CN115985515A - Amblyopia correction effect prediction method, device and equipment based on machine learning - Google Patents
Amblyopia correction effect prediction method, device and equipment based on machine learning Download PDFInfo
- Publication number
- CN115985515A CN115985515A CN202310265302.0A CN202310265302A CN115985515A CN 115985515 A CN115985515 A CN 115985515A CN 202310265302 A CN202310265302 A CN 202310265302A CN 115985515 A CN115985515 A CN 115985515A
- Authority
- CN
- China
- Prior art keywords
- amblyopia
- related data
- prediction
- correction
- effect
- 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
- 201000009487 Amblyopia Diseases 0.000 title claims abstract description 100
- 238000012937 correction Methods 0.000 title claims abstract description 65
- 230000000694 effects Effects 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000010801 machine learning Methods 0.000 title claims abstract description 32
- 230000004927 fusion Effects 0.000 claims abstract description 27
- 238000003066 decision tree Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000007637 random forest analysis Methods 0.000 claims abstract description 21
- 230000004438 eyesight Effects 0.000 claims abstract description 17
- 238000012106 screening analysis Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 12
- 230000003111 delayed effect Effects 0.000 abstract 1
- 238000003745 diagnosis Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 210000003205 muscle Anatomy 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 201000009310 astigmatism Diseases 0.000 description 2
- 230000001886 ciliary effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 208000001491 myopia Diseases 0.000 description 2
- 230000004379 myopia Effects 0.000 description 2
- 230000002040 relaxant effect Effects 0.000 description 2
- 230000004382 visual function Effects 0.000 description 2
- 206010038266 Refractive amblyopia Diseases 0.000 description 1
- 201000009406 ametropic amblyopia Diseases 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000004410 intraocular pressure Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a machine learning-based amblyopia correction effect prediction method, device and equipment, and the method comprises the following steps: acquiring amblyopia correction related data, wherein the amblyopia correction related data comprises basic information of patients, naked eye vision, spherical lens degrees and correction measures; performing feature screening analysis on the amblyopia correction related data based on a decision tree by adopting a random forest algorithm to obtain a feature set; and respectively inputting the feature set into a plurality of different basic prediction models to perform effect prediction, and performing fusion operation to obtain a prediction result. The method and the device can solve the technical problems that the treatment effect of the current amblyopia correction scheme is difficult to predict, and the treatment opportunity is delayed due to misdiagnosis, which cannot be controlled and avoided in the prior art.
Description
Technical Field
The application relates to the technical field of medical data processing, in particular to a method, a device and equipment for predicting amblyopia correcting effect based on machine learning.
Background
Amblyopia seriously affects the study and life of teenagers and children, and if the amblyopia cannot be treated in time, the lifelong eyesight of a patient can be damaged, and heavy burden is brought to families and society. However, the amblyopia eye has the characteristics of long course of disease, great difficulty in correction, smaller age of patients, better correction effect and the like. Therefore, the amblyopia treatment of the teenagers and children is a time-consuming process. However, in a clinical scenario, a doctor can develop a better correction scheme and a relatively rough estimation on the correction effect only after having abundant clinical experience and studying more clinical research reports.
The overall correction scheme for the amblyopia patient comprises specific correction measure formulation, correction effect prediction, review arrangement and the like, highly depends on abundant clinical experience of doctors, and needs to consume much time and energy of the doctors. In addition, the distribution of medical resources in China is not balanced, and the diagnosis and treatment of patients with amblyopia each time are challenges of big data for primary ophthalmologists including public health institutions in villages and towns and primary and secondary hospitals in counties and underdeveloped regions. Compared with memory analysis of the human brain, machine learning can help analysis and prediction, so that doctors are assisted to make more reasonable decisions. It is needless to say that the prediction of the amblyopia correcting effect is important for both the initial diagnosis patient and the follow-up diagnosis patient. Because: the prediction of the amblyopia correcting effect can help to formulate a more accurate correcting scheme; the method is helpful for avoiding the missing of treatment opportunity of the patient due to diagnosis error and improper treatment.
Disclosure of Invention
The application provides a machine learning-based amblyopia correction effect prediction method, device and equipment, which are used for solving the technical problems that the treatment effect of the current amblyopia correction scheme is difficult to predict in the prior art, and the treatment opportunity delay due to misdiagnosis cannot be controlled and avoided.
In view of the above, a first aspect of the present application provides a method for predicting an effect of correcting amblyopia based on machine learning, including:
acquiring amblyopia correcting related data, wherein the amblyopia correcting related data comprise basic information of patients, naked eye vision, spherical lens degrees and correcting measures;
performing feature screening analysis on the amblyopia correcting related data by adopting a random forest algorithm based on a decision tree to obtain a feature set;
and respectively inputting the feature set into a plurality of different basic prediction models to perform effect prediction, and performing fusion operation to obtain a prediction result.
Preferably, the acquiring of the data related to amblyopia correction further includes:
and performing first preprocessing operation on the amblyopia correcting related data, wherein the first preprocessing operation comprises missing value processing.
Preferably, the acquiring of the data related to amblyopia correction further includes:
and performing second preprocessing operation on the amblyopia correcting related data, wherein the second preprocessing operation comprises discretization processing and One-hot coding processing.
Preferably, the feature screening and analyzing the amblyopia correcting related data by using a random forest algorithm based on a decision tree to obtain a feature set, including:
calculating the importance of the sample characteristics corresponding to the amblyopia correcting related data in each decision tree by adopting a random forest algorithm;
and sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
Preferably, the step of inputting the feature set into a plurality of different basic prediction models respectively to perform effect prediction, and then performing fusion operation to obtain a prediction result includes:
respectively inputting the feature set into a plurality of different basic prediction models to carry out effect prediction to obtain basic prediction results;
and calculating a fusion result based on a preset linear fusion formula and the basic prediction result to obtain a prediction result, wherein the preset linear fusion formula comprises fusion weight.
The second aspect of the present application provides a device for predicting an amblyopia correction effect based on machine learning, including:
the data acquisition unit is used for acquiring amblyopia correction related data, wherein the amblyopia correction related data comprises basic information of patients, naked eye vision, spherical lens degrees and correction measures;
the feature screening unit is used for carrying out feature screening analysis on the amblyopia correcting related data based on a decision tree by adopting a random forest algorithm to obtain a feature set;
and the effect prediction unit is used for inputting the feature set into a plurality of different basic prediction models respectively to perform effect prediction and then performing fusion operation to obtain a prediction result.
Preferably, the method further comprises the following steps:
the first preprocessing unit is used for performing first preprocessing operation on the amblyopia correcting related data, and the first preprocessing operation comprises missing value processing.
Preferably, the method further comprises the following steps:
and the second preprocessing unit is used for performing second preprocessing operation on the amblyopia correcting related data, and the second preprocessing operation comprises discretization processing and One-hot coding processing.
Preferably, the feature screening unit is specifically configured to:
calculating the importance of the sample characteristics corresponding to the amblyopia correcting related data in each decision tree by adopting a random forest algorithm;
and sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
The third aspect of the application provides an amblyopia correcting effect predicting device based on machine learning, which comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the method for predicting the effect of amblyopia correction based on machine learning according to the first aspect according to instructions in the program code.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a machine learning-based amblyopia correction effect prediction method, which comprises the following steps: acquiring related data for amblyopia correction, wherein the related data for amblyopia correction comprises basic information of patients, naked eye vision, spherical lens degree and correction measures; performing feature screening analysis on the amblyopia correction related data based on a decision tree by adopting a random forest algorithm to obtain a feature set; and respectively inputting the feature set into a plurality of different basic prediction models to perform effect prediction, and performing fusion operation to obtain a prediction result.
The amblyopia correcting effect prediction method based on machine learning provided by the application obtains amblyopia correcting related data based on machine learning, wherein the data comprise basic information of patients and objective detection information such as naked eye vision, spherical power and the like; then, a random forest algorithm is adopted to carry out feature screening analysis based on amblyopia correction related data, and the accuracy of feature extraction is ensured; in the effect prediction stage, fusion prediction is carried out by adopting various different prediction models, so that a more reliable prediction result is obtained. Therefore, the method and the device can solve the technical problems that in the prior art, the treatment effect of the current amblyopia correction scheme is difficult to predict, and the treatment time delay due to misdiagnosis cannot be controlled and avoided.
Drawings
Fig. 1 is a schematic flowchart of a method for predicting an amblyopia correction effect based on machine learning according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a device for predicting an amblyopia correction effect based on machine learning according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, referring to fig. 1, an embodiment of a method for predicting an amblyopia correction effect based on machine learning provided by the present application includes:
The data screen in the embodiment is selected from a CREST project of cooperation of Zhongshan ophthalmological center of Zhongshan university and people hospital of Luoding city, and the specific screen is the data of the refractive amblyopia teenager and child patients which follow up for a long time on the project during 2014 to 2022. The attributes of the screened data related to amblyopia correction include basic information of patients, such as sex, age, time of visit, etc., some objective detection information, such as naked eye vision, sphere power, cylinder axis, intraocular pressure, etc., and datum data similar to best corrected vision, correction measures, etc. The correcting measures comprise operations of fitting glasses, shielding eyes, training fine eyesight, training visual functions, relaxing ciliary muscles, enhancing eye muscle strength and eye adjusting force and the like. The corrective measures can be described and expressed in a datamation mode, so that subsequent data analysis and effect prediction are facilitated, and a specific data conversion method is not limited herein.
Further, step 101, thereafter, further includes:
and performing a first preprocessing operation on the amblyopia correction related data, wherein the first preprocessing operation comprises missing value processing.
The first preprocessing operation aims to improve the quality of the amblyopia correction related data, for example, missing value processing can be carried out, and filling and deleting operations can be carried out on missing values of time sequence data in the amblyopia correction related data; if the quantity is small, filling the mean value; if the missing degree is larger, deleting the row of data. Other preprocessing processes can be added to improve the data quality, and the specific details are not limited herein.
Further, step 101, thereafter, further includes:
and performing second preprocessing operation on the amblyopia correcting related data, wherein the second preprocessing operation comprises discretization processing and One-hot coding processing.
The second preprocessing operation aims to unify dimensions, and since the amblyopia correction related data contains data and information with various dimensions, the second preprocessing operation can unify the data and information into a data form which is convenient to process by an algorithm.
For example, the discretization process classifies the case of sphere > +5.00D as high-distance vision, the case of 0< sphere < = +5.00D as medium-low-distance vision, the case of-6.00D < = sphere <0 as medium-low-distance myopia, and the case of sphere < -6.00D as high-distance myopia. There is also lenticular classification: medium-low astigmatism is in the case of 0< = cylinder < =2.50D and high astigmatism is in the case of cylinder > 2.50D. In addition, compliance analysis is also needed, because the treatment effect of the patient is closely related to compliance, but the patient often lacks quantitative indexes, for this reason, the embodiment uses the patient re-diagnosis time interval as a basis for compliance judgment, for example, the re-diagnosis time interval < =3 months is classified as high compliance, the re-diagnosis time interval between 3 to 6 months is classified as compliance, and the re-diagnosis time interval greater than 6 months is classified as low compliance.
The One-hot coding processing is a quantitative expression process aiming at the corrective measures, the corrective measures are subjected to thermal coding processing, namely six types of treatment measures including fitting glasses, shielding eyes, fine eyesight training, visual function training, relaxing ciliary muscles, enhancing eye muscle strength and eye adjustment are independently listed, whether the measures are carried out or not is marked by 0 and 1, for example, the eye adjustment operation is executed, the marks are 1, and otherwise, the marks are 0.
And 102, performing feature screening analysis on the amblyopia correcting related data by adopting a random forest algorithm based on a decision tree to obtain a feature set.
Further, step 102 includes:
calculating the importance of sample characteristics corresponding to the amblyopia correction related data in each decision tree by adopting a random forest algorithm;
and (4) sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
The amblyopia correction related data after the preprocessing operation can be uniformly processed by adopting a specific algorithm, and the random forest algorithm is adopted to screen and analyze the related characteristics of the amblyopia correction related data in the embodiment, so that the accuracy of characteristic expression is ensured, and the reliability of a prediction result is further improved.
Calculating out-of-bag data error of each decision tree in random foresterrOOB1, randomly comparing the characteristics of all samples of the data outside the bagfAdding noise, and calculating error of data outside bagerrOOB2; sample characterization assuming N trees in a random forestXThe significance of (d) is expressed as:
wherein,iis as followsiA decision tree is determined, and the decision tree is determined,Nfor the total number of decision trees, each time a decision tree is constructed, the decision tree may be trained by repeatedly extracting the data set, at which time approximately 1/3 of the remaining data is not used, and this portion of data is the data outside the bag and is noted as the data outside the bagOOB。
And (3) performing descending order on the importance of each feature calculation, sequentially expressing that the features are weakened, and when the sample features are screened according to a preset percentage, directly deleting the later weak features according to a preset proportion to obtain the undeleted features so as to form a feature set. In addition, error change analysis can be performed according to the mean square error corresponding to the sample characteristics, and a characteristic set with the minimum mean square error is selected. The preset percentage, the preset proportion and the like can be set according to actual conditions, and are not limited herein.
And 103, respectively inputting the feature sets into multiple different basic prediction models to perform effect prediction, and performing fusion operation to obtain a prediction result.
Further, step 103 includes:
respectively inputting the feature set into a plurality of different basic prediction models to carry out effect prediction to obtain basic prediction results;
and calculating a fusion result based on a preset linear fusion formula and the basic prediction result to obtain a prediction result, wherein the preset linear fusion formula comprises fusion weight.
The basic prediction model selected in the embodiment includes four types of SVM, xgboost (XGB _ Reg), lightGBM, and GBDT, model parameters of the four basic prediction models are pre-trained, and respective optimal prediction states are achieved, so that effect prediction can be performed based on the model parameters, and a basic prediction result is obtained. Then, linear fusion is performed by using a Linear mixing Linear Blending method, and the specific fusion process can be expressed as follows:
wherein,
is as followsiIndividual basic prediction model, or basic prediction result, is/are>
And fusion weight corresponding to the basic prediction model.
It can be understood that the basic prediction model can be selected according to actual situations, and the number can be set by itself, which is only an example and is not limited specifically; the fusion weights may also be configured in time. In addition, the predicted effect of the embodiment is only used for assisting the amblyopia correcting process, is not used as a core treatment means or a main reference standard, and cannot be used as a treatment basis independently.
The amblyopia correcting effect prediction method based on machine learning provided by the embodiment of the application obtains amblyopia correcting relevant data on the basis of machine learning, wherein the data comprise basic information of patients and objective detection information such as naked eye vision, spherical power and the like; then, a random forest algorithm is adopted to carry out feature screening analysis based on amblyopia correction related data, so that the accuracy of feature extraction is ensured; in the effect prediction stage, fusion prediction is carried out by adopting various different prediction models, so that a more reliable prediction result is obtained. Therefore, the embodiment of the application can solve the technical problems that the treatment effect of the current amblyopia correction scheme is difficult to predict, and the treatment time delay due to misdiagnosis cannot be controlled and avoided in the prior art.
For easy understanding, please refer to fig. 2, the present application provides an embodiment of a device for predicting an amblyopia correction effect based on machine learning, comprising:
the data acquisition unit 201 is used for acquiring amblyopia correction related data, wherein the amblyopia correction related data comprise basic information of a patient, naked eye vision, a sphere lens degree and correction measures;
the feature screening unit 202 is configured to perform feature screening analysis on the data related to amblyopia correction based on a decision tree by using a random forest algorithm to obtain a feature set;
and the effect prediction unit 203 is used for inputting the feature set into a plurality of different basic prediction models respectively to perform effect prediction, and then performing fusion operation to obtain a prediction result.
Further, still include:
the first preprocessing unit 204 is configured to perform a first preprocessing operation on the amblyopia-related data, where the first preprocessing operation includes missing value processing.
Further, still include:
the second preprocessing unit 205 is configured to perform a second preprocessing operation on the data related to amblyopia correction, where the second preprocessing operation includes discretization and One-hot encoding.
Further, the feature filtering unit 202 is specifically configured to:
calculating the importance of sample characteristics corresponding to the amblyopia correction related data in each decision tree by adopting a random forest algorithm;
and (4) sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
The application also provides amblyopia correcting effect prediction equipment based on machine learning, and the equipment comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the amblyopia correcting effect prediction method based on machine learning in the method embodiment according to the instructions in the program codes.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (10)
1. A machine learning-based amblyopia correction effect prediction method is characterized by comprising the following steps:
acquiring related data for amblyopia correction, wherein the related data for amblyopia correction comprises basic information of patients, naked eye vision, spherical lens degree and correction measures;
performing feature screening analysis on the amblyopia correction related data by adopting a random forest algorithm based on a decision tree to obtain a feature set;
and respectively inputting the feature sets into a plurality of different basic prediction models to carry out effect prediction, and then carrying out fusion operation to obtain a prediction result.
2. The method for predicting the effect of correcting amblyopia based on machine learning of claim 1, wherein the obtaining of data related to amblyopia correction further comprises:
and performing first preprocessing operation on the amblyopia correcting related data, wherein the first preprocessing operation comprises missing value processing.
3. The method for predicting the amblyopia correcting effect based on machine learning of claim 1, wherein the obtaining of data related to amblyopia correction further comprises:
and performing second preprocessing operation on the amblyopia correcting related data, wherein the second preprocessing operation comprises discretization processing and One-hot coding processing.
4. The amblyopia correcting effect prediction method based on machine learning of claim 1, wherein the feature screening analysis is performed on the amblyopia correcting related data by using a random forest algorithm based on a decision tree to obtain a feature set, comprising:
calculating the importance of the sample characteristics corresponding to the amblyopia correcting related data in each decision tree by adopting a random forest algorithm;
and sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
5. The method for predicting the effect of correcting amblyopia based on machine learning of claim 1, wherein the step of inputting the feature set into a plurality of different basic prediction models respectively for effect prediction and then performing fusion operation to obtain a prediction result comprises the steps of:
respectively inputting the feature set into a plurality of different basic prediction models to carry out effect prediction to obtain basic prediction results;
and calculating a fusion result based on a preset linear fusion formula and the basic prediction result to obtain a prediction result, wherein the preset linear fusion formula comprises fusion weight.
6. The utility model provides an effect prediction device is rescued to amblyopia based on machine learning which characterized in that includes:
the data acquisition unit is used for acquiring amblyopia correction related data, wherein the amblyopia correction related data comprises basic information of patients, naked eye vision, spherical lens degrees and correction measures;
the feature screening unit is used for carrying out feature screening analysis on the amblyopia correcting related data based on a decision tree by adopting a random forest algorithm to obtain a feature set;
and the effect prediction unit is used for inputting the feature set into a plurality of different basic prediction models respectively to perform effect prediction and then performing fusion operation to obtain a prediction result.
7. The device for predicting the effect of amblyopia correction based on machine learning according to claim 6, further comprising:
the first preprocessing unit is used for performing first preprocessing operation on the amblyopia correcting related data, and the first preprocessing operation comprises missing value processing.
8. The device for predicting the effect of amblyopia correction based on machine learning according to claim 6, further comprising:
and the second preprocessing unit is used for performing second preprocessing operation on the amblyopia correcting related data, and the second preprocessing operation comprises discretization processing and One-hot coding processing.
9. The device for predicting the effect of correcting amblyopia based on machine learning according to claim 6, wherein the feature screening unit is specifically configured to:
calculating the importance of the sample characteristics corresponding to the amblyopia correcting related data in each decision tree by adopting a random forest algorithm;
and sorting the importance of all the sample characteristics in a descending order, and screening the sample characteristics according to a preset percentage to obtain a characteristic set.
10. An amblyopia correcting effect prediction device based on machine learning is characterized by comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the method for predicting the effect of amblyopia correction based on machine learning according to any one of claims 1 to 5 according to instructions in the program code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310265302.0A CN115985515A (en) | 2023-03-20 | 2023-03-20 | Amblyopia correction effect prediction method, device and equipment based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310265302.0A CN115985515A (en) | 2023-03-20 | 2023-03-20 | Amblyopia correction effect prediction method, device and equipment based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115985515A true CN115985515A (en) | 2023-04-18 |
Family
ID=85958208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310265302.0A Pending CN115985515A (en) | 2023-03-20 | 2023-03-20 | Amblyopia correction effect prediction method, device and equipment based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115985515A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116798630A (en) * | 2023-07-05 | 2023-09-22 | 广州视景医疗软件有限公司 | Myopia physiotherapy compliance prediction method, device and medium based on machine learning |
| CN117095790A (en) * | 2023-08-08 | 2023-11-21 | 广州视景医疗软件有限公司 | Method, system and device for constructing amblyopia training effect prediction model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020143226A1 (en) * | 2019-01-07 | 2020-07-16 | 浙江大学 | Industrial control system intrusion detection method based on integrated learning |
| CN112614590A (en) * | 2020-12-10 | 2021-04-06 | 浙江大学 | Machine learning-based elderly disability risk prediction method and system |
| US20210196428A1 (en) * | 2019-12-30 | 2021-07-01 | University Of Connecticut | Artificial Intelligence (AI) based Decision-Making Model for Orthodontic Diagnosis and Treatment Planning |
| CN113160978A (en) * | 2020-12-11 | 2021-07-23 | 刘泉 | Full femtosecond postoperative vision prediction method, system and medium based on machine learning |
| CN113178261A (en) * | 2021-06-04 | 2021-07-27 | 福州大学 | Diabetes prediction model construction method and system based on machine learning |
| CN113191926A (en) * | 2021-04-12 | 2021-07-30 | 北京工商大学 | Grain and oil crop supply chain hazard identification method and system based on deep ensemble learning network |
| CN114420301A (en) * | 2022-01-28 | 2022-04-29 | 广东工业大学 | Method, system and storage medium for predicting blood glucose based on segmented domain RF modeling |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
-
2023
- 2023-03-20 CN CN202310265302.0A patent/CN115985515A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020143226A1 (en) * | 2019-01-07 | 2020-07-16 | 浙江大学 | Industrial control system intrusion detection method based on integrated learning |
| US20210196428A1 (en) * | 2019-12-30 | 2021-07-01 | University Of Connecticut | Artificial Intelligence (AI) based Decision-Making Model for Orthodontic Diagnosis and Treatment Planning |
| CN112614590A (en) * | 2020-12-10 | 2021-04-06 | 浙江大学 | Machine learning-based elderly disability risk prediction method and system |
| CN113160978A (en) * | 2020-12-11 | 2021-07-23 | 刘泉 | Full femtosecond postoperative vision prediction method, system and medium based on machine learning |
| CN113191926A (en) * | 2021-04-12 | 2021-07-30 | 北京工商大学 | Grain and oil crop supply chain hazard identification method and system based on deep ensemble learning network |
| CN113178261A (en) * | 2021-06-04 | 2021-07-27 | 福州大学 | Diabetes prediction model construction method and system based on machine learning |
| CN114420301A (en) * | 2022-01-28 | 2022-04-29 | 广东工业大学 | Method, system and storage medium for predicting blood glucose based on segmented domain RF modeling |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116798630A (en) * | 2023-07-05 | 2023-09-22 | 广州视景医疗软件有限公司 | Myopia physiotherapy compliance prediction method, device and medium based on machine learning |
| CN116798630B (en) * | 2023-07-05 | 2024-03-08 | 广州视景医疗软件有限公司 | Myopia physiotherapy compliance prediction method, device and medium based on machine learning |
| CN117095790A (en) * | 2023-08-08 | 2023-11-21 | 广州视景医疗软件有限公司 | Method, system and device for constructing amblyopia training effect prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kwasigroch et al. | Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy | |
| Lavric et al. | KeratoDetect: keratoconus detection algorithm using convolutional neural networks | |
| CN115985515A (en) | Amblyopia correction effect prediction method, device and equipment based on machine learning | |
| CN112133441B (en) | Method and terminal for establishing MH postoperative crack state prediction model | |
| JP6672529B2 (en) | Apparatus and computer program for determining predicted subjective refraction data or predicted correction value | |
| Pieczynski et al. | The role of telemedicine, in-home testing and artificial intelligence to alleviate an increasingly burdened healthcare system: Diabetic retinopathy | |
| CN112700858B (en) | Early warning method and device for myopia of children and teenagers | |
| US20210391056A1 (en) | Health big data service method and system based on remote fundus screening | |
| CN112101424B (en) | Method, device and equipment for generating retinopathy identification model | |
| CN113284623B (en) | Personalized cognitive training task recommendation algorithm and system based on user ability | |
| CN110046757B (en) | Outpatient clinic volume prediction system and prediction method based on LightGBM algorithm | |
| Miao | Using machine learning algorithms to predict diabetes mellitus based on Pima Indians Diabetes dataset | |
| Datta et al. | Hyper parameter tuning based gradient boosting algorithm for detection of diabetic retinopathy: an analytical review | |
| CN112185564B (en) | Ophthalmic disease prediction method based on structured electronic medical record and storage device | |
| CN117338234A (en) | Diopter and vision joint detection method | |
| CN111369499B (en) | Fundus image processing method and device | |
| CN114202772B (en) | Reference information generation system and method based on artificial intelligence and intelligent medical treatment | |
| WO2023195919A2 (en) | Method for predicting risk of developing myopia | |
| CN115714016A (en) | Brucellosis screening rate improving method based on machine learning | |
| CN114420289A (en) | Eye health index evaluation system | |
| Hartmann et al. | Keratoconus Progression Determined at the First Visit: A Deep Learning Approach With Fusion of Imaging and Numerical Clinical Data | |
| Fu et al. | Exploiting active learning in novel refractive error detection with smartphones | |
| CN115223232A (en) | Eye health comprehensive management system | |
| CN113273959A (en) | Portable diabetic retinopathy diagnosis and treatment instrument | |
| Zhong et al. | CeCNN: Copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus images |
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 | ||
| 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: 20230418 |