Machine Learning Applications in One Health: Linking Animal Environment, Human Health, and Ecosystem Sustainability

Abstract

The One Health approach emphasizes the interconnection between human health, animal health, and environmental sustainability, requiring integrated solutions to address emerging global health challenges. Advances in Machine Learning (ML) provide significant opportunities to analyze heterogeneous data collected from healthcare systems, veterinary services, environmental monitoring platforms, remote sensing technologies, and Internet of Things (IoT) devices. This paper proposes a Machine Learning-Based One Health Framework that integrates multisource data to support disease prediction, environmental monitoring, ecosystem sustainability assessment, and intelligent decision-making. The framework consists of data acquisition, preprocessing, feature engineering, machine learning modeling, and decision support modules that collectively enable comprehensive health analysis across interconnected domains. Multiple machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM), were evaluated using an integrated One Health dataset. Experimental results demonstrate that the LSTM model achieved the highest prediction accuracy of 98.12%, outperforming other machine learning techniques while maintaining robust performance across human, animal, and environmental health datasets. The proposed framework facilitates early disease surveillance, livestock health monitoring, environmental risk assessment, and sustainable ecosystem management. Overall, the study demonstrates the effectiveness of machine learning in implementing the One Health paradigm and provides a scalable intelligent framework for supporting public health, biodiversity conservation, and evidence-based sustainable development.