Exploring prediction of tick and tick-borne encephalitis cases in Sweden using citizen science data

Tick-borne encephalitis (TBE) remains a severe public health threat in affected areas with shifting geographic distribution linked to environmental change. However, systematic tick surveillance is limited due to the cost and effort of field monitoring. Here, we evaluate the potential of using national citizen science tick data reports for predicting tick-human interaction and TBE risk alongside socioeconomic and environmental data. We integrate citizen science observations with socioeconomic and environmental data, and apply statistical and machine learning models to identify key drivers and assess predictive performance. Among them, XGBoost achieved the highest accuracy for predicting tick report frequency and TBE cases. Rural population size, soil temperature, and vegetation index were key predictors of tick-human interaction, while tick report frequency, soil temperature, and diurnal temperature range were associated with TBE cases. These findings underscore the value of tick citizen science data for enhancing public health surveillance and prevention strategies.