《advanced big data analytics for -omic data and electronic health records_ toward precision medicine.[][ieee trans biomed eng][10.1109_tbme..25》由会员分享,可在线阅读,更多相关《advanced big data analytics for -omic data and electronic health records_ toward precision medicine.[][ieee trans biomed eng][10.1109_tbme..25(11页珍藏版)》请在金锄头文库上搜索。
1、IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 64, NO. 2, FEBRUARY 2017263Omic and Electronic Health Record Big DataAnalytics for Precision MedicinePo-Yen Wu, Member, IEEE, Chih-Wen Cheng, Member, IEEE, Chanchala D. Kaddi, Member, IEEE,Janani Venugopalan, Member, IEEE, Ryan Hoffman, Member, IEEE,
2、and May D. Wang, Senior Member, IEEE(Review Paper)AbstractObjective: Rapid advances of high-throughputtechnologiesandwideadoptionofelectronichealthrecords(EHRs) have led to fast accumulation of omic and EHRdata. These voluminous complex data contain abundant in-formation for precision medicine, and
3、big data analytics canextractsuchknowledgetoimprovethequalityofhealthcare.Methods: In this paper, we present omic and EHR datacharacteristics, associated challenges, and data analyticsincluding data preprocessing, mining, and modeling. Re-sults: To demonstrate how big data analytics enables preci-si
4、on medicine, we provide two case studies, including iden-tifying disease biomarkers from multi-omic data and incor-porating omic information into EHR. Conclusion: Big dataanalytics is able to address omic and EHR data challengesfor paradigm shift toward precision medicine. Significance:Big data anal
5、ytics makes sense of omic and EHR data toimprove healthcare outcome. It has long lasting societal im-pact.Index TermsBig data analytics, bioinformatics, elec-tronic health records (EHRs), health informatics, omicdata, precision medicine.I. INTRODUCTIONTO ACHIEVE the best care for patients, many mode
6、ls havebeen proposed over the years to improve the healthcareManuscript received September 20, 2015; revised January 31, 2016;accepted February 18, 2016. Date of publication October 10, 2016; dateof current version January 18, 2017. This work was supported in partby grants from the National Center f
7、or Advancing Translational Sciencesof the National Institutes of Health (NIH) under Award UL1TR000454and Award NIH R01CA163256, the Georgia Research Alliance CancerCoalition (Distinguished Cancer Scholar Award to Prof. M. D. Wang), theChildrens Healthcare of Atlanta, Centers for Disease Control and
8、Pre-vention, Microsoft Research, and Hewlett-Packard. The content of thisarticle is solely the responsibility of the authors and does not necessarilyrepresent the official views of the NIH. Asterisk indicates correspondingauthor.P.-Y. Wu is with the School of Electrical and Computer Engineering,Geor
9、gia Institute of Technology.C.-W.Cheng,C.D.Kaddi,J.Venugopalan,andR.HoffmanarewiththeDepartment of Biomedical Engineering, Georgia Institute of Technology,and also with Emory University.M. D. Wang is with the Department of Biomedical Engineering,Georgia Institute of Technology, Atlanta, GA 30332, US
10、A, and alsowith Emory University, Atlanta, GA 30322, USA (e-mail: maywangbme.gatech.edu).Digital Object Identifier 10.1109/TBME.2016.2573285Fig. 1.Key types of biomedical big data for precision medicine.system. The goal of the early “personalized medicine” model istocustomizehealthcaredeliveryforeac
11、hindividualandtomax-imize the effectiveness of each patients treatment 1. In 2009,Hood and Friend propose the “personalized, predictive, preven-tive, and participatory medicine” (a.k.a. P4 medicine) modelthat aims to transform current reactive care to future proactivemedicine, and ultimately to redu
12、ce healthcare expenditure andimprove patients health outcome 2. Recently, the new “preci-sion medicine” model is proposed to precisely classify patientsinto subgroups sharing a common biological basis of diseasesformoreeffectivetreatmentandimprovedcareoutcome3,4.Precision medicine requires data util
13、ity ranging from collectionand management (i.e., data storage, sharing, and privacy) toanalytics (i.e., data mining, integration, and visualization) 5.Because of rapid advances in biotechnologies, highly complexbiomedical data are becoming available in huge volumes 6.To make sense of these heterogen
14、eous data, big data analytics,including data quality control, analysis, modeling, interpreta-tion, and validation, is needed to cover application areas suchasbioinformatics79,healthinformatics1012,imaginginformatics 13, 14, and sensor informatics 15, 16.As presented in 2015 U.S. Precision Medicine I
15、nitiative 17,incorporating -omic data and knowledge into electronic healthrecord (EHR) (see Fig. 1) is viewed as a necessary step fordelivering precision medicine 3, 5, 17, 18. Thus, thispaper reviews big omic and EHR data analytics for preci-sion medicine with key terms summarized in Tables I and I
16、I.Section II presents omic and EHR data characteristics, chal-lenges,andbigdataanalytics;SectionIIIusestwocasestudiestoillustrate the impact of big data analytics in precision medicine;Section IV enumerates several well-known biomedical big datainitiatives; Section V discusses current opportunities in big dataanalytics for precision medicine; and finally, Section VI con-cludes this paper.0018-9294 2016 IEEE. Translations and content mining are permitted for academic research only. Personal use i