Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records
Recent advancement in EHR-based (Electronic Health Record) systems has resulted in producing data at an unprecedented rate. The complex, growing, and high-dimensional data available in EHRs creates great opportunities for machine learning techniques such as clustering. Cluster analysis often require...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Informatics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9709/7/2/17 |
id |
doaj-7653556f0f6942f5aef077627c88c3a5 |
---|---|
record_format |
Article |
spelling |
doaj-7653556f0f6942f5aef077627c88c3a52020-11-25T02:54:02ZengMDPI AGInformatics2227-97092020-05-017171710.3390/informatics7020017Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health RecordsSheikh S. Abdullah0Neda Rostamzadeh1Kamran Sedig2Amit X. Garg3Eric McArthur4Insight Lab, Western University, 1151 Richmond Street, London, ON N6A 3K7, CanadaInsight Lab, Western University, 1151 Richmond Street, London, ON N6A 3K7, CanadaInsight Lab, Western University, 1151 Richmond Street, London, ON N6A 3K7, CanadaDepartment of Medicine, Epidemiology and Biostatistics, Western University, 1151 Richmond Street, London, ON N6A 3K7, CanadaICES, London, ON N6A 3K7, CanadaRecent advancement in EHR-based (Electronic Health Record) systems has resulted in producing data at an unprecedented rate. The complex, growing, and high-dimensional data available in EHRs creates great opportunities for machine learning techniques such as clustering. Cluster analysis often requires dimension reduction to achieve efficient processing time and mitigate the curse of dimensionality. Given a wide range of techniques for dimension reduction and cluster analysis, it is not straightforward to identify which combination of techniques from both families leads to the desired result. The ability to derive useful and precise insights from EHRs requires a deeper understanding of the data, intermediary results, configuration parameters, and analysis processes. Although these tasks are often tackled separately in existing studies, we present a visual analytics (VA) system, called Visual Analytics for Cluster Analysis and Dimension Reduction of High Dimensional Electronic Health Records (VALENCIA), to address the challenges of high-dimensional EHRs in a single system. VALENCIA brings a wide range of cluster analysis and dimension reduction techniques, integrate them seamlessly, and make them accessible to users through interactive visualizations. It offers a balanced distribution of processing load between users and the system to facilitate the performance of high-level cognitive tasks in such a way that would be difficult without the aid of a VA system. Through a real case study, we have demonstrated how VALENCIA can be used to analyze the healthcare administrative dataset stored at ICES. This research also highlights what needs to be considered in the future when developing VA systems that are designed to derive deep and novel insights into EHRs.https://www.mdpi.com/2227-9709/7/2/17visual analyticsdimension reductioncluster analysiselectronic health recordshigh-dimensional datainteractive visualization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sheikh S. Abdullah Neda Rostamzadeh Kamran Sedig Amit X. Garg Eric McArthur |
spellingShingle |
Sheikh S. Abdullah Neda Rostamzadeh Kamran Sedig Amit X. Garg Eric McArthur Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records Informatics visual analytics dimension reduction cluster analysis electronic health records high-dimensional data interactive visualization |
author_facet |
Sheikh S. Abdullah Neda Rostamzadeh Kamran Sedig Amit X. Garg Eric McArthur |
author_sort |
Sheikh S. Abdullah |
title |
Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records |
title_short |
Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records |
title_full |
Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records |
title_fullStr |
Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records |
title_full_unstemmed |
Visual Analytics for Dimension Reduction and Cluster Analysis of High Dimensional Electronic Health Records |
title_sort |
visual analytics for dimension reduction and cluster analysis of high dimensional electronic health records |
publisher |
MDPI AG |
series |
Informatics |
issn |
2227-9709 |
publishDate |
2020-05-01 |
description |
Recent advancement in EHR-based (Electronic Health Record) systems has resulted in producing data at an unprecedented rate. The complex, growing, and high-dimensional data available in EHRs creates great opportunities for machine learning techniques such as clustering. Cluster analysis often requires dimension reduction to achieve efficient processing time and mitigate the curse of dimensionality. Given a wide range of techniques for dimension reduction and cluster analysis, it is not straightforward to identify which combination of techniques from both families leads to the desired result. The ability to derive useful and precise insights from EHRs requires a deeper understanding of the data, intermediary results, configuration parameters, and analysis processes. Although these tasks are often tackled separately in existing studies, we present a visual analytics (VA) system, called Visual Analytics for Cluster Analysis and Dimension Reduction of High Dimensional Electronic Health Records (VALENCIA), to address the challenges of high-dimensional EHRs in a single system. VALENCIA brings a wide range of cluster analysis and dimension reduction techniques, integrate them seamlessly, and make them accessible to users through interactive visualizations. It offers a balanced distribution of processing load between users and the system to facilitate the performance of high-level cognitive tasks in such a way that would be difficult without the aid of a VA system. Through a real case study, we have demonstrated how VALENCIA can be used to analyze the healthcare administrative dataset stored at ICES. This research also highlights what needs to be considered in the future when developing VA systems that are designed to derive deep and novel insights into EHRs. |
topic |
visual analytics dimension reduction cluster analysis electronic health records high-dimensional data interactive visualization |
url |
https://www.mdpi.com/2227-9709/7/2/17 |
work_keys_str_mv |
AT sheikhsabdullah visualanalyticsfordimensionreductionandclusteranalysisofhighdimensionalelectronichealthrecords AT nedarostamzadeh visualanalyticsfordimensionreductionandclusteranalysisofhighdimensionalelectronichealthrecords AT kamransedig visualanalyticsfordimensionreductionandclusteranalysisofhighdimensionalelectronichealthrecords AT amitxgarg visualanalyticsfordimensionreductionandclusteranalysisofhighdimensionalelectronichealthrecords AT ericmcarthur visualanalyticsfordimensionreductionandclusteranalysisofhighdimensionalelectronichealthrecords |
_version_ |
1724722951947812864 |