Exploratory Data Analysis of Adverse Birth Outcomes and Exposure to Oxides of Nitrogen Using Interactive Parallel Coordinates Plot Technique

Aweke A Mitku,Aweke A Mitku,Rajen N Naidoo,Delia North,Temesgen Zewotir

doi:10.1038/s41598-020-64471-w

Aweke A Mitku, Aweke A Mitku + Show 3 more

Open Access

https://doi.org/10.1038/s41598-020-64471-w

Copy DOI

Journal: Scientific Reports	Publication Date: Apr 30, 2020
Citations: 10	License type: open-access

Affiliation: University of KwaZulu-Natal

Abstract

We propose that a parallel coordinates plot can be used to study multidimensional data particularly to explore discovery of patterns across the variables. This can assist researchers from the health sciences to visualize their cohort data with interactive data analysis. The study used data from Mother and Child in the Environment birth cohort in Durban, South Africa for the period 2013 to 2017 retrospectively registered. In this paper, we demonstrate that the exploration of multidimensional data with parallel coordinates plot and use of brushing using different colours assists with the identification of relationships and patterns. Parallel coordinates plot visualization facilitates the researcher’s skills to find trends, identify outliers and perform quality checks in large multivariate data. We have identified trends in the data that provide directions for further research, and illustrated thereby the potential of parallel coordinates plot to explore patterns and relationships of prenatal oxides of nitrogen exposure with multidimensional birth outcomes. The study recognized the co-occurrence of adverse birth outcomes among infants and these infants had mothers with moderate to high level of NOx exposure during pregnancy. Brushing using different colours facilitated the detection of patterns of relationships to perform basic and advanced statistical model-based analysis.

Highlights

The parallel coordinates plot (PCP) is one of the most recently applied visualizations of multidimensional datasets via a 2D mapping, wherein each dimension is drawn as N parallel axes next to each other and each data item is drawn as a polyline that connects its data values on parallel vertical axes[11]
We are interested in extending the use of PCP as a tool that can be used in health sciences research to provide exploration for multidimensional health research data with easy-to-use graphical user interfaces such as brushing using different colours
The main aim of this study is to extend the use of PCPs with brushing using different colours to explore patterns and trends of annual prenatal oxides of nitrogen (NOx) exposure with multidimensional birth outcomes

Summary

Introduction

The parallel coordinates plot (PCP) is one of the most recently applied visualizations of multidimensional datasets via a 2D mapping, wherein each dimension is drawn as N parallel axes next to each other and each data item is drawn as a polyline that connects its data values on parallel vertical axes[11]. The technique produces a compact two-dimensional representation of N-dimensional data tuple C with coordinates (c1,c2,...,cN) by points (Fig. 1)[12,13] This is an efficient way to place a large number of axes and to visualize the multivariate relations. Researchers have been working on improving this technique for better data investigation and user-friendly interaction by adding data clustering[18], brushing[1,19], etc With these improvements, PCP becomes a very efficient technique for visualization relationships between selected neighbouring dimensions. The main aim of this study is to extend the use of PCPs with brushing using different colours to explore patterns and trends of annual prenatal oxides of nitrogen (NOx) exposure with multidimensional birth outcomes

Objectives

Methods

Results

Discussion

Conclusion