CN112233750A - Information matching system based on hemoptysis character and disease - Google Patents
Information matching system based on hemoptysis character and disease Download PDFInfo
- Publication number
- CN112233750A CN112233750A CN202011124012.7A CN202011124012A CN112233750A CN 112233750 A CN112233750 A CN 112233750A CN 202011124012 A CN202011124012 A CN 202011124012A CN 112233750 A CN112233750 A CN 112233750A
- Authority
- CN
- China
- Prior art keywords
- hemoptysis
- information
- calculated
- disease
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000000616 Hemoptysis Diseases 0.000 title claims abstract description 139
- 201000010099 disease Diseases 0.000 title claims abstract description 92
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 92
- 239000013598 vector Substances 0.000 claims abstract description 110
- 238000003062 neural network model Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 208000024891 symptom Diseases 0.000 claims description 39
- 210000002569 neuron Anatomy 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 11
- 206010036790 Productive cough Diseases 0.000 description 9
- 239000008280 blood Substances 0.000 description 8
- 210000004369 blood Anatomy 0.000 description 8
- 206010011224 Cough Diseases 0.000 description 6
- 208000024794 sputum Diseases 0.000 description 6
- 210000003802 sputum Anatomy 0.000 description 6
- 206010008479 Chest Pain Diseases 0.000 description 4
- 230000001154 acute effect Effects 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- 210000003462 vein Anatomy 0.000 description 4
- 208000032843 Hemorrhage Diseases 0.000 description 3
- 206010035664 Pneumonia Diseases 0.000 description 3
- 206010037660 Pyrexia Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 201000009267 bronchiectasis Diseases 0.000 description 3
- 201000003453 lung abscess Diseases 0.000 description 3
- 208000008128 pulmonary tuberculosis Diseases 0.000 description 3
- 230000009885 systemic effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000014181 Bronchial disease Diseases 0.000 description 2
- 201000009030 Carcinoma Diseases 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 2
- 206010011703 Cyanosis Diseases 0.000 description 2
- 208000000059 Dyspnea Diseases 0.000 description 2
- 206010013975 Dyspnoeas Diseases 0.000 description 2
- 206010024119 Left ventricular failure Diseases 0.000 description 2
- 208000019693 Lung disease Diseases 0.000 description 2
- 206010033557 Palpitations Diseases 0.000 description 2
- 208000010378 Pulmonary Embolism Diseases 0.000 description 2
- 230000000740 bleeding effect Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 206010006451 bronchitis Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000011010 flushing procedure Methods 0.000 description 2
- 208000014951 hematologic disease Diseases 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 208000006887 mitral valve stenosis Diseases 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000003492 pulmonary vein Anatomy 0.000 description 2
- 210000002345 respiratory system Anatomy 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 201000008827 tuberculosis Diseases 0.000 description 2
- 206010003497 Asphyxia Diseases 0.000 description 1
- 206010006458 Bronchitis chronic Diseases 0.000 description 1
- 206010069729 Collateral circulation Diseases 0.000 description 1
- 208000002330 Congenital Heart Defects Diseases 0.000 description 1
- 206010013954 Dysphoria Diseases 0.000 description 1
- 208000031220 Hemophilia Diseases 0.000 description 1
- 208000009292 Hemophilia A Diseases 0.000 description 1
- 208000032982 Hemorrhagic Fever with Renal Syndrome Diseases 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000035478 Interatrial communication Diseases 0.000 description 1
- 241000588747 Klebsiella pneumoniae Species 0.000 description 1
- 206010024238 Leptospirosis Diseases 0.000 description 1
- 208000020128 Mitral stenosis Diseases 0.000 description 1
- 201000008235 Mycoplasma pneumoniae pneumonia Diseases 0.000 description 1
- 206010030972 Oral discharge Diseases 0.000 description 1
- 241000935974 Paralichthys dentatus Species 0.000 description 1
- 208000009362 Pneumococcal Pneumonia Diseases 0.000 description 1
- 206010035724 Pneumonia mycoplasmal Diseases 0.000 description 1
- 206010035728 Pneumonia pneumococcal Diseases 0.000 description 1
- 208000003251 Pruritus Diseases 0.000 description 1
- 206010037368 Pulmonary congestion Diseases 0.000 description 1
- 208000006193 Pulmonary infarction Diseases 0.000 description 1
- 206010043561 Thrombocytopenic purpura Diseases 0.000 description 1
- 206010046996 Varicose vein Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 208000022531 anorexia Diseases 0.000 description 1
- 230000002924 anti-infective effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 208000013914 atrial heart septal defect Diseases 0.000 description 1
- 206010003664 atrial septal defect Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000024753 bloody sputum Diseases 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 208000007451 chronic bronchitis Diseases 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 206010061428 decreased appetite Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 230000005986 heart dysfunction Effects 0.000 description 1
- 208000031169 hemorrhagic disease Diseases 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 230000000622 irritating effect Effects 0.000 description 1
- 230000007803 itching Effects 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 208000032839 leukemia Diseases 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 206010029410 night sweats Diseases 0.000 description 1
- 230000036565 night sweats Effects 0.000 description 1
- 206010033794 paragonimiasis Diseases 0.000 description 1
- 208000003278 patent ductus arteriosus Diseases 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 208000002815 pulmonary hypertension Diseases 0.000 description 1
- 230000007575 pulmonary infarction Effects 0.000 description 1
- 206010037833 rales Diseases 0.000 description 1
- 208000022218 streptococcal pneumonia Diseases 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 230000035900 sweating Effects 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 210000004876 tela submucosa Anatomy 0.000 description 1
- 208000027185 varicose disease Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides an information matching system based on hemoptysis traits and diseases. The method comprises the following steps: the acquisition module is used for acquiring hemoptysis character information and corresponding disease information and establishing a corresponding space vector set; the conversion module is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated; the calculation module is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculating the vector sets to be matched and generating corresponding matching values; and the recording module is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value. According to the invention, the matching numerical value between the two confidences is calculated by constructing the radial basis function neural network model, so that the calculation accuracy is improved, and meanwhile, the data is stored, so that the relevance between the data can be enhanced, and the data loss is prevented.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an information matching system based on hemoptysis traits and diseases.
Background
Hemoptysis refers to bleeding in any part of the respiratory tract of the throat and below the larynx, which is caused by oral discharge. A small amount of hemoptysis sometimes only shows that phlegm carries blood, and blood gushes out from the mouth and nose during a large amount of hemoptysis, so that respiratory tract can be blocked frequently, and suffocation and death can be caused.
In the prior art, when information matching of hemoptysis traits and accompanying symptoms is performed, training is often performed through a BP network to complete information matching, but the training time of the BP network is long, and due to the characteristics of the BP network, when the information is matched, each information item influences each other, so that the information matching result is not accurate enough, and therefore, an information matching system based on hemoptysis traits and diseases is urgently needed to improve the accuracy of the information matching result.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In view of this, the invention provides an information matching system based on hemoptysis traits and diseases, and aims to solve the technical problem that the prior art cannot improve the information matching accuracy through a radial basis function neural network.
The technical scheme of the invention is realized as follows:
in one aspect, the present invention provides an information matching system based on hemoptysis traits and diseases, including:
the acquisition module is used for acquiring hemoptysis character information and corresponding disease information and respectively establishing corresponding space vector sets according to the hemoptysis character information and the corresponding disease information;
the conversion module is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated according to the hemoptysis character information to be calculated;
the calculation module is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculating the vector sets to be matched and generating corresponding matching values;
and the recording module is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value.
On the basis of the above technical solution, preferably, the obtaining module includes a feature extracting module, configured to obtain hemoptysis trait information and corresponding disease information, where the hemoptysis trait information includes: hemoptysis trait information and corresponding accompanying symptom information, the disease information comprising: and extracting words with the maximum numerical values from the hemoptysis character information and the corresponding disease information through TF-IDF to serve as feature words.
On the basis of the above technical solution, preferably, the acquisition module includes a set establishment module, configured to establish different space vector sets according to the hemoptysis trait feature words, the accompanying symptom feature words, the disease feature words, and the disease symptom feature words, store the accompanying symptom feature words, the disease feature words, and the disease symptom feature words into corresponding space vector sets according to the correspondence, and establish a correspondence table.
On the basis of the above technical solution, preferably, the conversion module includes a vectorization module, configured to obtain hemoptysis trait information to be calculated, where the hemoptysis trait information to be calculated includes: verifying the integrity of the hemoptysis trait information to be calculated, extracting a word with the maximum value from the hemoptysis trait information to be calculated which passes integrity verification by using TF-IDF as a hemoptysis trait feature word to be calculated and an accompanying symptom feature word to be calculated, establishing a space vector set to be calculated according to the hemoptysis trait feature word to be calculated, and storing the accompanying symptom feature word to be calculated into a corresponding space vector set to be calculated.
On the basis of the above technical solution, preferably, the calculation module includes an initialization module configured to construct a radial basis function neural network model, use the space vector set and the space vector set to be calculated as a vector set to be matched, place the vector set to be matched in the input layer, initialize the connection weight from the hidden layer to the output layer and the central parameters of each neuron of the hidden layer, and initialize the width vector.
On the basis of the above technical solution, preferably, the calculation module includes a calculation output module, which is configured to calculate an output value of a neuron in the output layer according to the vector set to be matched and the connection weight in the input layer, and iterate the output value according to the central parameter and the width vector to obtain an iterative value as the matching value.
On the basis of the above technical solution, preferably, the recording module includes a matching storage module, configured to set a matching threshold, compare the matching value with the matching threshold, store corresponding data in the radial basis function neural network model when the matching value is greater than the matching threshold, establish association with the space vector set, and produce a corresponding matching report according to the space vector set.
Still further preferably, the information matching apparatus based on hemoptysis trait and disease includes:
the acquiring unit is used for acquiring hemoptysis character information and corresponding disease information and respectively establishing corresponding space vector sets according to the hemoptysis character information and the corresponding disease information;
the conversion unit is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated according to the hemoptysis character information to be calculated;
the computing unit is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be computed into corresponding vector sets to be matched through the radial basis function neural network model, computing the vector sets to be matched and generating corresponding matching values;
and the recording unit is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value.
Compared with the prior art, the information matching system based on hemoptysis traits and diseases has the following beneficial effects:
(1) by utilizing the radial basis function neural network model, the matching numerical value between the hemoptysis character information and the hemoptysis character information to be calculated can be quickly and accurately calculated, so that the matching accuracy is improved, and the user experience is improved;
(2) by storing the data after the radial basis function neural network model calculation in real time, the problem that the basis function neural network model loses data is greatly avoided, and meanwhile, the relevance between the data is also improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a first embodiment of an information matching system based on hemoptysis trait and disease in accordance with the present invention;
FIG. 2 is a block diagram of a second embodiment of the information matching system based on hemoptysis trait and disease;
FIG. 3 is a block diagram of a third embodiment of the information matching system based on hemoptysis trait and disease;
FIG. 4 is a block diagram of a fourth embodiment of the information matching system based on hemoptysis trait and disease;
FIG. 5 is a block diagram of a fifth embodiment of the information matching system based on hemoptysis trait and disease;
fig. 6 is a block diagram of the structure of information matching equipment based on hemoptysis traits and diseases.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, fig. 1 is a block diagram showing a configuration of a first embodiment of an information matching system based on hemoptysis trait and disease according to the present invention. Wherein the information matching system based on hemoptysis traits and diseases comprises: the device comprises an acquisition module 10, a conversion module 20, a calculation module 30 and a recording module 40.
An obtaining module 10, configured to obtain hemoptysis trait information and corresponding disease information, and respectively establish corresponding space vector sets according to the hemoptysis trait information and the corresponding disease information;
the conversion module 20 is configured to obtain hemoptysis trait information to be calculated, and establish a corresponding space vector set to be calculated according to the hemoptysis trait information to be calculated;
the calculation module 30 is configured to construct a radial basis function neural network model, convert the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculate the vector sets to be matched, and generate corresponding matching values;
and the recording module 40 is used for generating an information matching report of the corresponding hemoptysis character and disease according to the matching numerical value.
Further, as shown in fig. 2, a block diagram of a second embodiment of the information matching system based on hemoptysis trait and disease according to the present invention is proposed based on the above embodiments, and in this embodiment, the obtaining module 10 further includes:
a feature extraction module 101, configured to obtain hemoptysis trait information and corresponding disease information, where the hemoptysis trait information includes: hemoptysis trait information and corresponding accompanying symptom information, the disease information comprising: and extracting words with the maximum numerical values from the hemoptysis character information and the corresponding disease information through TF-IDF to serve as feature words.
The set establishing module 102 is configured to establish different space vector sets according to the hemoptysis trait feature words, the accompanying symptom feature words, the disease feature words and the disease symptom feature words, store the accompanying symptom feature words, the disease feature words and the disease symptom feature words into corresponding space vector sets according to the corresponding relationship, and establish a corresponding relationship table.
It should be understood that the system will obtain hemoptysis trait information, including: hemoptysis trait information and corresponding accompanying symptom information, the disease information comprising: disease information and disease symptom information, wherein the acquired information comprises: news, medical history, and treatises, etc.
It should be understood that the system further extracts the words with the largest TF-IDF value from the information items according to the TF-IDF, and uses these words as feature words, and the extracted feature words are exemplified as follows:
wherein, the characteristic information of hemoptysis character comprises: the color, form, amount, inclusion, etc. of hemoptysis, such as color: hemoptysis due to pulmonary tuberculosis, bronchiectasis, lung abscess and hemorrhagic diseases, and its color is bright red; rust-colored sputum can be seen in typical pneumococcal pneumonia, as well as in paragonimiasis and alveolar hemorrhage; brick red jelly-like sputum is found in typical klebsiella pneumoniae; hemoptysis caused by mitral stenosis is mostly dark red; hemoptysis caused by left heart failure is serous pink foam sputum; hemoptysis caused by pulmonary embolism is sticky dark red blood sputum; further examples are the number: the standard of the amount of hemoptysis is not defined clearly, but it is generally considered that the amount of hemoptysis per day is small within 100ml, medium within 100-500 ml, and large within 500ml or 100-500 ml per time. A large number of hemoptysis are mainly seen in cavitary tuberculosis, bronchiectasis and chronic lung abscess. Bronchopulmonary carcinoma has little hemoptysis, which is mainly manifested as blood-stained sputum with continuous or intermittent characteristics. Chronic bronchitis and mycoplasmal pneumonia can also present with bloody or bloody sputum in the sputum, but often with severe coughing.
The hemoptysis associated symptom information includes: before the blood, patients often have symptoms such as itching throat, cough and the like; chest pain, palpitation, cyanosis and other accompanying symptoms can occur during hemoptysis; for example, in addition to hemoptysis, patients with pulmonary embolism are accompanied by symptoms of dyspnea, pale complexion, dysphoria, cyanosis, fever, thin and weak pulse, heart rate increase, precordial flushing, moist rales in the lungs, irritative cervical vein, liver swelling, and other acute right heart dysfunction such as mental stress, chest pain, chest distress, cough, palpitation, cold limbs, sweating, and the like.
The disease information and the disease symptom information include: all diseases corresponding to hemoptysis can be divided into four major groups, namely bronchial diseases, pulmonary diseases, cardiovascular diseases, systemic diseases and the like. The systemic diseases are classified into hematological diseases and acute infectious diseases. The method specifically comprises the following steps: bronchial diseases: it is commonly seen in bronchiectasis, bronchopulmonary carcinoma, endobronchial tuberculosis, bronchitis, intrabronchial calculus, and intrabronchial foreign body; pulmonary diseases: it is commonly seen in pulmonary tuberculosis, lung abscess, pneumonia, pulmonary infarction, and lung fluke; cardiovascular diseases: most commonly seen in rheumatic mitral stenosis and left heart failure, with hemoptysis due to pulmonary congestion, which is relatively low in blood volume. The amount of blood is high due to hemoptysis caused by rupture of varices in the bronchial submucosa veins. Collateral circulation exists between the pulmonary vein and the bronchial vein, and the small vein pressure in the sub-mucosal layer of the bronchial tract is increased due to the increase of the pulmonary vein pressure, so that the blood is curved and cracked, and the bleeding is more acute. Hemoptysis can also occur when pulmonary hypertension is caused by certain congenital heart diseases such as atrial septal defect, patent ductus arteriosus and the like; systemic diseases: blood diseases: such as thrombocytopenic purpura, leukemia, hemophilia, etc.; acute infectious diseases: it is commonly seen in leptospirosis and epidemic hemorrhagic fever.
The disease information and disease symptom information further include: the early symptoms of pulmonary tuberculosis are afternoon fever, the body temperature is 37.5 ℃ or 38 ℃, the early symptoms are obvious from afternoon to night, and some patients can have symptoms of flushing, night sweat, cough, expectoration and hemoptysis. The conventional anti-infection treatment effect is not obvious, the body temperature is not obviously reduced, the cough and expectoration are not obviously improved, the hemogram inflammation index is possibly normal, and the chest film or chest CT shows that exudative lesion or spot-shaped shadow, cavities and the like exist in the lung; in clinic, patients with pneumonia can have symptoms of cough, expectoration, chest pain, dyspnea, even severe fever, anorexia and the like, and the pneumonia can find the actually changed shadows of the lung with spots and pieces, even large pieces and the like on X-ray.
It should be understood that, in order to facilitate subsequent storage and calculation, the system may further establish different space vector sets according to the hemoptysis trait feature word, and then store the accompanying symptom, the disease information, and the disease symptom corresponding to the hemoptysis trait feature word as vectors into the corresponding space vector sets, where the accompanying symptom, the disease information, and the disease symptom may correspond to a plurality of space vector sets.
Further, as shown in fig. 3, a block diagram of a third embodiment of the information matching system based on hemoptysis trait and disease of the present invention is proposed based on the above embodiments, and in this embodiment, the conversion module 20 further includes:
the vectorization module 201 is configured to obtain hemoptysis trait information to be calculated, where the hemoptysis trait information to be calculated includes: verifying the integrity of the hemoptysis trait information to be calculated, extracting a word with the maximum value from the hemoptysis trait information to be calculated which passes integrity verification by using TF-IDF as a hemoptysis trait feature word to be calculated and an accompanying symptom feature word to be calculated, establishing a space vector set to be calculated according to the hemoptysis trait feature word to be calculated, and storing the accompanying symptom feature word to be calculated into a corresponding space vector set to be calculated.
It should be understood that, in order to facilitate the operation of the subsequent system and improve the system processing efficiency, after the hemoptysis trait information to be calculated is obtained, the system performs the same processing on the hemoptysis trait information to be calculated according to the steps of the above embodiment, the hemoptysis trait information to be calculated mainly consists of medical records, the system firstly verifies the integrity of the hemoptysis trait information to be calculated, the verification mode is to verify the integrity of the medical records, and only the complete medical records can extract feature words from the medical records by using TF-IDF and generate corresponding space vector sets to be calculated.
Further, as shown in fig. 4, a block diagram of a fourth embodiment of the information matching system based on hemoptysis trait and disease according to the present invention is proposed based on the above embodiments, and in this embodiment, the calculation module 30 includes:
the initialization module 301 is configured to construct a radial basis function neural network model, use the space vector set and the space vector set to be calculated as a vector set to be matched, place the vector set to be matched in the input layer, initialize the connection weight from the hidden layer to the output layer and the central parameters of each neuron in the hidden layer, and initialize the width vector.
And the calculation output module 302 is configured to calculate an output value of a neuron of the output layer according to the vector set to be matched and the connection weight of the input layer, and iterate the output value according to the central parameter and the width vector to obtain an iteration value as a matching value.
It should be understood that the system may calculate the matching value between the hemoptysis trait information to be calculated and the hemoptysis trait information by establishing a radial basis function neural network model and then using the radial basis function neural network model.
It should be understood that the radial basis function neural network nonlinearly maps the data to a high-dimensional linear space through the radial basis functions, and then fits or regresses the high-dimensional space with a linear model. The network comprises three layers, wherein the first layer is an input layer and comprises N nodes (namely characteristics or data); the second layer is a hidden layer and comprises M nodes, and each node is an activation function and is used for mapping the data of the input layer to a high-dimensional space in a nonlinear manner; the third layer is the output layer, where only one value is output. Here, the output of the radial basis function neural network is a predicted value of the SYNTAX integral, and it is estimated from the network output that the characteristic information of the hemoptysis trait of the subject corresponds to the characteristic information of the accompanying symptom, which is a possible lesion.
The specific method comprises the following steps: input vector X, corresponding target output vector Y and width vector D of radial basis functionj. In the training of the I < th > input sample (1, 2., N), the expression and calculation method of each parameter is as follows:
firstly, parameters are determined, and an input vector X is determined, wherein X is [ X ]1,x2,...,xn]TN is the number of input layer units, where the input vector X is the set of spatial vectors to be computed, and the determined output vector Y and the desired output vector O are determined, Y ═ Y1,y2,...,yq]TQ is the number of output layer units, O ═ O1,o2,...,oq]TThe output vector Y is a set of spatial vectors, and it is expected that the output vector is set by an administrator, but is generally a constant.
The implicit layer to output layer connection weights are then initialized, i.e., Wk=[wk1,wk2,...,wkp]TAnd (k ═ 1, 2.. q), wherein p is the number of hidden layer units, q is the number of output layer units, then the system initializes the central parameters of each neuron of the hidden layer, and it is noted that the centers of different hidden layer neurons should have different values, and the corresponding widths of the centers can be adjusted, so that different input information characteristics can be maximally reflected by different hidden layer neurons. In practical applications, an input message is always included in a certain range of values. Without loss of generality, the initial values of the central components of the neurons of the hidden layer are changed at equal intervals from small to large, so that weak input information generates strong response near a small center. The size of the space can be adjusted by the number of hidden layer neurons. The method has the advantages that the reasonable number of the hidden layer neurons can be found through a trial and error method, the initialization of the center is reasonable as much as possible, different input characteristics are reflected in different centers more obviously, and the characteristics of the Gaussian kernel are reflected.
The system then initializes a width vector that affects the extent to which the neuron acts on the input information: the smaller the width is, the narrower the shape of the corresponding hidden layer neuron action function is, the smaller the response of information near the center of other neurons in the neuron is, and finally the system can calculate the output of the output layer neuron and iterate the output value according to the center parameter and the width vector to obtain an iteration value as a matching value.
Further, as shown in fig. 5, a block diagram of a fifth embodiment of the information matching system based on hemoptysis trait and disease according to the present invention is proposed based on the above embodiments, and in this embodiment, the recording module 40 includes:
the matching storage module 401 is configured to set a matching threshold, compare the matching value with the matching threshold, store corresponding data in the radial basis function neural network model when the matching value is greater than the matching threshold, establish association with the space vector set, and produce a corresponding matching report according to the space vector set.
It should be understood that, the system will set a matching threshold value finally, compare the matching value with the matching threshold value, when the matching value is greater than the matching threshold value, store the corresponding data in the radial basis function neural network model, then store the space vector set to be calculated and the space vector set together in the same place according to the corresponding relationship, and mark the space vector set, so as to facilitate later-stage calling, then establish association with the space vector set, and produce a corresponding matching report according to the space vector set.
The above description is only for illustrative purposes and does not limit the technical solutions of the present application in any way.
As can be easily found from the above description, the present embodiment provides an information matching system based on hemoptysis trait and disease, including: the acquisition module is used for acquiring hemoptysis character information and corresponding disease information and respectively establishing corresponding space vector sets according to the hemoptysis character information and the corresponding disease information; the conversion module is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated according to the hemoptysis character information to be calculated; the calculation module is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculating the vector sets to be matched and generating corresponding matching values; and the recording module is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value. According to the embodiment, the matching numerical value between the two confidences is calculated by constructing the radial basis function neural network model, the calculation accuracy is improved, and meanwhile, the data are stored, so that the relevance between the data can be enhanced, and the data loss is prevented.
In addition, the embodiment of the invention also provides information matching equipment based on hemoptysis characters and diseases. As shown in fig. 6, the information matching apparatus based on hemoptysis trait and disease includes: an acquisition unit 10, a conversion unit 20, a calculation unit 30, and a recording unit 40.
An obtaining unit 10, configured to obtain hemoptysis trait information and corresponding disease information, and respectively establish corresponding space vector sets according to the hemoptysis trait information and the corresponding disease information;
the conversion unit 20 is configured to obtain hemoptysis trait information to be calculated, and establish a corresponding space vector set to be calculated according to the hemoptysis trait information to be calculated;
the calculating unit 30 is configured to construct a radial basis function neural network model, convert the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculate the vector sets to be matched, and generate corresponding matching values;
and the recording unit 40 is used for generating an information matching report of the corresponding hemoptysis character and disease according to the matching numerical value.
In addition, it should be noted that the above-described embodiments of the apparatus are merely illustrative, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of the modules to implement the purpose of the embodiments according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment can be referred to the information matching system based on hemoptysis trait and disease provided in any embodiment of the present invention, and are not described herein again.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An information matching system based on hemoptysis traits and diseases, comprising:
the acquisition module is used for acquiring hemoptysis character information and corresponding disease information and respectively establishing corresponding space vector sets according to the hemoptysis character information and the corresponding disease information;
the conversion module is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated according to the hemoptysis character information to be calculated;
the calculation module is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be calculated into corresponding vector sets to be matched through the radial basis function neural network model, calculating the vector sets to be matched and generating corresponding matching values;
and the recording module is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value.
2. The information matching system based on hemoptysis trait and disease as claimed in claim 1, wherein: the acquisition module comprises a feature extraction module and is used for acquiring hemoptysis trait information and corresponding disease information, wherein the hemoptysis trait information comprises: hemoptysis trait information and corresponding accompanying symptom information, the disease information comprising: and extracting words with the maximum numerical values from the hemoptysis character information and the corresponding disease information through TF-IDF to serve as feature words.
3. The information matching system based on hemoptysis trait and disease as claimed in claim 2, wherein: the acquisition module comprises a set establishment module for establishing different space vector sets according to the hemoptysis character characteristic words, the accompanying symptom characteristic words, the disease characteristic words and the disease symptom characteristic words, storing the accompanying symptom characteristic words, the disease characteristic words and the disease symptom characteristic words into corresponding space vector sets according to the corresponding relation and establishing a corresponding relation table.
4. The information matching system based on hemoptysis trait and disease as claimed in claim 3, wherein: the conversion module comprises a vectorization module and is used for acquiring hemoptysis character information to be calculated, wherein the hemoptysis character information to be calculated comprises: verifying the integrity of the hemoptysis trait information to be calculated, extracting a word with the maximum value from the hemoptysis trait information to be calculated which passes integrity verification by using TF-IDF as a hemoptysis trait feature word to be calculated and an accompanying symptom feature word to be calculated, establishing a space vector set to be calculated according to the hemoptysis trait feature word to be calculated, and storing the accompanying symptom feature word to be calculated into a corresponding space vector set to be calculated.
5. The information matching system based on hemoptysis trait and disease as claimed in claim 4, wherein: the calculation module comprises an initialization module used for constructing a radial basis function neural network model, taking a space vector set and a space vector set to be calculated as a vector set to be matched, putting the vector set to be matched into an input layer, initializing a connection weight value from a hidden layer to an output layer and central parameters of each neuron of the hidden layer, and initializing a width vector.
6. The information matching system based on hemoptysis trait and disease as claimed in claim 5, wherein: the calculation module comprises a calculation output module, and is used for calculating the output value of the neuron of the output layer according to the vector set to be matched and the connection weight of the input layer, and iterating the output value according to the central parameter and the width vector to obtain an iteration value as a matching value.
7. The information matching system based on hemoptysis trait and disease as claimed in claim 6, wherein: the recording module comprises a matching storage module, and is used for setting a matching threshold, comparing a matching value with the matching threshold, storing corresponding data in the radial basis function neural network model when the matching value is greater than the matching threshold, establishing association with the space vector set, and producing a corresponding matching report according to the space vector set.
8. An information matching apparatus based on hemoptysis trait and disease, comprising:
the acquiring unit is used for acquiring hemoptysis character information and corresponding disease information and respectively establishing corresponding space vector sets according to the hemoptysis character information and the corresponding disease information;
the conversion unit is used for acquiring the hemoptysis character information to be calculated and establishing a corresponding space vector set to be calculated according to the hemoptysis character information to be calculated;
the computing unit is used for constructing a radial basis function neural network model, converting the space vector set and the space vector set to be computed into corresponding vector sets to be matched through the radial basis function neural network model, computing the vector sets to be matched and generating corresponding matching values;
and the recording unit is used for generating a corresponding hemoptysis character and disease information matching report according to the matching numerical value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011124012.7A CN112233750B (en) | 2020-10-20 | 2020-10-20 | Information matching system based on hemoptysis characters and diseases |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011124012.7A CN112233750B (en) | 2020-10-20 | 2020-10-20 | Information matching system based on hemoptysis characters and diseases |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112233750A true CN112233750A (en) | 2021-01-15 |
CN112233750B CN112233750B (en) | 2024-02-02 |
Family
ID=74118071
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011124012.7A Active CN112233750B (en) | 2020-10-20 | 2020-10-20 | Information matching system based on hemoptysis characters and diseases |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112233750B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6135966A (en) * | 1998-05-01 | 2000-10-24 | Ko; Gary Kam-Yuen | Method and apparatus for non-invasive diagnosis of cardiovascular and related disorders |
CN1653025A (en) * | 2002-03-13 | 2005-08-10 | 先灵公司 | NK1 antagonists |
WO2013186634A2 (en) * | 2012-06-14 | 2013-12-19 | Singapore Health Services Pte Ltd. | Predicting acute cardiopulmonary events and survivability of a patient |
CN105740612A (en) * | 2016-01-27 | 2016-07-06 | 北京国医精诚科技有限公司 | Traditional Chinese medicine clinical medical record based disease diagnose and treatment method and system |
CN108577883A (en) * | 2018-04-03 | 2018-09-28 | 上海交通大学 | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods |
CN109243538A (en) * | 2018-07-19 | 2019-01-18 | 长沙学院 | A kind of method and system of predictive disease and LncRNA incidence relation |
CN110693526A (en) * | 2019-11-11 | 2020-01-17 | 深圳先进技术研究院 | Muscle disease assessment method and system and electronic equipment |
CN111091911A (en) * | 2019-12-30 | 2020-05-01 | 重庆同仁至诚智慧医疗科技股份有限公司 | System and method for screening stroke risk |
CN111261278A (en) * | 2018-11-30 | 2020-06-09 | 上海图灵医疗科技有限公司 | Heart disease detection method based on deep learning model of three-dimensional image |
CN111261277A (en) * | 2018-11-30 | 2020-06-09 | 上海图灵医疗科技有限公司 | Heart disease detection method based on deep learning model |
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 |
CN112017771A (en) * | 2020-08-31 | 2020-12-01 | 吾征智能技术(北京)有限公司 | Method and system for constructing disease prediction model based on semen routine examination data |
-
2020
- 2020-10-20 CN CN202011124012.7A patent/CN112233750B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6135966A (en) * | 1998-05-01 | 2000-10-24 | Ko; Gary Kam-Yuen | Method and apparatus for non-invasive diagnosis of cardiovascular and related disorders |
CN1653025A (en) * | 2002-03-13 | 2005-08-10 | 先灵公司 | NK1 antagonists |
WO2013186634A2 (en) * | 2012-06-14 | 2013-12-19 | Singapore Health Services Pte Ltd. | Predicting acute cardiopulmonary events and survivability of a patient |
CN105740612A (en) * | 2016-01-27 | 2016-07-06 | 北京国医精诚科技有限公司 | Traditional Chinese medicine clinical medical record based disease diagnose and treatment method and system |
CN108577883A (en) * | 2018-04-03 | 2018-09-28 | 上海交通大学 | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods |
CN109243538A (en) * | 2018-07-19 | 2019-01-18 | 长沙学院 | A kind of method and system of predictive disease and LncRNA incidence relation |
CN111261278A (en) * | 2018-11-30 | 2020-06-09 | 上海图灵医疗科技有限公司 | Heart disease detection method based on deep learning model of three-dimensional image |
CN111261277A (en) * | 2018-11-30 | 2020-06-09 | 上海图灵医疗科技有限公司 | Heart disease detection method based on deep learning model |
CN110693526A (en) * | 2019-11-11 | 2020-01-17 | 深圳先进技术研究院 | Muscle disease assessment method and system and electronic equipment |
CN111091911A (en) * | 2019-12-30 | 2020-05-01 | 重庆同仁至诚智慧医疗科技股份有限公司 | System and method for screening stroke risk |
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 |
CN112017771A (en) * | 2020-08-31 | 2020-12-01 | 吾征智能技术(北京)有限公司 | Method and system for constructing disease prediction model based on semen routine examination data |
Non-Patent Citations (2)
Title |
---|
MEHRABI, S等: "Application of multilayer perceptron and radial basis function neural networks in differentiating between chronic obstructive pulmonary and congestive heart failure diseases", EXPERT SYSTEMS WITH APPLICATIONS, vol. 36, no. 3, pages 6956 - 6959, XP025914587, DOI: 10.1016/j.eswa.2008.08.039 * |
宁建飞;黄发良;: "基于词向量句子相似度量的医疗科室推荐", 福建师范大学学报(自然科学版), no. 04, pages 16 - 21 * |
Also Published As
Publication number | Publication date |
---|---|
CN112233750B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI596600B (en) | Method and system for recognizing physiological sound | |
Pandey et al. | Quality controlled ECG data compression based on 2D discrete cosine coefficient filtering and iterative JPEG2000 encoding | |
Kung et al. | An efficient ECG classification system using resource-saving architecture and random forest | |
WO2021017313A1 (en) | Atrial fibrillation detection method and apparatus, computer device, and storage medium | |
US20230397887A1 (en) | Scatter diagram classification method and apparatus for photoplethysmography signal | |
WO2022267381A1 (en) | Patient-ventilator asynchrony classification method and system, terminal and storage medium | |
WO2022073374A1 (en) | Heartbeat tag data sequence generation method and apparatus based on multi-lead electrocardiogram signal | |
CN111528832B (en) | Arrhythmia classification method and validity verification method thereof | |
CN108091391A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
CN110400610B (en) | Small sample clinical data classification method and system based on multichannel random forest | |
US20230371831A1 (en) | Method and apparatus for predicting blood pressure by fusing calibrated photoplethysmographic signal data | |
WO2021184802A1 (en) | Blood pressure classification prediction method and apparatus | |
CN116961675A (en) | Intelligent processing method for medical care data | |
CN113539398A (en) | Breathing machine man-machine asynchronous classification method, system, terminal and storage medium | |
Li et al. | A one-dimensional Siamese few-shot learning approach for ECG classification under limited data | |
CN114328988A (en) | Multimedia data feature extraction method, multimedia data retrieval method and device | |
CN112233750A (en) | Information matching system based on hemoptysis character and disease | |
CN112914528B (en) | Model generation method, device and computer readable medium for cuff-free blood pressure measurement | |
CN113855042A (en) | Sequence labeling-based multi-lead electrocardiosignal classification method fusing depth and medical characteristics | |
CN108305688A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
CN112382397A (en) | Bridge vessel-based model construction method, device, equipment and storage medium | |
CN112560784B (en) | Electrocardiogram classification method based on dynamic multi-scale convolutional neural network | |
Gaudilliere et al. | Generative pre-trained transformer for cardiac abnormality detection | |
CN111755022A (en) | Mixed auscultation signal separation method based on time sequence convolution network and related device | |
CN108596017A (en) | A kind of method and device based on picture recognition diseases of garden stuff |
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 |