Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform
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-compl...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Public Library of Science
2016
|
| Online Access: | http://hdl.handle.net/1721.1/101881 |
| _version_ | 1811091308872204288 |
|---|---|
| author | Poucke, Sven Van Zhang, Zhongheng Schmitz, Martin Vukicevic, Milan Laenen, Margot Vander Deyne, Cathy De Celi, Leo Anthony G. |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Poucke, Sven Van Zhang, Zhongheng Schmitz, Martin Vukicevic, Milan Laenen, Margot Vander Deyne, Cathy De Celi, Leo Anthony G. |
| author_sort | Poucke, Sven Van |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T15:00:27Z |
| format | Article |
| id | mit-1721.1/101881 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:00:27Z |
| publishDate | 2016 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | mit-1721.1/1018812022-10-01T23:56:59Z Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform Poucke, Sven Van Zhang, Zhongheng Schmitz, Martin Vukicevic, Milan Laenen, Margot Vander Deyne, Cathy De Celi, Leo Anthony G. Massachusetts Institute of Technology. Institute for Medical Engineering & Science Celi, Leo Anthony G. 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. National Institutes of Health (U.S.) (National Institute for Biomedical Imaging and Bioengineering (U.S.) Grant R01 EB01720501A1) 2016-03-28T15:38:06Z 2016-03-28T15:38:06Z 2016-01 2015-06 Article http://purl.org/eprint/type/JournalArticle 1932-6203 http://hdl.handle.net/1721.1/101881 Poucke, Sven Van, Zhongheng Zhang, Martin Schmitz, Milan Vukicevic, Margot Vander Laenen, Leo Anthony Celi, and Cathy De Deyne. “Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform.” Edited by Tudor Groza. PLoS ONE 11, no. 1 (January 5, 2016): e0145791. en_US http://dx.doi.org/10.1371/journal.pone.0145791 PLOS ONE Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ application/pdf Public Library of Science Nature Publishing Group |
| spellingShingle | Poucke, Sven Van Zhang, Zhongheng Schmitz, Martin Vukicevic, Milan Laenen, Margot Vander Deyne, Cathy De Celi, Leo Anthony G. Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title | Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title_full | Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title_fullStr | Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title_full_unstemmed | Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title_short | Scalable Predictive Analysis in Critically Ill Patients Using a Visual Open Data Analysis Platform |
| title_sort | scalable predictive analysis in critically ill patients using a visual open data analysis platform |
| url | http://hdl.handle.net/1721.1/101881 |
| work_keys_str_mv | AT pouckesvenvan scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT zhangzhongheng scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT schmitzmartin scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT vukicevicmilan scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT laenenmargotvander scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT deynecathyde scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform AT celileoanthonyg scalablepredictiveanalysisincriticallyillpatientsusingavisualopendataanalysisplatform |