CN111145905A - Target decision model construction method and device, electronic equipment and storage medium - Google Patents
Target decision model construction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111145905A CN111145905A CN201911416966.2A CN201911416966A CN111145905A CN 111145905 A CN111145905 A CN 111145905A CN 201911416966 A CN201911416966 A CN 201911416966A CN 111145905 A CN111145905 A CN 111145905A
- Authority
- CN
- China
- Prior art keywords
- decision
- data
- model
- decision model
- label
- 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.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims description 10
- 238000012549 training Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000003066 decision tree Methods 0.000 claims description 8
- 230000002787 reinforcement Effects 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000003745 diagnosis Methods 0.000 description 14
- 238000002512 chemotherapy Methods 0.000 description 10
- 201000010099 disease Diseases 0.000 description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 208000024891 symptom Diseases 0.000 description 5
- 230000000153 supplemental effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005728 strengthening Methods 0.000 description 3
- 206010061218 Inflammation Diseases 0.000 description 2
- 206010026673 Malignant Pleural Effusion Diseases 0.000 description 2
- 206010064390 Tumour invasion Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000009400 cancer invasion Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003238 esophagus Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004054 inflammatory process Effects 0.000 description 2
- 210000001370 mediastinum Anatomy 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000036314 physical performance Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 210000003437 trachea Anatomy 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 206010013781 dry mouth Diseases 0.000 description 1
- 229940125753 fibrate Drugs 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Abstract
The invention provides a method and a device for constructing a target decision model, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring clinical guideline data, and constructing a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths; acquiring characteristic data corresponding to a target task and label data corresponding to the characteristic data; and training the pre-constructed second decision model through the characteristic data and the label data, and constructing a target decision model according to the trained second decision model and the trained first decision model. The technical scheme of the embodiment of the invention can improve the interpretation type and the accuracy of the decision result of the decision model and improve the working efficiency of doctors.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for constructing a goal decision model, an electronic device, and a computer-readable storage medium.
Background
With the rapid development of internet technology, the medical field increasingly depends on Clinical Decision making through a Clinical Decision Support System (CDSS). The purpose of the clinical assistant decision system is to make assistant decision for doctors through decision models in the system.
At present, a decision model in a clinical assistant decision system of a related technical scheme is a model driven by knowledge, the interpretability of a corresponding decision result is strong, but the accuracy of a recommendation result is low; or the model is based on data, the accuracy of the corresponding decision result is high, but the interpretation of the recommendation result is weak.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
Embodiments of the present invention provide a method, an apparatus, an electronic device and a computer-readable storage medium for constructing a target decision model, so as to overcome at least a problem that a decision result accuracy and interpretability corresponding to a decision model in a related scheme cannot be compatible to a certain extent.
Additional features and advantages of the invention will be set forth in the detailed description which follows, or may be learned by practice of the invention.
According to a first aspect of the embodiments of the present invention, there is provided a method for constructing a goal decision model, including: acquiring clinical guideline data and constructing a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths; acquiring characteristic data corresponding to a target task and label data corresponding to the characteristic data; and training a pre-constructed second decision model through the feature data and the label data, and constructing a target decision model according to the trained second decision model and the trained first decision model.
In some exemplary embodiments of the present invention, based on the foregoing scheme, training the pre-constructed second decision model by the feature data and the label data includes: inputting the characteristic data into the first decision-making model to determine a target decision-making branch path corresponding to the characteristic data, and determining initial decision-making data corresponding to the characteristic data according to the target decision-making branch path; and training a pre-constructed second decision model according to the initial decision data and the label data.
In some example embodiments of the present invention, based on the foregoing solution, the second decision model comprises a subdivision decision model, and the training of the pre-constructed second decision model by the initial decision data and the label data comprises: when determining that the initial decision data corresponds to a plurality of decision results, acquiring the pre-constructed subdivision decision model; and training the subdivision decision model according to a plurality of decision results and the label data so that the subdivision decision model classifies the initial decision data.
In some exemplary embodiments of the present invention, based on the foregoing scheme, the second decision model comprises a reinforced decision model, and the training of the pre-constructed second decision model by the initial decision data and the label data comprises: when the initial decision data are determined to be decision data to be enhanced, acquiring a pre-constructed enhanced decision model; training the reinforced decision-making model according to the feature data and the label data so that the reinforced decision-making model determines a decision result corresponding to the decision-making data to be reinforced; wherein the decision result comprises a plurality of decision classifications.
In some example embodiments of the present invention, based on the foregoing scheme, the training the reinforced decision model according to the feature data and the label data includes: pre-marking a label of the feature data as a target label, and judging whether leaf node data of the feature data in the first decision model is consistent with label data corresponding to the feature data; wherein the leaf node data comprises a first treatment plan and the label data comprises a second treatment plan; upon determining that the first treatment protocol is consistent with the second treatment protocol, treating the target label as reinforcement label data; and training the reinforced decision model according to the feature data, the label data and the reinforced label data so that the reinforced decision model performs reinforced decision on the decision data to be reinforced and determines the decision classification corresponding to the decision data to be reinforced.
In some example embodiments of the present invention, based on the foregoing, the second decision model comprises a supplementary decision model, and the training of the pre-constructed second decision model by the initial decision data and the label data comprises: when initial decision data corresponding to the characteristic data are determined to be characteristic data according to the target decision branch path, determining that the target decision branch path is in an empty state and acquiring a pre-constructed supplementary decision model; training the supplementary decision model according to the feature data and the label data so that the supplementary decision model classifies the feature data.
In some example embodiments of the present invention, based on the foregoing scheme, the first decision model includes a regular decision tree model, and the second decision model includes any one of a decision tree model, a logistic regression model, a random forest model, a bayesian model, and a deep learning model.
According to a second aspect of the embodiments of the present invention, there is provided a clinical assistant decision method, including: acquiring input decision influencing factors, and determining initial decision data corresponding to the decision influencing factors according to a first decision model in a pre-trained target decision model; and determining auxiliary decision data corresponding to the initial decision data according to a second decision model in the target decision models so as to assist the target object to determine a decision result corresponding to the decision influencing factor according to the auxiliary decision data.
In some example embodiments of the present invention, based on the foregoing solution, the second decision model includes a reinforced decision model, and determining auxiliary decision data corresponding to the initial decision data according to a second decision model in the objective decision model includes: when the initial decision data is determined to be decision data to be strengthened, inputting the decision data to be strengthened into the strengthened decision model to obtain decision classification of the decision data to be strengthened; and taking the decision classification as auxiliary decision data corresponding to the initial decision data.
According to a third aspect of the embodiments of the present invention, there is provided a target decision model constructing apparatus, including: the first decision model building module is used for obtaining clinical guideline data and building a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths; the sample data acquisition module is used for acquiring the characteristic data and the label data corresponding to the characteristic data; and the target decision model building module is used for training a pre-built second decision model through the characteristic data and the label data and building a target decision model according to the trained second decision model and the trained first decision model.
According to a fourth aspect of embodiments of the present invention, there is provided a clinical assistant decision device, comprising: the decision influencing factor acquiring unit is used for acquiring input decision influencing factors; an initial decision data determining unit, configured to determine initial decision data corresponding to the decision influencing factor according to a first decision model in a pre-trained target decision model; and the auxiliary decision data determining unit is used for determining auxiliary decision data corresponding to the initial decision data according to a second decision model in the target decision models so as to assist the target object to determine a decision result corresponding to the decision influencing factor according to the auxiliary decision data.
According to a fifth aspect of embodiments of the present invention, there is provided an electronic apparatus, including: a processor; and a memory having stored thereon computer readable instructions which, when executed by the processor, implement any of the above objective decision model construction methods or clinical assistant decision methods.
According to a sixth aspect of embodiments of the present invention, there is provided a computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements an objective decision model construction method or a clinical assistant decision method according to any one of the above.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
in the method for constructing the objective decision model in the exemplary embodiment of the present invention, a first decision model is constructed according to clinical guideline data, feature data is input into the first decision model to determine an objective decision branch path and initial decision data corresponding to the feature data is determined according to the objective decision branch path, a second decision model which is pre-constructed is trained through the initial decision data and label data, and the objective decision model is constructed according to the trained second decision model and the first decision model. On one hand, the initial decision data is determined according to the first decision model, the second decision model is trained according to the initial decision data and the label data, and finally the target decision model is constructed according to the first decision model and the second decision model, so that the interpretability of a decision result obtained by the target decision model can be improved, and more reference data can be provided for a target object (such as a doctor); on the other hand, the initial decision data is determined by performing initial decision on the feature data according to the first decision model, and the second decision model is trained according to the initial decision data and the label data so that the initial decision data is further classified by the second decision model and the decision result is determined, so that the accuracy of the decision result obtained by the target decision model can be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a method of goal decision model construction, in accordance with some embodiments of the invention;
FIG. 2 schematically illustrates a flow diagram for training a segmentation decision model in accordance with some embodiments of the invention;
FIG. 3 schematically illustrates a flow diagram for training a reinforced decision model in accordance with some embodiments of the invention;
FIG. 4 schematically illustrates a flow diagram for training a supplemental decision model according to some embodiments of the invention;
FIG. 5 schematically illustrates a flow diagram of a clinical assistant decision method according to some embodiments of the invention;
FIG. 6 schematically illustrates a schematic diagram of a goal decision model structure, in accordance with some embodiments of the invention;
FIG. 7 schematically illustrates a schematic diagram of an objective decision model building apparatus according to some embodiments of the invention;
figure 8 schematically illustrates a schematic diagram of a clinical assistant decision device according to some embodiments of the invention;
FIG. 9 schematically illustrates a structural diagram of a computer system of an electronic device, in accordance with some embodiments of the present invention;
FIG. 10 schematically illustrates a schematic diagram of a computer-readable storage medium according to some embodiments of the invention.
In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations or operations have not been shown or described in detail to avoid obscuring aspects of the invention.
Furthermore, the drawings are merely schematic illustrations and are not necessarily drawn to scale. The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The inventors have found that clinical aid decision systems can be divided into knowledge-driven models and data-driven models. In one technical scheme, a clinical assistant decision system mainly comprises a knowledge-driven model, wherein the knowledge-driven model can be realized by using a conditional statement structure IF-THEN as a basis to realize the logic of medical diagnosis and treatment, and finally determines a recommended decision result according to the input of symptom data and the logic execution of certainty, and the system is also called an expert system. However, although the simple knowledge-driven model has strong interpretability of the decision result, the accuracy of the predicted decision result is low when the node is judged to be not 1, namely 0, and the decision result cannot be recommended in many cases due to incomplete coverage of the knowledge rule. In another technical scheme, the clinical assistant decision system mainly comprises a data-driven model, wherein the data-driven model can be a decision model constructed based on data and based on retrieval or machine learning algorithm, and the decision model provides a final recommended decision result according to the input of symptom data. However, although the accuracy of the obtained decision result is high, the model driven by pure data seriously depends on the data quality, and the model based on machine learning, particularly deep learning, has weak interpretability, and the more complex the model is, the higher the accuracy is and the weaker the interpretability is; sometimes, the generalization ability is weak, namely the model training effect is good, but the model training effect is poor when the model training effect is changed to another data set for testing.
Based on this, in this exemplary embodiment, first, a method for constructing a goal decision model is provided, where the method for constructing a goal decision model may be applied to a terminal device or a server, and this is not particularly limited in this exemplary embodiment. In the following, the server performs the method as an example, and fig. 1 schematically shows a flow chart of a method for constructing an objective decision model according to some embodiments of the present invention. Referring to fig. 1, the goal decision model construction method may include the following steps:
step S110, acquiring clinical guideline data, and constructing a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths;
step S120, acquiring characteristic data and label data corresponding to the characteristic data;
step S130, training a pre-constructed second decision model through the initial decision data and the label data, and constructing a target decision model according to the trained second decision model and the trained first decision model.
According to the method for constructing the objective decision model in the exemplary embodiment, on one hand, initial decision data are determined according to the first decision model, the second decision model is trained according to the initial decision data and the label data, and finally the objective decision model is constructed according to the first decision model and the second decision model, so that the interpretability of a decision result obtained by the objective decision model can be improved, and more reference data can be provided for a target object (such as a doctor); on the other hand, the initial decision data is determined by performing initial decision on the feature data according to the first decision model, and the second decision model is trained according to the initial decision data and the label data so that the initial decision data is further classified by the second decision model and the decision result is determined, so that the accuracy of the decision result obtained by the target decision model can be improved.
Next, the objective decision model construction method in the present exemplary embodiment will be further explained.
In step S110, clinical guideline data is obtained, and a first decision model is constructed according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths.
In an exemplary embodiment of the present invention, the clinical guideline data may refer to reference data or a treatment scheme for diagnosing and treating a disease in the medical field, for example, the clinical guideline data may be a medical book of related diseases, may also be a clinical guideline, and may also be other reference data or a treatment scheme for diagnosing and treating a disease, which is not limited in this exemplary embodiment.
The first decision model may refer to a branch model constructed according to the clinical guideline data, and the first decision model may include a plurality of decision branch paths, each decision branch path corresponds to a diagnosis and treatment logic of a target disease in the clinical guideline data, for example, the first decision model may be a model in which a diagnosis logic in the clinical guideline data is implemented in a way of a conditional structure IF-THEN, or may be a regular decision tree model trained according to the clinical guideline data, and of course, the first decision model may also be another model capable of implementing the diagnosis logic in the clinical guideline data, which is not particularly limited in this example embodiment.
In step S120, feature data corresponding to the target task and tag data corresponding to the feature data are acquired.
In an example embodiment of the present invention, the feature data may refer to corresponding symptom data in real medical record data of a patient stored in a database, and the feature data is used for training a target decision model. The label data may refer to a corresponding treatment plan in real case history data stored in the database and presented by the patient, the label data corresponding to the characteristic data, and the label data and the characteristic data are used for training a goal decision model. The target task may refer to actual medical record data in the clinical guideline data.
In step S130, a pre-constructed second decision model is trained through the initial decision data and the label data, and a target decision model is constructed according to the trained second decision model and the trained first decision model.
In an example embodiment of the present invention, the second decision model may be a model for further decision determination on the initial decision data obtained by the first decision model, and the second decision model may be a data model based on a machine learning algorithm, for example, the second decision model may be a deep learning model, a logistic regression model, a decision tree model, a random forest model, or a bayesian model, which is not particularly limited in this example embodiment. The goal decision model may refer to a model formed jointly from the first decision model and the second decision model for assisting the target subject in making a diagnostic decision.
Specifically, the feature data is input into the first decision model to determine a target decision branch path corresponding to the feature data, and initial decision data corresponding to the feature data is determined according to the target decision branch path. The objective decision branch path may refer to diagnosis and treatment logic corresponding to feature data in the clinical guideline data, and the initial decision data may refer to a diagnosis and treatment plan or a diagnosis result corresponding to the objective decision branch path. The target object can be made to know the judgment logic corresponding to the initial decision data through the target decision branch path, and the interpretability of the initial decision data is improved.
In this example embodiment, the second decision model may include one or more of a subdivision decision model, an enhanced decision model, and a supplemental decision model, and of course, the second decision model may also be a decision model with other functions, which is not limited in this example embodiment. The second decision model may be a subdivision decision model, for example when only initial decision data comprising a plurality of decision results need to be subdivided and classified; when the initial decision data including a plurality of decision results need to be classified in a refined manner and the initial decision data including a plurality of decision factors need to be clearly classified, the second decision model may be a subdivision decision model or a reinforced decision model, and the type of the second decision model may be determined according to the initial decision data corresponding to the target decision branch path, which is not particularly limited in this example embodiment.
And training the second decision model according to the initial decision data obtained by the first decision model and the label data of the feature data corresponding to the initial decision data, and splicing the first decision model and the trained second decision model to obtain the constructed target decision model.
FIG. 2 schematically illustrates a flow diagram for training a segmentation decision model in accordance with some embodiments of the present invention.
Referring to fig. 2, in step S210, when it is determined that the initial decision data corresponds to a plurality of decision results, the pre-constructed subdivision decision model is obtained.
In an exemplary embodiment of the present invention, the subdivided decision model may refer to a model that further classifies a plurality of decision results (of course, a plurality of treatment schemes, which is not limited in this exemplary embodiment) in the initial decision data obtained by the first decision model, for example, if the feature data may be fever, dry mouth, tongue dryness, etc., the feature data is input to the first decision model to obtain the initial decision data, for example, the initial decision data may be a treatment scheme corresponding to a cold and a cold or a treatment scheme corresponding to inflammation and inflammation, etc., the initial decision data has two decision results, but the decision result still has two classifications at this time, which results in a vague decision result and an inaccurate classification, and at this time, the initial decision data may be further decided by training the subdivided decision model in the second decision model, of course, this is merely an illustrative example, and should not be construed as limiting this example embodiment in any way.
Step S220, training the subdivision decision model according to the decision results and the label data, so that the subdivision decision model classifies the initial decision data.
In an exemplary embodiment of the present invention, when it is detected that the initial decision data includes a plurality of decision results or treatment schemes, the decision result obtained by the first decision model is considered to be ambiguous and cannot be directly used as the final decision result, and therefore, the plurality of decision results or treatment schemes included in the initial decision data need to be further classified to determine the most correct decision result corresponding to the feature data. Specifically, a subdivision decision model may be trained according to the initial decision data, the feature data, and the label data, and the initial decision data including a plurality of decision results may be further classified according to the trained subdivision decision model, so as to determine the most correct decision result corresponding to the feature data.
For example, a target decision branch path (which may also be considered as a diagnostic rule or diagnostic logic in a medical book or clinical guideline) corresponding to the feature data is determined according to the first decision model, and the initial decision data (which may also be considered as a plurality of recommended treatment options in the medical book or clinical guideline) corresponding to the target decision branch path is determined, but which treatment option is better is not indicated. At this time, relevant features in the feature data are selected as model features, a real treatment plan corresponding to the feature data is selected as Label data (Label), and a subdivision decision model is constructed based on the model features and a data set constructed by the Label data to subdivide the treatment plan corresponding to the feature data entering the target decision branch path.
FIG. 3 schematically illustrates a flow diagram for training a reinforced decision model in accordance with some embodiments of the invention.
Referring to fig. 3, in step S310, when it is determined that the initial decision data is decision data to be enhanced, a pre-constructed enhanced decision model is obtained.
In an exemplary embodiment of the present invention, the enhanced decision model may refer to a model for accurately classifying initial decision data including a plurality of decision factors obtained by a first decision model, for example, it is assumed that the initial decision data may be a model for performing chemotherapy on a patient, but whether the patient is subjected to chemotherapy needs to comprehensively consider decision factors such as age, physical condition, and combined basic disease, so that a "decision point" enhanced decision model needs to be added in the target decision branch path for determining "comprehensive assessment of physical ability" of the patient corresponding to the feature data, when the enhanced decision model determines that the "comprehensive assessment of physical ability" is good, the patient corresponding to the feature data is subjected to chemotherapy, when the enhanced decision model determines that the "comprehensive assessment of physical ability" is not good, the patient corresponding to the feature data is not subjected to chemotherapy, and diagnosis logics of other decision branch paths are performed, of course, this is merely an illustrative example, and should not be construed as limiting this example embodiment in any way.
Step S320, training the reinforced decision-making model according to the feature data and the label data so that the reinforced decision-making model determines a decision result corresponding to decision-making data to be reinforced; wherein the decision result comprises a plurality of decision classifications.
In an exemplary embodiment of the present invention, the decision data to be enhanced may refer to initial decision data in a case where the first decision model determines that there is a high risk factor or T stage (international TNM clinical stage) is T4 (which may refer to primary tumor invasion and mediastinum, heart, large blood vessel, trachea, esophagus, vertebral body, carina, or accompanied by malignant pleural effusion), for example, according to clinical guideline data, whether chemotherapy is to be performed on a patient in clinical phase II needs to comprehensively consider factors that may affect chemotherapy risk, such as age, physical condition, and underlying disease, so that further classification for decision data to be enhanced is needed to determine a decision result. When the initial decision data is detected to be decision data to be strengthened, the decision result obtained by the first decision model is considered to be needed to be subjected to strengthening decision, if further decision is needed, whether the comprehensive physical ability condition of the patient is suitable for chemotherapy is judged, so that the strengthening decision of the decision data to be strengthened is needed to be carried out so as to determine the most correct decision result corresponding to the characteristic data, the accuracy of the decision result is ensured through the strengthening decision model, and the life safety of the patient is ensured.
Further, the label of the feature data is labeled as a target label in advance, for example, when the physical ability comprehensive condition of the patient in the initial decision data needs to be judged, the label of the feature data can be labeled as a good physical ability condition (i.e., a target label) in advance.
Then judging whether the leaf node data of the feature data in the first decision model is consistent with the label data corresponding to the feature data; where the leaf node data comprises a first treatment plan and the label data comprises a second treatment plan, for example assuming that the 'physical fitness status' is 'good' (target label), the rule tree in the first decision model continues to be executed to the leaf nodes, if the treatment plan of the leaf node is consistent with the treatment plan ultimately used by the patient, this assumed 'target label' may be considered correct, otherwise other assumptions are executed (e.g. assuming 'physical fitness status' is 'poor') until the sample label is unambiguous.
Specifically, when it is determined that the first treatment plan is consistent with the second treatment plan, if the assumed target label is correct, such as "physical fitness status is good", the target label is used as the reinforcement label data; when the first treatment scheme is determined to be inconsistent with the second treatment scheme, the assumed target label such as 'physical ability condition is good' is considered to be wrong, the 'physical ability' label can be continuously assumed to be 'poor', then whether the leaf node data of the feature data in the first decision model is consistent with the label data corresponding to the feature data is continuously judged, and when the first treatment scheme is determined to be consistent with the second treatment scheme, the assumed target label such as 'physical ability condition is poor' is determined to be correct, and the target label is used as the strengthened label data.
And finally, training the reinforced decision model according to the feature data, the label data and the reinforced label data so that the reinforced decision model carries out reinforced decision on the decision data to be reinforced and determines the decision classification corresponding to the decision data to be reinforced.
FIG. 4 schematically illustrates a flow diagram for training a supplemental decision model according to some embodiments of the invention.
Referring to fig. 4, in step S410, when it is determined that the initial decision data corresponding to the feature data is the feature data according to the objective decision branch path, it is determined that the objective decision branch path is in an empty state, and a pre-constructed supplementary decision model is obtained.
In an exemplary embodiment of the present invention, when the initial decision data corresponding to the feature data is determined to be the feature data according to the objective decision branch path, it is considered that the first decision model does not include the decision branch path corresponding to the feature data, that is, the objective decision branch path corresponding to the feature data is in an empty state. A goal decision branch path in an empty state may indicate that the feature data is not covered in the clinical guideline data, and therefore a decision branch path corresponding to the feature data needs to be added.
Step S420, training the supplementary decision model according to the feature data and the label data, so that the supplementary decision model classifies the feature data.
In an example embodiment of the present invention, the supplementary decision model may be a model for making a decision on feature data not covered by the decision branch path, or may be considered as a decision branch path corresponding to feature data through the supplementary decision model.
In this exemplary embodiment, a clinical assistant decision method is further provided, where the clinical assistant decision method may be applied to a terminal device or a server, and this is not particularly limited in this exemplary embodiment. In the following, the server is taken as an example for carrying out the method, and fig. 5 schematically shows a flow chart of a clinical assistant decision method according to some embodiments of the invention.
Referring to fig. 5, in step S510, input decision influencing factors are acquired.
In an exemplary embodiment of the present invention, the decision influencing factor may refer to all relevant data that may influence the decision result and that currently needs to perform decision analysis to determine the decision result, for example, the decision influencing factor may be symptom data of the patient (or all data that may influence the decision result, such as basic information data, historical diagnosis data, and the like) input by the target object through the terminal device, or may be text data on medical record data of the patient, and of course, the decision influencing factor may also be a symptom image of the patient acquired through the image acquisition device, which is not particularly limited in this exemplary embodiment.
In step S510, initial decision data corresponding to the decision influencing factor is determined according to a first decision model in the pre-trained target decision models.
In an exemplary embodiment of the present invention, the pre-trained goal decision model may refer to a goal decision model constructed by the aforementioned goal decision model construction method, and the first decision model may refer to a model constituting the goal decision model. The initial decision data may refer to that the decision influencing factors are input into the objective decision model, so that a first decision model in the objective decision model determines a target decision branch path corresponding to the decision influencing factors, and then the initial decision data corresponding to the decision influencing factors is determined according to the target decision branch path.
In step S510, auxiliary decision data corresponding to the initial decision data is determined according to a second decision model in the target decision models, so as to assist the target object in determining a decision result corresponding to the decision influencing factor according to the auxiliary decision data.
In an example embodiment of the present invention, the assistant decision data may refer to a decision result obtained by a second decision model in the target decision model making a further decision according to the initial decision data obtained by the first decision model. The target object may be an object for determining a diagnosis result or a treatment plan corresponding to the decision influencing factor according to the auxiliary decision data, for example, the target object may be a doctor of a patient corresponding to the decision influencing factor or may be a medical robot serving the patient, and of course, the target object may also be another object capable of determining a diagnosis result or a diagnosis plan corresponding to the decision influencing factor according to the auxiliary decision data, which is not particularly limited in this example. And the target decision model outputs the determined auxiliary decision data to the terminal equipment associated with the target object, so that the target object determines a decision result corresponding to the decision influencing factor according to the auxiliary decision data.
Specifically, when the initial decision data is determined to be the decision data to be enhanced, the decision data to be enhanced is input into an enhanced decision model to obtain decision classification of the decision data to be enhanced; and taking the decision classification as auxiliary decision data corresponding to the initial decision data. The decision data to be enhanced may refer to initial decision data when the first decision model determines that there is a high risk factor or T stage (international TNM clinical stage) is T4 (which may refer to primary tumor invasion and mediastinum, heart, great vessel, trachea, esophagus, vertebral body, carina, or accompanied by malignant pleural effusion), for example, according to clinical guideline data, whether chemotherapy is performed on a patient in clinical phase II needs to comprehensively consider factors that may affect chemotherapy risk, such as age, physical condition, and underlying disease, so that the decision data to be enhanced needs to be further classified for determining a decision result. When the initial decision data is detected to be decision data to be strengthened, the strengthened decision model in the second decision model is considered to be needed to carry out strengthened decision on the obtained decision result, if further decision is needed, whether the physical ability comprehensive condition of the patient is suitable for chemotherapy is judged, and therefore strengthened decision classification needs to be carried out on the decision data to be strengthened. For example, for the decision-making influencing factors classified as high-risk factors or belonging to T4 in the T stage, factors such as age, physical condition, and combined basic diseases which may cause medical risk need to be comprehensively considered, and at this time, a strengthened decision-making model is needed as a "decision point" to perform decision-making classification on the decision-making influencing factors to determine whether the physical performance of the patient is good or poor so as to perform further diagnosis decision.
FIG. 6 schematically illustrates a schematic diagram of a goal decision model structure, according to some embodiments of the invention.
Referring to fig. 6, the goal decision model 600 may include a first decision model 601 and a second decision model, wherein the second decision model may include a supplemental decision model 606, an enhanced decision model 611, and a refined decision model 609. First decision model 601 may include a plurality of decision branch paths, which may include, for example, decision branch path 602, decision branch path 603, and decision branch path 604.
Decision branch path 602 is in a null state, and when the feature data stream is transferred to the decision branch path (i.e., it can be considered that the feature data is not covered by the decision branch path of first decision model 601), the decision result of the feature data needs to be determined, but at this time, depending on that the first decision model 601 is not enough to determine the decision result of the feature data, it is considered that a new feature 605 (i.e., a feature corresponding to the feature data) appears in the branch path, so that a supplementary decision model 606 is trained to replace decision branch path 602 in the null state to perform decision classification on feature data 605 transferred to the branch.
For the feature data flowing to the decision branch path 604, the first decision model 601 makes a first decision on the feature data according to whether the diagnostic logic 607 is "high-risk factor", and when "no high-risk factor" is determined, a diagnostic result 608 (or a diagnostic scheme) corresponding to the feature data is determined, but the diagnostic result 608 includes a plurality of diagnostic schemes, which are relatively ambiguous, so that the refined decision model 609 needs to be trained to make a further classification decision on the diagnostic result 608 to determine the most correct decision result corresponding to the feature data flowing to the decision branch path 604.
When the flow is forwarded to the decision branch path 603 and the diagnosis logic 607 is determined to be "there is a high risk factor", the decision point 610 "physical performance status" needs to be determined by integrating the decision factors such as the age, physical condition, and basic disease of the patient corresponding to the feature data, so as to determine the decision results under different decision factors. Specifically, the enhanced decision model 611 may be trained to make a final decision on the feature data forwarded to the decision point according to the decision factor to determine a decision result.
It is noted that although the steps of the methods of the present invention are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
In addition, in the present exemplary embodiment, an objective decision model building apparatus is also provided. Referring to fig. 7, the goal decision model building means 700 includes: the first decision model building module 710 is configured to obtain clinical guideline data and build a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths; the feature data obtaining module 720 is configured to obtain feature data and tag data corresponding to the feature data; the objective decision model constructing module 730 is configured to train a pre-constructed second decision model through the initial decision data and the label data, and construct an objective decision model according to the trained second decision model and the trained first decision model.
In an exemplary embodiment of the present invention, based on the foregoing solution, the objective decision model building module 730 further comprises a second decision model training unit configured to: inputting the characteristic data into the first decision-making model to determine a target decision-making branch path corresponding to the characteristic data, and determining initial decision-making data corresponding to the characteristic data according to the target decision-making branch path; and training a pre-constructed second decision model according to the initial decision data and the label data.
In an exemplary embodiment of the present invention, based on the foregoing scheme, the goal decision model building module 730 further comprises a subdivision decision model training unit configured to: when determining that the initial decision data corresponds to a plurality of decision results, acquiring the pre-constructed subdivision decision model; and training the subdivision decision model according to a plurality of decision results and the label data so that the subdivision decision model classifies the initial decision data.
In an exemplary embodiment of the present invention, based on the foregoing solution, the goal decision model building module 730 further includes a reinforced decision model training unit configured to: when the initial decision data are determined to be decision data to be enhanced, acquiring a pre-constructed enhanced decision model; training the reinforced decision-making model according to the feature data and the label data so that the reinforced decision-making model determines a decision result corresponding to the decision-making data to be reinforced; wherein the decision result comprises a plurality of decision classifications.
In an exemplary embodiment of the invention, based on the foregoing scheme, the reinforced decision model training unit is further configured to: pre-marking a label of the feature data as a target label, and judging whether leaf node data of the feature data in the first decision model is consistent with label data corresponding to the feature data; wherein the leaf node data comprises a first treatment plan and the label data comprises a second treatment plan; upon determining that the first treatment protocol is consistent with the second treatment protocol, treating the target label as reinforcement label data; and training the reinforced decision model according to the feature data, the label data and the reinforced label data so that the reinforced decision model performs reinforced decision on the decision data to be reinforced and determines the decision classification corresponding to the decision data to be reinforced.
In an exemplary embodiment of the present invention, based on the foregoing scheme, the goal decision model building module 730 further comprises a supplementary decision model training unit configured to: when initial decision data corresponding to the characteristic data are determined to be characteristic data according to the target decision branch path, determining that the target decision branch path is in an empty state and acquiring a pre-constructed supplementary decision model; training the supplementary decision model according to the feature data and the label data so that the supplementary decision model classifies the feature data.
In an exemplary embodiment of the present invention, based on the foregoing scheme, the first decision model includes a regular decision tree model, and the second decision model includes any one of a decision tree model, a logistic regression model, a random forest model, a fibrates model, and a deep learning model.
In the present exemplary embodiment, a clinical assistant decision device is also provided. Referring to fig. 8, the goal decision model building means 800 includes: the decision influencing factor obtaining unit 810 is configured to obtain an input decision influencing factor; the initial decision data determining unit 820 is configured to determine initial decision data corresponding to the decision influencing factor according to a first decision model in the pre-trained target decision models; the assistant decision data determining unit 830 is configured to determine, according to a second decision model of the target decision models, assistant decision data corresponding to the initial decision data to assist the target object in determining, according to the assistant decision data, a decision result corresponding to the decision influencing factor.
In an exemplary embodiment of the present invention, based on the foregoing scheme, the assistant decision data determining unit 830 is further configured to: when the initial decision data is determined to be decision data to be strengthened, inputting the decision data to be strengthened into the strengthened decision model to obtain decision classification of the decision data to be strengthened; and taking the decision classification as auxiliary decision data corresponding to the initial decision data.
The specific details of each module of the objective decision model building device or the clinical decision-making assisting device are already described in detail in the corresponding objective decision model building method or the clinical decision-making assisting method, and therefore, the details are not repeated here.
It should be noted that although several modules or units of the object decision model building means are mentioned in the above detailed description, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the invention. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above objective decision model building method is also provided.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 900 according to such an embodiment of the invention is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is only an example and should not bring any limitations to the functionality or scope of use of the embodiments of the present invention.
As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.
Wherein the storage unit stores program code that is executable by the processing unit 910 to cause the processing unit 910 to perform steps according to various exemplary embodiments of the present invention described in the above section "exemplary methods" of the present specification. For example, the processing unit 910 may execute step S110 as shown in fig. 1, obtain clinical guideline data, and construct a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths; step S120, acquiring characteristic data and label data corresponding to the characteristic data; step S130, training a pre-constructed second decision model through the initial decision data and the label data, and constructing a target decision model according to the trained second decision model and the trained first decision model.
The storage unit 920 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)921 and/or a cache memory unit 922, and may further include a read only memory unit (ROM) 923.
The electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 900, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interface 950. Also, the electronic device 900 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 960. As shown, the network adapter 960 communicates with the other modules of the electronic device 900 via the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above-mentioned "exemplary methods" section of the present description, when said program product is run on the terminal device.
Referring to fig. 10, a program product 1000 for implementing the above objective decision model building method or clinical assistant decision method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (12)
1. A method for constructing a goal decision model, comprising:
acquiring clinical guideline data and constructing a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths;
acquiring characteristic data corresponding to a target task and label data corresponding to the characteristic data;
and training a pre-constructed second decision model through the feature data and the label data, and constructing a target decision model according to the trained second decision model and the trained first decision model.
2. The method of claim 1, wherein training a pre-constructed second decision model with the feature data and the label data comprises:
inputting the characteristic data into the first decision-making model to determine a target decision-making branch path corresponding to the characteristic data, and determining initial decision-making data corresponding to the characteristic data according to the target decision-making branch path;
and training a pre-constructed second decision model according to the initial decision data and the label data.
3. A method for constructing a goal decision model according to claim 1, wherein the second decision model comprises a subdivision decision model, and the training of the pre-constructed second decision model by the initial decision data and label data comprises:
when determining that the initial decision data corresponds to a plurality of decision results, acquiring the pre-constructed subdivision decision model;
and training the subdivision decision model according to a plurality of decision results and the label data so that the subdivision decision model classifies the initial decision data.
4. A method for constructing a goal decision model according to claim 1, wherein the second decision model comprises a reinforced decision model, and the training of the pre-constructed second decision model by the initial decision data and the label data comprises:
when the initial decision data are determined to be decision data to be enhanced, acquiring a pre-constructed enhanced decision model;
training the reinforced decision-making model according to the feature data and the label data so that the reinforced decision-making model determines a decision result corresponding to the decision-making data to be reinforced; wherein the decision result comprises a plurality of decision classifications.
5. The method of constructing a goal decision model according to claim 4, wherein the training of the reinforced decision model based on the feature data and the label data comprises:
pre-marking a label of the feature data as a target label, and judging whether leaf node data of the feature data in the first decision model is consistent with label data corresponding to the feature data; wherein the leaf node data comprises a first treatment plan and the label data comprises a second treatment plan;
upon determining that the first treatment protocol is consistent with the second treatment protocol, treating the target label as reinforcement label data;
and training the reinforced decision model according to the feature data, the label data and the reinforced label data so that the reinforced decision model performs reinforced decision on the decision data to be reinforced and determines the decision classification corresponding to the decision data to be reinforced.
6. A method for constructing a goal decision model according to claim 1, wherein the second decision model comprises a supplementary decision model, and the training of the pre-constructed second decision model by the initial decision data and the label data comprises:
when initial decision data corresponding to the characteristic data are determined to be characteristic data according to the target decision branch path, determining that the target decision branch path is in an empty state and acquiring a pre-constructed supplementary decision model;
training the supplementary decision model according to the feature data and the label data so that the supplementary decision model classifies the feature data.
7. The method of constructing a goal decision model according to any one of claims 1 to 6, wherein the first decision model comprises a regular decision tree model and the second decision model comprises any one of a decision tree model, a logistic regression model, a random forest model, a Bayesian model, and a deep learning model.
8. A method of clinical aid decision making, comprising:
acquiring input decision influencing factors;
determining initial decision data corresponding to the decision influencing factors according to a first decision model in pre-trained target decision models;
and determining auxiliary decision data corresponding to the initial decision data according to a second decision model in the target decision models so as to assist the target object to determine a decision result corresponding to the decision influencing factor according to the auxiliary decision data.
9. A clinical assistant decision method according to claim 8, wherein the second decision model comprises a reinforcement decision model, and the determining of assistant decision data corresponding to the initial decision data according to the second decision model in the objective decision model comprises:
when the initial decision data is determined to be decision data to be strengthened, inputting the decision data to be strengthened into the strengthened decision model to obtain decision classification of the decision data to be strengthened;
and taking the decision classification as auxiliary decision data corresponding to the initial decision data.
10. An object decision model building apparatus, comprising:
the first decision model building module is used for obtaining clinical guideline data and building a first decision model according to the clinical guideline data; wherein the first decision model comprises a plurality of decision branch paths;
the characteristic data acquisition module is used for acquiring characteristic data and label data corresponding to the characteristic data;
and the target decision model building module is used for training a pre-built second decision model through the characteristic data and the label data and building a target decision model according to the trained second decision model and the trained first decision model.
11. An electronic device, comprising:
a processor; and
a memory having stored thereon computer readable instructions which, when executed by the processor, implement an objective decision model construction method according to any one of claims 1 to 7 or a clinical assistant decision method according to any one of claims 8 to 9.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out an objective decision model construction method according to any one of claims 1 to 7 or a clinical assistant decision method according to any one of claims 8 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911416966.2A CN111145905B (en) | 2019-12-31 | 2019-12-31 | Target decision model construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911416966.2A CN111145905B (en) | 2019-12-31 | 2019-12-31 | Target decision model construction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111145905A true CN111145905A (en) | 2020-05-12 |
| CN111145905B CN111145905B (en) | 2024-04-05 |
Family
ID=70522873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911416966.2A Active CN111145905B (en) | 2019-12-31 | 2019-12-31 | Target decision model construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111145905B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582489A (en) * | 2020-05-14 | 2020-08-25 | 上海深至信息科技有限公司 | Distributed deployment decision making system and method of ultrasonic artificial intelligence model |
| CN111816300A (en) * | 2020-06-30 | 2020-10-23 | 平安科技（深圳）有限公司 | Data classification method, device, equipment and medium based on deep reinforcement learning |
| CN112365975A (en) * | 2020-11-12 | 2021-02-12 | 医渡云（北京）技术有限公司 | Medical aid decision model interpretation method and device, storage medium and electronic equipment |
| CN112600282A (en) * | 2021-01-06 | 2021-04-02 | 亨铨实业(深圳)有限公司 | Intelligent solar luggage charging and discharging control method and system |
| WO2021139223A1 (en) * | 2020-08-06 | 2021-07-15 | 平安科技（深圳）有限公司 | Method and apparatus for interpretation of clustering model, computer device, and storage medium |
| CN114745289A (en) * | 2022-04-19 | 2022-07-12 | 中国联合网络通信集团有限公司 | Method, device, storage medium and equipment for predicting network performance data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144147A1 (en) * | 2003-12-26 | 2005-06-30 | Lee Shih-Jong J. | Feature regulation for hierarchical decision learning |
| US20100063839A1 (en) * | 2006-09-20 | 2010-03-11 | Koninklijke Philips Electronics N.V. | Molecular diagnostics decision support system |
| CN109378065A (en) * | 2018-10-30 | 2019-02-22 | 医渡云（北京）技术有限公司 | Medical data processing method and processing device, storage medium, electronic equipment |
| CN109801705A (en) * | 2018-12-12 | 2019-05-24 | 平安科技（深圳）有限公司 | Treat recommended method, system, device and storage medium |
| CN110111887A (en) * | 2019-05-15 | 2019-08-09 | 清华大学 | Clinical aid decision-making method and device |
| CN110289095A (en) * | 2019-06-28 | 2019-09-27 | 青岛百洋智能科技股份有限公司 | A kind of fracture of neck of femur clinic intelligence aided decision method and system |
-
2019
- 2019-12-31 CN CN201911416966.2A patent/CN111145905B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144147A1 (en) * | 2003-12-26 | 2005-06-30 | Lee Shih-Jong J. | Feature regulation for hierarchical decision learning |
| US20100063839A1 (en) * | 2006-09-20 | 2010-03-11 | Koninklijke Philips Electronics N.V. | Molecular diagnostics decision support system |
| CN109378065A (en) * | 2018-10-30 | 2019-02-22 | 医渡云（北京）技术有限公司 | Medical data processing method and processing device, storage medium, electronic equipment |
| CN109801705A (en) * | 2018-12-12 | 2019-05-24 | 平安科技（深圳）有限公司 | Treat recommended method, system, device and storage medium |
| CN110111887A (en) * | 2019-05-15 | 2019-08-09 | 清华大学 | Clinical aid decision-making method and device |
| CN110289095A (en) * | 2019-06-28 | 2019-09-27 | 青岛百洋智能科技股份有限公司 | A kind of fracture of neck of femur clinic intelligence aided decision method and system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582489A (en) * | 2020-05-14 | 2020-08-25 | 上海深至信息科技有限公司 | Distributed deployment decision making system and method of ultrasonic artificial intelligence model |
| CN111816300A (en) * | 2020-06-30 | 2020-10-23 | 平安科技（深圳）有限公司 | Data classification method, device, equipment and medium based on deep reinforcement learning |
| WO2021139223A1 (en) * | 2020-08-06 | 2021-07-15 | 平安科技（深圳）有限公司 | Method and apparatus for interpretation of clustering model, computer device, and storage medium |
| CN112365975A (en) * | 2020-11-12 | 2021-02-12 | 医渡云（北京）技术有限公司 | Medical aid decision model interpretation method and device, storage medium and electronic equipment |
| CN112365975B (en) * | 2020-11-12 | 2021-07-23 | 医渡云（北京）技术有限公司 | Medical aid decision model interpretation method and device, storage medium and electronic equipment |
| WO2022100417A1 (en) * | 2020-11-12 | 2022-05-19 | 医渡云（北京）技术有限公司 | Interpretation method and apparatus for medical auxiliary decision-making model, and storage medium and electronic device |
| CN112600282A (en) * | 2021-01-06 | 2021-04-02 | 亨铨实业(深圳)有限公司 | Intelligent solar luggage charging and discharging control method and system |
| CN112600282B (en) * | 2021-01-06 | 2021-06-25 | 亨铨实业(深圳)有限公司 | Intelligent solar luggage charging and discharging control method and system |
| CN114745289A (en) * | 2022-04-19 | 2022-07-12 | 中国联合网络通信集团有限公司 | Method, device, storage medium and equipment for predicting network performance data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111145905B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145905B (en) | Target decision model construction method and device, electronic equipment and storage medium | |
| Dias et al. | Artificial intelligence in clinical and genomic diagnostics | |
| Wainberg et al. | Deep learning in biomedicine | |
| Pradhan et al. | Medical Internet of things using machine learning algorithms for lung cancer detection | |
| US11688518B2 (en) | Deep neural network based identification of realistic synthetic images generated using a generative adversarial network | |
| KR102153920B1 (en) | System and method for interpreting medical images through the generation of refined artificial intelligence reinforcement learning data | |
| CN109378065A (en) | Medical data processing method and processing device, storage medium, electronic equipment | |
| US10936628B2 (en) | Automatic processing of ambiguously labeled data | |
| CN111564223B (en) | Infectious disease survival probability prediction method, and prediction model training method and device | |
| CN112002410A (en) | Infectious disease state prediction method and device, storage medium, and electronic device | |
| CN109448858A (en) | Colorectal cancer medical data processing method and processing device, storage medium, electronic equipment | |
| CN114300141A (en) | Disease risk grade prediction method and device, readable storage medium and electronic equipment | |
| Sedighi-Maman et al. | A two-stage modeling approach for breast cancer survivability prediction | |
| Teo et al. | Discovering the predictive value of clinical notes: machine learning analysis with text representation | |
| Moazemi et al. | Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: A systematic review | |
| Kapoor et al. | Cardiovascular disease prognosis and analysis using machine learning techniques | |
| CN111161884A (en) | Disease prediction method, device, equipment and medium for unbalanced data | |
| Chandrasekar et al. | Lung cancer disease detection using service-oriented architectures and multivariate boosting classifier | |
| CN111403028B (en) | Medical text classification method and device, storage medium and electronic equipment | |
| KR102639807B1 (en) | Multimodal Multitask Deep Learning Model for Alzheimer's Disease Progression Detection based on Time Series Data | |
| Rafiei et al. | Meta-learning in healthcare: A survey | |
| Alur et al. | Auditing for Human Expertise | |
| Chen et al. | Machine learning for precision health economics and outcomes research (P-HEOR): conceptual review of applications and next steps | |
| Khaneja et al. | Analysing risk of coronary heart disease through discriminative neural networks | |
| Wang et al. | Interpretable knowledge mining for heart failure prognosis risk evaluation |
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 | ||
| GR01 | Patent grant |