CN113628716A - Prescription recommendation system - Google Patents
Prescription recommendation system Download PDFInfo
- Publication number
- CN113628716A CN113628716A CN202110897823.9A CN202110897823A CN113628716A CN 113628716 A CN113628716 A CN 113628716A CN 202110897823 A CN202110897823 A CN 202110897823A CN 113628716 A CN113628716 A CN 113628716A
- Authority
- CN
- China
- Prior art keywords
- prescription
- module
- medicine
- medicines
- main
- 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
- 239000003814 drug Substances 0.000 claims abstract description 84
- 229940079593 drug Drugs 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 16
- 208000024891 symptom Diseases 0.000 claims description 4
- 238000000034 method Methods 0.000 description 5
- 229960004099 azithromycin Drugs 0.000 description 3
- MQTOSJVFKKJCRP-BICOPXKESA-N azithromycin Chemical compound O([C@@H]1[C@@H](C)C(=O)O[C@@H]([C@@]([C@H](O)[C@@H](C)N(C)C[C@H](C)C[C@@](C)(O)[C@H](O[C@H]2[C@@H]([C@H](C[C@@H](C)O2)N(C)C)O)[C@H]1C)(C)O)CC)[C@H]1C[C@@](C)(OC)[C@@H](O)[C@H](C)O1 MQTOSJVFKKJCRP-BICOPXKESA-N 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 206010057190 Respiratory tract infections Diseases 0.000 description 1
- 208000034940 Undiagnosed disease Diseases 0.000 description 1
- 206010046306 Upper respiratory tract infection Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 229960002626 clarithromycin Drugs 0.000 description 1
- AGOYDEPGAOXOCK-KCBOHYOISA-N clarithromycin Chemical compound O([C@@H]1[C@@H](C)C(=O)O[C@@H]([C@@]([C@H](O)[C@@H](C)C(=O)[C@H](C)C[C@](C)([C@H](O[C@H]2[C@@H]([C@H](C[C@@H](C)O2)N(C)C)O)[C@H]1C)OC)(C)O)CC)[C@H]1C[C@@](C)(OC)[C@@H](O)[C@H](C)O1 AGOYDEPGAOXOCK-KCBOHYOISA-N 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002483 medication Methods 0.000 description 1
- 208000020029 respiratory tract infectious disease Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H20/13—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 delivered from dispensers
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a prescription recommendation system which comprises a characteristic extraction module, a prescription prediction module, a medicine expansion module, a medicine taboo checking module, a dose friendly module and a compatibility taboo module, wherein the prescription prediction module comprises a plurality of special prescription models which are respectively constructed according to special categories. The invention realizes the simultaneous training and prediction of the types and the dosages of the medicines in the same task, thereby providing more accurate and personalized recommended prescriptions for patients.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a prescription recommendation system.
Background
In clinical work, the prescription recommendation system can improve the work efficiency of a third-level hospital, can achieve the aim of 'knowledge sinking of a higher-level hospital' for a primary hospital, achieves the effect of knowledge inheritance, and has important value.
Existing prescription recommendation systems mainly use collaborative filtering techniques or model classifier modes. The method adopts a collaborative filtering technology, wherein the statistical distribution of the medication information of the same diagnosed patient is obtained according to the statistics of the medication information of the same diagnosed patient, and then the medicine which is similar to the target patient and has the highest use rate is recommended, and the method lacks enough generalization capability; the model classifier mode only can train the medicine type, and the numerical variable of the dosage cannot be effective.
Disclosure of Invention
To solve the above problems, the present invention provides a prescription recommendation system.
The invention adopts the following technical scheme:
a prescription recommendation system comprises a feature extraction module, a prescription prediction module, a medicine expansion module, a medicine contraindication checking module, a dose friendly module and a compatibility contraindication module, wherein the prescription prediction module comprises a plurality of special prescription models which are respectively constructed according to special categories;
the work flow of the system is as follows:
s1, inputting medical record information and the special category, and extracting the patient characteristics in the medical record by a characteristic extraction module;
s2, inputting the patient characteristics into a corresponding special prescription model by a prescription prediction module according to the special category of the medical record information to predict the prescription, and outputting a recommended medicine and a corresponding dosage and usage;
s3, the medicine expansion module searches for similar medicines which have the same type and the same main components as the recommended medicines from the medicine library;
s4, the medicine contraindication checking module checks whether the use contraindication exists according to the medical record information;
s5, the dose friendly module converts the main component dose of the medicine into a user-friendly administration mode according to the specific specifications of the recommended medicine and the similar medicine;
s6, the incompatibility module further checks whether the prescription has incompatibility among medicines and outputs a final recommended prescription.
Further, the characteristics in the medical record information comprise symptom signs, examination results, medical history, patient age and patient sex.
Further, the specialist prescription model is used for classifying and scoring the medicines, and divides the medicines into a plurality of main classes according to the functions of the medicines, wherein each main class comprises a plurality of sub-classes of medicines which have the same functions and can be replaced mutually, and each sub-class of medicines comprises a plurality of commonly used doses.
Further, the special prescription model comprises a representation layer, an embedding layer, a multi-residual layer, an application layer and a multitask loss function, wherein the representation layer is used for collecting medicine function characteristics, and the application layer comprises a main classification scoring layer, a sub-classification scoring layer and a dose grade scoring layer.
Further, the primary classification scoring layer is used for weighting and scoring the primary classification; the sub-classification scoring layer is used for carrying out weight scoring on the sub-class medicines; the dose grade scoring layer is used for weighting and scoring the common dose of the subclass medicines.
Further, the multitask penalty function L is specifically:
wherein p ismainA probability estimate representing a principal class;
probability estimation of the corresponding subcategories of the ith main classification is represented;
a probability estimate representing the dose corresponding to the jth sub-class of the ith main class; gtmainA fact label representing a master classification;
representing the ith master classificationA fact label for the corresponding sub-category;
a fact label of a dose corresponding to a jth sub-class of the ith main class;
indicating whether the dose classification is legal.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
1. the prescription prediction module of the prescription recommendation system adopts a special prescription model which is respectively constructed and trained according to special categories, so that the number of medicines to be distinguished by a single model is greatly reduced, the model is a deep learning model which simultaneously represents multiple tasks, the fusion of multi-mode characteristics is realized by using a deep cross network, specifically, a representation layer is the characteristics of a patient, an application layer divides corresponding medicines into a plurality of classes according to functions aiming at different special categories and medicine functions, no overlapping exists between the classes, the dosage and the usage of each medicine are also independently divided into a branch, namely, the same representation layer information is adopted to train the selection of the classes of the application layer, the selection of the medicines in the classes and the selection of the medicine dosage usage, so that the types and the dosages of the medicines are simultaneously trained and predicted in the same task, the defect that the existing model classifier cannot take effect on the dose numerical type variable is overcome;
2. through the combination of the prescription prediction module and the medicine expansion module, similar medicines are expanded from recommended medicines while the medical record information of the patient is fully considered, and the medicine expansion module has better generalization capability;
3. the system also adopts medical record information of a clinical outstanding doctor as a training material, and the characteristic extraction module extracts a plurality of information such as symptom signs, inspection and medical history in the medical record and matches demographic information such as age, gender and the like as characteristics, so that a more personalized recommended prescription is provided for a patient;
4. the dosage friendly module is combined with the specification of the medicine, the prescription recommendation result is converted into a dosage friendly form, and the patient can conveniently take the medicine according to the prescription.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a diagram of a medicine sorting structure according to the present invention;
FIG. 3 is a block diagram of the specialist prescription model of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1, a prescription recommendation system includes a feature extraction module, a prescription prediction module, a drug expansion module, a drug contraindication check module, a dose-friendly module and a compatibility contraindication module, wherein the prescription prediction module includes a plurality of special prescription models respectively constructed according to special categories;
the work flow of the system is as follows:
s1, inputting medical record information and the special category, and extracting the patient characteristics in the medical record by a characteristic extraction module;
s2, inputting the patient characteristics into a corresponding special prescription model by a prescription prediction module according to the special category of the medical record information to predict the prescription, and outputting a recommended medicine and a corresponding dosage and usage;
s3, the medicine expansion module searches for similar medicines which have the same type and the same main components as the recommended medicines from the medicine library;
s4, the medicine contraindication checking module checks whether the use contraindication exists according to the medical record information;
s5, the dose friendly module converts the main component dose of the medicine into a user-friendly administration mode according to the specific specifications of the recommended medicine and the similar medicine;
s6, the incompatibility module further checks whether the prescription has incompatibility among medicines and outputs a final recommended prescription.
The specialist prescription model is used for classifying and scoring medicines, as shown in fig. 2, the medicine is divided into a plurality of main classes according to the functions of the medicines, each main class comprises a plurality of sub-classes of medicines which have the same functions and can be replaced with each other, and each sub-class of medicines comprises a plurality of common dosages.
As shown in fig. 3, the specialist prescription model comprises a presentation layer, an embedding layer, a multi-residual layer, an application layer and a multitask loss function, wherein the presentation layer is used for collecting the medicine function characteristics, and the application layer comprises a main classification scoring layer, a sub-classification scoring layer and a dose level scoring layer. The main classification scoring layer is used for carrying out weight scoring on the main classification; the sub-classification scoring layer is used for carrying out weight scoring on the sub-class medicines; the dose grade scoring layer is used for weighting and scoring the common dose of the subclass medicines.
The multitask loss function L specifically includes:
wherein p ismainA probability estimate representing a principal class;
probability estimation of the corresponding subcategories of the ith main classification is represented;
a probability estimate representing the dose corresponding to the jth sub-class of the ith main class; gtmainA fact label representing a master classification;
a fact label representing a sub-classification corresponding to the ith main classification;
a fact label of a dose corresponding to a jth sub-class of the ith main class;
indicating whether the dose classification is legitimate or not,
indicating that the dose classification is not legal,
indicating that the dose classification is legal.
The following takes a prescription recommendation process as an example:
1. inputting complete medical record information;
2. and extracting different types of features, namely One-hot types, by a feature extraction module, wherein the method comprises the following steps: acute upper respiratory infection, 10 indicates the diagnosis of the disease, 01 indicates the undiagnosed disease; time type (by day), such as cough days 3; floating point type, such as age (unit year), 3.5 means 3 and half years; all the different types of features are connected in series to form a long vector to form a complete feature, namely the patient feature;
3. the patient characteristics are fed into a prescription prediction module that outputs recommended medications and corresponding dosages and regimens, such as azithromycin (three times a day, 20g each);
4. the information is sent to a medicine expansion module to expand the medicine clarithromycin;
5. the medicine contraindication checking module checks that no special symptoms exist and the medicine can be taken;
6. a dosage friendly module for outputting friendly administration mode, for example, the azithromycin is 10 g/bag, and then the azithromycin is output (three times a day, 2 bags each time);
7. the incompatibility module can be used for prescription dispensing without incompatibility in the prescription.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A prescription recommendation system, characterized by: the system comprises a characteristic extraction module, a prescription prediction module, a medicine expansion module, a medicine contraindication checking module, a dose friendly module and a compatibility contraindication module, wherein the prescription prediction module comprises a plurality of special prescription models which are respectively constructed according to special categories;
the work flow of the system is as follows:
s1, inputting medical record information and the special category, and extracting the patient characteristics in the medical record by a characteristic extraction module;
s2, inputting the patient characteristics into a corresponding special prescription model by a prescription prediction module according to the special category of the medical record information to predict the prescription, and outputting a recommended medicine and a corresponding dosage and usage;
s3, the medicine expansion module searches for similar medicines which have the same type and the same main components as the recommended medicines from the medicine library;
s4, the medicine contraindication checking module checks whether the use contraindication exists according to the medical record information;
s5, the dose friendly module converts the main component dose of the medicine into a user-friendly administration mode according to the specific specifications of the recommended medicine and the similar medicine;
s6, the incompatibility module further checks whether the prescription has incompatibility among medicines and outputs a final recommended prescription.
2. A prescription recommendation system as claimed in claim 1, wherein: patient characteristics in the medical records include signs of symptoms, test results, medical history, patient age, and patient gender.
3. A prescription recommendation system as claimed in claim 2, wherein: the medicines are divided into a plurality of main classes according to the functions of the medicines in the special prescription model, each main class comprises a plurality of sub-classes of medicines which have the same functions and can be replaced mutually, and each sub-class of medicines comprises a plurality of common doses.
4. A prescription recommendation system as claimed in claim 3, wherein: the special prescription model comprises a representation layer, an embedding layer, a multi-residual layer, an application layer and a multitask loss function, wherein the representation layer is used for collecting the characteristics of the patient, and the application layer comprises a main classification scoring layer, a sub-classification scoring layer and a dose grade scoring layer.
5. A prescription recommendation system as claimed in claim 4, wherein: the main classification scoring layer is used for carrying out weight scoring on the main classification; the sub-classification scoring layer is used for carrying out weight scoring on the sub-class medicines; the dose grade scoring layer is used for weighting and scoring the common dose of the subclass medicines.
6. A prescription recommendation system as claimed in claim 5, wherein: the multitask loss function L specifically includes:
wherein p ismainA probability estimate representing a principal class;
probability estimation of the corresponding subcategories of the ith main classification is represented;
a probability estimate representing the dose corresponding to the jth sub-class of the ith main class; gtmainA fact label representing a master classification;
a fact label representing a sub-classification corresponding to the ith main classification;
a fact label of a dose corresponding to a jth sub-class of the ith main class;
indicating whether the dose classification is legal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110897823.9A CN113628716A (en) | 2021-08-05 | 2021-08-05 | Prescription recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110897823.9A CN113628716A (en) | 2021-08-05 | 2021-08-05 | Prescription recommendation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113628716A true CN113628716A (en) | 2021-11-09 |
Family
ID=78382998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110897823.9A Pending CN113628716A (en) | 2021-08-05 | 2021-08-05 | Prescription recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113628716A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102737165A (en) * | 2012-06-07 | 2012-10-17 | 北京太元通软件科技有限公司 | Clinical medication decision support system |
| CN105224794A (en) * | 2015-09-19 | 2016-01-06 | 石庆平 | A kind of intelligent Checking prescription system and method |
| CN108899070A (en) * | 2018-05-31 | 2018-11-27 | 平安医疗科技有限公司 | Prescription recommends generation method, device, computer equipment and storage medium |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| CN110223751A (en) * | 2019-05-16 | 2019-09-10 | 平安科技（深圳）有限公司 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
| CN110880362A (en) * | 2019-11-12 | 2020-03-13 | 南京航空航天大学 | Large-scale medical data knowledge mining and treatment scheme recommending system |
| 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 |
| CN111291266A (en) * | 2020-02-13 | 2020-06-16 | 腾讯科技（北京）有限公司 | Artificial intelligence based recommendation method and device, electronic equipment and storage medium |
| CN112214613A (en) * | 2020-10-15 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medication recommendation method and device, electronic equipment and medium |
| CN112348048A (en) * | 2020-09-28 | 2021-02-09 | 中国科学院信息工程研究所 | Multi-structure multi-task deep neural network and training and classifying method thereof |
| CN112489769A (en) * | 2019-08-22 | 2021-03-12 | 浙江远图互联科技股份有限公司 | Intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on deep neural network |
-
2021
- 2021-08-05 CN CN202110897823.9A patent/CN113628716A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102737165A (en) * | 2012-06-07 | 2012-10-17 | 北京太元通软件科技有限公司 | Clinical medication decision support system |
| CN105224794A (en) * | 2015-09-19 | 2016-01-06 | 石庆平 | A kind of intelligent Checking prescription system and method |
| CN108899070A (en) * | 2018-05-31 | 2018-11-27 | 平安医疗科技有限公司 | Prescription recommends generation method, device, computer equipment and storage medium |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| CN110223751A (en) * | 2019-05-16 | 2019-09-10 | 平安科技（深圳）有限公司 | Prescription evaluation method, system and computer equipment based on medical knowledge map |
| CN112489769A (en) * | 2019-08-22 | 2021-03-12 | 浙江远图互联科技股份有限公司 | Intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on deep neural network |
| CN110880362A (en) * | 2019-11-12 | 2020-03-13 | 南京航空航天大学 | Large-scale medical data knowledge mining and treatment scheme recommending system |
| 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 |
| CN111291266A (en) * | 2020-02-13 | 2020-06-16 | 腾讯科技（北京）有限公司 | Artificial intelligence based recommendation method and device, electronic equipment and storage medium |
| CN112348048A (en) * | 2020-09-28 | 2021-02-09 | 中国科学院信息工程研究所 | Multi-structure multi-task deep neural network and training and classifying method thereof |
| CN112214613A (en) * | 2020-10-15 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medication recommendation method and device, electronic equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 武玉伟等: "《深度学习基础与应用》", vol. 1, 北京理工大学出版社, pages: 229 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qiu et al. | A comprehensive review of computational methods for drug-drug interaction detection | |
| Du et al. | Neural attention with character embeddings for hay fever detection from twitter | |
| Karimi et al. | Text and data mining techniques in adverse drug reaction detection | |
| US20180293354A1 (en) | Clinical content analytics engine | |
| AU2019240633A1 (en) | System for automated analysis of clinical text for pharmacovigilance | |
| Zhou et al. | Using Medical Text Extraction, Reasoning and Mapping System (MTERMS) to process medication information in outpatient clinical notes | |
| JP7068106B2 (en) | Test plan formulation support device, test plan formulation support method and program | |
| CN102207990A (en) | Method and device for providing adverse effect information of drugs | |
| CN110299209A (en) | Similar case history lookup method, device, equipment and readable storage medium storing program for executing | |
| CN114664463A (en) | General practitioner diagnoses auxiliary system | |
| Banerji et al. | Natural language processing combined with ICD-9-CM codes as a novel method to study the epidemiology of allergic drug reactions | |
| Pereira et al. | Text mining applied to electronic medical records: a literature review | |
| Zhao et al. | Handling temporality of clinical events for drug safety surveillance | |
| CN106845118A (en) | A kind of auxiliary based on electronic health record shared document examines medication system and method | |
| CN115938608A (en) | Clinical decision early warning method and system based on prompt learning model | |
| Chandra et al. | Natural language Processing and Ontology based Decision Support System for Diabetic Patients | |
| Florez et al. | Deep learning for identification of adverse drug reaction relations | |
| Santos et al. | Fall detection in clinical notes using language models and token classifier | |
| CN113628716A (en) | Prescription recommendation system | |
| CN112258135A (en) | Method and device for auditing prescription data and computer-readable storage medium | |
| Henao et al. | Patient clustering with uncoded text in electronic medical records | |
| US20200143914A1 (en) | User Interface, System, and Method for Optimization of Patient Problem List Encoding | |
| Borlawsky et al. | Generating executable knowledge for evidence-based medicine using natural language and semantic processing | |
| Wunnava et al. | One Size Does Not Fit All: An Ensemble Approach Towards Information Extraction from Adverse Drug Event Narratives. | |
| van der Lei | Critiquing based on computer-stored medical records |
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 |