CN108520781A - A method of calculating test-tube baby's success final result probability - Google Patents
A method of calculating test-tube baby's success final result probability Download PDFInfo
- Publication number
- CN108520781A CN108520781A CN201810262122.6A CN201810262122A CN108520781A CN 108520781 A CN108520781 A CN 108520781A CN 201810262122 A CN201810262122 A CN 201810262122A CN 108520781 A CN108520781 A CN 108520781A
- Authority
- CN
- China
- Prior art keywords
- final result
- test
- data
- tube baby
- decision tree
- 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
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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Abstract
The invention discloses a kind of methods of calculating test-tube baby success final result probability.Steps of the method are：1) historical data and final result of the test-tube baby crowd of progress are collected；2) principal component analysis dimensionality reduction is carried out to the historical data of test-tube baby crowd；3) data after dimensionality reduction are constituted into data set with final result；4) training decision tree；5) decision tree system is built；6) new data is judged using decision tree system；7) probability of new data success final result is calculated.The present invention can carry out efficient data mining and analysis to the historical data and final result of test-tube baby crowd, build decision-tree model and system, to accurately calculate test-tube baby's success final result probability of new data.
Description
Technical field
The invention belongs to Data Minings, and in particular to a method of calculating test-tube baby's success final result probability.
Background technology
It is predicted according to the World Health Organization (WHO), 21 century infertility will be as being only second to tumour and cardiovascular and cerebrovascular diseases
The third-largest disease.The infertile patient numbers in China have surpassed 50,000,000 within 2016, wherein need auxiliary procreation technology as in vitro by
The crowd of essence-embryo transfer (i.e. test-tube baby) treatment is 5,000,000 or so, and test-tube baby helps pregnant mean clinical pregnancy rate only
40% or so, average live birth rate is 30% or so.Some large-scale Reproductive Medicine Centers have had more sufficient test tube
Baby's history case data and final result, but doctor is only capable of obtaining some fuzzy experiences using these data at present, it is difficult to it carries out
Better data mining and analysis, to obtain more helpful information.
Invention content
In order to solve the problems, such as to be difficult at present that test-tube baby's historical data is excavated and analyzed, the present invention proposes one
The method that kind calculates test-tube baby's success final result probability.It is analyzed by historical data to test-tube baby crowd and final result,
Decision tree system is built, realizes the calculating to new test-tube baby's data success final result probability.
Technical scheme is as follows：
A kind of computational methods of test-tube baby's insurance premium of the present invention, comprise the steps of：
1) historical data and final result of the test-tube baby crowd of progress are collected；User's history data include women relevant information,
Male's relevant information and medical information for hospital；Wherein women information is：Age, the infertile time limit, present illness history, history of operation, height, body
Weight, waist-to-hip ratio, anti-Muller test tube hormone, basic Antral follicles, Endocrine basis level, blood glucose, fasting insulin, thyroid gland
Function；Male's information is：Infertile factors；Medical information for hospital is：Medical Hospital Grade.Final result described in step 1) is successfully
It is pregnant and is not pregnant.
2) principal component analysis dimensionality reduction is carried out to the historical data of test-tube baby crowd, the characteristic dimension number after dimensionality reduction is set
It is 8.
3) data after dimensionality reduction are constituted into data set with final result.
4) a part of data are randomly selected in data set as training set, and decision tree is instructed using training set data
Practice；Preferably, training set sample size is the 70-80% of data set, the depth of decision tree is 5-15 layers, maximum characteristic
Mesh is 8.
5) it repeats step 4 and is total to n times, N decision tree of training builds decision tree system；Preferably, the ranging from 50- of N
100。
6) test-tube baby's data identical with the type of test-tube baby crowd historical data that are one newly being inputted, respectively
It goes to judge its final result using trained N decision tree.
7) count that N decision tree judge as a result, will be deemed as successfully decision tree tree/N of final result as test-tube baby
Success final result probability.
The present invention has the following advantages：
A kind of method calculating test-tube baby's success final result probability of the present invention, can go through test-tube baby crowd
History data and final result carry out efficient data mining and analysis, build decision-tree model and system, to accurately calculate new data
Test-tube baby's success final result probability.
Description of the drawings
Fig. 1 is a kind of flow chart calculating test-tube baby's success final result probability method provided in an embodiment of the present invention；
Fig. 2 is the result that 3 new datas provided in an embodiment of the present invention specifically calculate test-tube baby's success final result probability.
Specific implementation mode
Below by way of specific embodiment, the present invention will be further described, to more fully understand the present invention, but the present invention
It is not limited thereto.
As shown in Figure 1, a kind of flow chart calculating test-tube baby's success final result probability method of the present invention, is received first
Collect to collect more than 10000 and received historical data and final result that test-tube baby treats crowd, utilizes the method for principal component analysis
The historical data that crowd is treated to test-tube baby carries out dimensionality reduction, most important aspect in data is found out, with most important in data
Aspect replaces initial data.Data after dimensionality reduction are constituted into data set with final result, 80% number is randomly selected in data set
It according to as training set, is trained using decision tree of training set data pair, the depth of decision tree is 10 layers；Maximum characteristic
Mesh is 8.
Then 80% data are randomly selected in data set again as training set, using training set data to new one
Decision tree is trained, and the depth of decision tree randomly chooses in 5-15 layers；Maximum number of features is 8.Repeat the step
100 times, 100 decision trees for judging test-tube baby's final result are obtained, build decision tree system.
The test-tube baby's data newly inputted for one go to judge the data using trained 100 decision trees respectively
Corresponding final result；Count that 100 decision trees judge as a result, the decision tree tree/100 of final result is will be deemed as successfully, as this
The probability of data test-tube baby success final result.It is illustrated in figure 23 new datas and specifically calculates test-tube baby's success final result probability
As a result.It can be seen from the figure that 3 case parameters are different, it is several according to the calculated test-tube baby's success final result of 100 decision trees
Rate is also different
Although the present invention has been disclosed in the preferred embodiments as above, however, it is not intended to limit the invention.It is any to be familiar with ability
The technical staff in domain, without departing from the scope of the technical proposal of the invention, all using in the methods and techniques of the disclosure above
Appearance makes many possible changes and modifications to technical solution of the present invention, or is revised as the equivalent embodiment of equivalent variations.Therefore,
Every content without departing from technical solution of the present invention is made to the above embodiment any simple according to the technical essence of the invention
Modification, equivalent variations and modification, in the range of still falling within technical solution of the present invention protection.
Claims (7)
1. a kind of method calculating test-tube baby's success final result probability, which is characterized in that the method comprises the steps of：
1) historical data and final result of the test-tube baby crowd of progress are collected；
2) principal component analysis dimensionality reduction is carried out to the historical data of test-tube baby crowd；
3) data after dimensionality reduction are constituted into data set with final result；
4) a part of data are randomly selected in data set as training set, and decision tree is trained using training set data；
5) it repeats step 4 and is total to n times, N decision tree of training builds decision tree system；
6) the test-tube baby's data newly inputted to one are utilized respectively trained N decision tree and go to judge its final result；
7) count that N decision tree judges as a result, will be deemed as successfully decision tree tree/N of final result as test-tube baby's success
Final result probability.
2. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that in step 1)
The user's history data include women relevant information, male's relevant information and medical information for hospital；Wherein women information is：
Age, the infertile time limit, present illness history, history of operation, height, weight, waist-to-hip ratio, anti-Muller test tube hormone, basic Antral follicles, base
Plinth Endocrine Levels, blood glucose, fasting insulin, thyroid function；Male's information is：Infertile factors；Medical information for hospital is：Just
Examine Hospital Grade.
3. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that in step 1)
The final result is successfully to be pregnant and be not pregnant.
4. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that step 2) is main
Characteristic dimension number after constituent analysis dimensionality reduction is 8.
5. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that in step 4)
The training set sample size is the 70-80% of data set；The depth of decision tree is 5-15 layers；Maximum number of features is 8.
6. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that in step 5)
The trained N decision tree, the ranging from 50-100 of N.
7. a kind of method calculating test-tube baby's success final result probability as described in claim 1, which is characterized in that in step 6)
Test-tube baby's data of the new input are identical as the type of the historical data of the test-tube baby crowd described in step 1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810262122.6A CN108520781A (en) | 2018-03-28 | 2018-03-28 | A method of calculating test-tube baby's success final result probability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810262122.6A CN108520781A (en) | 2018-03-28 | 2018-03-28 | A method of calculating test-tube baby's success final result probability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108520781A true CN108520781A (en) | 2018-09-11 |
Family
ID=63434142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810262122.6A Pending CN108520781A (en) | 2018-03-28 | 2018-03-28 | A method of calculating test-tube baby's success final result probability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108520781A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112331340A (en) * | 2020-10-14 | 2021-02-05 | 国家卫生健康委科学技术研究所 | Intelligent prediction method and system for pregnancy probability of pregnant couple |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103876734A (en) * | 2014-03-24 | 2014-06-25 | 北京工业大学 | Electroencephalogram feature selection approach based on decision-making tree |
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN106897570A (en) * | 2017-03-02 | 2017-06-27 | 山东师范大学 | A kind of COPD test system based on machine learning |
| CN106980753A (en) * | 2017-02-28 | 2017-07-25 | 浙江工业大学 | A kind of data-driven machine learning method analyzed based on voxel for sacred disease |
-
2018
- 2018-03-28 CN CN201810262122.6A patent/CN108520781A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103876734A (en) * | 2014-03-24 | 2014-06-25 | 北京工业大学 | Electroencephalogram feature selection approach based on decision-making tree |
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN106980753A (en) * | 2017-02-28 | 2017-07-25 | 浙江工业大学 | A kind of data-driven machine learning method analyzed based on voxel for sacred disease |
| CN106897570A (en) * | 2017-03-02 | 2017-06-27 | 山东师范大学 | A kind of COPD test system based on machine learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112331340A (en) * | 2020-10-14 | 2021-02-05 | 国家卫生健康委科学技术研究所 | Intelligent prediction method and system for pregnancy probability of pregnant couple |
| CN112331340B (en) * | 2020-10-14 | 2021-11-23 | 国家卫生健康委科学技术研究所 | Intelligent prediction method and system for pregnancy probability of pregnant couple |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Vila-Blanco et al. | Deep neural networks for chronological age estimation from OPG images | |
| CN112216396B (en) | Method for predicting drug-side effect relationship based on graph neural network | |
| CN111613289B (en) | Individuation medicine dosage prediction method, device, electronic equipment and storage medium | |
| WO2021120936A1 (en) | Chronic disease prediction system based on multi-task learning model | |
| Wood et al. | The hominin fossil record: taxa, grades and clades | |
| CN110246577B (en) | Method for assisting gestational diabetes genetic risk prediction based on artificial intelligence | |
| CN107463771B (en) | Case grouping method and system | |
| CN103116707A (en) | Heart disease intelligent diagnostic method based on case reasoning | |
| CN111145912B (en) | Machine learning-based prediction device for personalized ovulation promotion scheme | |
| CN110443268B (en) | Liver CT image benign and malignant classification method based on deep learning | |
| Sabab et al. | Cardiovascular disease prognosis using effective classification and feature selection technique | |
| CN110767317A (en) | Cloud computing platform and method based on data mining and big data analysis | |
| Shahin et al. | Data mining in healthcare information systems: case studies in Northern Lebanon | |
| CN115862850A (en) | Modeling method and device of hepatocellular carcinoma monitoring model based on longitudinal multidimensional data | |
| CN108520781A (en) | A method of calculating test-tube baby's success final result probability | |
| CN117438029A (en) | Intelligent evaluation system for wound severity of orthopedic wound patient | |
| Li et al. | Lesion-aware convolutional neural network for chest radiograph classification | |
| CN111755129B (en) | Multi-mode osteoporosis layering early warning method and system | |
| Huang et al. | Uncertainty-based active learning by Bayesian U-Net for multi-label cone-beam CT segmentation | |
| Mishra et al. | Cancer detection in highly dense breasts using coherently focused time versa microwave imaging and using warm-boot random forest classifier | |
| CN115547502B (en) | Hemodialysis patient risk prediction device based on time sequence data | |
| Chauhan et al. | Framework to predict health diseases using attribute selection mechanism | |
| CN113693584B (en) | Method for selecting predicted variables for symptoms of depression, computer device, and storage medium | |
| Huang et al. | A new direction to promote the implementation of artificial intelligence in natural clinical settings | |
| CN111524564A (en) | Pneumonia clinical auxiliary monitoring method and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180911 |