CN114283949A - ADR (adaptive Doppler ratio) aided decision making system based on deep learning - Google Patents
ADR (adaptive Doppler ratio) aided decision making system based on deep learning Download PDFInfo
- Publication number
- CN114283949A CN114283949A CN202111316168.XA CN202111316168A CN114283949A CN 114283949 A CN114283949 A CN 114283949A CN 202111316168 A CN202111316168 A CN 202111316168A CN 114283949 A CN114283949 A CN 114283949A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- drug
- deep learning
- medicine
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 64
- 230000003044 adaptive effect Effects 0.000 title claims description 5
- 239000003814 drug Substances 0.000 claims abstract description 136
- 229940079593 drug Drugs 0.000 claims abstract description 89
- 238000011156 evaluation Methods 0.000 claims abstract description 53
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims abstract description 46
- 206010061623 Adverse drug reaction Diseases 0.000 claims abstract description 27
- 230000009467 reduction Effects 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 20
- 206010067484 Adverse reaction Diseases 0.000 claims description 14
- 230000006838 adverse reaction Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 201000010099 disease Diseases 0.000 claims description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 8
- 230000006378 damage Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 claims description 6
- 210000004204 blood vessel Anatomy 0.000 claims description 5
- 230000005779 cell damage Effects 0.000 claims description 5
- 208000037887 cell injury Diseases 0.000 claims description 5
- 239000012530 fluid Substances 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000003238 somatosensory effect Effects 0.000 claims description 3
- 208000027418 Wounds and injury Diseases 0.000 claims description 2
- 208000014674 injury Diseases 0.000 claims description 2
- 238000011160 research Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000001647 drug administration Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 208000003322 Coinfection Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000012382 advanced drug delivery Methods 0.000 description 1
- 208000003455 anaphylaxis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005229 chemical vapour deposition Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an ADR (advanced drug compliance) assistant decision system based on deep learning, which comprises a drug database module, a drug analysis module and a decision making module, wherein the drug database module is used for acquiring and storing drug information and relevant adverse drug reaction information; the CHPS drug evaluation module is used for exporting the improved adverse drug reaction data on the basis of the CHPS system; the deep learning module is used for learning the adverse drug reaction data derived from the CHPS drug evaluation module; the auxiliary evaluation and risk early warning module is used for comparing certain medicine information after input by using the deep learning module; the medication decision module is used for carrying out medication decision judgment after the auxiliary evaluation and risk early warning module and giving information on whether to take the medicine or not; the feedback module is used for feeding back relevant patient sign data after medication, the dosage of medication and frequency data to the deep learning modularity; the system improves and perfects adverse drug reaction data, and can make decision analysis and risk management on drug administration based on deep learning.
Description
Technical Field
The invention belongs to the technical field of medicine monitoring, and particularly relates to an ADR (adaptive data reduction) auxiliary decision-making system based on deep learning.
Background
Adverse Drug Reactions (ADRs) refer to Adverse, but not desirable, reactions that are causally related to the use of a Drug during normal use of a Drug at a specified dosage. Adverse drug reactions generally can be divided into four categories, namely side effects, toxic reactions, anaphylactic reactions and secondary infections, in real life, the incidence rate of adverse drug reactions is extremely high, especially when the drugs are used for a long time or the dosage is large, the adverse drug reactions can harm human monitoring, and even endanger human life in severe cases. Therefore, the detection of the adverse reaction rate of the medicine has great significance for ensuring the safety of the medicine and guaranteeing the public health.
In order to monitor adverse reaction of collected drugs, a CHPS drug alert system (CHPS) of the Chinese hospital is correspondingly taken out, and the main function of the CHPS drug evaluation system is to rapidly acquire the grouped cases required by the project by applying an intelligent retrieval tool, so as to realize development of the drug evaluation project and acquisition and management of evaluation report data thereof. At present, the system mainly comprises three functional modules of standard data management, drug evaluation management, data processing and analysis. The drug evaluation management module is the core, and the other two modules are mainly used for assisting in completing the function of the drug evaluation process.
Monitoring, reporting and managing adverse drug reactions are one of the important jobs in hospitals. Most studies of medical data in ADR monitoring are methodological development, and more evidence is needed to prove the application efficacy of the ADR monitoring. In ADR reporting, the data reported by ADR is insufficient and the quality is not high. In addition, there is difficulty in auditing and tracing the reported data; meanwhile, the existing CHPS system cannot perform decision analysis management at present, and people need to solve troubles for ADR related work from the technical aspect.
Disclosure of Invention
The invention aims to provide an ADR (adaptive data reduction) assistant decision-making system based on deep learning, which can improve and perfect adverse drug reaction data and can perform decision analysis and risk management on drug administration based on deep learning.
In order to achieve the purpose, the invention provides the following technical scheme: an ADR (advanced drug delivery) assistant decision-making system based on deep learning comprises a drug database module, a CHPS (chemical vapor deposition) drug evaluation module, a deep learning module, an assistant evaluation and risk early warning module, a medication decision-making module and a feedback module;
the drug database module is used for acquiring and storing drug information and relevant adverse drug reaction information;
the CHPS drug evaluation module is used for connecting the block chain data of the adverse drug reactions and the adverse drug reaction natural language recognition engine on the basis of the CHPS system and exporting the improved adverse drug reaction data;
the deep learning module is used for learning adverse drug reaction data derived from the CHPS drug evaluation module and uploading the data to the auxiliary evaluation and risk early warning module;
the auxiliary evaluation and risk early warning module is used for comparing certain input medicine information by using the deep learning module, evaluating the target medicine and making risk early warning;
the medication decision module is used for carrying out medication decision judgment and giving information on whether to take the medicine or not after the auxiliary evaluation and risk early warning module carries out evaluation and risk early warning;
and the feedback module is used for feeding back the relevant physical sign data of the patient after medication, the dosage of the medication and the frequency data to the deep learning module.
Preferably, the drug database module has the following data sources: the system comprises a medicine information database, a drug adverse reaction database, a patient chief complaint database and a medical diagnosis database, wherein the patient chief complaint database comprises the somatosensory adverse reaction of a patient after medication.
Preferably, the blockchain data of the ADRs are obtained from ADRs provided by various hospitals, clinics and medical research sites in the regional chain.
Preferably, the method for deep learning includes the following steps:
a. exporting data from the interior of the CHPS drug evaluation module, and cleaning the exported data;
b. carrying out scaling on the obtained large amount of cleaned data, and outputting the scaled data;
c. b, constructing a training data set matrix by using the scaled data, classifying the data in the training data set matrix, classifying according to the data obtained in the step a, specifically comprising the name of the medicine, the manufacturer of the medicine and the known adverse reaction of the medicine, and screening out effective factors in the data;
d. and d, performing data dimension reduction on the effective factors in the step c, and outputting the data dimension reduction through a deep learning trained model.
Preferably, the data dimensionality reduction comprises: and performing data input on the effective factors, performing matrix dimensionality reduction on the data after the data input, wherein the matrix adopts a training data set matrix, performing data activation after the matrix dimensionality reduction, performing deviation value calculation after the data activation, performing deviation value calculation after the deviation value gradient reduction iteration, and outputting after the iteration is completed until the deviation value calculation.
Preferably, the patient data in the auxiliary evaluation and risk early warning module comprises related ill data such as age and sex of the patient, the patient data and the medication information are subjected to data scaling by combining the medication information, and the scaled data are input into the deep learning module to be subjected to internal data comparison.
Preferably, the feedback module receives the information of the patient taking the medicine after the prediction and evaluation, monitors the reaction of the patient after the medicine taking, including physical sign monitoring data and patient chief complaint adverse reaction data, performs data scaling on the data, inputs the scaled data into the deep learning module, performs data learning through the deep learning step in the deep learning module again, and increases the accuracy of auxiliary evaluation and prediction.
Preferably, the natural language identification engine for ADRs comprises a knowledge base and an electronic medical record, and the natural language identification engine for ADRs guides the knowledge base and the electronic medical record into the CHPS drug evaluation module.
Preferably, the knowledge base comprises the content of medical disease diagnosis and treatment guidelines, and specifically comprises information of specific tissue cell damage, blood vessel damage, tissue fluid accumulation and the like of the medical disease.
Compared with the prior art, the invention has the beneficial effects that:
1. the method has the advantages that a training data set is constructed by combining data in the conventional CHPS system, case factors are screened, a trained AI model is output through a deep learning algorithm, risks can be estimated when medication is performed, measures are taken, risk data and decision support are provided for medical workers to use certain drugs, ADR data value is fully improved, and the safety of medication of the public is improved.
2. An adverse drug reaction natural language recognition engine is deployed in the existing CHPS system, the latest medical disease guide is recorded and is commonly recognized by experts, the inspection values of related tissues and organs can be smoothly captured, a record is formed, the defect that only key words can be automatically captured in the existing CHPS system is overcome, and therefore the condition that doctors fail to report or report can be avoided, and adverse drug reaction data can be uploaded.
3. By utilizing the feedback module, after the medicine is taken, medicine taking data and relevant medicine taking reaction data of a patient are collected, and the data are input into the deep learning module again, so that adverse medicine reaction data are continuously improved, and the accuracy of ADR data is further improved.
Drawings
FIG. 1 is a schematic block diagram of system connection of an ADR decision-making aid system based on deep learning according to the present invention;
FIG. 2 is a schematic block diagram of a ADR natural language recognition engine of an ADR decision-making assisting system based on deep learning according to the present invention;
FIG. 3 is a schematic diagram of a deep learning module of an ADR decision-making aid system based on deep learning according to the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution: an ADR aided decision making system based on deep learning.
As shown in fig. 1, the system comprises a drug database module, a CHPS drug evaluation module, a deep learning module, an auxiliary evaluation and risk early warning module, a medication decision module, and a feedback module;
the drug database module is used for acquiring and storing drug information and relevant adverse drug reaction information;
as each drug is produced, relevant experimental data is obtained, and then corresponding adverse drug reaction information is obtained, and the name and internal composition of each drug applied to the current medical means and the corresponding adverse drug reaction information are counted.
The CHPS drug evaluation module is used for connecting the block chain data of the adverse drug reactions and the adverse drug reaction natural language recognition engine on the basis of the CHPS system and exporting the improved adverse drug reaction data;
adding blockchain data and adverse drug reaction information of an adverse drug reaction natural language recognition engine on an original CHPS system, wherein the blockchain data comprise manufacturer, hospital, doctor, pharmacist and adverse drug reaction reporter participating blockchain information record, and simultaneously comprise information of certain medicine production, purchase, prescription, dispensing, patient taking and the like, the record of a patient end on the blockchain is fed back by using a mobile end, the information of the blockchain is uploaded to the CHPS system, and the CHPS system is enriched in data; the untoward-drug reaction natural language recognition engine comprises a knowledge base and an electronic medical record, the knowledge base and the electronic medical record are led into the CHPS drug evaluation module by the untoward-drug reaction natural language recognition engine, and the knowledge base specifically comprises the content of a medical treatment guideline of the medical diseases, and specifically comprises information of specific tissue cell injury, blood vessel injury, tissue fluid siltation and the like of the medical diseases.
As shown in fig. 3, the information data of the specific tissue cell damage, the blood vessel damage, the tissue fluid stasis and the like are quantitatively and quantitatively imported into the natural language identification engine for ADF, the information of the specific tissue cell damage, the blood vessel damage, the tissue fluid stasis and the like can be monitored in real time, the real-time data can be updated, the natural language identification engine for ADF can capture dynamic changes of the indexes of the tissues under the state that the data is updated in real time, and then the data is early warned to medical personnel in advance, and simultaneously the data is uploaded to the CHPS system, is digitized in the CHPS system, and is reported to the CHPS system after being audited.
The deep learning module is used for learning adverse drug reaction data derived from the CHPS drug evaluation module and uploading the data to the auxiliary evaluation and risk early warning module;
the auxiliary evaluation and risk early warning module is used for comparing certain input medicine information by using the deep learning module, evaluating the target medicine and making risk early warning;
the medication decision module is used for carrying out medication decision judgment and giving information on whether to take the medicine or not after the auxiliary evaluation and risk early warning module carries out evaluation and risk early warning;
and the feedback module is used for feeding back the relevant physical sign data of the patient after medication, the dosage of the medication and the frequency data to the deep learning module.
Specifically, the drug database module has the following data sources: the system comprises a medicine information database, a drug adverse reaction database, a patient chief complaint database and a medical diagnosis database, wherein the patient chief complaint database comprises the somatosensory adverse reaction of a patient after medication.
Specifically, as shown in fig. 2, the deep learning method includes the following steps:
a. exporting data from the interior of the CHPS drug evaluation module, and cleaning the exported data;
b. carrying out scaling on the obtained large amount of cleaned data, and outputting the scaled data;
c. b, constructing a training data set matrix by using the scaled data, classifying the data in the training data set matrix, classifying according to the data obtained in the step a, specifically comprising the name of the medicine, the manufacturer of the medicine and the known adverse reaction of the medicine, and screening out effective factors in the data;
d. and d, performing data dimension reduction on the effective factors in the step c, and outputting the data dimension reduction through a deep learning trained model.
Wherein, the data dimensionality reduction comprises the following steps: and performing data input on the effective factors, performing matrix dimensionality reduction on the data after the data input, wherein the matrix adopts a training data set matrix, performing data activation after the matrix dimensionality reduction, performing deviation value calculation after the data activation, performing deviation value calculation after the deviation value gradient reduction iteration, and outputting after the iteration is completed until the deviation value calculation.
It can be understood that data from the interior of the CHPS drug evaluation module after data cleaning is input, after the data is input, because the CHPS drug evaluation module comprises various drugs, when deep learning is performed, the existing data of whether corresponding drugs have adverse drug reactions or not can be learned and identified firstly, if the adverse drug reactions exist, data scaling of related data is performed, a training data set matrix is constructed according to the existing CHPS system, and if no related adverse drug reactions exist, the learning of the related data is abandoned;
and (3) performing data screening on the data after passing through the training data set matrix, combining the effective factors of the corresponding drugs after the data screening with the patient information in the CHPS drug evaluation module to obtain specific data of adverse drug reactions, performing data reduction iteration on the data, and outputting a trained model after the data reduction iteration is completed by adopting the data dimension reduction series steps, namely completing the deep learning.
Specifically, the patient data inside the auxiliary evaluation and risk early warning module comprises related sick data such as the age and sex of a patient, the patient data and the drug information are subjected to data scaling by combining with the drug information, and the data after scaling is input into the deep learning module to be subjected to internal data comparison.
By combining the deep learning module, when the medicine is taken, medical staff carries out data standardization on the two data according to the relevant diagnosis and treatment data of a patient and the name of the medicine required to be used, the data standardization is input into the model after the deep learning is finished for evaluation and relevant prediction and risk are given out after the standardization is finished, the prediction result is carried out by combining and comparing the existing data information, if the adverse drug reaction is not available, the medicine is taken normally, and if the adverse drug reaction exists, the side effect prompt appears.
Specifically, the feedback module receives the information of the patient taking the medicine after prediction and evaluation, monitors the reaction of the patient after the medicine taking, comprises physical sign monitoring data and patient chief complaint adverse reaction data, carries out data scaling on the data, inputs the data after scaling into the deep learning module, carries out data learning through the deep learning step in the deep learning module again, and increases the accuracy of auxiliary evaluation and prediction.
After the auxiliary evaluation and risk early warning module prompts, the medicine taking is completed, the periodic physical sign monitoring is subsequently carried out on the patient, meanwhile, the data scaling is carried out on the reaction in the medicine taking process of the patient complaint, the scaling is carried out in the scalar mode of the data in the conventional CHPS system, the data is input into the deep learning module as the data again, the learning is continued, and the adverse medicine reaction system is gradually perfected.
By adopting the embodiment, after the deployment and the establishment of the whole system are completed, data acquisition and data storage can be carried out, the data acquisition and the data storage are connected to the block chain, the simulation operation is carried out, meanwhile, the ADR natural language recognition engine is deployed, the latest medical disease damage guideline and expert consensus are input, the tissue organ function test value in the rule can be smoothly captured, and the record is formed. Supplementing the ADR data to a CHPS system, establishing a deep learning module for deep learning of the data, and finally fully mining information provided by the ADR data through the system, such as the probability of predicting adverse drug reactions before a patient takes a medicine, and providing medical aid decision for medical staff. In addition, the medicine early warning is carried out aiming at specific patients of certain medicines, the incidence rate of ADR of the patients is reduced, and the patients are prevented from suffering from the ADR in the bud. Data is used to drive the manufacturer to refine the specification information, making the policy maker more directional.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (9)
1. An ADR (adaptive dose reduction) aided decision system based on deep learning is characterized in that: the system comprises a medicine database module, a CHPS medicine evaluation module, a deep learning module, an auxiliary evaluation and risk early warning module, a medication decision module and a feedback module;
the drug database module is used for acquiring and storing drug information and relevant adverse drug reaction information;
the CHPS drug evaluation module is used for connecting the block chain data of the adverse drug reactions and the adverse drug reaction natural language recognition engine on the basis of the CHPS system and exporting the improved adverse drug reaction data;
the deep learning module is used for learning adverse drug reaction data derived from the CHPS drug evaluation module and uploading the data to the auxiliary evaluation and risk early warning module;
the auxiliary evaluation and risk early warning module is used for comparing certain input medicine information by using the deep learning module, evaluating the target medicine and making risk early warning;
the medication decision module is used for carrying out medication decision judgment and giving information on whether to take the medicine or not after the auxiliary evaluation and risk early warning module carries out evaluation and risk early warning;
and the feedback module is used for feeding back the relevant physical sign data of the patient after medication, the dosage of the medication and the frequency data to the deep learning module.
2. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the drug database module has the following data sources: the system comprises a medicine information database, a drug adverse reaction database, a patient chief complaint database and a medical diagnosis database, wherein the patient chief complaint database comprises the somatosensory adverse reaction of a patient after medication.
3. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the block chain data of the adverse drug reactions come from adverse drug reaction data provided by various hospitals, clinics and medical research sites in the regional chain.
4. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the deep learning method comprises the following steps:
a. exporting data from the interior of the CHPS drug evaluation module, and cleaning the exported data;
b. carrying out scaling on the obtained large amount of cleaned data, and outputting the scaled data;
c. b, constructing a training data set matrix by using the scaled data, classifying the data in the training data set matrix, classifying according to the data obtained in the step a, specifically comprising the name of the medicine, the manufacturer of the medicine and the known adverse reaction of the medicine, and screening out effective factors in the data;
d. and d, performing data dimension reduction on the effective factors in the step c, and outputting the data dimension reduction through a deep learning trained model.
5. An ADR aided decision making system based on deep learning according to claim 4, characterized in that: the data dimensionality reduction comprises the following steps: and performing data input on the effective factors, performing matrix dimensionality reduction on the data after the data input, wherein the matrix adopts a training data set matrix, performing data activation after the matrix dimensionality reduction, performing deviation value calculation after the data activation, performing deviation value calculation after the deviation value gradient reduction iteration, and outputting after the iteration is completed until the deviation value calculation.
6. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the patient data in the auxiliary evaluation and risk early warning module comprises related sick data such as age and sex of a patient, the patient data and the drug information are subjected to data scaling by combining with the drug information, and the data after scaling is input into the deep learning module to be subjected to internal data comparison.
7. An ADR aided decision making system based on deep learning according to claim 6, characterized in that: the feedback module receives the information of the patient taking the medicine after prediction and evaluation, monitors the reaction of the patient after the medicine taking, comprises sign monitoring data and patient chief complaint adverse reaction data, carries out data scaling on the data, inputs the data after scaling to the deep learning module, carries out data learning through the deep learning step in the deep learning module again, and increases the accuracy of auxiliary evaluation and prediction.
8. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the untoward-drug natural language recognition engine comprises a knowledge base and an electronic medical record, and the knowledge base and the electronic medical record are led into the CHPS drug evaluation module by the untoward-drug natural language recognition engine.
9. An ADR aided decision making system based on deep learning according to claim 1, characterized in that: the knowledge base comprises the content of medical disease diagnosis and treatment guidelines, and specifically comprises information of specific tissue cell injury, blood vessel injury, tissue fluid stasis and the like of medical diseases.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111316168.XA CN114283949A (en) | 2021-11-08 | 2021-11-08 | ADR (adaptive Doppler ratio) aided decision making system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111316168.XA CN114283949A (en) | 2021-11-08 | 2021-11-08 | ADR (adaptive Doppler ratio) aided decision making system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114283949A true CN114283949A (en) | 2022-04-05 |
Family
ID=80868803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111316168.XA Pending CN114283949A (en) | 2021-11-08 | 2021-11-08 | ADR (adaptive Doppler ratio) aided decision making system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114283949A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565326A (en) * | 2022-04-29 | 2022-05-31 | 深圳市誉兴通科技股份有限公司 | Medicine management method and system based on Internet of things |
| CN115312182A (en) * | 2022-07-26 | 2022-11-08 | 哈尔滨工业大学 | Model for predicting risk of adverse reaction converted into serious adverse reaction after vaccination |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013181820A1 (en) * | 2012-06-07 | 2013-12-12 | 北京太元通软件科技有限公司 | Clinical medication decision support system |
| CN103488890A (en) * | 2013-09-18 | 2014-01-01 | 万达信息股份有限公司 | Patient adverse drug reaction warning method and system based on Naive Bayes |
| 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 |
| CN109859815A (en) * | 2019-01-24 | 2019-06-07 | 西安交通大学 | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system |
| US20190228865A1 (en) * | 2018-01-24 | 2019-07-25 | International Business Machines Corporation | Evaluating Drug-Adverse Event Causality Based on an Integration of Heterogeneous Drug Safety Causality Models |
| US20190279774A1 (en) * | 2018-03-06 | 2019-09-12 | International Business Machines Corporation | Finding Precise Causal Multi-Drug-Drug Interactions for Adverse Drug Reaction Analysis |
| CN111696678A (en) * | 2020-06-15 | 2020-09-22 | 中南大学 | Deep learning-based medication decision method and system |
| CN112669991A (en) * | 2020-12-28 | 2021-04-16 | 山东健康医疗大数据有限公司 | Method for detecting adverse drug reaction signals |
| CN112863695A (en) * | 2021-02-22 | 2021-05-28 | 西京学院 | Bidirectional long-short term memory prediction model based on quantum attention mechanism and extraction method |
-
2021
- 2021-11-08 CN CN202111316168.XA patent/CN114283949A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013181820A1 (en) * | 2012-06-07 | 2013-12-12 | 北京太元通软件科技有限公司 | Clinical medication decision support system |
| CN103488890A (en) * | 2013-09-18 | 2014-01-01 | 万达信息股份有限公司 | Patient adverse drug reaction warning method and system based on Naive Bayes |
| 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 |
| US20190228865A1 (en) * | 2018-01-24 | 2019-07-25 | International Business Machines Corporation | Evaluating Drug-Adverse Event Causality Based on an Integration of Heterogeneous Drug Safety Causality Models |
| US20190279774A1 (en) * | 2018-03-06 | 2019-09-12 | International Business Machines Corporation | Finding Precise Causal Multi-Drug-Drug Interactions for Adverse Drug Reaction Analysis |
| CN109859815A (en) * | 2019-01-24 | 2019-06-07 | 西安交通大学 | A kind of adjuvant drug decision-making technique and intelligent adjuvant drug system |
| CN111696678A (en) * | 2020-06-15 | 2020-09-22 | 中南大学 | Deep learning-based medication decision method and system |
| CN112669991A (en) * | 2020-12-28 | 2021-04-16 | 山东健康医疗大数据有限公司 | Method for detecting adverse drug reaction signals |
| CN112863695A (en) * | 2021-02-22 | 2021-05-28 | 西京学院 | Bidirectional long-short term memory prediction model based on quantum attention mechanism and extraction method |
Non-Patent Citations (1)
| Title |
|---|
| 杨泽民 等: "《药品不良反应学》", 31 August 2011, 中国中医药出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565326A (en) * | 2022-04-29 | 2022-05-31 | 深圳市誉兴通科技股份有限公司 | Medicine management method and system based on Internet of things |
| CN114565326B (en) * | 2022-04-29 | 2022-08-30 | 深圳市誉兴通科技股份有限公司 | Medicine management method and system based on Internet of things |
| CN115312182A (en) * | 2022-07-26 | 2022-11-08 | 哈尔滨工业大学 | Model for predicting risk of adverse reaction converted into serious adverse reaction after vaccination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3223180A1 (en) | A system and a method for assessing patient risk using open data and clinician input | |
| US20140155763A1 (en) | Medical analysis and diagnostic system | |
| CN111899837A (en) | Operation report coordination method and system based on digital operating room | |
| Improta et al. | Discrete event simulation to improve clinical consultations in a rehabilitation cardiology unit | |
| CN108538352B (en) | Medication information processing method | |
| CN114283949A (en) | ADR (adaptive Doppler ratio) aided decision making system based on deep learning | |
| US20140379620A1 (en) | Systems and methods for automatic segment selection for multi-dimensional biomedical signals | |
| CN111128324A (en) | Preoperative visit and anesthesia evaluation information system software | |
| CN115714022A (en) | Neonatal jaundice health management system based on artificial intelligence | |
| CN111028936A (en) | Method, system and equipment for medical examination and reasonable compliance analysis of inspection | |
| CN114025253A (en) | Drug efficacy evaluation system based on real world research | |
| CN109859837A (en) | A kind of pyemia method for early warning, system and storage medium based on medical data | |
| Erdoğan et al. | Objective pain assessment using vital signs | |
| Ashu et al. | A novel approach of telemedicine for managing fetal condition based on machine learning technology from IoT-based wearable medical device | |
| WO2023129843A1 (en) | Wound management and treatment using computer vision and machine learning | |
| Fudholi et al. | An ontology model for clinical pathway audit | |
| CN108735286B (en) | Comprehensive health care treatment management system for whole life of individual | |
| Khatter et al. | Machine Learning-Based Automated Medical Diagnosis for Healthcare | |
| CN117219243A (en) | Cardiovascular disease assessment and management system | |
| Ratnakar et al. | Smart Innovative Medical Devices Based on Artificial Intelligence | |
| Sayganov et al. | Development of a portable telemedicine complex as the health service digital transformation and optimization technology | |
| CN110910980A (en) | Sepsis early warning device, equipment and storage medium | |
| CN118155869B (en) | Drug taking compliance evaluation method and system for acute myocardial infarction patient | |
| Ang et al. | Healthcare Data Handling with Machine Learning Systems: A Framework | |
| Toban | PAP Therapy and Sleep Stage Classification with Statistics, Signal Processing, and Deep Learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220405 |