Investigating climatic and demographic factors as predictors for typhoid-malaria coinfection: a machine learning analysis
Nigeria has a high percentage of burden of both typhoid fever and malaria, with climate change and population dynamics potentially influencing disease co-infection patterns. Emerging evidence suggest that climatic change may have influence in the coinfection dynamics of these diseases. However, a comprehensive epidemiological data on the pattern of coinfection is limited and this invariably affects the evidence-based interventions, the objective of this study is to develop and validate a predictive model that can serve as a framework for the coinfection of malaria and typhoid patterns in Nigeria using the effect of climate change, demographic factors and clinical presentations as contributing variables. An epidemiological informed datasets was generated synthetically using (n=10,000 cases) incorporating a probability distribution prevalence of the disease that were derived from literature on the disease prevalence, symptoms, demographic characteristics across the states in Nigeria. A random forest model classification algorithm was implemented in R programming language environment with the performance metrics evaluated and cross-validated correlation analysis and t-test was also examined to get the relationships between the predictors and the coinfection status. The random forest predictive model achieved an accuracy of 94.47Typhoid test result showed the strongest positive correlation with a co-infection rate of r = 0.533, followed by malaria test results with a co-infection rate of r = 0.361. Temperature as a climatic predictor showed a weak positive correlation of r = 0.040.The analyzed states showed that Borno, Gombe, and Osun have the highest co-infection rates of 65.8%, 65.6%, and 65.5% respectively, this study has developed a framework that serves as a proof-of-concept for the prediction of typhoid-malaria coinfection using machine learning, with diagnostic testing selected as the most reliable predictor, it can be concluded that the validation of the model should be done with clinical data.