An increase in global migration towards developed countries along with climate change has led to the occurrence of Neglected Tropical Diseases (NTDs) in otherwise non-endemic countries. In this paper we focus on Soil Transmitted Helminth (STH) infections which disproportionately affect people living in poverty in tropical regions. To reduce the threat of STHs in migrant populations living in non-endemic countries, diagnosis and treatment are paramount but also present logistical challenges. This study investigates how statistical modelling can be used to assist the identification of individuals infected with STHs. Specifically, we show how to combine individual variables (e.g., age, sex and time in Italy) with publicly available country indicators (Human Development Index, Multidimensional Poverty Index and Inequality-adjusted Human Development Index) which describe development in the migrant’s country of origin. We combine these indices and their factors in binomial mixed-effects models which can be used to predict the status of STH infections in migrant populations. By presenting a case study on migrants in southern Italy, we assess the relative importance of the individual-level variables and country-level indicators in enhancing the predictive power of the models. The results show that the country-level indices play a more important role but also highlight that individual data can help improve the model performance when combined with the former. To the best of our knowledge this is the first study investigating using country-level indicators to predict parasite infection status of migrants. Our study indicates that statistical models can play an important role in reducing the resources required to identify migrants requiring anthelmintic treatment against STHs and help to make statistically informed decisions.