CN110459321B - Traditional Chinese medicine auxiliary diagnosis system based on syndrome element - Google Patents
Traditional Chinese medicine auxiliary diagnosis system based on syndrome element Download PDFInfo
- Publication number
- CN110459321B CN110459321B CN201910768831.6A CN201910768831A CN110459321B CN 110459321 B CN110459321 B CN 110459321B CN 201910768831 A CN201910768831 A CN 201910768831A CN 110459321 B CN110459321 B CN 110459321B
- Authority
- CN
- China
- Prior art keywords
- syndrome
- chinese medicine
- traditional chinese
- patient
- disease
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Abstract
The invention discloses a traditional Chinese medicine auxiliary diagnosis system based on syndrome elements, which comprises: the database is used for storing a traditional Chinese medicine knowledge map, and the traditional Chinese medicine knowledge map comprises mapping relations from symptoms to syndrome elements, from syndrome elements to traditional Chinese medicine syndrome types, from syndrome elements to syndrome elements types, from traditional Chinese medicine syndrome types and from western medicine diagnosis to prescription names, prescription names and basic information of patients to prescription traditional Chinese medicine components and dosage; the patient information acquisition module is used for acquiring basic information, symptoms and western medicine diagnosis provided by the patient; the traditional Chinese medicine syndrome deducing module deduces the traditional Chinese medicine syndrome of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph; and the formula latent medicine module recommends a traditional Chinese medicine formula according to the traditional Chinese medicine knowledge map and the basic information of the patient, the traditional Chinese medicine syndrome type and the Western medicine diagnosis. By introducing the traditional Chinese medicine knowledge graph, the invention can comprehensively consider factors such as symptoms, basic information of patients, western medicine diagnosis and the like when the traditional Chinese medicine is recommended, and provide a more reasonable recommendation result.
Description
Technical Field
The invention belongs to the technical field of medical information data processing, and particularly relates to a traditional Chinese medicine auxiliary diagnosis system based on syndrome elements.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The traditional Chinese medicine has great advantages in the aspects of health preservation and health care, preventive treatment service, infectious disease prevention and treatment and special rehabilitation service, and especially can play a unique role in preventing and treating common diseases, frequently encountered diseases and chronic diseases. At the basic level, however, doctors of traditional Chinese medicine are still in a very short supply, especially in vast rural areas in China, medical resources are deficient, the number of doctors is seriously insufficient compared with the number of people to be served, and in addition, the medical skill of the village doctor is generally low, and the knowledge of the traditional Chinese medicine is very little. Therefore, the development of the clinical auxiliary diagnosis system of traditional Chinese medicine has great significance for solving the problem of insufficient quantity of primary traditional Chinese medicine doctors or assisting doctors to develop medical behaviors based on traditional Chinese medicine.
According to the inventor, various traditional Chinese medicine clinical auxiliary diagnosis systems at the present stage do not play a great role in the traditional Chinese medicine clinical practice, and the following problems mainly exist:
most systems only infer symptoms, and do not deeply combine with the theory of traditional Chinese medicine;
some systems carry out traditional Chinese medicine syndrome differentiation and typing through syndrome elements, but excessively depend on a mathematical method and do not combine clinical experience of traditional Chinese medicine doctors;
these systems can recognize symptoms described by traditional Chinese medicine terms, but cannot recognize colloquial symptoms, for example, the systems can understand that "eat less and eat and stay", but cannot understand that "I do not want to eat, do not speak";
moreover, the prescriptions developed by these systems are not combined with western medicine diagnosis of patients, and the prescriptions lack pertinence.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a traditional Chinese medicine auxiliary diagnosis system based on a syndrome differentiation agent, which can identify the colloquial symptom description of a patient, differentiate the type based on the syndrome differentiation agent and the practical experience of traditional Chinese medicine clinical according to the description of the patient, and develop a prescription by combining the western medicine diagnosis of the patient.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
a syndrome-based traditional Chinese medicine auxiliary diagnosis system comprises:
the database is used for storing a traditional Chinese medicine knowledge map, and the traditional Chinese medicine knowledge map comprises mapping relations from symptoms to syndrome elements, from syndrome elements to traditional Chinese medicine syndrome types, from syndrome elements to syndrome elements types, from traditional Chinese medicine syndrome types and from western medicine diagnosis to prescription names, prescription names and basic information of patients to prescription traditional Chinese medicine components and dosage;
the patient information acquisition module is used for acquiring basic information, symptoms and western medicine diagnosis provided by the patient;
the traditional Chinese medicine syndrome deducing module deduces the traditional Chinese medicine syndrome of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph;
and the formula latent medicine module recommends a traditional Chinese medicine formula according to the traditional Chinese medicine knowledge map and the basic information of the patient, the traditional Chinese medicine syndrome type and the Western medicine diagnosis.
One or more embodiments provide a syndrome-based chinese medical-assisted diagnostic system, including:
the client is used for acquiring basic information, symptoms and western medicine diagnosis provided by the patient and sending the basic information, symptoms and western medicine diagnosis to the server;
the server stores a traditional Chinese medicine knowledge map, wherein the traditional Chinese medicine knowledge map comprises mapping relations from symptoms to syndrome elements, from syndrome elements to traditional Chinese medicine syndrome types, from syndrome elements to syndrome elements types, from traditional Chinese medicine syndrome types and from western medicine diagnosis to prescription names, prescription names and basic information of patients to prescription traditional Chinese medicine components and dosage; after receiving the information provided by the patient and sent by the client, the following operations are carried out:
deducing the traditional Chinese medicine syndrome type of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph; according to the basic information of the patient, the traditional Chinese medicine syndrome type and the western medicine diagnosis, the traditional Chinese medicine prescription is recommended.
The above one or more technical solutions have the following beneficial effects:
the invention provides a traditional Chinese medicine auxiliary diagnosis system based on syndrome element, wherein a traditional Chinese medicine knowledge map is introduced into the system, and the mapping relation from symptom to syndrome element, from syndrome element to traditional Chinese medicine type, from syndrome element to syndrome element type, from traditional Chinese medicine syndrome type to traditional Chinese medicine formula name, from traditional Chinese medicine formula name and from patient basic information (sex, age and the like) to traditional Chinese medicine components and dosage of the formula is recorded in the knowledge map, so that the system can be combined with traditional Chinese medicine clinical experience and traditional Chinese medicine theory based on syndrome element, and the system is combined with the patient basic information and the western medicine diagnosis on the basis of the symptom provided by a patient to comprehensively provide a prescription suggestion.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a block diagram of a syndrome-based aided diagnosis system of TCM in accordance with one or more embodiments of the present invention;
FIG. 2 is a schematic diagram of a portion of a TCM knowledge mapping;
FIG. 3 is a schematic diagram of the map structure of the "symptom → viscin" part.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Interpretation of terms:
evidence element: the minimum unit for describing body lesions in the theory of traditional Chinese medicine is divided into disease property syndrome element and disease location syndrome element, wherein the disease property syndrome element refers to lesions (such as yin deficiency and yang deficiency) appearing in the body, and the disease location syndrome element refers to the sites (such as kidney) appearing in the lesions;
the syndrome types of traditional Chinese medicine are: the traditional Chinese medicine is equivalent to the diagnosis of western medicine, and consists of one or more disease symptoms combined (or not combined) with one (or more) disease symptom elements, for example, the syndrome type 'kidney yin-yang deficiency syndrome' consists of disease symptoms 'yin deficiency', 'yang deficiency' and disease symptom element 'kidney', and the syndrome type 'yin deficiency' consists of disease symptoms 'yin deficiency'. Each property syndrome corresponds to a single syndrome type only containing the property syndrome, for example, the single syndrome type corresponding to "qi deficiency" is "qi deficiency syndrome";
typical symptoms of the syndrome: each symptom corresponds to one or more syndrome elements, and if a certain symptom only corresponds to one syndrome element (disease property or disease position), the symptom is called as a typical symptom of the syndrome element.
Example one
The embodiment discloses a traditional Chinese medicine auxiliary diagnosis system based on syndrome elements, which comprises:
and the database is used for storing the traditional Chinese medicine knowledge map.
The nodes of the knowledge-graph are divided into a plurality of categories, including: symptoms, syndrome category, traditional Chinese medicine syndrome type, western medicine diagnosis, prescription name, patient information, and ingredients and dosage of traditional Chinese medicines in the prescription; edges are used to represent the correspondence between these categories, including: symptom → provenance, provenance → Chinese traditional syndrome type, provenance → provenance type, Chinese traditional syndrome type + Western diagnosis → name of prescription (Chinese traditional syndrome type combined with Western diagnosis), name of prescription + patient information (e.g. sex, age) → ingredients and amounts of the prescription (the ingredients and amounts of the prescription are adjusted according to the patient's basic information). The map is schematically shown in fig. 2, and fig. 3 is a map structure diagram of "symptom → viscin".
The knowledge-graph is stored in graph database neo4j in the form of a directed graph.
The patient information acquisition module is used for acquiring and storing the basic information, symptoms and western medicine diagnosis provided by the patient; wherein the basic information includes but is not limited to gender, age, etc. It will be appreciated by those skilled in the art that the patient may provide the patient's information through text input or voice input or other existing input methods.
And the patient information processing module is used for carrying out standardization processing on the acquired patient information, converting the symptom sentences into symptoms stored in the traditional Chinese medicine knowledge graph and obtaining the symptom set of the patient. The method specifically comprises the following steps:
(1) the method comprises the following steps of recording a set of all symptoms related in a traditional Chinese medicine knowledge graph as a symptom dictionary, recording symptom sentences input by a patient as meta sentences, and performing punctuation removal processing on the meta sentences to obtain combined sentences;
(2) segmenting words of the closed sentences by using a segmentation tool (such as a Chinese word segmentation tool), wherein the segmentation result is called an initial segmentation set;
(3) for each word in the initial word segmentation set, inquiring in a symptom dictionary, and if the word can be inquired, incorporating the word into the symptom set of the patient; the word can not be found and is included into a word set to be processed;
(4) for each word i in the "to-be-processed participle set", finding the punctuation where it is located in the meta-sentence, converting the punctuation into pinyin (only pinyin letters without tones), finding the symptom of the pinyin with the highest score among the pinyin sets of all symptoms contained in the symptom dictionary by using a search matching tool (for example, Lucene combined with BM25), and incorporating the symptom as the recognition result of i into the symptom set of the patient. The symptoms in the patient symptom set are arranged in order of appearance in the patient input information.
And the traditional Chinese medicine syndrome deducing module deduces the traditional Chinese medicine syndrome of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph. The method specifically comprises the following steps:
(1) inferring provenance based on symptoms in a symptom set of the patient according to a knowledge graph of traditional Chinese medicine;
in this embodiment, it is assumed that the symptom set of the patient includes 6 symptoms (i.e., 6 symptoms are identified from the patient information): z1, Z2, Z3, Z4, Z5 and Z6, and according to the knowledge graph of the traditional Chinese medicine, the corresponding syndrome elements of each symptom are as follows:
evidence element corresponding to Z1: e1, b 1;
evidence element corresponding to Z2: e2, e8, b2, b 8;
evidence element corresponding to Z3: e2, e3, e4, b2, b3, b 4;
evidence element corresponding to Z4: e1, e6, b1, b 6;
evidence element corresponding to Z5: e6, e7, b6, b 7;
evidence element corresponding to Z6: e7, b 7;
wherein e1-e7 is pathopoiesia syndrome, and b1-b7 is pathopoiesia syndrome.
(2) And (3) deducing the disease condition syndrome and the disease location syndrome of the patient according to the syndrome determined in the step (1). Wherein the deduction process of the disease condition syndrome comprises the following steps:
checking whether typical symptoms of certain disease symptoms exist in all symptoms (namely the symptoms only correspond to one symptom, such as Z1 and Z6 in the example), and if not, entering a step II;
if yes, checking whether the disease property syndrome corresponding to the typical symptom can cover all symptoms, if so, taking the syndrome corresponding to the typical symptom as an output result of the disease property syndrome of the patient, and if not, entering the step II;
in this embodiment, the disease symptoms e1 and e7 corresponding to Z1 and Z6 cannot cover the symptoms Z2 and Z3, so step two is performed.
Determining the disease condition element with the most occurrence frequency in the disease condition elements except the disease condition element corresponding to the typical symptom, and if only one disease condition element with the most occurrence frequency exists, taking the disease condition element and the disease condition element (if any) corresponding to the typical symptom as the output result of the disease condition element of the patient;
if more than one disease property element appears most frequently, entering the step three;
in this embodiment, the number of occurrences of the disease property element e2 and e6 is the largest, and is 2, so step three is performed.
Thirdly, selecting the disease property element with the most advanced appearance sequence from a plurality of disease property elements with the most frequent appearance according to the appearance sequence of symptoms, if the disease property element appears in the elements corresponding to the same symptom, the appearance sequence is the same, the disease property element with the most advanced appearance sequence can not be found, and only the disease property element (if any) corresponding to the typical symptom is taken as the output result of the disease property element of the patient;
if the disease viseme with the highest appearance sequence can be found, the disease viseme and the disease viseme (if any) corresponding to the typical symptom are taken as the output result of the disease viseme of the patient.
In this embodiment, the disease condition element e2 appears in the order before e6, so the output results of the disease condition elements of the patient are e1, e2 and e 7.
If no disease condition element can be found according to the step I-III, outputting 'the input symptom can not determine the syndrome type, and please input more symptoms or input the symptoms again' to prompt the patient; and after receiving the symptoms input again by the patient through the patient information acquisition module, performing disease syndrome inference again.
The disease location syndrome is carried out on the premise of deducing the disease location syndrome, and the deduction process comprises the following steps:
checking whether typical symptoms of certain disease location syndrome elements exist in all symptoms (namely the symptoms only correspond to one disease location syndrome element, such as Z1 and Z6 in the example), and if the typical symptoms do not exist, entering a step II;
if yes, checking whether the syndrome element corresponding to the typical symptom can cover all symptoms, if so, taking the syndrome element corresponding to the typical symptom as an output result of the syndrome element of the patient, and if not, entering the step II;
in this embodiment, the disease location syndrome elements b1 and b7 corresponding to Z1 and Z6 cannot cover the symptoms Z2 and Z3, so step two is performed.
Determining the disease location syndrome elements with the most occurrence times in the disease location syndrome elements except the disease location syndrome elements corresponding to the typical symptoms, and if only one disease location syndrome element with the most occurrence times exists, taking the disease location syndrome element and the disease location syndrome element (if any) corresponding to the typical symptoms as the output result of the disease location syndrome element of the patient;
if more than one disease location syndrome element appears most frequently, entering the step three;
in this embodiment, the number of occurrences of the syndrome elements b2 and b6 is the largest, 2, so step three is performed.
Thirdly, selecting the disease location syndrome element with the most advanced appearance sequence from a plurality of disease location syndrome elements with the most frequent appearance according to the appearance sequence of symptoms, if the disease location syndrome elements appear in the syndrome elements corresponding to the same symptoms, the appearance sequence is the same, the disease location syndrome element with the most advanced appearance sequence cannot be found, and only taking the disease location syndrome element (if the disease location syndrome element exists) corresponding to the typical symptom as the output result of the disease location syndrome element of the patient;
if the disease location syndrome element with the most advanced appearance sequence can be found, the disease location syndrome element and the disease location syndrome element (if any) corresponding to the typical symptom are used as the output result of the disease location syndrome element of the patient.
In this embodiment, the disease syndrome element b2 appears earlier than b6, so the output results of the disease syndrome elements of the patient are b1, b2 and b 7.
If no pathopoiesia syndrome can be found according to the steps (i) - (iii), the method enters the step (3), and the pathopoiesia syndrome result of the patient is an empty set.
In this embodiment, the output results of the patient syndrome elements are b1, b2, and b 7.
(3) And (3) deducing candidate traditional Chinese medicine syndrome types according to the disease syndrome deduced in the step (2).
The putative provenance is as follows:
and (3) a disease syndrome set E: e1, e2, e3, e 4;
syndrome set B: b1, b2, b 3;
inference principle: selecting the syndrome with the least number to cover the disease syndrome deduced in all steps (301)
Finding the traditional Chinese medicine syndrome in the knowledge graph, wherein the disease property and syndrome elements corresponding to the syndrome are completely equal to the following components: if such syndrome types (possibly more than one) can be found, outputting the syndrome types; if the information cannot be found, the step II is carried out;
searching two traditional Chinese medicine syndrome types in the knowledge graph, and meeting the following conditions: the union of their corresponding disease markers is exactly equal to [ note: if the syndrome type combination (possibly more than one combination) can be found, outputting the syndrome type combinations; if the Chinese medicine syndrome type combination meeting the conditions cannot be found in the step two, the step three is carried out;
thirdly, outputting the single traditional Chinese medicine syndrome type corresponding to each disease property syndrome element.
(4) Deducing the most appropriate traditional Chinese medicine syndrome from the candidate traditional Chinese medicine syndrome obtained in the step (3) by combining the syndrome elements deduced in the step (2); the method specifically comprises the following steps:
finding out the corresponding morbid syndrome elements of the candidate traditional Chinese medicine syndrome types obtained in the step (3) according to a traditional Chinese medicine knowledge graph.
Suppose that the evidence derived in step (2) is as follows:
and (3) a disease syndrome set E: e1, e2, e3, e 4;
syndrome set B: b1, b2, b 3;
selecting the corresponding syndrome set of the disease location syndrome as the combination of the syndrome sets of the B subsets of the candidate traditional Chinese medicine syndromes deduced in the step (3). For example, suppose that five sets of syndrome combinations are inferred in step (3), which are:
syndrome type combination G1: b1, b2, b 3;
syndrome type combination G2: b1, b2, b 4;
syndrome type combination G3: b2, b 3;
syndrome type combination G4, b1, b 4;
syndrome type combination G5 is empty set;
since the syndrome set B includes B1, B2, and B3, the syndrome types that meet the condition are combined into three groups, G1, G3, and G5.
Finding out the syndrome type combination with the most number of corresponding syndrome type elements in the candidate syndrome type combinations G1, G3 and G5, if the syndrome type combination with the most number is only one, outputting the syndrome type combination, and if the found syndrome type combinations are more than one group, optionally outputting one group.
And the formula latent medicine module is used for preparing the formula latent medicine for the patient according to the traditional Chinese medicine knowledge map through the symptoms of the patient, the traditional Chinese medicine syndrome type and the western medicine diagnosis. The specific implementation steps are as follows:
according to the traditional Chinese medicine syndrome type deduced by the traditional Chinese medicine syndrome type deduction module, the name, the medicine components and the dosage of a traditional Chinese medicine prescription are given according to a traditional Chinese medicine knowledge graph by combining the basic information (such as sex and age) of the patient and the Western diagnosis acquired by the patient information acquisition module.
Example two
The present embodiment aims to provide a syndrome-based auxiliary diagnostic system for chinese medicine, which includes:
the client is used for acquiring basic information, symptoms and western medicine diagnosis provided by the patient and sending the basic information, symptoms and western medicine diagnosis to the server;
the server stores a traditional Chinese medicine knowledge map, wherein the traditional Chinese medicine knowledge map comprises mapping relations from symptoms to syndrome elements, from syndrome elements to traditional Chinese medicine syndrome types, from syndrome elements to syndrome elements types, from traditional Chinese medicine syndrome types and from western medicine diagnosis to prescription names, prescription names and basic information of patients to prescription traditional Chinese medicine components and dosage; after receiving the information provided by the patient and sent by the client, the following operations are carried out:
converting symptoms provided by a patient into symptoms stored in a knowledge graph of traditional Chinese medicine to obtain a symptom set of the patient;
deducing the traditional Chinese medicine syndrome type of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph; according to the basic information of the patient, the traditional Chinese medicine syndrome type and the western medicine diagnosis, the traditional Chinese medicine prescription is recommended.
The specific implementation method related to the second embodiment corresponds to the first embodiment, and reference may be made to the relevant description part of the first embodiment.
One or more of the above embodiments have the following technical effects:
the invention provides a traditional Chinese medicine auxiliary diagnosis system based on syndrome element, wherein a traditional Chinese medicine knowledge map is introduced into the system, and the mapping relation from symptom to syndrome element, from syndrome element to traditional Chinese medicine type, from syndrome element to syndrome element type, from traditional Chinese medicine syndrome type to traditional Chinese medicine formula name, from traditional Chinese medicine formula name and from patient basic information (sex, age and the like) to traditional Chinese medicine components and dosage of the formula is recorded in the knowledge map, so that the system can be combined with traditional Chinese medicine clinical experience and traditional Chinese medicine theory based on syndrome element, and the system is combined with the patient basic information and the western medicine diagnosis on the basis of the symptom provided by a patient to comprehensively provide a prescription suggestion.
The system can also identify the oral-speaking symptom description of the patient to the symptom, and after the description of the patient is received, the oral-speaking symptom description is processed by a natural language processing method, so that the symptom in the oral-speaking description corresponds to the standardized expression in the knowledge graph of the traditional Chinese medicine, the system has strong expression identification capability to the patient, and the pertinence of the recommended prescription is stronger.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (1)
1. A syndrome-based traditional Chinese medicine auxiliary diagnosis system is characterized by comprising:
the database is used for storing a traditional Chinese medicine knowledge map, and the traditional Chinese medicine knowledge map comprises mapping relations from symptoms to syndrome elements, from syndrome elements to traditional Chinese medicine syndrome types, from syndrome elements to syndrome elements types, from traditional Chinese medicine syndrome types and from western medicine diagnosis to prescription names, prescription names and basic information of patients to prescription traditional Chinese medicine components and dosage;
the patient information acquisition module is used for acquiring basic information, symptoms and western medicine diagnosis provided by the patient;
the traditional Chinese medicine syndrome deducing module deduces the traditional Chinese medicine syndrome of the patient based on the symptoms of the patient according to the traditional Chinese medicine knowledge graph;
the formula latent medicine module recommends a traditional Chinese medicine formula according to the traditional Chinese medicine knowledge map and the basic information of the patient, the traditional Chinese medicine syndrome type and the western medicine diagnosis;
the nodes in the traditional Chinese medicine knowledge graph are used for representing a plurality of categories: symptoms, syndrome, traditional Chinese medicine syndrome type, traditional Chinese medicine syndrome type and western medicine diagnosis, name of prescription, patient information, prescription components and dosage; edges are used to represent the correspondence between these categories;
the system also comprises a patient information processing module used for converting the symptoms provided by the patient into the symptoms stored in the traditional Chinese medicine knowledge graph to obtain a symptom set of the patient;
converting the symptoms provided by the patient into symptoms stored in the knowledge-graph of traditional Chinese medicine specifically comprises:
extracting all symptoms related to the knowledge graph of the traditional Chinese medicine to form a symptom dictionary;
sequentially carrying out punctuation removal and word segmentation on symptom sentences provided by a patient to obtain an initial word segmentation set;
for each word in the initial word segmentation set, inquiring in a symptom dictionary, and if the word can be inquired, writing the word into the symptom set of the patient; if the word can not be found, writing the word into a word set to be processed;
for each word in the word segmentation set to be processed, determining a punctuation where the word is located in a symptom sentence provided by a patient, converting the punctuation into pinyin, searching for symptoms in a symptom dictionary based on pinyin similarity, obtaining a recognition result of the word, and writing the recognition result into the symptom set of the patient; the symptoms in the patient's symptom set are arranged in the order in which they appear in the patient-provided symptom statement;
inferring the traditional Chinese medicine syndrome type of the patient includes:
obtaining a syndrome corresponding to each symptom based on the symptoms provided by the patient according to a traditional Chinese medicine knowledge graph;
deducing the disease condition syndrome and the disease location syndrome of the patient according to the coverage degree, the occurrence frequency and the occurrence sequence of the syndrome to symptoms;
deducing candidate traditional Chinese medicine syndrome types according to the deduced disease syndrome elements;
deducing the most appropriate traditional Chinese medicine syndrome from the candidate traditional Chinese medicine syndrome by combining the deduced syndrome elements;
inferring pathological condition of the patient comprises:
inquiring whether a typical symptom corresponding to only one disease syndrome exists or not, and if not, entering a step II; if yes, checking whether the disease property syndrome elements can cover all symptoms, if yes, writing the disease property syndrome elements into a disease property syndrome element set of the patient, and if not, entering a step II;
determining the disease viseme with the most occurrence frequency in the residual disease visemes, and writing the disease viseme into the disease viseme set of the patient if only one disease viseme with the most occurrence frequency exists; if more than one disease property element appears most frequently, entering the step three;
checking whether the occurrence sequence of the disease visemes exists, if so, writing the disease visemes with the front occurrence sequence into the disease viseme set of the patient;
if no disease syndrome can be found according to the step I-III, a prompt for supplementing the symptom description is output;
upon inferring a pathognomone for the patient, further performing an inference of a pathognomone for the patient, comprising:
firstly, inquiring whether a typical symptom corresponding to only one disease location syndrome exists or not, and if not, entering a second step; if yes, checking whether the disease location syndrome elements can cover all symptoms, if so, writing the disease location syndrome elements into a disease location syndrome element set of the patient, and if not, entering a step II;
determining the disease location syndrome element with the most occurrence frequency in the rest disease location syndrome elements, and writing the disease location syndrome element into the disease location syndrome element set of the patient if only one disease location syndrome element with the most occurrence frequency exists; if more than one disease location syndrome element appears most frequently, entering the step three;
checking whether the occurrence sequence of the disease location syndrome elements exists, if so, writing the disease location syndrome elements with the front occurrence sequence into the disease location syndrome element set of the patient;
if no disease location syndrome element can be found according to the steps I-III, the disease location syndrome element set of the patient is a null set;
inferring candidate TCM syndromes includes:
searching traditional Chinese medicine syndrome types in a knowledge graph, and if one or more disease symptoms corresponding to the traditional Chinese medicine syndrome types can be found to be completely equal to a disease symptom set, the one or more traditional Chinese medicine syndrome types are candidate traditional Chinese medicine syndrome types; if the information cannot be found, the step II is carried out;
secondly, two traditional Chinese medicine syndrome types are further searched, the union of the disease property syndrome elements corresponding to the two traditional Chinese medicine syndrome types is completely equal to the disease property syndrome element set, and if the two traditional Chinese medicine syndrome types can be searched, the two traditional Chinese medicine syndrome types are candidate traditional Chinese medicine syndrome types; if the user can not find the target object, entering the step three;
searching a single traditional Chinese medicine syndrome type corresponding to each disease property syndrome element as a candidate traditional Chinese medicine syndrome type;
inferring the most appropriate TCM syndrome types includes:
for each Chinese medicine symptom type in the candidate Chinese medicine symptom types, searching corresponding morbid syndrome elements according to a Chinese medicine knowledge graph; selecting the corresponding syndrome set as the traditional Chinese medicine syndrome type combination of the syndrome set subset;
and searching the syndrome type combination with the most corresponding syndrome element number in the candidate syndrome type combinations, namely the most suitable traditional Chinese medicine syndrome type.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910768831.6A CN110459321B (en) | 2019-08-20 | 2019-08-20 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
| PCT/CN2020/121967 WO2021032220A2 (en) | 2019-08-20 | 2020-10-19 | Traditional chinese medicine supplementary diagnosis system based on syndrome factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910768831.6A CN110459321B (en) | 2019-08-20 | 2019-08-20 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110459321A CN110459321A (en) | 2019-11-15 |
| CN110459321B true CN110459321B (en) | 2020-10-23 |
Family
ID=68487882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910768831.6A Active CN110459321B (en) | 2019-08-20 | 2019-08-20 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110459321B (en) |
| WO (1) | WO2021032220A2 (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459321B (en) * | 2019-08-20 | 2020-10-23 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
| CN110931124A (en) * | 2019-12-09 | 2020-03-27 | 中国中医科学院中医药信息研究所 | Diagnostic system |
| CN112086206A (en) * | 2020-09-09 | 2020-12-15 | 北京小白世纪网络科技有限公司 | Prescription searching method and device for deduction by using editable knowledge graph |
| CN112216383B (en) * | 2020-10-26 | 2023-02-21 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine intelligent inquiry tongue diagnosis comprehensive system based on syndrome element and deep learning |
| CN112466436B (en) * | 2020-11-25 | 2024-02-23 | 北京小白世纪网络科技有限公司 | Intelligent traditional Chinese medicine prescription model training method and device based on cyclic neural network |
| CN112700838B (en) * | 2020-12-30 | 2024-03-01 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| CN113140310B (en) * | 2021-05-06 | 2024-02-27 | 王耘 | Intelligent diagnosis and treatment system for traditional Chinese medicine and creation method |
| CN113241173B (en) * | 2021-05-12 | 2023-06-13 | 华中科技大学 | Traditional Chinese medicine auxiliary diagnosis and treatment method and system for chronic obstructive pulmonary disease |
| CN115423052B (en) * | 2022-11-07 | 2023-03-24 | 南京大经中医药信息技术有限公司 | Traditional Chinese medicine syndrome type classification method based on multi-graph attention |
| CN116631612B (en) * | 2023-06-09 | 2024-03-19 | 广东工业大学 | Graph convolution herbal medicine recommendation method and computer based on multi-graph fusion |
| CN116821779B (en) * | 2023-08-31 | 2023-11-14 | 中南大学湘雅医院 | Big data identification method for gastrointestinal health |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2718703Y (en) * | 2003-12-16 | 2005-08-17 | 杨富元 | Traditional Chinese medical dialectical precription fast-checking up disc |
| CN1804850A (en) * | 2005-11-24 | 2006-07-19 | 朱文锋 | Symptom and sign differentiation, diagnosis and treatment system in traditional Chinese medicine |
| CN102222153A (en) * | 2010-01-27 | 2011-10-19 | 洪文学 | Quantitative dialectical diagnostic method for Chinese medicine machine interrogation |
| CN105825064A (en) * | 2016-03-22 | 2016-08-03 | 施弘 | Daily traditional Chinese medicine therapy intelligent consultancy system |
| CN107066814A (en) * | 2017-03-09 | 2017-08-18 | 南京邮电大学 | A kind of traditional Chinese medical science intelligent auxiliary diagnosis system cooperateed with based on the four methods of diagnosis |
| CN107145744B (en) * | 2017-05-08 | 2018-03-02 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
| CN107280648A (en) * | 2017-07-31 | 2017-10-24 | 郦永平 | Chinese Medicine Diagnoses System |
| CN108986911A (en) * | 2018-07-06 | 2018-12-11 | 成都中医药大学 | A kind of differential diagnosis in tcm opinion controls data processing method |
| CN109448838A (en) * | 2018-09-28 | 2019-03-08 | 小伍健康科技（上海）有限责任公司 | A kind of symptomatic diagnosis method and apparatus based on deep neural network |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109766445B (en) * | 2018-12-13 | 2024-03-26 | 平安科技（深圳）有限公司 | Knowledge graph construction method and data processing device |
| CN109670054B (en) * | 2018-12-26 | 2020-11-10 | 医渡云（北京）技术有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN109830299B (en) * | 2019-02-14 | 2021-07-27 | 南京大经中医药信息技术有限公司 | Traditional Chinese medicine pathogenesis syndrome differentiation method and device based on human body model and storage medium |
| CN110085307B (en) * | 2019-04-04 | 2023-02-03 | 华东理工大学 | Intelligent diagnosis guiding method and system based on multi-source knowledge graph fusion |
| CN110085325B (en) * | 2019-04-30 | 2021-06-01 | 王小岗 | Method and device for constructing knowledge graph about traditional Chinese medicine experience data |
| CN110459321B (en) * | 2019-08-20 | 2020-10-23 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
-
2019
- 2019-08-20 CN CN201910768831.6A patent/CN110459321B/en active Active
-
2020
- 2020-10-19 WO PCT/CN2020/121967 patent/WO2021032220A2/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN110459321A (en) | 2019-11-15 |
| WO2021032220A2 (en) | 2021-02-25 |
| WO2021032220A3 (en) | 2021-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110459321B (en) | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element | |
| CN109299239B (en) | ES-based electronic medical record retrieval method | |
| US20190251084A1 (en) | Search method and apparatus | |
| US9165116B2 (en) | Patient data mining | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| US20180246876A1 (en) | Apparatus and method for automatically mapping verbatim narratives to terms in a terminology dictionary | |
| US20140136184A1 (en) | Textual ambiguity resolver | |
| CN109887596A (en) | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map | |
| CN111292848A (en) | Bayesian estimation-based medical knowledge map assisted reasoning method | |
| CN112885478B (en) | Medical document retrieval method, medical document retrieval device, electronic device and storage medium | |
| Hammami et al. | Automated classification of cancer morphology from Italian pathology reports using Natural Language Processing techniques: A rule-based approach | |
| CN111460797A (en) | Keyword extraction method and device, electronic equipment and readable storage medium | |
| CN111061835B (en) | Query method and device, electronic equipment and computer readable storage medium | |
| CN110491519B (en) | Medical data checking method | |
| CN113488157B (en) | Intelligent diagnosis guiding processing method and device, electronic equipment and storage medium | |
| Chandra et al. | Natural language Processing and Ontology based Decision Support System for Diabetic Patients | |
| Comelli et al. | An ontology-based retrieval system for mammographic reports | |
| CN112507138A (en) | Method and device for constructing disease-specific knowledge map, medium and electronic equipment | |
| CN109522331B (en) | Individual-centered regionalized multi-dimensional health data processing method and medium | |
| CN115631823A (en) | Similar case recommendation method and system | |
| US20240079109A1 (en) | Pharmacological recommendation system | |
| CN114627993A (en) | Information prediction method, information prediction device, storage medium and computer equipment | |
| CN114400090A (en) | Inquiry assisting method, inquiry assisting device, equipment and storage medium | |
| CN113972008A (en) | Associated disease analysis method, device, equipment and storage medium | |
| Kefeli et al. | TCGA-Reports: A machine-readable pathology report resource for benchmarking text-based AI models |
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 | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 12 / F, building 1, Aosheng building, 1166 Xinluo street, hi tech Zone, Jinan City, Shandong Province Patentee after: Zhongyang Health Technology Group Co.,Ltd. Address before: 12 / F, building 1, Aosheng building, 1166 Xinluo street, hi tech Zone, Jinan City, Shandong Province Patentee before: SHANDONG MSUNHEALTH TECHNOLOGY GROUP Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |