Artificial intelligence in infection surveillance: Data integration, applications and future directions

Abstract

This narrative review explores the transformative potential of Artificial Intelligence (AI) in addressing the limitations of traditional infection surveillance methods, which are often hindered by slow response times and restricted analytical capabilities. By integrating diverse data sources such as electronic health records, social media, spatiotemporal data, and wearable technologies, AI enables earlier detection of outbreaks, real-time monitoring, and improved disease transmission prediction.

We reviewed peer-reviewed articles and reports to analyze AI's capacity to process heterogeneous datasets using machine learning. Specific applications, such as the use of social media for outbreak prediction, wearable sensors for early infection detection, and spatiotemporal data for tracking disease spread, were synthesized.

AI-driven infection surveillance models improve the prediction of outbreaks and estimation of disease incidence. They also enhance risk assessment by identifying highly susceptible individuals and geographic hotspots, thereby strengthening public health strategies. For instance, integrating social media data improves influenza forecasting accuracy, while wearable technologies enable real-time monitoring of infection dynamics. However, these advancements face challenges such as data privacy concerns, model validation, and the need for external testing across diverse epidemiological settings.

Despite these challenges, AI holds significant promise for revolutionizing infection surveillance. Future efforts should prioritize refining AI models to improve adaptability, ensuring robust validation processes, and developing integrative tools that merge diverse data sources for effective public health interventions.