期刊名称：International Journal of Data Mining & Knowledge Management Process
印刷版ISSN：2231-007X
电子版ISSN：2230-9608
出版年度：2016
卷号：6
期号：5
页码：31
DOI：10.5121/ijdkp.2016.6503
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Developing predictive modelling solutions for risk estimation is extremely challenging in health-careinformatics. Risk estimation involves integration of heterogeneous clinical sources having differentrepresentation from different health-care provider making the task increasingly complex. Such sources aretypically voluminous, diverse, and significantly change over the time. Therefore, distributed and parallelcomputing tools collectively termed big data tools are in need which can synthesize and assist the physicianto make right clinical decisions. In this work we propose multi-model predictive architecture, a novelapproach for combining the predictive ability of multiple models for better prediction accuracy. Wedemonstrate the effectiveness and efficiency of the proposed work on data from Framingham Heart study.Results show that the proposed multi-model predictive architecture is able to provide better accuracy thanbest model approach. By modelling the error of predictive models we are able to choose sub set of modelswhich yields accurate results. More information was modelled into system by multi-level mining which hasresulted in enhanced predictive accuracy.
关键词：Multi model prediction; Framingham data; Hadoop; Clustering and Classification.
