Title: Feature analytics of asthma severity levels for bioinformatics improvement using Gini importance

Authors: Temitope Elizabeth Ogunbiyi; Michael Abejide Adegoke; Abe Oluwatobi Adetunji; Joseph Ayodele Ojo

Addresses: Department of Computer Science and Information Technology, Bells University of Technology, Ota, Nigeria ' Department of Computer Science and Information Technology, Bells University of Technology, Ota, Nigeria ' Department of Biological Science, Anchor University, Lagos, Nigeria ' Department of Biological Sciences, Bells University of Technology, Ota, Nigeria

Abstract: In the context of asthma severity prediction, this study delves into the feature importance of various symptoms and demographic attributes. Leveraging a comprehensive dataset encompassing symptom occurrences across varying severity levels, this investigation employs visualisation techniques, such as stacked bar plots, to illustrate the distribution of symptomatology within different severity categories. Additionally, correlation coefficient analysis is applied to quantify the relationships between individual attributes and severity levels. Moreover, the study harnesses the power of random forest and the Gini importance methodology, essential tools in feature importance analytics, to discern the most influential predictors in asthma severity prediction. The experimental results bring to light compelling associations between certain symptoms, notably 'runny-nose' and 'nasal-congestion', and specific severity levels, elucidating their potential significance as pivotal predictive indicators. Conversely, demographic factors, encompassing age groups and gender, exhibit comparatively weaker correlations with symptomatology. These findings underscore the pivotal role of individual symptoms in characterising asthma severity, reinforcing the potential for feature importance analysis to enhance predictive models in the realm of asthma management and bioinformatics.

Keywords: bioinformatics; asthma; severity prediction; feature importance; machine learning.

DOI: 10.1504/IJBRA.2024.142547

International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.6, pp.584 - 607

Received: 18 Dec 2023
Accepted: 01 Apr 2024
Published online: 08 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article