《徐州-医疗大数据分析徐建业2015-short ppt课件.ppt》由会员分享，可在线阅读，更多相关《徐州-医疗大数据分析徐建业2015-short ppt课件.ppt（76页珍藏版）》请在三一文库上搜索。
1、Health Information Database Application 巨量医疗健康生活数据分析与应用 Big Data for Biomedical Applications,1,2015-06-26 徐州医学院急诊医学两岸学术交流综合论坛,Chien-Yeh Hsu 徐建业 PhD 台北护理健康大学信息管理系所 National Taipei University of Nursing and Health Sciences 台北医学大学医学信息研究所 Taipei Medical University 台湾医学信息学会 Taiwan Association for Medical
2、 Informatics TAMI,2,Roadmap for ICT Development in Taiwan,行政院,m-Taiwan（2005）,NHIP & U-Taiwan （2008）,Ubiquitous e-Service,Mobile Services,Web Government Services,Web Healthcare Services,Health Insurance IC Card,HIS,HIN,NII,Tele Medicare,Construct Healthcare Informatics Infrastructure,Personal Healthc
3、are Record,2002,2005,2008,Electronic Medical Record,2011,Government e-Service & e-indus-trialization,International Trend,Application Trend,Development Trend of Taiwan Health Systems,4,The NHI VPN国家卫生基础设施,HIN,NHI VPN,IDC,NHI local offices,NHI head-quarter,CDC,17,000 Clinics,DOH,SC,Admin,BOH,HCA,600 H
4、ospitals,5,000 Pharmacy,Other 100 HIS,IDC Internet Data Center SC Service Center HIN Health Information Network NHI VPN Virtual Private Network, 【1-1】个人健康照护信息整合云端服务 执行单位 医学信息学会,卫生健康云规划, 【3-1】远距健康照护服务计划 执行单位 卫生署照护处、工研院, 【2-1】诊所病历云端备份服务 执行单位 卫生署医事处、工研院,数据源：资策会-创研所整理, 2010,1-1 个人健康照护信息整合云端服务 2-1 诊所病历云端
5、代管及备份服务 2-2 署立医院医疗照护云端服务 3-1 远距健康照护服务计划 4-1 健康数据加值中心网络化服务, 【2-2】署立医院医疗照护云端服务计划 执行单位 卫生署医管会、署立医院、资策会,【4-1】健康数据加值中心网络化服务 执行单位 卫生署统计室、资策会,Medical services,Rehabilitation &Follow-up services,Healthcare services,from Dr. Hsu, Min-Huei , DOH, Taiwan,Big Data and Information,Innovation, Social Networking W
6、ellness, travel, sport, dietary,Value of service mode, Need more evidence, Insurance,7,HCA Card医事人员卡及医保卡,RSA Card issues from HCA to health professionals,non-RSA Health insurance IC Card for all citizens,8,Establishing EMR in Taiwan,Vision: At any hospital, a patient can get his/her integrated medic
7、al records using the health insurance IC card under the agreement and authorization of the patient. Goal: By 2012, 80% hospitals(400, no clinics) DICOM and report, Test reports, and medications, 60% hospitals can exchange EMRs。 By 2014-(2016) complete EMR and exchange for all hospitals,9,Medical Inf
8、ormation Exchange Center MIEC 2000,10,Hospital Information System,Laboratory Information Systems,TMT mini-server,个人化健康信息整合架构 TMT File Exchange Pathway,Hospital Information System,Paperless server,TMT mini-server,Laboratory Information Systems,1,2,3,TMT viewer,Pre-Authorized,4,Internet Health and Lif
9、e Supporting Data Bank,EMR Exchange Center,National EEC Center,EMR providing Hospitals,EMR Reading Hospitals,Download, Querying, and Reading,12,Ministry of Health Image Exchange Center,Health Insurance Center,Hospital A,Hospital B,Index Server,CPOE,CPOE,Download image,Download image,Radiology,Radiol
10、ogy,Image Report Database,Image Report Database,eSignature,Dual Card system and inform consent,Dual Card system and inform consent,Request for image,Request for image,134 hospitals, 2010-2011 upload index 2,168,063 request: 6,592 download: 81,108,Lets ask google about “big data”,What Is Big Data?,Hi
11、gh-volume (大量) High-variety (多种类) High-velocity (快速) sources such as online personal activity, commercial transactions, and sensor networks Relating to health is a component of a growing field. e.g., e-health, m-health, digital health, health information technology, health 2.0, e-medicine, etc. Nils
12、en W, et al. J Health Commun, 2012. Laney D. META Group, 2001. Kumar S, et al. Computer, 2012,Bio-Medical and Health Informatics needs Analytics,医院信息系统快速的发展,各类数具快速大量的累积,需要分析数据来改善健康照护,What is BIG DATA?,Wikipedia: a collection of data sets so large and complex that it becomes difficult to process usin
13、g on-hand database management tools. The challenges include capture, curation, storage, search, sharing, analysis, and visualization. The trend to larger data sets is due to the additional information derivable from analysis of a single large set of related data, as compared to separate smaller sets
14、 with the same total amount of data, allowing correlations to be found to “spot business trends, determine quality of research, prevent diseases, link legal citations, combat crime, and determine real-time roadway traffic conditions”.,http:/ about human brain? The Human brains memory storage capacit
15、y compares to something closer to around 2.5 petabytes (or a thousand Terabytes); which hold three million hours of TV shows. You would have to leave the TV running continuously for more than 300 years to use up all that storage.,How Big is BIG DATA?,Database Size,Mb,Gb,Tb,Pb,Eb,Human brain capacity
16、 2. 5 Pb,NIH BTRIS DW 42K patients with 4 billion rows; 1 Tb,Human Genome (compressed) 1Gb,Facebook 100 Pb,NSA? Google?,NCBI Genbank Download 600 Gb,A 42 Tb,Variety of BIG DATA Sizes,Google Map 80 Tb,WikiPedia 10 million articles 50 Gb,Leveraging Big Data to Prevent Disease,Disease prevention requir
17、es two steps. Identify modifiable risk factors for disease e.g., diet, exercise, smoking, alcohol consumption, and environmental pollution. Interventions to improve disease risk factors To help that person achieve these goals.,International Cooperation Example Global Alliance Just announced: 7 June
18、2013 70 organisations joining to promote sharing and standardisation of genomic data,A Global Alliance for sharing genomic and clinical data A White Paper circulated in early 2013 has the support of nearly 70 organisations in Asia, Australia, Africa, Europe, North America and South America who are c
19、ommitted to creating a common framework that supports data analysis and protects the autonomy and privacy of participating individuals. http:/www.ebi.ac.uk/about/news/press-releases/Global-Alliance,Integrated Biomedical Informatics for Clinical Research 医学研究之道，就是整合研究数据,2003年9月30日，美国国家卫生研究院（NIH）院长塞乌尼
20、（Elias Zerhouni）宣布：对美国政府资助的医学研究进行重整。 研究路线图的计划 NIH Roadmap National Electronics Clinical Trials and Research (NECTAR) network 建立完整的路线图以及彻底更新医学数据的收集、储存及共享 methods for collecting, storage, and sharing 把庞大且分散的数据库结合成一个巨大的数据库 integrating data bases 发展软件，使实验计划的撰写能够简化并标准化 developing software for helping exp
21、eriment design and common data element 减少纸张的使用 reducing paper use, needs a re-usable, extensible, sharable and interoperable informatics infrastructure to enable and streamline collaboration and data sharing for translational research,Starts with “Quality Datasets”,BIG DATA in Biomedical Research,Ya
22、ng C. Fann, Ph.D. 2014 NIH/USA,Databanks related to health,Health-related Databanks,24,Use of cloud technology to provide health information value-added services加值應用,BUILDING A CLOUD-BASED CLINICAL DATA REPOSITORY (CDR),Bio-medical and Healthcare Data are BIG Data = EMR data + genomic data,New Techn
23、ology Triggers The Nexus of IT Forces: Social, Mobile, Cloud & Big Data/Information,Source: Gartner, 2013,Facebook can predict your breakups,5/9/2019,2011 Healthcare Information and Management Systems Society,27,Eating Habits,Stop counting calories start eating better https:/ Data Data Center,Local
24、Health Bureau,Bureau of Health Promotion,NHI,DOH,CDC,NHRI,MOI,NHIRDB in Taiwan,NHIRDB (National Health Insurance Research Database) 12 years of de-identified claim database for 23 million people Cohort DB (Five 1-million people groups for 13 years) Disease-specific DB (16 disease groups) Random samp
25、le DB (outpatient 1/500, inpatient 1/20) generates 100 research papers a year,健康加值数据的价值,Secondary Use(加值应用或二次运用)去识别化之健康资料为世界趋势 美国早已在20年前开放全国住院数据供研究者使用 新的治疗方式、疾病的诊断、药物之副作用、疾病之关联性等 若没有完整开放健康加值资料将严重损害广大病人之权益,From Prof. Jack Li,健康数据加值应用思维 健康与社会关联,社会结构 (Social structure),物质环境 (Material factors),劳动环境 (Wor
26、k),心理环境 (Psychological),社会环境 (Social environment),健康行为 (Health behaviors),生理病态的变化 (Pathophysiological changes) 器官损害 (Organ impairment),健康 (Well-being) 罹病 (Morbidity) 死亡 (Mortality),脑 (Brain) 神经内分泌 与免疫系统 的反应 (Neuroendocrine and immune response),幼儿期环境 (Early life),遗传因素 (Genes),文化因素 (Culture),数据源(Sourc
27、e)：Social determinants of health,2006,33,Cross-databank analysis,Databank A downloading Encryption of individual data,Databank B downloading Encryption of individual data,Generating processed collective results,Abolish the downloaded database, only collective results can be taken out from isolated a
28、rea,Algorithm of Cross-databank Analysis With Physical Isolation,35,健康数据加值应用,世代追踪应用,From 卫生署统计室,健康数据加值应用,健康与社会的关联 社会经济、劳动条件、 幼儿期、遗传、文化等 对健康的影响,卫生政策的评估 医疗、保健、防疫、 全民健保政策实施成效 的衡量、评估与建议,数据整合应用,36,From 卫生署统计室,Examples of value-added application,Cohort Study for Hemodialysis,38,Source: Translated from Hua
29、ng SM,Suicide vs. Psychotropic Medication,39,Medical visit in same year: 83.2%,No medical visit in same year: 16.8%,Psychiatric visit 38.3%,Non-psychiatric visit 44.9%,No 1.3%,Yes 17.6%,Never psychiatric medication: 1.3%,Suicide no. (2002-2005): 10,945,Psychotropic Drugs, yes: 37.0%,Ever psychiatric
30、 medication: 35.7%,No 27.4%,Source: Translated from Huang SM,20 80 Rule?,Gini coefficient Y2008 = 0.711 Y2003 = 0.696,23% patients account for 80% expense,*X-axis shows cumulated medical expenditure, Y-axis shows cumulated patient number (both by % of total) Source: Translated from Huang SM,41,集成健康加
31、值应用中心 Application of Health Databanks,Phase 1,Phase 2,Distant User,台北醫學大學健康暨臨床研究資料加值中心平面圖與現況圖Taipei Medical University,42,左側隔間使用者坐位8個，2名管理人員坐位(左邊隔間左下角以及右邊隔間左下角),Health Insurance DB,Cause of Death DB,Cancer Register DB,Household (census) Register DB,Integrated Data Center for Bio-medical Informatics,
32、Public Health Administration,Epidemiology,Health Care Management,Others, ,Limited Data Set,Continuity Research,Tool Kits,User,主動式具有分析評估能力的主題式資料架構 2010 Data Architecture by Subjects with Active Analysis and Assessment,Regular Data Released,Provide Data,Redundant / Feedback,未通過專法，本中心不直接釋出資料,De-identif
33、ication,Data Released after IRB approval,資料庫,生統報表資料集: 報表資料/ 彙整資料集,臨床研究資料集: 線上即時分析報表,次級資料/ 資料超市,連結 資料庫,ETL 工具,資料查詢與維護,行政院衛生署統計室,糖尿病確診後罹患為肝癌之預測模型- 預測表現,糖尿病確診後罹患為肝癌之預測模型 應用系統,CLOUD COMPUTING FOR PERSONALIZED HEALTH CARE Achieving Meaningful Use of EMR/PHR,Meaningful Use of Health/Medical Information -
34、4P Medicine,Personalization Participation Prediction Prevention More Ps Healthcare Promotion Precision medicine Payment system,Dr. Leroy E. Hood,49,A Definition of Personalized Medicine,Personalized medicine is the use of information from a patients Phenotype/genotype to: initiate a preventative mea
35、sure against the development of a disease or condition, or select the most appropriate therapy for a disease or condition that is particularly suited to that patient.,Definition paraphrased from www.wikipedia.org Other sources: Jones, D. Nature Reviews Drug Discovery 2007; 6:770-771; Katsanis et al.
36、 Science 2008; 320(5872):53-54; Feero et al. JAMA 2008; 299(11):1351-1352,健康照護雲端運算服務-A Personalized Wellness Ecosystem on Cloud,50,個人健康管理議題是全球健康醫療關注的焦點 Pervasive Personal Health Management Service Context aware health monitoring健康監測 Personal Health-aware devices個人裝置 Intelligent alert management智慧管理
37、Pervasive lifestyle incentive management生活方式 Pervasive access to healthcare information健康資訊 Preventive Care & Chronic Disease Mgmt疾病管理 Social Health Promotion社會健康,Source：Pervasive Healthcare as a Scientific Discipline, Methods Inf Med 2008.,The importance of this project Build infrastructure so that
38、 citizens own their health record and receive basic health care services at the right time and right place Fee for illness Fee for health Benefit Reduce the waste in medical resources Improve healthcare quality Promote the health for all citizens,Meaningful Use of EMR,51,Business Model Focus on heal
39、thcare industry,Interventions to improve disease risk factors,To help person achieve these goals. In the past a brief word of advice from ones physician at the annual checkup. e.g., avoid smoking, exercise, and eat healthy foods. Big data offer outside of the clinic in a personalized manner. more so
40、phisticated program would include algorithms that provide personalized feedback to assist with behavior modification at key moments of decision making. e.g., suggesting healthy recipes while the patient is shopping; encouraging exercise at the end of the workday, or giving a personalized warning abo
41、ut location based environmental triggers for asthma,Example 1: Big Data and Physical Activity,Smartphone apps that have the potential to passively and continuously track physical activity. More detail data how physical activity is affected by the social and environmental context. Directly help real-
42、time reminders to increase physical activity before the end of an unusually sedentary day to avoid missing ones daily activity target. linking groups in order to increase motivation. Donaire-Gonzalez D, et al. J Med Internet Res, 2013,Example 2: Big Data and Asthma,Sensor snaps onto asthma metered-d
43、ose inhalers, that passively captures the time, location, and GPS coordinates of inhaler use by communicating with a smartphone. App allows users to provide further contextual information, such as symptoms, perceived triggers, activity at time of use, and whether. Creating a data feedback loop to im
44、prove adherence behavior. Reducing asthma symptoms and improved control. city of Louisville, Kentucky, has adopted this technology to address their elevated asthma burden. Van Sickle D, et al. Resp Drug Delivery Europe, 2013 MacDonald C. The Environmental Magazine, 2012,PERSONALIZED MEDICINE,It is e
45、stimated in 2014, a personal Genome can be sequenced under $1,000 USD 3 billion DNA and 33K genes more than 100K proteins metabolic pathways all the functions of body,From Jack Li, TMU,Cloud computing will quickly change the use of medical information,The fact that Google and Microsoft are heavily i
46、nvested “in the cloud” extends to their new offerings for medical records services, such as Microsofts HealthVault and Google Health. Google 23andMe, 3.9 million USD and more, The integration of biological information, the use of new technology to establish a standardized DNA database, work with pharmaceutical and biotech industry to develop new drugs and personal medicine, Alzheimers foundation, Direct-to-Consumer research: recruit 10,000 patients with Parkinsons disease to enroll. Brins Search for a Parkinsons Cure, Brin proposes a different approach, one d