CN111191020A - Prescription recommendation method and system based on machine learning and knowledge graph - Google Patents
Prescription recommendation method and system based on machine learning and knowledge graph Download PDFInfo
- Publication number
- CN111191020A CN111191020A CN201911373211.9A CN201911373211A CN111191020A CN 111191020 A CN111191020 A CN 111191020A CN 201911373211 A CN201911373211 A CN 201911373211A CN 111191020 A CN111191020 A CN 111191020A
- Authority
- CN
- China
- Prior art keywords
- prescription
- patient
- recommendation
- medicine
- diagnosis
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to 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
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a prescription recommendation method and system based on machine learning and knowledge graph. The recommendation method comprises the following steps: acquiring and analyzing the diagnosis information to obtain one or more diagnosis details including patient information, doctor information and disease diagnosis; inputting the diagnosis details into a pre-constructed machine learning model for reasoning to obtain an initial recommendation list aiming at the diagnosis details; acquiring a relation graph network associated with the medicine from a medicine knowledge graph according to the medicine information contained in the initial recommendation list; and screening and eliminating contraindicated medicines according to the relationship graph network, and then giving a final recommendation list. The invention combines the quick learning ability of machine learning and the data mining and correlation display ability of the knowledge graph, can realize accurate prescription recommendation, simultaneously improves the prescription generation efficiency, can meet the prescription requirement of outpatient doctors, improves the working efficiency of doctors and reduces medical errors.
Description
Technical Field
The invention relates to the technical field of medical informatization, in particular to a personalized prescription recommendation method and system.
Background
In the medical service process, doctors diagnose the illness state of patients and then make corresponding prescriptions, and various factors such as age, sex, constitutional features and the like need to be comprehensively considered when making the prescriptions, so that even if the same disease is caused, the prescriptions and the dosages needed by different patients are different. As the number of patients to be treated increases, the treatment pressure of outpatients increases, the possibility of making mistakes by doctors also increases, and particularly, doctors with less experience are easier to repeatedly modify under the condition of lacking of powerful medical aid decision-making means.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problems in the prior art, the invention provides a prescription recommendation method and system based on machine learning and knowledge graph, so that accurate prescription recommendation is realized, and prescription generation efficiency is improved.
The technical scheme is as follows: according to a first aspect of the present invention, there is provided a machine learning and knowledge-graph based prescription recommendation method, comprising the steps of:
acquiring and analyzing the diagnosis information to obtain one or more diagnosis details including patient information, doctor information and disease diagnosis;
inputting the diagnosis details into a pre-constructed machine learning model for reasoning to obtain an initial recommendation list aiming at the diagnosis details;
acquiring a relation graph network associated with the medicine from a medicine knowledge graph according to the medicine information contained in the initial recommendation list;
and screening and eliminating contraindicated medicines according to the relationship graph network, and then giving a final recommendation list.
The pre-constructed machine learning model comprises a collaborative filtering-based recommendation model, a knowledge-based recommendation model and a neural network-based recommendation model, and the three basic recommendation models are obtained by training through a collaborative filtering algorithm, a knowledge-based recommendation algorithm and a neural network learning algorithm respectively; the method for obtaining the initial recommendation list comprises the following steps: and respectively inputting the diagnosis detail information into the three basic recommendation models to obtain respectively recommended prescription drugs, removing repeated items, and sequencing according to the predicted adoption probability to obtain an initial recommendation list.
According to a second aspect of the present invention, there is provided a machine learning and knowledge-graph based prescription recommendation system, comprising:
the diagnostic information analysis module is used for acquiring and analyzing the diagnostic information to obtain one or more pieces of diagnostic details including patient information, doctor information and disease diagnosis;
the machine learning module is used for inputting the diagnosis detail data into the machine learning model for training to obtain a recommendation model for recommending a prescription according to the patient information and the disease diagnosis;
the medicine relation graph module is used for acquiring a relation graph network associated with the medicine from the medicine knowledge graph according to the medicine information;
the prescription recommending module is used for recommending an optional prescription according to the input patient information, doctor information and disease diagnosis;
and the recommendation result screening module is used for filtering and eliminating contraindicated medicines for the recommended optional prescription according to the relationship graph network.
Has the advantages that: the invention provides a prescription recommendation method and system based on machine learning and a knowledge graph, which can realize accurate prescription recommendation and improve prescription generation efficiency. The recommendation system adopts a model fusion method, combines a model trained by three machine learning algorithms of collaborative filtering, knowledge-based recommendation and neural network to recommend the prescription, and provides the prescription to an outpatient doctor. The invention can meet the prescription requirement of outpatient doctors, improve the working efficiency of doctors and reduce medical errors.
Drawings
FIG. 1 is a flow chart of a recipe recommendation method provided by the present invention;
FIG. 2 is a schematic diagram of a knowledge-graph of a drug according to an embodiment of the invention;
FIG. 3 is a network of relationship graphs obtained from a drug knowledge-graph according to an embodiment of the present invention;
FIG. 4 is a block diagram of a prescription recommendation system according to the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
Referring to fig. 1, the invention provides a prescription recommendation method based on machine learning and knowledge graph, comprising the following steps:
and step S1, acquiring and analyzing the diagnosis information to obtain one or more diagnosis details.
With the rapid development of medical informatization technology, a large amount of prescription records are stored in electronic information systems of a plurality of hospitals, data can be exchanged through open interfaces of systems such as Hospital Information Systems (HIS)/Electronic Medical Records (EMR) and the like, diagnosis information in the electronic medical records can be acquired, and the diagnosis details can be obtained through analysis of natural language processing technology. Specifically, acquiring the character data of the electronic medical record of the outpatient clinic, including the basic fields of the sex, the birth date, the pregnancy, the lactation period, the height, the weight and the payment mode of the patient and the character content of the allergic history, extracting the name of the drug with the allergic reaction of the patient from the field of the allergic history by using a keyword matching method, and inquiring through a pre-obtained drug alias library to obtain all names of the drugs with the allergic reaction; the clinic record data is obtained at the same time, the diagnosis containing invalid or wrong codes is excluded by classifying through the ICD10 codes of the diagnosis field, and a large number of disease diagnosis < - > prescription drug data pairs of the clinic records are obtained, wherein the large number refers to more than five hundred parts of prescription records for each clinical diagnosis for the training of the following model.
And step S2, inputting the diagnosis details into the machine learning model for reasoning to obtain an initial recommendation list aiming at the diagnosis details.
The machine learning model needs to be trained firstly, after the acquired data are cleaned and sorted, three original models are obtained by training with disease diagnosis and basic information of a patient as input parameters and medicines as output parameters respectively by using three machine learning algorithms of collaborative filtering, knowledge-based recommendation and neural network; and fusing the three original models by using a model fusion technology to obtain a fused prescription recommendation model. In the outpatient service application, the patient information and the doctor diagnosis are used as input parameters to be provided for the fused prescription recommendation model, the model returns a plurality of recommendation results, the recommendation results are ranked from high to low according to the similarity, and the recommendation results are returned to the outpatient service doctor.
When the original model training is carried out, the used collaborative filtering algorithm comprises the following steps:
s21, firstly, carrying out data normalization processing, mapping the field values of sex, age at diagnosis and pregnancy in the basic information of the patient to a 16-digit space (hereinafter referred to as a fingerprint of the patient), and calculating the relative distance of the patient by using the 'and' relation, such as sex male, age 10, pregnancy possibility mapping to 0000000100010100, sex female, age 11 and pregnancy possibility mapping to; 0000000000010110, the similarity between the two numbers and 0000000000010100 is calculated, i.e. the fingerprint value is calculated, and the smaller the similarity value is, the higher the similarity is.
And S21, sorting the data according to the patient fingerprint, prescription medicine and disease diagnosis triple, calculating the grading data of the basic condition and disease diagnosis of the patient, taking the grading data as an index for measuring the similarity degree between the diseases of the patient, and obtaining a patient similarity matrix through a distance calculation method.
Further, the step of calculating the score data of the patient basic condition and disease diagnosis is as follows:
s21-1) reading the stored data of the triple groups of the patient fingerprint, the prescription medicine and the disease diagnosis (user, article and score);
s21-2) starting a merging process, extracting the number of the prescription medicine as a main key, taking the patient and the disease diagnosis as values, and merging the data with the same number of the prescription medicine in the storage according to the formats of the prescription medicine, the disease diagnosis and the patient fingerprint sequence pair;
s21-3) merging the data of the same main key, and outputting the final result, wherein the result takes the prescription drug number as the main key and the patient fingerprint and disease diagnosis sequence pair as values, and the values are stored in a database as the prescription drug evaluation data.
Further, the step of calculating the patient similarity matrix is as follows:
s21-a) reading the locally stored patient fingerprint and the score data of disease diagnosis;
s21-b) rearranging data by taking the fingerprint pair of the patient as a main key and the score pair of the fingerprint and the disease diagnosis as values, calculating the score distance between the patient and the disease diagnosis between the fingerprints of the patient, outputting the main key as the fingerprint pair of the patient, and outputting the value as the score distance between every two fingerprints of the patient for the same disease diagnosis; wherein the scoring distance is encoded in the same disease diagnosis ICD10 and the similar distance of the patient's fingerprint is used as the scoring distance;
s21-c) starting a merging process, merging the data of the same patient fingerprint pair to obtain the distance values of all the same disease diagnosis scores of the fingerprints of the two patients, wherein the main key of the merging result is the patient to be treated, the value is the score distance between the treated patient and the patient to be treated, and the merging result is stored as the patient similarity matrix data.
The method for recommending the prescription drugs according to the collaborative filtering model during use comprises the following steps:
a) reading locally stored prescription drug evaluation data and patient similarity matrix data, sorting the prescription drug evaluation data, taking a patient fingerprint pair as a main key, taking the evaluation data of disease diagnosis of the prescription drug and the patient as a value, sorting the patient similarity matrix, taking the patient fingerprint pair as a main key, taking the patient distance and the distance sum as values, merging the two types of data, searching the evaluation of the prescription drug and the prescription drug of the patient to be treated who is not treated but cured by the treated patient, calculating the recommended value of the patient to be treated for the prescription drug, and storing the recommended value in a database as the recommended value of the prescription drug; wherein the patient distance refers to the value calculated by and in step S21, and the sum of the distances refers to the patient distance plus the similarity of the diagnoses (because there are a plurality of diagnoses, the same sequence of diagnoses may be different, and therefore the similarity is highest when the sequence and the contents of the diagnoses are identical);
b) and sequencing all recommended prescription medicines of the patient to be treated according to the recommended values of the prescription medicines, and selecting the prescription medicine with the highest recommended value as a recommended result.
The algorithm based on knowledge recommendation used when performing the original model training is as follows: the knowledge-based recommendation rule construction method forms a recommendation relation between a fixed diagnosis (ICD10 code) and a prescription according to the latest clinical guidelines and expert consensus, wherein one code corresponds to one or more drug names and standard doses, the doses can be adjusted by doctors according to the actual weight of a patient, and the knowledge-based recommendation is one of recommendation algorithms and is mainly used for directly using a medication scheme recommended by the guidelines when cold start is performed, namely similar patients or identical diagnoses cannot be found in prescription records. When the ICD10 coded format diagnosis result is input and the prediction recommendation result is output, the knowledge-based recommendation algorithm is mainly used for solving the cold start problem, namely the condition of lacking pre-training data.
The neural network recommendation algorithm is used as a supplement of collaborative filtering in personalized recommendation taking the historical prescription record of a doctor as a theme. When the original model training is carried out, the neural network algorithm used comprises the following steps:
S2A, acquiring a user behavior log reported by a doctor client, wherein the user behavior log comprises doctor ID, ICD10 diagnosis codes, basic information of a patient (sex, date of birth, pregnancy, lactation period, height, weight and payment mode), a prescription medicine list and dosage, and storing the user behavior log in a server basic database;
S2B, performing data acquisition, cleaning, standardization processing and feature combination and extraction on the user behavior log data by constructing a feature collector to obtain feature vectors which are unified and standard and meet the requirement of mathematical modeling;
further, constructing a feature collector to obtain uniform and standard feature vectors includes the following specific steps:
S2B-1, carrying out the following processing on the data: separating time sequence data into dimensions required by each basic operation model according to different time units; carrying out Z-score standardization processing on the numerical data; performing semantic analysis on the text data; processing the enumeration classification data by adopting one-hot coding;
S2B-2, extracting the features of each item of processed data, and performing dimensionality reduction processing on the extracted feature vectors, wherein the features are each field information given in the step S2A;
S2B-3, generating a feature vector which has a uniform specification and can be used for model training after dimension reduction processing, and the method comprises the following steps: user feature vector, prescription drug feature vector, disease feature vector.
S2C, transmitting the feature vectors into a multilayer neural network as input, wherein each layer of the network is a global neural network layer; the invention adopts the convolution neural network to train, because the input data is not pictures and can not be convoluted by channels, the convolution is carried out on all the input data (vector matrix), each layer is a convolution neural network, which is called as a global neural network layer and is used for carrying out convolution operation on the input data, and the convolution result of the previous layer is used as the input of the next layer;
because the output matrix becomes smaller after the convolution is carried out on the previous layer, the number of nodes of the network layer from the front to the back of the global neural network layer is decreased progressively, and the number of the nodes of the global neural network layer on the previous layer is 2 times that of the nodes of the global neural network layer on the next layer;
taking the feature vector of the prescription medicine as an output target, taking the user feature vector and the disease feature vector after the dimensionality reduction processing as inputs, respectively mapping the input vectors into dense vectors, and then outputting the dense vectors to the first global neural network layer;
acquiring interlayer weight information of the neural network through training of the neural network, and acquiring output information of currently input user characteristic vectors and disease characteristic vectors in the neural network based on the trained interlayer weight information, namely similarity of the currently input user characteristic vectors and the disease characteristic vectors with the characteristic vectors of prescription drugs;
fully connecting the hidden layer of the last layer of the neural network, outputting the prediction scores of the user and the disease to the prescription, constructing a user-disease-prescription score prediction table based on the prediction scores, and storing the user-disease-prescription score prediction table in a database;
when the prescriptions are recommended, reading a user-disease-prescription score prediction table from a database, sorting the prescriptions available for current diagnosis in a descending order based on the prediction scores in the user-disease-prescription score prediction table, selecting and recommending N prescriptions with the top sorting as a recommended data table of the current user, wherein the N value can be dynamically adjusted.
Furthermore, each basic recommendation model is trained by adopting a k-fold cross validation method, in the training stage, each basic recommendation model is subjected to parameter tuning optimization by adopting a grid search method to obtain optimal parameters, a prescription medicine recommendation list of each user under each basic recommendation model is generated, and the utilization rate of each prescription medicine in the preliminary prescription medicine list by the corresponding user is also generated.
The method for training each basic recommendation model by adopting a k-fold cross validation method comprises the following steps:
a) dividing the training sample set of each basic recommendation model into k subsets with the same size and mutually exclusive content;
b) and performing k iterations, wherein each iteration adopts a union of k-I subsets as a training set, the rest subsets are used as a test set, and the obtained k groups of training sets and the test set are subjected to training of the basic recommendation model. Therefore, under the condition that the data quantity is not large enough, the utilization rate of the data can be improved, and the condition of over-fitting or under-fitting is avoided. The value of I is adjusted according to experience and model training, and is typically 1.
The generalization capability of a single basic recommendation model is improved by training each basic recommendation model by adopting a k-fold cross validation method.
And after the construction of the three basic recommendation models is completed, carrying out model fusion processing. Calculating according to the input user and diagnosis information, calculating fingerprint and scoring distance required by a collaborative filtering model, requiring patient and diagnosis information by a knowledge-based recommendation model and requiring characteristic vectors by a neural network model, obtaining a preliminary prescription medicine list of disease diagnosis of a corresponding user under each basic recommendation model and the adoption probability of each prescription medicine in the preliminary prescription medicine list by the corresponding user, wherein the adoption probability is obtained by the similarity of the patient information, doctor diagnosis and currently input patient information and diagnosis corresponding to the medicine recommendation lists returned by the three models, and the adoption probability is considered to be higher as the similarity is closer. And (3) personalized recommendation based on a neural network under a default condition > collaborative filtering > recommendation based on knowledge, inputting the adoption probability obtained by each recommendation model as a new feature vector, and sequencing according to the predicted adoption probability from high to low. And after the recommended prescriptions obtained by all the recommendation models are sorted, repeated recommendations are removed, the recommended prescriptions are displayed to a clinician in a list mode, the clinician can select whether to adopt the recommended prescriptions or not, whether to actually adopt the recommended prescriptions or not is used as feedback of the fusion recommendation model, and the recommendation sequence of the fusion recommendation model is readjusted.
Step S3, according to the medicine information contained in the initial recommendation list, obtaining the relation graph network associated with the medicine from the medicine knowledge graph.
The method comprises the steps of firstly obtaining a prescription list returned by a recommendation engine, extracting all medicine lists contained in each prescription, then obtaining records of corresponding entities of the medicines and entity and relation sets associated with the medicines in a knowledge graph according to medicine names, namely attribute sets of indications, medicines, medicine interaction, contraindications and the like of the medicines, if a plurality of medicines of the same prescription can be associated through interaction, forming a connected graph subset and explaining that the medicines in the subset have interaction relation, and if not, explaining that the medicines of the prescription do not have interaction. FIG. 2 is a schematic view of a knowledge graph of a drug, and FIG. 3 is an example of a subset of the graph of a drug derived from FIG. 2.
Step S4, drug screening is carried out according to the drug map subset network, contraindications of all drugs are inquired about the map subsets of each prescription returned by the recommendation engine, whether the drugs in the prescription have usage contraindications is judged according to information such as age, pregnancy, allergy history and the like of a patient, and if the contraindications are found, the drugs are excluded from the prescription recommendation result list.
Preferably, the recommended prescription is returned while the price of the medicine is obtained, and the total price of the prescriptions is automatically calculated, and the method comprises the following steps:
summarizing and calculating all the medicine prices of the single recommended prescription to obtain the total price of the single recommended prescription;
performing a summarizing step on all recommended prescriptions to respectively obtain the total prices of all the prescriptions;
the prescription prices are sorted, and prescriptions exceeding a preset total price threshold value provide independent visual identification, so that a prompt effect is provided for a clinician to control a big prescription.
According to another embodiment of the present invention, there is provided a machine learning and knowledge-graph based prescription recommendation system, as shown in fig. 4, including: the diagnosis information analysis module 100 is used for acquiring and analyzing diagnosis information from the existing electronic medical record to obtain one or more diagnosis details including basic fields of sex, birth date, pregnancy, lactation period, height, weight and payment mode of a patient and the text content of an allergy history, extracting the name of a drug with anaphylactic reaction of the patient from the field of the allergy history by using a keyword matching method, and inquiring through a pre-obtained drug alias library to obtain all names of the anaphylactic reaction drugs; acquiring outpatient service record data, classifying through ICD10 codes of diagnosis fields, eliminating diagnoses containing invalid or wrong codes, and acquiring a large number of disease diagnosis < - > prescription medicine data pairs of outpatient service records;
the machine learning module 200 is configured to input the diagnosis detail data and the disease diagnosis data into a machine learning model for training, so as to obtain a recommendation model for recommending a prescription according to patient information and the diagnosis detail, and obtain three recommendation models based on collaborative filtering, a neural network and knowledge according to subjects of the input data, including departments, doctors and guidelines; if the subject is a historical prescription record from a doctor, obtaining a neural network model; if the topic is from all doctors in the department (prescription data of multiple experts), a collaborative filtering based model is obtained; if the topic is from guide data, a knowledge-based model is derived. The training process of the original model is the same as the steps in the method embodiment, and details are not repeated here.
A prescription recommending module 300 for recommending an optional prescription according to the input patient information, doctor information and disease diagnosis.
Specifically, the recommendation module 300 includes a recommendation unit 301 for transmitting input data to three recommendation models based on collaborative filtering, neural networks, and knowledge, and receiving initial prescription recommendations from the recommendation models;
and the fusion unit 302 integrates the initial prescription recommendation results provided by the three recommendation models, removes repeated items, and sorts the initial prescription recommendation results according to the similarity of the patients.
And a medicine relation graph module 400, configured to obtain a relation graph network associated with the medicine from the medicine knowledge graph according to the medicine information included in the prescription recommended by the prescription recommendation module. The drug relationship graph module 400 first obtains knowledge graph information of the drug and returns relationship data consisting of related drug information nodes and edges representing association relationships.
And a recommendation result screening module 500, configured to screen and exclude contraindicated drugs according to the relationship graph network.
Specifically, the recommendation result screening module 500 includes a matching unit 501, configured to match drug information included in the prescription returned by the prescription recommendation model with nodes and relationship information pre-stored in a drug knowledge graph, so as to obtain a network relationship including the recommended drug name, drug indications, drug affiliations, drug interactions, and contraindications;
the screening unit 502 is configured to filter out a prescription of an item containing a contraindicated drug in the recommendation result according to the network relationship among the drug, the drug indication, the drug category, the drug interaction, and the contraindicated drug;
a sending unit 503, configured to send the filtered recommended prescription information to the user.
Preferably, the recommendation screening module 500 further comprises a drug rule configuration unit 504, which controls the total drug price of the prescription based on the relevant rules, integrates the national medical insurance basic drug list, and prompts the outpatient physician to control the base drug ratio.
Preferably, the recommendation system further comprises a nurse station operation instruction module 600 for directly transmitting the medicine injection mode and the indication of dropping speed, proportioning and the like to the nurse station, so as to reduce the risk caused by improper medication.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A prescription recommendation method based on machine learning and knowledge graph is characterized by comprising the following steps:
acquiring and analyzing the diagnosis information to obtain one or more diagnosis details including patient information, doctor information and disease diagnosis;
inputting the diagnosis details into a pre-constructed machine learning model for reasoning to obtain an initial recommendation list aiming at the diagnosis details;
acquiring a relation graph network associated with the medicine from a medicine knowledge graph according to the medicine information contained in the initial recommendation list;
and screening and eliminating contraindicated medicines according to the relationship graph network, and then giving a final recommendation list.
2. The prescription recommendation method according to claim 1, wherein the pre-constructed machine learning model comprises a collaborative filtering-based recommendation model, a knowledge-based recommendation model and a neural network-based recommendation model, and the three basic recommendation models are obtained by training through a collaborative filtering algorithm, a knowledge-based recommendation algorithm and a neural network learning algorithm, respectively; the method for obtaining the initial recommendation list comprises the following steps: and respectively inputting the diagnosis detail information into the three basic recommendation models to obtain respectively recommended prescription drugs, removing repeated items, and sequencing according to the predicted adoption probability to obtain an initial recommendation list.
3. The prescription recommendation method of claim 2, wherein the collaborative filtering algorithm training of the original model comprises:
s21, mapping the values of the sex, the age at diagnosis and whether the patient is pregnant to a 16-digit space as the fingerprint of the patient, and calculating the relative distance of the patient by using the AND relation;
s22, sorting the data according to the patient fingerprint, prescription medicine and disease diagnosis triple, calculating the score data of the basic condition and disease diagnosis of the patient, then taking the score data as the index for measuring the similarity degree between the diseases of the patient, and obtaining the patient similarity matrix through a distance calculation method.
4. The prescription recommendation method according to claim 3, wherein said step of calculating the score data of patient baseline and disease diagnosis is:
a) reading the stored patient fingerprint, prescription medicine and disease diagnosis triple data;
b) starting a merging process, extracting the number of the prescription medicine as a main key, taking the patient and the disease diagnosis as values, and merging the data with the same number of the prescription medicine in the storage according to the formats of the prescription medicine, the disease diagnosis and the patient fingerprint sequence pair;
c) merging the data of the same main key, outputting the final result, taking the number of the prescription medicine as the main key and the fingerprint and disease diagnosis sequence pair of the patient as values, and storing the values in a database as the evaluation data of the prescription medicine.
5. The prescription recommendation method of claim 3, wherein the patient similarity matrix calculation step is:
a) reading the locally stored patient fingerprint and grading data of disease diagnosis;
b) rearranging data by taking the fingerprint pair of the patient as a main key and the score pair of the fingerprint of the patient and the disease diagnosis as values, calculating the score distance between the fingerprint of the patient and the disease diagnosis, outputting the main key as the fingerprint pair of the patient, and the value is the score distance between every two fingerprints of the patient for the same disease diagnosis;
c) starting a merging process, merging the data of the same patient fingerprint pair to obtain the distance values of all the same disease diagnosis scores of the fingerprints of the two patients, wherein the main key of the merging result is the patient to be treated, the value is the score distance between the treated patient and the patient to be treated, and the merging result is stored and used as the patient similarity matrix data.
6. The prescription recommendation method of claim 2, wherein the training of the original model by the knowledge-based recommendation algorithm comprises: the fixed diagnostic ICD10 code is formed in a recommended relationship to the prescription based on the latest clinical guidelines and expert consensus.
7. The prescription recommendation method of claim 2, wherein the neural network learning algorithm performing training of the raw model comprises:
s2a, obtaining a user behavior log reported by a doctor client, wherein the user behavior log comprises doctor ID, ICD10 diagnosis codes, patient basic information, prescription medicine lists and dosage, and storing the user behavior log in a server basic database;
s2b, carrying out data acquisition, cleaning, standardization processing, characteristic combination and extraction on the user behavior log data by constructing a characteristic collector to obtain characteristic vectors which have unified specifications and can be used for model training, wherein the characteristic vectors comprise user characteristic vectors, prescription medicine characteristic vectors and disease characteristic vectors;
s2c, transmitting the feature vectors into a multilayer neural network, taking the user feature vectors and the disease feature vectors as input, taking the prescription medicine feature vectors as output targets, taking each layer of the network as a global neural network layer, performing convolution operation on input data, and taking the convolution result of the previous layer as the input of the next layer;
acquiring interlayer weight information of the neural network through training of the neural network, and acquiring output information of currently input user characteristic vectors and disease characteristic vectors in the neural network based on the trained interlayer weight information, namely similarity of the currently input user characteristic vectors and the disease characteristic vectors with the characteristic vectors of prescription drugs;
and fully connecting the last layer of the neural network, outputting the prediction scores of the user and the disease prescription, constructing a user-disease-prescription score prediction table based on the prediction scores, and storing the user-disease-prescription score prediction table in a database.
8. The prescription recommendation method of claim 1, wherein said obtaining a relationship graph network associated with the drug from a drug knowledge graph comprises: the method comprises the steps of obtaining an initial recommendation list, extracting all medicines contained in each prescription, obtaining records of corresponding entities of the medicines in a knowledge graph according to medicine names, and obtaining entity and relation sets associated with the medicines, namely an indication, medicine belonging, medicine interaction and contraindication attribute set of the medicines, wherein if a plurality of medicines of the same prescription can be associated through interaction, a connected graph subset is formed, and the condition that the medicines in the subset have interaction relation is explained, otherwise, the condition that the medicines of the prescription do not have interaction is explained.
9. A machine learning and knowledge graph-based prescription recommendation system, comprising:
the diagnostic information analysis module is used for acquiring and analyzing the diagnostic information to obtain one or more pieces of diagnostic details including patient information, doctor information and disease diagnosis;
the machine learning module is used for inputting the diagnosis detail data into the machine learning model for training to obtain a recommendation model for recommending a prescription according to the patient information and the disease diagnosis;
the prescription recommending module is used for recommending an optional prescription according to the input patient information, doctor information and disease diagnosis;
the medicine relation graph module is used for acquiring a relation graph network associated with the medicine from a medicine knowledge graph according to the medicine information in the prescription;
and the recommendation result screening module is used for filtering and eliminating contraindicated medicines for the recommended optional prescription according to the relationship graph network.
10. The prescription recommendation system of claim 9, wherein the machine learning module comprises a collaborative filtering model, a knowledge-based recommendation model and a neural network learning model, and the three basic recommendation models are obtained by training respectively using a collaborative filtering algorithm, a knowledge-based recommendation algorithm and a neural network algorithm, and then the prescription recommendation model is obtained by fusing the three basic recommendation models.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911373211.9A CN111191020B (en) | 2019-12-27 | 2019-12-27 | Prescription recommendation method and system based on machine learning and knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911373211.9A CN111191020B (en) | 2019-12-27 | 2019-12-27 | Prescription recommendation method and system based on machine learning and knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111191020A true CN111191020A (en) | 2020-05-22 |
| CN111191020B CN111191020B (en) | 2023-09-22 |
Family
ID=70707677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911373211.9A Active CN111191020B (en) | 2019-12-27 | 2019-12-27 | Prescription recommendation method and system based on machine learning and knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191020B (en) |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627515A (en) * | 2020-05-29 | 2020-09-04 | 上海商汤智能科技有限公司 | Medicine recommendation method and device, electronic equipment and medium |
| CN111667890A (en) * | 2020-05-29 | 2020-09-15 | 平安科技（深圳）有限公司 | Medication recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN111753543A (en) * | 2020-06-24 | 2020-10-09 | 北京百度网讯科技有限公司 | Medicine recommendation method and device, electronic equipment and storage medium |
| CN111798954A (en) * | 2020-06-11 | 2020-10-20 | 西北工业大学 | Drug combination recommendation method based on time attention mechanism and graph convolution network |
| CN111833984A (en) * | 2020-07-16 | 2020-10-27 | 平安科技（深圳）有限公司 | Medicine quality control analysis method, device, equipment and medium based on machine learning |
| CN111883228A (en) * | 2020-07-28 | 2020-11-03 | 平安科技（深圳）有限公司 | Health information recommendation method, device, equipment and medium based on knowledge graph |
| CN111951915A (en) * | 2020-08-10 | 2020-11-17 | 智业软件股份有限公司 | Medicine and medicine usage recommendation method, terminal device and storage medium |
| CN111968715A (en) * | 2020-06-30 | 2020-11-20 | 厦门大学 | Drug recommendation modeling method based on medical record data and drug interaction risk |
| CN112017747A (en) * | 2020-09-04 | 2020-12-01 | 四川大学 | Intelligent recommendation method for enhanced CT contrast agent injection scheme |
| CN112071431A (en) * | 2020-09-18 | 2020-12-11 | 山东众阳健康科技集团有限公司 | Clinical path automatic generation method and system based on deep learning and knowledge graph |
| CN112100202A (en) * | 2020-11-12 | 2020-12-18 | 北京药联健康科技有限公司 | Product identification and product information completion method, storage medium and robot |
| CN112133425A (en) * | 2020-09-11 | 2020-12-25 | 北京欧应信息技术有限公司 | System for assisting doctor to optimize diagnosis and treatment process based on intelligent recommendation |
| CN112216364A (en) * | 2020-10-10 | 2021-01-12 | 福建健康之路信息技术有限公司 | Medication prescription pushing method and system based on artificial intelligence |
| CN112435761A (en) * | 2020-12-04 | 2021-03-02 | 中国信息通信研究院 | Information recommendation method and device |
| CN112541351A (en) * | 2020-12-08 | 2021-03-23 | 济南市城乡建设数字化中心 | Method and system for dispatching government affair hotline work order in residential building field |
| CN112700838A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| CN112786198A (en) * | 2021-02-08 | 2021-05-11 | 科大讯飞股份有限公司 | Diagnosis and treatment information recommendation model construction method, diagnosis and treatment information recommendation method and device |
| CN112802575A (en) * | 2021-04-10 | 2021-05-14 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN112802573A (en) * | 2021-01-26 | 2021-05-14 | 中国科学技术大学 | Medicine package recommendation method and device, computer system and readable storage medium |
| CN112951362A (en) * | 2021-02-23 | 2021-06-11 | 上海商汤智能科技有限公司 | Medicine recommendation method, device, equipment and storage medium |
| CN113436746A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Medicine taking recommendation method, device, equipment and storage medium based on sorting algorithm |
| CN113434626A (en) * | 2021-08-27 | 2021-09-24 | 之江实验室 | Multi-center medical diagnosis knowledge map representation learning method and system |
| CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
| CN113628726A (en) * | 2021-08-10 | 2021-11-09 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine dialectical treatment recommendation system and method based on graph neural network and electronic equipment |
| CN113707261A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medicine recommendation method and device and related equipment |
| CN113707262A (en) * | 2021-08-31 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Medicine use recommendation method and device, computer equipment and storage medium |
| CN113744867A (en) * | 2021-08-30 | 2021-12-03 | 平安科技（深圳）有限公司 | Drug recommendation evidence-based support method, device, equipment and storage medium |
| CN113808751A (en) * | 2020-06-15 | 2021-12-17 | 中国中医科学院中国医史文献研究所 | Traditional Chinese medicine prescription evaluation and pushing method and device and electronic equipment |
| WO2022041729A1 (en) * | 2020-08-31 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Medication recommendation method, apparatus and device, and storage medium |
| CN114203276A (en) * | 2021-12-16 | 2022-03-18 | 山东众阳健康科技集团有限公司 | Intelligent dialysis prescription information generation method and system |
| CN114283925A (en) * | 2022-01-17 | 2022-04-05 | 厦门大学 | Intelligent prescription recommendation method and storage medium |
| CN114386528A (en) * | 2022-01-18 | 2022-04-22 | 平安科技（深圳）有限公司 | Model training method and device, computer equipment and storage medium |
| CN114464312A (en) * | 2022-01-04 | 2022-05-10 | 北京欧应信息技术有限公司 | System for assisting disease reasoning and storage medium |
| CN114582463A (en) * | 2022-05-05 | 2022-06-03 | 成都尚医信息科技有限公司 | Personalized motion guidance system and method based on machine learning |
| CN114722976A (en) * | 2022-06-09 | 2022-07-08 | 青岛美迪康数字工程有限公司 | Medicine recommendation system and construction method |
| CN114783571A (en) * | 2022-04-06 | 2022-07-22 | 北京交通大学 | Traditional Chinese medicine dynamic diagnosis and treatment scheme optimization method and system based on deep reinforcement learning |
| CN115620886A (en) * | 2022-12-19 | 2023-01-17 | 北京大学第三医院（北京大学第三临床医学院） | Data auditing method and device |
| CN115658877A (en) * | 2022-12-27 | 2023-01-31 | 神州医疗科技股份有限公司 | Medicine recommendation method and device based on reinforcement learning, electronic equipment and medium |
| CN115691741A (en) * | 2023-01-03 | 2023-02-03 | 四川大学华西医院 | Medical information-based information transmission and information combination method |
| CN116110533A (en) * | 2023-02-27 | 2023-05-12 | 之江实验室 | Event map-based drug type and dosage recommendation system and method |
| CN116364240A (en) * | 2023-02-02 | 2023-06-30 | 复旦大学附属肿瘤医院 | Remote nutrition information processing method and system based on Internet |
| CN116469527A (en) * | 2023-04-21 | 2023-07-21 | 脉景（杭州）健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
| CN116467471A (en) * | 2023-06-20 | 2023-07-21 | 山东志诚普惠健康科技有限公司 | Intelligent prescription filling method and device based on medical knowledge graph |
| CN116486939A (en) * | 2022-12-26 | 2023-07-25 | 北京左医健康技术有限公司 | Data mining method and system for medicine knowledge graph and electronic equipment |
| CN117034202A (en) * | 2023-10-09 | 2023-11-10 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
| CN117252664A (en) * | 2023-11-10 | 2023-12-19 | 浙江口碑网络技术有限公司 | Medicine recommendation reason generation method, device, medium and equipment |
| CN117334352A (en) * | 2023-11-24 | 2024-01-02 | 北京邮电大学 | Hypertension diagnosis and treatment decision reasoning method and device based on multiple role knowledge graph |
| CN117633340A (en) * | 2023-08-14 | 2024-03-01 | 江南大学附属医院 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170277841A1 (en) * | 2016-03-23 | 2017-09-28 | HealthPals, Inc. | Self-learning clinical intelligence system based on biological information and medical data metrics |
| CN108932975A (en) * | 2018-07-18 | 2018-12-04 | 中山大学 | A kind of recommender system based on mixing collaborative filtering doctors and patients information |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| CN110223751A (en) * | 2019-05-16 | 2019-09-10 | 平安科技（深圳）有限公司 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
-
2019
- 2019-12-27 CN CN201911373211.9A patent/CN111191020B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170277841A1 (en) * | 2016-03-23 | 2017-09-28 | HealthPals, Inc. | Self-learning clinical intelligence system based on biological information and medical data metrics |
| CN108932975A (en) * | 2018-07-18 | 2018-12-04 | 中山大学 | A kind of recommender system based on mixing collaborative filtering doctors and patients information |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| CN110223751A (en) * | 2019-05-16 | 2019-09-10 | 平安科技（深圳）有限公司 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
Cited By (74)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627515A (en) * | 2020-05-29 | 2020-09-04 | 上海商汤智能科技有限公司 | Medicine recommendation method and device, electronic equipment and medium |
| CN111667890A (en) * | 2020-05-29 | 2020-09-15 | 平安科技（深圳）有限公司 | Medication recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN111798954A (en) * | 2020-06-11 | 2020-10-20 | 西北工业大学 | Drug combination recommendation method based on time attention mechanism and graph convolution network |
| CN113808751A (en) * | 2020-06-15 | 2021-12-17 | 中国中医科学院中国医史文献研究所 | Traditional Chinese medicine prescription evaluation and pushing method and device and electronic equipment |
| CN111753543A (en) * | 2020-06-24 | 2020-10-09 | 北京百度网讯科技有限公司 | Medicine recommendation method and device, electronic equipment and storage medium |
| CN111753543B (en) * | 2020-06-24 | 2024-03-12 | 北京百度网讯科技有限公司 | Medicine recommendation method, device, electronic equipment and storage medium |
| CN111968715B (en) * | 2020-06-30 | 2022-11-01 | 厦门大学 | Drug recommendation modeling method based on medical record data and drug interaction risk |
| CN111968715A (en) * | 2020-06-30 | 2020-11-20 | 厦门大学 | Drug recommendation modeling method based on medical record data and drug interaction risk |
| CN111833984A (en) * | 2020-07-16 | 2020-10-27 | 平安科技（深圳）有限公司 | Medicine quality control analysis method, device, equipment and medium based on machine learning |
| CN111833984B (en) * | 2020-07-16 | 2023-06-20 | 平安科技（深圳）有限公司 | Medicine quality control analysis method, device, equipment and medium based on machine learning |
| WO2021135429A1 (en) * | 2020-07-28 | 2021-07-08 | 平安科技（深圳）有限公司 | Knowledge map-based health information recommendation method, apparatus, device, and medium |
| CN111883228B (en) * | 2020-07-28 | 2023-07-07 | 平安科技（深圳）有限公司 | Knowledge graph-based health information recommendation method, device, equipment and medium |
| CN111883228A (en) * | 2020-07-28 | 2020-11-03 | 平安科技（深圳）有限公司 | Health information recommendation method, device, equipment and medium based on knowledge graph |
| CN111951915A (en) * | 2020-08-10 | 2020-11-17 | 智业软件股份有限公司 | Medicine and medicine usage recommendation method, terminal device and storage medium |
| WO2022041729A1 (en) * | 2020-08-31 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Medication recommendation method, apparatus and device, and storage medium |
| CN112017747A (en) * | 2020-09-04 | 2020-12-01 | 四川大学 | Intelligent recommendation method for enhanced CT contrast agent injection scheme |
| CN112017747B (en) * | 2020-09-04 | 2022-09-27 | 四川大学 | Intelligent recommendation method for enhanced CT contrast agent injection scheme |
| CN112133425A (en) * | 2020-09-11 | 2020-12-25 | 北京欧应信息技术有限公司 | System for assisting doctor to optimize diagnosis and treatment process based on intelligent recommendation |
| CN112071431B (en) * | 2020-09-18 | 2024-02-23 | 众阳健康科技集团有限公司 | Clinical path automatic generation method and system based on deep learning and knowledge graph |
| CN112071431A (en) * | 2020-09-18 | 2020-12-11 | 山东众阳健康科技集团有限公司 | Clinical path automatic generation method and system based on deep learning and knowledge graph |
| CN112216364A (en) * | 2020-10-10 | 2021-01-12 | 福建健康之路信息技术有限公司 | Medication prescription pushing method and system based on artificial intelligence |
| CN112100202A (en) * | 2020-11-12 | 2020-12-18 | 北京药联健康科技有限公司 | Product identification and product information completion method, storage medium and robot |
| CN112435761A (en) * | 2020-12-04 | 2021-03-02 | 中国信息通信研究院 | Information recommendation method and device |
| CN112541351B (en) * | 2020-12-08 | 2023-09-05 | 济南市城乡建设数字化中心 | Method and system for dispatching government service heat line work orders in living construction field |
| CN112541351A (en) * | 2020-12-08 | 2021-03-23 | 济南市城乡建设数字化中心 | Method and system for dispatching government affair hotline work order in residential building field |
| CN112700838A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| CN112700838B (en) * | 2020-12-30 | 2024-03-01 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| CN112802573B (en) * | 2021-01-26 | 2023-06-20 | 中国科学技术大学 | Medicine package recommendation method, device, computer system and readable storage medium |
| CN112802573A (en) * | 2021-01-26 | 2021-05-14 | 中国科学技术大学 | Medicine package recommendation method and device, computer system and readable storage medium |
| CN112786198A (en) * | 2021-02-08 | 2021-05-11 | 科大讯飞股份有限公司 | Diagnosis and treatment information recommendation model construction method, diagnosis and treatment information recommendation method and device |
| CN112786198B (en) * | 2021-02-08 | 2024-05-31 | 科大讯飞股份有限公司 | Diagnosis and treatment information recommendation model construction method, diagnosis and treatment information recommendation method and device |
| CN112951362A (en) * | 2021-02-23 | 2021-06-11 | 上海商汤智能科技有限公司 | Medicine recommendation method, device, equipment and storage medium |
| CN112802575A (en) * | 2021-04-10 | 2021-05-14 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN112802575B (en) * | 2021-04-10 | 2021-09-03 | 浙江大学 | Medication decision support method, device, equipment and medium based on graphic state machine |
| CN113436746A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Medicine taking recommendation method, device, equipment and storage medium based on sorting algorithm |
| CN113436746B (en) * | 2021-06-30 | 2024-04-12 | 平安科技（深圳）有限公司 | Medication recommendation method, device, equipment and storage medium based on sorting algorithm |
| CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
| CN113628726B (en) * | 2021-08-10 | 2023-12-26 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine diagnosis and treatment recommendation system and method based on graph neural network and electronic equipment |
| CN113628726A (en) * | 2021-08-10 | 2021-11-09 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine dialectical treatment recommendation system and method based on graph neural network and electronic equipment |
| CN113434626B (en) * | 2021-08-27 | 2021-12-07 | 之江实验室 | Multi-center medical diagnosis knowledge map representation learning method and system |
| CN113434626A (en) * | 2021-08-27 | 2021-09-24 | 之江实验室 | Multi-center medical diagnosis knowledge map representation learning method and system |
| CN113707261A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medicine recommendation method and device and related equipment |
| CN113744867B (en) * | 2021-08-30 | 2024-03-08 | 平安科技（深圳）有限公司 | Medicine recommendation evidence-based support method, device, equipment and storage medium |
| CN113744867A (en) * | 2021-08-30 | 2021-12-03 | 平安科技（深圳）有限公司 | Drug recommendation evidence-based support method, device, equipment and storage medium |
| CN113707262A (en) * | 2021-08-31 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Medicine use recommendation method and device, computer equipment and storage medium |
| CN114203276A (en) * | 2021-12-16 | 2022-03-18 | 山东众阳健康科技集团有限公司 | Intelligent dialysis prescription information generation method and system |
| CN114464312A (en) * | 2022-01-04 | 2022-05-10 | 北京欧应信息技术有限公司 | System for assisting disease reasoning and storage medium |
| CN114283925A (en) * | 2022-01-17 | 2022-04-05 | 厦门大学 | Intelligent prescription recommendation method and storage medium |
| CN114386528B (en) * | 2022-01-18 | 2024-05-14 | 平安科技（深圳）有限公司 | Model training method and device, computer equipment and storage medium |
| WO2023137924A1 (en) * | 2022-01-18 | 2023-07-27 | 平安科技（深圳）有限公司 | Model training method and apparatus, computer device, and storage medium |
| CN114386528A (en) * | 2022-01-18 | 2022-04-22 | 平安科技（深圳）有限公司 | Model training method and device, computer equipment and storage medium |
| CN114783571A (en) * | 2022-04-06 | 2022-07-22 | 北京交通大学 | Traditional Chinese medicine dynamic diagnosis and treatment scheme optimization method and system based on deep reinforcement learning |
| CN114582463A (en) * | 2022-05-05 | 2022-06-03 | 成都尚医信息科技有限公司 | Personalized motion guidance system and method based on machine learning |
| CN114722976A (en) * | 2022-06-09 | 2022-07-08 | 青岛美迪康数字工程有限公司 | Medicine recommendation system and construction method |
| CN115620886B (en) * | 2022-12-19 | 2023-04-28 | 北京大学第三医院（北京大学第三临床医学院） | Data auditing method and device |
| CN115620886A (en) * | 2022-12-19 | 2023-01-17 | 北京大学第三医院（北京大学第三临床医学院） | Data auditing method and device |
| CN116486939B (en) * | 2022-12-26 | 2024-01-23 | 北京左医健康技术有限公司 | Data mining method and system for medicine knowledge graph and electronic equipment |
| CN116486939A (en) * | 2022-12-26 | 2023-07-25 | 北京左医健康技术有限公司 | Data mining method and system for medicine knowledge graph and electronic equipment |
| CN115658877B (en) * | 2022-12-27 | 2023-03-21 | 神州医疗科技股份有限公司 | Medicine recommendation method and device based on reinforcement learning, electronic equipment and medium |
| CN115658877A (en) * | 2022-12-27 | 2023-01-31 | 神州医疗科技股份有限公司 | Medicine recommendation method and device based on reinforcement learning, electronic equipment and medium |
| CN115691741A (en) * | 2023-01-03 | 2023-02-03 | 四川大学华西医院 | Medical information-based information transmission and information combination method |
| CN116364240B (en) * | 2023-02-02 | 2024-01-26 | 复旦大学附属肿瘤医院 | Remote nutrition information processing method and system based on Internet |
| CN116364240A (en) * | 2023-02-02 | 2023-06-30 | 复旦大学附属肿瘤医院 | Remote nutrition information processing method and system based on Internet |
| CN116110533A (en) * | 2023-02-27 | 2023-05-12 | 之江实验室 | Event map-based drug type and dosage recommendation system and method |
| CN116110533B (en) * | 2023-02-27 | 2023-09-01 | 之江实验室 | Event map-based drug type and dosage recommendation system and method |
| CN116469527B (en) * | 2023-04-21 | 2023-09-08 | 脉景（杭州）健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
| CN116469527A (en) * | 2023-04-21 | 2023-07-21 | 脉景（杭州）健康管理有限公司 | Optimized recommendation method, system and equipment for traditional Chinese medicine prescription |
| CN116467471A (en) * | 2023-06-20 | 2023-07-21 | 山东志诚普惠健康科技有限公司 | Intelligent prescription filling method and device based on medical knowledge graph |
| CN117633340A (en) * | 2023-08-14 | 2024-03-01 | 江南大学附属医院 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
| CN117034202A (en) * | 2023-10-09 | 2023-11-10 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
| CN117034202B (en) * | 2023-10-09 | 2024-01-05 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
| CN117252664A (en) * | 2023-11-10 | 2023-12-19 | 浙江口碑网络技术有限公司 | Medicine recommendation reason generation method, device, medium and equipment |
| CN117334352B (en) * | 2023-11-24 | 2024-03-08 | 北京邮电大学 | Hypertension diagnosis and treatment decision reasoning method and device based on multiple role knowledge graph |
| CN117334352A (en) * | 2023-11-24 | 2024-01-02 | 北京邮电大学 | Hypertension diagnosis and treatment decision reasoning method and device based on multiple role knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111191020B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191020B (en) | Prescription recommendation method and system based on machine learning and knowledge graph | |
| CN112037880B (en) | Medication recommendation method, device, equipment and storage medium | |
| Sherimon et al. | OntoDiabetic: an ontology-based clinical decision support system for diabetic patients | |
| CN110291555B (en) | Systems and methods for facilitating computational analysis of health conditions | |
| US20180011980A1 (en) | Differential medical diagnosis apparatus adapted in order to determine an optimal sequence of diagnostic tests for identifying a pathology by adopting diagnostic appropriateness criteria | |
| US20080033894A1 (en) | Prognosis Modeling From One or More Sources of Information | |
| US7856362B2 (en) | System and method for early identification of safety concerns of new drugs | |
| US11450434B2 (en) | Implementation of machine-learning based query construction and pattern identification through visualization in user interfaces | |
| CN116013534A (en) | Clinical auxiliary decision-making method and system based on medical guideline and data | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| US10832822B1 (en) | Methods and systems for locating therapeutic remedies | |
| KR101295785B1 (en) | Apparatus and Method for Constructing Gene-Disease Relation Database | |
| Yu et al. | Clinical coverage of an archetype repository over SNOMED-CT | |
| Chen et al. | Using data mining strategies in clinical decision making: a literature review | |
| CN113742443A (en) | Multi-medicine sharing query method, mobile terminal and storage medium | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN110473636B (en) | Intelligent medical advice recommendation method and system based on deep learning | |
| Gupta et al. | An overview of clinical decision support system (cdss) as a computational tool and its applications in public health | |
| Chen et al. | Cognitive computing-based CDSS in medical practice | |
| Prabhakar et al. | Neural language modeling of unstructured clinical notes for automated patient phenotyping | |
| US12019657B1 (en) | Apparatus and method for heuristic data forecasting in high-paced, limited data environments | |
| CN117688226B (en) | Intelligent pre-diagnosis self-service bill making method and system based on similar child patient matching | |
| Johnson | Addressing Highly Imbalanced Big Data Challenges for Medicare Fraud Classification | |
| Singh et al. | Big Data in Oncology: Extracting Knowledge from Machine Learning | |
| CN117690549A (en) | Traditional Chinese medicine individuation intelligent prescription medicine recommendation system based on similar patient matching |
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 |