Work

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

Year: 2026
Type: preprint
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.
Source: Figshare
Language: English
Open Access status: green
OpenAlex ID: W7226002754
Cites:
Cited by:
Related to: 10