Dengue Virus Stage Prediction Using Machine Learning: A Comparative Study of Four Classifiers

This study evaluates and compares four standard machine learning classifiers (Decision Tree, Logistic Regression, Naïve Bayes, and Random Forest) for predicting the clinical severity stage (Mild, Moderate, Acute) of dengue fever based on six binary symptom attributes. Using a dataset of 300 records, the research audits data quality, identifies label-encoding defects caused by stray whitespace, and quantifies dataset duplication that can artificially inflate hold-out scores.Model performance is evaluated using both hold-out and cross-validated protocols, reporting accuracy, weighted-average precision, recall, F1-score, and confusion matrices. Beyond algorithm ranking, this work plainly states what the results do and do not support, highlighting that the models classify severity within suspected dengue patients rather than diagnosing dengue itself. The paper concludes with actionable recommendations for future data collection (e.g., richer clinical variables, multi-site records), robust evaluation methods, and proper deployment pipelines for clinical decision support.

Authors

Publication Details

Journal
Figshare
Published
2026-11-13
DOI
https://doi.org/10.6084/m9.figshare.35002831
Primary Topic
Artificial Intelligence in Healthcare
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Dengue Virus Stage Prediction Using Machine Learning: A Comparative Study of Four Classifiers

Sareena Bilal
2 links
Figshare
Artificial Intelligence in Healthcare
preprint

Dengue Virus Stage Prediction Using Machine Learning: A Comparative Study of Four Classifiers

Sareena Bilal
preprint en

Abstract

This study evaluates and compares four standard machine learning classifiers (Decision Tree, Logistic Regression, Naïve Bayes, and Random Forest) for predicting the clinical severity stage (Mild, Moderate, Acute) of dengue fever based on six binary symptom attributes. Using a dataset of 300 records, the research audits data quality, identifies label-encoding defects caused by stray whitespace, and quantifies dataset duplication that can artificially inflate hold-out scores.Model performance is evaluated using both hold-out and cross-validated protocols, reporting accuracy, weighted-average precision, recall, F1-score, and confusion matrices. Beyond algorithm ranking, this work plainly states what the results do and do not support, highlighting that the models classify severity within suspected dengue patients rather than diagnosing dengue itself. The paper concludes with actionable recommendations for future data collection (e.g., richer clinical variables, multi-site records), robust evaluation methods, and proper deployment pipelines for clinical decision support.

Figshare
Good health and well-being
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon