Machine learning prediction of kangaroo mother care in Sierra Leone - a comparative study of feature selection techniques and classification algorithms

Aug 5, 2026

Kangaroo Mother Care (KMC) is a key intervention to improve neonatal outcomes, especially for low-birth-weight infants. This study leverages data from the 2019 Sierra Leone demographic and health survey to identify predictors of KMC practice using multiple feature selection techniques and seven classification algorithms. A total of 7,377 maternal and child health records were analyzed with preprocessing including class balancing, SMOTE, and cross-validation. Results show Random Forest and XGBoost delivering the strongest performance across feature selection methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Article Information

Abstract Overview

Background and Objective

Methods and Data

Results

Conclusion

Osborne, Augustus, Soladoye, Afeez A. , Usani, Kobloobase O. ORCID logoORCID: [https://orcid.org/0009-0009-9668-3128](https://orcid.org/0009-0009-9668-3128) , Adekoya, Ayomide Israel ORCID logoORCID: [https://orcid.org/0009-0006-6275-9030](https://orcid.org/0009-0006-6275-9030) , Wada, Ojima Z. and Olawade, David ORCID logoORCID: [https://orcid.org/0000-0003-](https://orcid.org/0000-0003-)[ ](https://orcid.org/0000-0003-)[0188-9836](0188-9836) (2026) Machine learning prediction of kangaroo mother care in Sierra Leone: a comparative study of feature selection techniques and classification algorithms. International Journal of Medical Informatics, 206. p. 106166. Downloaded from: [https://ray.yorksj.ac.uk/id/eprint/13294/](https://ray.yorksj.ac.uk/id/eprint/13294/) The version presented here may differ from the published version or version of record. If you intend to cite from the work you are advised to consult the publisher's version: [https://doi.org/10.1016/j.ijmedinf.2025.106166](https://doi.org/10.1016/j.ijmedinf.2025.106166) Research at York St John (RaY) is an institutional repository. It supports the principles of open access by making the research outputs of the University available in digital form. Copyright of the items stored in RaY reside with the authors and/or other copyright owners. Users may access full text items free of charge, and may download a copy for private study or non-commercial research. For further reuse terms, see licence terms governing individual outputs. Institutional Repositories Policy Statement RaY Research at the University of York St John For more information please contact RaY at [ray@yorksj.ac. uk](ray@yorksj.ac. uk) International Journal of Medical Informatics 206 (2026) 106166 Contents lists available at ScienceDirect International Journal of Medical Informatics journal [homepage:](homepage: www.elsevier.com/locate/ijmedinf)[ www.elsevier.com/locate/ijmedinf](homepage: www.elsevier.com/locate/ijmedinf) | Machine learning prediction of kangaroo mother care in Sierra Leone: a comparative study of feature selection techniques and
classification algorithms
Augustus Osborne a, Afeez A. Soladoye b,c, Kobloobase O. Usanid ,
Ayomide Israel Adekoya e,f, Ojima Z. Wadag, David B. Olawade h,i,j,k,*
a Institute for Development, Western Area, Freetown, the Republic of Sierra Leone b Department of Computer Engineering, Federal University, Oye-Ekiti, Nigeria c Department of Computer Engineering, Adeleke University, Ede, Nigeria
d Department of Data Science and Artificial Intelligence, School of Business, Computing and Social Sciences, University of Gloucestershire, Cheltenham, United Kingdome Department of Computer Science, Faculty of Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, United Kingdom, f Department of Physiology, Faculty of Basic Medical Sciences, University of Ibadan, Ibadan, Nigeria
g College of Science and Engineering, Division of Sustainable Development, Hamad Bin Khalifa University, Qatar Foundation, Education City, Doha, Qatar h Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London, United Kingdom
i Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham ME7 5NY, United Kingdom j Department of Public Health, York St John University, London, United Kingdom
k School of Health and Care Management, Arden University, Arden House, Middlemarch Park, Coventry CV3 4FJ, United Kingdom | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords:
Kangaroo mother care Machine learning Feature selection Ensemble methods Maternal health | | Background: Kangaroo Mother Care (KMC) is a critical intervention for improving neonatal outcomes, particularly for low-birth-weight infants. Identifying predictors of KMC practice remains essential for targeted health interventions and policy development.
Obje

FAQs

What problem does the study address regarding Kangaroo Mother Care (KMC)?

The study focuses on identifying predictors of KMC practice to support targeted maternal and child health interventions and policy development.

Which dataset and sample size are used to build the prediction models?

The models are trained on 7,377 maternal and child health records from the 2019 Sierra Leone demographic and health survey.

Which feature selection techniques and classification algorithms are compared?

Feature selection techniques include Adaptive Ant Colony Optimization (ACO), Recursive Feature Elimination (RFE), and Backward Feature Selection; classification algorithms include Logistic Regression, SVM variants, K-Nearest Neighbours, Random Forest, XGBoost, stacking ensemble, and voting ensemble.

Aug 5, 2026

Upload by Clementine