CN112768056A - Disease prediction model establishing method and device based on joint learning framework - Google Patents
Disease prediction model establishing method and device based on joint learning framework Download PDFInfo
- Publication number
- CN112768056A CN112768056A CN202110046461.2A CN202110046461A CN112768056A CN 112768056 A CN112768056 A CN 112768056A CN 202110046461 A CN202110046461 A CN 202110046461A CN 112768056 A CN112768056 A CN 112768056A
- Authority
- CN
- China
- Prior art keywords
- model
- joint learning
- joint
- participants
- training
- 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 43
- 201000010099 disease Diseases 0.000 title claims abstract description 34
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 68
- 230000036541 health Effects 0.000 claims abstract description 24
- 230000002068 genetic effect Effects 0.000 claims abstract description 19
- 230000003044 adaptive effect Effects 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 12
- 210000000349 chromosome Anatomy 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000005192 partition Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 10
- 238000012545 processing 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
- 230000007246 mechanism Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 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
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Physiology (AREA)
- Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is suitable for the technical field of artificial intelligence, and provides a disease prediction model establishing method and device based on a joint learning framework. The method comprises the following steps: determining a data set with health characteristic data of different dimensions of a patient as joint learning participants, and establishing a joint learning framework for a plurality of the participants; performing model training based on the joint learning architecture, wherein the model training comprises determining an initialization weight of the model and an optimal path of a threshold value by using an adaptive genetic algorithm; and establishing a target model for disease prediction according to the model training result. According to the invention, health characteristic data of different dimensions of a patient are combined through combined learning, and a global disease prediction model is obtained by combining the prediction model of each partition, so that the quality of the prediction model is improved, and the efficiency of model training is also improved.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a disease prediction model establishing method and device based on a joint learning framework.
Background
The development of artificial intelligence medical treatment is more and more paid attention to by people, but the special problems exist in the health field. In consideration of privacy and non-union of health data, in practice, medical data of the same patient exists in an unused place such as a physical examination institution, a specialized hospital, a community hospital, and the like, and the detection point of the emphasis of each hospital is different. Therefore, each hospital or other medical structure trains own patient data by using a machine learning algorithm, and the quality of the obtained intelligent medical model is not high, and the training efficiency is not high.
Disclosure of Invention
In view of this, embodiments of the present invention provide a disease prediction model establishing method and apparatus based on a joint learning framework, so as to solve the problem that existing hospitals or medical structures cannot train and establish a target model meeting application requirements by using data owned by themselves.
In a first aspect of the present invention, a disease prediction model building method based on a joint learning framework is provided, which includes: determining a data set with health characteristic data of different dimensions of a patient as joint learning participants, and establishing a joint learning framework for a plurality of the participants; performing model training based on the joint learning architecture, wherein the model training comprises determining an initialization weight of the model and an optimal path of a threshold value by using an adaptive genetic algorithm; and establishing a target model for disease prediction according to the model training result.
In some optional embodiments, the establishing a joint learning architecture for a plurality of the participants comprises: and establishing a horizontal joint learning framework for the plurality of participants, wherein the overlapping degree of the same health data features in the data sets of the participants meets a preset value.
In some optional embodiments, the model training based on the joint learning architecture comprises: and performing joint training on the extreme learning machine based on the joint learning framework.
In some optional embodiments, the model training based on the joint learning architecture comprises: the participants each download the latest model from a server of the joint learning architecture; each participant trains a model by using health characteristic data of different dimensionalities of patients in a data set, encrypts and uploads the trained model parameters to a server, and the server is used for gathering the model parameters of each participant to update the model; the server returns the updated model to each of the participants; the participants update their respective models.
In some optional embodiments, the training of the model by each of the participants using health feature data of different dimensions of the patient in the data set comprises: randomly initializing hidden layer neuron functions; calculating an output matrix of the hidden layer node; calculating an output weight from the hidden layer to the output layer; and calculating a predicted value and an error value according to the matrix and the weight value.
In some alternative embodiments, the model training includes determining optimal paths for initialization weights and thresholds of the model using an adaptive genetic algorithm, including: the joint training of the limit learning machine comprises: after determining the optimal path of the initialization weight and the threshold of the extreme learning machine by using a self-adaptive genetic algorithm, each participant performs joint training by using a data set owned by the participant.
In some optional embodiments, after determining the optimal path of the initialization weight and the threshold of the extreme learning machine by using an adaptive genetic algorithm, each participant performs joint training by using its own data set, including: generating parameters such as initial kernel function parameters and penalty factors, setting the size of a population and the number of iterations, wherein each individual in the population is in a parameter coding form, and randomly generating an initial value of the individual; assigning the obtained parameters to an extreme learning machine for prediction, and calculating the fitness value of each chromosome according to the prediction result; after obtaining the individual fitness value, calculating the selection probability of population individuals according to the obtained fitness value, and selecting the individuals according to the individual selection probability; calculating individual chromosome crossing probability; calculating individual chromosome variation probability; and judging whether a termination condition is reached, if the termination condition is less than the maximum iteration number or the error does not reach a certain threshold value, circularly returning and utilizing the obtained parameters to assign values to the extreme learning machine for prediction, and calculating the fitness value of each chromosome according to the prediction result, otherwise, utilizing the data set to train the extreme learning machine prediction model.
In a second aspect of the present invention, there is provided a disease prediction model building apparatus based on a joint learning framework, including: the joint learning establishing module is used for determining a data set with health characteristic data of different dimensionalities of a patient to be joint learning participants and establishing a joint learning framework for the participants; the joint learning training module is used for carrying out model training based on the joint learning framework, and the model training comprises the step of determining the optimal path of the initialization weight and the threshold of the model by using a self-adaptive genetic algorithm; and the prediction model establishing module is used for establishing a target model for disease prediction according to the result of the model training.
In a third aspect of the present invention, there is provided a terminal device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of the aspects of the first aspect when executing the computer program.
In a fourth aspect of the present invention, there is provided a storage medium storing a computer program which, when executed by a processor, performs the steps of the method according to any one of the first aspect.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: according to the method, more health characteristic data of different dimensions of the patient are combined through a combined learning framework, so that the number of samples for model training is increased; meanwhile, the optimal path of the model is optimized by using the self-adaptive genetic algorithm in the model training process, so that the error between the output value of the prediction output and the expected value is minimized, and the problem that the model training falls into the local optimal solution is avoided. Compared with a model trained by a single mechanism by utilizing self data, the model obtained by training is remarkably improved in model training efficiency and model quality.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for building a disease prediction model based on a joint learning framework according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a disease prediction model building apparatus based on a joint learning framework according to a second embodiment of the present invention;
fig. 3 is a terminal device to which the method and apparatus for building a disease prediction model based on a joint learning framework according to the present invention can be applied.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Example one
Referring to fig. 1, which is a flowchart of a disease prediction model building method based on a joint learning framework according to a first embodiment of the present invention, with reference to fig. 1, the disease prediction model building method based on the joint learning framework includes the following steps:
s01, determining a data set with health characteristic data of different dimensionalities of a patient as a joint learning participant, and establishing a joint learning framework for a plurality of participants;
s02, performing model training based on the joint learning architecture, wherein the model training comprises determining the optimal path of the initialization weight and the threshold of the model by using an adaptive genetic algorithm;
and S03, establishing a target model for disease prediction according to the model training result.
According to the method, more health characteristic data of different dimensions of the patient are combined through a combined learning framework, so that the number of samples for model training is increased; meanwhile, the optimal path of the model is optimized by using the self-adaptive genetic algorithm in the model training process, so that the error between the output value of the prediction output and the expected value is minimized, and the problem that the model training falls into the local optimal solution is avoided. Compared with a model trained by a single mechanism by utilizing self data, the model obtained by training is remarkably improved in model training efficiency and model quality.
In step S01, due to different hospitals or medical institutions, the patients having different dimensional characteristics tend to have higher user overlapping degree in the same region. Thus, in one example, establishing a joint learning framework for a plurality of the participants in step S01 may include: and establishing a horizontal joint learning framework for the plurality of participants, wherein the overlapping degree of the same health data features in the data sets of the participants meets a preset value. Specifically, the preset value includes the number of overlapping users in the health feature data of different dimensions of patients of different participants.
In step S02, under the joint learning architecture, the model trained by using the health feature data of different dimensions of the patient may include any machine learning model such as an extreme learning machine. For example, in an example two, the model training based on the joint learning architecture includes: and performing joint training on the extreme learning machine based on the joint learning framework.
Further, in an example three, when the extreme learning machine algorithm is used for training, the training of the model in step S02 includes determining an optimal path of the initialization weight and the threshold of the model by using an adaptive genetic algorithm, and then specifically includes: the joint training of the limit learning machine comprises: after determining the optimal path of the initialization weight and the threshold of the extreme learning machine by using a self-adaptive genetic algorithm, each participant performs joint training by using a data set owned by the participant.
Specifically, in the example immediately above, the specific process of performing model training based on the joint learning architecture includes the steps of:
s201, the participants download the latest model from a server of the joint learning architecture respectively;
s202, each participant trains a model by using health characteristic data of different dimensionalities of a patient in a data set, encrypts and uploads the trained model parameters to a server, and the server is used for gathering model parameter updating models of all participants;
s203, the server returns the updated model to each participant;
s204, the participants update the respective models.
The server is a union in a joint learning framework, and in practical application, a desired target model is obtained through iterative training of a participant and the union. I.e. the steps S202-S204 are looped until the model satisfies the convergence condition.
In step S202, each of the participants trains a model by using health feature data of different dimensions of the patient in the data set, which specifically includes: and (3) locally processing health characteristic data of different dimensions of the patient into sample data by each participant, then training the extreme learning machine by using the sample data, and finally obtaining a target model according to a training structure.
Illustratively, the process of training the extreme learning machine includes: randomly initializing hidden layer neuron functions, namely the weight and the threshold of each neuron; calculating an output matrix of the hidden layer node; calculating an output weight from the hidden layer to the output layer; and calculating a predicted value and an error value according to the matrix and the weight value.
More specifically, the extreme learning machine is random when acquiring the initialization weight and the threshold, so that the network output result and accuracy cannot be guaranteed, and the extreme learning machine is easy to fall into a local optimal solution. The optimal path can be found by employing an adaptive genetic algorithm, just as in example three above. The error between the output value of the prediction output and the expected value is minimized.
For example, after determining the optimal path of the initialization weight and the threshold of the extreme learning machine by using the adaptive genetic algorithm, each participant performs joint training by using a data set owned by the participant, which may specifically include the steps of:
s301, generating parameters such as initial kernel function parameters and penalty factors, setting the size of a population and the number of iterations, wherein each individual in the population is in a parameter coding form, and randomly generating an initial value of the individual;
s302, assigning the obtained parameters to an extreme learning machine for prediction, and calculating the fitness value of each chromosome according to the prediction result;
s303, after obtaining the individual fitness value, calculating the selection probability of the population individuals according to the obtained fitness value, and selecting the individuals according to the individual selection probability;
s304, calculating the individual chromosome crossing probability;
s305, calculating individual chromosome variation probability;
and S306, judging whether a termination condition is reached, if the termination condition is less than the maximum iteration number or the error does not reach a certain threshold value, circularly skipping to S302, otherwise, training the extreme learning machine prediction model by using the data set.
The problem that the model training falls into the local optimal solution can be avoided through the above steps S301-S306. Therefore, compared with a model trained by a single mechanism by utilizing self data, the model obtained by training has the advantage that the model training efficiency is remarkably improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two
Under the same inventive concept, as shown in fig. 2, which is a schematic structural diagram of a disease prediction model building apparatus based on a joint learning framework according to a second embodiment of the present invention, as shown in fig. 2, the disease prediction model building apparatus 200 based on a joint learning framework includes: a joint learning establishing module 210, configured to determine a data set having health feature data of different dimensions of a patient as joint learning participants, and establish a joint learning framework for a plurality of the participants; a joint learning training module 220, configured to perform model training based on the joint learning architecture, where the model training includes determining an optimal path of an initialization weight and a threshold of the model by using an adaptive genetic algorithm; and a prediction model establishing module 230, configured to establish a target model for disease prediction according to a result of the model training.
Since the second embodiment and the first embodiment belong to the same inventive concept and have the same specific technical features, reference may be made to the first embodiment for specific technical content of the disease prediction model building apparatus based on the joint learning framework, and details are not repeated here.
EXAMPLE III
Fig. 3 shows a terminal device to which the method and apparatus for building a disease prediction model based on a joint learning framework according to the present invention can be applied.
As shown in fig. 3, the terminal device 300 includes: a processor 301, a memory 302 and a computer program 303 stored in said memory 302 and executable on said processor 301, such as a program for implementing a disease prediction model joint learning method. The processor 301, when executing the computer program 303, implements the steps in the above-described embodiments of the disease prediction model joint learning method, such as the steps S01 to S02 shown in fig. 1. Alternatively, the processor 301, when executing the computer program 303, implements the functions of the modules/units in the above-mentioned apparatus embodiments, such as the functions of the joint learning module 210 and the model parameter optimization model 220 shown in fig. 2.
Illustratively, the computer program 303 may be partitioned into one or more modules/units that are stored in the memory 302 and executed by the processor 301 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 303 in the terminal device 300. For example, the computer program 303 may be partitioned into a joint learning building module 210, a joint learning training module 220, and a predictive model building module 230.
The terminal device 300 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 301, a memory 302. Those skilled in the art will appreciate that fig. 3 is merely an example of a terminal device 300 and does not constitute a limitation of terminal device 300 and may include more or fewer components than shown, or some components may be combined, or different components, for example, the terminal device may also include input output devices, network access devices, buses, etc.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 302 may be an internal storage unit of the terminal device 300, such as a hard disk or a memory of the terminal device 300. The memory 302 may also be an external storage device of the terminal device 300, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 300. Further, the memory 302 may also include both an internal storage unit and an external storage device of the terminal device 300. The memory 302 is used for storing the computer programs and other programs and data required by the terminal device. The memory 302 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, 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 place, or may be distributed on a plurality of 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 invention 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 can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can be executed by a processor to implement the steps of the above-described embodiments of joint learning of disease prediction models. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A disease prediction model building method based on a joint learning framework is characterized by comprising the following steps:
determining a data set with health characteristic data of different dimensions as joint learning participants, and establishing a joint learning framework for a plurality of participants;
performing model training based on the joint learning architecture, wherein the model training comprises determining an initialization weight of the model and an optimal path of a threshold value by using an adaptive genetic algorithm;
and establishing a target model for disease prediction according to the model training result.
2. The method for building disease prediction model based on joint learning framework according to claim 1, wherein building joint learning framework for a plurality of participants comprises:
and establishing a horizontal joint learning framework for the plurality of participants, wherein the overlapping degree of the same health data features in the data sets of the participants meets a preset value.
3. The method according to claim 1, wherein the model training based on the joint learning framework comprises: and performing joint training on the extreme learning machine based on the joint learning framework.
4. The method for building a disease prediction model based on a joint learning framework according to claim 1, wherein the model training based on the joint learning framework comprises:
the participants each download the latest model from a server of the joint learning architecture;
each participant trains a model by using health characteristic data of different dimensionalities of patients in a data set, encrypts and uploads the trained model parameters to a server, and the server is used for gathering the model parameters of each participant to update the model;
the server returns the updated model to each of the participants;
the participants update their respective models.
5. The method for building a disease prediction model based on a joint learning framework according to claim 4, wherein each of the participants trains the model by using health feature data of different dimensions of patients in a data set, and comprises the following steps:
randomly initializing hidden layer neuron functions;
calculating an output matrix of the hidden layer node;
calculating an output weight from the hidden layer to the output layer;
and calculating a predicted value and an error value according to the matrix and the weight value.
6. The method for building a disease prediction model based on a joint learning framework according to claim 3, wherein the model training comprises determining an optimal path of initialization weights and thresholds of the model by using an adaptive genetic algorithm, comprising:
the joint training of the limit learning machine comprises: after determining the optimal path of the initialization weight and the threshold of the extreme learning machine by using a self-adaptive genetic algorithm, each participant performs joint training by using a data set owned by the participant.
7. The disease prediction model building method based on the joint learning framework according to claim 6, wherein after the optimal path of the initialization weight and the threshold of the extreme learning machine is determined by each participant through an adaptive genetic algorithm, joint training is performed through a data set owned by each participant, and the method comprises the following steps:
generating parameters such as initial kernel function parameters and penalty factors, setting the size of a population and the number of iterations, wherein each individual in the population is in a parameter coding form, and randomly generating an initial value of the individual;
assigning the obtained parameters to an extreme learning machine for prediction, and calculating the fitness value of each chromosome according to the prediction result;
after obtaining the individual fitness value, calculating the selection probability of population individuals according to the obtained fitness value, and selecting the individuals according to the individual selection probability;
calculating individual chromosome crossing probability;
calculating individual chromosome variation probability;
and judging whether a termination condition is reached, if the termination condition is less than the maximum iteration number or the error does not reach a certain threshold value, circularly returning and utilizing the obtained parameters to assign values to the extreme learning machine for prediction, and calculating the fitness value of each chromosome according to the prediction result, otherwise, utilizing the data set to train the extreme learning machine prediction model.
8. A disease prediction model building device based on a joint learning framework is characterized by comprising:
the joint learning establishing module is used for determining a data set with health characteristic data of different dimensionalities of a patient to be joint learning participants and establishing a joint learning framework for the participants;
the joint learning training module is used for carrying out model training based on the joint learning framework, and the model training comprises the step of determining the optimal path of the initialization weight and the threshold of the model by using a self-adaptive genetic algorithm;
and the prediction model establishing module is used for establishing a target model for disease prediction according to the result of the model training.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 6 when executing the computer program.
10. A storage medium storing a computer program, characterized in that the computer program realizes the steps of the method according to any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046461.2A CN112768056A (en) | 2021-01-14 | 2021-01-14 | Disease prediction model establishing method and device based on joint learning framework |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046461.2A CN112768056A (en) | 2021-01-14 | 2021-01-14 | Disease prediction model establishing method and device based on joint learning framework |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112768056A true CN112768056A (en) | 2021-05-07 |
Family
ID=75700427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110046461.2A Pending CN112768056A (en) | 2021-01-14 | 2021-01-14 | Disease prediction model establishing method and device based on joint learning framework |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112768056A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113384241A (en) * | 2021-07-08 | 2021-09-14 | 郑州大学第二附属医院 | Wearable device assisted chronic patient clinical monitoring platform and method |
| CN113486584A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment fault prediction method and device, computer equipment and computer readable storage medium |
| CN114141369A (en) * | 2021-10-20 | 2022-03-04 | 中国科学院自动化研究所 | Method and device for calculating spasm degree, electronic equipment and storage medium |
| WO2022247143A1 (en) * | 2021-11-01 | 2022-12-01 | F. Hoffmann-La Roche Ag | Federated learning of medical validation model |
| CN116092683A (en) * | 2023-04-12 | 2023-05-09 | 深圳达实旗云健康科技有限公司 | Cross-medical institution disease prediction method without original data out of domain |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109346177A (en) * | 2018-09-10 | 2019-02-15 | 昆明理工大学 | A kind of disease symptoms quantitative forecasting technique based on improvement GA-BP algorithm |
| CN110444263A (en) * | 2019-08-21 | 2019-11-12 | 深圳前海微众银行股份有限公司 | Disease data processing method, device, equipment and medium based on federation's study |
| CN110889155A (en) * | 2019-11-07 | 2020-03-17 | 长安大学 | Steel bridge deck corrosion prediction model and construction method |
| CN111126578A (en) * | 2020-04-01 | 2020-05-08 | 阿尔法云计算(深圳)有限公司 | Joint data processing method, device and system for model training |
| CN111190487A (en) * | 2019-12-30 | 2020-05-22 | 中国科学院计算技术研究所 | Method for establishing data analysis model |
| CN111310974A (en) * | 2020-01-18 | 2020-06-19 | 河北工程大学 | Short-term water demand prediction method based on GA-ELM |
| US20200285984A1 (en) * | 2019-03-06 | 2020-09-10 | Hcl Technologies Limited | System and method for generating a predictive model |
| US20200293887A1 (en) * | 2019-03-11 | 2020-09-17 | doc.ai, Inc. | System and Method with Federated Learning Model for Medical Research Applications |
-
2021
- 2021-01-14 CN CN202110046461.2A patent/CN112768056A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109346177A (en) * | 2018-09-10 | 2019-02-15 | 昆明理工大学 | A kind of disease symptoms quantitative forecasting technique based on improvement GA-BP algorithm |
| US20200285984A1 (en) * | 2019-03-06 | 2020-09-10 | Hcl Technologies Limited | System and method for generating a predictive model |
| US20200293887A1 (en) * | 2019-03-11 | 2020-09-17 | doc.ai, Inc. | System and Method with Federated Learning Model for Medical Research Applications |
| CN110444263A (en) * | 2019-08-21 | 2019-11-12 | 深圳前海微众银行股份有限公司 | Disease data processing method, device, equipment and medium based on federation's study |
| CN110889155A (en) * | 2019-11-07 | 2020-03-17 | 长安大学 | Steel bridge deck corrosion prediction model and construction method |
| CN111190487A (en) * | 2019-12-30 | 2020-05-22 | 中国科学院计算技术研究所 | Method for establishing data analysis model |
| CN111310974A (en) * | 2020-01-18 | 2020-06-19 | 河北工程大学 | Short-term water demand prediction method based on GA-ELM |
| CN111126578A (en) * | 2020-04-01 | 2020-05-08 | 阿尔法云计算(深圳)有限公司 | Joint data processing method, device and system for model training |
Non-Patent Citations (3)
| Title |
|---|
| 张杜娟;苏曦;: "基于改进极限学习机的疾病预测研究", 电子测量技术, no. 09 * |
| 王健宗等: "金融智能", 北京：机械工业出版社, pages: 79 * |
| 王新环等: "一种基于遗传算法的极限学习机改进算法研究", 软件导刊, vol. 16, no. 9, pages 79 - 82 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486584A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment fault prediction method and device, computer equipment and computer readable storage medium |
| CN113486584B (en) * | 2021-07-06 | 2023-12-29 | 新奥新智科技有限公司 | Method and device for predicting equipment failure, computer equipment and computer readable storage medium |
| CN113384241A (en) * | 2021-07-08 | 2021-09-14 | 郑州大学第二附属医院 | Wearable device assisted chronic patient clinical monitoring platform and method |
| CN113384241B (en) * | 2021-07-08 | 2023-01-31 | 郑州大学第二附属医院 | Wearable device assisted chronic patient clinical monitoring platform and method |
| CN114141369A (en) * | 2021-10-20 | 2022-03-04 | 中国科学院自动化研究所 | Method and device for calculating spasm degree, electronic equipment and storage medium |
| CN114141369B (en) * | 2021-10-20 | 2022-09-27 | 中国科学院自动化研究所 | Method and device for calculating spasm degree, electronic equipment and storage medium |
| WO2022247143A1 (en) * | 2021-11-01 | 2022-12-01 | F. Hoffmann-La Roche Ag | Federated learning of medical validation model |
| CN115699207A (en) * | 2021-11-01 | 2023-02-03 | 豪夫迈·罗氏有限公司 | Federal learning of medical verification models |
| CN115699207B (en) * | 2021-11-01 | 2024-04-26 | 豪夫迈·罗氏有限公司 | Federal learning of medical validation models |
| CN116092683A (en) * | 2023-04-12 | 2023-05-09 | 深圳达实旗云健康科技有限公司 | Cross-medical institution disease prediction method without original data out of domain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112768056A (en) | Disease prediction model establishing method and device based on joint learning framework | |
| CN109902706B (en) | Recommendation method and device | |
| WO2022227198A1 (en) | Method and device for determining drug regimen of patient | |
| CN109656878B (en) | Health record data generation method and device | |
| CN112085615A (en) | Method and device for training graph neural network | |
| CN111784699B (en) | Method and device for carrying out target segmentation on three-dimensional point cloud data and terminal equipment | |
| WO2024067373A1 (en) | Data processing method and related apparatus | |
| US20230252070A1 (en) | Method and apparatus for training retrieval model, retrieval method and apparatus, device and medium | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN113298931B (en) | Reconstruction method and device of object model, terminal equipment and storage medium | |
| CN111046882A (en) | Disease name standardization method and system based on profile hidden Markov model | |
| CN114297934A (en) | Model parameter parallel simulation optimization method and device based on proxy model | |
| CN111967581B (en) | Method, device, computer equipment and storage medium for interpreting grouping model | |
| CN110489435B (en) | Data processing method and device based on artificial intelligence and electronic equipment | |
| WO2023185541A1 (en) | Model training method and related device | |
| WO2022127603A1 (en) | Model processing method and related device | |
| CN113657525B (en) | KMeans-based cross-feature federal clustering method and related equipment | |
| CN110580517A (en) | Feature extraction method and device based on stacked self-encoder and terminal equipment | |
| CN115803821A (en) | Intelligent triage method and device, storage medium and electronic equipment | |
| CN114692808A (en) | Method and system for determining graph neural network propagation model | |
| CN114528893A (en) | Machine learning model training method, electronic device and storage medium | |
| CN117174319B (en) | Sepsis time sequence prediction method and system based on knowledge graph | |
| CN113780518B (en) | Network architecture optimization method, terminal equipment and computer readable storage medium | |
| CN111651226B (en) | Virtual button ordering method and device, electronic equipment and storage medium | |
| WO2021210543A1 (en) | Device and method for model estimation |
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 |