Revolutionizing Zoonotic Disease Outbreaks Detection and Prediction with AI: Based on One Health Perspective
Code: G-1757
Authors: Shakiba Mazaheri ℗, Sharareh Siavoshi, Melika Ahmadi, Mohammad Aradzandieh *
Schedule: Not Scheduled!
Tag: Intelligent Virtual Assistant
Download: Download Poster
Abstract:
Abstract
Background and objectives: Zoonotic diseases are responsible for approximately 70% of emerging infections outbreak, which require innovative and precise methods of identifying and predicting them. This study examines the role of artificial intelligence (AI) in managing these diseases through a one-health approach which integrates human, animal, and environmental health. Methods: A comprehensive review of literature was conducted from 2020 to 2024 across PubMed, ScienceDirect, Google Scholar, and IEEE Xplore databases using key terms such "One health","Zoonotic disease", "Disease Surve illanc", "Artificial intelligence" Results: Emerging zoonotic diseases require rigorous analysis and advanced technologies, such as artificial intelligence (AI), the Internet of Things (IoT), remote sensors, and molecular tools, in order to prevent them from spreading and resulting in epidemics or pandemics. Machine learning (ML) improved the accuracy of predicting outbreaks of leptospirosis by 13.3% to 31.26 %, while neural network models improved sensitivity by up to 35.43 %. It has been demonstrated that deep learning was employed to train a deep convolutional neural network that can accurately predict bovine tuberculosis by 70-90%, with sensitivity and specificity increasing by 1.22 and 1.45 times, respectively. In studies on COVID-19, recurrent neural networks (RNNs) and long short-term memory (LSTM) units were shown to possess high accuracy in predicting pandemic curves. A multilayer perceptron (MLP) neural network, analyzing 57 variables, accurately predicted the cumulative incidence of COVID-19 in the United States with a correlation of 65%. Furthermore, studies have demonstrated the value of machine learning in tracing the origin of emerging viruses, including COVID-19, based on genomic data and spike protein sequences. Conclusion: Artificial intelligence has the potential to revolutionize disease diagnosis and management by analyzing immense amounts of data and identifying intricate patterns. The use of machine learning can allow for faster and more accurate diagnoses, thereby reducing antibiotic overuse and assisting with the management of antimicrobial resistance. Furthermore, AI-driven systems can predict and prevent emerging infections. The use of artificial intelligence is ultimately a promising solution for improving health while adhering to One Health principles.
Keywords
One Health, Zoonotic Disease, Disease Surveillance
