CN110223751A - Prescription evaluation method, system and computer equipment based on medical knowledge map - Google Patents
Prescription evaluation method, system and computer equipment based on medical knowledge map Download PDFInfo
- Publication number
- CN110223751A CN110223751A CN201910405122.1A CN201910405122A CN110223751A CN 110223751 A CN110223751 A CN 110223751A CN 201910405122 A CN201910405122 A CN 201910405122A CN 110223751 A CN110223751 A CN 110223751A
- Authority
- CN
- China
- Prior art keywords
- medication
- prescription
- information
- target
- data
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 37
- 239000003814 drug Substances 0.000 claims abstract description 156
- 229940079593 drug Drugs 0.000 claims abstract description 153
- 239000011159 matrix material Substances 0.000 claims abstract description 21
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 25
- 201000010099 disease Diseases 0.000 claims description 24
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 24
- 238000003860 storage Methods 0.000 claims description 20
- 206010013710 Drug interaction Diseases 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 11
- 241000894006 Bacteria Species 0.000 claims description 9
- 239000000902 placebo Substances 0.000 claims description 9
- 229940068196 placebo Drugs 0.000 claims description 9
- 241000700605 Viruses Species 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000003745 diagnosis Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000036961 partial effect Effects 0.000 claims description 5
- 241001269238 Data Species 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 230000001717 pathogenic effect Effects 0.000 claims description 3
- 208000024891 symptom Diseases 0.000 claims description 3
- 206010067671 Disease complication Diseases 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- XZWYZXLIPXDOLR-UHFFFAOYSA-N metformin Chemical compound CN(C)C(=N)NC(N)=N XZWYZXLIPXDOLR-UHFFFAOYSA-N 0.000 description 6
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000007939 sustained release tablet Substances 0.000 description 5
- 239000003826 tablet Substances 0.000 description 5
- 206010020772 Hypertension Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 210000000987 immune system Anatomy 0.000 description 2
- 238000002483 medication Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 229940123208 Biguanide Drugs 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 208000036647 Medication errors Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- -1 hydrochloride Biguanides Chemical class 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000002147 killing effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 229960004329 metformin hydrochloride Drugs 0.000 description 1
- OETHQSJEHLVLGH-UHFFFAOYSA-N metformin hydrochloride Chemical compound Cl.CN(C)C(=N)N=C(N)N OETHQSJEHLVLGH-UHFFFAOYSA-N 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 229940126532 prescription medicine Drugs 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum 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
- 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)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a kind of Prescription evaluation methods based on medical knowledge map, which comprises obtains the electronic prescription information that doctor issues, the electronic prescription information includes patient information and medication information;N number of target data is extracted from the electronic prescription information;N number of target data is input in Knowledge Representation Model, N*d dimension term vector matrix is obtained, wherein each target data is mapped as a d dimension term vector;By N*d dimension term vector Input matrix into convolutional neural networks model, pass through the convolutional neural networks model output category vector;At least one target medication classification is filtered out from multiple medication classifications according to the class vector;Prescription comment data are exported according to the target medication classification and preconfigured medical knowledge map.Prescription data of the embodiment of the present invention analyzes accuracy rate height, and computer equipment brings higher operation burden and maintenance cost.
Description
Technical field
The present embodiments relate to field of computer data processing more particularly to a kind of prescriptions based on medical knowledge map
Evaluation method, system, computer equipment and computer readable storage medium.
Background technique
Prescription comment is the medication regulatory format that developed recently gets up, be hospital by during doctor formula medication to clinic
Prescription carries out comprehensive statistics analysis, the entirety and subdivision feelings to work from different level and different angle reflection medical institutions' prescription
Condition carries out decision for medical institutions' management level and provides the data of science to support, to reach the rational use of medicines, Medication monitor, management
Purpose.
Prescription comment system on the market is based on a large amount of Rulemakings at present.Therefore, it is necessary to configure and safeguard prescription
Rule base is commented on, and judges whether the prescription that doctor provides is reasonable based on the rule of the Prescription comment rule base.However, drug
Type, kinds of Diseases etc. are abnormal various, especially with the increasingly increase of drug variety, it is desirable to obtain high-precision comment knot
Fruit, regular clause amount in Prescription comment rule base may exponentially grade increase, and even if write enough rules, accuracy rate
Also it is not necessarily promoted.It, will be inevitable after quantity has arrived to a certain degree because every rule has its condition of compatibility
In the presence of a large amount of conflict.The loss for the bring accuracy rate that finally conflicts, the promotion of killing policies quantity bring accuracy rate
?.In addition, if when accuracy rate and recall rate one bottleneck of arrival, increasing by a rules and regulations using rule-based method
Then or one rule of change to involve be that there are many data, this process is very time-consuming.
It is found that the prescription data analysis accuracy rate of above-mentioned Prescription comment system is not high, and the growth of a large amount of rules can be meter
It calculates machine equipment and brings higher operation burden and maintenance cost.
Summary of the invention
In view of this, the purpose of the embodiment of the present invention is that provide a kind of Prescription evaluation method based on medical knowledge map,
System, computer equipment and computer readable storage medium, for solving the following problems of existing Prescription comment system: prescription number
Not high according to analysis accuracy rate, the growth of a large amount of rules is that computer equipment brings higher operation burden and maintenance cost.
To achieve the above object, the embodiment of the invention provides a kind of Prescription evaluation method based on medical knowledge map,
The described method includes:
The electronic prescription information that doctor issues is obtained, the electronic prescription information includes patient information and medication information;
N number of target data is extracted from the electronic prescription information;
N number of target data is input in Knowledge Representation Model, N*d dimension term vector matrix is obtained, wherein each mesh
Mark data are mapped as a d dimension term vector;
By N*d dimension term vector Input matrix into convolutional neural networks model, pass through the convolutional neural networks mould
Type output category vector, the class vector include multiple vector parameters, and each vector parameter is for indicating to preset multiple medications
The prediction probability of one of medication classification in classification;
At least one target medication classification is filtered out from multiple medication classifications according to the class vector;And
Prescription comment data are exported according to the target medication classification and preconfigured medical knowledge map.
Preferably, the step of obtaining the electronic prescription information that doctor issues, comprising:
The electronic prescription list of doctor's transmission is obtained, the electronic prescription list includes multiple fields;And
The electronic prescription list is parsed to obtain structural data.
Preferably, the step of extracting N number of target data from the electronic prescription information, comprising:
According to the multiple field names pre-seted, the multiple aiming field is searched from the structural data;
Corresponding N number of target data is obtained from the multiple aiming field.
Preferably, the multiple aiming field includes multiple first kind aiming fields, the multiple first kind aiming field
Including patient diagnosis information field and ethical goods information field, one or more has been respectively associated in each first kind aiming field
Segment dictionary;
The step of obtaining corresponding target data from the multiple aiming field, comprising:
Obtain the field text information of each first kind aiming field;
The one or more participle dictionaries being respectively associated according to each first kind aiming field, to each first classification
The field text information of marking-up section carries out participle operation, to obtain multiple participles;
Wherein, the multiple participle is the partial target data in N number of target data.
Preferably, further include the steps that training the Knowledge Representation Model in advance:
The medical data in medical data base is acquired, the medical data includes multiple training datas;
The training set being made of multiple triples is defined according to the multiple training data;And
The Knowledge Representation Model is corresponded to based on the training set to be trained, obtain each training data and relationship to
Map vector in quantity space.
Preferably, further include the steps that being pre-configured with medical knowledge map:
The medical data in medical data base is acquired, medical knowledge map is constructed according to the medical data;
Wherein, the medical knowledge map includes the relationship letter between the nodal information and each node of multiple nodes
Breath;The multiple node includes: disease, symptom, virus, bacterium, chemical substance, drug, physical feeling, crowd;It is described each
Relation information between node includes: mutual between conformity relation or taboo relationship, drug and drug between drug and disease
Interactively, the pathogenic cause of disease relationship of virus and bacteria and disease, drug and the conformity relation of crowd or taboo relationship, each disease
Between complication relationship.
Preferably, the multiple medication classification includes: repeated drug taking, drug interaction, medication taboo, medication in medication
Side effect, placebo and prescription are reasonable;At the target medication classification and preconfigured medical knowledge map output
The step of side's comment data, comprising:
If the target medication classification is that prescription is reasonable, generates medication and reasonably comment on content;
If the target is one or more of: drug interaction, medication in repeated drug taking, medication according to classification
Taboo, medication side effect and placebo, according to the diagnostic message in the target medication classification and the electronic prescription information
With medication information, corresponding association content is found from the medical knowledge map, and phase is generated according to the association content
The comment content answered.
To achieve the above object, the embodiment of the invention also provides a kind of Prescription evaluation systems based on medical knowledge map
System, comprising:
Module is obtained, the electronic prescription information issued for obtaining doctor, the electronic prescription information includes patient information
With medication information;
Extraction module, for extracting N number of target data from the electronic prescription information;
Term vector obtains module, for N number of target data to be input in Knowledge Representation Model, obtains N*d dimension word
Vector matrix, wherein each target data is mapped as a d dimension term vector;
Prediction module, for N*d dimension term vector Input matrix into convolutional neural networks model, to be passed through the volume
Product neural network model output category vector, the class vector include multiple vector parameters, and each vector parameter is for indicating
Preset the prediction probability of one of medication classification in multiple medication classifications;
Screening module, for filtering out at least one target medication class from multiple medication classifications according to the class vector
Not;And
Output module, for exporting prescription point according to the target medication classification and preconfigured medical knowledge map
Comment data.
To achieve the above object, the embodiment of the invention also provides a kind of computer equipment, the computer equipment storages
Device, processor and it is stored in the computer program that can be run on the memory and on the processor, the computer journey
The step of Prescription evaluation method as described above is realized when sequence is executed by processor.
To achieve the above object, the embodiment of the invention also provides a kind of computer readable storage medium, the computers
Computer program is stored in readable storage medium storing program for executing, the computer program can be performed by least one processor, so that institute
State the step of at least one processor executes Prescription evaluation method as described above.
It is provided in an embodiment of the present invention by the Prescription evaluation method of medical knowledge map, system, computer equipment and based on
Calculation machine readable storage medium storing program for executing, knowledge based indicate that model obtains the term vector matrix of electronic prescription information, and by term vector matrix
It is input to output category vector in convolutional neural networks model, according to class vector target medication classification, and then is used according to target
Medicine classification searches corresponding medication errors reason for it from medical knowledge mapping.It is predicted at electronics by convolutional neural networks
The medication problem of square information has very high precision of prediction, and avoids the big gauge formulated needed for conventional prescriptions comment system
Then, to reduce the operation burden and maintenance cost of computer equipment.
Detailed description of the invention
Fig. 1 is that the present invention is based on the flow charts of the Prescription evaluation embodiment of the method one of medical knowledge map.
Fig. 2 is that the present invention is based on the program module schematic diagrames of the Prescription evaluation system embodiment two of medical knowledge map.
Fig. 3 is the hardware structural diagram of computer equipment embodiment three of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Following embodiment will be that executing subject carries out exemplary description with computer equipment 2.
Embodiment one
Refering to fig. 1, the step of showing the Prescription evaluation method based on medical knowledge map of the embodiment of the present invention one stream
Cheng Tu.The sequence for executing step is defined it is appreciated that the flow chart in this method embodiment is not used in.It is specific as follows.
Step S100 obtains the electronic prescription information that doctor issues, and the electronic prescription information includes patient information and use
Medicine information.
In the exemplary embodiment, the patient information includes patient's name, age, gender, allergy information, pregnancy letter
Breath, diagnostic message etc., the medication information include nomenclature of drug, specification, quantity and usage and dosage.
In the exemplary embodiment, step S100 can specifically include sub-step S100A and S100B:
Step S100A obtains the electronic prescription list of doctor's transmission, and the electronic prescription list includes multiple fields.This
A little fields are defined according to the rules for writing of " Prescription Administrative Policy ", for acquiring the electronic prescription information.The multiple word
The field type of section may include text box, check box, radio box, drop-down choice box etc..
Step S100B parses the electronic prescription list, obtains structural data.
Step S102 extracts N number of target data from the electronic prescription information.
In the exemplary embodiment, step S102 can specifically include sub-step S102A and S102B.
Step S102A searches the multiple target according to the multiple field names pre-seted from the structural data
Field;
Step S102B obtains corresponding N number of target data from the multiple aiming field.
When having longer text information in some aiming field, such as collecting the aiming field of patient diagnosis information
In when there is longer diagnostic message, or there are more than two drugs in aiming field for collecting ethical goods information
When information, then need to segment operation.
In the exemplary embodiment, the multiple aiming field can be divided into multiple classifications, such as first kind target
Field, the second class aiming field ....Wherein, what first kind aiming field can fill in for user or doctor has certain character
The aiming field of length.For example, the multiple first kind aiming field may include patient diagnosis information field and prescription
Medicine information field.Corresponding one or more participle dictionaries have been respectively associated in each first kind aiming field.
Step S102B can specifically comprise the following steps:
Step 1, the field text information of each first kind aiming field is obtained;
Step 2, the one or more participle dictionaries being respectively associated according to each first kind aiming field, to described each the
The field text information of a kind of aiming field carries out participle operation, to obtain multiple participles;
Wherein, the multiple participle is the partial target data in N number of target data.
It can be appreciated that can effectively be mentioned for the corresponding one or more participle dictionaries of each first kind aiming field configuration
Rise the precision of word segmentation of the field text information of each first kind aiming field.
N number of target data is input in Knowledge Representation Model by step S104, obtains N*d dimension term vector matrix,
In each target data be mapped as d dimension term vector.N and d is the positive integer greater than 1.
Specifically, N number of target data is defined as N number of target entity, it is based on preconfigured Knowledge Representation Model
For each target entity match a target entity object set, each target entity object set include with respective objects entity it
Between with relationship by objective (RBO) all target entity objects.
The Knowledge Representation Model can be using transE, transH, transR, deepwalk etc..
In the exemplary embodiment, further include the steps that training the Knowledge Representation Model in advance, specific as follows:
The medical data in medical data base is acquired, the medical data includes multiple training datas;
The training set being made of multiple triples is defined according to the multiple training data;And
The Knowledge Representation Model is corresponded to based on the training set to be trained, obtain each training data and relationship to
Map vector in quantity space.
Step S106 passes through the convolution mind by N*d dimension term vector Input matrix into convolutional neural networks model
Through network model output category vector.
The convolutional neural networks model includes convolutional layer, pond layer, full articulamentum and softmax layers.
In the exemplary embodiment, the step S106 may include step S106A and S106B.
Step S106A ties up term vector matrix to the N*d by convolutional layer and executes convolution operation, obtains M convolution feature
Figure, the convolutional layer includes the convolution kernel of M f*d.
The convolutional layer includes the convolution kernel for the f*d that several step-lengths are 1, ties up term vector square to N*d by the convolutional layer
Battle array does convolution operation, to obtain the convolution characteristic pattern of several (L-f+1) * 1.That is, the width of each convolution characteristic pattern is 1, it is long
Degree is L-f+1.The length of convolution kernel is f, and participle quantity is L.
(L-f+1) * 1 element in convolution characteristic pattern, calculation formula are as follows:
The convolutional layer includes the convolution kernel for the f*d that several step-lengths are 1, ties up term vector square to N*d by the convolutional layer
Battle array does convolution operation, to obtain the convolution characteristic pattern of several (L-f+1) * 1.That is, the width of each convolution characteristic pattern is 1, it is long
Degree is L-f+1.The length of convolution kernel is f, and participle quantity is L.
(L-f+1) * 1 element in convolution characteristic pattern, calculation formula are as follows:
cij=f (wij⊙mi+bi)
Wherein, cijFor the characteristic value of j-th of element in (L-f+1) in ith feature trellis diagram, wijIt is corresponding i-th
The term vector matrix for being convolved core and being covered of a convolution characteristic pattern, ⊙ representing matrix are multiplied, miFor for calculating i-th volume
The convolution kernel of product characteristic pattern, biFor the bias term for calculating i-th of convolution characteristic pattern, f is nonlinear activation primitive, such as
ReLU function.
Step S106B, to the M convolution characteristic pattern by pond layer, full articulamentum and softmax layers, by described
Softmax layers of output category vector;
The class vector includes multiple vector parameters, and each vector parameter is for indicating to preset in multiple medication classifications
The prediction probability of one of medication classification.
Specifically, medication classification includes, but are not limited to: [indication repeats multiple medical instruments identical function to 1. repeated drug takings
Effect];2. drug interaction in medication;3 medications taboo;4, medication side effect;5. placebo [have in write a prescription product to disease without
Effect];6 prescriptions are reasonable.
Step S108 filters out at least one target medication classification according to the class vector from multiple medication classifications.
For example, filtering out one or more medication classifications that prediction probability is greater than preset threshold, and one that this is filtered out
A or multiple medication classifications are as target medication classification.
Step S110 exports Prescription comment number according to the target medication classification and preconfigured medical knowledge map
According to.
In the exemplary embodiment:
(1) it if the target medication classification is that prescription is reasonable, generates medication and reasonably comments on content;
(2) if the target according to classification is one or more of: drug interaction in repeated drug taking, medication,
Medication taboo, medication side effect and placebo, according to the diagnosis in the target medication classification and the electronic prescription information
Information and medication information find corresponding association content from the medical knowledge map, and raw according to the association content
At corresponding comment content.
For example, when target medication classification is " having drug interaction in prescription ", then according to the target medication class
The interaction relationship between recipe product not everywhere in medical knowledge mapping in lookup electronic prescription information, and according to the phase
Interaction relationship generates comment content, and the comment content of generation is output to headend equipment, as doctor computer on.
In the exemplary embodiment, further include the steps that being pre-configured with medical knowledge map: in acquisition medical data base
Medical data, according to the medical data construct medical knowledge map.
Wherein, the medical knowledge map includes the relationship letter between the nodal information and each node of multiple nodes
Breath;The multiple node includes: disease, symptom, virus, bacterium, chemical substance, drug, physical feeling, crowd;It is described each
Relation information between node includes: mutual between conformity relation or taboo relationship, drug and drug between drug and disease
Interactively, the pathogenic cause of disease relationship of virus and bacteria and disease, drug and the conformity relation of crowd or taboo relationship, each disease
Between complication relationship.
In order to enable the present invention is more clear clear a, specific example presented below:
Partial data is as follows in a certain prescription list: diagnosis: hypertension;It writes a prescription: Dimethyldiguanide hydrochloride enteric solubility tablet xx box
Xxg, diabecron sustained-release tablet xx box xxg;
1) N number of target data is extracted from the prescription list, such as: hypertension, Dimethyldiguanide hydrochloride enteric solubility tablet, hydrochloride
Biguanides sustained release tablets;
2) hypertension, Dimethyldiguanide hydrochloride enteric solubility tablet, diabecron sustained-release tablet are obtained into 3*128 dimension by transE
Term vector matrix, i.e. hypertension, Dimethyldiguanide hydrochloride enteric solubility tablet, diabecron sustained-release tablet are mapped as one 128 respectively
Tie up term vector;
3) term vector matrix is tieed up to the 3*128 by convolutional layer and executes convolution operation, obtain 1 convolution characteristic pattern, institute
State the convolution kernel that convolutional layer includes 1 1*128;
4) the M convolution characteristic pattern is exported by pond layer, full articulamentum and softmax layers by described softmax layers
Class vector, class vector to the prediction probability including 6 kinds of medication classifications, such as class vector of output be (0.98,0.66,
0.50,0.91,0.69,0.66), then it represents that:
1, repeated drug taking, prediction probability 0.98;
2, drug interaction in medication, prediction probability 0.66;
3, medication taboo, prediction probability 0.50;
4, medication side effect, prediction probability 0.91;
5, placebo, prediction probability 0.69;
6, prescription is reasonable, prediction probability 0.66;
5) whether the prediction probability for judging each medication classification is more than preset threshold, will be more than the medication classification of preset threshold
It is determined as and the associated target medication classification of the prescription list;
It is assumed that setting 0.95 for preset threshold, then " drug interaction in medication " is targeted medication classification;
Certain preset threshold also can be defined as other values, such as set 0.90, then " in medication for preset threshold
Drug interaction " and " medication side effect " are targeted medication classification;
6) medical knowledge map is searched according to the target medication classification, and comment is generated according to the object content found
Content.
According to " repeated drug taking " from the lookup Dimethyldiguanide hydrochloride enteric solubility tablet and Metformin hydrochloride in medical knowledge mapping
Sustained release tablets, and the comment content push of " repeated drug taking " is generated to front end, illustratively, which includes: above-mentioned two
Drug indication, and it is marked as medication classification: repeated drug taking.
It should be noted that searched from medical knowledge mapping according to above-mentioned process above two drug information and mutually
Interactively, rather than searched from medical knowledge mapping according to prescription data at the very start, reason is: various drug varieties
Various and various cross correlations are complicated, some disease is caused by bacterium, and doctor has opened two medicines, and two medicines respectively have this disease
Different efficacies are not belonging to repeated drug taking classification, but wherein have a kind of medicine that can play inhibiting effect to immune system, and immune system
This germ can be fought, is directly searched from medical knowledge mapping according to prescription data, there is very big lookup difficulty, and search
Low efficiency.
Embodiment two
Please continue to refer to Fig. 2, the journey of the Prescription evaluation system embodiment two the present invention is based on medical knowledge map is shown
Sequence module diagram.In the present embodiment, Prescription evaluation system 20 may include or be divided into one or more program modules,
One or more program module is stored in storage medium, and as performed by one or more processors, to complete this hair
It is bright, and can realize above-mentioned Prescription evaluation method.The so-called program module of the embodiment of the present invention refers to complete specific function
Series of computation machine program instruction section, the execution than program itself more suitable for description Prescription evaluation system 20 in storage medium
Process.The function of each program module of the present embodiment will specifically be introduced by being described below:
Module 200, the electronic prescription information issued for obtaining doctor are obtained, the electronic prescription information includes patient's letter
Breath and medication information.
In the exemplary embodiment, the acquisition module 200, is also used to: the electronic prescription list of doctor's transmission is obtained,
The electronic prescription list includes multiple fields;And the parsing electronic prescription list is to obtain structural data.
Extraction module 202, for extracting N number of target data from the electronic prescription information.
In the exemplary embodiment, the extraction module 202, is also used to: according to the multiple field names pre-seted, from
The multiple aiming field is searched in the structural data;Corresponding N number of mesh is obtained from the multiple aiming field
Mark data.
In the exemplary embodiment, the multiple aiming field includes multiple first kind aiming fields, and the multiple
A kind of aiming field includes patient diagnosis information field and ethical goods information field, and each first kind aiming field is respectively associated
There are one or more participle dictionaries.The extraction module 202, is also used to: obtaining the field text of each first kind aiming field
Information;The one or more participle dictionaries being respectively associated according to each first kind aiming field, to each first kind target
The field text information of field carries out participle operation, to obtain multiple participles;Wherein, the multiple participle is N number of target
Partial target data in data.
Term vector obtains module 204, for N number of target data to be input in Knowledge Representation Model, obtains N*d dimension
Term vector matrix, wherein each target data is mapped as a d dimension term vector.
Prediction module 206, for N*d dimension term vector Input matrix into convolutional neural networks model, to be passed through institute
Convolutional neural networks model output category vector is stated, the class vector includes multiple vector parameters, and each vector parameter is used for
The prediction probability of one of medication classification in multiple medication classifications is preset in expression.
Screening module 208 is used for filtering out at least one target from multiple medication classifications according to the class vector
Medicine classification.
Output module 210, at according to the target medication classification and preconfigured medical knowledge map output
Side's comment data.
In the exemplary embodiment, the multiple medication classification include: repeated drug taking, drug interaction in medication,
Medication taboo, medication side effect, placebo and prescription are reasonable.Output module 210, is also used to: if the target medication classification
It is reasonable for prescription, it generates medication and reasonably comments on content;If the target is one or more of according to classification: repeating to use
Drug interaction, medication taboo, medication side effect and placebo in medicine, medication, according to the target medication classification and institute
The diagnostic message and medication information in electronic prescription information are stated, is found in corresponding association from the medical knowledge map
Hold, and corresponding comment content is generated according to the association content.
It in the exemplary embodiment, further include map configuration module 212, for being pre-configured with medical knowledge map: adopting
Collect the medical data in medical data base, medical knowledge map is constructed according to the medical data.Wherein, the medical knowledge figure
Spectrum includes the relation information between the nodal information and each node of multiple nodes;The multiple node includes: disease, disease
Shape, virus, bacterium, chemical substance, drug, physical feeling, crowd;Relation information between each node includes: drug
The cause of interaction relationship, virus and bacteria and disease between disease between conformity relation or taboo relationship, drug and drug
Complication relationship between cause of disease relationship, drug and the conformity relation of crowd or taboo relationship, each disease
It in the exemplary embodiment, further include model training module 214, for first training the Knowledge Representation Model:
The medical data in medical data base is acquired, the medical data includes multiple training datas;According to the multiple training data
Define the training set being made of multiple triples;And the Knowledge Representation Model is corresponded to based on the training set and is trained, it obtains
To the map vector of each training data and relationship in vector space.
Embodiment three
It is the hardware structure schematic diagram of the computer equipment of the embodiment of the present invention three refering to Fig. 3.It is described in the present embodiment
Computer equipment 2 is that one kind can be automatic to carry out numerical value calculating and/or information processing according to the instruction for being previously set or storing
Equipment.The computer equipment 2 can be rack-mount server, blade server, tower server or Cabinet-type server
(including server cluster composed by independent server or multiple servers) etc..As shown, the computer equipment
2 include at least, but are not limited to, can be in communication with each other by system bus connection memory 21, processor 22, network interface 23, with
And Prescription evaluation system 20.Wherein:
In the present embodiment, memory 21 includes at least a type of computer readable storage medium, the readable storage
Medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device
(RAM), static random-access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), programmable read only memory (PROM), magnetic storage, disk, CD etc..In some embodiments, memory
21 can be the internal storage unit of computer equipment 2, such as the hard disk or memory of the computer equipment 2.In other implementations
In example, memory 21 is also possible to the grafting being equipped on the External memory equipment of computer equipment 2, such as the computer equipment 20
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Certainly, memory 21 can also both including computer equipment 2 internal storage unit and also including outside it
Store equipment.In the present embodiment, memory 21 is installed on the operating system and types of applications of computer equipment 2 commonly used in storage
Software, for example, embodiment five Prescription evaluation system 20 program code etc..In addition, memory 21 can be also used for temporarily depositing
Store up the Various types of data that has exported or will export.
Processor 22 can be in some embodiments central processing unit (Central Processing Unit, CPU),
Controller, microcontroller, microprocessor or other data processing chips.The processor 22 is commonly used in control computer equipment 2
Overall operation.In the present embodiment, program code or processing data of the processor 22 for being stored in run memory 21, example
Prescription evaluation system 20 is run, such as to realize the Prescription evaluation method of embodiment one.
The network interface 23 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established between the computer equipment 2 and other electronic devices.For example, the network interface 23 is for passing through network
The computer equipment 2 is connected with exterior terminal, establishes data transmission between the computer equipment 2 and exterior terminal
Channel and communication connection etc..The network can be intranet (Intranet), internet (Internet), whole world movement
Communication system (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband
Code Division Multiple Access, WCDMA), 4G network, 5G network, bluetooth (Bluetooth), the nothings such as Wi-Fi
Line or cable network.
It should be pointed out that Fig. 3 illustrates only the computer equipment 2 with component 20-23, it should be understood that simultaneously
All components shown realistic are not applied, the implementation that can be substituted is more or less component.
In the present embodiment, the Prescription evaluation system 20 being stored in memory 21 can also be divided into one or
The multiple program modules of person, one or more of program modules are stored in memory 21, and are handled by one or more
Device (the present embodiment is processor 22) is performed, to complete the present invention.
For example, Fig. 2 shows the program module schematic diagram for realizing 20 embodiment two of Prescription evaluation system, the embodiment
In, described can be divided into based on Prescription evaluation system 20 obtains module 200, extraction module 202, term vector acquisition module
204, prediction module 206, screening module 208, output module 210, map configuration module 212 and model configuration module 214.Its
In, the so-called program module of the present invention is the series of computation machine program instruction section for referring to complete specific function, more than program
It is suitable for describing implementation procedure of the Prescription evaluation system 20 in the computer equipment 2.Described program module 200-214
Concrete function had a detailed description in example 2, details are not described herein.
Example IV
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.
Answer function.The computer readable storage medium of the present embodiment is for storing Prescription evaluation system 20, realization when being executed by processor
The Prescription evaluation method of embodiment one.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Prescription evaluation method based on medical knowledge map, which is characterized in that the described method includes:
The electronic prescription information that doctor issues is obtained, the electronic prescription information includes patient information and medication information;
N number of target data is extracted from the electronic prescription information;
N number of target data is input in Knowledge Representation Model, N*d dimension term vector matrix is obtained, wherein each number of targets
Term vector is tieed up according to a d is mapped as;
It is defeated by the convolutional neural networks model by N*d dimension term vector Input matrix into convolutional neural networks model
Class vector out, the class vector include multiple vector parameters, and each vector parameter is for indicating to preset multiple medication classifications
In one of medication classification prediction probability;
At least one target medication classification is filtered out from multiple medication classifications according to the class vector;And
Prescription comment data are exported according to the target medication classification and preconfigured medical knowledge map.
2. Prescription evaluation method according to claim 1, which is characterized in that obtain the electronic prescription information that doctor issues
Step, comprising:
The electronic prescription list of doctor's transmission is obtained, the electronic prescription list includes multiple fields;And
The electronic prescription list is parsed to obtain structural data.
3. Prescription evaluation method according to claim 2, which is characterized in that extracted from the electronic prescription information N number of
The step of target data, comprising:
According to the multiple field names pre-seted, the multiple aiming field is searched from the structural data;
Corresponding N number of target data is obtained from the multiple aiming field.
4. Prescription evaluation method according to claim 3, which is characterized in that the multiple aiming field includes multiple first
Class aiming field, the multiple first kind aiming field include patient diagnosis information field and ethical goods information field, each
One or more participle dictionaries have been respectively associated in first kind aiming field;
The step of obtaining corresponding target data from the multiple aiming field, comprising:
Obtain the field text information of each first kind aiming field;
The one or more participle dictionaries being respectively associated according to each first kind aiming field, to each first kind target word
The field text information of section carries out participle operation, to obtain multiple participles;
Wherein, the multiple participle is the partial target data in N number of target data.
5. Prescription evaluation method according to claim 3, which is characterized in that further include training the representation of knowledge mould in advance
The step of type:
The medical data in medical data base is acquired, the medical data includes multiple training datas;
The training set being made of multiple triples is defined according to the multiple training data;And
The Knowledge Representation Model is corresponded to based on the training set to be trained, and obtains each training data and relationship in vector sky
Between in map vector.
6. Prescription evaluation method according to claim 5, which is characterized in that further include being pre-configured with medical knowledge map
Step:
The medical data in medical data base is acquired, medical knowledge map is constructed according to the medical data;
Wherein, the medical knowledge map includes the relation information between the nodal information and each node of multiple nodes;Institute
Stating multiple nodes includes: disease, symptom, virus, bacterium, chemical substance, drug, physical feeling, crowd;Each node it
Between relation information include: between drug and disease conformity relation or taboo relationship, the interaction between drug and drug close
Between system, pathogenic cause of disease relationship, drug and the conformity relation of crowd of virus and bacteria and disease or taboo relationship, each disease
Complication relationship.
7. Prescription evaluation method according to claim 6, which is characterized in that the multiple medication classification includes: that repetition is used
Drug interaction, medication taboo, medication side effect, placebo and prescription are reasonable in medicine, medication;According to the target medication class
The step of other and preconfigured medical knowledge map output Prescription comment data, comprising:
If the target medication classification is that prescription is reasonable, generates medication and reasonably comment on content;
If the target is one or more of according to classification: drug interaction, medication are prohibited in repeated drug taking, medication
Avoid, medication side effect and placebo, according in the target medication classification and the electronic prescription information diagnostic message and
Medication information finds corresponding association content from the medical knowledge map, and is generated accordingly according to the association content
Comment content.
8. a kind of Prescription evaluation system based on medical knowledge map characterized by comprising
Module is obtained, the electronic prescription information issued for obtaining doctor, the electronic prescription information includes patient information and use
Medicine information;
Extraction module, for extracting N number of target data from the electronic prescription information;
Term vector obtains module, for N number of target data to be input in Knowledge Representation Model, obtains N*d dimension term vector
Matrix, wherein each target data is mapped as a d dimension term vector;
Prediction module, for N*d dimension term vector Input matrix into convolutional neural networks model, to be passed through the convolution mind
Through network model output category vector, the class vector includes multiple vector parameters, and each vector parameter is for indicating default
The prediction probability of one of medication classification in multiple medication classifications;
Screening module, for filtering out at least one target medication classification from multiple medication classifications according to the class vector;
And
Output module, for exporting Prescription comment number according to the target medication classification and preconfigured medical knowledge map
According to.
9. a kind of computer equipment, the computer equipment memory, processor and it is stored on the memory and can be in institute
State the computer program run on processor, which is characterized in that such as right is realized when the computer program is executed by processor
It is required that described in any one of 1 to 7 the step of Prescription evaluation method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program, the computer program can be performed by least one processors, so that at least one described processor executes such as right
It is required that described in any one of 1 to 7 the step of Prescription evaluation method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910405122.1A CN110223751A (en) | 2019-05-16 | 2019-05-16 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910405122.1A CN110223751A (en) | 2019-05-16 | 2019-05-16 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110223751A true CN110223751A (en) | 2019-09-10 |
Family
ID=67821289
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910405122.1A Pending CN110223751A (en) | 2019-05-16 | 2019-05-16 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110223751A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院(南京医科大学第一附属医院) | Prescription recommendation method and system based on machine learning and knowledge graph |
CN111564186A (en) * | 2020-03-25 | 2020-08-21 | 湖南大学 | Method and system for predicting interaction of graph-volume drug pairs based on knowledge graph |
CN111767412A (en) * | 2020-09-02 | 2020-10-13 | 成都数联铭品科技有限公司 | Data mapping method and system for knowledge graph construction and electronic equipment |
WO2020220635A1 (en) * | 2019-09-18 | 2020-11-05 | 平安科技(深圳)有限公司 | Pharmaceutical drug classification method and apparatus, computer device and storage medium |
CN112036478A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Identification method and device for chronic disease reimbursement medicine and computer equipment |
CN112652373A (en) * | 2020-12-09 | 2021-04-13 | 华南理工大学 | Prescription recommendation method based on tongue image retrieval |
CN112700016A (en) * | 2020-12-28 | 2021-04-23 | 济南浪潮高新科技投资发展有限公司 | Predictive maintenance method and apparatus |
CN112837794A (en) * | 2021-01-12 | 2021-05-25 | 山东众阳健康科技集团有限公司 | High-value medical consumable intelligent evaluation method and system |
WO2021114736A1 (en) * | 2020-07-07 | 2021-06-17 | 平安科技(深圳)有限公司 | Medical consultation assistance method and apparatus, electronic device, and medium |
CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
CN114005507A (en) * | 2021-09-23 | 2022-02-01 | 厦门大学 | Clinical medication risk assessment method and system based on knowledge graph |
WO2022021990A1 (en) * | 2020-07-28 | 2022-02-03 | 北京京东拓先科技有限公司 | Information determination method and apparatus |
CN114191219A (en) * | 2022-01-17 | 2022-03-18 | 牡丹江医学院 | Intelligent dressing change system for nursing |
WO2022062353A1 (en) * | 2020-09-23 | 2022-03-31 | 康键信息技术(深圳)有限公司 | Medical data processing method and apparatus, and computer device and storage medium |
CN114913948A (en) * | 2022-03-31 | 2022-08-16 | 联想(北京)有限公司 | Information processing method and device, electronic equipment and readable storage medium |
CN116069956A (en) * | 2023-03-29 | 2023-05-05 | 之江实验室 | Drug knowledge graph entity alignment method and device based on mixed attention mechanism |
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 |
CN117438104A (en) * | 2023-12-21 | 2024-01-23 | 成都市第一人民医院 | Intelligent medicine early warning method, electronic equipment and computer storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341345A (en) * | 2017-06-22 | 2017-11-10 | 厦门大学 | A kind of clinical rational drug use methods of risk assessment based on electronic health record big data |
CN108363774A (en) * | 2018-02-09 | 2018-08-03 | 西北大学 | A kind of drug relationship sorting technique based on multilayer convolutional neural networks |
CN109271516A (en) * | 2018-09-26 | 2019-01-25 | 清华大学 | Entity type classification method and system in a kind of knowledge mapping |
CN109378045A (en) * | 2018-09-26 | 2019-02-22 | 北京理工大学 | Medication decision support method based on drug knowledge mapping reasoning |
CN109446338A (en) * | 2018-09-20 | 2019-03-08 | 大连交通大学 | Drug disease relationship classification method neural network based |
CN109471945A (en) * | 2018-11-12 | 2019-03-15 | 中山大学 | Medical file classification method, device and storage medium based on deep learning |
-
2019
- 2019-05-16 CN CN201910405122.1A patent/CN110223751A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341345A (en) * | 2017-06-22 | 2017-11-10 | 厦门大学 | A kind of clinical rational drug use methods of risk assessment based on electronic health record big data |
CN108363774A (en) * | 2018-02-09 | 2018-08-03 | 西北大学 | A kind of drug relationship sorting technique based on multilayer convolutional neural networks |
CN109446338A (en) * | 2018-09-20 | 2019-03-08 | 大连交通大学 | Drug disease relationship classification method neural network based |
CN109271516A (en) * | 2018-09-26 | 2019-01-25 | 清华大学 | Entity type classification method and system in a kind of knowledge mapping |
CN109378045A (en) * | 2018-09-26 | 2019-02-22 | 北京理工大学 | Medication decision support method based on drug knowledge mapping reasoning |
CN109471945A (en) * | 2018-11-12 | 2019-03-15 | 中山大学 | Medical file classification method, device and storage medium based on deep learning |
Non-Patent Citations (1)
Title |
---|
邵云婷等: "基于知识图谱的药品联用建模及风险评价", 《中国数字医学》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020220635A1 (en) * | 2019-09-18 | 2020-11-05 | 平安科技(深圳)有限公司 | Pharmaceutical drug classification method and apparatus, computer device and storage medium |
CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院(南京医科大学第一附属医院) | Prescription recommendation method and system based on machine learning and knowledge graph |
CN111191020B (en) * | 2019-12-27 | 2023-09-22 | 江苏省人民医院(南京医科大学第一附属医院) | Prescription recommendation method and system based on machine learning and knowledge graph |
CN111564186A (en) * | 2020-03-25 | 2020-08-21 | 湖南大学 | Method and system for predicting interaction of graph-volume drug pairs based on knowledge graph |
WO2021114736A1 (en) * | 2020-07-07 | 2021-06-17 | 平安科技(深圳)有限公司 | Medical consultation assistance method and apparatus, electronic device, and medium |
WO2022021990A1 (en) * | 2020-07-28 | 2022-02-03 | 北京京东拓先科技有限公司 | Information determination method and apparatus |
CN112036478A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Identification method and device for chronic disease reimbursement medicine and computer equipment |
CN111767412A (en) * | 2020-09-02 | 2020-10-13 | 成都数联铭品科技有限公司 | Data mapping method and system for knowledge graph construction and electronic equipment |
CN111767412B (en) * | 2020-09-02 | 2020-12-08 | 成都数联铭品科技有限公司 | Data mapping method and system for knowledge graph construction and electronic equipment |
WO2022062353A1 (en) * | 2020-09-23 | 2022-03-31 | 康键信息技术(深圳)有限公司 | Medical data processing method and apparatus, and computer device and storage medium |
CN112652373A (en) * | 2020-12-09 | 2021-04-13 | 华南理工大学 | Prescription recommendation method based on tongue image retrieval |
CN112652373B (en) * | 2020-12-09 | 2022-10-25 | 华南理工大学 | Prescription recommendation method based on tongue image retrieval |
CN112700016A (en) * | 2020-12-28 | 2021-04-23 | 济南浪潮高新科技投资发展有限公司 | Predictive maintenance method and apparatus |
CN112837794A (en) * | 2021-01-12 | 2021-05-25 | 山东众阳健康科技集团有限公司 | High-value medical consumable intelligent evaluation method and system |
CN112837794B (en) * | 2021-01-12 | 2023-11-14 | 众阳健康科技集团有限公司 | Intelligent evaluation method and system for high-value medical consumables |
CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
CN114005507A (en) * | 2021-09-23 | 2022-02-01 | 厦门大学 | Clinical medication risk assessment method and system based on knowledge graph |
CN114191219A (en) * | 2022-01-17 | 2022-03-18 | 牡丹江医学院 | Intelligent dressing change system for nursing |
CN114191219B (en) * | 2022-01-17 | 2023-06-06 | 牡丹江医学院 | Intelligent dressing change system for nursing |
CN114913948A (en) * | 2022-03-31 | 2022-08-16 | 联想(北京)有限公司 | Information processing method and device, electronic equipment and readable storage medium |
CN116069956A (en) * | 2023-03-29 | 2023-05-05 | 之江实验室 | Drug knowledge graph entity alignment method and device based on mixed attention mechanism |
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 |
CN117438104A (en) * | 2023-12-21 | 2024-01-23 | 成都市第一人民医院 | Intelligent medicine early warning method, electronic equipment and computer storage medium |
CN117438104B (en) * | 2023-12-21 | 2024-03-22 | 成都市第一人民医院 | Intelligent medicine early warning method, electronic equipment and computer storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110223751A (en) | Prescription evaluation method, system and computer equipment based on medical knowledge map | |
US10818397B2 (en) | Clinical content analytics engine | |
CN107808124B (en) | Electronic device, the recognition methods of medical text entities name and storage medium | |
Drury et al. | A survey of semantic web technology for agriculture | |
US20200327404A1 (en) | Systems and methods for applying deep learning to data | |
US10510022B1 (en) | Machine learning model feature contribution analytic system | |
ES2753524T3 (en) | System for calculating drug similarities and using the similarities to extrapolate side effects | |
US8996581B2 (en) | Obtaining hierarchical information of planar data | |
WO2020139861A1 (en) | Constructing a knowledge graph employing multiple subgraphs and a linking layer including multiple linking nodes | |
WO2020172446A9 (en) | Automated generation of structured patient data record | |
KR102368520B1 (en) | HUMAN-IN-THE-LOOP interactive model training | |
JP2014225176A (en) | Analysis system and health business support method | |
CN111066033A (en) | Machine learning method for generating labels of fuzzy results | |
CN113808693A (en) | Medicine recommendation method based on graph neural network and attention mechanism | |
CN113707303A (en) | Method, device, equipment and medium for solving medical problems based on knowledge graph | |
CN108711443A (en) | The text data analysis method and device of electronic health record | |
US11093864B1 (en) | Distributable feature analysis and tree model training system | |
CN110362829A (en) | Method for evaluating quality, device and the equipment of structured patient record data | |
CN113436754A (en) | Medical software and method for intelligent terminal inquiry | |
CN113657550A (en) | Patient marking method, device, equipment and storage medium based on hierarchical calculation | |
US11372892B2 (en) | Relational database retrieval procedures for cohort-wise data comparisons | |
CN109767819B (en) | Medical record grouping method and device, storage medium and electronic equipment | |
Khatoon et al. | Importance of semantic interoperability in smart agriculture systems | |
CN115775635A (en) | Medicine risk identification method and device based on deep learning model and terminal equipment | |
CN115762769A (en) | Intelligent risk early warning system after ERCP (effective Range planning) operation |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
RJ01 | Rejection of invention patent application after publication |