a gradient descent method according to the initial value as follows:
j is 1,2, … p, if the k-th sample is a positive sample,
if the k-th sample is a negative sample,
therefore, the ith weak classifier C based on LR is obtained through trainingiI ═ 1,2, …, g; calculating the classification error rate of the weak classifier with m samples as input (namely the sum of the weighted values of the training samples misclassified by the weak classifier):
calculating the output weight value alpha of the ith weak classifieri：αi＝max(ln((1-fi)/fi)+ln2,0)。
Strong classification subunit 42: updating the strong classifier based on the plurality of weak classifiers, and calculating the error rate of classification of the strong classifier;
the expression of the update strong classifier is as follows:
wherein HfqIn order to have a strong classifier before updating,
for the updated strong classifier, η1∈[0,1]To the learning rate, αjIs the output weight value of the jth weak classifier,
for the input of the weak classifier, l is the return value of the argmax function, i.e. the stroke risk class grade prediction value.
The expression for calculating the error rate of the strong classifier classification is:
where sign is a sign function, TkIs the feature of the kth training sample, if the kth sample is a positive sample, SkIs a pair ofShould TkThe stroke risk level of (1), m is the number of training set samples.
The circulation subunit 43: judging whether a circulation ending condition is reached, if so, ending circulation, otherwise, recalculating a sample weight value according to the classification error rate of the ith weak classifier, and adding a new sample weight value into the sample for training; and the cycle ending condition is to judge whether the classification error rate of the strong classifier is 0 or not, if so, the cycle is ended, otherwise, whether the number of the weak classifiers is more than or equal to the set maximum number of the weak classifiers is judged, and if so, the cycle is ended.
The recalculating the sample weight value according to the classification error rate of the ith weak classifier, and adding the new sample weight value to the sample specifically includes:
calculating a new sample weight value of the (i + 1) th weak classifier according to the classification error rate of the (i) th weak classifier: e.g. of the typei+1k＝eik·exp(αi·[Hi fq(Tk)≠Sk]),k∈[1,2,…,m]，αiIs the output weight value of the ith weak classifier, eikIs the kth sample weight value of the ith weak classifier, ei+1kThe kth sample weight value of the (i + 1) th weak classifier;
and (3) processing the weight values newly generated by the samples and carrying out normalization processing by making i equal to i + 1:
the model prediction unit 50 is configured to predict sample data to be tested through the fusion model to obtain a stroke risk category.
Through comparison, after the IV value is fully utilized to analyze and screen the characteristic data, the accuracy of the fusion model classifier can be obviously improved, the convergence speed of the model is accelerated in the training process, the calculation time cost is saved, and the generalization capability of the prediction model can be finally improved; meanwhile, the weak classifiers are constructed by a plurality of LR classifiers, the LR-based weak classifier is trained in a one-VS-rest form, the strong classifier is constructed on the basis of the weak classifiers, the population with the potential risk of cerebral apoplexy is predicted, and certain help can be provided for patients and clinicians. The stroke onset risk prediction model can realize early discovery of high-risk individuals in target groups, and has important significance for providing preventive measures for the high-risk individuals.
The present invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the memory stores program instructions executable by the processor, which invokes the program instructions to implement the methods of the invention described above.
The invention also discloses a computer readable storage medium which stores computer instructions for causing the computer to implement all or part of the steps of the method of the embodiment of the invention. The storage medium includes: u disk, removable hard disk, ROM, RAM, magnetic disk or optical disk, etc.
The above-described system embodiments are merely illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, i.e. may be distributed over a plurality of network units. Some or all of the modules may be selected according to the actual Xian to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A stroke onset risk prediction system, the system comprising:
a data acquisition unit: the system is used for acquiring health data information of a target crowd and performing desensitization treatment;
a pretreatment unit: the method is used for standardizing basic data information of a target population and marking the risk category of the cerebral apoplexy;
a characteristic screening unit: the method is used for screening cerebral apoplexy characteristic data based on an IV value analysis method to obtain characteristic data with the model prediction value higher than a preset threshold value, and a data set is formed;
a model establishing unit: the method is used for training data and establishing a fusion model by using an Adaboost reinforcement learning method based on logistic regression;
a model prediction unit: and the method is used for predicting the sample data to be tested through the fusion model to obtain the stroke risk category.
2. The system of claim 1, wherein the target population health data information in the data collection unit includes name, gender, age, weight, occupation, residence, blood pressure, heart rate, blood oxygen, atrial fibrillation, smoking history, alcoholism history, diabetes history, cardiovascular disease history, family stroke history, obesity, carotid artery stenosis with symptoms, limb weakness with symptoms, speech impairment with symptoms, and duration of corresponding accompanying symptoms.
3. The system of claim 1, wherein the normalization process comprises: performing type conversion, data filling and data deleting operations on irregular and non-uniform data; the data conversion includes binary data conversion and continuous data conversion.
4. The system for predicting stroke onset risk according to claim 1, wherein the model building unit specifically includes:
weak classification subunit: constructing a weak classifier by using a plurality of LR classifiers, initializing a sample weight value, and training the LR-based weak classifier in a one-VS-rest form; taking the maximum probability value of the cerebral apoplexy as the output of each weak classifier, wherein the number of LR classifiers in each weak classifier is equal to the number of cerebral apoplexy risk categories;
calculating the output weight value of the weak classifier, i-th weak classifieriComprises the following steps: alpha is alphai＝max(ln((1-fi)/fi)+ln2,0)，fiThe sum of the weighted values of the training samples misclassified by the weak classifier;
strongly categorised subunits: updating the strong classifier based on the plurality of weak classifiers, and calculating the error rate of classification of the strong classifier;
a circulation subunit: judging whether a circulation ending condition is reached, if so, ending circulation, otherwise, recalculating a sample weight value according to the classification error rate of the ith weak classifier, and adding a new sample weight value into the sample for training; and the cycle ending condition is to judge whether the classification error rate of the strong classifier is 0 or not, if so, the cycle is ended, otherwise, whether the number of the weak classifiers is more than or equal to the set maximum number of the weak classifiers is judged, and if so, the cycle is ended.
5. The stroke onset risk prediction system of claim 4, wherein the expression of the update strong classifier is:
where a is the LR classifier number in each weak classification, HfqIn order to have a strong classifier before updating,
for the updated strong classifier, η1∈[0,1]To the learning rate, αjIs the output weight value of the jth weak classifier,
is the input of the weak classifier and is,
and the return value of the argmax function is the predicted value of the stroke risk category grade.
6. The stroke onset risk prediction system of claim 5, wherein the error rate for calculating the strong classifier classification is expressed as:
where sign is a sign function, TkIs the feature of the kth training sample, if the kth sample is a positive sample, SkTo correspond to TkThe stroke risk level of (1), m is the number of training set samples.
7. The system of claim 1, wherein the recalculating the sample weight value according to the classification error rate of the ith weak classifier comprises adding a new sample weight value to the sample:
calculating a new sample weight value of the (i + 1) th weak classifier according to the classification error rate of the (i) th weak classifier: e.g. of the typei+1k＝eik·exp(αi·[Hi fq(Tk)≠Sk]),k∈[1,2,…,m]，αiIs the output weight value of the ith weak classifier, eikIs the kth sample weight value of the ith weak classifier, ei+1kThe kth sample weight value of the (i + 1) th weak classifier; and processing the weight values newly generated by the samples and carrying out normalization processing.
8. An electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to implement the system of any one of claims 1-7.
9. A computer readable storage medium storing computer instructions which cause a computer to implement the system of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110233465.1A CN113040711B (en) | 2021-03-03 | 2021-03-03 | Cerebral apoplexy incidence risk prediction system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110233465.1A CN113040711B (en) | 2021-03-03 | 2021-03-03 | Cerebral apoplexy incidence risk prediction system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113040711A true CN113040711A (en) | 2021-06-29 |
| CN113040711B CN113040711B (en) | 2023-08-18 |
Family
ID=76509620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110233465.1A Active CN113040711B (en) | 2021-03-03 | 2021-03-03 | Cerebral apoplexy incidence risk prediction system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113040711B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393935A (en) * | 2021-06-30 | 2021-09-14 | 吾征智能技术(北京)有限公司 | Method and system for evaluating early cancer risk based on physical examination data |
| CN113520319A (en) * | 2021-07-12 | 2021-10-22 | 吾征智能技术(北京)有限公司 | Epileptic event risk management method and system based on logistic regression |
| CN113876437A (en) * | 2021-09-13 | 2022-01-04 | 上海微创医疗机器人（集团）股份有限公司 | Storage medium, robot system, and computer device |
| CN114093448A (en) * | 2021-11-24 | 2022-02-25 | 首都医科大学附属北京天坛医院 | Construction method of disease risk prediction model |
| CN114334157A (en) * | 2022-01-19 | 2022-04-12 | 北京富通东方科技有限公司 | Cerebral apoplexy risk prediction method and device |
| CN115019919A (en) * | 2022-06-16 | 2022-09-06 | 江苏省人民医院（南京医科大学第一附属医院） | Deep learning-based method for establishing function prediction model after early recovery of stroke |
| WO2023284321A1 (en) * | 2021-07-15 | 2023-01-19 | 华为云计算技术有限公司 | Method and device for predicting survival hazard ratio |
| CN117116475A (en) * | 2023-06-27 | 2023-11-24 | 开滦总医院 | Method, system, terminal and storage medium for predicting risk of ischemic cerebral apoplexy |
| CN117238478A (en) * | 2023-06-27 | 2023-12-15 | 开滦总医院 | Cerebral apoplexy risk early warning model generation method based on sleep monitoring |
| CN117457220A (en) * | 2023-12-26 | 2024-01-26 | 深圳市健怡康医疗器械科技有限公司 | Informationized management method and system for neurological stroke patients |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015066564A1 (en) * | 2013-10-31 | 2015-05-07 | Cancer Prevention And Cure, Ltd. | Methods of identification and diagnosis of lung diseases using classification systems and kits thereof |
| CN111079978A (en) * | 2019-11-20 | 2020-04-28 | 辽宁工程技术大学 | Coal and gas outburst prediction method based on logistic regression and reinforcement learning |
| CN111968746A (en) * | 2020-07-21 | 2020-11-20 | 华中科技大学协和深圳医院 | Cerebral apoplexy risk prediction method and device based on hybrid deep transfer learning |
| CN112092675A (en) * | 2020-08-31 | 2020-12-18 | 长城汽车股份有限公司 | Battery thermal runaway early warning method, system and server |
| CN112101413A (en) * | 2020-08-12 | 2020-12-18 | 海南大学 | Intelligent system for predicting cerebral apoplexy risk |
| US20210042667A1 (en) * | 2018-04-30 | 2021-02-11 | Koninklijke Philips N.V. | Adapting a machine learning model based on a second set of training data |
-
2021
- 2021-03-03 CN CN202110233465.1A patent/CN113040711B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015066564A1 (en) * | 2013-10-31 | 2015-05-07 | Cancer Prevention And Cure, Ltd. | Methods of identification and diagnosis of lung diseases using classification systems and kits thereof |
| US20210042667A1 (en) * | 2018-04-30 | 2021-02-11 | Koninklijke Philips N.V. | Adapting a machine learning model based on a second set of training data |
| CN111079978A (en) * | 2019-11-20 | 2020-04-28 | 辽宁工程技术大学 | Coal and gas outburst prediction method based on logistic regression and reinforcement learning |
| CN111968746A (en) * | 2020-07-21 | 2020-11-20 | 华中科技大学协和深圳医院 | Cerebral apoplexy risk prediction method and device based on hybrid deep transfer learning |
| CN112101413A (en) * | 2020-08-12 | 2020-12-18 | 海南大学 | Intelligent system for predicting cerebral apoplexy risk |
| CN112092675A (en) * | 2020-08-31 | 2020-12-18 | 长城汽车股份有限公司 | Battery thermal runaway early warning method, system and server |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393935A (en) * | 2021-06-30 | 2021-09-14 | 吾征智能技术(北京)有限公司 | Method and system for evaluating early cancer risk based on physical examination data |
| CN113520319A (en) * | 2021-07-12 | 2021-10-22 | 吾征智能技术(北京)有限公司 | Epileptic event risk management method and system based on logistic regression |
| WO2023284321A1 (en) * | 2021-07-15 | 2023-01-19 | 华为云计算技术有限公司 | Method and device for predicting survival hazard ratio |
| CN113876437A (en) * | 2021-09-13 | 2022-01-04 | 上海微创医疗机器人（集团）股份有限公司 | Storage medium, robot system, and computer device |
| CN113876437B (en) * | 2021-09-13 | 2024-02-23 | 上海微创医疗机器人（集团）股份有限公司 | Storage medium, robot system, and computer device |
| CN114093448A (en) * | 2021-11-24 | 2022-02-25 | 首都医科大学附属北京天坛医院 | Construction method of disease risk prediction model |
| CN114334157A (en) * | 2022-01-19 | 2022-04-12 | 北京富通东方科技有限公司 | Cerebral apoplexy risk prediction method and device |
| CN115019919A (en) * | 2022-06-16 | 2022-09-06 | 江苏省人民医院（南京医科大学第一附属医院） | Deep learning-based method for establishing function prediction model after early recovery of stroke |
| CN115019919B (en) * | 2022-06-16 | 2023-04-07 | 江苏省人民医院（南京医科大学第一附属医院） | Deep learning-based method for establishing function prediction model after early recovery of stroke |
| CN117116475A (en) * | 2023-06-27 | 2023-11-24 | 开滦总医院 | Method, system, terminal and storage medium for predicting risk of ischemic cerebral apoplexy |
| CN117238478A (en) * | 2023-06-27 | 2023-12-15 | 开滦总医院 | Cerebral apoplexy risk early warning model generation method based on sleep monitoring |
| CN117457220A (en) * | 2023-12-26 | 2024-01-26 | 深圳市健怡康医疗器械科技有限公司 | Informationized management method and system for neurological stroke patients |
| CN117457220B (en) * | 2023-12-26 | 2024-04-12 | 深圳市健怡康医疗器械科技有限公司 | Informationized management method and system for neurological stroke patients |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113040711B (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113040711A (en) | Cerebral stroke attack risk prediction system, equipment and storage medium | |
| CN111192680B (en) | Intelligent auxiliary diagnosis method based on deep learning and collective classification | |
| CN111160139B (en) | Electrocardiosignal processing method and device and terminal equipment | |
| CN109620152B (en) | MutifacolLoss-densenert-based electrocardiosignal classification method | |
| CN113486578B (en) | Method for predicting residual life of equipment in industrial process | |
| CN105930663B (en) | Hand tremor signal and audio signal classification method based on evolution fuzzy rule | |
| CN110532398B (en) | Automatic family map construction method based on multi-task joint neural network model | |
| CN111387938B (en) | Patient heart failure death risk prediction system based on characteristic rearrangement one-dimensional convolutional neural network | |
| Xu et al. | Intelligent emotion detection method based on deep learning in medical and health data | |
| CN108492877A (en) | A kind of cardiovascular disease auxiliary prediction technique based on DS evidence theories | |
| CN116671919B (en) | Emotion detection reminding method based on wearable equipment | |
| CN108937967A (en) | A kind of psychology data memory promotion detection method and system based on VR technology | |
| Jain et al. | Machine learning-based monitoring system with IoT using wearable sensors and pre-convoluted fast recurrent neural networks (P-FRNN) | |
| CN117633625B (en) | Gynaecology and obstetrics postoperative care data analysis method and system based on big data | |
| CN112466284B (en) | Mask voice identification method | |
| CN114464319A (en) | AMS susceptibility assessment system based on slow feature analysis and deep neural network | |
| CN113855008A (en) | Wearable body fluid monitoring device and operation method thereof | |
| Batool et al. | An ensemble deep learning model for human activity analysis using wearable sensory data | |
| Zhang et al. | A deep Bayesian neural network for cardiac arrhythmia classification with rejection from ECG recordings | |
| Hao et al. | Classification of cardiovascular disease via a new softmax model | |
| Marcano-Cedeño et al. | Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients | |
| CN111696674A (en) | Deep learning method and system for electronic medical record | |
| CN114521900B (en) | Arrhythmia classification and identification method based on transfer learning | |
| Suganthi et al. | Performance Analysis of Machine Learning Classification for Parkinson's Disease from Biomedical Audio Data | |
| Srivastava et al. | Moth monarch optimization-based deep belief network in deception detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |