CN112086200B - System, equipment and storage medium for predicting diseases based on bitter taste - Google Patents
System, equipment and storage medium for predicting diseases based on bitter taste Download PDFInfo
- Publication number
- CN112086200B CN112086200B CN202010981317.3A CN202010981317A CN112086200B CN 112086200 B CN112086200 B CN 112086200B CN 202010981317 A CN202010981317 A CN 202010981317A CN 112086200 B CN112086200 B CN 112086200B
- Authority
- CN
- China
- Prior art keywords
- disease
- bitter taste
- symptoms
- module
- clustering
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 128
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 128
- 235000019658 bitter taste Nutrition 0.000 title claims abstract description 94
- 208000024891 symptom Diseases 0.000 claims abstract description 80
- 239000013598 vector Substances 0.000 claims abstract description 27
- 208000025371 Taste disease Diseases 0.000 claims abstract description 9
- 238000003064 k means clustering Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 5
- 241000282461 Canis lupus Species 0.000 claims description 30
- 241000282421 Canidae Species 0.000 claims description 25
- 210000004185 liver Anatomy 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 206010061218 Inflammation Diseases 0.000 claims description 7
- 230000004054 inflammatory process Effects 0.000 claims description 7
- 230000003340 mental effect Effects 0.000 claims description 7
- 208000017667 Chronic Disease Diseases 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 210000002784 stomach Anatomy 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000002496 gastric effect Effects 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 6
- 210000000214 mouth Anatomy 0.000 description 14
- 210000000232 gallbladder Anatomy 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 235000019640 taste Nutrition 0.000 description 5
- 206010047700 Vomiting Diseases 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 206010028980 Neoplasm Diseases 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 3
- 210000000941 bile Anatomy 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 235000019643 salty taste Nutrition 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000035943 smell Effects 0.000 description 3
- 230000008673 vomiting Effects 0.000 description 3
- 241000254173 Coleoptera Species 0.000 description 2
- 206010013789 Dry throat Diseases 0.000 description 2
- 206010019233 Headaches Diseases 0.000 description 2
- 208000002193 Pain Diseases 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 210000000748 cardiovascular system Anatomy 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 208000002173 dizziness Diseases 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 239000000796 flavoring agent Substances 0.000 description 2
- 235000019634 flavors Nutrition 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 231100000869 headache Toxicity 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000036407 pain Effects 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 206010000060 Abdominal distension Diseases 0.000 description 1
- 208000007848 Alcoholism Diseases 0.000 description 1
- 206010051625 Conjunctival hyperaemia Diseases 0.000 description 1
- 206010015150 Erythema Diseases 0.000 description 1
- 206010018276 Gingival bleeding Diseases 0.000 description 1
- 206010022998 Irritability Diseases 0.000 description 1
- 208000025157 Oral disease Diseases 0.000 description 1
- 206010038776 Retching Diseases 0.000 description 1
- 208000010340 Sleep Deprivation Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 208000038016 acute inflammation Diseases 0.000 description 1
- 230000006022 acute inflammation Effects 0.000 description 1
- 201000007930 alcohol dependence Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 201000001352 cholecystitis Diseases 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 206010013781 dry mouth Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000029142 excretion Effects 0.000 description 1
- 208000020694 gallbladder disease Diseases 0.000 description 1
- 230000007661 gastrointestinal function Effects 0.000 description 1
- 208000007565 gingivitis Diseases 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 208000006454 hepatitis Diseases 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000030194 mouth disease Diseases 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000010025 steaming Methods 0.000 description 1
- 235000021147 sweet food Nutrition 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a system, equipment and storage medium for predicting diseases based on bitter taste, wherein the system comprises: the symptom acquisition module acquires the bitter taste accompanying symptoms on the premise of establishing bitter taste as a first clinical complaint symptom; a disease library module for establishing a bitter taste disease library of association relations between bitter taste accompanying symptoms and corresponding diseases and disease symptoms; the preprocessing module is used for vectorizing and representing various disease symptom information in the disease library in a text processing mode; the disease clustering module clusters the diseases in the bitter disease library by adopting an optimized k-means clustering algorithm; the major class dividing module: clustering feature vectors of bitter taste accompanying symptoms to be identified; and the disease prediction module is used for predicting the disease by calculating the intra-class semantic similarity.
Description
Technical Field
The invention relates to the field of disease auxiliary diagnosis equipment, in particular to a system, equipment and storage medium for predicting diseases based on bitter taste.
Background
In common telephone, the nose smells the smell and the tongue tastes five flavors. The sour, sweet, bitter, spicy and salty five flavors of information are transmitted by the fine papillae densely distributed on the lingual surface, called the taste cells of the lingual buds, and are excited by the cerebral cortex taste center, and the feedback loop nerve body fluid system completes the analysis activity of the whole taste. However, some people feel bad smell in the mouth when eating or feel abnormal taste in the mouth when not eating. This often suggests that a certain disease may be obtained. Bitter taste in the mouth means bitter taste in the mouth. The heart corresponds to the intangible form of traditional Chinese medicine, but is less frequently seen in heart-related diseases. Acute inflammation is usually associated with metabolism of bile, and is mainly caused by inflammation of liver and gallbladder. Bitter taste can also be seen in cancer. The american medical doctor deweisi also found that cancer patients lost the taste of sweet foods and the bitter feel to foods increased with time, which was associated with impaired tongue blood circulation and altered composition in saliva.
Disclosure of Invention
In view of the above, the present invention provides a system, device and storage medium for predicting diseases based on bitter taste, which are used for solving the problem that the prior art cannot accurately diagnose diseases under the condition of bitter taste as main complaints.
In a first aspect of the invention, a system for predicting a disease based on oral bitterness is disclosed, the system comprising:
symptom acquisition module: acquiring bitter taste accompanying symptoms on the premise of establishing bitter taste as a first clinical complaint symptom;
a disease library module: acquiring information of all diseases and disease symptoms corresponding to bitter taste, and establishing a bitter taste disease library of association relations between bitter taste accompanying symptoms and corresponding diseases and disease symptoms;
and a pretreatment module: vectorizing the information of various disease symptoms in the disease library in a text processing mode to obtain feature vectors of the various disease symptoms;
disease clustering module: determining a clustering class according to the cause of bitter taste, and clustering diseases in a bitter taste disease library by adopting a k-means clustering algorithm optimized by a siro-longhorn beetle whisker algorithm;
the major class dividing module: acquiring a bitter taste symptom to be identified, establishing a bitter taste symptom feature vector, and clustering the bitter taste symptom feature vector to obtain a major classification result;
disease prediction module: and according to the large class division result, carrying out disease prediction by calculating the intra-class semantic similarity.
Preferably, the clustering categories are divided into five categories of mental bitter taste, oral inflammation bitter taste, stomach heat bitter taste, bitter taste of certain chronic diseases and bitter taste of liver and gall diseases.
Preferably, the disease clustering module specifically includes:
an initializing unit: the method is used for initializing a wolf algorithm, setting group scale, solution space dimension and wolf group initialization;
a first wolf screening unit: respectively calculating the fitness of each wolf, and screening three wolves with the minimum fitness as head wolves;
position updating unit: calculating the distance from other wolves to the head wolves respectively, and carrying out the position update of individual wolves by combining the competition consciousness in the shoal algorithm:
wherein X (t+1) is the position of the gray wolf at t+1 iterations, X 1 、X 2 、X 3 To update intermediate variables, b1, b 2E [0,2, for the position of the wolf based on the position, distance estimate of the wolf]K is [1, N]Random integer between them, and k not equal to i, f i 、f k The adaptation values of the ith and the k gray wolves are respectively; sumf is the sum of fitness of the entire population, ε is a constant close to 0, mean j Is the average fitness value of the population;
returning the updated individual position results of the gray wolves to the fitness calculation unit for iterative operation until the maximum iterative times are reached, and outputtingAs the optimized cluster centroid.
Preferably, in the fitness evaluation unit, the fitness function may be a sum of intra-class distances,wherein K is the number of cluster categories, d (X) i ,C j ) For each wolf object X in the jth cluster class i To the cluster center point C j Is a distance of (3).
Preferably, in the large class classification module, the Euclidean distance between the feature vector of the bitter taste accompanying symptoms and the centroid of each cluster is calculated, and the cluster class with the smallest distance is selected as the large class classification result.
Preferably, in the disease prediction module, calculating the similarity between the feature vector of the bitter taste accompanying symptoms to be classified and the feature vector of each disease symptom in the major classification result, and taking N diseases with the highest similarity as preliminary disease prediction results; and for each disease in the preliminary disease prediction result, if the same disease corresponds to a plurality of accompanying symptoms, respectively calculating the similarity between the characteristic vector of the bitter accompanying symptoms of the mouth to be classified and the plurality of accompanying symptoms, carrying out similarity comprehensive sequencing, and taking N diseases with the highest similarity as final disease prediction results.
In a second aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor that the processor invokes to implement the system according to the first aspect of the present invention.
In a third aspect of the present invention, a computer-readable storage medium is disclosed, the computer-readable storage medium storing computer instructions that cause the computer to implement the system according to the first aspect of the present invention.
Compared with the prior art, the invention has the following beneficial effects:
1) The invention establishes a bitter taste disease library, adopts a cluster algorithm based on the optimization of a longhorn beetle whisker-gray wolf algorithm to cluster disease categories, divides diseases with similar disease symptoms into a large category, determines the large category of the diseases to be classified, then calculates the similarity of the diseases, does not need to compare and judge all the diseases, greatly reduces the operand, improves the speed and the accuracy of disease diagnosis, can deduce and predict possible diseases and health problems more accurately, and is a simple and practical auxiliary diagnosis system.
2) According to the invention, the gray wolf algorithm and the shoal algorithm are combined for clustering optimization, so that the advantages of cooperation trapping and mutual competition among populations are fully exerted, on one hand, the wolves with better adaptability can be enabled to approach the current optimal position at the fastest speed, and on the other hand, the wolves with other poor adaptations can be enabled to search the potential optimal position near the current optimal position, and the global optimal solution can be searched at the fastest speed.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a system for predicting disease based on bitter taste according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will clearly and fully describe the technical aspects of the embodiments of the present invention, and 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, are intended to fall within the scope of the present invention.
As shown in fig. 1, the present invention proposes a system for predicting a disease based on bitter taste, which includes a symptom acquisition module 100, a disease library module 200, a preprocessing module 300, a disease clustering module 400, a broad classification module 500, and a disease prediction module 600;
the symptom acquisition module 100 acquires the bitter taste accompanying symptoms on the premise of establishing bitter taste as the first clinical complaint symptom; for example, the traditional Chinese medicine considers that bitter taste is often accompanied by symptoms such as headache, dizziness, red face, acute and irritable, dry stool, reddish tongue, thin and yellow coating, wiry and rapid pulse, and the like, and the symptoms are mostly caused by heat in liver and gallbladder; bitter taste in the mouth often has symptoms such as cold and heat, vexation, vomiting, bitter and full chest rib, and dark urine, etc., and is mostly caused by upward steaming of gallbladder heat;
the disease library module 200 acquires information of all diseases and disease symptoms corresponding to the bitter taste, and establishes a bitter taste disease library of association relations between bitter taste accompanying symptoms and corresponding diseases and disease symptoms; for example, the main symptoms of gallbladder heat syndrome are: bitter in chest and hypochondrium, cold and heat going forward, bitter in mouth, dry throat, vomiting or retching; or gallbladder diseases such as hypochondriac distention and pain, nausea and vomiting, or bile vomiting, thin and yellow coating and wiry and thready pulse; the main symptoms of liver depression transforming into heat are: bitter taste in mouth, dry throat, vexation, irritability, dizziness, headache, conjunctival congestion, hypochondriac pain, yellow and short urine, dry stool, red tongue edge and tip, thin and yellow coating, and wiry and rapid pulse;
since there are many symptoms of each disease, and not all the symptoms need to be satisfied for diagnosis, the present invention establishes a correspondence relationship between the disease and the symptoms of the disease according to salty taste and salty taste associated symptoms, and different salty taste associated symptoms may correspond to the same disease.
The preprocessing module 300 performs vectorization representation on various disease symptoms in the disease library in a text processing mode to obtain feature vectors of the various disease symptoms;
specifically, word segmentation and word disabling processing are carried out on disease symptom information corresponding to various diseases; mathematical modeling is carried out by adopting a vector space model, word segmentation weight calculation is carried out on the text data after word segmentation by adopting TF-IDF, and keywords in the text data are extracted; and carrying out Word vectorization by using a Word2Vec model, and inputting data clustered by the feature vectors of various disease symptoms by taking the text data vector after vectorization as the feature vector of various disease symptoms.
The disease clustering module 400 determines a clustering category according to the cause of bitter taste, and clusters the diseases in the bitter taste disease library by adopting a k-means clustering algorithm optimized by a sirius-longhorn whisker algorithm; the disease clustering module specifically comprises:
category determination unit: according to the cause of bitter taste, determining cluster categories, wherein the cluster categories are divided into five categories of mental bitter taste, oral inflammation bitter taste, stomach heat bitter taste, bitter taste of certain chronic diseases and bitter taste of liver and gall diseases.
1) Mental bitter taste, modern working and living pressures, so that a large number of people can have long-term working and mental pressures, irregular life, insufficient sleep and rest, lack of movement and the like, and bitter taste is caused; excessive smoking, alcoholism, snoring, sleeping with open mouth and the like are easy to cause dry mouth and bitter mouth; 2) Oral inflammation, if there are gingivitis, gingival bleeding and other oral diseases, is a common cause of bitter taste; 3) If improper diet, the gastrointestinal function is stagnant, the food which is eaten stays in the stomach and intestine for too long, damp heat is extremely easy to generate, and the bitter taste is caused; 4) Some chronic diseases and diabetes mellitus are often accompanied by bitter taste; in addition, cancer patients can feel bitter in the oral cavity due to the increase of the sweet valve and the decrease of the bitter valve, and the vigilance should be improved; 5) In the morning, bitter taste is mostly caused by damp-heat, and damp-heat in liver and gallbladder is probably caused by inflammation in liver and gallbladder. Such as when the liver or gall bladder is inflamed, abnormal bile excretion results in bitter taste.
An initializing unit: for the initialization of the wolf algorithm (GWO, grey Wolf Optimizer), the group size N, the solution space dimension N and the wolf group initialization X are set i ＝(x 1 ,x 2 ,......,x n ) Where i E [ N ]]The method comprises the steps of carrying out a first treatment on the surface of the Selecting one case of mental bitter taste, oral inflammation bitter taste, stomach heat bitter taste, chronic disease bitter taste, liver and gall disease bitter taste as an initial clustering center;
fitness evaluation unit: respectively calculating the fitness of each wolf, and screening out the minimum fitnessAlpha, beta, delta of the wolf, the corresponding positions of which are respectively X α 、X β 、X δ X is taken as α 、X β 、X δ An input position updating unit; the fitness function may be the sum of the intra-class distances,wherein K is the number of cluster categories, d (X) i ,C j ) For each wolf object X in the jth cluster class i To its cluster center point C j Is a distance of (3).
Position updating unit: calculating the distance D from the omega of the other wolves to alpha, beta and delta of the wolves α 、D β 、D δ ：
D α ＝|C 1 *X α (t)-X|,D β ＝|C 2 *X β (t)-X|,D δ ＝|C 3 *X δ (t)-X|
Updating an intermediate variable X according to the position of the wolf and the position of the wolf obtained by estimating the distance 1 、X 2 、X 3 ：
X 1 ＝X α (t)-A 1 *D α ,X 2 ＝X β (t)-A 2 *D β ,X 3 ＝X δ (t)-A 3 *D δ
The gray wolf individual position update was performed in combination with competition awareness in the shoal algorithm (Bird Swarm Algorithm, BSA):
wherein X (t+1) is the position of the wolf at t+1 iterations, and A and C are twoIndividual system vectors, a=2a×r 1 -a,C＝2a*r 2 ,a＝a 1 (1-t/t max )，r 1 、r 2 Is [0,1]Random vector uniformly distributed on a 1 Is constant, t max The maximum iteration number; b1, b2 ε [0,2 ]]K is [1, N]Random integer between them, and k not equal to i, f i 、f k The adaptation values of the ith and the k gray wolves are respectively; sumf is the sum of fitness of the entire population, ε is a constant close to 0, mean j Is the average fitness value of the population.
Returning the updated position results of the individual gray wolves to the fitness calculation unit for iterative operation until the maximum iterative times are reached, and outputting X α As the optimized cluster centroid.
According to the invention, the gray wolf algorithm is combined with the shoal algorithm, when the position is updated, the position is not directly moved to the next target position determined by the first wolves, but the vigilance is maintained, each wolf tries to move to the center of the population, the behavior is influenced by competition among the population, the wolves with better adaptability have higher probability to fly to the center, the optimal position can be found at the fastest speed, and the convergence speed is improved; and other wolves can search near the target position, so that the local search range is enlarged, and the situation of sinking into local optimum is avoided. Therefore, the gray wolf algorithm is combined with the shoal algorithm, on one hand, the wolves with better adaptability can be enabled to approach the current optimal position at the fastest speed, on the other hand, the wolves with other poor adaptability can be enabled to search the potential optimal position near the current optimal position, and on the other hand, the advantages of cooperation trapping and mutual competition among populations are fully exerted, and the global optimal solution is searched at the fastest speed.
The large class classification module 500 acquires the bitter taste accompanying symptoms to be identified, establishes bitter taste accompanying symptom feature vectors through the preprocessing module 300, and clusters the bitter taste accompanying symptom feature vectors through the disease clustering module 400 to obtain a large class classification result;
specifically, euclidean distance between the characteristic vector of bitter taste accompanying symptoms and each cluster centroid is calculated, and the cluster category with the smallest distance is selected as a major class division result.
The disease prediction module 600 performs disease prediction by calculating intra-class semantic similarity according to the large class classification result.
In the disease prediction module, calculating the similarity between the feature vector of the bitter accompanying symptoms of the mouth to be classified and the feature vector of the symptoms of various diseases in the large classification result, and taking N diseases with the highest similarity as preliminary disease prediction results; for each disease in the preliminary disease prediction result, if the same disease corresponds to a plurality of accompanying symptoms, as the accompanying symptoms are clinically the most easily acquired symptoms, but the disease symptoms of each disease may be more, the situation that the distinction degree is not large may occur by simply comparing the bitter accompanying symptoms of the mouth to be classified with the disease symptoms, at this time, the similarity between the characteristic vector of the bitter accompanying symptoms of the mouth to be classified and the plurality of accompanying symptoms may be calculated respectively, the similarity comprehensive reordering is performed, and the N diseases with the highest similarity are taken as the final disease prediction result. Specifically, a cosine similarity calculation method can be adopted, cosine similarity in the class is arranged in a descending order, and the first N most disease prediction results with the highest similarity are recommended to medical staff.
The invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus; the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor, and the processor calls the program instructions to realize the system for intelligently identifying the infection cases of the cardiovascular system based on the current cardiovascular system infection diagnosis standard, which is disclosed by the invention, and comprises a symptom acquisition module, a disease library module, a preprocessing module, a disease clustering module, a major class division module and a disease prediction module.
The invention also discloses a computer readable storage medium storing computer instructions that cause the computer to implement all or part of the system described in the embodiments of the invention. For example, the system comprises a symptom acquisition module, a disease library module, a preprocessing module, a disease clustering module, a general classification module and a disease prediction module. The storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic or optical disk, or other various media capable of storing program code.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, i.e., may be distributed over a plurality of network elements. Some or all of the modules may be selected according to the actual government office in feudal China to achieve the purpose of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. A system for predicting disease based on bitter taste, the system comprising:
symptom acquisition module: acquiring information of symptoms accompanied with bitter taste on the premise of establishing bitter taste as a first clinical complaint symptom;
a disease library module: acquiring information of all diseases and disease symptoms corresponding to bitter taste, and establishing a bitter taste disease library of association relations between bitter taste accompanying symptoms and corresponding diseases and disease symptoms;
and a pretreatment module: vectorizing the information of various disease symptoms and the corresponding information of bitter taste accompanying symptoms in the disease library in a text processing mode to obtain feature vectors of the various disease symptoms;
disease clustering module: determining a clustering category according to the cause of bitter taste, and clustering diseases in a bitter taste disease library by adopting a k-means clustering algorithm optimized by a gray wolf-bird swarm algorithm;
in the disease clustering module, the k-means clustering algorithm optimized by the wolf-bird swarm algorithm is used for clustering the diseases in the bitter taste disease library, and specifically comprises the following steps:
an initializing unit: the method is used for initializing a wolf algorithm, setting group scale, solution space dimension and wolf group initialization; selecting one case of mental bitter taste, oral inflammation bitter taste, gastric heat bitter taste, chronic disease bitter taste and liver and gall disease bitter taste as an initial clustering center;
fitness evaluation unit: respectively calculating the fitness of each wolf, and screening three wolves with the minimum fitness as head wolves;
position updating unit: calculating the distance from other wolves to the head wolves respectively, and carrying out the position update of individual wolves by combining the competition consciousness in the shoal algorithm:
；
；
wherein,is thattPosition of the wolf, +1 iteration->Updating intermediate variables for the position of the wolf estimated from the position and distance of the wolf,/->， kIs [1, N]Random integer between them, andk≠i， f i 、f k respectively the firsti、kThe adaptability value of only the gray wolves;sumfe is a constant close to 0, which is the sum of fitness of the whole population,mean j is the average fitness value of the population;
returning the updated position results of the individual gray wolves to the fitness evaluation unit for iterative operation until the maximum iterative times are reached, and outputtingAs the optimized cluster centroid;
the major class dividing module: acquiring a bitter taste accompanying symptom to be identified, establishing a bitter taste accompanying symptom feature vector to be identified, and clustering the bitter taste accompanying symptom feature vector to be identified to obtain a large class classification result;
disease prediction module: and according to the large class division result, carrying out disease prediction by calculating the intra-class semantic similarity.
2. The system for predicting disease based on bitter taste in mouth of claim 1, wherein the clustering categories are divided into five categories of mental bitter taste, oral inflammation bitter taste, stomach heat bitter taste, chronic disease bitter taste, liver and gall disease bitter taste.
3. The system for predicting disease based on bitter taste as claimed in claim 1, wherein the fitness evaluation unit is configured to evaluate a fitness function as a sum of intra-class distances,whereinKFor clustering the category number, ++>For each wolf object in the j-th cluster classX i To the cluster center pointC j Is a distance of (3).
4. The system for predicting diseases based on bitter taste according to claim 1, wherein in the disease prediction module, calculating the similarity between the feature vector of the bitter taste associated symptoms to be classified and the feature vector of each disease symptom in the major classification result, and taking N diseases with the highest similarity as preliminary disease prediction results; and for each disease in the preliminary disease prediction result, if the same disease corresponds to a plurality of accompanying symptoms, respectively calculating the similarity between the characteristic vector of the bitter accompanying symptoms of the mouth to be classified and the plurality of accompanying symptoms, carrying out similarity comprehensive sequencing, and taking N diseases with the highest similarity as final disease prediction results.
5. An electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to implement the system of any of claims 1-4.
6. A computer readable storage medium storing computer instructions that cause the computer to implement the system of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981317.3A CN112086200B (en) | 2020-09-17 | 2020-09-17 | System, equipment and storage medium for predicting diseases based on bitter taste |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981317.3A CN112086200B (en) | 2020-09-17 | 2020-09-17 | System, equipment and storage medium for predicting diseases based on bitter taste |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112086200A CN112086200A (en) | 2020-12-15 |
| CN112086200B true CN112086200B (en) | 2024-01-12 |
Family
ID=73736541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010981317.3A Active CN112086200B (en) | 2020-09-17 | 2020-09-17 | System, equipment and storage medium for predicting diseases based on bitter taste |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112086200B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112885334A (en) * | 2021-01-18 | 2021-06-01 | 吾征智能技术(北京)有限公司 | Disease recognition system, device, storage medium based on multi-modal features |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520272A (en) * | 2018-03-22 | 2018-09-11 | 江南大学 | A kind of semi-supervised intrusion detection method improving blue wolf algorithm |
| CN110136836A (en) * | 2019-03-27 | 2019-08-16 | 周凡 | A kind of disease forecasting method based on physical examination report clustering |
| WO2020115730A1 (en) * | 2018-12-06 | 2020-06-11 | B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University | Integrated system and method for personalized stratification and prediction of neurodegenerative disease |
| CN111368891A (en) * | 2020-02-27 | 2020-07-03 | 大连大学 | K-Means text classification method based on immune clone wolf optimization algorithm |
| CN111653359A (en) * | 2020-05-30 | 2020-09-11 | 吾征智能技术(北京)有限公司 | Intelligent prediction model construction method and prediction system for hemorrhagic diseases |
-
2020
- 2020-09-17 CN CN202010981317.3A patent/CN112086200B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520272A (en) * | 2018-03-22 | 2018-09-11 | 江南大学 | A kind of semi-supervised intrusion detection method improving blue wolf algorithm |
| WO2020115730A1 (en) * | 2018-12-06 | 2020-06-11 | B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University | Integrated system and method for personalized stratification and prediction of neurodegenerative disease |
| CN110136836A (en) * | 2019-03-27 | 2019-08-16 | 周凡 | A kind of disease forecasting method based on physical examination report clustering |
| CN111368891A (en) * | 2020-02-27 | 2020-07-03 | 大连大学 | K-Means text classification method based on immune clone wolf optimization algorithm |
| CN111653359A (en) * | 2020-05-30 | 2020-09-11 | 吾征智能技术(北京)有限公司 | Intelligent prediction model construction method and prediction system for hemorrhagic diseases |
Non-Patent Citations (3)
| Title |
|---|
| Dynamic Equivalence for Wind Farm Based on IBSA-K-means Algorithm;Sun. YC等;《2nd International Conference on Power and Renewable Energy (ICPRE)》;443-446 * |
| Using Grey Wolf Algorithm to Solve the Capacitated Vehicle Routing Problem;L Korayem等;《IOP Conference Series: Materials Science and Engineering》;第83卷;012014 * |
| 种结合灰狼优化和+K-均值的混合聚类算法;杨红光、刘建生;《江西理工大学学报》;第36卷(第5期);85-89 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112086200A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wosiak et al. | Integrating Correlation‐Based Feature Selection and Clustering for Improved Cardiovascular Disease Diagnosis | |
| Rubaiat et al. | Important feature selection & accuracy comparisons of different machine learning models for early diabetes detection | |
| CN111292853A (en) | Cardiovascular disease risk prediction network model based on multiple parameters and construction method thereof | |
| El Hajj et al. | Cuffless and continuous blood pressure estimation from PPG signals using recurrent neural networks | |
| CN108763590B (en) | Data clustering method based on double-variant weighted kernel FCM algorithm | |
| Nandipati et al. | Polycystic Ovarian Syndrome (PCOS) classification and feature selection by machine learning techniques | |
| CN110801221A (en) | Sleep apnea fragment detection method and device based on unsupervised feature learning | |
| CN111261289A (en) | Heart disease detection method based on artificial intelligence model | |
| Moreno et al. | Type 2 diabetes screening test by means of a pulse oximeter | |
| CN111183424A (en) | System and method for identifying user | |
| CN112088408A (en) | Method for sleep stage detection, computing device and wearable device | |
| Gnanadass | Prediction of gestational diabetes by machine learning algorithms | |
| Nguyen et al. | Heart sound classification using deep learning techniques based on log-mel spectrogram | |
| KR102439082B1 (en) | Method for predicting liver disease of ordinary perseon using ecg analysis data based on deep running | |
| CN112002419B (en) | Disease auxiliary diagnosis system, equipment and storage medium based on clustering | |
| CN115024725A (en) | Tumor treatment aid decision-making system integrating psychological state multi-parameter detection | |
| WO2021184802A1 (en) | Blood pressure classification prediction method and apparatus | |
| CN112086200B (en) | System, equipment and storage medium for predicting diseases based on bitter taste | |
| Świerczyński et al. | Sensor data analysis and development of machine learning models for detection of glaucoma | |
| CN112712895A (en) | Data analysis method of multi-modal big data for type 2 diabetes complications | |
| US11915833B2 (en) | Integrated system and method for personalized stratification and prediction of neurodegenerative disease | |
| Kiladze et al. | Multimodal Neural Network for Recognition of Cardiac Arrhythmias Based on 12-Load Electrocardiogram Signals | |
| US11935642B2 (en) | System and method for generating a neonatal disorder nourishment program | |
| Xu et al. | Prediction of Diabetes with its Symptoms Based on Machine Learning | |
| CN114550910A (en) | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |