Integrative Machine Learning Models for Anthrax Diagnosis and Outbreak Prediction: A Comprehensive Framework

K. Lekha, M. Yuvaraju

2025

Abstract

Due to its high mortality rate and potential use as a biological weapon, anthrax is a major public health concern. The disease, which is caused by Bacillus anthracis, can kill if not treated rapidly, especially in an inhalational form. Moreover, the Hardy nature of anthrax spores and their suitability for intentional spread render it a serious bioterrorism threat. Timely and accurate diagnosis, as well as predictive analytics for epidemic forecasting, are couple essential to better health outcomes and resource allocation. Machine learning is becoming more frequently utilized to solve complex problems such as diagnosing anthrax, drawing upon genomic or other molecular data, clinical or imaging data or environmental exposure data. By incorporating meteorological and ecological factors to predict environmental conditions conducive to outbreaks, this technique provides more than routine diagnostics. From the above results, the diagnostic accuracy of XGBoost is better than other models (82%). The results show the transformational potential of ML for the diagnosis and control of anthrax epidemics.

Paper Citation

in Harvard Style

Lekha K. and Yuvaraju M. (2025). Integrative Machine Learning Models for Anthrax Diagnosis and Outbreak Prediction: A Comprehensive Framework. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 360-368. DOI: 10.5220/0013883000004919

in Bibtex Style

@conference{icrdicct`2525,
author={K. Lekha and M. Yuvaraju},
title={Integrative Machine Learning Models for Anthrax Diagnosis and Outbreak Prediction: A Comprehensive Framework},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={360-368},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013883000004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Integrative Machine Learning Models for Anthrax Diagnosis and Outbreak Prediction: A Comprehensive Framework
SN - 978-989-758-777-1
AU - Lekha K.
AU - Yuvaraju M.
PY - 2025
SP - 360
EP - 368
DO - 10.5220/0013883000004919
PB - SciTePress