CN115186918A - Fetal birth weight prediction method based on ensemble learning - Google Patents
Fetal birth weight prediction method based on ensemble learning Download PDFInfo
- Publication number
- CN115186918A CN115186918A CN202210874763.3A CN202210874763A CN115186918A CN 115186918 A CN115186918 A CN 115186918A CN 202210874763 A CN202210874763 A CN 202210874763A CN 115186918 A CN115186918 A CN 115186918A
- Authority
- CN
- China
- Prior art keywords
- weight
- ensemble learning
- model
- newborns
- prediction method
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000001605 fetal effect Effects 0.000 title claims abstract description 27
- 230000005477 standard model Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000012935 Averaging Methods 0.000 claims abstract description 4
- 238000002604 ultrasonography Methods 0.000 claims description 17
- 230000035935 pregnancy Effects 0.000 claims description 16
- 230000003187 abdominal effect Effects 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 210000003754 fetus Anatomy 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 208000004104 gestational diabetes Diseases 0.000 claims description 3
- 230000004584 weight gain Effects 0.000 claims description 3
- 235000019786 weight gain Nutrition 0.000 claims description 3
- 210000004381 amniotic fluid Anatomy 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 230000001936 parietal effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 8
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000005303 weighing Methods 0.000 description 3
- 208000021017 Weight Gain Diseases 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 208000018773 low birth weight Diseases 0.000 description 2
- 231100000533 low birth weight Toxicity 0.000 description 2
- 230000005906 menstruation Effects 0.000 description 2
- 208000010392 Bone Fractures Diseases 0.000 description 1
- 206010017076 Fracture Diseases 0.000 description 1
- 208000035223 Gestational Weight Gain Diseases 0.000 description 1
- 206010033307 Overweight Diseases 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 208000018525 Postpartum Hemorrhage Diseases 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 206010040613 Shoulder Dystocia Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007636 ensemble learning method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004578 fetal growth Effects 0.000 description 1
- 230000009546 growth abnormality Effects 0.000 description 1
- 210000002758 humerus Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002175 menstrual effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to the technical field of fetal birth weight prediction, and provides a fetal birth weight prediction method based on ensemble learning, which comprises the following steps: preprocessing and data balancing processing are carried out on case data; determining a standard model; averaging the standard models to generate an ensemble learning model; training the ensemble learning model through the case data; and inputting feature information into the ensemble learning model to generate a predicted fetal weight.
Description
Technical Field
The invention relates to the technical field of fetal birth weight prediction in general. In particular, the invention relates to a fetus birth weight prediction method based on ensemble learning.
Background
In modern prenatal care, it is essential to predict fetal weight in order to monitor fetal growth. Since growth abnormalities are associated with adverse consequences for the parturient and fetus, such as the birth of a giant fetus associated with shoulder dystocia, postpartum hemorrhage and fracture at birth, infants with low birth weight are at increased risk of receiving Neonatal Intensive Care Unit (NICU) and lifelong disease. Thus, accurate prediction of fetal weight facilitates clinical decisions, such as timely prenatal intervention and selection of a reasonable delivery style to improve pregnancy outcome.
In the prior art, an ultrasonic evaluation method based on biological characteristic measurement and a regression equation is the most preferred method in obstetrical practice due to objectivity and convenience. However, most ultrasound formulas are established based on the western population, and since the fetal weight varies from race to race after 20 weeks, there is a deviation when the ultrasound formula is applied to chinese. In addition, the accuracy of fetal weight prediction for large and low birth weight infants is low. Taking the Hadlock equation as an example, the overall sensitivity of estimating fetal weight is only 0.56 (95% Cl, 0.49-0.62), while inaccurate estimates may lead to inappropriate prenatal intervention. In addition, the prior art generally depends on professional ultrasonic instruments, so that a lot of inconvenience exists in use.
At present, a method for predicting the birth weight of a fetus with high convenience and accuracy needs to be provided.
Disclosure of Invention
To at least partially solve the above problems in the prior art, the present invention provides a method for predicting birth weight of fetus based on ensemble learning, comprising the following steps:
preprocessing and data balancing processing are carried out on case data;
determining a standard model;
averaging the standard models to generate an ensemble learning model;
training the ensemble learning model through the case data; and
inputting feature information into the ensemble learning model to generate a fetal predicted weight.
In one embodiment of the invention, it is provided that the preprocessing of the case data comprises:
deleting the missing value; and/or
Confirming the deletion value of one of height, weight and BMI before pregnancy according to the BMI formula; and/or
Converting the number of gestational days into the number of gestational weeks; and/or
Converting a first feature into a second feature', wherein the first feature comprises obstetrics related features and ultrasound related features, and the second feature is related to pregnancy time and is represented by the following formula:
in one embodiment of the present invention, it is provided that the data equalization processing of the case data includes:
classifying newborns weighing less than 2500g as low-weight newborns, newborns weighing 2500g or more and 4000g or less as normal-weight newborns, and newborns weighing 4000g or more as large-weight newborns; and
the number of low-weight and large-weight newborns is increased by the up-sampling method.
In one embodiment of the invention, it is provided that the upsampling method comprises a SMOTE method.
In one embodiment of the invention, the standard model comprises a Ridge model, an SVM model, a Random Forest model, an XGboost model and an MLP model.
In one embodiment of the invention, the standard model is averaged by a Bagging method to generate an ensemble learning model.
In one embodiment of the invention, it is provided that the characteristic information comprises: pre-pregnancy weight, last parity weight, last ultrasound births day, pre-pregnancy BMI, weight gain during pregnancy, last parity births day, gestational diabetes mellitus, parity, parietal diameter, abdominal circumference, left and right abdominal diameters, anteroposterior abdominal diameter, and amniotic fluid index.
The present invention further provides a computer system, comprising:
a processor configured to execute machine executable instructions; and
a memory having stored thereon machine executable instructions which, when executed by the processor, perform the steps according to the ensemble learning-based fetal birth weight prediction method.
The invention also proposes a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, performs the steps according to the ensemble learning based fetal birth weight prediction method.
It should be noted that the present invention is not related to methods for diagnosis and treatment of disease, but merely provides information related to medical treatment, and pertains to an intelligent system, i.e. the present invention is neither intended to determine the disease of a patient, nor to provide a parameter or index for diagnosing a disease, nor is it a method for prescreening a disease. In contrast, the information provided by the solution of the invention cannot be used for diagnosis and treatment of diseases, but the corresponding diagnosis and treatment should be provided to the user by the hospital/doctor.
The invention has at least the following beneficial effects: the invention provides a fetus birth weight prediction method based on ensemble learning, and the prediction effect of the method in different weight ranges greatly exceeds that of an ultrasonic formula. The accuracy of final prediction of the fetal birth weight can reach 82.25%. In addition, in the method, the user can input the characteristic information through the mobile terminal, so that the use convenience is greatly improved.
Drawings
To further clarify the advantages and features that may be present in various embodiments of the present invention, a more particular description of various embodiments of the invention will be rendered by reference to the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. In the drawings, the same or corresponding parts will be denoted by the same or similar reference numerals for clarity.
Fig. 1 shows a computer system implementing the method according to the invention.
Fig. 2 is a flow chart of a method for predicting birth weight of a fetus based on ensemble learning according to an embodiment of the present invention.
Fig. 3 shows a schematic diagram of a multi-layer perceptron model.
Detailed Description
It should be noted that the components in the figures may be exaggerated and not necessarily to scale for illustrative purposes. In the figures, identical or functionally identical components are provided with the same reference symbols.
In the present invention, "disposed on" \ 8230 "", "disposed over" \823030 "", and "disposed over" \8230 "", do not exclude the presence of an intermediate therebetween, unless otherwise specified. Furthermore, "arranged on or above" \\8230 ", merely indicates a relative positional relationship between two components, and in certain cases, such as after reversing the product direction, may also be converted to" arranged under or below \8230 ", and vice versa.
In the present invention, the embodiments are only intended to illustrate the aspects of the present invention, and should not be construed as limiting.
In the present invention, the terms "a" and "an" do not exclude the presence of a plurality of elements, unless otherwise specified.
It is further noted herein that in embodiments of the present invention, only a portion of the components or assemblies may be shown for clarity and simplicity, but those of ordinary skill in the art will appreciate that, given the teachings of the present invention, required components or assemblies may be added as needed for a particular situation. Furthermore, features from different embodiments of the invention may be combined with each other, unless otherwise indicated. For example, a feature of the second embodiment may be substituted for a corresponding or functionally equivalent or similar feature of the first embodiment, and the resulting embodiments are likewise within the scope of the disclosure or recitation of the present application.
It is also noted herein that, within the scope of the present invention, the terms "same", "equal", and the like do not mean that the two values are absolutely equal, but allow some reasonable error, that is, the terms also encompass "substantially the same", "substantially equal". By analogy, in the present disclosure, the terms "perpendicular," parallel, "and the like in the directions of the tables also encompass the meanings of" substantially perpendicular, "" substantially parallel.
The numbering of the steps of the methods of the present invention does not limit the order in which the method steps are performed. Unless specifically stated, the method steps may be performed in a different order.
The invention is further elucidated with reference to the following description, in conjunction with the detailed description, and with reference to the accompanying drawings.
FIG. 1 illustrates a computer system 100 implementing systems and/or methods in accordance with the present invention. Unless specifically stated otherwise, a method and/or system in accordance with the present invention may be implemented in the computer system 100 shown in FIG. 1 for purposes of the present invention, or the present invention may be implemented in a distributed fashion across a network, such as a local area network or the Internet, among multiple computer systems 100 in accordance with the present invention. Computer system 100 of the present invention may comprise various types of computer systems, such as hand-held devices, laptop computers, personal Digital Assistants (PDAs), multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, network servers, tablet computers, and the like.
As shown in FIG. 1, computer system 100 comprises processor 111, system bus 101, system memory 102, video adapter 105, audio adapter 107, hard drive interface 109, optical drive interface 113, network interface 114, and Universal Serial Bus (USB) interface 112. The system bus 101 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The system bus 101 is used for communication between the respective bus devices. In addition to the bus devices or interfaces shown in fig. 1, other bus devices or interfaces are also contemplated. The system memory 102 includes a Read Only Memory (ROM) 103 and a Random Access Memory (RAM) 104, where the ROM 103 may store, for example, basic input/output system (BIOS) data used to implement basic routines for information transfer at start-up, and the RAM 104 is used to provide operating memory for the system that is accessed quickly. The computer system 100 further includes a hard disk drive 109 for reading from and writing to a hard disk 110, an optical drive interface 113 for reading from or writing to optical media such as a CD-ROM, and the like. Hard disk 110 may store, for example, an operating system and application programs. The drives and their associated computer-readable media provide nonvolatile storage of computer readable instructions, data structures, program modules and other data for the computer system 100. Computer system 100 may also include a video adapter 105 for image processing and/or image output for connecting an output device such as a display 106. Computer system 100 may also include an audio adapter 107 for audio processing and/or audio output, for connecting output devices such as speakers 108. In addition, the computer system 100 may also include a network interface 114 for network connections, where the network interface 114 may connect to the Internet 116 through a network device, such as a router 115, where the connection may be wired or wireless. Additionally, computer system 100 may also include a universal serial bus interface (USB) 112 for connecting peripheral devices, including, for example, a keyboard 117, a mouse 118, and other peripheral devices, such as a microphone, a camera, and the like.
When the invention is implemented on the computer system 100 shown in fig. 1, the fetal birth weight can be predicted in different weight ranges, the prediction effect can greatly exceed the ultrasonic formula, and the accuracy of the fetal birth weight prediction can finally reach 82.25%. In addition, in the method, the user can input the characteristic information through the mobile terminal, so that the use convenience is greatly improved.
Furthermore, embodiments may be provided as a computer program product that may include one or more machine-readable media having stored thereon machine-executable instructions that, when executed by one or more machines such as a computer, network of computers, or other electronic devices, may result in the one or more machines performing operations in accordance with embodiments of the present invention. The machine-readable medium may include, but is not limited to, floppy diskettes, optical disks, CD-ROMs (compact disc read-only memories), and magneto-optical disks, ROMs (read-only memories), RAMs (random access memories), EPROMs (erasable programmable read-only memories), EEPROMs (electrically erasable programmable read-only memories), magnetic or optical cards, flash memory, or other type of media/machine-readable medium suitable for storing machine-executable instructions.
Moreover, embodiments may be downloaded as a computer program product, wherein the program may be transferred from a remote computer (e.g., a server) to a requesting computer (e.g., a client) by way of one or more data signals embodied in and/or modulated by a carrier wave or other propagation medium via a communication link (e.g., a modem and/or network connection). Thus, a machine-readable medium as used herein may include, but is not necessarily required to be, such a carrier wave.
Fig. 2 is a flow chart of a method for predicting birth weight of a fetus based on ensemble learning according to an embodiment of the present invention. As shown in fig. 2, the method may include the steps of:
step 201, preprocessing and data balancing are performed on the case data.
Step 202, determining a standard model.
And step 203, averaging the standard models to generate an ensemble learning model.
And step 204, training the ensemble learning model through the case data.
Step 205, inputting the characteristic information into the ensemble learning model to generate the predicted fetal weight.
In step 201, for the missing values in the case data, the corresponding missing values can be filled as much as possible according to the calculation formula BMI = weight/[ height ] 2, and the relationship between height, weight and BMI before pregnancy. For other missing values, they can be deleted directly because the amount of original data is sufficient and the missing value ratio is not high. 17036 samples remained after the null was removed. New features of the BMI classification can be added based on chinese body mass index and in combination with the corresponding BMI to consider whether the weight gain during pregnancy is within the appropriate range. In addition, the number of gestational days may be converted into the number of gestational weeks. Processing the characteristics into a form related to pregnancy time, including obstetric related characteristics and ultrasound related characteristics, as represented by the formula:
the proportion of low and large births is very small relative to normal-weight newborns, and we classify the samples into three categories by boundaries of 2500g and 4000g and then upsample to increase the number of extreme-weight newborns so that the model can be used for any weight of newborn weight prediction. A SMOTE (Synthetic minimum Oversampling Technique) method can be used as the upsampling method, and the SMOTE method is based on an improved scheme of a random Oversampling method, so that the problem of model overfitting caused by repeated sampling can be solved. In the SMOTE method, comprising:
calculating the distance from each sample x in the minority class to all samples in the minority class sample set Smin by taking the Euclidean distance as a standard, and obtaining k nearest neighbors of the sample x;
the sampling rate is set according to the sample imbalance rate to determine the sampling rate N. For each minority class sample x, randomly selecting a plurality of samples from k nearest neighbors centered on the minority class sample x, assuming that the selected nearest neighbors are xn; and
for each randomly selected neighbor xn, a new sample is constructed from the original sample according to the following formula:
x new ＝x+rand(0，1)*|x-x n |。
ridge, SVM, random-Forest, XGboost, MLP may be used as reference models in step 202.
In the Ridge model, the first term of the cost function of the regression is consistent with the standard linear regression, which is the sum of squared euclidean distances, except that the L2 norm is added as a penalty term. The cost function is expressed as:
the XGBoost model is an improvement on a (GBDT) Gradient Boosting Decision Tree. The objective function (loss function and regularization) needed to minimize iteration t in the XGBoost model is expressed as:
the method is operated in a Random Forest model by constructing a plurality of decision trees during training and outputting an average prediction class, wherein the method comprises the following steps:
generating n samples (same number as original training set) from the sample set by resampling (first bagging);
assuming that the feature number is k, randomly selecting t features from the k features of the n samples, and obtaining an optimal segmentation point by constructing a decision tree (bagging for the second time); repeating m times to generate m decision trees; and
the prediction is made by a majority voting mechanism.
An SVM (support vector machine) model is a generalized linear classifier, binary classification is carried out on data according to supervised learning, and a decision boundary is the maximum margin for solving a learning sample. The maximum margin hyperplane can also be used for regression problems. A linear kernel can be used in the regression problem.
As shown in fig. 3, a four-layer neural network may be constructed in an MLP (multi layer Perceptron) model, in which Batch norms are used, and Batch norm and a leak ReLU function are used in multiple neural layers
In step 203, a plurality of reference models can be combined by an ensemble learning method to obtain a model with better prediction effect. Ensemble learning is generally classified into three types, bagging, boosting, and Stacking. In the invention, only Bagging is used for constructing the ensemble learning model, and the ensemble learning model is averaged on the basis of the reference model result to obtain the final ensemble learning model result.
In step 205, 16 feature variables are extracted from the information transmitted by the user and the uploaded picture information, and input into the prediction model, which gives the predicted birth weight of the fetus, and records the relevant information according to the number of the doctor card of the user as an identification code, so as to perform later query and verification. Wherein the characteristic variables and sources are as follows: pregnancy weight (user input), last birth sample weight (user input), last ultrasound distance delivery day (due date-date of last delivery ultrasound), last BMI { due weight of pregnancy/(square of height (m) }, pregnancy weight gain (weight of last delivery-due weight of last delivery), last delivery distance delivery day (due date-last delivery), gestational diabetes (user input), birth time (user input), double-vertex diameter (obtained by OCR recognizing ultrasound information, range of values [50, 120 ]) mm), head circumference (obtained by OCR recognizing ultrasound information, range of values [150, 400 ]) mm), femur length (obtained by recognizing ultrasound information, range of values [20, 80 ]) mm), humerus length (obtained by OCR recognizing ultrasound information, range of values [5, 80 ]) mm), abdominal circumference (obtained by OCR recognizing ultrasound information, range of values [150, 400 ]) mm, abdominal circumference (obtained by OCR recognizing ultrasound information, range of values [40, 140 mm ], sheep circumference range of values [ OCR, 40, 140 mm ], abdominal circumference of values [ OCR information, OCR range of values [ 140, 140 mm ], abdominal circumference of values [ 140 mm ], abdominal circumference of values (obtained by OCR recognizing ultrasound information, 140 mm ], abdominal circumference of values [150, 140 mm ], abdominal circumference of values obtained by OCR recognizing ultrasound information, 140 mm, and abdominal circumference. And (3) outputting a model: it is estimated that [82.44]% of your fetal weight has a probability of [2790-3410] g, and the closest value is [3100] g. [] The result value given by the model is in the inner part, and the rest characters are fixed.
The calculation formula of the expected delivery period is as follows: adding 9 or subtracting 3 in the month of the last menstrual date to obtain the number of the month of the edd; the number of days plus 7 is the predicted date of delivery. For example, the last menstruation is 2 month 1, month 2+9, date 1+7, expected date of delivery =11 month 8 (85 years) in 1985; the last menstruation is 15 months 4 and 15 days 4-3 of 1985, day 15+7, and edd = 22 days 1 and 22 days (86 years).
The final prediction result is evaluated in a segmented manner, and the division values of the three segments are 2500g and 4000g respectively. To select an index with a float range of 10%. The prediction effects of different models in different weight intervals are greatly different, and some models have better prediction effects in low weight intervals, such as XGboost and Random Forest; some models have better prediction effect in high-weight intervals, such as Ridge and SVM. In addition, the multi-layer perceptron has better prediction effect in the normal weight range. The integrated model integrates the advantages and the disadvantages of the different algorithm models, the result has no particularly outstanding disadvantages, and the prediction effect in different weight ranges can greatly exceed that of an ultrasonic formula. The accuracy of final prediction of the fetal birth weight can reach 82.25%.
While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not limitation. It will be apparent to persons skilled in the relevant art that various combinations, modifications, and changes can be made thereto without departing from the spirit and scope of the invention. Thus, the breadth and scope of the present invention should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalents.
Claims (9)
1. A fetus birth weight prediction method based on ensemble learning is characterized by comprising the following steps:
preprocessing and data balancing processing are carried out on case data;
determining a standard model;
averaging the standard models to generate an ensemble learning model;
training the ensemble learning model through the case data; and
inputting feature information into the ensemble learning model to generate a predicted fetal weight.
2. The ensemble learning-based fetal birth weight prediction method of claim 1, wherein pre-processing the case data comprises:
deleting the missing value; and/or
Confirming the deletion value of one of height, weight and BMI before pregnancy according to the BMI formula; and/or
Converting the gestational days into gestational weeks; and/or
Converting a first feature into a second feature', wherein the first feature comprises an obstetric related feature and an ultrasound related feature, and the second feature is related to a pregnancy time and is represented by the following formula:
3. the integrated learning-based fetal birth weight prediction method of claim 1 wherein the data equalization processing of case data comprises:
classifying newborns with a weight of less than 2500g as low-weight newborns, classifying newborns with a weight of 2500g or more and 4000g or less as normal-weight newborns, and classifying newborns with a weight of 4000g or more as large-weight newborns; and
the number of low-weight and large-weight newborns is increased by the up-sampling method.
4. The ensemble learning-based fetal birth weight prediction method of claim 3, wherein the up-sampling method comprises a SMOTE method.
5. The ensemble learning-based fetal birth weight prediction method according to claim 4, wherein the standard model comprises a Ridge model, an SVM model, a Random Forest model, an XGboost model and an MLP model.
6. The ensemble learning-based fetal birth weight prediction method of claim 5, wherein the standard model is averaged by Bagging to generate an ensemble learning model.
7. The ensemble learning-based fetal birth weight prediction method of claim 1, wherein the characteristic information comprises: pre-pregnancy weight, last parity weight, last ultrasound births day, pre-pregnancy BMI, weight gain during pregnancy, last parity births day, gestational diabetes mellitus, parity, parietal diameter, abdominal circumference, left and right abdominal diameters, anteroposterior abdominal diameter, and amniotic fluid index.
8. A computer system, comprising:
a processor configured to execute machine-executable instructions; and
memory having stored thereon machine executable instructions which, when executed by the processor, perform the steps of the method according to one of claims 1 to 7.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210874763.3A CN115186918A (en) | 2022-07-22 | 2022-07-22 | Fetal birth weight prediction method based on ensemble learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210874763.3A CN115186918A (en) | 2022-07-22 | 2022-07-22 | Fetal birth weight prediction method based on ensemble learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115186918A true CN115186918A (en) | 2022-10-14 |
Family
ID=83521161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210874763.3A Pending CN115186918A (en) | 2022-07-22 | 2022-07-22 | Fetal birth weight prediction method based on ensemble learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186918A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301409A (en) * | 2017-07-18 | 2017-10-27 | 云南大学 | Learn the system and method for processing electrocardiogram based on Wrapper feature selectings Bagging |
| CN109214437A (en) * | 2018-08-22 | 2019-01-15 | 湖南自兴智慧医疗科技有限公司 | A kind of IVF-ET early pregnancy embryonic development forecasting system based on machine learning |
| CN113855080A (en) * | 2021-10-25 | 2021-12-31 | 南方医科大学南方医院 | Method for predicting birth weight of full-term newborn at 21-23 weeks of pregnancy |
-
2022
- 2022-07-22 CN CN202210874763.3A patent/CN115186918A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301409A (en) * | 2017-07-18 | 2017-10-27 | 云南大学 | Learn the system and method for processing electrocardiogram based on Wrapper feature selectings Bagging |
| CN109214437A (en) * | 2018-08-22 | 2019-01-15 | 湖南自兴智慧医疗科技有限公司 | A kind of IVF-ET early pregnancy embryonic development forecasting system based on machine learning |
| CN113855080A (en) * | 2021-10-25 | 2021-12-31 | 南方医科大学南方医院 | Method for predicting birth weight of full-term newborn at 21-23 weeks of pregnancy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920501B (en) | Electronic medical record classification method and system based on convolutional neural network and active learning | |
| WO2021120936A1 (en) | Chronic disease prediction system based on multi-task learning model | |
| US10825167B2 (en) | Rapid assessment and outcome analysis for medical patients | |
| EP3404666A2 (en) | Rapid assessment and outcome analysis for medical patients | |
| US20230038364A1 (en) | Method and system for automatically detecting anatomical structures in a medical image | |
| US20240029866A1 (en) | Image-driven brain atlas construction method, device and storage medium | |
| US11531851B2 (en) | Sequential minimal optimization algorithm for learning using partially available privileged information | |
| US20230005138A1 (en) | Lumbar spine annatomical annotation based on magnetic resonance images using artificial intelligence | |
| CN116681958A (en) | Fetal lung ultrasonic image maturity prediction method based on machine learning | |
| JP2023500511A (en) | Combining Model Outputs with Combined Model Outputs | |
| CN114242259A (en) | Advanced influenza condition prediction system, program product and establishing and using method thereof | |
| Schwartz et al. | Fully Automated Placental Volume Quantification From 3D Ultrasound for Prediction of Small‐for‐Gestational‐Age Infants | |
| Kaplan et al. | PFP‐LHCINCA: Pyramidal Fixed‐Size Patch‐Based Feature Extraction and Chi‐Square Iterative Neighborhood Component Analysis for Automated Fetal Sex Classification on Ultrasound Images | |
| CN116797572A (en) | Rheumatoid arthritis activity grading device based on multi-mode data | |
| CN115035346A (en) | Classification method for Alzheimer disease based on cooperative learning method enhancement | |
| US20240105308A1 (en) | System and method for generating a gestational disorder nourishment program | |
| CN113221541A (en) | Data extraction method and device | |
| CN116563224B (en) | Image histology placenta implantation prediction method and device based on depth semantic features | |
| EP4191608A1 (en) | Two-tiered machine learning generation of birth risk score | |
| CN115186918A (en) | Fetal birth weight prediction method based on ensemble learning | |
| CN114420291B (en) | Lymph node metastasis risk assessment system and equipment for gastric cancer based on machine learning and storage medium | |
| Modi et al. | Detection and Classification of Polycystic Ovary Syndrome using Machine Learning-Based Approaches | |
| CN114565617A (en) | Pruning U-Net + + based breast tumor image segmentation method and system | |
| Ferreira et al. | Ensemble learning for fetal ultrasound and maternal–fetal data to predict mode of delivery after labor induction | |
| Abbas | Predicting the outcome of intracytoplasmic sperm injection in women using machine learning combining Doppler and clinical data: SPIRL |
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 |