CN110634566A - Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal - Google Patents
Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal Download PDFInfo
- Publication number
- CN110634566A CN110634566A CN201910907000.2A CN201910907000A CN110634566A CN 110634566 A CN110634566 A CN 110634566A CN 201910907000 A CN201910907000 A CN 201910907000A CN 110634566 A CN110634566 A CN 110634566A
- Authority
- CN
- China
- Prior art keywords
- data
- mining
- diagnosis
- obj
- processing
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012545 processing Methods 0.000 title claims abstract description 53
- 238000003759 clinical diagnosis Methods 0.000 title claims abstract description 41
- 239000003814 drug Substances 0.000 title claims abstract description 34
- 238000003745 diagnosis Methods 0.000 claims abstract description 50
- 238000007418 data mining Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000005065 mining Methods 0.000 claims abstract description 29
- 201000010099 disease Diseases 0.000 claims abstract description 24
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 24
- 208000011580 syndromic disease Diseases 0.000 claims abstract description 22
- 230000009467 reduction Effects 0.000 claims abstract description 20
- 230000004069 differentiation Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 7
- 208000024891 symptom Diseases 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 230000000052 comparative effect Effects 0.000 claims 1
- 238000010276 construction Methods 0.000 abstract description 2
- 230000036541 health Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 210000004556 brain Anatomy 0.000 description 4
- 208000037386 Typhoid Diseases 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 201000008297 typhoid fever Diseases 0.000 description 3
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 238000012067 mathematical method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010063659 Aversion Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 238000001467 acupuncture Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000000291 postprandial effect Effects 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of alternative medicine, e.g. homeopathy or non-orthodox
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Bioethics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Alternative & Traditional Medicine (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of data mining, and discloses a system and a method for processing traditional Chinese medicine clinical diagnosis data and an information data processing terminal; the method comprises the following steps: a data mining module; a diagnostic data analysis module; a clinical diagnostic information reduction module; a clinical diagnostic data reduction module; and a syndrome differentiation and classification module. Mining the diagnostic data by adopting a data mining learning algorithm; analyzing diagnosis and treatment data of a large number of patients; the contrast mining in the data mining is adopted to complete the reduction of clinical diagnosis information; training the diagnostic data through a training data set based on a data mining method; reducing the clinical diagnosis data and processing by using a computer; and (5) performing syndrome differentiation, classification and storage. The invention has scientific mining basis, accurate diagnosis, reduced diagnosis range, reduced misdiagnosis rate, and quickest comparison of similar diseases for making judgment; the requirements of the national key construction primary health system are met, the medical level of primary doctors is improved, and the medical cost is reduced.
Description
Technical Field
The invention belongs to the technical field of data mining, and particularly relates to a system and a method for processing traditional Chinese medicine clinical diagnosis data and an information data processing terminal.
Background
Currently, the current state of the art commonly used in the industry is such that:
the application of data mining technology in the process of traditional Chinese medicine disease diagnosis is a new application of data mining research in recent years, the treatment and diagnosis of diseases have some statistical characteristics, the process is completed by means of experience and intuition accumulated by doctors in the past, the brain is used for processing basic information, disease conditions and symptoms of patients, but the judgment capability of diseases is limited by insufficient accumulated experience of people and the limitation of the brain, and the brain is insufficient to deal with the diseases when the disease conditions become extremely complicated. The computer has excellent performance in the aspects of mathematical statistics and logical reasoning compared with the human brain, so that the data mining technology has high application value in the traditional Chinese medicine diagnostics. Modern medicine accumulates a large amount of diagnostic data, and processing large data is the characteristic of computers with increasingly strong performance, and the processing of the computers can eliminate interference of human factors as much as possible. The syndrome is the theoretical essence and important concept of the diagnosis of traditional Chinese medicine, and the inquiry of traditional Chinese medicine is mainly the judgment of the syndrome. At present, the traditional Chinese medicine syndrome judgment lacks a uniform standard and has the phenomenon of non-uniform description and classification. Therefore, the normalization of syndrome is the key point of applying data mining technology in diagnostics of traditional Chinese medicine. For example, Chenming et al tried to establish a database with disease names, symptoms, tongue veins, etc. in Shanghai Zhang Zhongjing, written in the beginning of the 3 rd century of the public Ministry as data, and then to mine the typhoid diagnosis mode by applying the association rules. The research finds that: the dampness-heat collateral obstruction, the cold-dampness collateral obstruction and the deficiency of both qi and yin are more than the typhoid fever (the confidence coefficient is 5 percent and the support degree is 65 percent), so the dampness-heat collateral obstruction, the cold-dampness collateral obstruction and the deficiency of both qi and yin are considered as the diagnosis basis of the typhoid fever. Qin Zhongguang et al apply rough set algorithm in data mining to diagnose and research the rheumatoid syndromes in traditional Chinese medicine, and they obtain possible rules and certain rules of floating pulse, aversion to cold and fever by using reduction attribute method. In 55 cases of prediction diagnosis, the correct diagnosis rate reaches more than 95 percent, which is higher than that of the fuzzy mathematical method used before, the experiment ensures that the data mining rough set algorithm is probably more suitable for being used as a tool for traditional Chinese medicine diagnosis than the fuzzy mathematical method, and the data mining technology is considered to have wider and more important application in the traditional Chinese medicine diagnosis. During the course of treatment, the rules of treatment change over time, which is reflected in the prescription of the patient. The prescriptions made for patients with similar disease conditions may change continuously with the abundance of doctor experience, so that only establishing a static famous and old medical rule mining model does not conform to the actual rule of doctor's seeing, and a system capable of evolving and progressing continuously according to the increase of doctor clinical prescriptions is needed.
In summary, the problems of the prior art are as follows:
(1) in the prior art, the mining of big data is unscientific, the diagnosis is inaccurate, the diagnosis range is large, the misdiagnosis rate is high, and the similar diseases cannot be quickly and accurately compared, so that the judgment is made and inaccurate;
(2) the traditional Chinese medicine only diagnoses by experience, can not carry out scientific data analysis and can not dig out medical rules;
(3) at present, the traditional Chinese medicine syndrome judgment lacks a uniform standard and has the phenomenon of non-uniform description and classification.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a system and a method for processing traditional Chinese medicine clinical diagnosis data and an information data processing terminal.
The invention is realized in such a way that a method for processing traditional Chinese medicine clinical diagnosis data comprises the following steps:
the method comprises the following steps: mining the diagnostic data by adopting a data mining learning algorithm;
step two: analyzing the diagnosis and treatment data of a large number of mined patients to obtain medical diagnosis rules;
step three: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
step four: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
step five: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
step six: and (4) carrying out syndrome differentiation and classification on the clinical diagnosis data processed by the computer, and storing.
Further, in the step one, a local outlier data algorithm is adopted in data mining: let vi be the subspace definition vector of obj, d ═ viDimension of (a), λijIs a local sparse factor, d, corresponding to the jth attribute dimension of objRS(o, s) represents the euclidean distance between data objects s and o in the relevant subspace RS, obj relative to the local data set lds (obj), the standard distance in its relevant subspace RS being:
in the relevant subspace RS of obj, any nearest neighbor loc _ obj ∈ lds (obj) of obj (assuming loc _ obj is the mth data object) is relative to:
the standard distance of LDS (loc _ obj) is:
the probability local anomaly factor PLOF of obj in its relevant subspace RS is:
in the formula, PLOFRS(obj) and PLOFRS(loc _ obj) describes the degree of local outliers of loc _ obj in the relevant subspace RS of obj, similar to the local outlier factor LOF in the relevant subspace RS of obj.
Further, in the step one, the nonlinear least square principle and solution method in the ifelong learning algorithm are adopted as follows: the method is provided with the following measurement data: (t)i，yi) I 1, 2.. said, m; and selecting a model of the fitted curve as y (t) phi (t; x); wherein the parameter x ═ x1，x2，…xn)T∈Rn，n＜m，y(t)，y(t)Is a non-linear function of x; selecting y according to the least squares principle(t)Such that y is(t)The sum of the squares of the differences from the measured function at the discrete points is minimal, x is a problem:
φi(x)＝φ(ii；x)-yi，
if the term F (x) ═ phi means1(x)，φ2(x)，…，φm(x))T；
Then write to:
furthermore, in the third step, comparison and mining are carried out, the weight of a plurality of symptoms for diagnosing a certain disease is counted, and dimension reduction processing is carried out on syndrome differentiation data.
Further, in the third step, the key symptom for judging a certain disease is found based on the exposure pattern mining in the comparison mining, that is, for an item set, when the difference of the support degrees of the item set in different data sets is larger than a specified threshold value, the item set is called the exposure pattern.
Further, in the third step, the comparison mining algorithm mainly includes the following steps:
(1) for any one attribute AiAssuming it has miThe attribute values are expressed by { theta 1, theta 2.,. theta m i }, and the probabilities corresponding to the attribute values are p respectively1，p2，...，pmiAnd the information entropy calculation formula corresponding to each attribute value is as follows:
(2) by means ofComputing Attribute AiThe corresponding entropy;
(3) continue to calculate attribute Ai+1，Ai+2,.. corresponding entropy values, and selecting the attribute corresponding to the minimum entropy value as a node from all the entropy values;
(4) continuing each subsequent node according to the methods (1) to (3);
(5) when each node determined by the new round of calculation results is a leaf node, the decision tree is constructed; otherwise, the steps are continuously executed, and the clinical diagnosis information of the patient is digitalized frequently and simply.
Another object of the present invention is to provide a chinese medical clinical diagnostic data processing system for implementing the method for processing chinese medical clinical diagnostic data, the system comprising:
a data mining module: mining the diagnostic data by using a life learning algorithm in data mining;
a diagnostic data analysis module: analyzing the mined diagnosis and treatment data of a large number of patients; digging out medical diagnosis rules with high medical value;
clinical diagnosis information simplification module: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
a data training module: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
clinical diagnostic data reduction module: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
a syndrome differentiation and classification module: and (4) carrying out syndrome differentiation and classification on the diagnosis data processed by the computer, and storing.
Another object of the present invention is to provide a computer program for implementing the method for processing clinical diagnostic data of chinese medical science.
Another object of the present invention is to provide an information data processing terminal for implementing the method for processing clinical diagnosis data of chinese medicine.
Another object of the present invention is to provide a computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to execute the method for processing clinical diagnostic data of chinese medical science.
In summary, the advantages and positive effects of the invention are:
the invention provides a system and a method for processing traditional Chinese medicine clinical diagnosis data, wherein (1) the system has scientific big data mining basis, more accurate diagnosis, minimized diagnosis range, reduced misdiagnosis rate, and fastest comparison for similar diseases to make judgment; (2) meanwhile, the requirement of national key construction of a basic health system is met, the medical level of basic doctors can be greatly improved, and the medical cost is reduced; (3) the questionnaire survey of 44 hospitals in 12 provinces (prefecture city) in the country in the early stage of the invention shows that 92.36% of the visitors need the services of auxiliary diagnosis and acupuncture evidence-based diagnosis and treatment schemes. (4) The method is applied to the field of traditional Chinese medicine disease diagnosis, a large number of diagnosis rules with good objectivity and comprehensiveness are obtained, and medical diagnosis rules with high medical value can be mined by analyzing diagnosis and treatment data of a large number of patients; the data mining technology based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm is trained through the training data set, so that medical decision making of a doctor can be effectively assisted, and the diagnosis level of the doctor is improved.
Drawings
Fig. 1 is a block diagram of a system for processing clinical diagnostic data of traditional Chinese medicine according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for processing clinical diagnostic data of traditional Chinese medicine according to an embodiment of the present invention.
In the figure: 1. a data mining module; 2. a diagnostic data analysis module; 3. a clinical diagnostic information reduction module; 4. a data training module; 5. a clinical diagnostic data reduction module; 6. and a syndrome differentiation and classification module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention is explained in further detail below with reference to the drawings;
as shown in fig. 1, a system for processing data of clinical diagnosis in traditional chinese medicine provided by an embodiment of the present invention includes: a data mining module 1; a diagnostic data analysis module 2; a clinical diagnosis information simplifying module 3; a data training module 4; a clinical diagnostic data reduction module 5; and a syndrome differentiation and classification module 6.
The data mining module 1: mining the diagnostic data by adopting a data mining learning algorithm;
diagnostic data analysis module 2: analyzing the mined diagnosis and treatment data of a large number of patients; digging out medical diagnosis rules with high medical value;
clinical diagnostic information reduction module 3: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
the data training module 4: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
clinical diagnostic data reduction module 5: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
and a syndrome differentiation and classification module 6: and (4) carrying out syndrome differentiation and classification on the diagnosis data processed by the computer, and storing.
As shown in fig. 2, a method for processing data of clinical diagnosis in traditional Chinese medicine provided by the embodiment of the present invention:
s101: mining the diagnostic data by adopting a data mining learning algorithm;
s102: analyzing the diagnosis and treatment data of a large number of mined patients to obtain medical diagnosis rules;
s103: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
s104: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
s105: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
s106: and (4) carrying out syndrome differentiation and classification on the clinical diagnosis data processed by the computer, and storing.
In step S101, the data mining provided in the embodiment of the present invention adopts a local outlier data algorithm:
let vi be the subspace definition vector of obj, d ═ viDimension of (a), λijIs a local sparse factor, d, corresponding to the jth attribute dimension of objRS(o, s) represents the euclidean distance between data objects s and o in the relevant subspace RS, obj relative to the local data set lds (obj), the standard distance in its relevant subspace RS being:
in the relevant subspace RS of obj, any nearest neighbor of obj, loc _ obj ∈ LDS (obj) (it is assumed that loc _ obj is the mth data object), is relative to
The standard distance of LDS (loc _ obj) is:
the probability local anomaly factor PLOF of obj in its relevant subspace RS is:
in the formula (2) and the formula (3), PLOFRS(obj) and PLOFRS(loc _ obj) describes the degree of local outliers of loc _ obj in the relevant subspace RS of obj, similar to the local outlier factor LOF in the relevant subspace RS of obj.
In step S101, the nonlinear least square principle and solution method in the ifelong learning algorithm provided in the embodiment of the present invention specifically include:
the method is provided with the following measurement data: (t)i，yi) I 1, 2.. said, m; and selecting a model of the fitted curve as y (t) phi (t; x); wherein the parameter x ═ x1，x2，…xn)T∈Rn，n＜m，y(t)，y(t)Is a non-linear function of x, selecting y according to the least squares principle(t)Such that y is(t)The sum of the squares of the differences from the measured function at discrete points is minimal, x being a problem
φi(x)＝φ(ii；x)-yi，
If the term F (x) ═ phi means1(x)，φ2(x)，…，φm(x))T
The above formula can be written as
The addition coefficient 1/2 is only for calculation convenience, and has no influence on the extreme problem solution.
In step S103, the comparison and mining provided by the embodiment of the present invention counts the weight of a plurality of symptoms for diagnosing a certain disease, and performs dimensionality reduction on syndrome differentiation data.
In step S103, the exposure pattern mining provided by the embodiment of the present invention finds key symptoms for determining a certain disease based on the exposure pattern mining, that is, for an item set, when the difference of the support degrees of the item set in different data sets is greater than a specified threshold, the item set is called an exposure pattern.
In step S103, the comparison mining algorithm provided in the embodiment of the present invention mainly includes the following steps:
(1) for any one attribute AiAssuming it has miThe attribute values can be represented by { theta 1, theta 2.,. theta m i }, and the probability corresponding to the attribute values is p1，p2，...，pmiAnd the information entropy calculation formula corresponding to each attribute value is as follows:
(2) by means of
Computing Attribute AiThe corresponding entropy;
(3) according to the method of the first step and the second step, the attribute A is continuously calculatedi+1，Ai+2,.. corresponding entropy values, and selecting the attribute corresponding to the minimum entropy value as a node from all the entropy values;
(4) continuing each subsequent node according to the method of the steps (1) to (3);
(5) when each node determined by the new round of calculation results is a leaf node, the decision tree is constructed; otherwise, the steps are continuously executed, so that the clinical diagnosis information of the patient is digitalized frequently and simply.
The present invention will be described in further detail with reference to specific examples;
example 1;
when diabetes is judged: 1) the function with height as independent variable is used as a mode, and the function hardly plays a role in judgment; 2) the function with age or weight as independent variable is used as a mode, and a certain judgment reference function is achieved; 3) the determination of the measure of fasting glucose is limited; 4) the measurement of postprandial blood glucose is an important criterion.
I.e., conditions 1) and 3) are not revealed, while conditions 2) and 4) are revealed;
and obtaining a data set through the protocol to obtain accurate syndrome differentiation and classification.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
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 and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for processing Chinese medicine clinical diagnosis data is characterized in that the method for processing the Chinese medicine clinical diagnosis data comprises the following steps:
the method comprises the following steps: mining the diagnostic data by adopting a data mining learning algorithm;
step two: analyzing the diagnosis and treatment data of a large number of mined patients to obtain medical diagnosis rules;
step three: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
step four: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
step five: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
step six: and (4) carrying out syndrome differentiation and classification on the clinical diagnosis data processed by the computer, and storing.
2. The method for processing clinical diagnostic data of traditional Chinese medicine according to claim 1, wherein in the first step, the data mining adopts a local outlier data algorithm: let vi be the subspace definition vector of obj, d ═ viDimension of (a), λijIs a local sparse factor, d, corresponding to the jth attribute dimension of objRS(o, s) represents the euclidean distance between data objects s and o in the relevant subspace RS, obj relative to the local data set lds (obj), the standard distance in its relevant subspace RS being:
in the relevant subspace RS of obj, any nearest neighbor loc _ obj ∈ lds (obj) of obj (assuming loc _ obj is the mth data object) is relative to:
the standard distance of LDS (loc _ obj) is:
the probability local anomaly factor PLOF of obj in its relevant subspace RS is:
in the formula, PLOFRS(obj) and PLOFRS(loc _ obj) describes the degree of local outliers of loc _ obj in the relevant subspace RS of obj, similar to the local outlier factor LOF in the relevant subspace RS of obj.
3. The method for processing clinical diagnostic data of traditional Chinese medicine according to claim 1, wherein in the first step, the nonlinear least squares principle and solution in the ifelenglearning learning algorithm are adopted as follows: the method is provided with the following measurement data: (t)i，yi) I is 1, 2, …, m; and selecting a model of the fitted curve as y (t) phi (t; x); wherein the parameter x ═ x1，x2，…xn)T∈Rn，n＜m，y(t)，y(t)Is a non-linear function of x; selecting y according to the least squares principle(t)Such that y is(t)The sum of the squares of the differences from the measured function at the discrete points is minimal, x is a problem:
φi(x)＝φ(ti；x)-yi，
if the term F (x) ═ phi means1(x)，φ2(x)，…，φm(x))T；
Then write to:
4. the method for processing clinical diagnostic data of TCM as in claim 1, wherein in the third step, the weights of several symptoms for diagnosing a certain disease are counted by comparative mining, and the dialectic data is processed by dimension reduction.
5. The method for processing clinical diagnostic data of TCM according to claim 1, wherein in the third step, the key symptom for judging a disease is found based on the exposure pattern mining in the contrast mining, i.e. for an item set, when the difference of its support degree in different data sets is larger than a specified threshold, the item set is called the exposure pattern.
6. The method for processing clinical diagnostic data of traditional Chinese medicine according to claim 1, wherein in the third step, the comparison mining algorithm mainly comprises the following steps:
(1) for any one attribute AiAssuming it has miThe attribute values are represented by { theta 1, theta 2, …, theta mi }, and the probabilities corresponding to the attribute values are p1，p2，…，pmiAnd the information entropy calculation formula corresponding to each attribute value is as follows:
(2) by means of
Computing Attribute AiThe corresponding entropy;
(3) continue to calculate attribute Ai+1，Ai+2…, and selecting the attribute corresponding to the minimum entropy value as the node from all entropy values;
(4) continuing each subsequent node according to the methods (1) to (3);
(5) when each node determined by the new round of calculation results is a leaf node, the decision tree is constructed; otherwise, the steps are continuously executed, and the clinical diagnosis information of the patient is digitalized frequently and simply.
7. A system for processing clinical diagnostic data of chinese medicine for implementing the method of processing clinical diagnostic data of chinese medicine according to claim 1, wherein the system for processing clinical diagnostic data of chinese medicine comprises:
a data mining module: mining the diagnostic data by using a life learning algorithm in data mining;
a diagnostic data analysis module: analyzing the mined diagnosis and treatment data of a large number of patients; digging out medical diagnosis rules with high medical value;
clinical diagnosis information simplification module: the method adopts contrast mining in data mining, and completes the reduction of clinical diagnosis information into simplification by contrasting the clinical diagnosis information of patients under different symptoms and disease conditions;
a data training module: the data mining method based on the rough set algorithm, the clustering algorithm, the classification algorithm and the neural network algorithm trains the diagnosis data through the training data set;
clinical diagnostic data reduction module: reducing the dialectical clinical diagnosis data with multi-dimensional and multi-layer properties to reach the computer processing standard, and processing the diagnosis data by using a computer;
a syndrome differentiation and classification module: and (4) carrying out syndrome differentiation and classification on the diagnosis data processed by the computer, and storing.
8. A computer program for implementing the method for processing clinical diagnostic data of TCM as set forth in any one of claims 1 to 6.
9. An information data processing terminal for implementing the method of processing clinical diagnostic data of traditional Chinese medicine according to any one of claims 1 to 6.
10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method for processing clinical diagnostic data of chinese medical science according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907000.2A CN110634566A (en) | 2019-09-24 | 2019-09-24 | Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907000.2A CN110634566A (en) | 2019-09-24 | 2019-09-24 | Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110634566A true CN110634566A (en) | 2019-12-31 |
Family
ID=68974298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910907000.2A Withdrawn CN110634566A (en) | 2019-09-24 | 2019-09-24 | Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110634566A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243753A (en) * | 2020-02-27 | 2020-06-05 | 西安交通大学 | A multi-factor correlation interactive analysis method for medical data |
| CN111489809A (en) * | 2020-04-07 | 2020-08-04 | 上海中医药大学附属岳阳中西医结合医院 | Traditional Chinese medicine diagnosis and treatment system based on set pair analysis |
| CN111882533A (en) * | 2020-07-15 | 2020-11-03 | 山东省眼科研究所 | Decision model diagnosis method, device and computer readable storage medium |
| CN112270994A (en) * | 2020-10-14 | 2021-01-26 | 中国医学科学院阜外医院 | Construction method, device, terminal and storage medium of a risk prediction model |
| CN113707286A (en) * | 2021-08-30 | 2021-11-26 | 康键信息技术（深圳）有限公司 | Inquiry allocation method, device, equipment and storage medium based on decision tree |
| WO2024008043A1 (en) * | 2022-07-05 | 2024-01-11 | 浙江大学 | Automated clinical data generation method and system based on causal relationship mining |
-
2019
- 2019-09-24 CN CN201910907000.2A patent/CN110634566A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243753A (en) * | 2020-02-27 | 2020-06-05 | 西安交通大学 | A multi-factor correlation interactive analysis method for medical data |
| CN111243753B (en) * | 2020-02-27 | 2024-04-02 | 西安交通大学 | Multi-factor correlation interactive analysis method for medical data |
| CN111489809A (en) * | 2020-04-07 | 2020-08-04 | 上海中医药大学附属岳阳中西医结合医院 | Traditional Chinese medicine diagnosis and treatment system based on set pair analysis |
| CN111882533A (en) * | 2020-07-15 | 2020-11-03 | 山东省眼科研究所 | Decision model diagnosis method, device and computer readable storage medium |
| CN112270994A (en) * | 2020-10-14 | 2021-01-26 | 中国医学科学院阜外医院 | Construction method, device, terminal and storage medium of a risk prediction model |
| CN113707286A (en) * | 2021-08-30 | 2021-11-26 | 康键信息技术（深圳）有限公司 | Inquiry allocation method, device, equipment and storage medium based on decision tree |
| WO2024008043A1 (en) * | 2022-07-05 | 2024-01-11 | 浙江大学 | Automated clinical data generation method and system based on causal relationship mining |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110634566A (en) | Traditional Chinese medicine clinical diagnosis data processing system and method and information data processing terminal | |
| CN108648827B (en) | Cardiovascular and cerebrovascular disease risk prediction method and device | |
| CN111933281B (en) | Disease typing determination system, method, device and storage medium | |
| Garavand et al. | Efficient model for coronary artery disease diagnosis: a comparative study of several machine learning algorithms | |
| Baker et al. | Continuous and automatic mortality risk prediction using vital signs in the intensive care unit: a hybrid neural network approach | |
| Theerthagiri et al. | Cardiovascular disease prediction using recursive feature elimination and gradient boosting classification techniques | |
| Ghosh et al. | Hypotension risk prediction via sequential contrast patterns of ICU blood pressure | |
| US20210035693A1 (en) | Methods, systems, and apparatuses for predicting the risk of hospitalization | |
| CN116364299A (en) | A method and system for clustering disease diagnosis and treatment paths based on heterogeneous information network | |
| Aras et al. | Electrocardiogram detection of pulmonary hypertension using deep learning | |
| Kadi et al. | Systematic mapping study of data mining–based empirical studies in cardiology | |
| Agrawal et al. | Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data | |
| CN118471420B (en) | A health examination report data analysis and management system based on the Internet | |
| CN118969291A (en) | A hospital infection risk prediction method and system based on random forest algorithm | |
| Luo et al. | Data mining-based detection of rapid growth in length of stay on COPD patients | |
| Wang et al. | An optimal learning method for developing personalized treatment regimes | |
| Huang et al. | Data mining of association between hyperuricemia and common chronic diseases based on evolutionary apriori algorithm (EAA) | |
| Zhang et al. | Cardiac arrhythmia classification with rejection of ECG recordings based on uncertainty estimation from deep neural networks | |
| Podrat et al. | Evolution of risk calculators and the Dawn of artificial intelligence in predicting patient complications | |
| Kryvenchuk et al. | Random Forest as a Method of Predicting the Presence of Cardiovasculars Diseases. | |
| US9002863B2 (en) | Method, apparatus and computer program product for providing a rational range test for data translation | |
| CN119479957B (en) | A clinical data acquisition system for respiratory patients and a data correction method | |
| Abbaszadeh et al. | Heart disease prediction using ECG-based lightweight system in IoT based on meta-heuristic approach | |
| US20240363247A1 (en) | Method and an apparatus for detecting a level of cardiovascular disease | |
| US20250046461A1 (en) | Apparatus and method for determining a patient survival profile using artificial intelligence-enabled electrocardiogram (ecg) |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191231 |
|
| WW01 | Invention patent application withdrawn after publication |