CN115171890A - Non-invasive IUI treatment scoring system based on artificial intelligence technology - Google Patents

Non-invasive IUI treatment scoring system based on artificial intelligence technology Download PDF

Info

Publication number
CN115171890A
CN115171890A CN202210613874.9A CN202210613874A CN115171890A CN 115171890 A CN115171890 A CN 115171890A CN 202210613874 A CN202210613874 A CN 202210613874A CN 115171890 A CN115171890 A CN 115171890A
Authority
CN
China
Prior art keywords
sample
score
interval
artificial intelligence
clinical
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
Application number
CN202210613874.9A
Other languages
Chinese (zh)
Inventor
金昌博
宗佳琪
金莉萍
时文明
王鼎臣
以善佳
金勐
薛淑雅
王同帅
秦佳颖
王小波
刘振
牛丽慧
刘慧姝
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai First Maternity and Infant Hospital
Original Assignee
Shanghai First Maternity and Infant Hospital
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai First Maternity and Infant Hospital filed Critical Shanghai First Maternity and Infant Hospital
Priority to CN202210613874.9A priority Critical patent/CN115171890A/en
Publication of CN115171890A publication Critical patent/CN115171890A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Surgery (AREA)
  • Urology & Nephrology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a non-invasive IUI treatment scoring system based on an artificial intelligence technology, which is used for constructing a random forest model and evaluating the weight of clinical indexes; then, establishing an entropy-based model for discretizing data, and dividing each continuous clinical index into a plurality of preset intervals; configuring a score based on historical sample data for each interval; calculating a predictive score for each sample based on the weight of the clinical indicator and the score for each interval. The invention starts from the angle of artificial intelligence, combines the related theory of gynecological endocrine, takes clinical data of the previous patient diagnosis and treatment in the IUI treatment process as a research object, obtains an artificial intelligence function model through autonomous learning and training, obtains an IUI patient integration system according to the product of the treatment success rate of each interval and the weight of the characteristic, assists a clinician to make clinical decision by a total integration rule and an algorithm formula, and improves the safety, the accuracy and the high efficiency of clinical diagnosis and treatment.

Description

Non-invasive IUI treatment scoring system based on artificial intelligence technology
Technical Field
The invention relates to ICT specially adapted for medical diagnosis, medical simulation or medical data mining; the system is specially suitable for the technical field of detecting, monitoring or modeling epidemic diseases or infectious diseases, and particularly relates to a non-invasive IUI treatment scoring system based on an artificial intelligence technology.
Background
The world health organization predicts that infertility is the third most serious disease next to tumor and cardiovascular and cerebrovascular diseases, and the incidence rate of infertility is increasing year by year. In recent years, with the rapid development of assisted reproduction technologies, it has become an important method for treating infertility, such as artificial insemination within uterine cavity, in vitro fertilization-embryo transfer, and the like. Artificial insemination (IUI) in the uterine cavity of husband semen is a pregnancy-assisting technique for injecting high-activity semen suspension, which is preferably selected by a husband of a patient, into the uterine cavity of the patient to naturally combine the semen and the ovum to obtain pregnancy, and the treatment process of the pregnancy-assisting technique is very close to the natural pregnancy process, and has the advantages of economy, simple operation, small wound and the like.
IUI is usually performed in the natural cycle, but many factors need to be considered, including age, body Mass Index (BMI), hormone levels and ovarian reserve capacity, among others. The hormone level, including anti-mullerian hormone (AMH) and Follicle Stimulating Hormone (FSH), is measured by invasive blood tests, which are invasive and cause some harm to the patient, and the economic and time costs of treatment are increased, and it is a considerable problem to be able to determine the disease severity of IUI patients from the non-invasive information of the patient to assist clinical decisions. The importance of noninvasive prognostic factors such as age, infertility type and duration of infertility are appreciated from studies in recent years, but these studies are promising but lack an effective approach to assessing the severity of disease in IUI patients, and thus improve patient prognosis.
Currently, artificial intelligence including Machine Learning (ML), natural Language Processing (NLP), and robotic surgery has been widely used in the medical field for the treatment of many diseases. The method is widely applied to the reproduction fields of random forest models, support vector machines, artificial neural networks and the like, and achieves good effects. However, the use of artificial intelligence in IUI has been studied only rarely, particularly in the analysis of conditions in IUI patients.
Disclosure of Invention
The invention solves the problems in the prior art, provides a non-invasive IUI treatment scoring system based on an artificial intelligence technology, can comprehensively know the severity of an artificial insemination patient, measures and evaluates the basic condition of Artificial Insemination (AIH) population, and determines the subsequent operation mode by data.
The technical scheme adopted by the invention is that a non-invasive IUI treatment scoring system based on an artificial intelligence technology constructs a random forest model for evaluating the weight of clinical indexes; then, establishing an entropy-based model for discretizing data, and dividing each continuous clinical index into a plurality of preset intervals; configuring a score based on historical sample data for each interval;
calculating a predictive score for each sample based on the weight of the clinical indicator and the score for each interval.
Preferably, in the system, obtaining the score of each sample comprises the following steps:
step 1: constructing a random forest model, and evaluating and sequencing N characteristics related to each sample; the N features correspond to N clinical indicators;
step 2: constructing an entropy-based model, and discretizing all continuous features in the N features to divide the continuous features into a plurality of continuous intervals;
and 3, step 3: inputting all historical sample data, adjusting the historical sample data to each interval, and scoring and sequencing each interval based on the historical result corresponding to each interval;
and 4, step 4: an estimate is calculated for each sample.
Preferably, the step 1 comprises the steps of:
step 1.1: obtaining a decision tree corresponding to each feature in historical sample data, selecting corresponding data outside the bag to obtain an error of the data outside the bag, and recording the error as err 1 ；
Step 1.2: randomly adding noise interference to the current characteristics of all samples of the data outside the bag, and obtaining the error of the data outside the bag again and recording the error as err 2 ；
Step 1.3: the importance of the current feature is calculated,
Figure BDA0003672888890000021
is recorded as Weight X Wherein N is the total number of features and X is the current feature;
step 1.4: and traversing the N characteristics, and calculating each characteristic in the steps 1.1-1.3 until N importance results are obtained.
Preferably, the N features are sorted in descending order by their importance import.
Preferably, the step 2 comprises the steps of:
step 2.1: for the sample set S, let it include m output labels to
Figure BDA0003672888890000031
Is one sample of S, and S A Is a sample
Figure BDA0003672888890000032
The values on the continuous characteristic A are sorted from low to high, then
Figure BDA0003672888890000033
Wherein n is the total number of samples;
step 2.2: let T i Is a boundary value of the interval for dividing the sample set S into two subsets S 1 And S 2 Attribute value in a subset less than or equal to T i Attribute values in another subset greater than T i ；
Step 2.3: entropy E (S, T) obtained when divided i ) Above the threshold δ, S is recursively aligned using the method described above 1 And S 2 And (4) dividing until the number of preset intervals is reached or the interval cannot be divided again, wherein the delta belongs to the 0,1.
Preferably, in said step 2.2, T i Dividing the entropy E (S, T) i ) And minimum.
Preferably, the first and second electrodes are formed of a metal,
Figure BDA0003672888890000034
wherein the content of the first and second substances,
Figure BDA0003672888890000035
Figure BDA0003672888890000036
p k, finger tag l in subset S k K is the number of subsets.
Preferably, the first and second electrodes are, in an initial state,
Figure BDA0003672888890000037
preferably, each sample gets a Score of Score at feature i i ，Score i ＝q t ×Weight i ；
The estimated total score of each sample is
Figure BDA0003672888890000038
Wherein q is t Is the score in the interval t.
Preferably, the system is validated in a 10-fold cross-validation method.
The invention relates to a non-invasive IUI treatment scoring system based on an artificial intelligence technology, which is used for constructing a random forest model and evaluating the weight of clinical indexes; then, establishing an entropy-based model for discretizing data, and dividing each continuous clinical index into a plurality of preset intervals; configuring a score based on historical sample data for each interval; calculating a predictive score for each sample based on the weight of the clinical indicator and the score for each interval.
The invention starts from the angle of artificial intelligence, combines the related theory of gynecological endocrine, takes clinical data of the previous patient diagnosis and treatment in the IUI treatment process as a research object, obtains an artificial intelligence function model through autonomous learning and training, obtains an IUI patient integration system according to the product of the treatment success rate of each interval and the weight of the characteristic, and assists a clinician to make clinical decision by using a total integration rule and an algorithm formula, thereby improving the safety, the accuracy and the high efficiency of clinical diagnosis and treatment.
The invention provides a new visual angle for the clinical management and disease judgment of IUI patients, improves the limitations of insufficient human clinical diagnosis and treatment experience and limited prediction and prediction capability in the IUI treatment process, and optimizes the diagnosis and treatment efficiency of clinicians.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention is described in further detail with reference to the following examples, but the scope of the present invention is not limited thereto.
The invention relates to a non-invasive IUI treatment scoring system based on an artificial intelligence technology, which constructs a random forest model for evaluating the weight of clinical indexes; then, establishing an entropy-based model for discretizing data, and dividing each continuous clinical index into a plurality of preset intervals; configuring a score based on historical sample data for each interval;
calculating a predictive score for each sample based on the weight of the clinical indicator and the score for each interval. .
In the system, the step of obtaining the score of each sample comprises the following steps:
step 1: constructing a random forest model, and evaluating and sequencing N characteristics related to each sample; the N features correspond to N clinical indicators, such as age.
The step 1 comprises the following steps:
step 1.1: obtaining a decision tree corresponding to each feature in historical sample data, selecting corresponding data outside the bag to obtain an error of the data outside the bag, and recording the error as err 1 ；
Step 1.2: randomly adding noise interference to the current characteristics of all samples of the data outside the bag, and obtaining the error of the data outside the bag again and recording the error as err 2 ；
Step 1.3: the importance of the current feature is calculated,
Figure BDA0003672888890000041
is recorded as Weight X Wherein N is the total number of features and X is the current feature;
step 1.4: and traversing the N characteristics, and calculating each characteristic in the steps 1.1-1.3 until N importance results are obtained.
The N features are sorted in descending order by the importance import of the features.
Step 2: constructing an entropy-based model, and discretizing all continuous features in the N features to divide the continuous features into a plurality of continuous intervals, such as 5 intervals;
the step 2 comprises the following steps:
step 2.1: for the sample set S, let it include m output labels to
Figure BDA0003672888890000051
Is one sample of S, and S A Is a sample
Figure BDA0003672888890000052
The values on the continuous characteristic A are sorted from low to high, then
Figure BDA0003672888890000053
Wherein n is the total number of samples; in this embodiment, the output labels are "pregnant" and "not pregnant".
Step 2.2: let T i Is a boundary value of the interval for dividing the sample set S into two subsets S 1 And S 2 Attribute value in a subset less than or equal to T i Another subset having attribute values greater than T i ；
In said step 2.2, T i Let the divided entropy E (S, T) i ) And minimum.
In the initial state of the process, the temperature of the molten steel is controlled,
Figure BDA0003672888890000054
step 2.3: entropy E (S, T) obtained when divided i ) Above the threshold δ, S is recursively aligned using the method described above 1 And S 2 The division is carried out until the number of the preset intervals is reached or the division cannot be carried out again, delta belongs to (0,1), and generally delta is 0.5.
Figure BDA0003672888890000055
Wherein the content of the first and second substances,
Figure BDA0003672888890000056
p kl finger tag l in subset S k K is the number of subsets.
And step 3: inputting all historical sample data, adjusting the historical sample data to each interval, and scoring and sequencing each interval based on the historical result corresponding to each interval;
and 4, step 4: an estimate is calculated for each sample.
Score is obtained for each sample at feature i as Score i ，Score i ＝q t ×Weight i ；
The estimated total score of each sample is
Figure BDA0003672888890000057
Wherein q is t For the score in the interval t, t is generally a positive integer, corresponding to the number of each interval.
The system performs validity verification by a 10-fold cross-validation method.
In the invention, the trained system needs to be verified, and generally, a 10-fold cross-validation method is adopted.
In the invention, the 10-fold cross validation method comprises the following steps:
step 3.1: dividing all samples into 10 equal parts at random, wherein each part is used as a sample subset and is marked as a fold;
step 3.2: for each fold of the ten-fold system, selecting the fold as a test set, taking the other 9 folds as training sets, training a model, obtaining a generation error on the test set, obtaining a prediction result of each fold of data, and establishing 10 grading systems;
in step 3.2, the model is reinitialized every 10 cycles, but the weights remain the same for random initialization.
Step 3.3: after each cycle, calculating the classification accuracy S of each scoring system i ，
Figure BDA0003672888890000061
Figure BDA0003672888890000062
Wherein i, x, j are the positions of the labels in the set, y is a real label set in the test set, and y _ pred is a label value set obtained by using model prediction;
step 3.4, calculating the average value of the classification rate obtained 10 times,
Figure BDA0003672888890000063
true classification rate with S as a model or hypothesis function.
In the invention, 18 common characteristic division intervals and weights corresponding to the characteristics are given, as shown in table 1, in the practical application process, technicians in the field can set more dimensional characteristics according to practical requirements, including but not limited to whether both men and women have smoking history, alcoholism history, drug allergy history and the like; of course, in the implementation of the algorithm, the feature determines the upper limit, and precisely, the upper limit of the success rate fitting is determined to what extent, and an endless feature will cause overfitting due to the overlarge dimension, so that a proper amount of accurate and effective features play a great role in final scoring guidance.
TABLE 1
Figure BDA0003672888890000071
Figure BDA0003672888890000081
On the basis of table 1, table 2 is given as a total integration comparison table;
TABLE 2
Figure BDA0003672888890000082
Based on tables 1 and 2, two examples are given.
Example 1
The data of the female prescription comprise a 28-year-old female (5 points), a BMI24 (5 points), a non-pregnant woman history (5 points), a non-dysmenorrhea history (5 points), an earlier ovulation period intima thickness of 13mm (5 points) and the like;
male data include the amount of 5ml (5 minutes) of sperm routinely measured, density 74 x 10 6 Ml (3 min), etc.;
therefore, in this embodiment, each score is calculated, such as BMI score =12.49% by 5=62.45%, or age score =11.88% by 5=59.4%, and all the scores of the items are added to the total score;
the total score in this example was 80, and the table 2 was looked up, corresponding to 80 score a, indicating that the IUI pregnancy rate was higher in this patient, and this is recommended.
Example 2
The data of the female prescription comprise a 38-year-old female (score 2), a BMI36 (score 2), 4 pregnancies (score 1), dysmenorrhea (score 1), an inner membrane thickness of 5mm (score 1) in the ovulation period and the like;
male data included the routine measurement of semen at 1.6ml (2 min), density 16 x 10 6 Ml (2 min), etc.;
in this embodiment, therefore, each score is calculated, such as BMI score =12.49% by 2=24.98%, and age score =11.88% by 2=23.76%, and all the scores of the items are added to the total score;
let the total score in this example be 25, look up table 2, corresponding to 25 score E, indicating that the IUI pregnancy rate for this patient is very low, and this is not recommended.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A non-invasive IUI treatment scoring system based on artificial intelligence techniques, characterized by: the system constructs a random forest model for evaluating the weight of the clinical index; then, establishing an entropy-based model for discretizing data, and dividing each continuous clinical index into a plurality of preset intervals; configuring a score based on historical sample data for each interval;
calculating a predictive score for each sample based on the weight of the clinical indicator and the score for each interval.
2. The system of claim 1, wherein the system comprises: in the system, obtaining the score of each sample comprises the following steps:
step 1: constructing a random forest model, and evaluating and sequencing N characteristics related to each sample; the N features correspond to N clinical indicators;
step 2: constructing an entropy-based model, and discretizing all continuous features in the N features to divide the continuous features into a plurality of continuous intervals;
and step 3: inputting all historical sample data, adjusting the historical sample data to each interval, and scoring and sequencing each interval based on the historical result corresponding to each interval;
and 4, step 4: an estimate is calculated for each sample.
3. A non-invasive IUI treatment scoring system based on artificial intelligence techniques according to claim 2, characterized in that: the step 1 comprises the following steps:
step 1.1: obtaining a decision tree corresponding to each feature in historical sample data, selecting corresponding data outside the bag to obtain an error of the data outside the bag, and recording the error as err 1 ；
Step 1.2: data outside the bagRandomly adding noise interference to the current characteristics of all samples, and obtaining the error of the data outside the bag again and recording the error as err 2 ；
Step 1.3: the importance of the current feature is calculated,
Figure FDA0003672888880000021
is recorded as Weight X Wherein N is the total number of features and X is the current feature;
step 1.4: and traversing the N characteristics, and calculating each characteristic in the steps 1.1-1.3 until N importance results are obtained.
4. An artificial intelligence technology based non-invasive IUI treatment scoring system according to claim 2 or 3, characterized in that: the N features are sorted in descending order by the importance import of the features.
5. The system of claim 2, wherein the system comprises: the step 2 comprises the following steps:
step 2.1: for the sample set S, let it include m output labels to
Figure FDA0003672888880000022
Is one sample of S, and S A Is a sample
Figure FDA0003672888880000023
The values on the continuous characteristic A are sorted from low to high, then
Figure FDA0003672888880000024
Wherein n is the total number of samples;
step 2.2: let T i Is a boundary value of the interval for dividing the sample set S into two subsets S 1 And S 2 Attribute value in a subset less than or equal to T i Another subset having attribute values greater than T i ；
Step 2.3: entropy E (S, T) obtained when divided i ) Above the threshold δ, S is recursively aligned using the method described above 1 And S 2 And (4) dividing until the number of preset intervals is reached or the interval cannot be divided again, wherein the delta belongs to the 0,1.
6. The system of claim 5, wherein the system comprises: in said step 2.2, T i Let the divided entropy E (S, T) i ) And is minimal.
7. An artificial intelligence technology based non-invasive IUI treatment scoring system according to claim 5 or 6, characterized in that:
Figure FDA0003672888880000031
wherein the content of the first and second substances,
Figure FDA0003672888880000032
p kl finger tag l in subset S k K is the number of subsets.
8. The system of claim 5, wherein the system comprises: in the initial state of the process, the temperature of the molten steel is controlled,
Figure FDA0003672888880000033
9. a non-invasive IUI treatment scoring system based on artificial intelligence techniques according to claim 2, characterized in that: score obtained at feature i for each sample i ，Score i ＝q t ×Weight i ；
The estimated score of each sample is
Figure FDA0003672888880000034
Wherein q is t Is divided into intervals tThe value is obtained.
10. The system of claim 2, wherein the system comprises: the system performs validity verification by a 10-fold cross-validation method.
CN202210613874.9A 2022-05-31 2022-05-31 Non-invasive IUI treatment scoring system based on artificial intelligence technology Pending CN115171890A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210613874.9A CN115171890A (en) 2022-05-31 2022-05-31 Non-invasive IUI treatment scoring system based on artificial intelligence technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210613874.9A CN115171890A (en) 2022-05-31 2022-05-31 Non-invasive IUI treatment scoring system based on artificial intelligence technology

Publications (1)

Publication Number Publication Date
CN115171890A true CN115171890A (en) 2022-10-11

Family

ID=83482740

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210613874.9A Pending CN115171890A (en) 2022-05-31 2022-05-31 Non-invasive IUI treatment scoring system based on artificial intelligence technology

Country Status (1)

Country Link
CN (1) CN115171890A (en)

Similar Documents

Publication Publication Date Title
Georgieva et al. Artificial neural networks applied to fetal monitoring in labour
CN107887022B (en) SSTM-based intelligent diagnosis method for traditional Chinese medicine syndromes
CN110246577B (en) Method for assisting gestational diabetes genetic risk prediction based on artificial intelligence
CN110956626B (en) Image-based prognosis evaluation method and device
Khezri et al. A fuzzy rule-based expert system for the prognosis of the risk of development of the breast cancer
Higa Diagnosis of breast cancer using decision tree and artificial neural network algorithms
CN108847285A (en) Pregnant early period and second trimester Down's syndreme screening method based on machine learning
Sakinah et al. LSTM with adam optimization-powered high accuracy preeclampsia classification
CN113066574A (en) Neural network-based aneurysm rupture prediction method, device and storage medium
CN115862850A (en) Modeling method and device of hepatocellular carcinoma monitoring model based on longitudinal multidimensional data
CN112397176A (en) Intelligent oxytocin dose regulation and control method and system based on uterine contraction signals and LightGBM
Peterek et al. Human fetus health classification on cardiotocographic data using random forests
CN113628761B (en) Method for predicting treatment efficacy of anti-angiogenesis drug combined with immune checkpoint inhibitor
Tahir et al. Neural networks algorithm to inquire previous preeclampsia factors in women with chronic hypertension during pregnancy in childbirth process
CN113052205B (en) Lying-in woman data classification method, device, equipment and medium based on machine learning
CN116580847B (en) Method and system for predicting prognosis of septic shock
Hamilton et al. The evolution of the labor curve and its implications for clinical practice: the relationship between cervical dilation, station, and time during labor
CN115171890A (en) Non-invasive IUI treatment scoring system based on artificial intelligence technology
CN117116477A (en) Construction method and system of prostate cancer disease risk prediction model based on random forest and XGBoost
Chaudhary et al. Detection Of Postpartum Hemorrhaged Using Fuzzy Deep Learning Architecture
CN109102896A (en) A kind of method of generating classification model, data classification method and device
CN112382382B (en) Cost-sensitive integrated learning classification method and system
Guo et al. Integrated learning: screening optimal biomarkers for identifying preeclampsia in placental mRNA samples
CN111184948B (en) Vascular targeted photodynamic therapy-based nevus flammeus treatment method and system
Zhong et al. Gestational Diabetes Mellitus Prediction Based on Two Classification Algorithms

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