CN107092797A - A kind of medicine proposed algorithm based on deep learning - Google Patents

A kind of medicine proposed algorithm based on deep learning Download PDF

Info

Publication number
CN107092797A
CN107092797A CN201710281786.2A CN201710281786A CN107092797A CN 107092797 A CN107092797 A CN 107092797A CN 201710281786 A CN201710281786 A CN 201710281786A CN 107092797 A CN107092797 A CN 107092797A
Authority
CN
China
Prior art keywords
medicine
information
deep learning
disease
proposed algorithm
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
Application number
CN201710281786.2A
Other languages
Chinese (zh)
Inventor
罗日红
蔡君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Yirong E Commerce Co ltd
Guangdong Polytechnic Normal University
Original Assignee
Guangdong Yirong E Commerce Co ltd
Guangdong Polytechnic Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Yirong E Commerce Co ltd, Guangdong Polytechnic Normal University filed Critical Guangdong Yirong E Commerce Co ltd
Priority to CN201710281786.2A priority Critical patent/CN107092797A/en
Publication of CN107092797A publication Critical patent/CN107092797A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Marketing (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Pathology (AREA)
  • Development Economics (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The present invention proposes a kind of medicine proposed algorithm of deep learning.Belong to the field of computer software, pharmaceutical effectiveness and disease corresponding relation model are constructed under deep learning framework, a kind of personalized medicine proposed algorithm is proposed based on the model.The proposed algorithm of the present invention includes three parts：First, it is information concerning medications gatherer process, including gathers from CFDA the nomenclature of drug and its treatment disease of approval, medicine side effect, the information such as medication points for attention；Medicine sales data are gathered in online medicine store, user evaluates, the information such as price.Secondly, it is deep learning features training process, including the structure based on deep learning training network and characteristic parameter training process and the output of classifying drugs information.Finally, it is personalized recommendation, including the medicine based on long-term personal health feature is recommended and its implementation process.It is of the invention preferably to solve the problem of user lacks expert's instruction purchase medicine.

Description

A kind of medicine proposed algorithm based on deep learning
Technical field
The invention belongs to the technical field of computer software.
Technical background
With continuing to develop for information technology, increasing researcher begins attempt to apply to state-of-the-art science and technology Medical treatment ＆ health field, the rise of popularization and the shopping online of medicinal knowledge makes the now sick people for oneself buying medicine on the net afterwards Also more and more, also there are the Internet pharmacies such as online, the big pharmacy of Golden Elephant of flourish medicine foreign network You Shang pharmacies, the country, by more and more Concern.Buy medicine on the net not limited by time, space, region, for the time hurries or is not easy to the crowd of prolonged exercise It is particularly convenient；, can be with addition, the information such as substantial amounts of medicine information, pricing information and user comment can be obtained on the net Buy it is local without medicine；And because Internet pharmacy saves a series of expenses such as rent StoreFront, employee and storage keeping, always For the more general pharmacy of its price similar drug it is less expensive.
Medicine is bought while great convenience is brought on the net, and because drug variety is various, FDA approval listings have been obtained at present Medicine has taken in the disease of UMLS medical data bases more than 25000 kinds more than 1710 kinds, and medicine and the direct relation structure of disease Into millions of corresponding relations.The problem of online autonomous purchase medicine has maximum can not obtain effective expert when being purchase medicine and refer to Opinion is led, therefore, medicine is bought on the net all has certain blindness, easily occurred between wrong medicine thing, repeated drug taking, ignorance medicine The mistakes such as interaction, it is impossible to the problems such as medicine of oneself most suitable state of an illness is bought in the very first time.Current online medicine is pushed away Algorithm is recommended to be mainly based upon medicine sales sequence, price and evaluate sequence etc., but these algorithms can not efficiently solve medicine Relation between product and disease.
The content of the invention
In view of the above-mentioned problems, it is an object of the invention to provide a kind of medicine proposed algorithm based on deep learning, utilizing depth Spend learning model and extract pharmaceutical effectiveness linked character model corresponding with disease, and note with reference to user's evaluation, drug price, medication The information such as item, build personalized deep learning medicine recommended models, instruct user efficiently to be purchased medicine on the net.
The present invention constructs pharmaceutical effectiveness and disease corresponding relation model under deep learning framework, is proposed based on the model A kind of personalized medicine proposed algorithm, preferably solves the problem of user lacks expert's instruction purchase medicine.
Technical scheme includes：Information concerning medications collection analysis；Deep learning features training；Personalized recommendation Deng three processes.
Information concerning medications collection analysis includes：The nomenclature of drug and its treatment disease of approval, medicine are gathered from CFDA Side effect, the information such as medication points for attention；Medicine sales data are gathered in online medicine store, user evaluates, the information such as price.
Deep learning features training：Including the structure based on deep learning training network and characteristic parameter training process and Classifying drugs information is exported.
Personalized recommendation：Recommend including the medicine based on long-term personal health feature and its implementation process.
Brief description of the drawings
Fig. 1 is the medicine specifit training implementation framework figure based on deep learning；
Fig. 2 is personalized medicine recommendation process.
Specific implementation method
Data acquisition and its features training implementation framework of the present invention as shown in figure 1, gather the medicines such as CFDA, FDA first Information authority data message and the medicine sales information of online shopping mall, build own coding deep learning network, utilize collection Data train acquisition network weight.In personalized recommendation process as shown in Fig. 2 personal relevant information and its state of an illness input are instructed Practice in the network completed, the personalized medicine for obtaining system is recommended.
Medicine information is gathered and medicine specifit training specific implementation process：
1. from CFDA websites ratify medicine from obtain nomenclature of drug, treat disease name, drug dosage, side effect and Drug chemistry architectural feature etc.；
2. collect disease information from the data source including UMLS databases；
3. from including CDT (Comparative Toxicogenomics Database) data source collect medicine- The treatment relation information of disease；
4. collect medicine-disease side effect relation information from the data source including OFFSIDES；
5. medicine sales information is collected in medicine store from network；
6. the Various types of data of pair collection is standardized；
7. sparse own coding eigenmatrix X=Yx1, x2 ..., the xnY of medicine are built, for arbitrary X after training It is output as h (x(i)；W, b)=σ (Wx(i)+ b), wherein W is the weight of autoencoder network, and b is bias weight, and σ is activation letter Number.
Using gathered data training network parameter, it is allowed to meet personalized medicine recommendation process：
1. user personalized information is collected, including the history of disease such as age, sex, height, body weight, drug allergy；
2. the medicine information of user's request, can be illness information or nomenclature of drug；
3. medicine prediction is carried out by the individual demand construction feature matrix of user, and by autoencoder network, output Including the information such as medicine and its drug dosage, medication points for attention.

Claims (4)

1. a kind of medicine proposed algorithm based on deep learning, it is characterized in that including：Information concerning medications collection analysis, depth Practise features training, three processes of personalized recommendation：
Information concerning medications collection analysis：Nomenclature of drug and its treatment disease including gathering approval from CFDA, medicine pair are made With the information such as medication points for attention；Medicine sales data are gathered in online medicine store, user evaluates, the information such as price；
Deep learning features training：Including the structure based on deep learning training network and characteristic parameter training process and medicine Classification information is exported；
Personalized recommendation：Recommend including the medicine based on long-term personal health feature and its implementation process.
2. the medicine proposed algorithm according to claim 1 based on deep learning, it is characterized in that described medicine correlation letter Breath collection：
(1) ratify medicine from CFDA websites from nomenclature of drug is obtained, treat disease name, drug dosage, side effect and medicine Product chemical structure characteristic；
(2) disease information is collected from the data source including UMLS databases；
(3) medicine-disease is collected from the data source including CDT (Comparative Toxicogenomics Database) The treatment relation information of disease；
(4) medicine-disease side effect relation information is collected from the data source including OFFSIDES；
(5) medicine sales information is collected in medicine store from network.
3. the medicine proposed algorithm according to claim 1 based on deep learning, it is characterized in that deep learning features training：
(1) Various types of data to collection is standardized；
(2) sparse own coding eigenmatrix X=Yx1, x2 ..., the xnY of medicine are built, it is defeated after training for any X Go out for h (x(i)；W, b)=σ (Wx(i)+ b), wherein W is the weight of autoencoder network, and b is bias weight, and σ is activation primitive.
4. the medicine proposed algorithm according to claim 1 based on deep learning, it is characterized in that described personalized recommendation：
(1) history of disease such as user personalized information, including age, sex, height, body weight, drug allergy are collected；
(2) medicine information of user's request, can be illness information or nomenclature of drug；
(3) by the individual demand construction feature matrix of user, and medicine prediction is carried out by autoencoder network, output includes The information such as medicine and its drug dosage, medication points for attention.
CN201710281786.2A 2017-04-26 2017-04-26 A kind of medicine proposed algorithm based on deep learning Pending CN107092797A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710281786.2A CN107092797A (en) 2017-04-26 2017-04-26 A kind of medicine proposed algorithm based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710281786.2A CN107092797A (en) 2017-04-26 2017-04-26 A kind of medicine proposed algorithm based on deep learning

Publications (1)

Publication Number Publication Date
CN107092797A true CN107092797A (en) 2017-08-25

Family

ID=59637990

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710281786.2A Pending CN107092797A (en) 2017-04-26 2017-04-26 A kind of medicine proposed algorithm based on deep learning

Country Status (1)

Country Link
CN (1) CN107092797A (en)

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108062970A (en) * 2017-12-15 2018-05-22 泰康保险集团股份有限公司 Drug recommends method and device
CN108062556A (en) * 2017-11-10 2018-05-22 广东药科大学 A kind of drug-disease relationship recognition methods, system and device
CN108231152A (en) * 2018-02-05 2018-06-29 南昌医软科技有限公司 Medicine prescription result generation method and device
CN108231153A (en) * 2018-02-08 2018-06-29 康美药业股份有限公司 A kind of drug recommends method, electronic equipment and storage medium
CN108389608A (en) * 2018-02-08 2018-08-10 康美药业股份有限公司 Drug recommends method, electronic equipment and storage medium
CN108417271A (en) * 2018-01-11 2018-08-17 复旦大学 Mental inhibitor object based on phrenoblabia Subtypes recommends method and system
CN109033275A (en) * 2018-07-10 2018-12-18 武汉海云健康科技股份有限公司 A kind of prediction technique of the drug regional demand based on association map and neural network
CN109064294A (en) * 2018-08-21 2018-12-21 重庆大学 A kind of time of fusion factor, the drug recommended method of text feature and correlation
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
CN109636494A (en) * 2017-10-09 2019-04-16 耀方信息技术(上海)有限公司 Drug recommended method and system
CN110176291A (en) * 2019-04-19 2019-08-27 周凡 A kind of health and fitness information recommended method based on deep learning
CN110824142A (en) * 2019-11-13 2020-02-21 杭州鲁尔物联科技有限公司 Geological disaster prediction method, device and equipment
CN110827951A (en) * 2019-12-24 2020-02-21 陕西省中医医院 Clinical intelligent decision platform
CN111133450A (en) * 2017-09-14 2020-05-08 西门子股份公司 Method for generating at least one recommendation
WO2020091375A3 (en) * 2018-10-29 2020-06-25 고려대학교 산학협력단 Antidepressant recommendation method and system
WO2020132918A1 (en) * 2018-12-24 2020-07-02 深圳市优必选科技有限公司 Method and device for pharmaceutical forecasting, computer device, and storage medium
CN111696678A (en) * 2020-06-15 2020-09-22 中南大学 Deep learning-based medication decision method and system
CN112463973A (en) * 2019-09-06 2021-03-09 医渡云（北京）技术有限公司 Construction method, device and medium of medical knowledge graph and electronic equipment
CN113222699A (en) * 2021-05-12 2021-08-06 北京小乔机器人科技发展有限公司 Method for recommending medicine by robot
CN113838583A (en) * 2021-09-27 2021-12-24 中国人民解放军空军军医大学 Intelligent drug efficacy evaluation method based on machine learning and application thereof
CN114722976A (en) * 2022-06-09 2022-07-08 青岛美迪康数字工程有限公司 Medicine recommendation system and construction method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130317316A1 (en) * 2012-05-25 2013-11-28 City Of Hope Carbohydrate modeling methods, systems, and devices
CN104951665A (en) * 2015-07-22 2015-09-30 浙江大学 Method and system of medicine recommendation
CN106022004A (en) * 2016-05-20 2016-10-12 北京千安哲信息技术有限公司 Method and system for detecting mixed drug conflict
CN106066936A (en) * 2016-05-30 2016-11-02 北京千安哲信息技术有限公司 A kind of method and system improving adverse effect precision of prediction

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130317316A1 (en) * 2012-05-25 2013-11-28 City Of Hope Carbohydrate modeling methods, systems, and devices
CN104951665A (en) * 2015-07-22 2015-09-30 浙江大学 Method and system of medicine recommendation
CN106022004A (en) * 2016-05-20 2016-10-12 北京千安哲信息技术有限公司 Method and system for detecting mixed drug conflict
CN106066936A (en) * 2016-05-30 2016-11-02 北京千安哲信息技术有限公司 A kind of method and system improving adverse effect precision of prediction

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111133450A (en) * 2017-09-14 2020-05-08 西门子股份公司 Method for generating at least one recommendation
CN109636494A (en) * 2017-10-09 2019-04-16 耀方信息技术(上海)有限公司 Drug recommended method and system
CN108062556A (en) * 2017-11-10 2018-05-22 广东药科大学 A kind of drug-disease relationship recognition methods, system and device
CN108062556B (en) * 2017-11-10 2021-09-14 广东药科大学 Drug-disease relationship identification method, system and device
CN108062970A (en) * 2017-12-15 2018-05-22 泰康保险集团股份有限公司 Drug recommends method and device
CN108417271A (en) * 2018-01-11 2018-08-17 复旦大学 Mental inhibitor object based on phrenoblabia Subtypes recommends method and system
CN108417271B (en) * 2018-01-11 2021-11-19 复旦大学 Mental inhibition drug recommendation method and system based on mental disorder subtype classification
CN108231152A (en) * 2018-02-05 2018-06-29 南昌医软科技有限公司 Medicine prescription result generation method and device
CN108231153A (en) * 2018-02-08 2018-06-29 康美药业股份有限公司 A kind of drug recommends method, electronic equipment and storage medium
CN108389608A (en) * 2018-02-08 2018-08-10 康美药业股份有限公司 Drug recommends method, electronic equipment and storage medium
CN109033275B (en) * 2018-07-10 2021-07-30 武汉海云健康科技股份有限公司 Medicine area demand prediction method based on association map and neural network
CN109033275A (en) * 2018-07-10 2018-12-18 武汉海云健康科技股份有限公司 A kind of prediction technique of the drug regional demand based on association map and neural network
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
CN109064294A (en) * 2018-08-21 2018-12-21 重庆大学 A kind of time of fusion factor, the drug recommended method of text feature and correlation
CN109064294B (en) * 2018-08-21 2021-11-12 重庆大学 Medicine recommendation method integrating time factors, text features and correlation
WO2020091375A3 (en) * 2018-10-29 2020-06-25 고려대학교 산학협력단 Antidepressant recommendation method and system
WO2020132918A1 (en) * 2018-12-24 2020-07-02 深圳市优必选科技有限公司 Method and device for pharmaceutical forecasting, computer device, and storage medium
CN110176291A (en) * 2019-04-19 2019-08-27 周凡 A kind of health and fitness information recommended method based on deep learning
CN112463973A (en) * 2019-09-06 2021-03-09 医渡云（北京）技术有限公司 Construction method, device and medium of medical knowledge graph and electronic equipment
CN110824142B (en) * 2019-11-13 2022-06-24 杭州鲁尔物联科技有限公司 Geological disaster prediction method, device and equipment
CN110824142A (en) * 2019-11-13 2020-02-21 杭州鲁尔物联科技有限公司 Geological disaster prediction method, device and equipment
CN110827951A (en) * 2019-12-24 2020-02-21 陕西省中医医院 Clinical intelligent decision platform
CN111696678A (en) * 2020-06-15 2020-09-22 中南大学 Deep learning-based medication decision method and system
CN113222699A (en) * 2021-05-12 2021-08-06 北京小乔机器人科技发展有限公司 Method for recommending medicine by robot
CN113838583A (en) * 2021-09-27 2021-12-24 中国人民解放军空军军医大学 Intelligent drug efficacy evaluation method based on machine learning and application thereof
CN113838583B (en) * 2021-09-27 2023-10-24 中国人民解放军空军军医大学 Intelligent medicine curative effect evaluation method based on machine learning and application thereof
CN114722976A (en) * 2022-06-09 2022-07-08 青岛美迪康数字工程有限公司 Medicine recommendation system and construction method

Similar Documents

Publication Publication Date Title
CN107092797A (en) A kind of medicine proposed algorithm based on deep learning
Bentlage et al. Practical recommendations for maintaining active lifestyle during the COVID-19 pandemic: a systematic literature review
Sharp et al. A systematic review and meta-analysis of intensive multidisciplinary intervention for pediatric feeding disorders: how standard is the standard of care?
CN109087691A (en) A kind of OTC drugs recommender system and recommended method based on deep learning
Aguilera-Rubio et al. Feasibility and efficacy of a virtual reality game-based upper extremity motor function rehabilitation therapy in patients with chronic stroke: A pilot study
Ehn et al. Technology-based motivation support for seniors’ physical activity—A qualitative study on seniors’ and health care professionals’ views
Miguel-Rubio et al. Is virtual reality effective for balance recovery in patients with spinal cord injury? A systematic review and meta-analysis
Abad-Segura et al. Management accounting for healthy nutrition education: meta-analysis
Bacanoiu et al. New strategies to improve the quality of life for normal aging versus pathological aging
Valdés-Badilla et al. Effectiveness of olympic combat sports on balance, fall risk or falls in older adults: a systematic review
Salvalaggio et al. Virtual feedback for arm motor function rehabilitation after stroke: a randomized controlled trial
Liu et al. The origin, application and mechanism of therapeutic climbing: a narrative review
Kiper et al. Effects of Immersive virtual reality on Upper-Extremity Stroke Rehabilitation: a systematic review with Meta-analysis
Faria et al. Effect of the Active Aging-in-Place–Rehabilitation Nursing Program: A Randomized Controlled Trial
Park et al. Effects of virtual reality-based cognitive rehabilitation in stroke patients: a randomized controlled trial
Lee et al. Estimating health-related quality of life based on demographic characteristics, questionnaires, gait ability, and physical fitness in Korean elderly adults
Marco-Ahulló et al. Encouraging people with spinal cord injury to take part in physical activity in the COVID-19 epidemic through the mHealth ParaSportAPP
Carvalho et al. Repeated massage improves swimmers’ perceptions during training sessions but not sprint and functional performance: a randomized controlled trial
Taghinejad et al. Investigating the effects of nurse post-discharge follow-up phone calls on the self-efficacy of patients caregivers suffering from stroke
Zhang et al. Mapping research trends from 20 years of publications in rhythmic auditory stimulation
Fuentes-García et al. Modification of the forms of self-determined regulation and quality of life after a cardiac rehabilitation programme: Tennis-based vs. bicycle ergometer-based
Bowman et al. Classification and quantification of physical therapy interventions across multiple neurological disorders: an Italian multicenter network
Bruschetta et al. Gender influences virtual reality-based recovery of cognitive functions in patients with traumatic brain injury: A secondary analysis of a randomized clinical trial
Lambert et al. Accident vulnerability and vision for action: a pilot investigation
Rodríguez-Huguet et al. Aquatic Exercise in Physical Therapy Treatment for Fibromyalgia: Systematic Review

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

Application publication date: 20170825

WD01 Invention patent application deemed withdrawn after publication