CN112133382B - Learning method and system for medical analysis by using algorithm model - Google Patents
Learning method and system for medical analysis by using algorithm model Download PDFInfo
- Publication number
- CN112133382B CN112133382B CN202011021484.XA CN202011021484A CN112133382B CN 112133382 B CN112133382 B CN 112133382B CN 202011021484 A CN202011021484 A CN 202011021484A CN 112133382 B CN112133382 B CN 112133382B
- Authority
- CN
- China
- Prior art keywords
- medicine
- medicines
- node
- drug
- components
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 48
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000003814 drug Substances 0.000 claims abstract description 239
- 229940079593 drug Drugs 0.000 claims abstract description 74
- 201000010099 disease Diseases 0.000 claims abstract description 42
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 42
- 230000005484 gravity Effects 0.000 claims abstract description 32
- 230000000694 effects Effects 0.000 claims abstract description 30
- 229940126673 western medicines Drugs 0.000 claims abstract description 28
- 229940126678 chinese medicines Drugs 0.000 claims abstract description 17
- 239000000126 substance Substances 0.000 claims description 27
- 239000000203 mixture Substances 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 6
- 238000012948 formulation analysis Methods 0.000 claims 1
- 239000004615 ingredient Substances 0.000 claims 1
- 238000013179 statistical model Methods 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000001647 drug administration Methods 0.000 description 4
- 238000009098 adjuvant therapy Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003012 network analysis Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 229940126680 traditional chinese medicines Drugs 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/50—Molecular design, e.g. of drugs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- 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
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Pharmacology & Pharmacy (AREA)
- Medical Informatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Physics & Mathematics (AREA)
- Toxicology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
- Medicines Containing Plant Substances (AREA)
Abstract
The invention relates to the technical field of medicine data analysis, and discloses a learning method and a system for medicine analysis by utilizing an algorithm model, wherein the method comprises the following steps: s1, inquiring the names of Chinese and western medicines for treatment according to the diseases; s2, searching the components and the proportions of the medicines in a national medicine database through the names of Chinese and western medicines; s3, finding out components with higher specific gravity and higher occurrence frequency from the components of the medicine through a traversal algorithm; s4, analyzing which drug-taking mode has the heaviest proportion and which proportion and drug-taking mode have the best treatment effect through a traversing algorithm. So as to solve the problem that the distribution ratio and the drug-taking mode of the traditional Chinese medicine and the western medicine are difficult to analyze.
Description
Technical Field
The invention relates to the technical field of medical data analysis, in particular to a learning method and a learning system for medical analysis by utilizing an algorithm model.
Background
Traditional Chinese medicine prescription is a main means of traditional Chinese medicine treatment, however, the prescription often contains a plurality of medicines, wherein only a few medicines play an important role in treating specific diseases or symptoms, and other medicines play an auxiliary role, so that the medicines are considered as core medicines for treating the diseases; the same is true for most western medicines, however, the difference of taking medicines orally or injecting or smearing the medicines on the parts of the human body acted by the western medicines is large. The core medicine is an important medicine combination for treating certain diseases, which is often matched together in the prescription. The core medicine combination corresponding to the specific diseases is found, which is beneficial to verifying the theory of 'corresponding to prescription' and researching the prescription compatibility rules and the like, and assists clinical medication.
Chinese patent CN104820775A provides a method for discovering a Chinese medicine prescription core medicine. The patent consists of an improved clustering algorithm and a weighted TF-IDF algorithm, wherein the clustering algorithm comprises three parts of pretreatment of prescription data, selection of a clustering distance function and a clustering mining algorithm, and the prescription data is processed into a model suitable for the clustering algorithm by a prediction theory of the prescription data; the selection of the clustering distance is used for selecting a reasonable clustering distance function; the distance mining algorithm is used for clustering similar prescriptions into a cluster; the weighting TF-IDF algorithm is used for calculating the weight of the medicine, and the weight calculation formula combines the clustering result, the medicine sequence importance and the TF-IDF algorithm. Fourth, a complex network analysis-based method: the intrinsic structure and node importance of the network are researched by networking prescriptions or medicines and adopting a means of complex network analysis, so that the compatibility relationship between medicines and the importance of medicines are revealed.
The defects in the prior art are that 1, although the patent discloses a core drug analysis method of traditional Chinese medicine, the analysis of drug proportion and drug administration mode is lacking in the western medicine field; 2. the statistical method depends on the occurrence frequency of medicines, and medicine combinations with less occurrence frequency and good curative effect are difficult to find.
Disclosure of Invention
The invention mainly aims to provide a learning method and a learning system for medical analysis by utilizing an algorithm model, so as to solve the problem that the distribution ratio and the drug-taking mode of the traditional Chinese medicine and the western medicine are difficult to analyze at present.
In order to achieve the above object, the present invention provides the following techniques:
a learning method for medical analysis by using an algorithm model comprises the following steps:
s1, inquiring the names of Chinese and western medicines for treatment according to the diseases;
s2, searching the components and the proportions of the medicines in a national medicine database through the names of Chinese and western medicines;
s3, finding out components with higher specific gravity and higher occurrence frequency from the components of the medicine through a traversal algorithm;
s4, analyzing which drug-taking mode has the heaviest proportion and which proportion and drug-taking mode have the best treatment effect through a traversing algorithm.
Further, in step S1, when the name of the drug for treating the disease is queried, the drug corresponding to the drug for treating the disease should be the main treatment efficacy, excluding the auxiliary treatment efficacy.
Further, in step S2, the steps include:
s20, judging whether the medicine is a traditional Chinese medicine or a western medicine according to the medicine name and the medicine category inquired in the association database;
s21, if the medicine is a traditional Chinese medicine, further judging whether the formula composition form of the medicine is a combination of a plurality of medicines in gram units or recording the components of the medicine in percentage form; if the combination is a combination of a plurality of medicines in gram units, the form needs to be converted into a percent form to record each component of the medicine;
s22, if western medicines are adopted, the Chinese names or the chemical formula names in the medicine components are required to be converted into the same form.
Further, in the step S3 and the step S4, the formulas of the medicines are analyzed, and when the weights are summarized, the traditional Chinese medicines and the western medicines are respectively counted.
Further, the traversal algorithm adopted in steps S3 and S4 is a multi-tree analysis method.
Further, in step S3, the medicine is a parent node, and the composition is a child node, and the node with the highest specific gravity and the node with the highest occurrence frequency are counted by traversing the entire multi-tree node.
Further, in step S4, the medicine is a parent node, the medicine-taking mode is a child node, and the node with the highest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node.
Further, step S5 is also included, training is carried out by using a recursion deep neural network model, so that a plurality of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula are obtained, and the best medicine-taking mode is obtained.
A learning system for medical analysis by utilizing an algorithm model comprises a medicine inquiry module, a medicine component analysis module, a calculation and statistics module and a neural network model training module;
the medicine inquiry module is used for inquiring the names of the Chinese and western medicines for treatment according to the diseases;
the medicine component analysis module is used for searching the composition components and the proportion of the medicines in the national medicine database through the medicine names;
the calculation and statistics module is used for calculating or counting the composition components and the proportion of the whole medicine through a traversal algorithm to obtain the component with the heaviest specific gravity and the component with the highest occurrence frequency; meanwhile, the mode with the heaviest specific gravity and the highest occurrence frequency in the drug feeding mode is counted;
the neural network model training module is used for obtaining a plurality of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine-taking mode.
Further, the medicine analysis and statistics system also comprises a storage module which is used for storing the whole medicine analysis and statistics process and forming an analysis and statistics model.
Compared with the prior art, the invention can bring the following technical effects:
1. not only the analysis of the prescription proportion and the drug feeding mode of the traditional Chinese medicine is realized, but also the analysis of the prescription proportion and the drug feeding mode of the western medicine field is realized;
2. according to the occurrence frequency and specific gravity of each component of the medicine variety, distinguishing the proportion of main medicinal materials or chemical substances for treating the disease from the curative effect;
3. meanwhile, the medicinal materials or chemical components with the highest specific gravity in the prescription are trained through a neural network model, and a plurality of groups of medicaments with the best curative effect for treating a certain disease are obtained through analysis.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the invention and are not to be construed as unduly limiting the invention. In the drawings:
FIG. 1 is a flow chart of a learning method for medical analysis using an algorithmic model in accordance with the present invention;
FIG. 2 is a block flow diagram of a learning system for medical analysis using an algorithmic model in accordance with the present invention;
in the figure: the system comprises a medicine inquiry module M10, a medicine component analysis module M20, a calculation and statistics module M30, a neural network model training module M40 and a storage module M50.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present invention, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present invention and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present invention will be understood by those of ordinary skill in the art according to the specific circumstances.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
Example 1
As shown in fig. 1 and 2, a learning method for medical analysis using an algorithm model includes the steps of:
s1, inquiring the names of Chinese and western medicines for treatment according to the diseases;
in step S1, when the name of the drug for treating the disease is queried, the drug corresponding to the drug for treating the disease should be the main treatment efficacy, excluding the drug with the auxiliary treatment efficacy.
S2, searching the components and the proportions of the medicines in a national medicine database through the names of Chinese and western medicines;
in step S2, the steps include:
s20, judging whether the medicine is a traditional Chinese medicine or a western medicine according to the medicine name and the medicine category inquired in the association database;
s21, if the medicine is a traditional Chinese medicine, further judging whether the formula composition form of the medicine is a combination of a plurality of medicines in gram units or recording the components of the medicine in percentage form; if the combination is a combination of a plurality of medicines in gram units, the form needs to be converted into a percent form to record each component of the medicine;
s22, if western medicines are adopted, the Chinese names or the chemical formula names in the medicine components are required to be converted into the same form.
S3, finding out components with higher specific gravity and higher occurrence frequency from the components of the medicine through a traversal algorithm;
in step S3, the medicine is a parent node, and the composition is a child node, and the node with the highest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node.
S4, analyzing which drug-taking mode has the heaviest proportion and which proportion and drug-taking mode have the best treatment effect through a traversing algorithm.
In step S4, the medicine is a father node, the medicine-taking mode is a child node, and the node with the heaviest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node.
And S3 and S4, analyzing the formula of the medicine, and respectively counting the traditional Chinese medicine and the western medicine when the weights are counted and summarized.
The traversal algorithm adopted in steps S3 and S4 is a multi-way tree analysis method.
And step S5, training by using a recurrent deep neural network model to obtain a plurality of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine-taking mode.
A learning system for medical analysis by using an algorithm model comprises a medicine inquiry module M10, a medicine component analysis module M20, a calculation and statistics module M30 and a neural network model training module M40;
the medicine inquiry module M10 is used for inquiring the names of the Chinese and western medicines for treatment according to the diseases;
the medicine component analysis module M20 is used for searching the composition components and the proportion of the medicine in the national medicine database through the medicine name;
the calculation and statistics module M30 is used for calculating or counting the composition components and the proportion of the whole medicine through a traversal algorithm to obtain the component with the heaviest proportion and the component with the highest occurrence frequency; meanwhile, the mode with the heaviest specific gravity and the highest occurrence frequency in the drug feeding mode is counted;
the neural network model training module M40 is used for obtaining a plurality of groups of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine-taking mode.
The system also comprises a storage module M50 for storing the whole drug analysis and statistics process to form an analysis and statistics model.
Example 2
As shown in fig. 1 and 2, a learning method for medical analysis using an algorithm model includes the steps of:
s1, inquiring the names of Chinese and western medicines for treatment according to the diseases;
in step S1, when the name of the drug for treating the disease is queried, the drug corresponding to the drug for treating the disease should be the main treatment efficacy, excluding the drug with the auxiliary treatment efficacy. The medicine for preventing excessive adjuvant treatment efficacy increases the calculation amount for the subsequent steps, affecting the accuracy of the calculation result, because the main component of the medicine for adjuvant treatment is not the composition of the important component for treating the disease.
S2, searching the components and the proportions of the medicines in a national medicine database through the names of Chinese and western medicines;
in step S2, the steps include:
s20, judging whether the medicine is a traditional Chinese medicine or a western medicine according to the medicine name and the medicine category inquired in the association database;
s21, if the medicine is a traditional Chinese medicine, further judging whether the formula composition form of the medicine is a combination of a plurality of medicines in gram units or recording the components of the medicine in percentage form; if the combination is a combination of a plurality of medicines in gram units, the form needs to be converted into a percent form to record each component of the medicine; the method is convenient for the subsequent algorithm statistical calculation, eliminates various metering modes and influences the final drug analysis result.
S22, if western medicines are adopted, the Chinese names or the chemical formula names in the medicine components are required to be converted into the same form. Preventing the error of the specific gravity metering statistics of the same substance due to the influence of various names of the same substance, and leading to the error of the final result.
S3, finding out components with higher specific gravity and higher occurrence frequency from the components of the medicine through a traversal algorithm;
in step S3, the medicine is a parent node, and the composition is a child node, and the node with the highest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node. When the best curative effect of the mixture ratio of the substances (namely, the best curative effect of the medicines) is required to be evaluated, the maximum value of the comprehensive value can be obtained through an assignment method by the proportion (namely, specific gravity) of the substances in the components of the medicines for treating certain diseases and the occurrence frequency of the substances in the medicines for treating certain diseases, wherein the occurrence frequency of the substances is 50%, and finally, the specific medicine is obtained.
S4, analyzing which drug-taking mode has the heaviest proportion and which proportion and drug-taking mode have the best treatment effect through a traversing algorithm.
In step S4, the medicine is a father node, the medicine-taking mode is a child node, and the node with the heaviest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node. When the treatment effect of which drug administration mode is the best to be assessed in the same step S3, the maximum value of the comprehensive value is finally obtained by an assignment method according to the proportion of the drug in the drug administration mode for treating a certain disease and the occurrence frequency of the drug in the drug administration mode for treating a certain disease, wherein the frequency is 50% respectively.
And S3 and S4, analyzing the formula of the medicine, and respectively counting the traditional Chinese medicine and the western medicine when the weights are counted and summarized. The traditional Chinese medicine is different from western medicine in that only a few medicinal materials of the traditional Chinese medicine can treat diseases, and other medicinal materials are auxiliary curative effects; the western medicines are more severely proportioned, and the fatal result is probably brought by excessive substances or different proportions of the western medicines, so that the western medicines are quite a lot of substances proved by experiments, are more difficult to calculate and count and have larger calculated amount. Preventing the core substances or medicinal materials in western medicines or Chinese medicines from being buried by big data statistics due to mixed statistics of the Chinese medicines and the western medicines.
The traversal algorithm adopted in steps S3 and S4 is a multi-way tree analysis method.
And step S5, training by using a recurrent deep neural network model to obtain a plurality of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine-taking mode. And (3) integrating the steps S3 and S4 to obtain the medicine with the best final treatment effect, wherein the curative effect of the mixture ratio of the substances is the best (namely, the curative effect of the medicine is the best), the curative effect of the administration mode is the best, and the administration modes respectively account for 70% and 30% by an assignment method to obtain the best administration mode and medicine for treating the diseases. The method comprises the following steps: western medicine with rapid effect for treating symptoms and slow effect for treating root causes.
A learning system for medical analysis by using an algorithm model comprises a medicine inquiry module M10, a medicine component analysis module M20, a calculation and statistics module M30 and a neural network model training module M40;
the medicine inquiry module M10 is used for inquiring the names of the Chinese and western medicines for treatment according to the diseases;
the medicine component analysis module M20 is used for searching the composition components and the proportion of the medicine in the national medicine database through the medicine name;
the calculation and statistics module M30 is used for calculating or counting the composition components and the proportion of the whole medicine through a traversal algorithm to obtain the component with the heaviest proportion and the component with the highest occurrence frequency; meanwhile, the mode with the heaviest specific gravity and the highest occurrence frequency in the drug feeding mode is counted;
the neural network model training module M40 is used for obtaining a plurality of groups of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine-taking mode.
The system also comprises a storage module M50 for storing the whole drug analysis and statistics process to form an analysis and statistics model.
Compared with the prior art, the invention can bring the following technical effects:
1. not only the analysis of the prescription proportion and the drug feeding mode of the traditional Chinese medicine is realized, but also the analysis of the prescription proportion and the drug feeding mode of the western medicine field is realized;
2. according to the occurrence frequency and specific gravity of each component of the medicine variety, distinguishing the proportion of main medicinal materials or chemical substances for treating the disease from the curative effect;
3. meanwhile, the medicinal materials or chemical components with the highest specific gravity in the prescription are trained through a neural network model, and a plurality of groups of medicaments with the best curative effect for treating a certain disease are obtained through analysis.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A learning method for medical analysis by using an algorithm model is characterized by comprising the following steps:
s1, inquiring the names of Chinese and western medicines for treatment according to the diseases;
s2, searching the components and the proportions of the medicines in a national medicine database through the names of Chinese and western medicines;
s3, finding out components with higher specific gravity and higher occurrence frequency from the components of the medicine through a traversal algorithm;
s4, analyzing which drug-taking mode has the heaviest proportion and which proportion and drug-taking mode have the best treatment effect through a traversing algorithm;
s5, training by using a recursion deep neural network model to obtain a plurality of groups of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the highest specific gravity of the medicine formula, and simultaneously obtaining the best medicine feeding mode;
in step S1, when the name of the drug for treating the disease is queried, the drug corresponding to the drug for treating the disease should have main treatment efficacy, excluding the drug with auxiliary treatment efficacy;
in step S2, the steps include:
s20, judging whether the medicine is a traditional Chinese medicine or a western medicine according to the medicine name and the medicine category inquired in the association database;
s21, if the medicine is a traditional Chinese medicine, further judging whether the formula composition form of the medicine is a combination of a plurality of medicines in gram units or recording the components of the medicine in percentage form; if the combination is a combination of a plurality of medicines in gram units, the form needs to be converted into a percent form to record each component of the medicine;
s22, if western medicines are adopted, the Chinese names or chemical formula names in the medicine components are required to be converted into the same form;
in step S3, the medicine is a father node, the composition is a child node, and the node with the heaviest proportion and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node;
in step S4, the medicine is a father node, the medicine-taking mode is a child node, and the node with the heaviest specific gravity and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node.
2. The learning method for medical analysis by using an algorithm model according to claim 1, wherein the formulation analysis of the medicines in steps S3 and S4 is performed by counting the Chinese medicines and western medicines respectively when the weights are summarized.
3. The learning system for medical analysis by utilizing the algorithm model is characterized by comprising a medicine query module, a medicine component analysis module, a calculation and statistics module and a neural network model training module;
the medicine inquiry module is used for inquiring the names of the Chinese and western medicines for treatment according to the diseases;
the medicine component analysis module is used for searching the composition components and the proportion of the medicines in the national medicine database through the medicine names;
the calculation and statistics module is used for calculating or counting the composition components and the proportion of the whole medicine through a traversal algorithm to obtain the component with the heaviest specific gravity and the component with the highest occurrence frequency; meanwhile, the mode with the heaviest specific gravity and the highest occurrence frequency in the drug feeding mode is counted;
the neural network model training module is used for obtaining a plurality of groups of medicines with the best curative effect for treating a certain disease, and medicinal materials or chemical components with the heaviest specific gravity of the medicine formula, and obtaining the best medicine feeding mode;
in the medicine inquiry module, when the name of the medicine for treating the disease is inquired, the corresponding medicine for treating the disease is the medicine with main treatment efficacy and auxiliary treatment efficacy is excluded;
in a drug ingredient analysis module, comprising:
s20, judging whether the medicine is a traditional Chinese medicine or a western medicine according to the medicine name and the medicine category inquired in the association database;
s21, if the medicine is a traditional Chinese medicine, further judging whether the formula composition form of the medicine is a combination of a plurality of medicines in gram units or recording the components of the medicine in percentage form; if the combination is a combination of a plurality of medicines in gram units, the form needs to be converted into a percent form to record each component of the medicine;
s22, if western medicines are adopted, the Chinese names or chemical formula names in the medicine components are required to be converted into the same form;
in the calculation and statistics module, the medicine is a father node, the composition is a child node, and the node with the heaviest proportion and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node;
in the calculation and statistics module, the medicine is a father node, the medicine-taking mode is a child node, and the node with the heaviest proportion and the node with the highest occurrence frequency are counted by traversing the whole multi-tree node.
4. A learning system for medical analysis using an algorithmic model as claimed in claim 3, further comprising a storage module for storing the whole drug analysis statistical process to form an analysis statistical model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021484.XA CN112133382B (en) | 2020-09-24 | 2020-09-24 | Learning method and system for medical analysis by using algorithm model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011021484.XA CN112133382B (en) | 2020-09-24 | 2020-09-24 | Learning method and system for medical analysis by using algorithm model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112133382A CN112133382A (en) | 2020-12-25 |
| CN112133382B true CN112133382B (en) | 2024-02-20 |
Family
ID=73839794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011021484.XA Active CN112133382B (en) | 2020-09-24 | 2020-09-24 | Learning method and system for medical analysis by using algorithm model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112133382B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102188720A (en) * | 2010-03-08 | 2011-09-21 | 大连大学 | Method for studying base of medicinal effect materials |
| CN104794341A (en) * | 2015-04-20 | 2015-07-22 | 南京大学 | Traditional Chinese medicine and western medicine combined medication contraindication early-warning system |
| CN104820775A (en) * | 2015-04-17 | 2015-08-05 | 南京大学 | Discovery method of core drug of traditional Chinese medicine prescription |
| CN107423347A (en) * | 2017-05-17 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of Chinese medicine preparation analysis of effective component method and terminal device |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
| CN110289106A (en) * | 2019-06-28 | 2019-09-27 | 淮阴工学院 | A method of effect, which is analyzed, from Chinese medicine compound prescription corresponds to Chinese medicine and its pharmacological property compatibility relationship |
| CN110544536A (en) * | 2019-07-26 | 2019-12-06 | 山西中医药大学 | Lung cancer treatment core prescription discovery method based on data mining analysis method |
| CN111180045A (en) * | 2019-11-25 | 2020-05-19 | 浙江大学 | Method for mining relation between medicine pairs and efficacy from prescription information |
| CN111599487A (en) * | 2020-05-12 | 2020-08-28 | 成都睿明医疗信息技术有限公司 | Traditional Chinese medicine compatibility assistant decision-making method based on correlation analysis |
-
2020
- 2020-09-24 CN CN202011021484.XA patent/CN112133382B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102188720A (en) * | 2010-03-08 | 2011-09-21 | 大连大学 | Method for studying base of medicinal effect materials |
| CN104820775A (en) * | 2015-04-17 | 2015-08-05 | 南京大学 | Discovery method of core drug of traditional Chinese medicine prescription |
| CN104794341A (en) * | 2015-04-20 | 2015-07-22 | 南京大学 | Traditional Chinese medicine and western medicine combined medication contraindication early-warning system |
| CN107423347A (en) * | 2017-05-17 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of Chinese medicine preparation analysis of effective component method and terminal device |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
| CN110289106A (en) * | 2019-06-28 | 2019-09-27 | 淮阴工学院 | A method of effect, which is analyzed, from Chinese medicine compound prescription corresponds to Chinese medicine and its pharmacological property compatibility relationship |
| CN110544536A (en) * | 2019-07-26 | 2019-12-06 | 山西中医药大学 | Lung cancer treatment core prescription discovery method based on data mining analysis method |
| CN111180045A (en) * | 2019-11-25 | 2020-05-19 | 浙江大学 | Method for mining relation between medicine pairs and efficacy from prescription information |
| CN111599487A (en) * | 2020-05-12 | 2020-08-28 | 成都睿明医疗信息技术有限公司 | Traditional Chinese medicine compatibility assistant decision-making method based on correlation analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112133382A (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kleyer et al. | Trait correlation network analysis identifies biomass allocation traits and stem specific length as hub traits in herbaceous perennial plants | |
| Vassiliev et al. | Consensus drug design using IT microcosm | |
| CN111613297B (en) | Method, system and device for establishing traditional Chinese medicine action mechanism model based on network pharmacology | |
| CN109859815A (en) | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system | |
| CN111785395B (en) | Monitoring method, system, equipment and storage medium for clinical application of antibacterial drugs | |
| CN107391941A (en) | A kind of method and system for improving compliance | |
| CN110223784A (en) | Clinical test patient's matching process | |
| CN108363774A (en) | A kind of drug relationship sorting technique based on multilayer convolutional neural networks | |
| CN107220484B (en) | A kind of Chinese medicine recipe data analysis mining system | |
| CN111951979A (en) | Drug information standardization method, drug information standardization and retrieval platform and device | |
| CN113935608A (en) | Evaluation method and device for community endowment service facilities | |
| CN110246550B (en) | Drug combination prediction method based on drug similarity network data | |
| WO2022178947A1 (en) | Monitoring and early warning method and apparatus based on multiple dimensions, and device and storage medium | |
| CN105373911A (en) | Traditional Chinese medicine prescription dispensing sequence control system | |
| CN112133382B (en) | Learning method and system for medical analysis by using algorithm model | |
| Kumari | Regional disparity in Uttar Pradesh and Bihar: A disaggregated level analysis | |
| CN106709231A (en) | Method for evaluating influences of drugs on inter-module relations in biomolecule network | |
| CN111667898B (en) | Classification processing method of medical medication rule information | |
| Chazard et al. | Detection of adverse drug events: proposal of a data model | |
| CN112185544A (en) | Semantic-based family medical consultation decision support method | |
| He et al. | Extended analysis of topological-pattern-based ontology enrichment | |
| CN115691751A (en) | Traditional Chinese medicine prescription screening method and system based on diagnosis and treatment experience and intelligent learning | |
| Florentinus et al. | Linking community pharmacy dispensing data to prescribing data of general practitioners | |
| CN113506592A (en) | Mechanism analysis method of traditional Chinese medicine for treating chronic bronchitis | |
| CN110245272A (en) | A kind of blood disease case database generation system |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 801 and 802, Building 5, Jieyuan Financial City, No. 55 Andemen Street, Yuhuatai District, Nanjing City, Jiangsu Province, 210012 Applicant after: Nanjing Fantai Digital Technology Research Institute Co.,Ltd. Address before: 6 / F, building 10 (building E), yunmi City, 19 ningshuang Road, Yuhuatai District, Nanjing City, Jiangsu Province, 210041 Applicant before: Nanjing Zhongai artificial intelligence and Life Sciences Research Institute Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |