Proceedings of the Workshop on Computation: Theory and Practice (WCTP 2024)

Machine Learning Classifiers on Predicting the Survival of Pediatric Hematologic Transplant Patients

Authors
Bryan S. Subingsubing1, Danielle Cyrele D. Azarraga1, Marvic Gabriel Ruiz1, Ma Sheila A. Magboo1, Vincent Peter C. Magboo1, *
1University of the Philippines Manila, Manila, Philippines
*Corresponding author. Email: vcmagboo@up.edu.ph
Corresponding Author
Vincent Peter C. Magboo
Available Online 30 April 2025.
DOI
10.2991/978-94-6463-684-0_18How to use a DOI?
Keywords
Pediatric hematologic transplant survivorship; mutual information; SMOTE; hyperparameter tuning
Abstract

Predicting the survival outcomes of pediatric hematologic transplant patients remains to be a formidable task for clinicians. This study aims to assess the capability to predict survival post bone marrow transplantation of machine learning classifiers namely: random forest, decision trees, logistic regression, Naïve Bayes, support vector machine and AdaBoost. Several model configurations representing various methodological enhancements as to feature selection using mutual information, synthetic minority oversampling technique to address class imbalance and hyperparameter tuning were analyzed. The results showed random forest model consistently besting other models in all model configurations generating an accuracy of 97.37%, 93.75% recall, 100% precision, and 96.77% F1-score. The study underscores the importance of these methodological enhancements to further strengthen the predictive performance of machine learning models in pediatric patients post bone marrow transplantation. The results of this research study represent a significant advancement in leveraging machine learning techniques to upgrade the care for pediatric patients with hematologic malignancies.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the Workshop on Computation: Theory and Practice (WCTP 2024)
Series
Atlantis Highlights in Computer Sciences
Publication Date
30 April 2025
ISBN
978-94-6463-684-0
ISSN
2589-4900
DOI
10.2991/978-94-6463-684-0_18How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Bryan S. Subingsubing
AU  - Danielle Cyrele D. Azarraga
AU  - Marvic Gabriel Ruiz
AU  - Ma Sheila A. Magboo
AU  - Vincent Peter C. Magboo
PY  - 2025
DA  - 2025/04/30
TI  - Machine Learning Classifiers on Predicting the Survival of Pediatric Hematologic Transplant Patients
BT  - Proceedings of the  Workshop on Computation: Theory and Practice (WCTP 2024)
PB  - Atlantis Press
SP  - 281
EP  - 296
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-684-0_18
DO  - 10.2991/978-94-6463-684-0_18
ID  - Subingsubing2025
ER  -