A Data Analytics Suite for Exploratory Predictive, and Visual Analysis of Type 2 Diabetes
Keywords:
Extensive data for medical care, data analysis, individualized treatment, medical data representation, forecasting analytics, risk assessment, type 2 diabetesAbstract
The availability of large volumes of electronic records of T2D patient data provides opportunities for application of big data analysis to gain insight into the disease manifestation and its impact on patients. Data science in healthcare has the potential to identify hidden knowledge from the database, re-confirm existing knowledge, and aid in personalising treatment. In this paper, we present a suite of data analytics for T2D disease management that allows clinicians and researchers to identify associations between different patient biological markers and T2D related complications. The analytics suite consists of exploratory, predictive, and visual analytics with capabilities including multi-tier classification of T2D patient profiles that associate them to specific conditions, T2Drelated complication risk prediction, and prediction of patient response to a particular line of treatment.The analyses provided in this document examine sophisticated data evaluation methods, which are possible resources for clinical and decision-making processes that may enhance the management of T2D.
Downloads
Metrics
References
D.Soudris,S.Xydis,C.Baloukas,A.Hadzidimitriou,I.Chouvarda,
K. Stamatopoulos, N. Maglaveras, J. Chang, A. Raptopoulos, D. Manset,and B. Pierscionek, ‘‘AEGLE: A big bio-data analytics framework forintegrated health-care services,’’ in Proc. Int. Conf. Embedded Comput.Syst., Archit., Modeling, Simulation (SAMOS), Jul. 2015, pp. 246–253.
N. Holman, B. Young, and R.Gadsby, ‘‘Currentprevalence oftype 1 andtype2diabetesinadultsandchildrenintheU.K.,’’DiabeticMed.,vol.32,no. 9, pp. 1119–1120, Sep. 2015.
NumberofPeopleWithDiabetesReaches4.7Million.Accessed:Oct. 30, 2019. [Online]. Available: https://www.diabetes.org.U.K./about_us/news/new-stats-People-livingwith-diabetes
C.D.MathersandD.Loncar,‘‘Projectionsofglobalmortalityandburdenofdiseasefrom2002to2030,’’PLoSMed.,vol.3,no.11,p.e442,Nov.2006.
AmericanDiabetesAssociation,‘‘Economiccostsofdiabetesinthe U.S. in 2017,’’ Diabetes Care, vol. 41, no. 5, pp. 917–928, 2018, doi:10.2337/dci18-0007.
J.M.M.Rumbold,M.O’Kane,N.Philip,andB.K.Pierscionek,‘‘Bigdataanddiabetes:Theapplicationsofbigdatafordiabetescarenowandinthefuture,’’ Diabetic Med., vol. 37, no. 2, pp. 187–193, Feb. 2020.
J. Hippisley-Cox and C. Coupland, ‘‘Development and validation of riskprediction equations to estimate future risk of blindness and lower limbamputationinpatientswithdiabetes:Cohortstudy,’’ BMJ,vol.351,no.1,Nov. 2015, Art. no. h5441.CI.Marzona,F.Avanzini,G.Lucisano,M.Tettamanti,M.Baviera,
A. Nicolucci, and M. C. Roncaglioni, ‘‘Are all people with diabetes andcardiovascular risk factors or microvascular complications at very highrisk? Findings from the risk and prevention study,’’ Acta Diabetolog.,vol. 54, no. 2, pp. 123–131, Feb. 2017.
S.Basu,J.B.Sussman,S.A.Berkowitz,R.A.Hayward,andJ.S.Yudkin,‘‘Developmentandvalidationofriskequationsforcomplicationsoftype2diabetes(RECODe)usingindividualparticipantdatafromrandomisedtri-als,’’LancetDiabetesEndocrinol.,vol.5,no.10,pp.788–798,Oct.2017.
E. B. Schroeder, S. Xu, G. K. Goodrich, G. A. Nichols, P. J. O’Connor,and J. F. Steiner, ‘‘Predicting the 6-month risk of severe hypoglycemiaamongadultswithdiabetes:Developmentandexternalvalidationofapre-dictionmodel,’’J.DiabetesComplications,vol.31,no.7,pp.1158–1163,Jul.2017.
N. Barakat, A. P. Bradley, and M. N. H. Barakat, ‘‘Intelligible supportvector machines for diagnosis of diabetes mellitus,’’ IEEE Trans. Inf.Technol. Biomed., vol. 14, no. 4, pp. 1114–1120, Jul. 2010.
B. Liu, Y. Li, S. Ghosh, Z. Sun, K. Ng, and J. Hu, ‘‘Complication riskprofiling in diabetes care: A Bayesian multi-task and feature relation-ship learning approach,’’ IEEE Trans. Knowl. Data Eng., vol. 32, no. 7, pp.1276–1289,Jul.2020.
A.PavateandN.Ansari,‘‘Riskpredictionofdiseasecomplicationsintype2diabetes patientsusingsoft computingtechniques,’’ in Proc.5th Int. Conf.Adv. Comput. Commun. (ICACC), Sep. 2015, pp. 371–375.
J.Yan,X.Du,Y.Yu,andH.Xu,‘‘Establishmentofriskpredictionmodelfor retinopathyin type 2diabeticpatients,’’ in Proc. Int.Conf. Brain Inform.Haikou, China: Springer, 2019, pp. 233–243.
A.Dagliati,S.Marini,L.Sacchi,G.Cogni,M.Teliti,V.Tibollo,P.D.Cata, L. Chiovato, and R. Bellazzi, ‘‘Machine learning methods to predict dia-betes complications,’’ J. DiabetesSci. Technol., vol. 12, no.2,pp.295–302,Mar.2018.
K. V. Dalakleidi, K. Zarkogianni, V. G. Karamanos, A. C. Thanopoulou,and K. S. Nikita, ‘‘A hybrid genetic algorithm for the selection of thecritical features for risk prediction of cardiovascularcomplicationsintype 2 diabetes patients,’’ in Proc. 13th IEEE Int. Conf. Bioinf. BioEng.,Nov. 2013, pp. 1–4.
R. GargeyaandT.Leng,‘‘Automatedidentificationofdiabeticretinopathyusingdeeplearning,’’Ophthalmology, vol. 124,no.7,pp.962–969,2017.
M.-H.Hsieh,L.-M.Sun,C.-L. Lin,M.-J.Hsieh,K.Sun,C.-Y.Hsu,sA.-K. Chou, and C.-H. Kao, ‘‘Development of a prediction model forcolorectalcanceramongpatientswithtype2diabetesmellitususingadeepneural network,’’ J. Clin. Med., vol. 7, no. 9, p. 277, Sep. 2018.
Y.Cheng,F.Wang,P. Zhang,andJ.Hu,‘‘Riskpredictionwithelectronichealthrecords: Adeeplearningapproach,’’in Proc.SIAMInt.Conf.DataMining, Jun. 2016, pp. 432–440.
D.Masouros,K.Koliogeorgi,G.Zervakis,A.Kosvyra,A.Chytas, S. Xydis, I. Chouvarda, and D. Soudris, ‘‘Co-design implications of cost-effective on-demand acceleration for cloud healthcare analytics: TheAEGLE approach,’’ in Proc. Design, Autom. Test Eur. Conf. Exhib.(DATE), Mar. 2019, pp. 622–625.
M. Richmond, Population Pyramids. Corvallis, OR, USA: Oregon StateUniv.,2014.
rChartsbyRamnathVaidyanathan.Accessed:Oct.25,2019.[Online]. Available:https://ramnathv.github.io/rCharts
Highcharts. Accessed: Oct. 25, 2019. [Online]. Available: https://www.highcharts.com/demo/bar-negative-stack.
...
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
