Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/20677

Title: Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform
Authors: Van Poucke, Sven
Zhang, Zhongheng
Schmitz, Martin
Vukicevic, Milan
Vander Laenen, Margot
Celi, Leo Anthony
De Deyne, Cathy
Issue Date: 2016
Citation: PLOS ONE, 11 (1)
Abstract: With the accumulation of large amounts of health related data, predictive analytics could stimulate the transformation of reactive medicine towards Predictive, Preventive and Personalized (PPPM) Medicine, ultimately affecting both cost and quality of care. However, high-dimensionality and high-complexity of the data involved, prevents data-driven methods from easy translation into clinically relevant models. Additionally, the application of cutting edge predictive methods and data manipulation require substantial programming skills, limiting its direct exploitation by medical domain experts. This leaves a gap between potential and actual data usage. In this study, the authors address this problem by focusing on open, visual environments, suited to be applied by the medical community. Moreover, we review code free applications of big data technologies. As a showcase, a framework was developed for the meaningful use of data from critical care patients by integrating the MIMIC-II database in a data mining environment (RapidMiner) supporting scalable predictive analytics using visual tools (RapidMiner's Radoop extension). Guided by the CRoss-Industry Standard Process for Data Mining (CRISP-DM), the ETL process (Extract, Transform, Load) was initiated by retrieving data from the MIMIC-II tables of interest. As use case, correlation of platelet count and ICU survival was quantitatively assessed. Using visual tools for ETL on Hadoop and predictive modeling in RapidMiner, we developed robust processes for automatic building, parameter optimization and evaluation of various predictive models, under different feature selection schemes. Because these processes can be easily adopted in other projects, this environment is attractive for scalable predictive analytics in health research.
Notes: [Van Poucke, Sven; Vander Laenen, Margot; De Deyne, Cathy] Ziekenhuis Oost Limburg, Dept Anesthesiol Intens Care Emergency Med & Pain, Genk, Belgium. [Zhang, Zhongheng] Zhejiang Univ, Jinhua Hosp, Dept Crit Care Med, Hangzhou, Zhejiang, Peoples R China. [Schmitz, Martin] RapidMiner GmbH, Dortmund, Germany. [Vukicevic, Milan] Univ Belgrade, Dept Org Sci, Belgrade, Serbia. [Celi, Leo Anthony] MIT, Inst Med Engn & Sci, Cambridge, MA 02139 USA. [De Deyne, Cathy] Univ Hasselt, Fac Med, Limburg Clin Res Program, Hasselt, Belgium.
URI: http://hdl.handle.net/1942/20677
DOI: 10.1371/journal.pone.0145791
ISI #: 000367801400054
ISSN: 1932-6203
Category: A1
Type: Journal Contribution
Validation: ecoom, 2017
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
published version826.73 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.