One of the challenges vulnerable populations in low-resource and high-density settings face includes the high probability of encountering an infectious disease outbreak because of the inadequate healthcare, overcrowding, and limited access to preventive services in such regions. Most traditional analytics in epidemiology do not address the challenges of modeling disease in these regions and thus fail to analyze the gaps in intervention and public health preparedness. This study focuses on the use of artificial intelligence (AI) based risk modeling systems to address infectious disease spread and public health security among these vulnerable populations. From epidemiology to public health, the response is built on machine learning (supervised, unsupervised, deep learning) algorithms on diverse datasets. These datasets include epidemiological incidences, population density, human mobility, health system, and socioeconomic and environmental factors. The identification of the disease’s transmission location, prediction of the disease, and vulnerability of the health system to the disease model the outbreaks, serving the gaps in public health preparedness. These benefits of AI-based risk modeling assist the decision-making in the optimal allocation of resources such as hospital capacity, the availability of rapid diagnostic tests, and the focus of vaccination.