Application of spatial multicriteria decision analysis in healthcare: Identifying drivers and triggers of infectious disease outbreaks using ensemble learning

Abstract Modelling infectious diseases is a complex and multi‐disciplinary problem that necessitates the combined use of multicriteria decision analysis (MCDA) machine learning (ML) in spatial framework. This research attempts to demonstrate extensive applications MCDA field public health illustrate its utility with models learning. The study investigates risk factors for communicable focus on vector‐borne diseases, such as West Nile Virus (WNV), malaria, dengue, etc. It aims quantify disease by examining geographic contextual effects socio‐economic, climatic, environmental using objective‐weighting technique adopted from information systems (GIS) authors attempted minimize subjective bias space utilizing an objective‐weighted risk. Shannon's entropy derive weights each factor classes. derived weighted layers are fed artificial neural network obtain final map susceptibility. allows policymakers examine vulnerable areas identify pivotal contribution Findings show traffic volume most influential variable, terrain slope least one spread area. appears be concentrated distributed along vegetation, wetlands, around water bodies. results produced ensemble great promise more than 94% accuracy. accuracy was determined confusion matrix kappa index agreement (KIA). vector control programmes need adapt better manage dynamic changes patterns involving diseases.