A supervised machine learning statistical design of experiment approach to modeling the barriers to effective snakebite treatment in Ghana - open access research article

Aug 5, 2026

Upload by Miles

Snakebite envenoming is a major public health problem, with millions affected and tens of thousands of deaths annually, especially in tropical and subtropical regions. While global targets aim to cut snakebite-related deaths and disabilities by 2030, limited high-quality evidence—particularly in sub-Saharan Africa—impedes progress. This study combines a MaxDiff statistical experiment design with supervised machine learning to evaluate barriers to effective snakebite treatment in Ghana using hold-out validation and comparative model performance metrics.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Abstract

Background

Method

Results

Conclusion

University of Texas Rio Grande Valley ScholarWorks @ UTRGV | School of Mathematical and Statistical
Sciences Faculty Publications and College of Sciences
Presentations | | --- | | 12-13-2024
A supervised machine learning statistical design of experiment approach to modeling the barriers to effective snakebite treatment in Ghana
Eric Nyarko
Edmund F. Agyemang
The University of Texas Rio Grande Valley, [edmund.agyemang01@utrgv.edu](edmund.agyemang01@utrgv.edu)[ ](edmund.agyemang01@utrgv.edu)Ebenezer Kwesi Ameho
Louis Agyekum
José María Gutiérrez
See next page for additional authors
Follow this and additional works at: [https://scholarworks.utrgv.edu/mss_fac](https://scholarworks.utrgv.edu/mss_fac)
Part of the Mathematics Commons, and the Public Health Commons | Recommended Citation Nyarko, Eric, Edmund Fosu Agyemang, Ebenezer Kwesi Ameho, Louis Agyekum, José María Gutiérrez, and Eduardo Alberto Fernandez. "A supervised machine learning statistical design of experiment approach to modeling the barriers to effective snakebite treatment in Ghana." PLOS Neglected Tropical Diseases 18, no. 12 (2024): e0012736 . [https://doi.org/10.1371/journal.pntd.0012736](https://doi.org/10.1371/journal.pntd.0012736) This Article is brought to you for free and open access by the College of Sciences at ScholarWorks @ UTRGV. It has been accepted for inclusion in School of Mathematical and Statistical Sciences Faculty Publications and Presentations by an authorized administrator of ScholarWorks @ UTRGV. For more information, please contact [william.flores01@utrgv.edu](william.flores01@utrgv.edu). Authors Eric Nyarko, Edmund F. Agyemang, Ebenezer Kwesi Ameho, Louis Agyekum, José María Gutiérrez, and Eduardo Alberto Fernandez This article is available at ScholarWorks @ UTRGV: [https://scholarworks.utrgv.edu/mss_fac/598](https://scholarworks.utrgv.edu/mss_fac/598) RESEARCH ARTICLE A supervised machine learning statistical design of experiment approach to modeling the barriers to effective snakebite treatment in Ghana Eric Nyarko1 *, Edmund Fosu Agyemang1,2, Ebenezer KwesiAmeho1, LouisAgyekum1, Jos´e Mar´ıa Guti´errez3, Eduardo Alberto Fernandez4 1 Department of Statistics and Actuarial Science, College of Basic and Applied Sciences, University of Ghana, Legon, Accra, Ghana, 2 School of Mathematical and Statistical Science, College of Sciences, University of Texas Rio Grande Valley, Edinburg, Texas, United States of America, 3 Instituto Clodomiro Picado, Facultad de Microbiolog´ıa, Universidad de Costa Rica, San Jos´e, Costa Rica, 4 Department of Health Sciences, Brock University, St Catharines, Ontario, Canada * [ericnyarko@ug.edu.gh](ericnyarko@ug.edu.gh) OPEN ACCESS Citation: Nyarko E, Agyemang EF, Ameho EK, Agyekum L, Guti´errez JM, Fernandez EA (2024) A supervised machine learning statistical design of experiment approach to modeling the barriers to effective snakebite treatment in Ghana. PLoS Negl Trop Dis 18(12): e0012736 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pntd.0012736](10.1371/journal.pntd.0012736) Editor: Wuelton Monteiro, Fundaão de Medicina Tropical Doutor Heitor Vieira Dourado: Fundacaode Medicina Tropical Doutor Heitor Vieira Dourado, BRAZIL Received: August 26, 2024 Accepted: November 27, 2024 Published: December 13, 2024 Copyright: © 2024 Nyarko et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data are within the paper and its Supporting Information file. Funding: The author(s) received no specific funding for this work. Competing interests: The authors have declared that no competing interests exist. Abstract Background Snakebite envenoming is a serious condition that affects 2.5 mi

FAQs

What problem does the study address regarding snakebite care in Ghana?

It evaluates barriers that prevent effective snakebite treatment in Ghana, in the context of global goals to reduce deaths and disabilities by 2030.

How were data collected and models trained in this research?

Data were collected using a MaxDiff statistical experiment design, and six supervised machine learning models were trained and validated using a 70% training and 30% hold-back validation split.

Which machine learning model performed best and what barriers were identified?

Across candidate models, the Generalized Regression Model (Ridge) performed consistently better, and the study highlighted barriers such as high antivenom costs, harmful unorthodox practices, limited access in remote areas, and reliance on harmful practices alongside hospital treatment.

Aug 5, 2026

Upload by Miles