A Novel Hematological Machine Learning Framework for Predictive Modeling of Dengue Diagnosis Using CBC Parameters in Bangladesh

DOI

10.2991/978-94-6239-664-7_12How to use a DOI?

Keywords

Dengue fever; hematological parameters; machine learning; predictive model; Random Forest; Support Vector Machines; Bangladesh

Abstract

Early diagnosis of dengue fever is critical to patient care and outbreak control, yet reliable clinical indicators are often elusive. Machine learning (ML) offers promise by learning complex patterns in clinical and hematological data. In this study, we first review recent ML-based dengue diagnosis models that use routine clinical or blood parameters. Notably, Support Vector Machines (SVM) and Random Forests (RF) frequently perform best. Key studies include a Brazilian RF model (85% accuracy) for misdiagnosed hospital cases and a Brazilian symptom-based screening model (93% accuracy) using decision trees and neural networks. However, most work focuses on non-Bangladeshi cohorts, with few models addressing explainability. We then apply ML to a new dataset of 1,523 Bangladeshi patients with complete blood count (CBC) and demographic features. We preprocess and encode features (e.g., one-hot gender) and split data into training/test sets. We train logistic regression, RF, and XGBoost models and evaluate accuracy, F1-score, and ROC AUC. Random forest performed best (84.5% accuracy, AUC 69%), outperforming logistic regression (61.2% accuracy), XGBoost (81% accuracy), SVM (81.4%) and neural network (81%). These results highlight the potential of ML for dengue screening in underrepresented populations. The findings underscore gaps in local data, limited feature sets, and the need for interpretable models (e.g., using SHAP/LIME) to support clinicians.

Copyright

© 2026 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)

TY  - CONF
AU  - Md Mehedi Imam Hasan
AU  - Ahasan Habib
AU  - Sawhardo Biswas Sikto
AU  - Md. Mortuza Ahmmed
PY  - 2026
DA  - 2026/06/08
TI  - A Novel Hematological Machine Learning Framework for Predictive Modeling of Dengue Diagnosis Using CBC Parameters in Bangladesh
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 147
EP  - 162
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_12
DO  - 10.2991/978-94-6239-664-7_12
ID  - Hasan2026
ER  -