CN110517787A - A kind of clinical data group classification method based on Chinese medical main suit's analysis - Google Patents

A kind of clinical data group classification method based on Chinese medical main suit's analysis Download PDF

Info

Publication number
CN110517787A
CN110517787A CN201910814991.XA CN201910814991A CN110517787A CN 110517787 A CN110517787 A CN 110517787A CN 201910814991 A CN201910814991 A CN 201910814991A CN 110517787 A CN110517787 A CN 110517787A
Authority
CN
China
Prior art keywords
data
main suit
clinical
data group
analysis
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
CN201910814991.XA
Other languages
Chinese (zh)
Inventor
曹梦莉
王国超
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.)
Shandong Health And Medical Big Data Co Ltd
Original Assignee
Shandong Health And Medical Big Data Co Ltd
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 Shandong Health And Medical Big Data Co Ltd filed Critical Shandong Health And Medical Big Data Co Ltd
Priority to CN201910814991.XA priority Critical patent/CN110517787A/en
Publication of CN110517787A publication Critical patent/CN110517787A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • G06F16/355Class or cluster creation or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H80/00ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring

Landscapes

  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • General Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention is more particularly directed to a kind of clinical data group classification methods based on Chinese medical main suit's analysis.The clinical data group classification method based on Chinese medical main suit's analysis carries out analysis mining using data group of the machine learning algorithm to the main suit composition of various clinical examinations inspection data and doctor's typing, obtains information and knowledge that data group implies;It is analyzed and processed according to the data source that hospital information system provides, obtains the data classification of data group;By the corresponding data category in data group deposit clinical data center relevant knowledge library.The clinical data group classification method based on Chinese medical main suit's analysis, data model is established by using machine learning related algorithm, the data group of the main suit composition of data and doctor's typing, which carries out analysis mining, to be checked to various clinical examinations, realize the exact classification to data group, the working efficiency of doctor can not only be greatly improved, is also of great significance to small-sized, miniature clinical data center in building institute.

Description

A kind of clinical data group classification method based on Chinese medical main suit's analysis
Technical field
It is the present invention relates to machine learning algorithm and data mining technology field, in particular to a kind of based on the medical main suit of Chinese The clinical data group classification method of analysis.
Background technique
The different brackets of different hospital, hospital, the level of informatization is irregular in institute, in the not high doctor of the level of informatization Inside institute, each operation system is there are data silo, in institute between each system, between Hospitals in Region and hospital, and hospital and society Can there be different degrees of data barrier between the public.
With the continuous development of big data technology, under the dual promotion of policy and technology, hospital has strong wish to disappear Except internal data barrier, miniature, small hospital's clinical data center is established, to the interconnecting of data, the scientific research of doctor needs It asks, the Diseases diagnosis in institute, reduce doctor's misdiagnosis rate etc. and will have important meaning.
Doctor needs the auxiliary of many relevant informations in diagnosis and treatment process, and most important information source is the various of patient Clinical examination checks the data group of data composition.These examine detection datas composition data group, be imported into disease database it Afterwards, it is capable of forming the support of disease aid decision, guidance is further formed to the work of doctor, so that accurate judgement disease, provides Diagnosis and treatment scheme reduces technical fault.Therefore, if data model can be established, data composition is checked to various clinical examinations Data group carries out analysis mining, realizes the exact classification to data group, it will the working efficiency for greatly improving doctor, to building institute Interior small-sized, miniature clinical data center is of great significance.
Based on the above situation, the invention proposes a kind of clinical data group classification sides based on Chinese medical main suit's analysis Method.
Summary of the invention
In order to compensate for the shortcomings of the prior art, the present invention provides it is a kind of be simple and efficient analyzed based on Chinese medical main suit Clinical data group classification method.
The present invention is achieved through the following technical solutions:
A kind of clinical data group classification method based on Chinese medical main suit's analysis, it is characterised in that: the following steps are included:
The first step is formed using main suit of the machine learning algorithm to various clinical examinations inspection data and doctor's typing Data group carries out analysis mining, obtains information and knowledge that data group implies;
Second step, the data source provided according to hospital information system carry out at analysis the main suit content of doctor's typing Reason obtains the data classification of data group in conjunction with information and knowledge that the data group got implies;
Third step, by the corresponding data category in data group deposit clinical data center relevant knowledge library.
In the first step, it is described using machine learning algorithm to various clinical examinations check data composition data group into Row analysis mining, including Chinese text pretreatment, feature extraction, data modeling and Knowledge Discovery.
The Chinese text pretreatment includes text data cleaning, word segmentation and data mapping.
The data cleansing refers to processing missing data and exceptional value, and weeds out unrelated with data modeling in initial data Data.
The word segmentation, which refers to, checks that data and doctor are recorded for various clinical examinations using the customized dictionary for word segmentation of user The main suit entered segments respectively;The customized dictionary for word segmentation of user uses main suit's relevant medical dictionary, and cuts in word Timesharing load uses.
The data mapping refers to building inspection and data classification Standard Map table, and using Standard Map table respectively to each Kind clinical examination checks that the main suit of data and doctor's typing is standardized.Example: hypertension three-level (XXX) is mapped as height Blood pressure three-level.
The feature extraction includes following two parts:
First, load user's Custom Dictionaries segment the main suit content of doctor's typing, after being converted to term vector After extracting main suit's Feature Words, code conversion is carried out to main suit's Feature Words;
Second, data, which carry out cutting, to be checked to various clinical examinations using additional character, filters out the character without Chinese , and data, which are standardized, to be checked to various clinical examinations respectively using Standard Map table;Then load user makes by oneself Various clinical examinations after standardization are checked that data segment by adopted dictionary, extract clinical examination after being converted to term vector It checks data characteristics word, data characteristics word, which carries out code conversion, then to be checked to clinical examination.
The data modeling refer to the main suit's content and various clinical examinations that have carried out code conversion check data into Row modeling;After data modeling, it is original set that the result of data model output, which is carried out code conversion again, to construct main suit Content, various clinical examinations check the regulation engine between data and data classification.
In the third step, the corresponding data category in the clinical data center relevant knowledge library includes disease category and inspection Look into classification.
The beneficial effects of the present invention are: should be based on the clinical data group classification method of Chinese medical main suit's analysis, by making Data model is established with machine learning related algorithm, the main suit composition of data and doctor's typing is checked to various clinical examinations Data group carries out analysis mining, realizes the exact classification to data group, can not only greatly improve the working efficiency of doctor, also It is of great significance to small-sized, miniature clinical data center in building institute.
Specific embodiment
In order to which technical problems, technical solutions and advantages to be solved are more clearly understood, tie below Embodiment is closed, the present invention will be described in detail.It should be noted that specific embodiment described herein is only to explain The present invention is not intended to limit the present invention.
The clinical data group classification method based on Chinese medical main suit's analysis, comprising the following steps:
The first step is formed using main suit of the machine learning algorithm to various clinical examinations inspection data and doctor's typing Data group carries out analysis mining, obtains information and knowledge that data group implies;
Second step, the data source provided according to hospital information system carry out at analysis the main suit content of doctor's typing Reason obtains the data classification of data group in conjunction with information and knowledge that the data group got implies;
Third step, by the corresponding data category in data group deposit clinical data center relevant knowledge library.
The data source that the hospital information system provides comes from hospital HIS (Hospital Information System) System.HIS is the information management system for covering hospital all business and business overall process, is a kind of living in hospital management and medical treatment The computer application system of information management and on-line operation, english abbreviation HIS are carried out in dynamic.
Hospital HIS system includes following components:
(1) clinic diagnosis part: doctor workstation, nursing station, clinic information system (Clinical Information System, CIS), radiological information system (Radiology Information System, RIS), experiment Room information system (Laboratory Information System, LIS) medical image information system PACS (Picture Archiving and Communication Systems), blood transfusion and blood bank management system, surgery anesthesia management system;
(2) drug control part: data preparation and drug dictionary, drug store management function, outpatients pharmacy manage function Energy, dispensary for inpatients management function, drug calculate function, Drug price control, preparation management subsystem, rational use of medicines consulting function Energy;
(3) economic management part: Emergency call hospital registration system, pricing and fees for outpatients and ER department system, inpatient enters, goes out, tube Reason system, patient's cost of hospitalization system, material Management System, the equipment management subsystem, financial management and business accounting management system System;
(4) integrated management and statistical analysis part: health record management system, Medical Statistical System, president's inquiry are with analysis System, patient's consultative service system;
(5) external interface part: medical insurance interface, urban community health services interface, remote medical consultation system interface.
In the first step, it is described using machine learning algorithm to various clinical examinations check data composition data group into Row analysis mining, including Chinese text pretreatment, feature extraction, data modeling and Knowledge Discovery.
The Chinese text pretreatment includes text data cleaning, word segmentation and data mapping.
The data cleansing refers to processing missing data and exceptional value, and weeds out unrelated with data modeling in initial data Data.
The word segmentation, which refers to, checks that data and doctor are recorded for various clinical examinations using the customized dictionary for word segmentation of user The main suit entered segments respectively;The customized dictionary for word segmentation of user uses main suit's relevant medical dictionary, and cuts in word Timesharing load uses.
The data mapping refers to building inspection and data classification Standard Map table, and using Standard Map table respectively to each Kind clinical examination checks that the main suit of data and doctor's typing is standardized.Example: hypertension three-level (XXX) is mapped as height Blood pressure three-level.
The feature extraction includes following two parts:
First, load user's Custom Dictionaries segment the main suit content of doctor's typing, after being converted to term vector After extracting main suit's Feature Words, code conversion is carried out to main suit's Feature Words;
Second, data, which carry out cutting, to be checked to various clinical examinations using additional character, filters out the character without Chinese , and data, which are standardized, to be checked to various clinical examinations respectively using Standard Map table;Then load user makes by oneself Various clinical examinations after standardization are checked that data segment by adopted dictionary, extract clinical examination after being converted to term vector It checks data characteristics word, data characteristics word, which carries out code conversion, then to be checked to clinical examination.
The data modeling refer to the main suit's content and various clinical examinations that have carried out code conversion check data into Row modeling;After data modeling, it is original set that the result of data model output, which is carried out code conversion again, to construct main suit Content, various clinical examinations check the regulation engine between data and data classification.
In the third step, the corresponding data category in the clinical data center relevant knowledge library includes disease category and inspection Look into classification.
Compared with prior art, there should be following spy based on the clinical data group classification method of Chinese medical main suit's analysis Point:
1, using dependency rules engines such as machine learning related algorithm building diagnosis.
2, by checking that data carry out mining analysis to the various clinical examinations in hospital information system, the data institute is obtained Implicit information and knowledge, and main suit's content of doctor's typing can be analyzed and processed obtain corresponding disease category and It checks classification, and is automatically credited corresponding classification, to build small-sized, miniature clinical data center in institute.
Embodiment described above, only one kind of the specific embodiment of the invention, those skilled in the art is in this hair The usual variations and alternatives carried out in bright technical proposal scope should be all included within the scope of the present invention.

Claims (9)

1. a kind of clinical data group classification method based on Chinese medical main suit's analysis, which comprises the following steps:
The first step checks various clinical examinations the data of the main suit composition of data and doctor's typing using machine learning algorithm Group carries out analysis mining, obtains information and knowledge that data group implies;
Second step, the data source provided according to hospital information system are analyzed and processed the main suit content of doctor's typing, tie The data group got implicit information and knowledge are closed, the data classification of data group is obtained;
Third step, by the corresponding data category in data group deposit clinical data center relevant knowledge library.
2. the clinical data group classification method according to claim 1 based on Chinese medical main suit's analysis, it is characterised in that: It is described that the data group of data composition, which carries out analysis digging, to be checked to various clinical examinations using machine learning algorithm in the first step Pick, including Chinese text pretreatment, feature extraction, data modeling and Knowledge Discovery.
3. the clinical data group classification method according to claim 2 based on Chinese medical main suit's analysis, it is characterised in that: The Chinese text pretreatment includes text data cleaning, word segmentation and data mapping.
4. the clinical data group classification method according to claim 3 based on Chinese medical main suit's analysis, it is characterised in that: The data cleansing refers to processing missing data and exceptional value, and weeds out data unrelated with data modeling in initial data.
5. the clinical data group classification method according to claim 3 based on Chinese medical main suit's analysis, it is characterised in that: The word segmentation refers to the main suit that various clinical examinations are checked to data and doctor's typing using the customized dictionary for word segmentation of user Item is segmented respectively;The customized dictionary for word segmentation of user uses main suit's relevant medical dictionary, and loads in word segmentation It uses.
6. the clinical data group classification method according to claim 3 based on Chinese medical main suit's analysis, it is characterised in that: The data mapping refers to building inspection and data classification Standard Map table, and is examined respectively to various clinics using Standard Map table It tests and checks that the main suit of data and doctor's typing is standardized.
7. the clinical data group classification method according to claim 2 based on Chinese medical main suit's analysis, it is characterised in that: The feature extraction includes following two parts:
First, load user's Custom Dictionaries segment the main suit content of doctor's typing, extract after being converted to term vector After main suit's Feature Words, code conversion is carried out to main suit's Feature Words;
Second, second, data, which carry out cutting, to be checked to various clinical examinations using additional character, filters out the character without Chinese , and data, which are standardized, to be checked to various clinical examinations respectively using Standard Map table;Then load user makes by oneself Various clinical examinations after standardization are checked that data segment by adopted dictionary, extract clinical examination after being converted to term vector It checks data characteristics word, data characteristics word, which carries out code conversion, then to be checked to clinical examination.
8. the clinical data group classification method according to claim 2 based on Chinese medical main suit's analysis, it is characterised in that: The data modeling, which refers to, checks that data model to the main suit content and various clinical examinations that have carried out code conversion;Number After modeling, it is original set that the result of data model output, which is carried out code conversion again, to construct main suit's content, various Clinical examination checks the regulation engine between data and data classification.
9. the clinical data group classification method according to claim 1 based on Chinese medical main suit's analysis, it is characterised in that: In the third step, the corresponding data category in the clinical data center relevant knowledge library includes disease category and checks classification.
CN201910814991.XA 2019-08-30 2019-08-30 A kind of clinical data group classification method based on Chinese medical main suit's analysis Pending CN110517787A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910814991.XA CN110517787A (en) 2019-08-30 2019-08-30 A kind of clinical data group classification method based on Chinese medical main suit's analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910814991.XA CN110517787A (en) 2019-08-30 2019-08-30 A kind of clinical data group classification method based on Chinese medical main suit's analysis

Publications (1)

Publication Number Publication Date
CN110517787A true CN110517787A (en) 2019-11-29

Family

ID=68628490

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910814991.XA Pending CN110517787A (en) 2019-08-30 2019-08-30 A kind of clinical data group classification method based on Chinese medical main suit's analysis

Country Status (1)

Country Link
CN (1) CN110517787A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111739601A (en) * 2020-06-28 2020-10-02 山东健康医疗大数据有限公司 Normalization method, device and readable medium for non-standard disease names

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013008159A (en) * 2011-06-23 2013-01-10 Toshio Kobayashi Medical data analysis method, medical data analysis device and program
CN104123395A (en) * 2014-08-13 2014-10-29 北京赛科世纪数码科技有限公司 Decision making method and system based on big data
CN106228000A (en) * 2016-07-18 2016-12-14 北京千安哲信息技术有限公司 Over-treatment detecting system and method
CN107833605A (en) * 2017-03-14 2018-03-23 北京大瑞集思技术有限公司 A kind of coding method, device, server and the system of hospital's medical record information
CN109522973A (en) * 2019-01-17 2019-03-26 云南大学 Medical big data classification method and system based on production confrontation network and semi-supervised learning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013008159A (en) * 2011-06-23 2013-01-10 Toshio Kobayashi Medical data analysis method, medical data analysis device and program
CN104123395A (en) * 2014-08-13 2014-10-29 北京赛科世纪数码科技有限公司 Decision making method and system based on big data
CN106228000A (en) * 2016-07-18 2016-12-14 北京千安哲信息技术有限公司 Over-treatment detecting system and method
CN107833605A (en) * 2017-03-14 2018-03-23 北京大瑞集思技术有限公司 A kind of coding method, device, server and the system of hospital's medical record information
CN109522973A (en) * 2019-01-17 2019-03-26 云南大学 Medical big data classification method and system based on production confrontation network and semi-supervised learning

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
姚纯旭 等: "临床医学数据的分析方法与利用", 《中国医药导报》 *
王淑 等: "基于临床数据中心的专病研究系统建设与实践", 《中国医院》 *
阮彤 等: "基于电子病历的临床医疗大数据挖掘流程与方法", 《大数据》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111739601A (en) * 2020-06-28 2020-10-02 山东健康医疗大数据有限公司 Normalization method, device and readable medium for non-standard disease names
CN111739601B (en) * 2020-06-28 2022-03-29 山东健康医疗大数据有限公司 Normalization method, device and readable medium for non-standard disease names

Similar Documents

Publication Publication Date Title
US8626533B2 (en) Patient data mining with population-based analysis
US8086468B2 (en) Method for computerising and standardizing medical information
US20060122865A1 (en) Procedural medicine workflow management
US20070118399A1 (en) System and method for integrated learning and understanding of healthcare informatics
US20070005621A1 (en) Information system using healthcare ontology
US10565315B2 (en) Automated mapping of service codes in healthcare systems
US10318635B2 (en) Automated mapping of service codes in healthcare systems
KR100739570B1 (en) Hospital information system and method
Bell et al. Experiments in concept modeling for radiographic image reports
Rubin et al. A data warehouse for integrating radiologic and pathologic data
Arvanitis Semantic interoperability in healthcare
US11875884B2 (en) Expression of clinical logic with positive and negative explainability
KR101239140B1 (en) Mapping method and its system of medical standard terminologies
CN110517787A (en) A kind of clinical data group classification method based on Chinese medical main suit's analysis
Yousefianzadeh et al. COVID-19 ontologies and their application in medical sciences: Reviewing Bioportal
CN115831298B (en) Clinical trial patient recruitment method and device based on hospital management information system
Kang et al. Mapping Korean National Health Insurance reimbursement claim codes for therapeutic and surgical procedures to SNOMED-CT to facilitate data reuse
US20140278481A1 (en) Large scale identification and analysis of population health risks
Blankshain et al. Research registries: a tool to advance understanding of rare neuro-ophthalmic diseases
KR20220149795A (en) System for managing smart hospital based on intelligent workflow
CN106484812A (en) A kind of realization method and system of medical treatment framework data interchange
Irschara et al. Building the MedCorpInn corpus: Issues and goals
Bansal et al. Healthcare Data Organization
Stolba et al. EHealth integrator-clinical data integration in lower austria
Alyami et al. Health decision support system based on patient provided data for both patients and physicians use

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20191129

RJ01 Rejection of invention patent application after publication