Integrating multimodal health datasets with AI-driven epidemiological modeling to accurately forecast infectious disease transmission across populations

Read full text Summarise with VIRAT
Authors: Hassan Ali
Cited by: 0
References: 55

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The accelerating frequency and scale of infectious disease outbreaks underscore the urgent need for more reliable forecasting methods to strengthen global health resilience. Traditional epidemiological models, while valuable, often rely on limited and siloed datasets that fail to capture the multifactorial dynamics of disease transmission. Recent advances in Artificial Intelligence (AI) offer opportunities to overcome these limitations by integrating multimodal health datasets encompassing clinical records, genomic information, behavioral data, environmental exposures, and mobility patterns. This integration expands the analytical depth of epidemiological modeling, enabling more accurate detection of early outbreak signals and enhancing the capacity to predict transmission pathways across diverse populations. AI-driven approaches, including machine learning, deep learning, and hybrid ensemble techniques, provide the computational power to identify complex, non-linear relationships in large-scale health data. By combining multimodal inputs with epidemiological modeling, these systems can account for heterogeneous risk factors such as social determinants of health, co-morbidities, and population density. Beyond forecasting, such integrated frameworks support decision-making in real time, informing public health interventions such as vaccination campaigns, resource allocation, and quarantine strategies. However, challenges remain, particularly in ensuring data interoperability, managing privacy concerns, and addressing algorithmic bias that could reinforce existing inequities in healthcare delivery. This paper proposes a structured framework for integrating multimodal health datasets with AI-driven epidemiological modeling, emphasizing accuracy, equity, and ethical governance. By narrowing the scope from broad health system complexity to targeted AI-enabled modeling, the discussion illustrates how this convergence can revolutionize infectious disease surveillance and ultimately improve global preparedness for future pandemics.

Fields of Study & Subjects

Data-Driven Disease Surveillance Mathematical and Theoretical Epidemiology and Ecology Models Viral Infections and Outbreaks Research

Publication details

Journal / source
Magna Scientia Advanced Biology and Pharmacy
Volume
17
Issue
2
Pages
033–051
Publication date
21 March 2026
Language
EN