CN108511056A - Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system - Google Patents
Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system Download PDFInfo
- Publication number
- CN108511056A CN108511056A CN201810136206.5A CN201810136206A CN108511056A CN 108511056 A CN108511056 A CN 108511056A CN 201810136206 A CN201810136206 A CN 201810136206A CN 108511056 A CN108511056 A CN 108511056A
- Authority
- CN
- China
- Prior art keywords
- data
- therapeutic scheme
- feature
- group
- module
- 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
- 230000001225 therapeutic effect Effects 0.000 title claims abstract description 112
- 208000006011 Stroke Diseases 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 38
- 206010008190 Cerebrovascular accident Diseases 0.000 title claims abstract description 34
- 238000004458 analytical method Methods 0.000 title claims abstract description 33
- 230000002490 cerebral effect Effects 0.000 title claims abstract description 30
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 5
- 239000012141 concentrate Substances 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000004393 prognosis Methods 0.000 description 15
- 230000036772 blood pressure Effects 0.000 description 14
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 13
- 206010033799 Paralysis Diseases 0.000 description 12
- 239000008280 blood Substances 0.000 description 12
- 210000004369 blood Anatomy 0.000 description 12
- 208000021090 palsy Diseases 0.000 description 12
- 208000011580 syndromic disease Diseases 0.000 description 11
- 201000010099 disease Diseases 0.000 description 10
- 238000007689 inspection Methods 0.000 description 9
- 206010020772 Hypertension Diseases 0.000 description 7
- 108010028554 LDL Cholesterol Proteins 0.000 description 6
- 238000000540 analysis of variance Methods 0.000 description 6
- 238000000546 chi-square test Methods 0.000 description 6
- 206010012601 diabetes mellitus Diseases 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 230000001154 acute effect Effects 0.000 description 5
- 208000026106 cerebrovascular disease Diseases 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 239000003814 drug Substances 0.000 description 5
- 108090000623 proteins and genes Proteins 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 4
- 206010061216 Infarction Diseases 0.000 description 4
- 230000001269 cardiogenic effect Effects 0.000 description 4
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000008103 glucose Substances 0.000 description 4
- 230000007574 infarction Effects 0.000 description 4
- 150000003626 triacylglycerols Chemical class 0.000 description 4
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 3
- 206010062717 Increased upper airway secretion Diseases 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 206010008118 cerebral infarction Diseases 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 208000026435 phlegm Diseases 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 200000000007 Arterial disease Diseases 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 2
- 208000028922 artery disease Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 235000012000 cholesterol Nutrition 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 201000001320 Atherosclerosis Diseases 0.000 description 1
- 208000032382 Ischaemic stroke Diseases 0.000 description 1
- 208000032023 Signs and Symptoms Diseases 0.000 description 1
- 238000012352 Spearman correlation analysis Methods 0.000 description 1
- 230000003143 atherosclerotic effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000035487 diastolic blood pressure Effects 0.000 description 1
- 230000005714 functional activity Effects 0.000 description 1
- 238000003205 genotyping method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000000554 physical therapy Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009747 swallowing Effects 0.000 description 1
- 238000002560 therapeutic procedure 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medicines That Contain Protein Lipid Enzymes And Other Medicines (AREA)
Abstract
The present invention provides a kind of, and the therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system, including：Data are pre-processed, the target group data needed for data modeling is obtained；Feature selecting is differently carried out to the different types of data of target group data, obtains feature selecting data；Classify to feature selecting data, and a point group character is obtained to each classification progress feature description and is described；The therapeutic scheme of each classification is extracted and summarized based on a point group character description, validity sequence is carried out to the therapeutic scheme of all categories, recommends optimum treatment scheme.The present invention carries out similarity analysis to patients with cerebral apoplexy and group is divided to handle, and is effectively sorted to each group of therapeutic scheme, provides the therapeutic scheme of accurate personalization, reduces time cost and economic cost；Similar accurate crowd is found for individual patient, effective therapeutic scheme suggestion of individuation is provided, implementing rehabilitation and correlative study to patient for doctor has very big directive significance.
Description
Technical field
The present invention relates to the rehabilitation of stroke patients therapy fields in medical field, and in particular, to one kind is suffered from based on cerebral apoplexy
The therapeutic scheme of person's similarity analysis recommends method and system.
Background technology
" cerebral apoplexy " (cerebral stroke) is also known as " apoplexy ", " cerebrovascular accident ".It is a kind of acute cerebrovascular disease
Disease has the characteristics that high disability rate and high recurrent.Evidence-based medicine EBM confirms that rehabilitation of stroke patients treatment is that reduction disability rate is most effective
Method and cerebral apoplexy organizational management pattern in indispensable key link, currently, hurt of rehabilitation scheme mainly has fortune
Dynamic training, Functional Activities of OT, speech training, swallowing training, air pressure treatment, physical therapy etc..
Shen Ming is waited by force《Chinese hemorheology magazine》[2008,18 (2):205-231] " palsy is anxious for the paper delivered
In the correlative study of property phase blood pressure and prognosis ", the relationship of acute stage of stroke blood pressure and prognosis is analyzed with guiding clinical treatment, is ground
Study carefully to be admitted to hospital and be less than acute cerebral infarction for 24 hours and the inpatient of cerebral hemorrhage away from disease time, carry out basic document collection, monitor into
Blood pressure in 7d after institute scores disease accompanied in the course of disease, the mode and intervention time to blood pressure management after being admitted to hospital into
Row registration.The results show that blood pressure and mean blood pressure and the death rate in January and June be dead or disability rate in 7d after being admitted to hospital when (1) is admitted to hospital
U-shaped relationship, hyperpiesia or too low person's prognosis inequality.When being admitted to hospital systolic pressure 120~180mmHg and diastolic pressure 70~
100mmHg prognosis is preferable, takes the prognosis in 150/85mmHg of median i.e. blood pressure best.(2) main artery hardens type infarct and the heart
When being admitted to hospital, prognosis is relatively preferable when blood pressure (120~180/70~100) mmHg for source property infarct, the average blood in the 2d that is admitted to hospital
Press, there was no significant difference for infarct recent death rate, late mortality and the disability rate of mean blood pressure difference blood pressure section in the 7d that is admitted to hospital,
The other hypotype cerebral infarctions of TOAST because sample size is small can not be for statistical analysis.(3) systolic pressure is 120 when patients with cerebral hemorrhage is admitted to hospital
~180mmHg, dead or disability rate is relatively low when June, and prognosis is preferable.Average systolic in 7d of being admitted to hospital is lower, and when June is dead or residual
Disease rate is lower, and prognosis is better.When being admitted to hospital, in the 7d that is admitted to hospital AvDP and when June dead or disability rate without obvious relation.(4)
Multiple linear regression analysis finds that concomitant disease scores, aggravated in Post stroke 3d, DBP declines NIHSS when being more than 20% and June in 1d
Scoring positive correlation, Treatment of Hypertension and NIHSS scorings when June are negatively correlated after being admitted to hospital, P<0.05.Obtain, acute stage of stroke blood pressure with
The U-shaped relationship of prognosis, it is best in (120~180/70~100) mmHg blood pressure section prognosis.Divide after palsy classification and infarct parting
It is not studied, infers that the hypertension of Acute Cerebral Hemorrhage preferably steadily declines, cerebral infarction cannot still draw a conclusion because case load is few.
Wang Le etc. exists《Tianjin traditional Chinese medicine》Paper " the CISS palsys that [2011, the 5th phase of volume 28,366-369 pages] are delivered
In the meaning pre-test that parting is judged with tcm syndrome element correlation analysis and its prognosis ", Study of China Ischemic Stroke hypotype
(CISS) palsy parting and tcm syndrome element and the correlation of Index for diagnosis.1) it collects in the new hair apoplexy patient in 72h
Cure four methods of diagnosis information and electrocardiogram, Color Sonography, transcranial Doppler (TCD), computed tomography (CT) or Magnetic resonance imaging
(MRI) inspection results such as.2) Syndrome Differentiation of Traditional Chinese Medicine and CISS genotyping results are done into Spearman correlation analysis.The results show that
1) Syndrome in TCM class is based on blood stasis (179), phlegm (105).2) cardiogenic palsy prognosis is poor (22.7%), perforating artery disease
Sick prognosis is preferably (3.5%)；Fire syndrome prognosis final result is bad (20.5%), and the preferable person of syndrome of blood stasis (16.2%) prognosis is in the majority.3) fiery
(related coefficient 0.49, P=0.009), syndrome of blood stasis (related coefficient 0.55, P=0.004) are demonstrate,proved to cardiogenic palsy with related
Property；And phlegm demonstrate,proves (related coefficient 0.38, P=0.001) related to main artery atherosclerotic palsy, wind card and perforating artery disease
Related (related coefficient 0.47, P=0.009).It obtains, the syndrome of blood stasis, phlegm card in differentiation of symptoms and signs for classification of syndrome are moved with cardiogenic palsy, greatly respectively
Pulse atherosclerosis palsy is related, and fire syndrome is related to cardiogenic palsy.CISS partings are with Syndrome in TCM class for cerebrovascular accident
Description has certain similitude.
The grade of Wu Yi exists《Micro computer and application》The paper that [the 13rd phase of volume 2016,35,55-59 pages] delivers is " based on branch
Hold the headstroke microwave detection of vector machine classification " in, it is proposed that in a kind of machine learning brain using support vector machines as core
Wind detects sorting algorithm, and carries out optimizing to SVM parameters by particle swarm optimization algorithm, to reach Optimum Classification accuracy rate
Purpose realizes that whether there is or not the correct classification of headstroke.It is verified by headstroke microwave checking test, the grader of headstroke is flat
Detection accuracy it is optimized after improve 16%, prove the feasibility of algorithm.
[the S Ka Malakalan etc., using with patient-specific correlation of Chinese Patent Application No. 201380061665.7
Property evaluation variant-disease-associated diagnostic gene analysis, 104838384.A, 2015-08-12] patent of invention disclose and make
With the disease-associated diagnostic gene analysis of variant-with patient-specific relativity evaluation, pass through clinical research and phenotype
The correlation of the associated research genetic mutation observed in diagnosing subject gene data of feature is according to hereafter being evaluated.
With the research genetic mutation functionally relevant one group it is polymorphic identified.For the polymorphic calculating of the group in the diagnosis object
The foreground for the variant observed in gene data is distributed.For the polymorphic gene number calculated in the object of the clinical research of the group
The background distributions for the variant observed in.Calculate the comparison measuring of the foreground distribution and the background distributions.It is based on
The comparison measuring quantifies the correlation of the research variant and the diagnosis object, foreground distribution and background distributions
Higher similitude corresponds to higher correlation.
Chinese Patent Application No. 201710036979.1 [Li Hao Min etc., a kind of quick calculating side of patient's similarity analysis
Method, 106650299.A, 2017-05-10] patent of invention disclose a kind of quick calculation method of patient's similarity analysis, wrap
It includes：(1) patient is described as feature vector and is mapped to feature space, select n clinical indices and formulate characteristic value scheme；
(2) according to the characteristic value scheme and patient data, the n clinical indices are mapped to bit specific, generation system
One characteristic value, each patient correspond to a uniform characteristics value；(3) similitude operation is carried out to the uniform characteristics value of two patients,
Obtain similar features value；(4) the number m of similar features in the similar features value described in counting, calculates the similar features and exists
The ratio m/n of entire feature space, the similitude of two patients of qualitative assessment is carried out with m/n.Can be greatly lowered calculation amount with
And the efficiency of data acquisition is improved, it provides the foundation to carry out Similarity measures in real time in super large PATIENT POPULATION's data.
In summary, the rehabilitation effect of patients with cerebral apoplexy is related to many factors, and different patients is for same
The therapeutic effect of scheme is different, carries out similarity analysis to patient, can pointedly provide therapeutic scheme, also more effectively, passes
The method of system is selected therapeutic scheme based on doctors experience, and in recent years, some scholars carry out patient's similitude
Exploratory development, still, for single disease, using the method for machine learning to patient's similarity analysis, and according to population characteristic
It carries out therapeutic scheme recommendation and not yet realizes that the present invention is directed to this technical problem, introduce machine learning method to patients with cerebral apoplexy
Similitude is analyzed, and to the feature description of each group of progress various dimensions, and is directed to different groups, provides different treatment sides
Case recommend, therapeutic scheme according to validity carry out descending arrangement, can preferably help doctor carry out therapeutic scheme precision,
Intelligent selection.
Invention content
For the defects in the prior art, the object of the present invention is to provide a kind of based on patients with cerebral apoplexy similarity analysis
Therapeutic scheme recommends method and system.
According to a kind of therapeutic scheme recommendation method based on patients with cerebral apoplexy similarity analysis provided by the invention, including such as
Lower step：
Data prediction step：Data are pre-processed, the target group data needed for data modeling is obtained；
Feature selection step：Feature selecting is differently carried out to the different types of data of target group data, is obtained
Feature selecting data；
Similitude divides group's step：Classify to feature selecting data, and feature description is carried out to each classification and is divided
Group character describes；
Therapeutic scheme recommendation step：The therapeutic scheme of each classification is extracted and summarizes based on a point group character description, to all
The therapeutic scheme of classification carries out validity sequence, recommends optimum treatment scheme.
Preferably, the data prediction step includes：
Data integration step：Data are integrated, complete data set is formed；
Data cleansing step：Data cleansing is carried out to the data lack of standardization that partial data is concentrated；
Data remove deletion procedure：Concentrate the classifying type that there are the data lacked and continuous type feature according to crowd partial data
Number or mean value carry out missing data filling；
Enter a group screening step：It is based on into a group condition, data screening is carried out to complete data set.
Preferably, the feature selection step includes：
The derivative step of conversion：Conversion derivative is carried out to target group data, forms characteristic variable；
Feature Selection step：Characteristic variable is screened, candidate feature is obtained；
Feature Selection step：P-value values are calculated separately to all candidate features, p-value values is chosen and is less than threshold value
Candidate feature as feature selecting data.
Preferably, the similitude divides group's step to include：
Characteristic grouping step：Characteristic of division is chosen, setting divides group's rule to divide group to handle feature selecting data, obtains a point group
As a result；
Feature description step：Each category feature of grouping result is described, a point group character is obtained and describes.
Preferably, the therapeutic scheme recommendation step includes：
Therapeutic scheme set step：It is described based on a point group character, the therapeutic scheme in each point of group is selected, is converged
Always, the therapeutic scheme set of each point of group is obtained；
Therapeutic scheme sequence step：Being calculated using generalized regression method the therapeutic scheme of each point of group is influenced, and is calculated
Odds ratio values sort to the therapeutic scheme to each point of group according to odds ratio values；
Therapeutic scheme recommendation step：Each point of group's therapeutic scheme is recommended, is arranged according to odds ratio value size descendings.
The present invention provides a kind of therapeutic scheme commending systems based on patients with cerebral apoplexy similarity analysis, including such as lower die
Block：
Data preprocessing module：For being pre-processed to data, the target group data needed for data modeling is obtained；
Feature selection module：Feature selecting is differently carried out for the different types of data to target group data,
Obtain feature selecting data；
Similitude grouping module：For classifying to feature selecting data, and feature description is carried out to each classification and is obtained
It is described to a point group character；
Therapeutic scheme recommending module：It is right for extracting and summarizing the therapeutic scheme of each classification based on a point group character description
The therapeutic scheme of all categories carries out validity sequence, recommends optimum treatment scheme.
Preferably, the data preprocessing module includes：
Data integration module：For being integrated to data, complete data set is formed；
Data cleansing module：Data lack of standardization for being concentrated to partial data carry out data cleansing；
Data go missing module：For to partial data concentrate exist missing data classifying type and continuous type feature according to
Missing data filling is carried out according to mode or mean value；
Enter a group screening module：For being based on into a group condition, data screening is carried out to complete data set.
Preferably, the feature selection module includes：
The derivative module of conversion：For carrying out conversion derivative to target group data, characteristic variable is formed；
Feature Selection module：For being screened to characteristic variable, candidate feature is obtained；
Characteristic selecting module：For calculating separately p-value values to all candidate features, chooses p-value values and be less than
The candidate feature of threshold value is as feature selecting data.
Preferably, the similitude grouping module includes：
Characteristic grouping module：For choosing characteristic of division, setting divides group's rule to divide group to handle feature selecting data, obtains
Grouping result；
Feature description module：It is described for each category feature to grouping result, obtains a point group character and describe.
Preferably, the therapeutic scheme recommending module includes：
Therapeutic scheme collection modules：It is described for being based on a point group character, the therapeutic scheme in each point of group is selected,
Summarize, obtains the therapeutic scheme set of each point of group；
Therapeutic scheme sorting module：It influences, and counts for being calculated using generalized regression method the therapeutic scheme of each point of group
Odds ratio values are calculated, are sorted to the therapeutic scheme to each point of group according to odds ratio values；
Therapeutic scheme recommending module：For recommending each point of group's therapeutic scheme, according to odds ratio value size descendings
Arrangement.
Compared with prior art, the present invention has following advantageous effect：
1, the present invention carries out similarity analysis to patients with cerebral apoplexy, is divided into different groups, and carry out to each group of feature
Description, by dividing group, can obtain the feature description of the various dimensions of patient, more fully understand patient profiles.
2, the present invention is based on similitude grouping results, and the sequence of validity, Ke Yigeng are carried out to each group of therapeutic scheme
It is efficiently and effectively different classes of patient's selection more accurate personalized therapeutic scheme to add, can greatly reduce time cost and
Economic cost.
3, the present invention is by dividing group and treatment efficiency analysis, for the interested therapeutic scheme of doctor or final result, model
Similar accurate crowd can be found for individual patient, and effective therapeutic scheme suggestion of individuation is provided on this basis, it is right
Yu doctor implements rehabilitation and correlative study to patient very big directive significance.
Description of the drawings
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon：
Fig. 1 is the flow chart that the therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method；
Fig. 2 is the fundamental diagram of data preprocessing module；
Fig. 3 is characterized the fundamental diagram of selecting module；
Fig. 4 is the fundamental diagram of similitude grouping module；
Fig. 5 is the fundamental diagram of therapeutic scheme recommending module.
Specific implementation mode
With reference to specific embodiment, the present invention is described in detail.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection domain.
As shown in Figures 1 to 5, the present invention provides a kind of hurt of rehabilitation scheme based on patients with cerebral apoplexy similarity analysis
Recommend method and system, similarity analysis is carried out to patients with cerebral apoplexy, is divided into different groups, and carry out to each group of feature
Description, by dividing group, can obtain the feature description of the various dimensions of patient, more fully understand patient profiles；It is based on
Similitude grouping result carries out each group of therapeutic scheme the sequence of validity, can be more efficiently and effectively inhomogeneity
Other more accurate personalized therapeutic scheme of patient's selection, can greatly reduce time cost and economic cost；By divide group and
Treatment efficiency analysis can find similar accurate people for the interested therapeutic scheme of doctor or final result for individual patient
Group, and effective therapeutic scheme suggestion of individuation is provided on this basis, rehabilitation and correlation are implemented to patient for doctor
Research has very big directive significance.
Specifically, according to a kind of hurt of rehabilitation scheme recommendation based on patients with cerebral apoplexy similarity analysis provided by the invention
Method, including：Data prediction step：Data are pre-processed, the target group data needed for data modeling is obtained；Feature
Select step：Feature selecting is differently carried out to the different types of data of target group data, obtains feature selecting data；
Similitude divides group's step：Classify to feature selecting data, and a point group character is obtained to each classification progress feature description and is retouched
It states；Therapeutic scheme recommendation step：It is extracted based on a point group character description and summarizes the therapeutic scheme of each classification, to all categories
Therapeutic scheme carries out validity sequence, recommends optimum treatment scheme.
Wherein, the data in data prediction step cover related to when discharge when stroke inpatients are admitted to hospital comment
Point, the doctor's advice of patient gender, age, occupation, medical history, laboratory examination, period of being admitted to hospital (includes rehabilitation and the use of use
Medicine) etc. relevant informations, indicated with data set D, pre-processed by the following method：
Step 1.1：Different time sections and the data for being dispersed in different tables are spliced to obtain one using data integrating method
It rises, forms complete data set：Each data source can export one or more csv files, according to the association rule of design, difference
Data source still has the information of same ID number or sequence number to link together, and association rule mainly according to patient's ID number or enters
Group sequence number.
Step 1.2：Data cleansing is carried out to nonstandard data (such as time format) in case data：For different classes
The different cleaning rule of the design data lack of standardization of type carries out regular and unreasonable data is handled or repaiied to data format
Change.
Step 1.3：For there are the classifying type of missing data and continuous type feature, being lacked respectively in accordance with mode and mean value
Lose data filling.
Step 1.4：According to entering group conditional log according to being screened, wherein entering a group condition is：
(a) there are the Barthel score datas in 7 days after being admitted to hospital, and the Barthel score datas in first 7 days of leaving hospital；
(b) scoring that goes out to be admitted to hospital at least is spaced 7 days；
(c) there are characteristic information data from case history typing, including hypertension, diabetes, smoking history etc..
It is handled by data prediction, obtains data with DpreIndicate, including data have continuous type characteristic, classify
Type characteristic, outcome data, hurt of rehabilitation scheme data.
More specifically, feature selection step includes：The data that will be obtained by data pre-processor, using different spies
Building method is levied, latent structure is differently carried out to different types of data, specially：
Step 2.1：The data that data prediction step obtains are converted and derived：Derived based on set operation new special
Sign, the set operation of use includes count, mean, min, max, std. etc., such as some patient may have several blood in one day
Pressure value, using average value, the last value of maximum value or minimum value this characteristic variable of blood pressure the most.Based on domain knowledge and association
Rule and method Apriori constructs new feature：New characteristic variable is derived according to the combination of existing feature.
Step 2.2：It is examined using Chi-square Test, Wilcoxon signed-rank, the ANOVA methods of inspection become two-value
Amount, binary object, continuous variable, successive objective feature are handled, and filter out impact factor as candidate feature, wherein：It is right
In two-valued variable, impact factor is filtered out using Chi-square Test；For binary object, Chi-square Test and Wilcoxon is respectively adopted
Signed-rank inspections filter out impact factor；For continuous variable, be respectively adopted Wilcoxon signed-rank examine and
ANOVA inspections filter out impact factor.For successive objective, impact factor is filtered out using ANOVA inspections；
Step 2.3：To all candidate features selected in step 2.2, its statistical check p-value values are calculated separately, are selected
P-value is taken to be less than 0.05 candidate feature, the final feature chosen as latent structure device.
By latent structure step process, obtained data are with DselectIt indicates, selection is characterized as gender, age, high blood
Press disease, diabetes, defect system of being admitted to hospital, GLU (blood glucose), LDLC (low density lipoprotein cholesterol), TG (triglycerides) etc..
In more detail, similitude divides group's step to include：Classify to patients with cerebral apoplexy, and each classification is carried out special
Sign description：First, it using the method for decision tree, chooses be admitted to hospital scoring and palsy disease time is used as characteristic of division successively, set
Divide group's rule, the data set D obtained to feature selection stepselectIt is handled, obtains grouping result.Then, based on dividing group to tie
Fruit, to GLU (blood glucose) average values and standard deviation, TG (triglycerides) average values and standard deviation, LDLC (low-density of each classification
Cholesterol) average value and standard deviation, average age, male's percentage accounting, average Barthel values, diabetes percentage accounting, high blood
Pressure percentage accounting etc. is described, and obtains a point group character and describes.
Further, by therapeutic scheme recommendation step, validity sequence is carried out to therapeutic scheme, is provided most effective
Therapeutic scheme is recommended：First, it is described based on a point group character, first extracts the therapeutic scheme that patient uses in each group and select,
Therapeutic scheme is summarized in such a way that collection merges, obtains each group of whole therapeutic scheme set.Then, for each
Each therapeutic scheme of group, being calculated using generalized regression method influences (whether can promote probability), and calculates odds ratio values
(computational methods show that the validity numerical value of each scheme is calculated as the index of e according to generalized regression), according to odds
Ratio values are ranked up therapeutic scheme.Finally, each group of therapeutic schemes are recommended, and are arranged according to odds ratio value size descendings
Row.Odds ratio values are bigger, illustrate that therapeutic scheme is more effective.
According to a kind of hurt of rehabilitation scheme commending system based on patients with cerebral apoplexy similarity analysis provided by the invention, packet
It includes：Data preprocessing module：For being pre-processed to data, the target group data needed for data modeling is obtained；Feature is selected
Select module：Feature selecting is differently carried out for the different types of data to target group data, obtains feature selecting number
According to；Similitude grouping module：For classifying to feature selecting data, and feature description is carried out to each classification and obtains a point group
Feature description；Therapeutic scheme recommending module：It is right for extracting and summarizing the therapeutic scheme of each classification based on a point group character description
The therapeutic scheme of all categories carries out validity sequence, recommends optimum treatment scheme.
Wherein, the data in data preprocessing module cover related to when discharge when stroke inpatients are admitted to hospital comment
Point, the doctor's advice of patient gender, age, occupation, medical history, laboratory examination, period of being admitted to hospital (includes rehabilitation and the use of use
Medicine) etc. relevant informations, indicated with data set D, by being pre-processed with lower module：
Data integration module：Different time sections and the data for being dispersed in different tables are spliced using data integrating method
To together, complete data set is formed：Each data source can export one or more csv files, according to the association rule of design,
Different data sources still have the information of same ID number or sequence number to link together, association rule mainly according to patient's ID number or
It is into a group sequence number.
Data cleansing module：Data cleansing is carried out to nonstandard data (such as time format) in case data：For not
With type the different cleaning rule of design data lack of standardization, to data format carry out it is regular and to unreasonable data at
Reason or modification.
Data go missing module：For there are the classifying types of missing data and continuous type feature, respectively in accordance with mode and
Value carries out missing data filling.
Enter a group screening module：According to entering group conditional log according to being screened, wherein entering a group condition is：
(a) there are the Barthel score datas in 7 days after being admitted to hospital, and the Barthel score datas in first 7 days of leaving hospital；
(b) scoring that goes out to be admitted to hospital at least is spaced 7 days；
(c) there are characteristic information data from case history typing, including hypertension, diabetes, smoking history etc..
It is handled by data prediction, obtains data with DpreIndicate, including data have continuous type characteristic, classify
Type characteristic, outcome data, hurt of rehabilitation scheme data.
More specifically, feature selection module includes：The data that will be obtained by data pre-processor, using different spies
Building method is levied, latent structure is differently carried out to different types of data, specially：
The derivative module of conversion：The data that data preprocessing module obtains are converted and derived：Spread out based on set operation
Raw new feature, the set operation of use includes count, mean, min, max, std. etc., such as some patient may have in one day
Several pressure values, using average value, the last value of maximum value or minimum value this characteristic variable of blood pressure the most.Based on domain knowledge
New feature is constructed with association rules method Apriori：New characteristic variable is derived according to the combination of existing feature.
Feature Selection module：It is examined using Chi-square Test, Wilcoxon signed-rank, the ANOVA methods of inspection pair two
Value variable, binary object, continuous variable, successive objective feature are handled, and filter out impact factor as candidate feature,
In：For two-valued variable, impact factor is filtered out using Chi-square Test；For binary object, be respectively adopted Chi-square Test and
Wilcoxon signed-rank inspections filter out impact factor；For continuous variable, Wilcoxon signed- are respectively adopted
Rank is examined and ANOVA inspections filter out impact factor.For successive objective, impact factor is filtered out using ANOVA inspections；
Characteristic selecting module：To all candidate features selected in Feature Selection module, its statistical check p- is calculated separately
Value values choose the candidate feature that p-value is less than 0.05, the final feature chosen as latent structure device.
By latent structure resume module, obtained data are with DselectIt indicates, selection is characterized as gender, age, high blood
Press disease, diabetes, defect system of being admitted to hospital, GLU (blood glucose), LDLC (low density lipoprotein cholesterol), TG (triglycerides) etc..
In more detail, similitude grouping module includes：Classify to patients with cerebral apoplexy, and each classification is carried out special
Sign description：First, it using the method for decision tree, chooses be admitted to hospital scoring and palsy disease time is used as characteristic of division successively, set
Divide group's rule, the data set D obtained to feature selection moduleselectIt is handled, obtains grouping result.Then, based on dividing group to tie
Fruit, to GLU (blood glucose) average values and standard deviation, TG (triglycerides) average values and standard deviation, LDLC (low-density of each classification
Cholesterol) average value and standard deviation, average age, male's percentage accounting, average Barthel values, diabetes percentage accounting, high blood
Pressure percentage accounting etc. is described, and obtains a point group character and describes.
Further, by therapeutic scheme recommending module, validity sequence is carried out to therapeutic scheme, is provided most effective
Therapeutic scheme is recommended：First, it is described based on a point group character, first extracts the therapeutic scheme that patient uses in each group and select,
Therapeutic scheme is summarized in such a way that collection merges, obtains each group of whole therapeutic scheme set.Then, for each
Each therapeutic scheme of group, being calculated using generalized regression method influences (whether can promote probability), and calculates odds ratio values
(computational methods show that the validity numerical value of each scheme is calculated as the index of e according to generalized regression), according to odds
Ratio values are ranked up therapeutic scheme.Finally, each group of therapeutic schemes are recommended, and are arranged according to odds ratio value size descendings
Row.Odds ratio values are bigger, illustrate that therapeutic scheme is more effective.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or change within the scope of the claims, this not shadow
Ring the substantive content of the present invention.In the absence of conflict, the feature in embodiments herein and embodiment can arbitrary phase
Mutually combination.
Claims (10)
1. a kind of therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method, which is characterized in that include the following steps：
Data prediction step：Data are pre-processed, the target group data needed for data modeling is obtained；
Feature selection step：Feature selecting is differently carried out to the different types of data of target group data, obtains feature
Select data；
Similitude divides group's step：Classify to feature selecting data, and feature description is carried out to each classification and obtains Fen Qunte
Sign description；
Therapeutic scheme recommendation step：It is extracted based on a point group character description and summarizes the therapeutic scheme of each classification, to all categories
Therapeutic scheme carry out validity sequence, recommend optimum treatment scheme.
2. the therapeutic scheme according to claim 1 based on patients with cerebral apoplexy similarity analysis recommends method, feature to exist
In the data prediction step includes：
Data integration step：Data are integrated, complete data set is formed；
Data cleansing step：Data cleansing is carried out to the data lack of standardization that partial data is concentrated；
Data remove deletion procedure：To partial data concentrate the data that there is missing classifying type and continuous type feature according to mode or
Person's mean value carries out missing data filling；
Enter a group screening step：It is based on into a group condition, data screening is carried out to complete data set.
3. the therapeutic scheme according to claim 1 based on patients with cerebral apoplexy similarity analysis recommends method, feature to exist
In the feature selection step includes：
The derivative step of conversion：Conversion derivative is carried out to target group data, forms characteristic variable；
Feature Selection step：Characteristic variable is screened, candidate feature is obtained；
Feature Selection step：P-value values are calculated separately to all candidate features, choose the time that p-value values are less than threshold value
Select feature as feature selecting data.
4. the therapeutic scheme according to claim 1 based on patients with cerebral apoplexy similarity analysis recommends method, feature to exist
Group's step is divided to include in, the similitude：
Characteristic grouping step：Characteristic of division is chosen, setting divides group's rule to divide group to handle feature selecting data, obtains a point group and tie
Fruit；
Feature description step：Each category feature of grouping result is described, a point group character is obtained and describes.
5. the therapeutic scheme according to claim 1 based on patients with cerebral apoplexy similarity analysis recommends method, feature to exist
In the therapeutic scheme recommendation step includes：
Therapeutic scheme set step：It is described based on a point group character, the therapeutic scheme in each point of group is selected, is summarized, is obtained
To the therapeutic scheme set of each point of group；
Therapeutic scheme sequence step：Being calculated using generalized regression method the therapeutic scheme of each point of group is influenced, and is calculated
Oddsratio values sort to the therapeutic scheme to each point of group according to odds ratio values；
Therapeutic scheme recommendation step：Each point of group's therapeutic scheme is recommended, is arranged according to odds ratio value size descendings.
6. a kind of therapeutic scheme commending system based on patients with cerebral apoplexy similarity analysis, which is characterized in that including following module：
Data preprocessing module：For being pre-processed to data, the target group data needed for data modeling is obtained；
Feature selection module：Feature selecting is differently carried out for the different types of data to target group data, is obtained
Feature selecting data；
Similitude grouping module：For classifying to feature selecting data, and feature description is carried out to each classification and is divided
Group character describes；
Therapeutic scheme recommending module：For extracting and summarizing the therapeutic scheme of each classification based on a point group character description, to all
The therapeutic scheme of classification carries out validity sequence, recommends optimum treatment scheme.
7. the therapeutic scheme commending system according to claim 6 based on patients with cerebral apoplexy similarity analysis, feature exist
In the data preprocessing module includes：
Data integration module：For being integrated to data, complete data set is formed；
Data cleansing module：Data lack of standardization for being concentrated to partial data carry out data cleansing；
Data go missing module：Classifying type and continuous type feature for concentrating the data that there is missing to partial data is according to crowd
Number or mean value carry out missing data filling；
Enter a group screening module：For being based on into a group condition, data screening is carried out to complete data set.
8. the therapeutic scheme commending system according to claim 6 based on patients with cerebral apoplexy similarity analysis, feature exist
In the feature selection module includes：
The derivative module of conversion：For carrying out conversion derivative to target group data, characteristic variable is formed；
Feature Selection module：For being screened to characteristic variable, candidate feature is obtained；
Characteristic selecting module：For calculating separately p-value values to all candidate features, chooses p-value values and be less than threshold value
Candidate feature as feature selecting data.
9. the therapeutic scheme commending system according to claim 6 based on patients with cerebral apoplexy similarity analysis, feature exist
In the similitude grouping module includes：
Characteristic grouping module：For choosing characteristic of division, setting divides group's rule to divide group to handle feature selecting data, obtains a point group
As a result；
Feature description module：It is described for each category feature to grouping result, obtains a point group character and describe.
10. the therapeutic scheme commending system according to claim 6 based on patients with cerebral apoplexy similarity analysis, feature exist
In the therapeutic scheme recommending module includes：
Therapeutic scheme collection modules：It is described for being based on a point group character, the therapeutic scheme in each point of group is selected, is converged
Always, the therapeutic scheme set of each point of group is obtained；
Therapeutic scheme sorting module：It influences, and calculates for being calculated using generalized regression method the therapeutic scheme of each point of group
Odds ratio values sort to the therapeutic scheme to each point of group according to odds ratio values；
Therapeutic scheme recommending module：For recommending each point of group's therapeutic scheme, arranged according to odds ratio value size descendings.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810136206.5A CN108511056A (en) | 2018-02-09 | 2018-02-09 | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810136206.5A CN108511056A (en) | 2018-02-09 | 2018-02-09 | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108511056A true CN108511056A (en) | 2018-09-07 |
Family
ID=63375584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810136206.5A Pending CN108511056A (en) | 2018-02-09 | 2018-02-09 | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108511056A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176308A (en) * | 2019-05-28 | 2019-08-27 | 广东工业大学 | Disease and the relevance of vital sign establish device, method, equipment and medium |
| CN110379505A (en) * | 2019-06-10 | 2019-10-25 | 天津开心生活科技有限公司 | A kind of recognition methods, device, readable medium and the electronic equipment of the common processing mode of disease |
| CN110970109A (en) * | 2019-11-14 | 2020-04-07 | 厦门中翎易优创科技有限公司 | Deep learning-based orthopaedic postoperative rehabilitation scheme recommendation method |
| CN112434737A (en) * | 2020-11-25 | 2021-03-02 | 南京大学 | Multi-agent evaluation criterion fused feature selection system for stroke analysis |
| CN112447292A (en) * | 2020-11-25 | 2021-03-05 | 南京大学 | Human body index-stroke relation analysis system based on machine learning interpretability |
| WO2021151295A1 (en) * | 2020-06-29 | 2021-08-05 | 平安科技（深圳）有限公司 | Method, apparatus, computer device, and medium for determining patient treatment plan |
| CN114078576A (en) * | 2021-11-19 | 2022-02-22 | 中国人民解放军总医院 | Clinical assistant decision method, device, equipment and medium |
| CN114171162A (en) * | 2021-12-03 | 2022-03-11 | 广州穗海新峰医疗设备制造股份有限公司 | Mirror neuron rehabilitation training method and system based on big data analysis |
| CN116246776A (en) * | 2023-04-04 | 2023-06-09 | 曜立科技(北京)有限公司 | Method and system for assisting cerebral apoplexy diagnosis decision |
| CN116504354A (en) * | 2023-06-28 | 2023-07-28 | 合肥工业大学 | Intelligent service recommendation method and system based on intelligent medical treatment |
| CN117912634A (en) * | 2024-03-20 | 2024-04-19 | 中国人民解放军总医院第八医学中心 | Postoperative rehabilitation training recommendation method for neurosurgery patients |
| CN118173262A (en) * | 2024-03-05 | 2024-06-11 | 齐鲁工业大学(山东省科学院) | Hemorrhagic stroke risk assessment method, system, storage medium and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050095660A1 (en) * | 2003-10-31 | 2005-05-05 | Unibio, S.R.I. | Enzyme activities and pH tests for the determination of the risk of obstetric and gynecologic complications in samples of body fluids of women |
| US20130197925A1 (en) * | 2012-01-31 | 2013-08-01 | Optumlnsight, Inc. | Behavioral clustering for removing outlying healthcare providers |
| US20140052465A1 (en) * | 2012-08-16 | 2014-02-20 | Ginger.io, Inc. | Method for modeling behavior and health changes |
| CN105279369A (en) * | 2015-09-06 | 2016-01-27 | 苏州协云和创生物科技有限公司 | Next generation sequencing based coronary heart disease genetic risk evaluation method |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
-
2018
- 2018-02-09 CN CN201810136206.5A patent/CN108511056A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050095660A1 (en) * | 2003-10-31 | 2005-05-05 | Unibio, S.R.I. | Enzyme activities and pH tests for the determination of the risk of obstetric and gynecologic complications in samples of body fluids of women |
| US20130197925A1 (en) * | 2012-01-31 | 2013-08-01 | Optumlnsight, Inc. | Behavioral clustering for removing outlying healthcare providers |
| US20140052465A1 (en) * | 2012-08-16 | 2014-02-20 | Ginger.io, Inc. | Method for modeling behavior and health changes |
| CN105279369A (en) * | 2015-09-06 | 2016-01-27 | 苏州协云和创生物科技有限公司 | Next generation sequencing based coronary heart disease genetic risk evaluation method |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110176308A (en) * | 2019-05-28 | 2019-08-27 | 广东工业大学 | Disease and the relevance of vital sign establish device, method, equipment and medium |
| CN110379505A (en) * | 2019-06-10 | 2019-10-25 | 天津开心生活科技有限公司 | A kind of recognition methods, device, readable medium and the electronic equipment of the common processing mode of disease |
| CN110970109A (en) * | 2019-11-14 | 2020-04-07 | 厦门中翎易优创科技有限公司 | Deep learning-based orthopaedic postoperative rehabilitation scheme recommendation method |
| WO2021151295A1 (en) * | 2020-06-29 | 2021-08-05 | 平安科技（深圳）有限公司 | Method, apparatus, computer device, and medium for determining patient treatment plan |
| CN112447292B (en) * | 2020-11-25 | 2022-03-25 | 南京大学 | Human body index-stroke relation analysis system based on machine learning interpretability |
| CN112447292A (en) * | 2020-11-25 | 2021-03-05 | 南京大学 | Human body index-stroke relation analysis system based on machine learning interpretability |
| CN112434737A (en) * | 2020-11-25 | 2021-03-02 | 南京大学 | Multi-agent evaluation criterion fused feature selection system for stroke analysis |
| CN112434737B (en) * | 2020-11-25 | 2024-03-19 | 南京大学 | Feature selection system for multi-agent evaluation criterion fusion for stroke analysis |
| CN114078576A (en) * | 2021-11-19 | 2022-02-22 | 中国人民解放军总医院 | Clinical assistant decision method, device, equipment and medium |
| CN114171162A (en) * | 2021-12-03 | 2022-03-11 | 广州穗海新峰医疗设备制造股份有限公司 | Mirror neuron rehabilitation training method and system based on big data analysis |
| CN116246776A (en) * | 2023-04-04 | 2023-06-09 | 曜立科技(北京)有限公司 | Method and system for assisting cerebral apoplexy diagnosis decision |
| CN116246776B (en) * | 2023-04-04 | 2023-11-07 | 曜立科技(北京)有限公司 | Method and system for assisting cerebral apoplexy diagnosis decision |
| CN116504354A (en) * | 2023-06-28 | 2023-07-28 | 合肥工业大学 | Intelligent service recommendation method and system based on intelligent medical treatment |
| CN116504354B (en) * | 2023-06-28 | 2024-01-09 | 合肥工业大学 | Intelligent service recommendation method and system based on intelligent medical treatment |
| CN118173262A (en) * | 2024-03-05 | 2024-06-11 | 齐鲁工业大学(山东省科学院) | Hemorrhagic stroke risk assessment method, system, storage medium and device |
| CN117912634A (en) * | 2024-03-20 | 2024-04-19 | 中国人民解放军总医院第八医学中心 | Postoperative rehabilitation training recommendation method for neurosurgery patients |
| CN117912634B (en) * | 2024-03-20 | 2024-05-24 | 中国人民解放军总医院第八医学中心 | Postoperative rehabilitation training recommendation method for neurosurgery patients |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108511056A (en) | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system | |
| Ibrahim et al. | Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases | |
| Yagis et al. | Generalization performance of deep learning models in neurodegenerative disease classification | |
| CN107193919A (en) | The search method and system of a kind of electronic health record | |
| CN111899866B (en) | Surgical operation complication evaluation system based on deep learning | |
| CN109360658B (en) | A disease pattern mining method and device based on word vector model | |
| CN114530249A (en) | Disease risk assessment model construction method based on intestinal microorganisms and application | |
| CN110739076A (en) | medical artificial intelligence public training platform | |
| CN103678534A (en) | Physiological information and health correlation acquisition method based on rough sets and fuzzy inference | |
| CN116864062B (en) | Health physical examination report data analysis management system based on Internet | |
| Chiwariro et al. | Comparative analysis of deep learning convolutional neural networks based on transfer learning for pneumonia detection | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN118197535B (en) | An antibiotic combination recommendation model and its application | |
| CN117095817A (en) | A feature-based and CT image-based fracture risk prediction method | |
| CN118312816B (en) | Cluster weighted clustering integrated medical text processing method and system based on member selection | |
| Maurya et al. | Balancing accuracy and efficiency: A lightweight deep learning model for COVID 19 detection | |
| CN120544908B (en) | A method and system for predicting tumor recurrence risk based on electronic medical record data | |
| González et al. | TRIALSCOPE: a unifying causal framework for scaling real-world evidence generation with biomedical language models | |
| Luo et al. | Detection of pneumonia in chest X‐ray image based on separable convolutional neural network | |
| Jiang et al. | Diabetes prediction model for unbalanced community follow-up data set based on optimal feature selection and scorecard | |
| CN118824507A (en) | Intelligent medical auxiliary diagnosis system based on multi-source collaborative mining of big data | |
| CN117766133A (en) | A method and device for identifying TCM syndromes based on intelligent algorithms | |
| Riad | IoT-based intelligent system For Alzheimer's Disease Detection & Monitoring | |
| CN116978539A (en) | Auxiliary diagnosis method and knowledge graph construction method, device, equipment and medium | |
| CN117790002B (en) | Information warning method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190408 Address after: Room 501-503, 43 Block 1485, Jialuo Road, Jiading District, Shanghai, 201800 Applicant after: Zhong electricity Ke software information Services Co., Ltd Applicant after: Shanghai Changjiang science and Technology Development Co Ltd Address before: Room 106-7, 50 Jiling Road, Jing'an District, Shanghai, 2003 Applicant before: Shanghai Changjiang science and Technology Development Co Ltd |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200617 Address after: Room 501-503, building 43, No. 1485, Jialuo Road, Jiading District, Shanghai, 201899 Applicant after: CETC SOFTWARE INFORMATION SERVICES Co.,Ltd. Applicant after: CHANGJIANG COMPUTER Group Corp. Address before: Room 501-503, 43 Block 1485, Jialuo Road, Jiading District, Shanghai, 201800 Applicant before: CETC SOFTWARE INFORMATION SERVICES Co.,Ltd. Applicant before: SHANGHAI CHANGJIANG TECHNOLOGY DEVELOPMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180907 |
|
| WD01 | Invention patent application deemed withdrawn after publication |