Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform

• Published in: PloS one Vol. 11; no. 1; p. e0145791
• Main Authors: Poucke, Sven Van, Zhang, Zhongheng, Schmitz, Martin, Vukicevic, Milan, Laenen, Margot Vander, Celi, Leo Anthony, Deyne, Cathy De
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 2016; Public Library of Science (PLoS)
• Subjects: Algorithms; Analytics; Anesthesiology; Artificial intelligence; Big Data; Clinical medicine; Critical care; Critical Care - statistics & numerical data; Critical Illness - therapy; Cybernetics; Data analysis; Data management; Data mining; Data Mining - methods; Data Mining - statistics & numerical data; Data processing; Databases, Factual - statistics & numerical data; Emergency medical care; Exploitation; Fault tolerance; Humans; Information Storage and Retrieval - methods; Information Storage and Retrieval - statistics & numerical data; Intensive care; Intensive Care Units - statistics & numerical data; Medicine; Models, Theoretical; Open data; Optimization; Pain; Patients; Prediction models; Process parameters; Programming Languages; Reproducibility of Results; Subject specialists; Transformation; Belgium; United States > US; Massachusetts
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0145791

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.