An Explainable Agentic Artificial Intelligence Framework for Early Prediction and Decision Support in Infectious Disease Outbreaks: A Case Study of Lassa Fever in Ebonyi State, Nigeria
IOSR Journal of Mobile Computing & Application · 2026-05 · 13 (5) · 01-11
DOI: 10.9790/0050-13050111 ↗Kurz gefasst
Fachartikel in der Zeitschrift IOSR Journal of Mobile Computing & Application, 2026-05. Verfasst von Jeremiah und 7 weiteren Autor:innen.
Abstract (Originalsprache)
Lassa fever remains a significant public health challenge in Nigeria and other West African countries, with recurrent outbreaks requiring timely surveillance, early detection, and rapid intervention. Conventional surveillance approaches are often dependent on passive reporting and laboratory confirmation, which may limit the ability of health authorities to identify emerging outbreaks at an early stage. Recent advances in artificial intelligence (AI), machine learning (ML), and deep learning have created opportunities for infectious disease prediction through the analysis of epidemiological, environmental, climatic, demographic, and geospatial data. However, many existing AI-based approaches focus primarily on predictive accuracy and provide limited explanation of the factors responsible for model predictions. Furthermore, existing predictive systems generally operate as standalone models rather than autonomous, coordinated systems capable of integrating heterogeneous information, reasoning over evidence, explaining predictions, and supporting public health decision-making. This paper proposes an Explainable Agentic Artificial Intelligence (EAAI) framework for early prediction and decision support in Lassa fever outbreaks in Ebonyi State, Nigeria. The proposed framework integrates specialized AI agents for epidemiological surveillance, environmental analysis, climate assessment, geospatial intelligence, predictive modeling, evidence retrieval, explainability, and decision support. The framework is designed to combine heterogeneous spatio-temporal data and generate localized outbreak-risk predictions accompanied by interpretable and evidence-grounded explanations. The proposed research is expected to contribute a novel architecture for trustworthy and human-centered AI-driven infectious disease surveillance. The study argues that the integration of agentic AI and explainable AI may provide a more transparent, adaptive, and actionable approach to infectious disease early warning and public health decision support.
Zitieren
APA
Jeremiah, Chukwu, Igwe, Agbo, S., Nworu, Amaka, U., Ugwu, & Evo, G. (2026). An Explainable Agentic Artificial Intelligence Framework for Early Prediction and Decision Support in Infectious Disease Outbreaks: A Case Study of Lassa Fever in Ebonyi State, Nigeria. IOSR Journal of Mobile Computing & Application, 13(5), 01-11. https://doi.org/10.9790/0050-13050111
Vancouver
Jeremiah, Chukwu, Igwe, Agbo S, Nworu, Amaka U, et al. An Explainable Agentic Artificial Intelligence Framework for Early Prediction and Decision Support in Infectious Disease Outbreaks: A Case Study of Lassa Fever in Ebonyi State, Nigeria. IOSR Journal of Mobile Computing & Application. 2026;13(5):01-11. doi:10.9790/0050-13050111
BibTeX
@article{Jeremiah2026,
author = {Jeremiah and Chukwu and Igwe and Agbo, Sylvester and Nworu and Amaka, Ursula and Ugwu and Evo, Gabriel},
title = {An Explainable Agentic Artificial Intelligence Framework for Early Prediction and Decision Support in Infectious Disease Outbreaks: A Case Study of Lassa Fever in Ebonyi State, Nigeria},
journal = {IOSR Journal of Mobile Computing & Application},
year = {2026},
volume = {13},
number = {5},
pages = {01--11},
doi = {10.9790/0050-13050111}
}
EUVIMED