We’re excited to share that our latest paper is now published in Computer Methods and Programs in Biomedicine Update: “Including environmental factors into Multiple Sclerosis relapse prediction models: A comparative study.”
In this work, we investigate how environmental factors, such as air pollution, can contribute to predicting relapses in Multiple Sclerosis (MS). We developed a predictive framework combining longitudinal clinical data with environmental information to forecast relapse occurrence one week ahead, using data from 814 individuals.
The framework explores a range of Machine Learning and Deep Learning approaches, different feature selection strategies, and alternative combinations of clinical and environmental features. Among the evaluated configurations, a Random Forest classifier combined with Backward Feature Selection achieved the best performance, with an Area Under the ROC Curve (AUC) of 0.869 (95% CI: 0.833–0.898). Particulate matter (PM10) and nitrogen dioxide (NO2) also emerged as informative predictors in certain settings.
These findings highlight the potential of integrating longitudinal clinical information and environmental exposures to improve MS relapse prediction. We hope this work will contribute to the development of more accurate predictive models and support further research into the relationship between environmental factors and disease activity.
Congratulations to Elena Marinello, Erica Tavazzi, Enrico Longato, Barbara Di Camillo and all other authors!
The paper is available at: https://doi.org/10.1016/j.cmpbup.2026.100272
