Predicting High-Risk Individuals in Disease Outbreaks Using Fuzzy Logic-Based Contact Tracing Model.

Abstract

Abstract Contact tracing plays a crucial role in identifying exposed individuals at high risk of infection during disease outbreaks. In this paper, we propose a fuzzy logic-based contact tracing model for predicting high-risk exposed individuals in disease outbreaks. The model utilizes various input parameters, including distance, overlap time, visiting time lag, incubation time, and facility size, to assess the risk of infection. Through the application of fuzzy logic, the model enables the modeling of complex relationships and uncertainties associated with these input parameters. We evaluated the model using simulated data, demonstrating its effectiveness in identifying individuals at different levels of risk. The evaluation includes partial input evaluation, and comprehensive inputs assessment to assess the impact of each parameter on the risk of infection. The results highlight the importance of considering multiple factors in contact tracing and provide insights into the key parameters that significantly influence the risk assessment. The proposed model has the potential to assist public health authorities in making informed decisions and implementing targeted interventions to mitigate the spread of diseases in outbreak situations. Moreover, it helps to alleviate unnecessary fear among individuals who are less likely to have been infected.