M. Kraemer, J. Tsui, Serina Chang, Spyros Lytras, M. Khurana, S. Vanderslott, S. Bajaj, N. Scheidwasser et al.
A perspective paper comprehensively reviewing the application of AI technologies to infectious disease epidemiology modeling and social considerations.
Infectious disease threats are diverse and unpredictable, and traditional epidemiological modeling has limitations in data processing and prediction. There is a need to leverage AI to improve the accuracy and utility of epidemiological models and effectively analyze real-time surveillance data.
Reviews recent research on applying AI systems (machine learning, computational statistics, information retrieval, data science) to infectious disease modeling. Discusses AI-based solutions to key epidemiological questions, specific AI methods applicable to routine surveillance data, and social contexts such as explainability, safety, accountability, and ethics.
Demonstrates that AI can accelerate breakthroughs in key questions of infectious disease epidemiology. Provides limitations and recommendations for AI applications, guiding future research directions. Offers a comprehensive overview of AI utilization in the field of infectious disease modeling.