Integrating eXplainable AI in Healthcare: A Web Application Framework for Advancing the One Health Paradigm

Danilo Danese, Tommaso Di Noia, Angela Lombardi, Domenico Lofù, Fatemeh Nazary, Rodolfo Sardone, Paolo Sorino

Abstract: In today’s complex world, the intricate connections between human health, socio-economic factors, and environmental conditions necessitate a holistic approach to health challenges. This paper highlights the critical need for the One Health paradigm, emphasizing a comprehensive framework that integrates human, economic, and environmental health considerations. By incorporating Explainable Artificial Intelligence (XAI) principles, this paper showcases a pioneering method to make the sophisticated insights derived from AI more accessible and actionable for a broad range of stakeholders, including healthcare professionals, environmental experts, and policy makers. Within the framework of the MISTRAL H2020 European project, we illustrate a healthcare model that employs XAI to demystify AI algorithms, thereby fostering trust and enhancing understanding among its users. This innovative approach not only improves clinical decision-making but also addresses environmental health issues by rendering the opaque decision-making processes of Machine Learning (ML) models transparent and understandable. The framework’s significance is underlined by its capacity to inform Health Impact Assessments (HIA) and predict disease risks, facilitating precise interventions and informed policy development. Furthermore, we propose a method for engineering and accessing this framework online, allowing users to engage directly with the system.