CN114822875B - Disease and medicine matching method based on naive Bayesian network - Google Patents
Disease and medicine matching method based on naive Bayesian network Download PDFInfo
- Publication number
- CN114822875B CN114822875B CN202210639583.7A CN202210639583A CN114822875B CN 114822875 B CN114822875 B CN 114822875B CN 202210639583 A CN202210639583 A CN 202210639583A CN 114822875 B CN114822875 B CN 114822875B
- Authority
- CN
- China
- Prior art keywords
- drug
- formula
- symptoms
- symptom
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003814 drug Substances 0.000 title claims abstract description 177
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 31
- 201000010099 disease Diseases 0.000 title claims abstract description 23
- 208000024891 symptom Diseases 0.000 claims abstract description 126
- 229940079593 drug Drugs 0.000 claims abstract description 120
- 238000012549 training Methods 0.000 claims description 42
- 238000009472 formulation Methods 0.000 claims description 35
- 239000000203 mixture Substances 0.000 claims description 35
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 10
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 3
- 208000035475 disorder Diseases 0.000 description 14
- 238000012360 testing method Methods 0.000 description 6
- 241000283973 Oryctolagus cuniculus Species 0.000 description 4
- 244000061408 Eugenia caryophyllata Species 0.000 description 3
- 235000016639 Syzygium aromaticum Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 244000020518 Carthamus tinctorius Species 0.000 description 2
- 235000003255 Carthamus tinctorius Nutrition 0.000 description 2
- 241000628997 Flos Species 0.000 description 2
- 240000001972 Gardenia jasminoides Species 0.000 description 2
- 240000000233 Melia azedarach Species 0.000 description 2
- 206010033557 Palpitations Diseases 0.000 description 2
- 206010036790 Productive cough Diseases 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 208000024794 sputum Diseases 0.000 description 2
- 210000003802 sputum Anatomy 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 206010008479 Chest Pain Diseases 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000890 drug combination Substances 0.000 description 1
- 230000000210 effect on cough Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007721 medicinal effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008194 pharmaceutical composition Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Pharmaceuticals Containing Other Organic And Inorganic Compounds (AREA)
- Acyclic And Carbocyclic Compounds In Medicinal Compositions (AREA)
Abstract
The invention discloses a method for matching a disease and a medicine based on a naive Bayesian network, which takes disease symptoms (x 1,x2,…,xi,…,xI) as input nodes, wherein each input node represents a disease symptom; taking medicines (y 1,y2,…,yj,…,yJ) as output nodes, wherein each output node represents one medicine; the connection between the input node and the output node represents a mapping between symptoms of the disorder and the drug. The condition symptom node and the medicine node are represented by conditional probability, the probability intensity between each input node and each output node is represented by the conditional probability, and the greater the conditional probability is, the stronger the correlation between the condition symptom connected with the two ends and the medicine is, namely the more suitable the medicine is for treating the condition symptom. According to the invention, a doctor only needs to determine the symptoms of the patients, a reference basis can be provided for determining the treatment scheme, reasonable, effective and efficient medicaments are recommended for the doctor, and the condition of unreasonable administration is reduced.
Description
Technical field:
The invention relates to the technical field of biological medicine, in particular to a disease and medicine matching method based on a naive Bayesian network.
The background technology is as follows:
In the traditional Chinese and Mongolian medical treatment process, doctors need to prescribe a prescription for patients according to own study, but due to the complexity and diversification of symptoms and medicinal effects, when the prescription is prescribed for the compatibility of medicines, the experience dependence on the doctors is high, and the situation that the medicines are unreasonably used exists, so that the treatment effect of the patients is directly influenced, and even the health of the patients can be influenced.
At present, a plurality of methods for researching the relation between medicines in a formula and the diseases treated by the medicines are adopted, and a method for analyzing the medicines is mostly adopted, such as a medicine pair research method, a single medicine research method and the like. The method obviously only can change one or two medicines under the condition of controlling other medicines, explores the relation between the medicines in the formula and the symptoms, researches the symptoms treated in the formula, obviously cannot accurately and comprehensively study the symptoms treated in the formula and the nonlinear mapping relation among the medicines in the whole angle, cannot provide reference basis for prescribing by doctors, and cannot efficiently and effectively reduce the condition of unreasonable medication and the degree of dependence on the experience of doctors.
The invention comprises the following steps:
the invention aims to provide a disease and medicine matching method based on a naive Bayesian network, which can provide reference basis for determining a treatment scheme, recommend reasonable, effective and efficient medicines for doctors, reduce the condition of unreasonable medicines, reduce the degree of dependence on the experience of the doctors and improve the working efficiency of the doctors.
The invention is implemented by the following technical scheme:
A method for matching a condition to a drug based on a naive bayes network, comprising the steps of:
S1, collecting a plurality of traditional formulas, and corresponding symptoms X of the formulas to the used medicines Y to form a formula sample set Z;
s2, taking part of formulas in the formula sample set Z established in the S1 as a training formula set, carrying out binarization treatment on the training formula set to obtain a training set, training a naive Bayesian network model by utilizing the training set, and calculating the probability P (x i) of symptoms in the training set, the probability P (y j) of medicines and the conditional probability P (x i＝t|yj =l) between symptoms and medicines, wherein t=0, 1 represents that symptoms x i are not present and are present, and l=0, and 1 represents that the medicines y j are not used and are used;
S3, taking a symptom X' of a to-be-prescribed case as an input parameter, and calculating a posterior probability P (y j = 1|X) of each medicine and an posterior probability P (y j = 0|X) of each medicine which are not used according to the probability P (X i) of the symptom, the probability P (y j) of the medicine and the conditional probability P (X i＝t|yj =l) between the symptom and the medicine calculated in the S2, wherein X= (X 1,x2,…,xi,…,xI) represents each symptom of a patient, and the value of X i (i=1, 2, …, I) is 1 or 0;
And S4, comparing the sizes of P (Y j = 1|X) and P (Y j = 0|X), if P (Y j＝1|X)≥P(yj = 0|X), judging that the medicine is a medicine matched with the symptom X 'of the case, and matching all medicines matched with the symptom X' of the case to obtain a matched medicine result Y= (Y 1,y2,...,yJ).
Preferably, in the step S1,
Recipe sample set Z＝{(X1,Y1),(X2,Y2),…,(Xn,Yn),…,(XN,YN)},
Wherein N is the total number of formulas in the formula sample set;
the corresponding symptoms in the nth recipe are noted as In vectorsIs the corresponding ith symptom of the disease in the nth formula;
The compatibility of medicines in the nth formula is recorded as In vectorsIs the jth medicine in the nth formula.
Preferably, the step S2 includes the steps of: the method for binarizing the training formula set is that in a first formula, if the symptom x i exists, 1 is assigned to the symptom x i; if symptom x i is absent, assigning 0 to symptom x i; similarly, if the prescribed prescription contains a drug y j, then the drug y j is assigned 1; if the prescribed prescription does not contain the drug y j, then the drug y j is assigned a value of 0.
Preferably, the step S2 includes the steps of:
(1) The probability of symptoms of the disorder in the training set P (x i) and the probability of the drug P (y j) are calculated, in particular,
In the formula (1), the amino acid sequence of the formula (1),The cumulative frequency of symptoms x i =t in the training set, t=0, 1 indicates both the absence and presence of symptoms x i, i.e., t=0 indicates the absence of symptoms x i in the nth formulation, t=1 indicates the presence of symptoms x i in the nth formulation, and N is the total number of formulations in the formulation sample set;
in the formula (2), the amino acid sequence of the formula (2), The cumulative frequency of drugs y j = l in the training set; l=0, 1 indicates both the non-use and use of drug y j, i.e., l=0 indicates that drug y j is not used in the nth formulation, l=1 indicates that drug y j is used in the nth formulation, and N is the total number of formulations in the formulation sample set;
(2) The probability P (x i＝t,yj =l) is calculated for the symptom x i =t and the drug y j =l in the training set,
In the formula (3), the amino acid sequence of the compound,Formulation accumulation frequency, representing symptoms x i =t and drug y j =l in the training set;
(3) The conditional probability P between symptoms of the disorder and the drug is calculated (x i＝t|yj = l),
The conditional probability can be obtained by substituting the expression (2) and the expression (3) into the expression (4).
Preferably, in the step S3: the calculation method of the posterior probability P (y j =l|x) of each drug used and unused is as follows:
In formula (5), x= (X 1,x2,…,xi,…,xI) represents each symptom of the disease in the patient, and X i (i=1, 2, …, I) has a value of 1 or 0; l=0, 1 indicates both the unused and used cases of drug y j, i.e., P (y j = 0|X) indicates the posterior probability of drug y j being unused, i.e., P (y j = 1|X) indicates the posterior probability of drug y j being used.
The invention has the advantages that:
The invention takes symptoms (x 1,x2,…,xi,…,xI) as input nodes, and each input node represents a symptom of the symptoms; taking medicines (y 1,y2,…,yj,…,yJ) as output nodes, wherein each output node represents one medicine; the connection between the input node and the output node represents a mapping between symptoms of the disorder and the drug. The condition symptom node and the medicine node are represented by conditional probability, the probability intensity between each input node and each output node is represented by the conditional probability, and the greater the conditional probability is, the stronger the correlation between the condition symptom connected with the two ends and the medicine is, namely the more suitable the medicine is for treating the condition symptom.
According to the invention, a doctor only needs to determine the symptoms of the patient, inputs the symptoms of the patient, can output matched medicine results, can provide a reference basis for determining a treatment scheme, and can recommend reasonable, effective and efficient medicines for the doctor, so that the condition of unreasonable medicine use is reduced, the dependence on the experience of the doctor is reduced, and the working efficiency of the doctor is improved.
Description of the drawings:
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method of matching a condition to a drug based on a naive bayes network of the invention;
fig. 2 is a structural model diagram of a naive bayes network based matching method of disorders and drugs of the present invention.
The specific embodiment is as follows:
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
A method for matching a condition to a drug based on a naive bayes network as shown in fig. 1 and 2, comprising the following steps:
s1, collecting 24 traditional Mongolian formulas, and corresponding symptoms X of the formulas to the used medicines Y to form a formula sample set
Z＝{(X1,Y1),(X2,Y2),…,(Xn,Yn),…,(X24,Y24)}, As shown in table 1.
Table 1 formulation sample set
In table 1, 46 symptoms of the disease and 78 medicines are involved. The symptoms x i (i=1, 2, …, 46) and the drug y j (j=1, 2, …, 78) of the disorders involved are listed in table 2.
Table 2 symptoms and drugs
S2, taking the first 22 items in the formula sample set Z established in the S1 as a training formula set, as shown in a table 3; the latter 2 were used as test formulation sets.
Table 3 training formulation set
Binarizing the data of the symptom x i and the drug y j in the training formula set in table 3, namely, in a first formula, assigning 1 to the symptom x i if the symptom x i exists; if symptom x i is absent, assigning 0 to symptom x i; when (when)When the ith symptom exists in the nth formula, namely the medicine compatibility in the nth formula can treat the symptom; when (when)When the ith symptom is not existed in the nth formula, that is, the medicine compatibility in the nth formula does not treat the symptom of the disease. Similarly, if the prescribed prescription contains a drug y j, then the drug y j is assigned 1; if the prescribed prescription does not contain the drug y j, then the drug y j is assigned with 0; when (when)When the j-th medicine is used in the n-th formulaWhen the j-th drug is not used in the n-th formulation. The training set as shown in table 4 is finally formed.
Table 4 training set
Training a naive Bayesian network model by using a training set, and calculating probability P (x i) of symptoms of a disease in the training set, probability P (y j) of a medicine and conditional probability P (x i＝t|yj =l) between symptoms of the disease and the medicine, wherein t=0, 1 represents that symptoms of the disease x i are absent and present, and l=0, 1 represents that the medicine y j is not used and is used; specifically, the method comprises the following steps:
(1) The probability of symptoms of the disorder in the training set P (x i) and the probability of the drug P (y j) are calculated, in particular,
In the formula (1), the amino acid sequence of the formula (1),The cumulative frequency of symptoms x i =t in the training set, t=0, 1 indicates both the absence and presence of symptoms x i, i.e., t=0 indicates the absence of symptoms x i in the nth formulation, t=1 indicates the presence of symptoms x i in the nth formulation, and N is the total number of formulations in the formulation sample set; the absence probability P (x i =0) of each symptom and the presence probability P (x i =1) of each symptom can be calculated using the formula (1).
In the formula (2), the amino acid sequence of the formula (2),The cumulative frequency of drugs y j = l in the training set; l=0, 1 indicates both the non-use and use of drug y j, i.e., l=0 indicates that drug y j is not used in the nth formulation, l=1 indicates that drug y j is used in the nth formulation, and N is the total number of formulations in the formulation sample set; the unused probability P (y j =0) and the drug use probability P (y j =1) of each drug can be calculated using the formula (2).
(2) The probability P (x i＝t,yj =l) is calculated for the symptom x i =t and the drug y j =l in the training set,
In the formula (3), the amino acid sequence of the compound,Formulation accumulation frequency, representing symptoms x i =t and drug y j =l in the training set;
The probabilities of the drug and the symptoms of the disease in the formula training set in different situations can be calculated by using the formula (3), wherein the probabilities are respectively P (x i＝1,yj＝1),P(xi＝1,yj＝0),P(xi＝0,yj =1) and P (x i＝0,yj =0).
(3) The conditional probability P between symptoms of the disorder and the drug is calculated (x i＝t|yj = l),
Substituting the calculated data P (y j =1) and P (x i＝1,yj =1) into formula (4), and calculating the conditional probability P (x i＝1|yj =1) of drug use and the existence of symptoms in the training set; substituting the calculated data P (y j =1) and P (x i＝0,yj =1) into formula (4), and calculating a conditional probability P (x i＝0|yj =1) that the drug use in the training set and the symptom of the disorder do not exist; substituting the calculated data P (y j =0) and P (x i＝1,yj =0) into formula (4), and calculating the conditional probability P (x i＝1|yj =0) that the drug in the training set is not used and symptoms of the disease exist; substituting the calculated data P (y j =0) and P (x i＝0,yj =0) into formula (4), and calculating the conditional probability P (x i＝0|yj =0) that the drug in the training set is not used and the symptom of the disorder does not exist.
S3, taking a symptom X' of a to-be-prescribed case as an input parameter, and calculating a posterior probability P (y j = 1|X) of each medicine and an posterior probability P (y j = 0|X) of each medicine which are not used according to the probability P (X i) of the symptom, the probability P (y j) of the medicine and the conditional probability P (X i＝t|yj =l) between the symptom and the medicine calculated in the S2, wherein X= (X 1,x2,…,xi,…,xI) represents each symptom of a patient, and the value of X i (i=1, 2, …, I) is 1 or 0;
The calculation method of the posterior probability P (y j =l|x) of each drug used and unused is as follows:
in the formula (5), the amino acid sequence of the compound,
X= (X 1,x2,…,xi,…,xI) represents each symptom of the patient, and X i (i=1, 2, …, I) has a value of 1 or 0. l=0, 1 indicates both the unused and used cases of drug y j, i.e., P (y j = 0|X) indicates the posterior probability of drug y j being unused, and P (y j = 1|X) indicates the posterior probability of drug y j being used.
And S4, comparing the sizes of P (Y j = 1|X) and P (Y j = 0|X), if P (Y j＝1|X)≥P(yj = 0|X), judging that the medicine is a medicine matched with the symptom X 'of the case, and matching all medicines matched with the symptom X' of the case to obtain a matched medicine result Y= (Y 1,y2,...,yJ).
Experimental example 1:
The method of the invention is used for obtaining the matched medicines by using the symptoms of the symptoms corresponding to the 2 formulas in the test formula set in the example 1, so as to verify the consistency of the medicine compatibility in the traditional formula and the medicine compatibility given by the method of the invention. The symptoms of the disease and the compatibility of the medicines are shown in Table 5.
Table 5 test formulation set
The symptoms x i and the drug y j in the test formulation set of table 5 were subjected to data binarization processing to finally form a test set.
With the symptoms of the disorder in the test set as input parameters, according to the method of example 1, first, the probability P of the symptoms of the disorder (x i), the probability P of the drug (y j), and the conditional probability P between the symptoms of the disorder and the drug (x i＝t|yj =l) are calculated, and then the posterior probability P with a certain drug (y j = 1|X) and the posterior probability P without a certain drug (y j = 0|X) are calculated. Comparing P (y j = 0|X) and P (y j = 1|X) corresponding to the same medicine, if P (y j＝1|X)≥P(yj = 0|X), judging that the medicine is used under the symptoms of the disease, otherwise, judging that the medicine is not used under the symptoms of the disease; finally, all the medicines used under the condition of the disease are matched, namely, the result Y= (Y 1,y2,...,yJ) of the medicine matched with the result is obtained by using the method of the invention, and the result is shown in table 6.
TABLE 6 results of matching drugs using the methods of the present invention
Comparing the traditional medicine compatibility in table 5 with the medicine results matched with the traditional medicine compatibility by the method in table 6, it can be known that the two groups of medicines with the serial number of 2 are completely the same, 9 medicines in the traditional formula in table 5 are in the serial number of 1, and 10 medicines are given in the traditional formula in table 6 by the method in the invention, wherein the rabbit hearts and the clove in table 5 are replaced by the gardenia, the szechwan chinaberry fruits and the safflower.
For the symptoms of the disorder in sequence number 2, the traditional formulation is different from the matched drug results obtained by the present invention, so the following analysis was performed:
The posterior probability P (x i＝1|yj =1) of using a single drug for a single symptom can be obtained from the formula (5) in example 1, and the therapeutic effect of the drug on the symptom can be reflected. Substituting the data of P (x i＝1)、P(yj =1) and P (x i＝1|yj =1) into formula (5) to obtain posterior probability P (y j＝1|xi =1) between single symptom and single drug, and obtaining the use and non-use of single drug, and the results are shown in table 7.
TABLE 7 Single drug use and unused conditions
The symptoms of the symptoms listed in Table 7 are those appearing in sequence No. 2, and the therapeutic effect of each drug on the symptoms of various symptoms can be seen. From Table 7, it can be seen that the effects of flos Caryophylli and rabbit heart are better than those of fructus Gardeniae, fructus Toosendan and Carthami flos in the traditional formulation in treating palpitation; in the aspect of thorny pain, the treatment effect of the gardenia and the szechwan chinaberry fruit is better than that of the clove and the rabbit heart. The safflower has better curative effect on cough and white sputum than on clove and rabbit heart. Thus, the drug combinations in Table 5 can be used for patients with chest pain, cough and profuse sputum; the pharmaceutical formulations in table 4 can be used for patients with severe palpitations.
In summary, the method of the invention for drug matching of symptoms of disorders is reliable.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (5)
1. A method for matching a condition to a drug based on a naive bayes network, comprising the steps of:
S1, collecting a plurality of traditional formulas, and corresponding symptoms X of the formulas to the used medicines Y to form a formula sample set Z;
S2, taking part of formulas in the formula sample set Z established in the S1 as a training formula set, carrying out binarization treatment on the training formula set to obtain a training set, training a naive Bayesian network model by utilizing the training set, and calculating the probability P (x i) of symptoms in the training set, the probability P (y j) of medicines and the conditional probability P (x i＝t|yj =l) between symptoms and medicines, wherein t=0, 1 represents that symptoms x i are not present and are present, and l=0, and 1 represents that the medicines y j are not used and are used;
S3, taking a symptom X' of a to-be-prescribed case as an input parameter, and calculating a posterior probability P (y j = 1|X) of each medicine and an posterior probability P (y j = 0|X) of each medicine which are not used according to the probability P (X i) of the symptom, the probability P (y j) of the medicine and the conditional probability P (X i＝t|yj =l) between the symptom and the medicine calculated in the S2, wherein X= (X 1,x2,…,xi,…,xI) represents each symptom of a patient, and the value of X i (i=1, 2, …, I) is 1 or 0;
and S4, comparing the sizes of P (Y j = 1|X) and P (Y j = 0|X), if P (Y j＝1|X)≥P(yj = 0|X), judging that the medicine is a medicine matched with the symptom X 'of the case, and matching all medicines matched with the symptom X' of the case to obtain a matched medicine result Y= (Y 1,y2,…,yJ).
2. The method for naive bayes network based condition to drug matching according to claim 1, wherein in S1,
Recipe sample set Z＝{(X1,Y1),(X2,Y2),…,(Xn,Yn),…,(XN,YN)},
Wherein N is the total number of formulas in the formula sample set;
the corresponding symptoms in the nth recipe are noted as In vectorsIs the corresponding ith symptom of the disease in the nth formula;
The compatibility of medicines in the nth formula is recorded as In vectorsIs the jth medicine in the nth formula.
3. A method of matching a naive bayes network based condition to a drug according to claim 2, wherein said S2 comprises the steps of: the method for binarizing the training formula set is that in a first formula, if the symptom x i exists, 1 is assigned to the symptom x i; if symptom x i is absent, assigning 0 to symptom x i; similarly, if the prescribed prescription contains a drug y j, then the drug y j is assigned 1; if the prescribed prescription does not contain the drug y j, then the drug y j is assigned a value of 0.
4. A method of matching a naive bayes network based condition to a drug according to claim 2, wherein said S2 comprises the steps of:
(1) The probability of symptoms of the disorder in the training set P (x i) and the probability of the drug P (y j) are calculated, in particular,
In the formula (1), the amino acid sequence of the formula (1),The cumulative frequency of symptoms x i =t in the training set, t=0, 1 indicates both the absence and presence of symptoms x i, i.e., t=0 indicates the absence of symptoms x i in the nth formulation, t=1 indicates the presence of symptoms x i in the nth formulation, and N is the total number of formulations in the formulation sample set;
in the formula (2), the amino acid sequence of the formula (2), The cumulative frequency of drugs y j = l in the training set; l=0, 1 indicates both the non-use and use of drug y j, i.e., l=0 indicates that drug y j is not used in the nth formulation, l=1 indicates that drug y j is used in the nth formulation, and N is the total number of formulations in the formulation sample set;
(2) The probability P (x i＝t,yj =l) is calculated for the symptom x i =t and the drug y j =l in the training set,
In the formula (3), the amino acid sequence of the compound,Formulation accumulation frequency, representing symptoms x i =t and drug y j =l in the training set;
(3) The conditional probability P between symptoms of the disorder and the drug is calculated (x i＝t|yj = l),
The conditional probability can be obtained by substituting the expression (2) and the expression (3) into the expression (4).
5. The method of naive bayes network based condition to drug matching of claim 4 wherein in S3: the calculation method of the posterior probability P (y j =l|x) of each drug used and unused is as follows:
in formula (5), x= (X 1,x2,…,xi,…,xI) represents each symptom of the disease in the patient, and X i (i=1, 2, …, I) has a value of 1 or 0; l=0, 1 indicates both the unused and used cases of drug y j, i.e., P (y j = 0|X) indicates the posterior probability of drug y j being unused, and P (y j = 1|X) indicates the posterior probability of drug y j being used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210639583.7A CN114822875B (en) | 2022-06-08 | 2022-06-08 | Disease and medicine matching method based on naive Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210639583.7A CN114822875B (en) | 2022-06-08 | 2022-06-08 | Disease and medicine matching method based on naive Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114822875A CN114822875A (en) | 2022-07-29 |
| CN114822875B true CN114822875B (en) | 2024-09-17 |
Family
ID=82520331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210639583.7A Active CN114822875B (en) | 2022-06-08 | 2022-06-08 | Disease and medicine matching method based on naive Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114822875B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717862A (en) * | 2018-04-10 | 2018-10-30 | 四川骏逸富顿科技有限公司 | A kind of careful square evolution model of the intelligence based on machine learning |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11562323B2 (en) * | 2009-10-01 | 2023-01-24 | DecisionQ Corporation | Application of bayesian networks to patient screening and treatment |
| CN111009316B (en) * | 2019-12-25 | 2022-06-21 | 福州大学 | Doctor-patient matching method based on Bayesian network |
-
2022
- 2022-06-08 CN CN202210639583.7A patent/CN114822875B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717862A (en) * | 2018-04-10 | 2018-10-30 | 四川骏逸富顿科技有限公司 | A kind of careful square evolution model of the intelligence based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114822875A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105760705B (en) | A kind of medical diagnosis system based on big data | |
| CN109087691A (en) | A kind of OTC drugs recommender system and recommended method based on deep learning | |
| CN105550526B (en) | A kind of tcm prescription effect quantitative approach and system based on Chinese medicine attribute | |
| CN109273098B (en) | Medicine curative effect prediction method and device based on intelligent decision | |
| CN108597587A (en) | A kind of veteran TCM doctor's experience intelligence succession and clinical aid decision-making system and method | |
| Rasooly et al. | The impact of race on analgesia use among pediatric emergency department patients | |
| CN110223784A (en) | Clinical test patient's matching process | |
| CN111223543A (en) | Method, system and equipment for intelligently guiding treatment scheme | |
| Novaliendry et al. | The expert system application for diagnosing human vitamin deficiency through forward chaining method | |
| CN116612852B (en) | Method, device and computer equipment for realizing drug recommendation | |
| CN117558464B (en) | Method for constructing ADR prediction model of elderly patient, prediction system and storage medium | |
| CN111599487A (en) | Traditional Chinese medicine compatibility assistant decision-making method based on correlation analysis | |
| CN114822875B (en) | Disease and medicine matching method based on naive Bayesian network | |
| CN113421653A (en) | Medical information pushing method and device, storage medium and computer equipment | |
| Jonas | Advising patients on the use of complementary and alternative medicine | |
| CN115101165A (en) | Disease and drug matching method based on decision tree | |
| Qin et al. | A traditional Chinese medicine prescription recommendation method based on mutual information clustering | |
| Jang et al. | Efficacy of Transcutaneous 4.4 MHz Radiofrequency Diathermy versus Therapeutic Ultrasound for Pain Relief and Functional Recovery in Patients with Knee Osteoarthritis: A Randomized Controlled Study | |
| CN112185503A (en) | Intelligent auxiliary diagnosis system and method for traditional Chinese medicine | |
| Mujahidah et al. | Web-Based Comprehensive Assessment for Postpartum Care using Rule-Based Algorithm | |
| Riaño et al. | Mining hospital data to learn SDA* clinical algorithms | |
| Soffer et al. | Characteristics of patients at a complementary medicine clinic in Beer Sheva: summary of the first two years of operation | |
| Nandita et al. | Awareness of Self Medication Practices among Dental Undergraduate Students. | |
| Neves et al. | Needs for at-home nursing care after discharge from hospital in the SUS context | |
| Wang et al. | Evaluation of the reliability and validity of the modified Morisky scale for patient’s compliance with moxibustion |
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 |