A Dominance‐Based Rough Set Approach for an Enhanced Assessment of Seasonal Influenza Risk

Abstract

Accounting for about 290,000–650,000 deaths across the globe, seasonal influenza is estimated by the World Health Organization to be a major cause of mortality. Hence, there is a need for a reliable and robust epidemiological surveillance decision‐making system to understand and combat this epidemic disease. In a previous study, the authors proposed a decision support system to fight against seasonal influenza. This system is composed of three subsystems: (i) modeling and simulation, (ii) data warehousing, and (iii) analysis. The analysis subsystem relies on spatial online analytical processing (S‐OLAP) technology. Although the S‐OLAP technology is useful in analyzing multidimensional spatial data sets, it cannot take into account the inherent multicriteria nature of seasonal influenza risk assessment by itself. Therefore, the objective of this article is to extend the existing decision support system by adding advanced multicriteria analysis capabilities for enhanced seasonal influenza risk assessment and monitoring. Bearing in mind the characteristics of the decision problem considered in this article, a well‐known multicriteria classification method, the dominance‐based rough set approach (DRSA), was selected to boost the existing decision support system. Combining the S‐OLAP technology and the multicriteria classification method DRSA in the same decision support system will largely improve and extend the scope of analysis capabilities. The extended decision support system has been validated by its application to assess seasonal influenza risk in the northwest region of Algeria.

Vulnerability to COVID-19 in Pernambuco, Brazil: A geospatial evaluation supported by multiple-criteria decision aid methodology

“…The advantage of producing vulnerability maps means that places that have been subject to previous pandemics and their risks (UNISDR, 2009;Hazarika et al, 2018) can be identified in addition to a multidimensional comprehension of social, economic, ecological and geographical factors. However, there are many aspects related to the current context (Adger, 2006;Younsi et al, 2020), which led us to construct a decision-learning model to identify areas vulnerable to COVID-19 using, simultaneously, demographic variables associated with the occurrence of the disease, including space characteristics and transmission dynamics.…”

A framework for supporting health capability‐based planning: Identifying and structuring health capabilities

“…On the scientific front, recent research has contributed to improved health capabilities. Initiatives include the development of decision support systems to increase the surveillance of health capability (Younsi et al., 2019; Younsi et al., 2020), the use of portfolio decision analysis to evaluate and improve capabilities of health security systems (Del Rio Vilas et al., 2013), and extensive discussions about the capabilities needed to face priority emerging and reemerging infectious diseases and to strength global health security systems (Ross et al., 2015). Other studies have focused on a specific health capability.…”